diff options
Diffstat (limited to 'arch')
1196 files changed, 22368 insertions, 26805 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 1aa59063f1fd..c6148166a7b4 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -3,6 +3,14 @@ # General architecture dependent options # +# +# Note: arch/$(SRCARCH)/Kconfig needs to be included first so that it can +# override the default values in this file. +# +source "arch/$(SRCARCH)/Kconfig" + +menu "General architecture-dependent options" + config CRASH_CORE bool @@ -13,6 +21,9 @@ config KEXEC_CORE config HAVE_IMA_KEXEC bool +config HOTPLUG_SMT + bool + config OPROFILE tristate "OProfile system profiling" depends on PROFILING @@ -405,150 +416,6 @@ config SECCOMP_FILTER See Documentation/userspace-api/seccomp_filter.rst for details. -preferred-plugin-hostcc := $(if-success,[ $(gcc-version) -ge 40800 ],$(HOSTCXX),$(HOSTCC)) - -config PLUGIN_HOSTCC - string - default "$(shell,$(srctree)/scripts/gcc-plugin.sh "$(preferred-plugin-hostcc)" "$(HOSTCXX)" "$(CC)")" - help - Host compiler used to build GCC plugins. This can be $(HOSTCXX), - $(HOSTCC), or a null string if GCC plugin is unsupported. - -config HAVE_GCC_PLUGINS - bool - help - An arch should select this symbol if it supports building with - GCC plugins. - -menuconfig GCC_PLUGINS - bool "GCC plugins" - depends on HAVE_GCC_PLUGINS - depends on PLUGIN_HOSTCC != "" - help - GCC plugins are loadable modules that provide extra features to the - compiler. They are useful for runtime instrumentation and static analysis. - - See Documentation/gcc-plugins.txt for details. - -config GCC_PLUGIN_CYC_COMPLEXITY - bool "Compute the cyclomatic complexity of a function" if EXPERT - depends on GCC_PLUGINS - depends on !COMPILE_TEST # too noisy - help - The complexity M of a function's control flow graph is defined as: - M = E - N + 2P - where - - E = the number of edges - N = the number of nodes - P = the number of connected components (exit nodes). - - Enabling this plugin reports the complexity to stderr during the - build. It mainly serves as a simple example of how to create a - gcc plugin for the kernel. - -config GCC_PLUGIN_SANCOV - bool - depends on GCC_PLUGINS - help - This plugin inserts a __sanitizer_cov_trace_pc() call at the start of - basic blocks. It supports all gcc versions with plugin support (from - gcc-4.5 on). It is based on the commit "Add fuzzing coverage support" - by Dmitry Vyukov <dvyukov@google.com>. - -config GCC_PLUGIN_LATENT_ENTROPY - bool "Generate some entropy during boot and runtime" - depends on GCC_PLUGINS - help - By saying Y here the kernel will instrument some kernel code to - extract some entropy from both original and artificially created - program state. This will help especially embedded systems where - there is little 'natural' source of entropy normally. The cost - is some slowdown of the boot process (about 0.5%) and fork and - irq processing. - - Note that entropy extracted this way is not cryptographically - secure! - - This plugin was ported from grsecurity/PaX. More information at: - * https://grsecurity.net/ - * https://pax.grsecurity.net/ - -config GCC_PLUGIN_STRUCTLEAK - bool "Force initialization of variables containing userspace addresses" - depends on GCC_PLUGINS - # Currently STRUCTLEAK inserts initialization out of live scope of - # variables from KASAN point of view. This leads to KASAN false - # positive reports. Prohibit this combination for now. - depends on !KASAN_EXTRA - help - This plugin zero-initializes any structures containing a - __user attribute. This can prevent some classes of information - exposures. - - This plugin was ported from grsecurity/PaX. More information at: - * https://grsecurity.net/ - * https://pax.grsecurity.net/ - -config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL - bool "Force initialize all struct type variables passed by reference" - depends on GCC_PLUGIN_STRUCTLEAK - depends on !COMPILE_TEST - help - Zero initialize any struct type local variable that may be passed by - reference without having been initialized. - -config GCC_PLUGIN_STRUCTLEAK_VERBOSE - bool "Report forcefully initialized variables" - depends on GCC_PLUGIN_STRUCTLEAK - depends on !COMPILE_TEST # too noisy - help - This option will cause a warning to be printed each time the - structleak plugin finds a variable it thinks needs to be - initialized. Since not all existing initializers are detected - by the plugin, this can produce false positive warnings. - -config GCC_PLUGIN_RANDSTRUCT - bool "Randomize layout of sensitive kernel structures" - depends on GCC_PLUGINS - select MODVERSIONS if MODULES - help - If you say Y here, the layouts of structures that are entirely - function pointers (and have not been manually annotated with - __no_randomize_layout), or structures that have been explicitly - marked with __randomize_layout, will be randomized at compile-time. - This can introduce the requirement of an additional information - exposure vulnerability for exploits targeting these structure - types. - - Enabling this feature will introduce some performance impact, - slightly increase memory usage, and prevent the use of forensic - tools like Volatility against the system (unless the kernel - source tree isn't cleaned after kernel installation). - - The seed used for compilation is located at - scripts/gcc-plgins/randomize_layout_seed.h. It remains after - a make clean to allow for external modules to be compiled with - the existing seed and will be removed by a make mrproper or - make distclean. - - Note that the implementation requires gcc 4.7 or newer. - - This plugin was ported from grsecurity/PaX. More information at: - * https://grsecurity.net/ - * https://pax.grsecurity.net/ - -config GCC_PLUGIN_RANDSTRUCT_PERFORMANCE - bool "Use cacheline-aware structure randomization" - depends on GCC_PLUGIN_RANDSTRUCT - depends on !COMPILE_TEST # do not reduce test coverage - help - If you say Y here, the RANDSTRUCT randomization will make a - best effort at restricting randomization to cacheline-sized - groups of elements. It will further not randomize bitfields - in structures. This reduces the performance hit of RANDSTRUCT - at the cost of weakened randomization. - config HAVE_STACKPROTECTOR bool help @@ -875,6 +742,9 @@ config COMPAT_32BIT_TIME config ARCH_NO_COHERENT_DMA_MMAP bool +config ARCH_NO_PREEMPT + bool + config CPU_NO_EFFICIENT_FFS def_bool n @@ -972,3 +842,7 @@ config REFCOUNT_FULL security flaw exploits. source "kernel/gcov/Kconfig" + +source "scripts/gcc-plugins/Kconfig" + +endmenu diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 04a4a138ed13..5b4f88363453 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -4,6 +4,7 @@ config ALPHA default y select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO + select ARCH_NO_PREEMPT select ARCH_USE_CMPXCHG_LOCKREF select HAVE_AOUT select HAVE_IDE @@ -74,9 +75,6 @@ config PGTABLE_LEVELS int default 3 -source "init/Kconfig" -source "kernel/Kconfig.freezer" - config AUDIT_ARCH bool @@ -573,8 +571,6 @@ config ARCH_DISCONTIGMEM_ENABLE or have huge holes in the physical address space for other reasons. See <file:Documentation/vm/numa.rst> for more. -source "mm/Kconfig" - config NUMA bool "NUMA Support (EXPERIMENTAL)" depends on DISCONTIGMEM && BROKEN @@ -713,28 +709,11 @@ config SRM_ENV This driver is also available as a module and will be called srm_env then. -source "fs/Kconfig.binfmt" - endmenu -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "arch/alpha/Kconfig.debug" - # DUMMY_CONSOLE may be defined in drivers/video/console/Kconfig # but we also need it if VGA_HOSE is set config DUMMY_CONSOLE bool depends on VGA_HOSE default y - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - diff --git a/arch/alpha/Kconfig.debug b/arch/alpha/Kconfig.debug index 5e93dffb818a..b88c7b641d72 100644 --- a/arch/alpha/Kconfig.debug +++ b/arch/alpha/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config EARLY_PRINTK bool @@ -39,5 +36,3 @@ config MATHEMU This option is required for IEEE compliant floating point arithmetic on the Alpha. The only time you would ever not say Y is to say M in order to debug the code. Say Y unless you know what you are doing. - -endmenu diff --git a/arch/alpha/boot/Makefile b/arch/alpha/boot/Makefile index 0cbe4c59d3ce..991e023a6fc4 100644 --- a/arch/alpha/boot/Makefile +++ b/arch/alpha/boot/Makefile @@ -14,7 +14,7 @@ targets := vmlinux.gz vmlinux \ tools/bootpzh bootloader bootpheader bootpzheader OBJSTRIP := $(obj)/tools/objstrip -HOSTCFLAGS := -Wall -I$(objtree)/usr/include +KBUILD_HOSTCFLAGS := -Wall -I$(objtree)/usr/include BOOTCFLAGS += -I$(objtree)/$(obj) -I$(srctree)/$(obj) # SRM bootable image. Copy to offset 512 of a partition. diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 767bfdd42992..150a1c5d6a2c 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -18,11 +18,11 @@ * To ensure dependency ordering is preserved for the _relaxed and * _release atomics, an smp_read_barrier_depends() is unconditionally * inserted into the _relaxed variants, which are used to build the - * barriered versions. To avoid redundant back-to-back fences, we can - * define the _acquire and _fence versions explicitly. + * barriered versions. Avoid redundant back-to-back fences in the + * _acquire and _fence versions. */ -#define __atomic_op_acquire(op, args...) op##_relaxed(args) -#define __atomic_op_fence __atomic_op_release +#define __atomic_acquire_fence() +#define __atomic_post_full_fence() #define ATOMIC_INIT(i) { (i) } #define ATOMIC64_INIT(i) { (i) } @@ -206,7 +206,7 @@ ATOMIC_OPS(xor, xor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -214,7 +214,7 @@ ATOMIC_OPS(xor, xor) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c, new, old; smp_mb(); @@ -235,38 +235,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) smp_mb(); return old; } - +#define atomic_fetch_add_unless atomic_fetch_add_unless /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as it was not @u. - * Returns true iff @v was not @u. + * Returns the old value of @v. */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) +static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { - long c, tmp; + long c, new, old; smp_mb(); __asm__ __volatile__( - "1: ldq_l %[tmp],%[mem]\n" - " cmpeq %[tmp],%[u],%[c]\n" - " addq %[tmp],%[a],%[tmp]\n" + "1: ldq_l %[old],%[mem]\n" + " cmpeq %[old],%[u],%[c]\n" + " addq %[old],%[a],%[new]\n" " bne %[c],2f\n" - " stq_c %[tmp],%[mem]\n" - " beq %[tmp],3f\n" + " stq_c %[new],%[mem]\n" + " beq %[new],3f\n" "2:\n" ".subsection 2\n" "3: br 1b\n" ".previous" - : [tmp] "=&r"(tmp), [c] "=&r"(c) + : [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c) : [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u) : "memory"); smp_mb(); - return !c; + return old; } +#define atomic64_fetch_add_unless atomic64_fetch_add_unless /* * atomic64_dec_if_positive - decrement by 1 if old value positive @@ -295,31 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) smp_mb(); return old - 1; } - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - -#define atomic_dec_return(v) atomic_sub_return(1,(v)) -#define atomic64_dec_return(v) atomic64_sub_return(1,(v)) - -#define atomic_inc_return(v) atomic_add_return(1,(v)) -#define atomic64_inc_return(v) atomic64_add_return(1,(v)) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) - -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) - -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) - -#define atomic_inc(v) atomic_add(1,(v)) -#define atomic64_inc(v) atomic64_add(1,(v)) - -#define atomic_dec(v) atomic_sub(1,(v)) -#define atomic64_dec(v) atomic64_sub(1,(v)) +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif /* _ALPHA_ATOMIC_H */ diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index be14f16149d5..065fb372e355 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -112,4 +112,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index de2bd217adad..d73dc473fbb9 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -87,7 +87,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr, struct vm_area_struct * vma; struct mm_struct *mm = current->mm; const struct exception_table_entry *fixup; - int fault, si_code = SEGV_MAPERR; + int si_code = SEGV_MAPERR; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* As of EV6, a load into $31/$f31 is a prefetch, and never faults diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 9cf59fc60eab..6d5eb8267e42 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -50,6 +50,9 @@ config ARC select HAVE_KERNEL_LZMA select ARCH_HAS_PTE_SPECIAL +config ARCH_HAS_CACHE_LINE_SIZE + def_bool y + config MIGHT_HAVE_PCI bool @@ -94,9 +97,6 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y depends on ARC_MMU_V4 -source "init/Kconfig" -source "kernel/Kconfig.freezer" - menu "ARC Architecture Configuration" menu "ARC Platform/SoC/Board" @@ -548,24 +548,13 @@ config ARC_BUILTIN_DTB_NAME Set the name of the DTB to embed in the vmlinux binary Leaving it blank selects the minimal "skeleton" dtb -source "kernel/Kconfig.preempt" - -menu "Executable file formats" -source "fs/Kconfig.binfmt" -endmenu - endmenu # "ARC Architecture Configuration" -source "mm/Kconfig" - config FORCE_MAX_ZONEORDER int "Maximum zone order" default "12" if ARC_HUGEPAGE_16M default "11" -source "net/Kconfig" -source "drivers/Kconfig" - menu "Bus Support" config PCI @@ -586,9 +575,4 @@ source "drivers/pci/Kconfig" endmenu -source "fs/Kconfig" -source "arch/arc/Kconfig.debug" -source "security/Kconfig" -source "crypto/Kconfig" -source "lib/Kconfig" source "kernel/power/Kconfig" diff --git a/arch/arc/Kconfig.debug b/arch/arc/Kconfig.debug index 03da1a6b3072..45add86decd5 100644 --- a/arch/arc/Kconfig.debug +++ b/arch/arc/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config 16KSTACKS bool "Use 16Kb for kernel stacks instead of 8Kb" @@ -11,5 +8,3 @@ config 16KSTACKS This increases the resident kernel footprint and will cause less threads to run on the system and also increase the pressure on the VM subsystem for higher order allocations. - -endmenu diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 11859287c52a..4e0072730241 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -187,7 +187,8 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ ATOMIC_OPS(add, +=, add) ATOMIC_OPS(sub, -=, sub) -#define atomic_andnot atomic_andnot +#define atomic_andnot atomic_andnot +#define atomic_fetch_andnot atomic_fetch_andnot #undef ATOMIC_OPS #define ATOMIC_OPS(op, c_op, asm_op) \ @@ -296,8 +297,6 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3) ATOMIC_FETCH_OP(op, c_op, asm_op) ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3) -#define atomic_andnot(mask, v) atomic_and(~(mask), (v)) -#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v)) ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3) ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) @@ -308,48 +307,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v - */ -#define __atomic_add_unless(v, a, u) \ -({ \ - int c, old; \ - \ - /* \ - * Explicit full memory barrier needed before/after as \ - * LLOCK/SCOND thmeselves don't provide any such semantics \ - */ \ - smp_mb(); \ - \ - c = atomic_read(v); \ - while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\ - c = old; \ - \ - smp_mb(); \ - \ - c; \ -}) - -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) - -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) - -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) - - #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> @@ -472,7 +429,8 @@ static inline long long atomic64_fetch_##op(long long a, atomic64_t *v) \ ATOMIC64_OP_RETURN(op, op1, op2) \ ATOMIC64_FETCH_OP(op, op1, op2) -#define atomic64_andnot atomic64_andnot +#define atomic64_andnot atomic64_andnot +#define atomic64_fetch_andnot atomic64_fetch_andnot ATOMIC64_OPS(add, add.f, adc) ATOMIC64_OPS(sub, sub.f, sbc) @@ -559,53 +517,43 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return val; } +#define atomic64_dec_if_positive atomic64_dec_if_positive /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * - * if (v != u) { v += a; ret = 1} else {ret = 0} - * Returns 1 iff @v was not @u (i.e. if add actually happened) + * Atomically adds @a to @v, if it was not @u. + * Returns the old value of @v */ -static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) { - long long val; - int op_done; + long long old, temp; smp_mb(); __asm__ __volatile__( "1: llockd %0, [%2] \n" - " mov %1, 1 \n" " brne %L0, %L4, 2f # continue to add since v != u \n" " breq.d %H0, %H4, 3f # return since v == u \n" - " mov %1, 0 \n" "2: \n" - " add.f %L0, %L0, %L3 \n" - " adc %H0, %H0, %H3 \n" - " scondd %0, [%2] \n" + " add.f %L1, %L0, %L3 \n" + " adc %H1, %H0, %H3 \n" + " scondd %1, [%2] \n" " bnz 1b \n" "3: \n" - : "=&r"(val), "=&r" (op_done) + : "=&r"(old), "=&r" (temp) : "r"(&v->counter), "r"(a), "r"(u) : "cc"); /* memory clobber comes from smp_mb() */ smp_mb(); - return op_done; + return old; } - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* !CONFIG_GENERIC_ATOMIC64 */ diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 8486f328cc5d..ff7d3232764a 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -48,7 +48,9 @@ }) /* Largest line length for either L1 or L2 is 128 bytes */ -#define ARCH_DMA_MINALIGN 128 +#define SMP_CACHE_BYTES 128 +#define cache_line_size() SMP_CACHE_BYTES +#define ARCH_DMA_MINALIGN SMP_CACHE_BYTES extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index d5da2115d78a..03d6bb0f4e13 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -17,8 +17,11 @@ #ifndef __ASM_ARC_UDELAY_H #define __ASM_ARC_UDELAY_H +#include <asm-generic/types.h> #include <asm/param.h> /* HZ */ +extern unsigned long loops_per_jiffy; + static inline void __delay(unsigned long loops) { __asm__ __volatile__( diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h index 2e52d18e6bc7..2c1b479d5aea 100644 --- a/arch/arc/include/asm/kprobes.h +++ b/arch/arc/include/asm/kprobes.h @@ -45,8 +45,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned int kprobe_status; - struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index 42b05046fad9..df35d4c0b0b8 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -225,24 +225,18 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) /* If we have no pre-handler or it returned 0, we continue with * normal processing. If we have a pre-handler and it returned - * non-zero - which is expected from setjmp_pre_handler for - * jprobe, we return without single stepping and leave that to - * the break-handler which is invoked by a kprobe from - * jprobe_return + * non-zero - which means user handler setup registers to exit + * to another instruction, we must skip the single stepping. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; + } else { + reset_current_kprobe(); + preempt_enable_no_resched(); } return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - setup_singlestep(p, regs); - kcb->kprobe_status = KPROBE_HIT_SS; - return 1; - } } /* no_kprobe: */ @@ -386,38 +380,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long sp_addr = regs->sp; - - kcb->jprobe_saved_regs = *regs; - memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr)); - regs->ret = (unsigned long)(jp->entry); - - return 1; -} - -void __kprobes jprobe_return(void) -{ - __asm__ __volatile__("unimp_s"); - return; -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long sp_addr; - - *regs = kcb->jprobe_saved_regs; - sp_addr = regs->sp; - memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr)); - preempt_enable_no_resched(); - - return 1; -} - static void __used kretprobe_trampoline_holder(void) { __asm__ __volatile__(".global kretprobe_trampoline\n" @@ -483,9 +445,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); regs->ret = orig_ret_address; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 9dbe645ee127..25c631942500 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -1038,7 +1038,7 @@ void flush_cache_mm(struct mm_struct *mm) void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr, unsigned long pfn) { - unsigned int paddr = pfn << PAGE_SHIFT; + phys_addr_t paddr = pfn << PAGE_SHIFT; u_vaddr &= PAGE_MASK; @@ -1058,8 +1058,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long u_vaddr) { /* TBD: do we really need to clear the kernel mapping */ - __flush_dcache_page(page_address(page), u_vaddr); - __flush_dcache_page(page_address(page), page_address(page)); + __flush_dcache_page((phys_addr_t)page_address(page), u_vaddr); + __flush_dcache_page((phys_addr_t)page_address(page), + (phys_addr_t)page_address(page)); } @@ -1246,6 +1247,16 @@ void __init arc_cache_init_master(void) } } + /* + * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger + * or equal to any cache line length. + */ + BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES, + "SMP_CACHE_BYTES must be >= any cache line length"); + if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES)) + panic("L2 Cache line [%d] > kernel Config [%d]\n", + l2_line_sz, SMP_CACHE_BYTES); + /* Note that SLC disable not formally supported till HS 3.0 */ if (is_isa_arcv2() && l2_line_sz && !slc_enable) arc_slc_disable(); diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 8c1071840979..ec47e6079f5d 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -129,14 +129,59 @@ int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, return ret; } +/* + * Cache operations depending on function and direction argument, inspired by + * https://lkml.org/lkml/2018/5/18/979 + * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20] + * dma-mapping: provide a generic dma-noncoherent implementation)" + * + * | map == for_device | unmap == for_cpu + * |---------------------------------------------------------------- + * TO_DEV | writeback writeback | none none + * FROM_DEV | invalidate invalidate | invalidate* invalidate* + * BIDIR | writeback+inv writeback+inv | invalidate invalidate + * + * [*] needed for CPU speculative prefetches + * + * NOTE: we don't check the validity of direction argument as it is done in + * upper layer functions (in include/linux/dma-mapping.h) + */ + void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - dma_cache_wback(paddr, size); + switch (dir) { + case DMA_TO_DEVICE: + dma_cache_wback(paddr, size); + break; + + case DMA_FROM_DEVICE: + dma_cache_inv(paddr, size); + break; + + case DMA_BIDIRECTIONAL: + dma_cache_wback_inv(paddr, size); + break; + + default: + break; + } } void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - dma_cache_inv(paddr, size); + switch (dir) { + case DMA_TO_DEVICE: + break; + + /* FROM_DEVICE invalidate needed if speculative CPU prefetch only */ + case DMA_FROM_DEVICE: + case DMA_BIDIRECTIONAL: + dma_cache_inv(paddr, size); + break; + + default: + break; + } } diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index b884bbd6f354..db6913094be3 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -15,6 +15,7 @@ #include <linux/uaccess.h> #include <linux/kdebug.h> #include <linux/perf_event.h> +#include <linux/mm_types.h> #include <asm/pgalloc.h> #include <asm/mmu.h> @@ -66,7 +67,8 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; siginfo_t info; - int fault, ret; + int ret; + vm_fault_t fault; int write = regs->ecr_cause & ECR_C_PROTV_STORE; /* ST/EX */ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h index 0c7d11022d0f..4f6a1673b3a6 100644 --- a/arch/arc/plat-eznps/include/plat/ctop.h +++ b/arch/arc/plat-eznps/include/plat/ctop.h @@ -21,6 +21,7 @@ #error "Incorrect ctop.h include" #endif +#include <linux/types.h> #include <soc/nps/common.h> /* core auxiliary registers */ @@ -143,6 +144,15 @@ struct nps_host_reg_gim_p_int_dst { }; /* AUX registers definition */ +struct nps_host_reg_aux_dpc { + union { + struct { + u32 ien:1, men:1, hen:1, reserved:29; + }; + u32 value; + }; +}; + struct nps_host_reg_aux_udmc { union { struct { diff --git a/arch/arc/plat-eznps/mtm.c b/arch/arc/plat-eznps/mtm.c index 2388de3d09ef..ed0077ef666e 100644 --- a/arch/arc/plat-eznps/mtm.c +++ b/arch/arc/plat-eznps/mtm.c @@ -15,6 +15,8 @@ */ #include <linux/smp.h> +#include <linux/init.h> +#include <linux/kernel.h> #include <linux/io.h> #include <linux/log2.h> #include <asm/arcregs.h> @@ -157,10 +159,10 @@ void mtm_enable_core(unsigned int cpu) /* Verify and set the value of the mtm hs counter */ static int __init set_mtm_hs_ctr(char *ctr_str) { - long hs_ctr; + int hs_ctr; int ret; - ret = kstrtol(ctr_str, 0, &hs_ctr); + ret = kstrtoint(ctr_str, 0, &hs_ctr); if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) { pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n", diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 843edfd000be..f69613fd4e68 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -9,6 +9,7 @@ config ARM select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_KCOV + select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_PTE_SPECIAL if ARM_LPAE select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_SET_MEMORY @@ -298,10 +299,6 @@ config PGTABLE_LEVELS default 3 if ARM_LPAE default 2 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - menu "System Type" config MMU @@ -337,8 +334,8 @@ config ARCH_MULTIPLATFORM select TIMER_OF select COMMON_CLK select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select MIGHT_HAVE_PCI - select MULTI_IRQ_HANDLER select PCI_DOMAINS if PCI select SPARSE_IRQ select USE_OF @@ -465,9 +462,9 @@ config ARCH_DOVE bool "Marvell Dove" select CPU_PJ4 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select MIGHT_HAVE_PCI - select MULTI_IRQ_HANDLER select MVEBU_MBUS select PINCTRL select PINCTRL_DOVE @@ -512,8 +509,8 @@ config ARCH_LPC32XX select COMMON_CLK select CPU_ARM926T select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB - select MULTI_IRQ_HANDLER select SPARSE_IRQ select USE_OF help @@ -532,11 +529,11 @@ config ARCH_PXA select TIMER_OF select CPU_XSCALE if !CPU_XSC3 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIO_PXA select GPIOLIB select HAVE_IDE select IRQ_DOMAIN - select MULTI_IRQ_HANDLER select PLAT_PXA select SPARSE_IRQ help @@ -572,11 +569,11 @@ config ARCH_SA1100 select CPU_FREQ select CPU_SA1100 select GENERIC_CLOCKEVENTS + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select HAVE_IDE select IRQ_DOMAIN select ISA - select MULTI_IRQ_HANDLER select NEED_MACH_MEMORY_H select SPARSE_IRQ help @@ -590,10 +587,10 @@ config ARCH_S3C24XX select GENERIC_CLOCKEVENTS select GPIO_SAMSUNG select GPIOLIB + select GENERIC_IRQ_MULTI_HANDLER select HAVE_S3C2410_I2C if I2C select HAVE_S3C2410_WATCHDOG if WATCHDOG select HAVE_S3C_RTC if RTC_CLASS - select MULTI_IRQ_HANDLER select NEED_MACH_IO_H select SAMSUNG_ATAGS select USE_OF @@ -627,10 +624,10 @@ config ARCH_OMAP1 select CLKSRC_MMIO select GENERIC_CLOCKEVENTS select GENERIC_IRQ_CHIP + select GENERIC_IRQ_MULTI_HANDLER select GPIOLIB select HAVE_IDE select IRQ_DOMAIN - select MULTI_IRQ_HANDLER select NEED_MACH_IO_H if PCCARD select NEED_MACH_MEMORY_H select SPARSE_IRQ @@ -921,11 +918,6 @@ config IWMMXT Enable support for iWMMXt context switching at run time if running on a CPU that supports it. -config MULTI_IRQ_HANDLER - bool - help - Allow each machine to specify it's own IRQ handler at run time. - if !MMU source "arch/arm/Kconfig-nommu" endif @@ -1485,8 +1477,6 @@ config ARCH_NR_GPIO If unsure, leave the default value. -source kernel/Kconfig.preempt - config HZ_FIXED int default 200 if ARCH_EBSA110 @@ -1721,8 +1711,6 @@ config ARM_MODULE_PLTS Disabling this is usually safe for small single-platform configurations. If unsure, say y. -source "mm/Kconfig" - config FORCE_MAX_ZONEORDER int "Maximum zone order" default "12" if SOC_AM33XX @@ -2175,12 +2163,6 @@ config KERNEL_MODE_NEON endmenu -menu "Userspace binary formats" - -source "fs/Kconfig.binfmt" - -endmenu - menu "Power management options" source "kernel/power/Kconfig" @@ -2201,23 +2183,10 @@ config ARCH_HIBERNATION_POSSIBLE endmenu -source "net/Kconfig" - -source "drivers/Kconfig" - source "drivers/firmware/Kconfig" -source "fs/Kconfig" - -source "arch/arm/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" if CRYPTO source "arch/arm/crypto/Kconfig" endif -source "lib/Kconfig" - source "arch/arm/kvm/Kconfig" diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 693f84392f1b..b48dc083d1b1 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config ARM_PTDUMP_CORE def_bool n @@ -1863,5 +1860,3 @@ config PID_IN_CONTEXTIDR are planning to use hardware trace tools with this kernel. source "drivers/hwtracing/coresight/Kconfig" - -endmenu diff --git a/arch/arm/Makefile b/arch/arm/Makefile index fc26c3d7b9b6..e7d703d8fac3 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -10,9 +10,6 @@ # # Copyright (C) 1995-2001 by Russell King -# Ensure linker flags are correct -LDFLAGS := - LDFLAGS_vmlinux :=-p --no-undefined -X --pic-veneer ifeq ($(CONFIG_CPU_ENDIAN_BE8),y) LDFLAGS_vmlinux += --be8 @@ -46,12 +43,12 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN),y) KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__ARMEB__ AS += -EB -LD += -EB +LDFLAGS += -EB else KBUILD_CPPFLAGS += -mlittle-endian CHECKFLAGS += -D__ARMEL__ AS += -EL -LD += -EL +LDFLAGS += -EL endif # diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts b/arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts index 389f5f83bef9..0b9b37d4d6ef 100644 --- a/arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts +++ b/arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts @@ -52,6 +52,7 @@ compatible = "fsi-master-gpio", "fsi-master"; #address-cells = <2>; #size-cells = <0>; + no-gpio-delays; clock-gpios = <&gpio ASPEED_GPIO(AA, 0) GPIO_ACTIVE_HIGH>; data-gpios = <&gpio ASPEED_GPIO(AA, 2) GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-witherspoon.dts b/arch/arm/boot/dts/aspeed-bmc-opp-witherspoon.dts index 78a511e6e482..656036106001 100644 --- a/arch/arm/boot/dts/aspeed-bmc-opp-witherspoon.dts +++ b/arch/arm/boot/dts/aspeed-bmc-opp-witherspoon.dts @@ -153,6 +153,7 @@ compatible = "fsi-master-gpio", "fsi-master"; #address-cells = <2>; #size-cells = <0>; + no-gpio-delays; clock-gpios = <&gpio ASPEED_GPIO(AA, 0) GPIO_ACTIVE_HIGH>; data-gpios = <&gpio ASPEED_GPIO(E, 0) GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/boot/dts/aspeed-bmc-opp-zaius.dts b/arch/arm/boot/dts/aspeed-bmc-opp-zaius.dts index ccbf645ab84d..2c5aa90a546d 100644 --- a/arch/arm/boot/dts/aspeed-bmc-opp-zaius.dts +++ b/arch/arm/boot/dts/aspeed-bmc-opp-zaius.dts @@ -91,6 +91,7 @@ compatible = "fsi-master-gpio", "fsi-master"; #address-cells = <2>; #size-cells = <0>; + no-gpio-delays; trans-gpios = <&gpio ASPEED_GPIO(O, 6) GPIO_ACTIVE_HIGH>; enable-gpios = <&gpio ASPEED_GPIO(D, 0) GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/boot/dts/gemini-dlink-dir-685.dts b/arch/arm/boot/dts/gemini-dlink-dir-685.dts index fb5c954ab95a..6f258b50eb44 100644 --- a/arch/arm/boot/dts/gemini-dlink-dir-685.dts +++ b/arch/arm/boot/dts/gemini-dlink-dir-685.dts @@ -156,6 +156,100 @@ }; }; + /* This is a RealTek RTL8366RB switch and PHY using SMI over GPIO */ + switch { + compatible = "realtek,rtl8366rb"; + /* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */ + mdc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>; + mdio-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio0 14 GPIO_ACTIVE_LOW>; + realtek,disable-leds; + + switch_intc: interrupt-controller { + /* GPIO 15 provides the interrupt */ + interrupt-parent = <&gpio0>; + interrupts = <15 IRQ_TYPE_LEVEL_LOW>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan0"; + phy-handle = <&phy0>; + }; + port@1 { + reg = <1>; + label = "lan1"; + phy-handle = <&phy1>; + }; + port@2 { + reg = <2>; + label = "lan2"; + phy-handle = <&phy2>; + }; + port@3 { + reg = <3>; + label = "lan3"; + phy-handle = <&phy3>; + }; + port@4 { + reg = <4>; + label = "wan"; + phy-handle = <&phy4>; + }; + rtl8366rb_cpu_port: port@5 { + reg = <5>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "rgmii"; + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + + }; + + mdio { + compatible = "realtek,smi-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + phy0: phy@0 { + reg = <0>; + interrupt-parent = <&switch_intc>; + interrupts = <0>; + }; + phy1: phy@1 { + reg = <1>; + interrupt-parent = <&switch_intc>; + interrupts = <1>; + }; + phy2: phy@2 { + reg = <2>; + interrupt-parent = <&switch_intc>; + interrupts = <2>; + }; + phy3: phy@3 { + reg = <3>; + interrupt-parent = <&switch_intc>; + interrupts = <3>; + }; + phy4: phy@4 { + reg = <4>; + interrupt-parent = <&switch_intc>; + interrupts = <12>; + }; + }; + }; + soc { flash@30000000 { /* @@ -223,10 +317,12 @@ * gpio0bgrp cover line 7 used by WPS LED * gpio0cgrp cover line 8, 13 used by keys * and 11, 12 used by the HD LEDs + * and line 14, 15 used by RTL8366 + * RESET and phy ready * gpio0egrp cover line 16 used by VDISP * gpio0fgrp cover line 17 used by TK IRQ * gpio0ggrp cover line 20 used by panel CS - * gpio0hgrp cover line 21,22 used by RTL8366RB + * gpio0hgrp cover line 21,22 used by RTL8366RB MDIO */ gpio0_default_pins: pinctrl-gpio0 { mux { @@ -250,6 +346,32 @@ groups = "gpio1bgrp"; }; }; + pinctrl-gmii { + mux { + function = "gmii"; + groups = "gmii_gmac0_grp"; + }; + conf0 { + pins = "V8 GMAC0 RXDV", "T10 GMAC1 RXDV", + "Y7 GMAC0 RXC", "Y11 GMAC1 RXC", + "T8 GMAC0 TXEN", "W11 GMAC1 TXEN", + "U8 GMAC0 TXC", "V11 GMAC1 TXC", + "W8 GMAC0 RXD0", "V9 GMAC0 RXD1", + "Y8 GMAC0 RXD2", "U9 GMAC0 RXD3", + "T7 GMAC0 TXD0", "U6 GMAC0 TXD1", + "V7 GMAC0 TXD2", "U7 GMAC0 TXD3", + "Y12 GMAC1 RXD0", "V12 GMAC1 RXD1", + "T11 GMAC1 RXD2", "W12 GMAC1 RXD3", + "U10 GMAC1 TXD0", "Y10 GMAC1 TXD1", + "W10 GMAC1 TXD2", "T9 GMAC1 TXD3"; + skew-delay = <7>; + }; + /* Set up drive strength on GMAC0 to 16 mA */ + conf1 { + groups = "gmii_gmac0_grp"; + drive-strength = <16>; + }; + }; }; }; @@ -291,6 +413,22 @@ <0x6000 0 0 4 &pci_intc 2>; }; + ethernet@60000000 { + status = "okay"; + + ethernet-port@0 { + phy-mode = "rgmii"; + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + ethernet-port@1 { + /* Not used in this platform */ + }; + }; + ata@63000000 { status = "okay"; }; diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index 85b2369d6b20..27ea6dfcf2f2 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -155,8 +155,8 @@ CONFIG_THERMAL_EMULATION=y CONFIG_WATCHDOG=y CONFIG_S3C2410_WATCHDOG=y CONFIG_MFD_CROS_EC=y -CONFIG_MFD_CROS_EC_I2C=y -CONFIG_MFD_CROS_EC_SPI=y +CONFIG_CROS_EC_I2C=y +CONFIG_CROS_EC_SPI=y CONFIG_MFD_MAX14577=y CONFIG_MFD_MAX77686=y CONFIG_MFD_MAX77693=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 8f6be1982545..be732f382418 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -490,8 +490,8 @@ CONFIG_MFD_AC100=y CONFIG_MFD_AXP20X_I2C=y CONFIG_MFD_AXP20X_RSB=y CONFIG_MFD_CROS_EC=m -CONFIG_MFD_CROS_EC_I2C=m -CONFIG_MFD_CROS_EC_SPI=m +CONFIG_CROS_EC_I2C=m +CONFIG_CROS_EC_SPI=m CONFIG_MFD_DA9063=m CONFIG_MFD_MAX14577=y CONFIG_MFD_MAX77686=y diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index 5655a1cee87d..6bb506edb1f5 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -398,8 +398,8 @@ CONFIG_MFD_AS3711=y CONFIG_MFD_BCM590XX=m CONFIG_MFD_AXP20X=y CONFIG_MFD_CROS_EC=m -CONFIG_MFD_CROS_EC_I2C=m -CONFIG_MFD_CROS_EC_SPI=m +CONFIG_CROS_EC_I2C=m +CONFIG_CROS_EC_SPI=m CONFIG_MFD_ASIC3=y CONFIG_PMIC_DA903X=y CONFIG_HTC_EGPIO=y diff --git a/arch/arm/crypto/chacha20-neon-core.S b/arch/arm/crypto/chacha20-neon-core.S index 3fecb2124c35..451a849ad518 100644 --- a/arch/arm/crypto/chacha20-neon-core.S +++ b/arch/arm/crypto/chacha20-neon-core.S @@ -51,9 +51,8 @@ ENTRY(chacha20_block_xor_neon) .Ldoubleround: // x0 += x1, x3 = rotl32(x3 ^ x0, 16) vadd.i32 q0, q0, q1 - veor q4, q3, q0 - vshl.u32 q3, q4, #16 - vsri.u32 q3, q4, #16 + veor q3, q3, q0 + vrev32.16 q3, q3 // x2 += x3, x1 = rotl32(x1 ^ x2, 12) vadd.i32 q2, q2, q3 @@ -82,9 +81,8 @@ ENTRY(chacha20_block_xor_neon) // x0 += x1, x3 = rotl32(x3 ^ x0, 16) vadd.i32 q0, q0, q1 - veor q4, q3, q0 - vshl.u32 q3, q4, #16 - vsri.u32 q3, q4, #16 + veor q3, q3, q0 + vrev32.16 q3, q3 // x2 += x3, x1 = rotl32(x1 ^ x2, 12) vadd.i32 q2, q2, q3 diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c index d9bb52cae2ac..8930fc4e7c22 100644 --- a/arch/arm/crypto/ghash-ce-glue.c +++ b/arch/arm/crypto/ghash-ce-glue.c @@ -152,7 +152,7 @@ static struct shash_alg ghash_alg = { .cra_name = "__ghash", .cra_driver_name = "__driver-ghash-ce", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_INTERNAL, + .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = GHASH_BLOCK_SIZE, .cra_ctxsize = sizeof(struct ghash_key), .cra_module = THIS_MODULE, @@ -308,9 +308,8 @@ static struct ahash_alg ghash_async_alg = { .cra_name = "ghash", .cra_driver_name = "ghash-ce", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = GHASH_BLOCK_SIZE, - .cra_type = &crypto_ahash_type, .cra_ctxsize = sizeof(struct ghash_async_ctx), .cra_module = THIS_MODULE, .cra_init = ghash_async_init_tfm, diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c index 555f72b5e659..b732522e20f8 100644 --- a/arch/arm/crypto/sha1-ce-glue.c +++ b/arch/arm/crypto/sha1-ce-glue.c @@ -75,7 +75,6 @@ static struct shash_alg alg = { .cra_name = "sha1", .cra_driver_name = "sha1-ce", .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c index 6fc73bf8766d..98ab8239f919 100644 --- a/arch/arm/crypto/sha1_glue.c +++ b/arch/arm/crypto/sha1_glue.c @@ -67,7 +67,6 @@ static struct shash_alg alg = { .cra_name = "sha1", .cra_driver_name= "sha1-asm", .cra_priority = 150, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c index 4e22f122f966..d15e0ea2c95e 100644 --- a/arch/arm/crypto/sha1_neon_glue.c +++ b/arch/arm/crypto/sha1_neon_glue.c @@ -83,7 +83,6 @@ static struct shash_alg alg = { .cra_name = "sha1", .cra_driver_name = "sha1-neon", .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c index df4dcef054ae..1211a5c129fc 100644 --- a/arch/arm/crypto/sha2-ce-glue.c +++ b/arch/arm/crypto/sha2-ce-glue.c @@ -78,7 +78,6 @@ static struct shash_alg algs[] = { { .cra_name = "sha224", .cra_driver_name = "sha224-ce", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -93,7 +92,6 @@ static struct shash_alg algs[] = { { .cra_name = "sha256", .cra_driver_name = "sha256-ce", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c index a84e869ef900..bf8ccff2c9d0 100644 --- a/arch/arm/crypto/sha256_glue.c +++ b/arch/arm/crypto/sha256_glue.c @@ -71,7 +71,6 @@ static struct shash_alg algs[] = { { .cra_name = "sha256", .cra_driver_name = "sha256-asm", .cra_priority = 150, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -86,7 +85,6 @@ static struct shash_alg algs[] = { { .cra_name = "sha224", .cra_driver_name = "sha224-asm", .cra_priority = 150, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c index 39ccd658817e..9bbee56fbdc8 100644 --- a/arch/arm/crypto/sha256_neon_glue.c +++ b/arch/arm/crypto/sha256_neon_glue.c @@ -79,7 +79,6 @@ struct shash_alg sha256_neon_algs[] = { { .cra_name = "sha256", .cra_driver_name = "sha256-neon", .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -94,7 +93,6 @@ struct shash_alg sha256_neon_algs[] = { { .cra_name = "sha224", .cra_driver_name = "sha224-neon", .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c index 269a394e4a53..86540cd4a6fa 100644 --- a/arch/arm/crypto/sha512-glue.c +++ b/arch/arm/crypto/sha512-glue.c @@ -63,7 +63,6 @@ static struct shash_alg sha512_arm_algs[] = { { .cra_name = "sha384", .cra_driver_name = "sha384-arm", .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -78,7 +77,6 @@ static struct shash_alg sha512_arm_algs[] = { { .cra_name = "sha512", .cra_driver_name = "sha512-arm", .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c index 32693684a3ab..8a5642b41fd6 100644 --- a/arch/arm/crypto/sha512-neon-glue.c +++ b/arch/arm/crypto/sha512-neon-glue.c @@ -75,7 +75,6 @@ struct shash_alg sha512_neon_algs[] = { { .cra_name = "sha384", .cra_driver_name = "sha384-neon", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_module = THIS_MODULE, @@ -91,7 +90,6 @@ struct shash_alg sha512_neon_algs[] = { { .cra_name = "sha512", .cra_driver_name = "sha512-neon", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 0cd4dccbae78..b17ee03d280b 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -460,6 +460,10 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) adds \tmp, \addr, #\size - 1 sbcccs \tmp, \tmp, \limit bcs \bad +#ifdef CONFIG_CPU_SPECTRE + movcs \addr, #0 + csdb +#endif #endif .endm diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 66d0e215a773..f74756641410 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -130,7 +130,7 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new) } #define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int oldval, newval; unsigned long tmp; @@ -156,6 +156,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return oldval; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #else /* ARM_ARCH_6 */ @@ -215,15 +216,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - - c = atomic_read(v); - while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c) - c = old; - return c; -} +#define atomic_fetch_andnot atomic_fetch_andnot #endif /* __LINUX_ARM_ARCH__ */ @@ -254,17 +247,6 @@ ATOMIC_OPS(xor, ^=, eor) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) - -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic_inc_return_relaxed(v) (atomic_add_return_relaxed(1, v)) -#define atomic_dec_return_relaxed(v) (atomic_sub_return_relaxed(1, v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0) - #ifndef CONFIG_GENERIC_ATOMIC64 typedef struct { long long counter; @@ -494,12 +476,13 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) return result; } +#define atomic64_dec_if_positive atomic64_dec_if_positive -static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a, + long long u) { - long long val; + long long oldval, newval; unsigned long tmp; - int ret = 1; smp_mb(); prefetchw(&v->counter); @@ -508,33 +491,23 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) "1: ldrexd %0, %H0, [%4]\n" " teq %0, %5\n" " teqeq %H0, %H5\n" -" moveq %1, #0\n" " beq 2f\n" -" adds %Q0, %Q0, %Q6\n" -" adc %R0, %R0, %R6\n" -" strexd %2, %0, %H0, [%4]\n" +" adds %Q1, %Q0, %Q6\n" +" adc %R1, %R0, %R6\n" +" strexd %2, %1, %H1, [%4]\n" " teq %2, #0\n" " bne 1b\n" "2:" - : "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter) + : "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter) : "r" (&v->counter), "r" (u), "r" (a) : "cc"); - if (ret) + if (oldval != u) smp_mb(); - return ret; + return oldval; } - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1LL, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* !CONFIG_GENERIC_ATOMIC64 */ #endif diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h index 4cab9bb823fb..c92e42a5c8f7 100644 --- a/arch/arm/include/asm/bitops.h +++ b/arch/arm/include/asm/bitops.h @@ -215,7 +215,6 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset); #if __LINUX_ARM_ARCH__ < 5 -#include <asm-generic/bitops/ffz.h> #include <asm-generic/bitops/__fls.h> #include <asm-generic/bitops/__ffs.h> #include <asm-generic/bitops/fls.h> @@ -223,93 +222,20 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset); #else -static inline int constant_fls(int x) -{ - int r = 32; - - if (!x) - return 0; - if (!(x & 0xffff0000u)) { - x <<= 16; - r -= 16; - } - if (!(x & 0xff000000u)) { - x <<= 8; - r -= 8; - } - if (!(x & 0xf0000000u)) { - x <<= 4; - r -= 4; - } - if (!(x & 0xc0000000u)) { - x <<= 2; - r -= 2; - } - if (!(x & 0x80000000u)) { - x <<= 1; - r -= 1; - } - return r; -} - -/* - * On ARMv5 and above those functions can be implemented around the - * clz instruction for much better code efficiency. __clz returns - * the number of leading zeros, zero input will return 32, and - * 0x80000000 will return 0. - */ -static inline unsigned int __clz(unsigned int x) -{ - unsigned int ret; - - asm("clz\t%0, %1" : "=r" (ret) : "r" (x)); - - return ret; -} - -/* - * fls() returns zero if the input is zero, otherwise returns the bit - * position of the last set bit, where the LSB is 1 and MSB is 32. - */ -static inline int fls(int x) -{ - if (__builtin_constant_p(x)) - return constant_fls(x); - - return 32 - __clz(x); -} - -/* - * __fls() returns the bit position of the last bit set, where the - * LSB is 0 and MSB is 31. Zero input is undefined. - */ -static inline unsigned long __fls(unsigned long x) -{ - return fls(x) - 1; -} - -/* - * ffs() returns zero if the input was zero, otherwise returns the bit - * position of the first set bit, where the LSB is 1 and MSB is 32. - */ -static inline int ffs(int x) -{ - return fls(x & -x); -} - /* - * __ffs() returns the bit position of the first bit set, where the - * LSB is 0 and MSB is 31. Zero input is undefined. + * On ARMv5 and above, the gcc built-ins may rely on the clz instruction + * and produce optimal inlined code in all cases. On ARMv7 it is even + * better by also using the rbit instruction. */ -static inline unsigned long __ffs(unsigned long x) -{ - return ffs(x) - 1; -} - -#define ffz(x) __ffs( ~(x) ) +#include <asm-generic/bitops/builtin-__fls.h> +#include <asm-generic/bitops/builtin-__ffs.h> +#include <asm-generic/bitops/builtin-fls.h> +#include <asm-generic/bitops/builtin-ffs.h> #endif +#include <asm-generic/bitops/ffz.h> + #include <asm-generic/bitops/fls64.h> #include <asm-generic/bitops/sched.h> diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 17f1f1a814ff..38badaae8d9d 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -58,6 +58,9 @@ void efi_virtmap_unload(void); #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (false) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h index e46e4e7bdba3..ac54c06764e6 100644 --- a/arch/arm/include/asm/hw_breakpoint.h +++ b/arch/arm/include/asm/hw_breakpoint.h @@ -111,14 +111,17 @@ static inline void decode_ctrl_reg(u32 reg, asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\ } while (0) +struct perf_event_attr; struct notifier_block; struct perf_event; struct pmu; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, int *gen_len, int *gen_type); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index b6f319606e30..c883fcbe93b6 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -31,11 +31,6 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *); void handle_IRQ(unsigned int, struct pt_regs *); void init_IRQ(void); -#ifdef CONFIG_MULTI_IRQ_HANDLER -extern void (*handle_arch_irq)(struct pt_regs *); -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); -#endif - #ifdef CONFIG_SMP extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 59655459da59..82290f212d8e 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -44,8 +44,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned int kprobe_status; struct prev_kprobe prev_kprobe; - struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 6493bd479ddc..fe2fb1ddd771 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -26,13 +26,13 @@ #include <asm/cputype.h> /* arm64 compatibility macros */ -#define COMPAT_PSR_MODE_ABT ABT_MODE -#define COMPAT_PSR_MODE_UND UND_MODE -#define COMPAT_PSR_T_BIT PSR_T_BIT -#define COMPAT_PSR_I_BIT PSR_I_BIT -#define COMPAT_PSR_A_BIT PSR_A_BIT -#define COMPAT_PSR_E_BIT PSR_E_BIT -#define COMPAT_PSR_IT_MASK PSR_IT_MASK +#define PSR_AA32_MODE_ABT ABT_MODE +#define PSR_AA32_MODE_UND UND_MODE +#define PSR_AA32_T_BIT PSR_T_BIT +#define PSR_AA32_I_BIT PSR_I_BIT +#define PSR_AA32_A_BIT PSR_A_BIT +#define PSR_AA32_E_BIT PSR_E_BIT +#define PSR_AA32_IT_MASK PSR_IT_MASK unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 5c1ad11aa392..bb8851208e17 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -59,7 +59,7 @@ struct machine_desc { void (*init_time)(void); void (*init_machine)(void); void (*init_late)(void); -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER void (*handle_irq)(struct pt_regs *); #endif void (*restart)(enum reboot_mode, const char *); diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h index 0f79e4dec7f9..4ac3a019a46f 100644 --- a/arch/arm/include/asm/mach/time.h +++ b/arch/arm/include/asm/mach/time.h @@ -13,7 +13,6 @@ extern void timer_tick(void); typedef void (*clock_access_fn)(struct timespec64 *); -extern int register_persistent_clock(clock_access_fn read_boot, - clock_access_fn read_persistent); +extern int register_persistent_clock(clock_access_fn read_persistent); #endif diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index 89ad0596033a..9e81b7c498d8 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -34,6 +34,7 @@ struct mod_arch_specific { #endif }; +struct module; u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val); /* diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h index 1e5b9bb92270..991c9127c650 100644 --- a/arch/arm/include/asm/probes.h +++ b/arch/arm/include/asm/probes.h @@ -51,7 +51,6 @@ struct arch_probes_insn { * We assume one instruction can consume at most 64 bytes stack, which is * 'push {r0-r15}'. Instructions consume more or unknown stack space like * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe. - * Both kprobe and jprobe use this macro. */ #define MAX_STACK_SIZE 64 diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index e71cc35de163..9b37b6ab27fe 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -123,8 +123,8 @@ struct user_vfp_exc; extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *, struct user_vfp_exc __user *); -extern int vfp_restore_user_hwstate(struct user_vfp __user *, - struct user_vfp_exc __user *); +extern int vfp_restore_user_hwstate(struct user_vfp *, + struct user_vfp_exc *); #endif /* diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index d5562f9ce600..f854148c8d7c 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -292,5 +292,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, { } +static inline void tlb_flush_remove_tables(struct mm_struct *mm) +{ +} + +static inline void tlb_flush_remove_tables_local(void *arg) +{ +} + #endif /* CONFIG_MMU */ #endif diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 3d614e90c19f..5451e1f05a19 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -85,6 +85,13 @@ static inline void set_fs(mm_segment_t fs) flag; }) /* + * This is a type: either unsigned long, if the argument fits into + * that type, or otherwise unsigned long long. + */ +#define __inttype(x) \ + __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) + +/* * Single-value transfer routines. They automatically use the right * size if we just have the right pointer type. Note that the functions * which read from user space (*get_*) need to take care not to leak @@ -153,7 +160,7 @@ extern int __get_user_64t_4(void *); ({ \ unsigned long __limit = current_thread_info()->addr_limit - 1; \ register typeof(*(p)) __user *__p asm("r0") = (p); \ - register typeof(x) __r2 asm("r2"); \ + register __inttype(x) __r2 asm("r2"); \ register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ unsigned int __ua_flags = uaccess_save_and_enable(); \ @@ -243,6 +250,16 @@ static inline void set_fs(mm_segment_t fs) #define user_addr_max() \ (uaccess_kernel() ? ~0UL : get_fs()) +#ifdef CONFIG_CPU_SPECTRE +/* + * When mitigating Spectre variant 1, it is not worth fixing the non- + * verifying accessors, because we need to add verification of the + * address space there. Force these to use the standard get_user() + * version instead. + */ +#define __get_user(x, ptr) get_user(x, ptr) +#else + /* * The "__xxx" versions of the user access functions do not verify the * address space - it must have been done previously with a separate @@ -259,12 +276,6 @@ static inline void set_fs(mm_segment_t fs) __gu_err; \ }) -#define __get_user_error(x, ptr, err) \ -({ \ - __get_user_err((x), (ptr), err); \ - (void) 0; \ -}) - #define __get_user_err(x, ptr, err) \ do { \ unsigned long __gu_addr = (unsigned long)(ptr); \ @@ -324,6 +335,7 @@ do { \ #define __get_user_asm_word(x, addr, err) \ __get_user_asm(x, addr, err, ldr) +#endif #define __put_user_switch(x, ptr, __err, __fn) \ diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 179a9f6bd1e3..e85a3af9ddeb 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -22,7 +22,7 @@ #include <asm/glue-df.h> #include <asm/glue-pf.h> #include <asm/vfpmacros.h> -#ifndef CONFIG_MULTI_IRQ_HANDLER +#ifndef CONFIG_GENERIC_IRQ_MULTI_HANDLER #include <mach/entry-macro.S> #endif #include <asm/thread_notify.h> @@ -39,7 +39,7 @@ * Interrupt handling. */ .macro irq_handler -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER ldr r1, =handle_arch_irq mov r0, sp badr lr, 9997f @@ -1226,9 +1226,3 @@ vector_addrexcptn: .globl cr_alignment cr_alignment: .space 4 - -#ifdef CONFIG_MULTI_IRQ_HANDLER - .globl handle_arch_irq -handle_arch_irq: - .space 4 -#endif diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 106a1466518d..746565a876dc 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -48,6 +48,7 @@ saved_pc .req lr * from those features make this path too inefficient. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts @@ -78,6 +79,7 @@ fast_work_pending: * call. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 @@ -255,7 +257,7 @@ local_restart: tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls? bne __sys_trace - invoke_syscall tbl, scno, r10, ret_fast_syscall + invoke_syscall tbl, scno, r10, __ret_fast_syscall add r1, sp, #S_OFF 2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index 7a9b86978ee1..ec29de250076 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -53,7 +53,11 @@ ENTRY(stext) THUMB(1: ) #endif - setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install +#endif + @ ensure svc mode and all interrupts masked + safe_svcmode_maskall r9 @ and irqs disabled #if defined(CONFIG_CPU_CP15) mrc p15, 0, r9, c0, c0 @ get processor id @@ -89,7 +93,11 @@ ENTRY(secondary_startup) * the processor type - there is no need to check the machine type * as it has already been validated by the primary processor. */ - setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install_secondary +#endif + safe_svcmode_maskall r9 + #ifndef CONFIG_CPU_CP15 ldr r9, =CONFIG_PROCESSOR_ID #else diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 629e25152c0d..1d5fbf1d1c67 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -456,14 +456,13 @@ static int get_hbp_len(u8 hbp_len) /* * Check whether bp virtual address is in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->ctrl.len); + va = hw->address; + len = get_hbp_len(hw->ctrl.len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -518,42 +517,42 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->ctrl.type = ARM_BREAKPOINT_EXECUTE; + hw->ctrl.type = ARM_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->ctrl.type = ARM_BREAKPOINT_LOAD; + hw->ctrl.type = ARM_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->ctrl.type = ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->ctrl.len = ARM_BREAKPOINT_LEN_1; + hw->ctrl.len = ARM_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->ctrl.len = ARM_BREAKPOINT_LEN_2; + hw->ctrl.len = ARM_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_8: - info->ctrl.len = ARM_BREAKPOINT_LEN_8; - if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE) + hw->ctrl.len = ARM_BREAKPOINT_LEN_8; + if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE) && max_watchpoint_len >= 8) break; default: @@ -566,24 +565,24 @@ static int arch_build_bp_info(struct perf_event *bp) * by the hardware and must be aligned to the appropriate number of * bytes. */ - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE && - info->ctrl.len != ARM_BREAKPOINT_LEN_2 && - info->ctrl.len != ARM_BREAKPOINT_LEN_4) + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE && + hw->ctrl.len != ARM_BREAKPOINT_LEN_2 && + hw->ctrl.len != ARM_BREAKPOINT_LEN_4) return -EINVAL; /* Address */ - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* Privilege */ - info->ctrl.privilege = ARM_BREAKPOINT_USER; - if (arch_check_bp_in_kernelspace(bp)) - info->ctrl.privilege |= ARM_BREAKPOINT_PRIV; + hw->ctrl.privilege = ARM_BREAKPOINT_USER; + if (arch_check_bp_in_kernelspace(hw)) + hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV; /* Enabled? */ - info->ctrl.enabled = !bp->attr.disabled; + hw->ctrl.enabled = !attr->disabled; /* Mismatch */ - info->ctrl.mismatch = 0; + hw->ctrl.mismatch = 0; return 0; } @@ -591,9 +590,10 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings. */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); int ret = 0; u32 offset, alignment_mask = 0x3; @@ -602,14 +602,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) return -ENODEV; /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) goto out; /* Check address alignment. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; switch (offset) { case 0: /* Aligned */ @@ -617,19 +617,19 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) case 1: case 2: /* Allow halfword watchpoints and breakpoints. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_2) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; case 3: /* Allow single byte watchpoint. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; default: ret = -EINVAL; goto out; } - info->address &= ~alignment_mask; - info->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; if (is_default_overflow_handler(bp)) { /* @@ -640,7 +640,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) return -EINVAL; /* We don't allow mismatch breakpoints in kernel space. */ - if (arch_check_bp_in_kernelspace(bp)) + if (arch_check_bp_in_kernelspace(hw)) return -EPERM; /* @@ -655,8 +655,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * reports them. */ if (!debug_exception_updates_fsr() && - (info->ctrl.type == ARM_BREAKPOINT_LOAD || - info->ctrl.type == ARM_BREAKPOINT_STORE)) + (hw->ctrl.type == ARM_BREAKPOINT_LOAD || + hw->ctrl.type == ARM_BREAKPOINT_STORE)) return -EINVAL; } diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index ece04a457486..9908dacf9229 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -102,16 +102,6 @@ void __init init_IRQ(void) uniphier_cache_init(); } -#ifdef CONFIG_MULTI_IRQ_HANDLER -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - if (handle_arch_irq) - return; - - handle_arch_irq = handle_irq; -} -#endif - #ifdef CONFIG_SPARSE_IRQ int __init arch_probe_nr_irqs(void) { diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c index be42c4f66a40..1ae99deeec54 100644 --- a/arch/arm/kernel/perf_event_v6.c +++ b/arch/arm/kernel/perf_event_v6.c @@ -233,7 +233,7 @@ armv6_pmcr_counter_has_overflowed(unsigned long pmcr, return ret; } -static inline u32 armv6pmu_read_counter(struct perf_event *event) +static inline u64 armv6pmu_read_counter(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -251,7 +251,7 @@ static inline u32 armv6pmu_read_counter(struct perf_event *event) return value; } -static inline void armv6pmu_write_counter(struct perf_event *event, u32 value) +static inline void armv6pmu_write_counter(struct perf_event *event, u64 value) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -411,6 +411,12 @@ armv6pmu_get_event_idx(struct pmu_hw_events *cpuc, } } +static void armv6pmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + clear_bit(event->hw.idx, cpuc->used_mask); +} + static void armv6pmu_disable_event(struct perf_event *event) { unsigned long val, mask, evt, flags; @@ -491,11 +497,11 @@ static void armv6pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->read_counter = armv6pmu_read_counter; cpu_pmu->write_counter = armv6pmu_write_counter; cpu_pmu->get_event_idx = armv6pmu_get_event_idx; + cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx; cpu_pmu->start = armv6pmu_start; cpu_pmu->stop = armv6pmu_stop; cpu_pmu->map_event = armv6_map_event; cpu_pmu->num_events = 3; - cpu_pmu->max_period = (1LLU << 32) - 1; } static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu) @@ -542,11 +548,11 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->read_counter = armv6pmu_read_counter; cpu_pmu->write_counter = armv6pmu_write_counter; cpu_pmu->get_event_idx = armv6pmu_get_event_idx; + cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx; cpu_pmu->start = armv6pmu_start; cpu_pmu->stop = armv6pmu_stop; cpu_pmu->map_event = armv6mpcore_map_event; cpu_pmu->num_events = 3; - cpu_pmu->max_period = (1LLU << 32) - 1; return 0; } diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 57f01e059f39..a4fb0f8b8f84 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -743,7 +743,7 @@ static inline void armv7_pmnc_select_counter(int idx) isb(); } -static inline u32 armv7pmu_read_counter(struct perf_event *event) +static inline u64 armv7pmu_read_counter(struct perf_event *event) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; @@ -763,7 +763,7 @@ static inline u32 armv7pmu_read_counter(struct perf_event *event) return value; } -static inline void armv7pmu_write_counter(struct perf_event *event, u32 value) +static inline void armv7pmu_write_counter(struct perf_event *event, u64 value) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; @@ -1058,6 +1058,12 @@ static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc, return -EAGAIN; } +static void armv7pmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + clear_bit(event->hw.idx, cpuc->used_mask); +} + /* * Add an event filter to a given event. This will only work for PMUv2 PMUs. */ @@ -1167,10 +1173,10 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->read_counter = armv7pmu_read_counter; cpu_pmu->write_counter = armv7pmu_write_counter; cpu_pmu->get_event_idx = armv7pmu_get_event_idx; + cpu_pmu->clear_event_idx = armv7pmu_clear_event_idx; cpu_pmu->start = armv7pmu_start; cpu_pmu->stop = armv7pmu_stop; cpu_pmu->reset = armv7pmu_reset; - cpu_pmu->max_period = (1LLU << 32) - 1; }; static void armv7_read_num_pmnc_events(void *info) @@ -1638,6 +1644,7 @@ static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc, bool venum_event = EVENT_VENUM(hwc->config_base); bool krait_event = EVENT_CPU(hwc->config_base); + armv7pmu_clear_event_idx(cpuc, event); if (venum_event || krait_event) { bit = krait_event_to_bit(event, region, group); clear_bit(bit, cpuc->used_mask); @@ -1967,6 +1974,7 @@ static void scorpion_pmu_clear_event_idx(struct pmu_hw_events *cpuc, bool venum_event = EVENT_VENUM(hwc->config_base); bool scorpion_event = EVENT_CPU(hwc->config_base); + armv7pmu_clear_event_idx(cpuc, event); if (venum_event || scorpion_event) { bit = scorpion_event_to_bit(event, region, group); clear_bit(bit, cpuc->used_mask); @@ -2030,6 +2038,7 @@ static struct platform_driver armv7_pmu_driver = { .driver = { .name = "armv7-pmu", .of_match_table = armv7_pmu_of_device_ids, + .suppress_bind_attrs = true, }, .probe = armv7_pmu_device_probe, }; diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c index 88d1a76f5367..f6cdcacfb96d 100644 --- a/arch/arm/kernel/perf_event_xscale.c +++ b/arch/arm/kernel/perf_event_xscale.c @@ -292,6 +292,12 @@ xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc, } } +static void xscalepmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + clear_bit(event->hw.idx, cpuc->used_mask); +} + static void xscale1pmu_start(struct arm_pmu *cpu_pmu) { unsigned long flags, val; @@ -316,7 +322,7 @@ static void xscale1pmu_stop(struct arm_pmu *cpu_pmu) raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } -static inline u32 xscale1pmu_read_counter(struct perf_event *event) +static inline u64 xscale1pmu_read_counter(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -337,7 +343,7 @@ static inline u32 xscale1pmu_read_counter(struct perf_event *event) return val; } -static inline void xscale1pmu_write_counter(struct perf_event *event, u32 val) +static inline void xscale1pmu_write_counter(struct perf_event *event, u64 val) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -370,11 +376,11 @@ static int xscale1pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->read_counter = xscale1pmu_read_counter; cpu_pmu->write_counter = xscale1pmu_write_counter; cpu_pmu->get_event_idx = xscale1pmu_get_event_idx; + cpu_pmu->clear_event_idx = xscalepmu_clear_event_idx; cpu_pmu->start = xscale1pmu_start; cpu_pmu->stop = xscale1pmu_stop; cpu_pmu->map_event = xscale_map_event; cpu_pmu->num_events = 3; - cpu_pmu->max_period = (1LLU << 32) - 1; return 0; } @@ -679,7 +685,7 @@ static void xscale2pmu_stop(struct arm_pmu *cpu_pmu) raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } -static inline u32 xscale2pmu_read_counter(struct perf_event *event) +static inline u64 xscale2pmu_read_counter(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -706,7 +712,7 @@ static inline u32 xscale2pmu_read_counter(struct perf_event *event) return val; } -static inline void xscale2pmu_write_counter(struct perf_event *event, u32 val) +static inline void xscale2pmu_write_counter(struct perf_event *event, u64 val) { struct hw_perf_event *hwc = &event->hw; int counter = hwc->idx; @@ -739,11 +745,11 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->read_counter = xscale2pmu_read_counter; cpu_pmu->write_counter = xscale2pmu_write_counter; cpu_pmu->get_event_idx = xscale2pmu_get_event_idx; + cpu_pmu->clear_event_idx = xscalepmu_clear_event_idx; cpu_pmu->start = xscale2pmu_start; cpu_pmu->stop = xscale2pmu_stop; cpu_pmu->map_event = xscale_map_event; cpu_pmu->num_events = 5; - cpu_pmu->max_period = (1LLU << 32) - 1; return 0; } diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 225d1c58d2de..d9c299133111 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = { static int __init gate_vma_init(void) { + vma_init(&gate_vma, NULL); gate_vma.vm_page_prot = PAGE_READONLY_EXEC; return 0; } diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 35ca494c028c..4c249cb261f3 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1145,7 +1145,7 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); -#ifdef CONFIG_MULTI_IRQ_HANDLER +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER handle_arch_irq = mdesc->handle_irq; #endif diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index dec130e7078c..b8f766cf3a90 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -150,22 +150,18 @@ static int preserve_vfp_context(struct vfp_sigframe __user *frame) static int restore_vfp_context(char __user **auxp) { - struct vfp_sigframe __user *frame = - (struct vfp_sigframe __user *)*auxp; - unsigned long magic; - unsigned long size; - int err = 0; - - __get_user_error(magic, &frame->magic, err); - __get_user_error(size, &frame->size, err); + struct vfp_sigframe frame; + int err; + err = __copy_from_user(&frame, *auxp, sizeof(frame)); if (err) - return -EFAULT; - if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE) + return err; + + if (frame.magic != VFP_MAGIC || frame.size != VFP_STORAGE_SIZE) return -EINVAL; - *auxp += size; - return vfp_restore_user_hwstate(&frame->ufp, &frame->ufp_exc); + *auxp += sizeof(frame); + return vfp_restore_user_hwstate(&frame.ufp, &frame.ufp_exc); } #endif @@ -176,6 +172,7 @@ static int restore_vfp_context(char __user **auxp) static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf) { + struct sigcontext context; char __user *aux; sigset_t set; int err; @@ -184,23 +181,26 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf) if (err == 0) set_current_blocked(&set); - __get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err); - __get_user_error(regs->ARM_r1, &sf->uc.uc_mcontext.arm_r1, err); - __get_user_error(regs->ARM_r2, &sf->uc.uc_mcontext.arm_r2, err); - __get_user_error(regs->ARM_r3, &sf->uc.uc_mcontext.arm_r3, err); - __get_user_error(regs->ARM_r4, &sf->uc.uc_mcontext.arm_r4, err); - __get_user_error(regs->ARM_r5, &sf->uc.uc_mcontext.arm_r5, err); - __get_user_error(regs->ARM_r6, &sf->uc.uc_mcontext.arm_r6, err); - __get_user_error(regs->ARM_r7, &sf->uc.uc_mcontext.arm_r7, err); - __get_user_error(regs->ARM_r8, &sf->uc.uc_mcontext.arm_r8, err); - __get_user_error(regs->ARM_r9, &sf->uc.uc_mcontext.arm_r9, err); - __get_user_error(regs->ARM_r10, &sf->uc.uc_mcontext.arm_r10, err); - __get_user_error(regs->ARM_fp, &sf->uc.uc_mcontext.arm_fp, err); - __get_user_error(regs->ARM_ip, &sf->uc.uc_mcontext.arm_ip, err); - __get_user_error(regs->ARM_sp, &sf->uc.uc_mcontext.arm_sp, err); - __get_user_error(regs->ARM_lr, &sf->uc.uc_mcontext.arm_lr, err); - __get_user_error(regs->ARM_pc, &sf->uc.uc_mcontext.arm_pc, err); - __get_user_error(regs->ARM_cpsr, &sf->uc.uc_mcontext.arm_cpsr, err); + err |= __copy_from_user(&context, &sf->uc.uc_mcontext, sizeof(context)); + if (err == 0) { + regs->ARM_r0 = context.arm_r0; + regs->ARM_r1 = context.arm_r1; + regs->ARM_r2 = context.arm_r2; + regs->ARM_r3 = context.arm_r3; + regs->ARM_r4 = context.arm_r4; + regs->ARM_r5 = context.arm_r5; + regs->ARM_r6 = context.arm_r6; + regs->ARM_r7 = context.arm_r7; + regs->ARM_r8 = context.arm_r8; + regs->ARM_r9 = context.arm_r9; + regs->ARM_r10 = context.arm_r10; + regs->ARM_fp = context.arm_fp; + regs->ARM_ip = context.arm_ip; + regs->ARM_sp = context.arm_sp; + regs->ARM_lr = context.arm_lr; + regs->ARM_pc = context.arm_pc; + regs->ARM_cpsr = context.arm_cpsr; + } err |= !valid_user_regs(regs); diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 1df21a61e379..f0dd4b6ebb63 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -329,9 +329,11 @@ asmlinkage long sys_oabi_semtimedop(int semid, return -ENOMEM; err = 0; for (i = 0; i < nsops; i++) { - __get_user_error(sops[i].sem_num, &tsops->sem_num, err); - __get_user_error(sops[i].sem_op, &tsops->sem_op, err); - __get_user_error(sops[i].sem_flg, &tsops->sem_flg, err); + struct oabi_sembuf osb; + err |= __copy_from_user(&osb, tsops, sizeof(osb)); + sops[i].sem_num = osb.sem_num; + sops[i].sem_op = osb.sem_op; + sops[i].sem_flg = osb.sem_flg; tsops++; } if (timeout) { diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index cf2701cb0de8..078b259ead4e 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -83,29 +83,18 @@ static void dummy_clock_access(struct timespec64 *ts) } static clock_access_fn __read_persistent_clock = dummy_clock_access; -static clock_access_fn __read_boot_clock = dummy_clock_access; void read_persistent_clock64(struct timespec64 *ts) { __read_persistent_clock(ts); } -void read_boot_clock64(struct timespec64 *ts) -{ - __read_boot_clock(ts); -} - -int __init register_persistent_clock(clock_access_fn read_boot, - clock_access_fn read_persistent) +int __init register_persistent_clock(clock_access_fn read_persistent) { /* Only allow the clockaccess functions to be registered once */ - if (__read_persistent_clock == dummy_clock_access && - __read_boot_clock == dummy_clock_access) { - if (read_boot) - __read_boot_clock = read_boot; + if (__read_persistent_clock == dummy_clock_access) { if (read_persistent) __read_persistent_clock = read_persistent; - return 0; } diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index 7a4b06049001..a826df3d3814 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -90,6 +90,15 @@ .text ENTRY(arm_copy_from_user) +#ifdef CONFIG_CPU_SPECTRE + get_thread_info r3 + ldr r3, [r3, #TI_ADDR_LIMIT] + adds ip, r1, r2 @ ip=addr+size + sub r3, r3, #1 @ addr_limit - 1 + cmpcc ip, r3 @ if (addr+size > addr_limit - 1) + movcs r1, #0 @ addr = NULL + csdb +#endif #include "copy_template.S" diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig index 1254bf9d91b4..903f23c309df 100644 --- a/arch/arm/mach-at91/Kconfig +++ b/arch/arm/mach-at91/Kconfig @@ -27,6 +27,7 @@ config SOC_SAMA5D2 select HAVE_AT91_H32MX select HAVE_AT91_GENERATED_CLK select HAVE_AT91_AUDIO_PLL + select HAVE_AT91_I2S_MUX_CLK select PINCTRL_AT91PIO4 help Select this if ou are using one of Microchip's SAMA5D2 family SoC. @@ -129,6 +130,9 @@ config HAVE_AT91_GENERATED_CLK config HAVE_AT91_AUDIO_PLL bool +config HAVE_AT91_I2S_MUX_CLK + bool + config SOC_SAM_V4_V5 bool diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile index 4ea93c9df77b..7415f181907b 100644 --- a/arch/arm/mach-at91/Makefile +++ b/arch/arm/mach-at91/Makefile @@ -19,31 +19,6 @@ ifeq ($(CONFIG_PM_DEBUG),y) CFLAGS_pm.o += -DDEBUG endif -# Default sed regexp - multiline due to syntax constraints -define sed-y - "/^->/{s:->#\(.*\):/* \1 */:; \ - s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 \2 /* \3 */:; \ - s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \ - s:->::; p;}" -endef - -# Use filechk to avoid rebuilds when a header changes, but the resulting file -# does not -define filechk_offsets - (set -e; \ - echo "#ifndef $2"; \ - echo "#define $2"; \ - echo "/*"; \ - echo " * DO NOT MODIFY."; \ - echo " *"; \ - echo " * This file was generated by Kbuild"; \ - echo " */"; \ - echo ""; \ - sed -ne $(sed-y); \ - echo ""; \ - echo "#endif" ) -endef - arch/arm/mach-at91/pm_data-offsets.s: arch/arm/mach-at91/pm_data-offsets.c $(call if_changed_dep,cc_s_c) diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c index d3db306a5a70..f3384e3a675d 100644 --- a/arch/arm/mach-exynos/suspend.c +++ b/arch/arm/mach-exynos/suspend.c @@ -272,7 +272,7 @@ static int exynos5420_cpu_suspend(unsigned long arg) static void exynos_pm_set_wakeup_mask(void) { /* Set wake-up mask registers */ - pmu_raw_writel(exynos_get_eint_wake_mask(), S5P_EINT_WAKEUP_MASK); + pmu_raw_writel(exynos_get_eint_wake_mask(), EXYNOS_EINT_WAKEUP_MASK); pmu_raw_writel(exynos_irqwake_intmask & ~(1 << 31), S5P_WAKEUP_MASK); } diff --git a/arch/arm/mach-mmp/sram.c b/arch/arm/mach-mmp/sram.c index bf5e64906e65..ba91e4fe444d 100644 --- a/arch/arm/mach-mmp/sram.c +++ b/arch/arm/mach-mmp/sram.c @@ -15,6 +15,7 @@ */ #include <linux/module.h> +#include <linux/mod_devicetable.h> #include <linux/init.h> #include <linux/platform_device.h> #include <linux/io.h> diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c index f4f8f23bda8c..af46d2182533 100644 --- a/arch/arm/mach-pxa/balloon3.c +++ b/arch/arm/mach-pxa/balloon3.c @@ -688,7 +688,6 @@ struct platform_nand_data balloon3_nand_pdata = { .chip_delay = 50, }, .ctrl = { - .hwcontrol = 0, .dev_ready = balloon3_nand_dev_ready, .select_chip = balloon3_nand_select_chip, .cmd_ctrl = balloon3_nand_cmd_ctl, diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c index d7c9a8476d57..5a16ea74e28a 100644 --- a/arch/arm/mach-pxa/devices.c +++ b/arch/arm/mach-pxa/devices.c @@ -4,6 +4,7 @@ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/dma-mapping.h> +#include <linux/dmaengine.h> #include <linux/spi/pxa2xx_spi.h> #include <linux/platform_data/i2c-pxa.h> @@ -59,16 +60,6 @@ static struct resource pxamci_resources[] = { .end = IRQ_MMC, .flags = IORESOURCE_IRQ, }, - [2] = { - .start = 21, - .end = 21, - .flags = IORESOURCE_DMA, - }, - [3] = { - .start = 22, - .end = 22, - .flags = IORESOURCE_DMA, - }, }; static u64 pxamci_dmamask = 0xffffffffUL; @@ -406,16 +397,6 @@ static struct resource pxa_ir_resources[] = { .end = 0x40700023, .flags = IORESOURCE_MEM, }, - [5] = { - .start = 17, - .end = 17, - .flags = IORESOURCE_DMA, - }, - [6] = { - .start = 18, - .end = 18, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa_device_ficp = { @@ -544,18 +525,6 @@ static struct resource pxa25x_resource_ssp[] = { .end = IRQ_SSP, .flags = IORESOURCE_IRQ, }, - [2] = { - /* DRCMR for RX */ - .start = 13, - .end = 13, - .flags = IORESOURCE_DMA, - }, - [3] = { - /* DRCMR for TX */ - .start = 14, - .end = 14, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa25x_device_ssp = { @@ -582,18 +551,6 @@ static struct resource pxa25x_resource_nssp[] = { .end = IRQ_NSSP, .flags = IORESOURCE_IRQ, }, - [2] = { - /* DRCMR for RX */ - .start = 15, - .end = 15, - .flags = IORESOURCE_DMA, - }, - [3] = { - /* DRCMR for TX */ - .start = 16, - .end = 16, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa25x_device_nssp = { @@ -620,18 +577,6 @@ static struct resource pxa25x_resource_assp[] = { .end = IRQ_ASSP, .flags = IORESOURCE_IRQ, }, - [2] = { - /* DRCMR for RX */ - .start = 23, - .end = 23, - .flags = IORESOURCE_DMA, - }, - [3] = { - /* DRCMR for TX */ - .start = 24, - .end = 24, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa25x_device_assp = { @@ -750,18 +695,6 @@ static struct resource pxa27x_resource_ssp1[] = { .end = IRQ_SSP, .flags = IORESOURCE_IRQ, }, - [2] = { - /* DRCMR for RX */ - .start = 13, - .end = 13, - .flags = IORESOURCE_DMA, - }, - [3] = { - /* DRCMR for TX */ - .start = 14, - .end = 14, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa27x_device_ssp1 = { @@ -788,18 +721,6 @@ static struct resource pxa27x_resource_ssp2[] = { .end = IRQ_SSP2, .flags = IORESOURCE_IRQ, }, - [2] = { - /* DRCMR for RX */ - .start = 15, - .end = 15, - .flags = IORESOURCE_DMA, - }, - [3] = { - /* DRCMR for TX */ - .start = 16, - .end = 16, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa27x_device_ssp2 = { @@ -826,18 +747,6 @@ static struct resource pxa27x_resource_ssp3[] = { .end = IRQ_SSP3, .flags = IORESOURCE_IRQ, }, - [2] = { - /* DRCMR for RX */ - .start = 66, - .end = 66, - .flags = IORESOURCE_DMA, - }, - [3] = { - /* DRCMR for TX */ - .start = 67, - .end = 67, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa27x_device_ssp3 = { @@ -894,16 +803,6 @@ static struct resource pxa3xx_resources_mci2[] = { .end = IRQ_MMC2, .flags = IORESOURCE_IRQ, }, - [2] = { - .start = 93, - .end = 93, - .flags = IORESOURCE_DMA, - }, - [3] = { - .start = 94, - .end = 94, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa3xx_device_mci2 = { @@ -933,16 +832,6 @@ static struct resource pxa3xx_resources_mci3[] = { .end = IRQ_MMC3, .flags = IORESOURCE_IRQ, }, - [2] = { - .start = 100, - .end = 100, - .flags = IORESOURCE_DMA, - }, - [3] = { - .start = 101, - .end = 101, - .flags = IORESOURCE_DMA, - }, }; struct platform_device pxa3xx_device_mci3 = { @@ -1020,18 +909,6 @@ static struct resource pxa3xx_resources_nand[] = { .end = IRQ_NAND, .flags = IORESOURCE_IRQ, }, - [2] = { - /* DRCMR for Data DMA */ - .start = 97, - .end = 97, - .flags = IORESOURCE_DMA, - }, - [3] = { - /* DRCMR for Command DMA */ - .start = 99, - .end = 99, - .flags = IORESOURCE_DMA, - }, }; static u64 pxa3xx_nand_dma_mask = DMA_BIT_MASK(32); @@ -1065,18 +942,6 @@ static struct resource pxa3xx_resource_ssp4[] = { .end = IRQ_SSP4, .flags = IORESOURCE_IRQ, }, - [2] = { - /* DRCMR for RX */ - .start = 2, - .end = 2, - .flags = IORESOURCE_DMA, - }, - [3] = { - /* DRCMR for TX */ - .start = 3, - .end = 3, - .flags = IORESOURCE_DMA, - }, }; /* @@ -1202,11 +1067,6 @@ void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info) platform_device_add(pd); } -static struct mmp_dma_platdata pxa_dma_pdata = { - .dma_channels = 0, - .nb_requestors = 0, -}; - static struct resource pxa_dma_resource[] = { [0] = { .start = 0x40000000, @@ -1233,9 +1093,7 @@ static struct platform_device pxa2xx_pxa_dma = { .resource = pxa_dma_resource, }; -void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors) +void __init pxa2xx_set_dmac_info(struct mmp_dma_platdata *dma_pdata) { - pxa_dma_pdata.dma_channels = nb_channels; - pxa_dma_pdata.nb_requestors = nb_requestors; - pxa_register_device(&pxa2xx_pxa_dma, &pxa_dma_pdata); + pxa_register_device(&pxa2xx_pxa_dma, dma_pdata); } diff --git a/arch/arm/mach-pxa/devices.h b/arch/arm/mach-pxa/devices.h index 11263f7c455b..498b07bc6a3e 100644 --- a/arch/arm/mach-pxa/devices.h +++ b/arch/arm/mach-pxa/devices.h @@ -1,4 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#define PDMA_FILTER_PARAM(_prio, _requestor) (&(struct pxad_param) { \ + .prio = PXAD_PRIO_##_prio, .drcmr = _requestor }) +struct mmp_dma_platdata; + extern struct platform_device pxa_device_pmu; extern struct platform_device pxa_device_mci; extern struct platform_device pxa3xx_device_mci2; @@ -55,7 +59,7 @@ extern struct platform_device pxa3xx_device_gpio; extern struct platform_device pxa93x_device_gpio; void __init pxa_register_device(struct platform_device *dev, void *data); -void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors); +void __init pxa2xx_set_dmac_info(struct mmp_dma_platdata *dma_pdata); struct i2c_pxa_platform_data; extern void pxa_set_i2c_info(struct i2c_pxa_platform_data *info); diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c index 49022ad338e9..29be04c6cc48 100644 --- a/arch/arm/mach-pxa/em-x270.c +++ b/arch/arm/mach-pxa/em-x270.c @@ -346,7 +346,6 @@ struct platform_nand_data em_x270_nand_platdata = { .chip_delay = 20, }, .ctrl = { - .hwcontrol = 0, .dev_ready = em_x270_nand_device_ready, .select_chip = 0, .cmd_ctrl = em_x270_nand_cmd_ctl, diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c index ba431fad5c47..ab8808ce7e21 100644 --- a/arch/arm/mach-pxa/pxa25x.c +++ b/arch/arm/mach-pxa/pxa25x.c @@ -16,6 +16,8 @@ * initialization stuff for PXA machines which can be overridden later if * need be. */ +#include <linux/dmaengine.h> +#include <linux/dma/pxa-dma.h> #include <linux/gpio.h> #include <linux/gpio-pxa.h> #include <linux/module.h> @@ -26,6 +28,7 @@ #include <linux/syscore_ops.h> #include <linux/irq.h> #include <linux/irqchip.h> +#include <linux/platform_data/mmp_dma.h> #include <asm/mach/map.h> #include <asm/suspend.h> @@ -201,6 +204,39 @@ static struct platform_device *pxa25x_devices[] __initdata = { &pxa_device_asoc_platform, }; +static const struct dma_slave_map pxa25x_slave_map[] = { + /* PXA25x, PXA27x and PXA3xx common entries */ + { "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) }, + { "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) }, + { "pxa2xx-ac97", "pcm_pcm_aux_mono_out", + PDMA_FILTER_PARAM(LOWEST, 10) }, + { "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) }, + { "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) }, + { "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 13) }, + { "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 14) }, + { "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 15) }, + { "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 16) }, + { "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) }, + { "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) }, + { "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) }, + { "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) }, + + /* PXA25x specific map */ + { "pxa25x-ssp.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) }, + { "pxa25x-ssp.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) }, + { "pxa25x-nssp.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) }, + { "pxa25x-nssp.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) }, + { "pxa25x-nssp.2", "rx", PDMA_FILTER_PARAM(LOWEST, 23) }, + { "pxa25x-nssp.2", "tx", PDMA_FILTER_PARAM(LOWEST, 24) }, +}; + +static struct mmp_dma_platdata pxa25x_dma_pdata = { + .dma_channels = 16, + .nb_requestors = 40, + .slave_map = pxa25x_slave_map, + .slave_map_cnt = ARRAY_SIZE(pxa25x_slave_map), +}; + static int __init pxa25x_init(void) { int ret = 0; @@ -215,7 +251,7 @@ static int __init pxa25x_init(void) register_syscore_ops(&pxa2xx_mfp_syscore_ops); if (!of_have_populated_dt()) { - pxa2xx_set_dmac_info(16, 40); + pxa2xx_set_dmac_info(&pxa25x_dma_pdata); pxa_register_device(&pxa25x_device_gpio, &pxa25x_gpio_info); ret = platform_add_devices(pxa25x_devices, ARRAY_SIZE(pxa25x_devices)); diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c index 0c06f383ad52..5a8990a9313d 100644 --- a/arch/arm/mach-pxa/pxa27x.c +++ b/arch/arm/mach-pxa/pxa27x.c @@ -11,6 +11,8 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/dmaengine.h> +#include <linux/dma/pxa-dma.h> #include <linux/gpio.h> #include <linux/gpio-pxa.h> #include <linux/module.h> @@ -23,6 +25,7 @@ #include <linux/io.h> #include <linux/irq.h> #include <linux/platform_data/i2c-pxa.h> +#include <linux/platform_data/mmp_dma.h> #include <asm/mach/map.h> #include <mach/hardware.h> @@ -297,6 +300,40 @@ static struct platform_device *devices[] __initdata = { &pxa27x_device_pwm1, }; +static const struct dma_slave_map pxa27x_slave_map[] = { + /* PXA25x, PXA27x and PXA3xx common entries */ + { "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) }, + { "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) }, + { "pxa2xx-ac97", "pcm_pcm_aux_mono_out", + PDMA_FILTER_PARAM(LOWEST, 10) }, + { "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) }, + { "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) }, + { "pxa-ssp-dai.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) }, + { "pxa-ssp-dai.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) }, + { "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) }, + { "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) }, + { "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) }, + { "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) }, + { "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) }, + { "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) }, + { "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 66) }, + { "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 67) }, + + /* PXA27x specific map */ + { "pxa2xx-i2s", "rx", PDMA_FILTER_PARAM(LOWEST, 2) }, + { "pxa2xx-i2s", "tx", PDMA_FILTER_PARAM(LOWEST, 3) }, + { "pxa27x-camera.0", "CI_Y", PDMA_FILTER_PARAM(HIGHEST, 68) }, + { "pxa27x-camera.0", "CI_U", PDMA_FILTER_PARAM(HIGHEST, 69) }, + { "pxa27x-camera.0", "CI_V", PDMA_FILTER_PARAM(HIGHEST, 70) }, +}; + +static struct mmp_dma_platdata pxa27x_dma_pdata = { + .dma_channels = 32, + .nb_requestors = 75, + .slave_map = pxa27x_slave_map, + .slave_map_cnt = ARRAY_SIZE(pxa27x_slave_map), +}; + static int __init pxa27x_init(void) { int ret = 0; @@ -313,7 +350,7 @@ static int __init pxa27x_init(void) if (!of_have_populated_dt()) { pxa_register_device(&pxa27x_device_gpio, &pxa27x_gpio_info); - pxa2xx_set_dmac_info(32, 75); + pxa2xx_set_dmac_info(&pxa27x_dma_pdata); ret = platform_add_devices(devices, ARRAY_SIZE(devices)); } diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c index 8c64f93b669b..df9c8970adcf 100644 --- a/arch/arm/mach-pxa/pxa3xx.c +++ b/arch/arm/mach-pxa/pxa3xx.c @@ -12,6 +12,8 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/dmaengine.h> +#include <linux/dma/pxa-dma.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> @@ -24,6 +26,7 @@ #include <linux/of.h> #include <linux/syscore_ops.h> #include <linux/platform_data/i2c-pxa.h> +#include <linux/platform_data/mmp_dma.h> #include <asm/mach/map.h> #include <asm/suspend.h> @@ -421,6 +424,42 @@ static struct platform_device *devices[] __initdata = { &pxa27x_device_pwm1, }; +static const struct dma_slave_map pxa3xx_slave_map[] = { + /* PXA25x, PXA27x and PXA3xx common entries */ + { "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) }, + { "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) }, + { "pxa2xx-ac97", "pcm_pcm_aux_mono_out", + PDMA_FILTER_PARAM(LOWEST, 10) }, + { "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) }, + { "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) }, + { "pxa-ssp-dai.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) }, + { "pxa-ssp-dai.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) }, + { "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) }, + { "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) }, + { "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) }, + { "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) }, + { "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) }, + { "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) }, + { "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 66) }, + { "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 67) }, + + /* PXA3xx specific map */ + { "pxa-ssp-dai.3", "rx", PDMA_FILTER_PARAM(LOWEST, 2) }, + { "pxa-ssp-dai.3", "tx", PDMA_FILTER_PARAM(LOWEST, 3) }, + { "pxa2xx-mci.1", "rx", PDMA_FILTER_PARAM(LOWEST, 93) }, + { "pxa2xx-mci.1", "tx", PDMA_FILTER_PARAM(LOWEST, 94) }, + { "pxa3xx-nand", "data", PDMA_FILTER_PARAM(LOWEST, 97) }, + { "pxa2xx-mci.2", "rx", PDMA_FILTER_PARAM(LOWEST, 100) }, + { "pxa2xx-mci.2", "tx", PDMA_FILTER_PARAM(LOWEST, 101) }, +}; + +static struct mmp_dma_platdata pxa3xx_dma_pdata = { + .dma_channels = 32, + .nb_requestors = 100, + .slave_map = pxa3xx_slave_map, + .slave_map_cnt = ARRAY_SIZE(pxa3xx_slave_map), +}; + static int __init pxa3xx_init(void) { int ret = 0; @@ -456,7 +495,7 @@ static int __init pxa3xx_init(void) if (of_have_populated_dt()) return 0; - pxa2xx_set_dmac_info(32, 100); + pxa2xx_set_dmac_info(&pxa3xx_dma_pdata); ret = platform_add_devices(devices, ARRAY_SIZE(devices)); if (ret) return ret; diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 39aef4876ed4..04b2f22c2739 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -212,7 +212,7 @@ static DEFINE_MUTEX(ecard_mutex); */ static void ecard_init_pgtables(struct mm_struct *mm) { - struct vm_area_struct vma; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, VM_EXEC); /* We want to set up the page tables for the following mapping: * Virtual Physical @@ -237,9 +237,6 @@ static void ecard_init_pgtables(struct mm_struct *mm) memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE)); - vma.vm_flags = VM_EXEC; - vma.vm_mm = mm; - flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE); flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE); } diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 96a7b6cf459b..b169e580bf82 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -702,7 +702,6 @@ config ARM_THUMBEE config ARM_VIRT_EXT bool - depends on MMU default y if CPU_V7 help Enable the kernel to make use of the ARM Virtualization diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index be0fa7e39c26..66566472c153 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -594,7 +594,7 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size, struct page *page; void *ptr = NULL; - page = dma_alloc_from_contiguous(dev, count, order, gfp); + page = dma_alloc_from_contiguous(dev, count, order, gfp & __GFP_NOWARN); if (!page) return NULL; @@ -1151,6 +1151,11 @@ int arm_dma_supported(struct device *dev, u64 mask) return __dma_supported(dev, mask, false); } +static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent) +{ + return coherent ? &arm_coherent_dma_ops : &arm_dma_ops; +} + #ifdef CONFIG_ARM_DMA_USE_IOMMU static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs) @@ -1294,7 +1299,8 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, unsigned long order = get_order(size); struct page *page; - page = dma_alloc_from_contiguous(dev, count, order, gfp); + page = dma_alloc_from_contiguous(dev, count, order, + gfp & __GFP_NOWARN); if (!page) goto error; @@ -2296,7 +2302,7 @@ void arm_iommu_detach_device(struct device *dev) iommu_detach_device(mapping->domain, dev); kref_put(&mapping->kref, release_iommu_mapping); to_dma_iommu_mapping(dev) = NULL; - set_dma_ops(dev, NULL); + set_dma_ops(dev, arm_get_dma_map_ops(dev->archdata.dma_coherent)); pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev)); } @@ -2357,11 +2363,6 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { } #endif /* CONFIG_ARM_DMA_USE_IOMMU */ -static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent) -{ - return coherent ? &arm_coherent_dma_ops : &arm_dma_ops; -} - void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 84becc911ee3..3232afb6fdc0 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -224,12 +224,12 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) return vma->vm_flags & mask ? false : true; } -static int __kprobes +static vm_fault_t __kprobes __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, unsigned int flags, struct task_struct *tsk) { struct vm_area_struct *vma; - int fault; + vm_fault_t fault; vma = find_vma(mm, addr); fault = VM_FAULT_BADMAP; @@ -264,7 +264,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { struct task_struct *tsk; struct mm_struct *mm; - int fault, sig, code; + int sig, code; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (notify_page_fault(regs, fsr)) diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 5dd6c58d653b..7d67c70bbded 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -53,7 +53,8 @@ static inline bool security_extensions_enabled(void) { /* Check CPUID Identification Scheme before ID_PFR1 read */ if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) - return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4); + return cpuid_feature_extract(CPUID_EXT_PFR1, 4) || + cpuid_feature_extract(CPUID_EXT_PFR1, 20); return 0; } diff --git a/arch/arm/mm/tcm.h b/arch/arm/mm/tcm.h index 8015ad434a40..24101925fe64 100644 --- a/arch/arm/mm/tcm.h +++ b/arch/arm/mm/tcm.h @@ -11,7 +11,7 @@ void __init tcm_init(void); #else /* No TCM support, just blank inlines to be optimized out */ -inline void tcm_init(void) +static inline void tcm_init(void) { } #endif diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index f6a62ae44a65..25b3ee85066e 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -22,6 +22,7 @@ #include <asm/cacheflush.h> #include <asm/hwcap.h> #include <asm/opcodes.h> +#include <asm/system_info.h> #include "bpf_jit_32.h" @@ -47,32 +48,73 @@ * The callee saved registers depends on whether frame pointers are enabled. * With frame pointers (to be compliant with the ABI): * - * high - * original ARM_SP => +------------------+ \ - * | pc | | - * current ARM_FP => +------------------+ } callee saved registers - * |r4-r8,r10,fp,ip,lr| | - * +------------------+ / - * low + * high + * original ARM_SP => +--------------+ \ + * | pc | | + * current ARM_FP => +--------------+ } callee saved registers + * |r4-r9,fp,ip,lr| | + * +--------------+ / + * low * * Without frame pointers: * - * high - * original ARM_SP => +------------------+ - * | r4-r8,r10,fp,lr | callee saved registers - * current ARM_FP => +------------------+ - * low + * high + * original ARM_SP => +--------------+ + * | r4-r9,fp,lr | callee saved registers + * current ARM_FP => +--------------+ + * low * * When popping registers off the stack at the end of a BPF function, we * reference them via the current ARM_FP register. */ #define CALLEE_MASK (1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \ - 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \ + 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R9 | \ 1 << ARM_FP) #define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR) #define CALLEE_POP_MASK (CALLEE_MASK | 1 << ARM_PC) -#define STACK_OFFSET(k) (k) +enum { + /* Stack layout - these are offsets from (top of stack - 4) */ + BPF_R2_HI, + BPF_R2_LO, + BPF_R3_HI, + BPF_R3_LO, + BPF_R4_HI, + BPF_R4_LO, + BPF_R5_HI, + BPF_R5_LO, + BPF_R7_HI, + BPF_R7_LO, + BPF_R8_HI, + BPF_R8_LO, + BPF_R9_HI, + BPF_R9_LO, + BPF_FP_HI, + BPF_FP_LO, + BPF_TC_HI, + BPF_TC_LO, + BPF_AX_HI, + BPF_AX_LO, + /* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4, + * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9, + * BPF_REG_FP and Tail call counts. + */ + BPF_JIT_SCRATCH_REGS, +}; + +/* + * Negative "register" values indicate the register is stored on the stack + * and are the offset from the top of the eBPF JIT scratch space. + */ +#define STACK_OFFSET(k) (-4 - (k) * 4) +#define SCRATCH_SIZE (BPF_JIT_SCRATCH_REGS * 4) + +#ifdef CONFIG_FRAME_POINTER +#define EBPF_SCRATCH_TO_ARM_FP(x) ((x) - 4 * hweight16(CALLEE_PUSH_MASK) - 4) +#else +#define EBPF_SCRATCH_TO_ARM_FP(x) (x) +#endif + #define TMP_REG_1 (MAX_BPF_JIT_REG + 0) /* TEMP Register 1 */ #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* TEMP Register 2 */ #define TCALL_CNT (MAX_BPF_JIT_REG + 2) /* Tail Call Count */ @@ -94,35 +136,35 @@ * scratch memory space and we have to build eBPF 64 bit register from those. * */ -static const u8 bpf2a32[][2] = { +static const s8 bpf2a32[][2] = { /* return value from in-kernel function, and exit value from eBPF */ [BPF_REG_0] = {ARM_R1, ARM_R0}, /* arguments from eBPF program to in-kernel function */ [BPF_REG_1] = {ARM_R3, ARM_R2}, /* Stored on stack scratch space */ - [BPF_REG_2] = {STACK_OFFSET(0), STACK_OFFSET(4)}, - [BPF_REG_3] = {STACK_OFFSET(8), STACK_OFFSET(12)}, - [BPF_REG_4] = {STACK_OFFSET(16), STACK_OFFSET(20)}, - [BPF_REG_5] = {STACK_OFFSET(24), STACK_OFFSET(28)}, + [BPF_REG_2] = {STACK_OFFSET(BPF_R2_HI), STACK_OFFSET(BPF_R2_LO)}, + [BPF_REG_3] = {STACK_OFFSET(BPF_R3_HI), STACK_OFFSET(BPF_R3_LO)}, + [BPF_REG_4] = {STACK_OFFSET(BPF_R4_HI), STACK_OFFSET(BPF_R4_LO)}, + [BPF_REG_5] = {STACK_OFFSET(BPF_R5_HI), STACK_OFFSET(BPF_R5_LO)}, /* callee saved registers that in-kernel function will preserve */ [BPF_REG_6] = {ARM_R5, ARM_R4}, /* Stored on stack scratch space */ - [BPF_REG_7] = {STACK_OFFSET(32), STACK_OFFSET(36)}, - [BPF_REG_8] = {STACK_OFFSET(40), STACK_OFFSET(44)}, - [BPF_REG_9] = {STACK_OFFSET(48), STACK_OFFSET(52)}, + [BPF_REG_7] = {STACK_OFFSET(BPF_R7_HI), STACK_OFFSET(BPF_R7_LO)}, + [BPF_REG_8] = {STACK_OFFSET(BPF_R8_HI), STACK_OFFSET(BPF_R8_LO)}, + [BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)}, /* Read only Frame Pointer to access Stack */ - [BPF_REG_FP] = {STACK_OFFSET(56), STACK_OFFSET(60)}, + [BPF_REG_FP] = {STACK_OFFSET(BPF_FP_HI), STACK_OFFSET(BPF_FP_LO)}, /* Temporary Register for internal BPF JIT, can be used * for constant blindings and others. */ [TMP_REG_1] = {ARM_R7, ARM_R6}, - [TMP_REG_2] = {ARM_R10, ARM_R8}, + [TMP_REG_2] = {ARM_R9, ARM_R8}, /* Tail call count. Stored on stack scratch space. */ - [TCALL_CNT] = {STACK_OFFSET(64), STACK_OFFSET(68)}, + [TCALL_CNT] = {STACK_OFFSET(BPF_TC_HI), STACK_OFFSET(BPF_TC_LO)}, /* temporary register for blinding constants. * Stored on stack scratch space. */ - [BPF_REG_AX] = {STACK_OFFSET(72), STACK_OFFSET(76)}, + [BPF_REG_AX] = {STACK_OFFSET(BPF_AX_HI), STACK_OFFSET(BPF_AX_LO)}, }; #define dst_lo dst[1] @@ -151,6 +193,7 @@ struct jit_ctx { unsigned int idx; unsigned int prologue_bytes; unsigned int epilogue_offset; + unsigned int cpu_architecture; u32 flags; u32 *offsets; u32 *target; @@ -196,9 +239,55 @@ static inline void emit(u32 inst, struct jit_ctx *ctx) } /* + * This is rather horrid, but necessary to convert an integer constant + * to an immediate operand for the opcodes, and be able to detect at + * build time whether the constant can't be converted (iow, usable in + * BUILD_BUG_ON()). + */ +#define imm12val(v, s) (rol32(v, (s)) | (s) << 7) +#define const_imm8m(x) \ + ({ int r; \ + u32 v = (x); \ + if (!(v & ~0x000000ff)) \ + r = imm12val(v, 0); \ + else if (!(v & ~0xc000003f)) \ + r = imm12val(v, 2); \ + else if (!(v & ~0xf000000f)) \ + r = imm12val(v, 4); \ + else if (!(v & ~0xfc000003)) \ + r = imm12val(v, 6); \ + else if (!(v & ~0xff000000)) \ + r = imm12val(v, 8); \ + else if (!(v & ~0x3fc00000)) \ + r = imm12val(v, 10); \ + else if (!(v & ~0x0ff00000)) \ + r = imm12val(v, 12); \ + else if (!(v & ~0x03fc0000)) \ + r = imm12val(v, 14); \ + else if (!(v & ~0x00ff0000)) \ + r = imm12val(v, 16); \ + else if (!(v & ~0x003fc000)) \ + r = imm12val(v, 18); \ + else if (!(v & ~0x000ff000)) \ + r = imm12val(v, 20); \ + else if (!(v & ~0x0003fc00)) \ + r = imm12val(v, 22); \ + else if (!(v & ~0x0000ff00)) \ + r = imm12val(v, 24); \ + else if (!(v & ~0x00003fc0)) \ + r = imm12val(v, 26); \ + else if (!(v & ~0x00000ff0)) \ + r = imm12val(v, 28); \ + else if (!(v & ~0x000003fc)) \ + r = imm12val(v, 30); \ + else \ + r = -1; \ + r; }) + +/* * Checks if immediate value can be converted to imm12(12 bits) value. */ -static int16_t imm8m(u32 x) +static int imm8m(u32 x) { u32 rot; @@ -208,6 +297,38 @@ static int16_t imm8m(u32 x) return -1; } +#define imm8m(x) (__builtin_constant_p(x) ? const_imm8m(x) : imm8m(x)) + +static u32 arm_bpf_ldst_imm12(u32 op, u8 rt, u8 rn, s16 imm12) +{ + op |= rt << 12 | rn << 16; + if (imm12 >= 0) + op |= ARM_INST_LDST__U; + else + imm12 = -imm12; + return op | (imm12 & ARM_INST_LDST__IMM12); +} + +static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8) +{ + op |= rt << 12 | rn << 16; + if (imm8 >= 0) + op |= ARM_INST_LDST__U; + else + imm8 = -imm8; + return op | (imm8 & 0xf0) << 4 | (imm8 & 0x0f); +} + +#define ARM_LDR_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_LDR_I, rt, rn, off) +#define ARM_LDRB_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_LDRB_I, rt, rn, off) +#define ARM_LDRD_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRD_I, rt, rn, off) +#define ARM_LDRH_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRH_I, rt, rn, off) + +#define ARM_STR_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_STR_I, rt, rn, off) +#define ARM_STRB_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_STRB_I, rt, rn, off) +#define ARM_STRD_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_STRD_I, rt, rn, off) +#define ARM_STRH_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_STRH_I, rt, rn, off) + /* * Initializes the JIT space with undefined instructions. */ @@ -227,19 +348,10 @@ static void jit_fill_hole(void *area, unsigned int size) #define STACK_ALIGNMENT 4 #endif -/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4, - * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9, - * BPF_REG_FP and Tail call counts. - */ -#define SCRATCH_SIZE 80 - /* total stack size used in JITed code */ #define _STACK_SIZE (ctx->prog->aux->stack_depth + SCRATCH_SIZE) #define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT) -/* Get the offset of eBPF REGISTERs stored on scratch space. */ -#define STACK_VAR(off) (STACK_SIZE - off) - #if __LINUX_ARM_ARCH__ < 7 static u16 imm_offset(u32 k, struct jit_ctx *ctx) @@ -355,7 +467,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx) static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op) { - const u8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp = bpf2a32[TMP_REG_1]; #if __LINUX_ARM_ARCH__ == 7 if (elf_hwcap & HWCAP_IDIVA) { @@ -402,44 +514,110 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op) emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx); } -/* Checks whether BPF register is on scratch stack space or not. */ -static inline bool is_on_stack(u8 bpf_reg) +/* Is the translated BPF register on stack? */ +static bool is_stacked(s8 reg) +{ + return reg < 0; +} + +/* If a BPF register is on the stack (stk is true), load it to the + * supplied temporary register and return the temporary register + * for subsequent operations, otherwise just use the CPU register. + */ +static s8 arm_bpf_get_reg32(s8 reg, s8 tmp, struct jit_ctx *ctx) +{ + if (is_stacked(reg)) { + emit(ARM_LDR_I(tmp, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg)), ctx); + reg = tmp; + } + return reg; +} + +static const s8 *arm_bpf_get_reg64(const s8 *reg, const s8 *tmp, + struct jit_ctx *ctx) { - static u8 stack_regs[] = {BPF_REG_AX, BPF_REG_3, BPF_REG_4, BPF_REG_5, - BPF_REG_7, BPF_REG_8, BPF_REG_9, TCALL_CNT, - BPF_REG_2, BPF_REG_FP}; - int i, reg_len = sizeof(stack_regs); - - for (i = 0 ; i < reg_len ; i++) { - if (bpf_reg == stack_regs[i]) - return true; + if (is_stacked(reg[1])) { + if (__LINUX_ARM_ARCH__ >= 6 || + ctx->cpu_architecture >= CPU_ARCH_ARMv5TE) { + emit(ARM_LDRD_I(tmp[1], ARM_FP, + EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx); + } else { + emit(ARM_LDR_I(tmp[1], ARM_FP, + EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx); + emit(ARM_LDR_I(tmp[0], ARM_FP, + EBPF_SCRATCH_TO_ARM_FP(reg[0])), ctx); + } + reg = tmp; + } + return reg; +} + +/* If a BPF register is on the stack (stk is true), save the register + * back to the stack. If the source register is not the same, then + * move it into the correct register. + */ +static void arm_bpf_put_reg32(s8 reg, s8 src, struct jit_ctx *ctx) +{ + if (is_stacked(reg)) + emit(ARM_STR_I(src, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg)), ctx); + else if (reg != src) + emit(ARM_MOV_R(reg, src), ctx); +} + +static void arm_bpf_put_reg64(const s8 *reg, const s8 *src, + struct jit_ctx *ctx) +{ + if (is_stacked(reg[1])) { + if (__LINUX_ARM_ARCH__ >= 6 || + ctx->cpu_architecture >= CPU_ARCH_ARMv5TE) { + emit(ARM_STRD_I(src[1], ARM_FP, + EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx); + } else { + emit(ARM_STR_I(src[1], ARM_FP, + EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx); + emit(ARM_STR_I(src[0], ARM_FP, + EBPF_SCRATCH_TO_ARM_FP(reg[0])), ctx); + } + } else { + if (reg[1] != src[1]) + emit(ARM_MOV_R(reg[1], src[1]), ctx); + if (reg[0] != src[0]) + emit(ARM_MOV_R(reg[0], src[0]), ctx); } - return false; } -static inline void emit_a32_mov_i(const u8 dst, const u32 val, - bool dstk, struct jit_ctx *ctx) +static inline void emit_a32_mov_i(const s8 dst, const u32 val, + struct jit_ctx *ctx) { - const u8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp = bpf2a32[TMP_REG_1]; - if (dstk) { + if (is_stacked(dst)) { emit_mov_i(tmp[1], val, ctx); - emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(dst)), ctx); + arm_bpf_put_reg32(dst, tmp[1], ctx); } else { emit_mov_i(dst, val, ctx); } } +static void emit_a32_mov_i64(const s8 dst[], u64 val, struct jit_ctx *ctx) +{ + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *rd = is_stacked(dst_lo) ? tmp : dst; + + emit_mov_i(rd[1], (u32)val, ctx); + emit_mov_i(rd[0], val >> 32, ctx); + + arm_bpf_put_reg64(dst, rd, ctx); +} + /* Sign extended move */ -static inline void emit_a32_mov_i64(const bool is64, const u8 dst[], - const u32 val, bool dstk, - struct jit_ctx *ctx) { - u32 hi = 0; +static inline void emit_a32_mov_se_i64(const bool is64, const s8 dst[], + const u32 val, struct jit_ctx *ctx) { + u64 val64 = val; if (is64 && (val & (1<<31))) - hi = (u32)~0; - emit_a32_mov_i(dst_lo, val, dstk, ctx); - emit_a32_mov_i(dst_hi, hi, dstk, ctx); + val64 |= 0xffffffff00000000ULL; + emit_a32_mov_i64(dst, val64, ctx); } static inline void emit_a32_add_r(const u8 dst, const u8 src, @@ -521,75 +699,94 @@ static inline void emit_alu_r(const u8 dst, const u8 src, const bool is64, /* ALU operation (32 bit) * dst = dst (op) src */ -static inline void emit_a32_alu_r(const u8 dst, const u8 src, - bool dstk, bool sstk, +static inline void emit_a32_alu_r(const s8 dst, const s8 src, struct jit_ctx *ctx, const bool is64, const bool hi, const u8 op) { - const u8 *tmp = bpf2a32[TMP_REG_1]; - u8 rn = sstk ? tmp[1] : src; - - if (sstk) - emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src)), ctx); + const s8 *tmp = bpf2a32[TMP_REG_1]; + s8 rn, rd; + rn = arm_bpf_get_reg32(src, tmp[1], ctx); + rd = arm_bpf_get_reg32(dst, tmp[0], ctx); /* ALU operation */ - if (dstk) { - emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx); - emit_alu_r(tmp[0], rn, is64, hi, op, ctx); - emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx); - } else { - emit_alu_r(dst, rn, is64, hi, op, ctx); - } + emit_alu_r(rd, rn, is64, hi, op, ctx); + arm_bpf_put_reg32(dst, rd, ctx); } /* ALU operation (64 bit) */ -static inline void emit_a32_alu_r64(const bool is64, const u8 dst[], - const u8 src[], bool dstk, - bool sstk, struct jit_ctx *ctx, +static inline void emit_a32_alu_r64(const bool is64, const s8 dst[], + const s8 src[], struct jit_ctx *ctx, const u8 op) { - emit_a32_alu_r(dst_lo, src_lo, dstk, sstk, ctx, is64, false, op); - if (is64) - emit_a32_alu_r(dst_hi, src_hi, dstk, sstk, ctx, is64, true, op); - else - emit_a32_mov_i(dst_hi, 0, dstk, ctx); + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rd; + + rd = arm_bpf_get_reg64(dst, tmp, ctx); + if (is64) { + const s8 *rs; + + rs = arm_bpf_get_reg64(src, tmp2, ctx); + + /* ALU operation */ + emit_alu_r(rd[1], rs[1], true, false, op, ctx); + emit_alu_r(rd[0], rs[0], true, true, op, ctx); + } else { + s8 rs; + + rs = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); + + /* ALU operation */ + emit_alu_r(rd[1], rs, true, false, op, ctx); + emit_a32_mov_i(rd[0], 0, ctx); + } + + arm_bpf_put_reg64(dst, rd, ctx); } -/* dst = imm (4 bytes)*/ -static inline void emit_a32_mov_r(const u8 dst, const u8 src, - bool dstk, bool sstk, +/* dst = src (4 bytes)*/ +static inline void emit_a32_mov_r(const s8 dst, const s8 src, struct jit_ctx *ctx) { - const u8 *tmp = bpf2a32[TMP_REG_1]; - u8 rt = sstk ? tmp[0] : src; + const s8 *tmp = bpf2a32[TMP_REG_1]; + s8 rt; - if (sstk) - emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(src)), ctx); - if (dstk) - emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst)), ctx); - else - emit(ARM_MOV_R(dst, rt), ctx); + rt = arm_bpf_get_reg32(src, tmp[0], ctx); + arm_bpf_put_reg32(dst, rt, ctx); } /* dst = src */ -static inline void emit_a32_mov_r64(const bool is64, const u8 dst[], - const u8 src[], bool dstk, - bool sstk, struct jit_ctx *ctx) { - emit_a32_mov_r(dst_lo, src_lo, dstk, sstk, ctx); - if (is64) { +static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], + const s8 src[], + struct jit_ctx *ctx) { + if (!is64) { + emit_a32_mov_r(dst_lo, src_lo, ctx); + /* Zero out high 4 bytes */ + emit_a32_mov_i(dst_hi, 0, ctx); + } else if (__LINUX_ARM_ARCH__ < 6 && + ctx->cpu_architecture < CPU_ARCH_ARMv5TE) { /* complete 8 byte move */ - emit_a32_mov_r(dst_hi, src_hi, dstk, sstk, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); + emit_a32_mov_r(dst_hi, src_hi, ctx); + } else if (is_stacked(src_lo) && is_stacked(dst_lo)) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + + emit(ARM_LDRD_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(src_lo)), ctx); + emit(ARM_STRD_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(dst_lo)), ctx); + } else if (is_stacked(src_lo)) { + emit(ARM_LDRD_I(dst[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(src_lo)), ctx); + } else if (is_stacked(dst_lo)) { + emit(ARM_STRD_I(src[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(dst_lo)), ctx); } else { - /* Zero out high 4 bytes */ - emit_a32_mov_i(dst_hi, 0, dstk, ctx); + emit(ARM_MOV_R(dst[0], src[0]), ctx); + emit(ARM_MOV_R(dst[1], src[1]), ctx); } } /* Shift operations */ -static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk, +static inline void emit_a32_alu_i(const s8 dst, const u32 val, struct jit_ctx *ctx, const u8 op) { - const u8 *tmp = bpf2a32[TMP_REG_1]; - u8 rd = dstk ? tmp[0] : dst; + const s8 *tmp = bpf2a32[TMP_REG_1]; + s8 rd; - if (dstk) - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx); + rd = arm_bpf_get_reg32(dst, tmp[0], ctx); /* Do shift operation */ switch (op) { @@ -604,303 +801,245 @@ static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk, break; } - if (dstk) - emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx); + arm_bpf_put_reg32(dst, rd, ctx); } /* dst = ~dst (64 bit) */ -static inline void emit_a32_neg64(const u8 dst[], bool dstk, +static inline void emit_a32_neg64(const s8 dst[], struct jit_ctx *ctx){ - const u8 *tmp = bpf2a32[TMP_REG_1]; - u8 rd = dstk ? tmp[1] : dst[1]; - u8 rm = dstk ? tmp[0] : dst[0]; + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *rd; /* Setup Operand */ - if (dstk) { - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do Negate Operation */ - emit(ARM_RSBS_I(rd, rd, 0), ctx); - emit(ARM_RSC_I(rm, rm, 0), ctx); + emit(ARM_RSBS_I(rd[1], rd[1], 0), ctx); + emit(ARM_RSC_I(rd[0], rd[0], 0), ctx); - if (dstk) { - emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + arm_bpf_put_reg64(dst, rd, ctx); } /* dst = dst << src */ -static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk, - bool sstk, struct jit_ctx *ctx) { - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; +static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[], + struct jit_ctx *ctx) { + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rd; + s8 rt; /* Setup Operands */ - u8 rt = sstk ? tmp2[1] : src_lo; - u8 rd = dstk ? tmp[1] : dst_lo; - u8 rm = dstk ? tmp[0] : dst_hi; - - if (sstk) - emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx); - if (dstk) { - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); + rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do LSH operation */ emit(ARM_SUB_I(ARM_IP, rt, 32), ctx); emit(ARM_RSB_I(tmp2[0], rt, 32), ctx); - emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx); - emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx); - emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx); - emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_ASL, rt), ctx); - - if (dstk) { - emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx); - } else { - emit(ARM_MOV_R(rd, ARM_LR), ctx); - emit(ARM_MOV_R(rm, ARM_IP), ctx); - } + emit(ARM_MOV_SR(ARM_LR, rd[0], SRTYPE_ASL, rt), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[1], SRTYPE_ASL, ARM_IP), ctx); + emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd[1], SRTYPE_LSR, tmp2[0]), ctx); + emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_ASL, rt), ctx); + + arm_bpf_put_reg32(dst_lo, ARM_LR, ctx); + arm_bpf_put_reg32(dst_hi, ARM_IP, ctx); } /* dst = dst >> src (signed)*/ -static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk, - bool sstk, struct jit_ctx *ctx) { - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; +static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[], + struct jit_ctx *ctx) { + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rd; + s8 rt; + /* Setup Operands */ - u8 rt = sstk ? tmp2[1] : src_lo; - u8 rd = dstk ? tmp[1] : dst_lo; - u8 rm = dstk ? tmp[0] : dst_hi; - - if (sstk) - emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx); - if (dstk) { - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); + rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do the ARSH operation */ emit(ARM_RSB_I(ARM_IP, rt, 32), ctx); emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx); - emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx); - emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx); + emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx); _emit(ARM_COND_MI, ARM_B(0), ctx); - emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASR, tmp2[0]), ctx); - emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_ASR, rt), ctx); - if (dstk) { - emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx); - } else { - emit(ARM_MOV_R(rd, ARM_LR), ctx); - emit(ARM_MOV_R(rm, ARM_IP), ctx); - } + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASR, tmp2[0]), ctx); + emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_ASR, rt), ctx); + + arm_bpf_put_reg32(dst_lo, ARM_LR, ctx); + arm_bpf_put_reg32(dst_hi, ARM_IP, ctx); } /* dst = dst >> src */ -static inline void emit_a32_rsh_r64(const u8 dst[], const u8 src[], bool dstk, - bool sstk, struct jit_ctx *ctx) { - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; +static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[], + struct jit_ctx *ctx) { + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rd; + s8 rt; + /* Setup Operands */ - u8 rt = sstk ? tmp2[1] : src_lo; - u8 rd = dstk ? tmp[1] : dst_lo; - u8 rm = dstk ? tmp[0] : dst_hi; - - if (sstk) - emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx); - if (dstk) { - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); + rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do RSH operation */ emit(ARM_RSB_I(ARM_IP, rt, 32), ctx); emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx); - emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx); - emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx); - emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx); - emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_LSR, rt), ctx); - if (dstk) { - emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx); - } else { - emit(ARM_MOV_R(rd, ARM_LR), ctx); - emit(ARM_MOV_R(rm, ARM_IP), ctx); - } + emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_LSR, tmp2[0]), ctx); + emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_LSR, rt), ctx); + + arm_bpf_put_reg32(dst_lo, ARM_LR, ctx); + arm_bpf_put_reg32(dst_hi, ARM_IP, ctx); } /* dst = dst << val */ -static inline void emit_a32_lsh_i64(const u8 dst[], bool dstk, - const u32 val, struct jit_ctx *ctx){ - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; - /* Setup operands */ - u8 rd = dstk ? tmp[1] : dst_lo; - u8 rm = dstk ? tmp[0] : dst_hi; +static inline void emit_a32_lsh_i64(const s8 dst[], + const u32 val, struct jit_ctx *ctx){ + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rd; - if (dstk) { - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + /* Setup operands */ + rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do LSH operation */ if (val < 32) { - emit(ARM_MOV_SI(tmp2[0], rm, SRTYPE_ASL, val), ctx); - emit(ARM_ORR_SI(rm, tmp2[0], rd, SRTYPE_LSR, 32 - val), ctx); - emit(ARM_MOV_SI(rd, rd, SRTYPE_ASL, val), ctx); + emit(ARM_MOV_SI(tmp2[0], rd[0], SRTYPE_ASL, val), ctx); + emit(ARM_ORR_SI(rd[0], tmp2[0], rd[1], SRTYPE_LSR, 32 - val), ctx); + emit(ARM_MOV_SI(rd[1], rd[1], SRTYPE_ASL, val), ctx); } else { if (val == 32) - emit(ARM_MOV_R(rm, rd), ctx); + emit(ARM_MOV_R(rd[0], rd[1]), ctx); else - emit(ARM_MOV_SI(rm, rd, SRTYPE_ASL, val - 32), ctx); - emit(ARM_EOR_R(rd, rd, rd), ctx); + emit(ARM_MOV_SI(rd[0], rd[1], SRTYPE_ASL, val - 32), ctx); + emit(ARM_EOR_R(rd[1], rd[1], rd[1]), ctx); } - if (dstk) { - emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + arm_bpf_put_reg64(dst, rd, ctx); } /* dst = dst >> val */ -static inline void emit_a32_rsh_i64(const u8 dst[], bool dstk, +static inline void emit_a32_rsh_i64(const s8 dst[], const u32 val, struct jit_ctx *ctx) { - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; - /* Setup operands */ - u8 rd = dstk ? tmp[1] : dst_lo; - u8 rm = dstk ? tmp[0] : dst_hi; + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rd; - if (dstk) { - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + /* Setup operands */ + rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do LSR operation */ if (val < 32) { - emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx); - emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx); - emit(ARM_MOV_SI(rm, rm, SRTYPE_LSR, val), ctx); + emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx); + emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx); + emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx); } else if (val == 32) { - emit(ARM_MOV_R(rd, rm), ctx); - emit(ARM_MOV_I(rm, 0), ctx); + emit(ARM_MOV_R(rd[1], rd[0]), ctx); + emit(ARM_MOV_I(rd[0], 0), ctx); } else { - emit(ARM_MOV_SI(rd, rm, SRTYPE_LSR, val - 32), ctx); - emit(ARM_MOV_I(rm, 0), ctx); + emit(ARM_MOV_SI(rd[1], rd[0], SRTYPE_LSR, val - 32), ctx); + emit(ARM_MOV_I(rd[0], 0), ctx); } - if (dstk) { - emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + arm_bpf_put_reg64(dst, rd, ctx); } /* dst = dst >> val (signed) */ -static inline void emit_a32_arsh_i64(const u8 dst[], bool dstk, +static inline void emit_a32_arsh_i64(const s8 dst[], const u32 val, struct jit_ctx *ctx){ - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; - /* Setup operands */ - u8 rd = dstk ? tmp[1] : dst_lo; - u8 rm = dstk ? tmp[0] : dst_hi; - - if (dstk) { - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rd; + + /* Setup operands */ + rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do ARSH operation */ if (val < 32) { - emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx); - emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx); - emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, val), ctx); + emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx); + emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx); + emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx); } else if (val == 32) { - emit(ARM_MOV_R(rd, rm), ctx); - emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx); + emit(ARM_MOV_R(rd[1], rd[0]), ctx); + emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, 31), ctx); } else { - emit(ARM_MOV_SI(rd, rm, SRTYPE_ASR, val - 32), ctx); - emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx); + emit(ARM_MOV_SI(rd[1], rd[0], SRTYPE_ASR, val - 32), ctx); + emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, 31), ctx); } - if (dstk) { - emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + arm_bpf_put_reg64(dst, rd, ctx); } -static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk, - bool sstk, struct jit_ctx *ctx) { - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; +static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[], + struct jit_ctx *ctx) { + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rd, *rt; + /* Setup operands for multiplication */ - u8 rd = dstk ? tmp[1] : dst_lo; - u8 rm = dstk ? tmp[0] : dst_hi; - u8 rt = sstk ? tmp2[1] : src_lo; - u8 rn = sstk ? tmp2[0] : src_hi; - - if (dstk) { - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } - if (sstk) { - emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx); - emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_hi)), ctx); - } + rd = arm_bpf_get_reg64(dst, tmp, ctx); + rt = arm_bpf_get_reg64(src, tmp2, ctx); /* Do Multiplication */ - emit(ARM_MUL(ARM_IP, rd, rn), ctx); - emit(ARM_MUL(ARM_LR, rm, rt), ctx); + emit(ARM_MUL(ARM_IP, rd[1], rt[0]), ctx); + emit(ARM_MUL(ARM_LR, rd[0], rt[1]), ctx); emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx); - emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx); - emit(ARM_ADD_R(rm, ARM_LR, rm), ctx); - if (dstk) { - emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); - } else { - emit(ARM_MOV_R(rd, ARM_IP), ctx); - } + emit(ARM_UMULL(ARM_IP, rd[0], rd[1], rt[1]), ctx); + emit(ARM_ADD_R(rd[0], ARM_LR, rd[0]), ctx); + + arm_bpf_put_reg32(dst_lo, ARM_IP, ctx); + arm_bpf_put_reg32(dst_hi, rd[0], ctx); } /* *(size *)(dst + off) = src */ -static inline void emit_str_r(const u8 dst, const u8 src, bool dstk, - const s32 off, struct jit_ctx *ctx, const u8 sz){ - const u8 *tmp = bpf2a32[TMP_REG_1]; - u8 rd = dstk ? tmp[1] : dst; - - if (dstk) - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx); - if (off) { - emit_a32_mov_i(tmp[0], off, false, ctx); - emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx); +static inline void emit_str_r(const s8 dst, const s8 src[], + s32 off, struct jit_ctx *ctx, const u8 sz){ + const s8 *tmp = bpf2a32[TMP_REG_1]; + s32 off_max; + s8 rd; + + rd = arm_bpf_get_reg32(dst, tmp[1], ctx); + + if (sz == BPF_H) + off_max = 0xff; + else + off_max = 0xfff; + + if (off < 0 || off > off_max) { + emit_a32_mov_i(tmp[0], off, ctx); + emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx); rd = tmp[0]; + off = 0; } switch (sz) { - case BPF_W: - /* Store a Word */ - emit(ARM_STR_I(src, rd, 0), ctx); + case BPF_B: + /* Store a Byte */ + emit(ARM_STRB_I(src_lo, rd, off), ctx); break; case BPF_H: /* Store a HalfWord */ - emit(ARM_STRH_I(src, rd, 0), ctx); + emit(ARM_STRH_I(src_lo, rd, off), ctx); break; - case BPF_B: - /* Store a Byte */ - emit(ARM_STRB_I(src, rd, 0), ctx); + case BPF_W: + /* Store a Word */ + emit(ARM_STR_I(src_lo, rd, off), ctx); + break; + case BPF_DW: + /* Store a Double Word */ + emit(ARM_STR_I(src_lo, rd, off), ctx); + emit(ARM_STR_I(src_hi, rd, off + 4), ctx); break; } } /* dst = *(size*)(src + off) */ -static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk, +static inline void emit_ldx_r(const s8 dst[], const s8 src, s32 off, struct jit_ctx *ctx, const u8 sz){ - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *rd = dstk ? tmp : dst; - u8 rm = src; + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *rd = is_stacked(dst_lo) ? tmp : dst; + s8 rm = src; s32 off_max; if (sz == BPF_H) @@ -909,7 +1048,7 @@ static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk, off_max = 0xfff; if (off < 0 || off > off_max) { - emit_a32_mov_i(tmp[0], off, false, ctx); + emit_a32_mov_i(tmp[0], off, ctx); emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx); rm = tmp[0]; off = 0; @@ -921,17 +1060,17 @@ static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk, case BPF_B: /* Load a Byte */ emit(ARM_LDRB_I(rd[1], rm, off), ctx); - emit_a32_mov_i(dst[0], 0, dstk, ctx); + emit_a32_mov_i(rd[0], 0, ctx); break; case BPF_H: /* Load a HalfWord */ emit(ARM_LDRH_I(rd[1], rm, off), ctx); - emit_a32_mov_i(dst[0], 0, dstk, ctx); + emit_a32_mov_i(rd[0], 0, ctx); break; case BPF_W: /* Load a Word */ emit(ARM_LDR_I(rd[1], rm, off), ctx); - emit_a32_mov_i(dst[0], 0, dstk, ctx); + emit_a32_mov_i(rd[0], 0, ctx); break; case BPF_DW: /* Load a Double Word */ @@ -939,10 +1078,7 @@ static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk, emit(ARM_LDR_I(rd[0], rm, off + 4), ctx); break; } - if (dstk) - emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx); - if (dstk && sz == BPF_DW) - emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx); + arm_bpf_put_reg64(dst, rd, ctx); } /* Arithmatic Operation */ @@ -981,64 +1117,66 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) { /* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */ - const u8 *r2 = bpf2a32[BPF_REG_2]; - const u8 *r3 = bpf2a32[BPF_REG_3]; - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; - const u8 *tcc = bpf2a32[TCALL_CNT]; + const s8 *r2 = bpf2a32[BPF_REG_2]; + const s8 *r3 = bpf2a32[BPF_REG_3]; + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *tcc = bpf2a32[TCALL_CNT]; + const s8 *tc; const int idx0 = ctx->idx; #define cur_offset (ctx->idx - idx0) #define jmp_offset (out_offset - (cur_offset) - 2) - u32 off, lo, hi; + u32 lo, hi; + s8 r_array, r_index; + int off; /* if (index >= array->map.max_entries) * goto out; */ + BUILD_BUG_ON(offsetof(struct bpf_array, map.max_entries) > + ARM_INST_LDST__IMM12); off = offsetof(struct bpf_array, map.max_entries); - /* array->map.max_entries */ - emit_a32_mov_i(tmp[1], off, false, ctx); - emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx); - emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx); + r_array = arm_bpf_get_reg32(r2[1], tmp2[0], ctx); /* index is 32-bit for arrays */ - emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx); + r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx); + /* array->map.max_entries */ + emit(ARM_LDR_I(tmp[1], r_array, off), ctx); /* index >= array->map.max_entries */ - emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx); + emit(ARM_CMP_R(r_index, tmp[1]), ctx); _emit(ARM_COND_CS, ARM_B(jmp_offset), ctx); + /* tmp2[0] = array, tmp2[1] = index */ + /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; * tail_call_cnt++; */ lo = (u32)MAX_TAIL_CALL_CNT; hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32); - emit(ARM_LDR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx); - emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx); - emit(ARM_CMP_I(tmp[0], hi), ctx); - _emit(ARM_COND_EQ, ARM_CMP_I(tmp[1], lo), ctx); + tc = arm_bpf_get_reg64(tcc, tmp, ctx); + emit(ARM_CMP_I(tc[0], hi), ctx); + _emit(ARM_COND_EQ, ARM_CMP_I(tc[1], lo), ctx); _emit(ARM_COND_HI, ARM_B(jmp_offset), ctx); - emit(ARM_ADDS_I(tmp[1], tmp[1], 1), ctx); - emit(ARM_ADC_I(tmp[0], tmp[0], 0), ctx); - emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx); - emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx); + emit(ARM_ADDS_I(tc[1], tc[1], 1), ctx); + emit(ARM_ADC_I(tc[0], tc[0], 0), ctx); + arm_bpf_put_reg64(tcc, tmp, ctx); /* prog = array->ptrs[index] * if (prog == NULL) * goto out; */ - off = offsetof(struct bpf_array, ptrs); - emit_a32_mov_i(tmp[1], off, false, ctx); - emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx); - emit(ARM_ADD_R(tmp[1], tmp2[1], tmp[1]), ctx); - emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx); - emit(ARM_MOV_SI(tmp[0], tmp2[1], SRTYPE_ASL, 2), ctx); - emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx); + BUILD_BUG_ON(imm8m(offsetof(struct bpf_array, ptrs)) < 0); + off = imm8m(offsetof(struct bpf_array, ptrs)); + emit(ARM_ADD_I(tmp[1], r_array, off), ctx); + emit(ARM_LDR_R_SI(tmp[1], tmp[1], r_index, SRTYPE_ASL, 2), ctx); emit(ARM_CMP_I(tmp[1], 0), ctx); _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx); /* goto *(prog->bpf_func + prologue_size); */ + BUILD_BUG_ON(offsetof(struct bpf_prog, bpf_func) > + ARM_INST_LDST__IMM12); off = offsetof(struct bpf_prog, bpf_func); - emit_a32_mov_i(tmp2[1], off, false, ctx); - emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx); + emit(ARM_LDR_I(tmp[1], tmp[1], off), ctx); emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx); emit_bx_r(tmp[1], ctx); @@ -1059,7 +1197,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx) { #if __LINUX_ARM_ARCH__ < 6 - const u8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx); emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 8), ctx); @@ -1074,7 +1212,7 @@ static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx) static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx) { #if __LINUX_ARM_ARCH__ < 6 - const u8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx); emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 24), ctx); @@ -1094,28 +1232,27 @@ static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx) } // push the scratch stack register on top of the stack -static inline void emit_push_r64(const u8 src[], const u8 shift, - struct jit_ctx *ctx) +static inline void emit_push_r64(const s8 src[], struct jit_ctx *ctx) { - const u8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *rt; u16 reg_set = 0; - emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(src[1]+shift)), ctx); - emit(ARM_LDR_I(tmp2[0], ARM_SP, STACK_VAR(src[0]+shift)), ctx); + rt = arm_bpf_get_reg64(src, tmp2, ctx); - reg_set = (1 << tmp2[1]) | (1 << tmp2[0]); + reg_set = (1 << rt[1]) | (1 << rt[0]); emit(ARM_PUSH(reg_set), ctx); } static void build_prologue(struct jit_ctx *ctx) { - const u8 r0 = bpf2a32[BPF_REG_0][1]; - const u8 r2 = bpf2a32[BPF_REG_1][1]; - const u8 r3 = bpf2a32[BPF_REG_1][0]; - const u8 r4 = bpf2a32[BPF_REG_6][1]; - const u8 fplo = bpf2a32[BPF_REG_FP][1]; - const u8 fphi = bpf2a32[BPF_REG_FP][0]; - const u8 *tcc = bpf2a32[TCALL_CNT]; + const s8 r0 = bpf2a32[BPF_REG_0][1]; + const s8 r2 = bpf2a32[BPF_REG_1][1]; + const s8 r3 = bpf2a32[BPF_REG_1][0]; + const s8 r4 = bpf2a32[BPF_REG_6][1]; + const s8 fplo = bpf2a32[BPF_REG_FP][1]; + const s8 fphi = bpf2a32[BPF_REG_FP][0]; + const s8 *tcc = bpf2a32[TCALL_CNT]; /* Save callee saved registers. */ #ifdef CONFIG_FRAME_POINTER @@ -1136,8 +1273,8 @@ static void build_prologue(struct jit_ctx *ctx) emit(ARM_SUB_I(ARM_SP, ARM_SP, ctx->stack_size), ctx); /* Set up BPF prog stack base register */ - emit_a32_mov_r(fplo, ARM_IP, true, false, ctx); - emit_a32_mov_i(fphi, 0, true, ctx); + emit_a32_mov_r(fplo, ARM_IP, ctx); + emit_a32_mov_i(fphi, 0, ctx); /* mov r4, 0 */ emit(ARM_MOV_I(r4, 0), ctx); @@ -1146,8 +1283,8 @@ static void build_prologue(struct jit_ctx *ctx) emit(ARM_MOV_R(r3, r4), ctx); emit(ARM_MOV_R(r2, r0), ctx); /* Initialize Tail Count */ - emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[0])), ctx); - emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[1])), ctx); + emit(ARM_STR_I(r4, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(tcc[0])), ctx); + emit(ARM_STR_I(r4, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(tcc[1])), ctx); /* end of prologue */ } @@ -1178,17 +1315,16 @@ static void build_epilogue(struct jit_ctx *ctx) static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) { const u8 code = insn->code; - const u8 *dst = bpf2a32[insn->dst_reg]; - const u8 *src = bpf2a32[insn->src_reg]; - const u8 *tmp = bpf2a32[TMP_REG_1]; - const u8 *tmp2 = bpf2a32[TMP_REG_2]; + const s8 *dst = bpf2a32[insn->dst_reg]; + const s8 *src = bpf2a32[insn->src_reg]; + const s8 *tmp = bpf2a32[TMP_REG_1]; + const s8 *tmp2 = bpf2a32[TMP_REG_2]; const s16 off = insn->off; const s32 imm = insn->imm; const int i = insn - ctx->prog->insnsi; const bool is64 = BPF_CLASS(code) == BPF_ALU64; - const bool dstk = is_on_stack(insn->dst_reg); - const bool sstk = is_on_stack(insn->src_reg); - u8 rd, rt, rm, rn; + const s8 *rd, *rs; + s8 rd_lo, rt, rm, rn; s32 jmp_offset; #define check_imm(bits, imm) do { \ @@ -1211,11 +1347,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) case BPF_ALU64 | BPF_MOV | BPF_X: switch (BPF_SRC(code)) { case BPF_X: - emit_a32_mov_r64(is64, dst, src, dstk, sstk, ctx); + emit_a32_mov_r64(is64, dst, src, ctx); break; case BPF_K: /* Sign-extend immediate value to destination reg */ - emit_a32_mov_i64(is64, dst, imm, dstk, ctx); + emit_a32_mov_se_i64(is64, dst, imm, ctx); break; } break; @@ -1255,8 +1391,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) case BPF_ALU64 | BPF_XOR | BPF_X: switch (BPF_SRC(code)) { case BPF_X: - emit_a32_alu_r64(is64, dst, src, dstk, sstk, - ctx, BPF_OP(code)); + emit_a32_alu_r64(is64, dst, src, ctx, BPF_OP(code)); break; case BPF_K: /* Move immediate value to the temporary register @@ -1265,9 +1400,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) * value into temporary reg and then it would be * safe to do the operation on it. */ - emit_a32_mov_i64(is64, tmp2, imm, false, ctx); - emit_a32_alu_r64(is64, dst, tmp2, dstk, false, - ctx, BPF_OP(code)); + emit_a32_mov_se_i64(is64, tmp2, imm, ctx); + emit_a32_alu_r64(is64, dst, tmp2, ctx, BPF_OP(code)); break; } break; @@ -1277,26 +1411,22 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU | BPF_MOD | BPF_X: - rt = src_lo; - rd = dstk ? tmp2[1] : dst_lo; - if (dstk) - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + rd_lo = arm_bpf_get_reg32(dst_lo, tmp2[1], ctx); switch (BPF_SRC(code)) { case BPF_X: - rt = sstk ? tmp2[0] : rt; - if (sstk) - emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), - ctx); + rt = arm_bpf_get_reg32(src_lo, tmp2[0], ctx); break; case BPF_K: rt = tmp2[0]; - emit_a32_mov_i(rt, imm, false, ctx); + emit_a32_mov_i(rt, imm, ctx); + break; + default: + rt = src_lo; break; } - emit_udivmod(rd, rd, rt, ctx, BPF_OP(code)); - if (dstk) - emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit_a32_mov_i(dst_hi, 0, dstk, ctx); + emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code)); + arm_bpf_put_reg32(dst_lo, rd_lo, ctx); + emit_a32_mov_i(dst_hi, 0, ctx); break; case BPF_ALU64 | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_X: @@ -1310,54 +1440,54 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) if (unlikely(imm > 31)) return -EINVAL; if (imm) - emit_a32_alu_i(dst_lo, imm, dstk, ctx, BPF_OP(code)); - emit_a32_mov_i(dst_hi, 0, dstk, ctx); + emit_a32_alu_i(dst_lo, imm, ctx, BPF_OP(code)); + emit_a32_mov_i(dst_hi, 0, ctx); break; /* dst = dst << imm */ case BPF_ALU64 | BPF_LSH | BPF_K: if (unlikely(imm > 63)) return -EINVAL; - emit_a32_lsh_i64(dst, dstk, imm, ctx); + emit_a32_lsh_i64(dst, imm, ctx); break; /* dst = dst >> imm */ case BPF_ALU64 | BPF_RSH | BPF_K: if (unlikely(imm > 63)) return -EINVAL; - emit_a32_rsh_i64(dst, dstk, imm, ctx); + emit_a32_rsh_i64(dst, imm, ctx); break; /* dst = dst << src */ case BPF_ALU64 | BPF_LSH | BPF_X: - emit_a32_lsh_r64(dst, src, dstk, sstk, ctx); + emit_a32_lsh_r64(dst, src, ctx); break; /* dst = dst >> src */ case BPF_ALU64 | BPF_RSH | BPF_X: - emit_a32_rsh_r64(dst, src, dstk, sstk, ctx); + emit_a32_rsh_r64(dst, src, ctx); break; /* dst = dst >> src (signed) */ case BPF_ALU64 | BPF_ARSH | BPF_X: - emit_a32_arsh_r64(dst, src, dstk, sstk, ctx); + emit_a32_arsh_r64(dst, src, ctx); break; /* dst = dst >> imm (signed) */ case BPF_ALU64 | BPF_ARSH | BPF_K: if (unlikely(imm > 63)) return -EINVAL; - emit_a32_arsh_i64(dst, dstk, imm, ctx); + emit_a32_arsh_i64(dst, imm, ctx); break; /* dst = ~dst */ case BPF_ALU | BPF_NEG: - emit_a32_alu_i(dst_lo, 0, dstk, ctx, BPF_OP(code)); - emit_a32_mov_i(dst_hi, 0, dstk, ctx); + emit_a32_alu_i(dst_lo, 0, ctx, BPF_OP(code)); + emit_a32_mov_i(dst_hi, 0, ctx); break; /* dst = ~dst (64 bit) */ case BPF_ALU64 | BPF_NEG: - emit_a32_neg64(dst, dstk, ctx); + emit_a32_neg64(dst, ctx); break; /* dst = dst * src/imm */ case BPF_ALU64 | BPF_MUL | BPF_X: case BPF_ALU64 | BPF_MUL | BPF_K: switch (BPF_SRC(code)) { case BPF_X: - emit_a32_mul_r64(dst, src, dstk, sstk, ctx); + emit_a32_mul_r64(dst, src, ctx); break; case BPF_K: /* Move immediate value to the temporary register @@ -1366,8 +1496,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) * reg then it would be safe to do the operation * on it. */ - emit_a32_mov_i64(is64, tmp2, imm, false, ctx); - emit_a32_mul_r64(dst, tmp2, dstk, false, ctx); + emit_a32_mov_se_i64(is64, tmp2, imm, ctx); + emit_a32_mul_r64(dst, tmp2, ctx); break; } break; @@ -1375,25 +1505,20 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) /* dst = htobe(dst) */ case BPF_ALU | BPF_END | BPF_FROM_LE: case BPF_ALU | BPF_END | BPF_FROM_BE: - rd = dstk ? tmp[0] : dst_hi; - rt = dstk ? tmp[1] : dst_lo; - if (dstk) { - emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + rd = arm_bpf_get_reg64(dst, tmp, ctx); if (BPF_SRC(code) == BPF_FROM_LE) goto emit_bswap_uxt; switch (imm) { case 16: - emit_rev16(rt, rt, ctx); + emit_rev16(rd[1], rd[1], ctx); goto emit_bswap_uxt; case 32: - emit_rev32(rt, rt, ctx); + emit_rev32(rd[1], rd[1], ctx); goto emit_bswap_uxt; case 64: - emit_rev32(ARM_LR, rt, ctx); - emit_rev32(rt, rd, ctx); - emit(ARM_MOV_R(rd, ARM_LR), ctx); + emit_rev32(ARM_LR, rd[1], ctx); + emit_rev32(rd[1], rd[0], ctx); + emit(ARM_MOV_R(rd[0], ARM_LR), ctx); break; } goto exit; @@ -1402,36 +1527,30 @@ emit_bswap_uxt: case 16: /* zero-extend 16 bits into 64 bits */ #if __LINUX_ARM_ARCH__ < 6 - emit_a32_mov_i(tmp2[1], 0xffff, false, ctx); - emit(ARM_AND_R(rt, rt, tmp2[1]), ctx); + emit_a32_mov_i(tmp2[1], 0xffff, ctx); + emit(ARM_AND_R(rd[1], rd[1], tmp2[1]), ctx); #else /* ARMv6+ */ - emit(ARM_UXTH(rt, rt), ctx); + emit(ARM_UXTH(rd[1], rd[1]), ctx); #endif - emit(ARM_EOR_R(rd, rd, rd), ctx); + emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx); break; case 32: /* zero-extend 32 bits into 64 bits */ - emit(ARM_EOR_R(rd, rd, rd), ctx); + emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx); break; case 64: /* nop */ break; } exit: - if (dstk) { - emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + arm_bpf_put_reg64(dst, rd, ctx); break; /* dst = imm64 */ case BPF_LD | BPF_IMM | BPF_DW: { - const struct bpf_insn insn1 = insn[1]; - u32 hi, lo = imm; + u64 val = (u32)imm | (u64)insn[1].imm << 32; - hi = insn1.imm; - emit_a32_mov_i(dst_lo, lo, dstk, ctx); - emit_a32_mov_i(dst_hi, hi, dstk, ctx); + emit_a32_mov_i64(dst, val, ctx); return 1; } @@ -1440,10 +1559,8 @@ exit: case BPF_LDX | BPF_MEM | BPF_H: case BPF_LDX | BPF_MEM | BPF_B: case BPF_LDX | BPF_MEM | BPF_DW: - rn = sstk ? tmp2[1] : src_lo; - if (sstk) - emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx); - emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code)); + rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); + emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code)); break; /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: @@ -1453,18 +1570,15 @@ exit: switch (BPF_SIZE(code)) { case BPF_DW: /* Sign-extend immediate value into temp reg */ - emit_a32_mov_i64(true, tmp2, imm, false, ctx); - emit_str_r(dst_lo, tmp2[1], dstk, off, ctx, BPF_W); - emit_str_r(dst_lo, tmp2[0], dstk, off+4, ctx, BPF_W); + emit_a32_mov_se_i64(true, tmp2, imm, ctx); break; case BPF_W: case BPF_H: case BPF_B: - emit_a32_mov_i(tmp2[1], imm, false, ctx); - emit_str_r(dst_lo, tmp2[1], dstk, off, ctx, - BPF_SIZE(code)); + emit_a32_mov_i(tmp2[1], imm, ctx); break; } + emit_str_r(dst_lo, tmp2, off, ctx, BPF_SIZE(code)); break; /* STX XADD: lock *(u32 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_W: @@ -1476,25 +1590,9 @@ exit: case BPF_STX | BPF_MEM | BPF_H: case BPF_STX | BPF_MEM | BPF_B: case BPF_STX | BPF_MEM | BPF_DW: - { - u8 sz = BPF_SIZE(code); - - rn = sstk ? tmp2[1] : src_lo; - rm = sstk ? tmp2[0] : src_hi; - if (sstk) { - emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx); - } - - /* Store the value */ - if (BPF_SIZE(code) == BPF_DW) { - emit_str_r(dst_lo, rn, dstk, off, ctx, BPF_W); - emit_str_r(dst_lo, rm, dstk, off+4, ctx, BPF_W); - } else { - emit_str_r(dst_lo, rn, dstk, off, ctx, sz); - } + rs = arm_bpf_get_reg64(src, tmp2, ctx); + emit_str_r(dst_lo, rs, off, ctx, BPF_SIZE(code)); break; - } /* PC += off if dst == src */ /* PC += off if dst > src */ /* PC += off if dst >= src */ @@ -1518,12 +1616,8 @@ exit: case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSLE | BPF_X: /* Setup source registers */ - rm = sstk ? tmp2[0] : src_hi; - rn = sstk ? tmp2[1] : src_lo; - if (sstk) { - emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx); - emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx); - } + rm = arm_bpf_get_reg32(src_hi, tmp2[0], ctx); + rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx); goto go_jmp; /* PC += off if dst == imm */ /* PC += off if dst > imm */ @@ -1552,18 +1646,13 @@ exit: rm = tmp2[0]; rn = tmp2[1]; /* Sign-extend immediate value */ - emit_a32_mov_i64(true, tmp2, imm, false, ctx); + emit_a32_mov_se_i64(true, tmp2, imm, ctx); go_jmp: /* Setup destination register */ - rd = dstk ? tmp[0] : dst_hi; - rt = dstk ? tmp[1] : dst_lo; - if (dstk) { - emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx); - emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx); - } + rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Check for the condition */ - emit_ar_r(rd, rt, rm, rn, ctx, BPF_OP(code)); + emit_ar_r(rd[0], rd[1], rm, rn, ctx, BPF_OP(code)); /* Setup JUMP instruction */ jmp_offset = bpf2a32_offset(i+off, i, ctx); @@ -1619,21 +1708,21 @@ go_jmp: /* function call */ case BPF_JMP | BPF_CALL: { - const u8 *r0 = bpf2a32[BPF_REG_0]; - const u8 *r1 = bpf2a32[BPF_REG_1]; - const u8 *r2 = bpf2a32[BPF_REG_2]; - const u8 *r3 = bpf2a32[BPF_REG_3]; - const u8 *r4 = bpf2a32[BPF_REG_4]; - const u8 *r5 = bpf2a32[BPF_REG_5]; + const s8 *r0 = bpf2a32[BPF_REG_0]; + const s8 *r1 = bpf2a32[BPF_REG_1]; + const s8 *r2 = bpf2a32[BPF_REG_2]; + const s8 *r3 = bpf2a32[BPF_REG_3]; + const s8 *r4 = bpf2a32[BPF_REG_4]; + const s8 *r5 = bpf2a32[BPF_REG_5]; const u32 func = (u32)__bpf_call_base + (u32)imm; - emit_a32_mov_r64(true, r0, r1, false, false, ctx); - emit_a32_mov_r64(true, r1, r2, false, true, ctx); - emit_push_r64(r5, 0, ctx); - emit_push_r64(r4, 8, ctx); - emit_push_r64(r3, 16, ctx); + emit_a32_mov_r64(true, r0, r1, ctx); + emit_a32_mov_r64(true, r1, r2, ctx); + emit_push_r64(r5, ctx); + emit_push_r64(r4, ctx); + emit_push_r64(r3, ctx); - emit_a32_mov_i(tmp[1], func, false, ctx); + emit_a32_mov_i(tmp[1], func, ctx); emit_blx_r(tmp[1], ctx); emit(ARM_ADD_I(ARM_SP, ARM_SP, imm8m(24)), ctx); // callee clean @@ -1745,6 +1834,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) memset(&ctx, 0, sizeof(ctx)); ctx.prog = prog; + ctx.cpu_architecture = cpu_architecture(); /* Not able to allocate memory for offsets[] , then * we must fall back to the interpreter diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h index d5cf5f6208aa..f4e58bcdaa43 100644 --- a/arch/arm/net/bpf_jit_32.h +++ b/arch/arm/net/bpf_jit_32.h @@ -77,11 +77,14 @@ #define ARM_INST_EOR_R 0x00200000 #define ARM_INST_EOR_I 0x02200000 -#define ARM_INST_LDRB_I 0x05d00000 +#define ARM_INST_LDST__U 0x00800000 +#define ARM_INST_LDST__IMM12 0x00000fff +#define ARM_INST_LDRB_I 0x05500000 #define ARM_INST_LDRB_R 0x07d00000 -#define ARM_INST_LDRH_I 0x01d000b0 +#define ARM_INST_LDRD_I 0x014000d0 +#define ARM_INST_LDRH_I 0x015000b0 #define ARM_INST_LDRH_R 0x019000b0 -#define ARM_INST_LDR_I 0x05900000 +#define ARM_INST_LDR_I 0x05100000 #define ARM_INST_LDR_R 0x07900000 #define ARM_INST_LDM 0x08900000 @@ -124,9 +127,10 @@ #define ARM_INST_SBC_R 0x00c00000 #define ARM_INST_SBCS_R 0x00d00000 -#define ARM_INST_STR_I 0x05800000 -#define ARM_INST_STRB_I 0x05c00000 -#define ARM_INST_STRH_I 0x01c000b0 +#define ARM_INST_STR_I 0x05000000 +#define ARM_INST_STRB_I 0x05400000 +#define ARM_INST_STRD_I 0x014000f0 +#define ARM_INST_STRH_I 0x014000b0 #define ARM_INST_TST_R 0x01100000 #define ARM_INST_TST_I 0x03100000 @@ -183,17 +187,18 @@ #define ARM_EOR_R(rd, rn, rm) _AL3_R(ARM_INST_EOR, rd, rn, rm) #define ARM_EOR_I(rd, rn, imm) _AL3_I(ARM_INST_EOR, rd, rn, imm) -#define ARM_LDR_I(rt, rn, off) (ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \ - | ((off) & 0xfff)) -#define ARM_LDR_R(rt, rn, rm) (ARM_INST_LDR_R | (rt) << 12 | (rn) << 16 \ +#define ARM_LDR_R(rt, rn, rm) (ARM_INST_LDR_R | ARM_INST_LDST__U \ + | (rt) << 12 | (rn) << 16 \ | (rm)) -#define ARM_LDRB_I(rt, rn, off) (ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \ - | (off)) -#define ARM_LDRB_R(rt, rn, rm) (ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \ +#define ARM_LDR_R_SI(rt, rn, rm, type, imm) \ + (ARM_INST_LDR_R | ARM_INST_LDST__U \ + | (rt) << 12 | (rn) << 16 \ + | (imm) << 7 | (type) << 5 | (rm)) +#define ARM_LDRB_R(rt, rn, rm) (ARM_INST_LDRB_R | ARM_INST_LDST__U \ + | (rt) << 12 | (rn) << 16 \ | (rm)) -#define ARM_LDRH_I(rt, rn, off) (ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \ - | (((off) & 0xf0) << 4) | ((off) & 0xf)) -#define ARM_LDRH_R(rt, rn, rm) (ARM_INST_LDRH_R | (rt) << 12 | (rn) << 16 \ +#define ARM_LDRH_R(rt, rn, rm) (ARM_INST_LDRH_R | ARM_INST_LDST__U \ + | (rt) << 12 | (rn) << 16 \ | (rm)) #define ARM_LDM(rn, regs) (ARM_INST_LDM | (rn) << 16 | (regs)) @@ -254,13 +259,6 @@ #define ARM_SUBS_I(rd, rn, imm) _AL3_I(ARM_INST_SUBS, rd, rn, imm) #define ARM_SBC_I(rd, rn, imm) _AL3_I(ARM_INST_SBC, rd, rn, imm) -#define ARM_STR_I(rt, rn, off) (ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \ - | ((off) & 0xfff)) -#define ARM_STRH_I(rt, rn, off) (ARM_INST_STRH_I | (rt) << 12 | (rn) << 16 \ - | (((off) & 0xf0) << 4) | ((off) & 0xf)) -#define ARM_STRB_I(rt, rn, off) (ARM_INST_STRB_I | (rt) << 12 | (rn) << 16 \ - | (((off) & 0xf0) << 4) | ((off) & 0xf)) - #define ARM_TST_R(rn, rm) _AL3_R(ARM_INST_TST, 0, rn, rm) #define ARM_TST_I(rn, imm) _AL3_I(ARM_INST_TST, 0, rn, imm) diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c index 2438b96004c1..fcc5bfec8bd1 100644 --- a/arch/arm/plat-omap/counter_32k.c +++ b/arch/arm/plat-omap/counter_32k.c @@ -110,7 +110,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase) } sched_clock_register(omap_32k_read_sched_clock, 32, 32768); - register_persistent_clock(NULL, omap_read_persistent_clock64); + register_persistent_clock(omap_read_persistent_clock64); pr_info("OMAP clocksource: 32k_counter at 32768 Hz\n"); return 0; diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c index ba13f793fbce..ed36dcab80f1 100644 --- a/arch/arm/plat-pxa/ssp.c +++ b/arch/arm/plat-pxa/ssp.c @@ -127,53 +127,6 @@ static int pxa_ssp_probe(struct platform_device *pdev) if (IS_ERR(ssp->clk)) return PTR_ERR(ssp->clk); - if (dev->of_node) { - struct of_phandle_args dma_spec; - struct device_node *np = dev->of_node; - int ret; - - /* - * FIXME: we should allocate the DMA channel from this - * context and pass the channel down to the ssp users. - * For now, we lookup the rx and tx indices manually - */ - - /* rx */ - ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells", - 0, &dma_spec); - - if (ret) { - dev_err(dev, "Can't parse dmas property\n"); - return -ENODEV; - } - ssp->drcmr_rx = dma_spec.args[0]; - of_node_put(dma_spec.np); - - /* tx */ - ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells", - 1, &dma_spec); - if (ret) { - dev_err(dev, "Can't parse dmas property\n"); - return -ENODEV; - } - ssp->drcmr_tx = dma_spec.args[0]; - of_node_put(dma_spec.np); - } else { - res = platform_get_resource(pdev, IORESOURCE_DMA, 0); - if (res == NULL) { - dev_err(dev, "no SSP RX DRCMR defined\n"); - return -ENODEV; - } - ssp->drcmr_rx = res->start; - - res = platform_get_resource(pdev, IORESOURCE_DMA, 1); - if (res == NULL) { - dev_err(dev, "no SSP TX DRCMR defined\n"); - return -ENODEV; - } - ssp->drcmr_tx = res->start; - } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (res == NULL) { dev_err(dev, "no memory resource defined\n"); diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c index 2da35735fa38..ee3d5c989a76 100644 --- a/arch/arm/plat-samsung/adc.c +++ b/arch/arm/plat-samsung/adc.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/mod_devicetable.h> #include <linux/platform_device.h> #include <linux/sched.h> #include <linux/list.h> diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index e90cc8a08186..f8bd523d64d1 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -47,9 +47,6 @@ (unsigned long)(addr) + \ (size)) -/* Used as a marker in ARM_pc to note when we're in a jprobe. */ -#define JPROBE_MAGIC_ADDR 0xffffffff - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -289,8 +286,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs) break; case KPROBE_REENTER: /* A nested probe was hit in FIQ, it is a BUG */ - pr_warn("Unrecoverable kprobe detected at %p.\n", - p->addr); + pr_warn("Unrecoverable kprobe detected.\n"); + dump_kprobe(p); /* fall through */ default: /* impossible cases */ @@ -303,10 +300,10 @@ void __kprobes kprobe_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we - * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry, - * so get out doing nothing more here. + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { kcb->kprobe_status = KPROBE_HIT_SS; @@ -315,20 +312,9 @@ void __kprobes kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_HIT_SSDONE; p->post_handler(p, regs, 0); } - reset_current_kprobe(); - } - } - } else if (cur) { - /* We probably hit a jprobe. Call its break handler. */ - if (cur->break_handler && cur->break_handler(cur, regs)) { - kcb->kprobe_status = KPROBE_HIT_SS; - singlestep(cur, regs, kcb); - if (cur->post_handler) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - cur->post_handler(cur, regs, 0); } + reset_current_kprobe(); } - reset_current_kprobe(); } else { /* * The probe was removed and a race is in progress. @@ -521,117 +507,6 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, regs->ARM_lr = (unsigned long)&kretprobe_trampoline; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long sp_addr = regs->ARM_sp; - long cpsr; - - kcb->jprobe_saved_regs = *regs; - memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr)); - regs->ARM_pc = (long)jp->entry; - - cpsr = regs->ARM_cpsr | PSR_I_BIT; -#ifdef CONFIG_THUMB2_KERNEL - /* Set correct Thumb state in cpsr */ - if (regs->ARM_pc & 1) - cpsr |= PSR_T_BIT; - else - cpsr &= ~PSR_T_BIT; -#endif - regs->ARM_cpsr = cpsr; - - preempt_disable(); - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - __asm__ __volatile__ ( - /* - * Setup an empty pt_regs. Fill SP and PC fields as - * they're needed by longjmp_break_handler. - * - * We allocate some slack between the original SP and start of - * our fabricated regs. To be precise we want to have worst case - * covered which is STMFD with all 16 regs so we allocate 2 * - * sizeof(struct_pt_regs)). - * - * This is to prevent any simulated instruction from writing - * over the regs when they are accessing the stack. - */ -#ifdef CONFIG_THUMB2_KERNEL - "sub r0, %0, %1 \n\t" - "mov sp, r0 \n\t" -#else - "sub sp, %0, %1 \n\t" -#endif - "ldr r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t" - "str %0, [sp, %2] \n\t" - "str r0, [sp, %3] \n\t" - "mov r0, sp \n\t" - "bl kprobe_handler \n\t" - - /* - * Return to the context saved by setjmp_pre_handler - * and restored by longjmp_break_handler. - */ -#ifdef CONFIG_THUMB2_KERNEL - "ldr lr, [sp, %2] \n\t" /* lr = saved sp */ - "ldrd r0, r1, [sp, %5] \n\t" /* r0,r1 = saved lr,pc */ - "ldr r2, [sp, %4] \n\t" /* r2 = saved psr */ - "stmdb lr!, {r0, r1, r2} \n\t" /* push saved lr and */ - /* rfe context */ - "ldmia sp, {r0 - r12} \n\t" - "mov sp, lr \n\t" - "ldr lr, [sp], #4 \n\t" - "rfeia sp! \n\t" -#else - "ldr r0, [sp, %4] \n\t" - "msr cpsr_cxsf, r0 \n\t" - "ldmia sp, {r0 - pc} \n\t" -#endif - : - : "r" (kcb->jprobe_saved_regs.ARM_sp), - "I" (sizeof(struct pt_regs) * 2), - "J" (offsetof(struct pt_regs, ARM_sp)), - "J" (offsetof(struct pt_regs, ARM_pc)), - "J" (offsetof(struct pt_regs, ARM_cpsr)), - "J" (offsetof(struct pt_regs, ARM_lr)) - : "memory", "cc"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_addr = kcb->jprobe_saved_regs.ARM_sp; - long orig_sp = regs->ARM_sp; - struct jprobe *jp = container_of(p, struct jprobe, kp); - - if (regs->ARM_pc == JPROBE_MAGIC_ADDR) { - if (orig_sp != stack_addr) { - struct pt_regs *saved_regs = - (struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp; - printk("current sp %lx does not match saved sp %lx\n", - orig_sp, stack_addr); - printk("Saved registers for jprobe %p\n", jp); - show_regs(saved_regs); - printk("Current registers\n"); - show_regs(regs); - BUG(); - } - *regs = kcb->jprobe_saved_regs; - memcpy((void *)stack_addr, kcb->jprobes_stack, - MIN_STACK_SIZE(stack_addr)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - int __kprobes arch_trampoline_kprobe(struct kprobe *p) { return 0; diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c index 14db14152909..cc237fa9b90f 100644 --- a/arch/arm/probes/kprobes/test-core.c +++ b/arch/arm/probes/kprobes/test-core.c @@ -1461,7 +1461,6 @@ fail: print_registers(&result_regs); if (mem) { - pr_err("current_stack=%p\n", current_stack); pr_err("expected_memory:\n"); print_memory(expected_memory, mem_size); pr_err("result_memory:\n"); diff --git a/arch/arm/vfp/Makefile b/arch/arm/vfp/Makefile index a81404c09d5d..94516c40ebd3 100644 --- a/arch/arm/vfp/Makefile +++ b/arch/arm/vfp/Makefile @@ -8,8 +8,5 @@ # asflags-y := -DDEBUG KBUILD_AFLAGS :=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp -mfloat-abi=soft) -LDFLAGS +=--no-warn-mismatch -obj-y += vfp.o - -vfp-$(CONFIG_VFP) += vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o +obj-y += vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 35d0f823e823..dc7e6b50ef67 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -596,13 +596,11 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp, } /* Sanitise and restore the current VFP state from the provided structures. */ -int vfp_restore_user_hwstate(struct user_vfp __user *ufp, - struct user_vfp_exc __user *ufp_exc) +int vfp_restore_user_hwstate(struct user_vfp *ufp, struct user_vfp_exc *ufp_exc) { struct thread_info *thread = current_thread_info(); struct vfp_hard_struct *hwstate = &thread->vfpstate.hard; unsigned long fpexc; - int err = 0; /* Disable VFP to avoid corrupting the new thread state. */ vfp_flush_hwstate(thread); @@ -611,17 +609,16 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp, * Copy the floating point registers. There can be unused * registers see asm/hwcap.h for details. */ - err |= __copy_from_user(&hwstate->fpregs, &ufp->fpregs, - sizeof(hwstate->fpregs)); + memcpy(&hwstate->fpregs, &ufp->fpregs, sizeof(hwstate->fpregs)); /* * Copy the status and control register. */ - __get_user_error(hwstate->fpscr, &ufp->fpscr, err); + hwstate->fpscr = ufp->fpscr; /* * Sanitise and restore the exception registers. */ - __get_user_error(fpexc, &ufp_exc->fpexc, err); + fpexc = ufp_exc->fpexc; /* Ensure the VFP is enabled. */ fpexc |= FPEXC_EN; @@ -630,10 +627,10 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp, fpexc &= ~(FPEXC_EX | FPEXC_FP2V); hwstate->fpexc = fpexc; - __get_user_error(hwstate->fpinst, &ufp_exc->fpinst, err); - __get_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err); + hwstate->fpinst = ufp_exc->fpinst; + hwstate->fpinst2 = ufp_exc->fpinst2; - return err ? -EFAULT : 0; + return 0; } /* diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 42c090cf0292..d0a53cc6293a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -24,6 +24,7 @@ config ARM64 select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX + select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK if !PREEMPT @@ -42,8 +43,19 @@ config ARM64 select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPT select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPT select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPT + select ARCH_INLINE_SPIN_TRYLOCK if !PREEMPT + select ARCH_INLINE_SPIN_TRYLOCK_BH if !PREEMPT + select ARCH_INLINE_SPIN_LOCK if !PREEMPT + select ARCH_INLINE_SPIN_LOCK_BH if !PREEMPT + select ARCH_INLINE_SPIN_LOCK_IRQ if !PREEMPT + select ARCH_INLINE_SPIN_LOCK_IRQSAVE if !PREEMPT + select ARCH_INLINE_SPIN_UNLOCK if !PREEMPT + select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPT + select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPT + select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPT select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_QUEUED_SPINLOCKS select ARCH_SUPPORTS_MEMORY_FAILURE select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG @@ -74,6 +86,7 @@ config ARM64 select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP select GENERIC_IDLE_POLL_SETUP + select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL @@ -96,6 +109,7 @@ config ARM64 select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT select HAVE_ARCH_SECCOMP_FILTER + select HAVE_ARCH_STACKLEAK select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE @@ -127,6 +141,7 @@ config ARM64 select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RCU_TABLE_FREE + select HAVE_RSEQ select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select HAVE_KPROBES @@ -264,13 +279,6 @@ config ARCH_SUPPORTS_UPROBES config ARCH_PROC_KCORE_TEXT def_bool y -config MULTI_IRQ_HANDLER - def_bool y - -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - source "arch/arm64/Kconfig.platforms" menu "Bus support" @@ -756,7 +764,6 @@ config HOLES_IN_ZONE def_bool y depends on NUMA -source kernel/Kconfig.preempt source kernel/Kconfig.hz config ARCH_SUPPORTS_DEBUG_PAGEALLOC @@ -775,6 +782,9 @@ config ARCH_SPARSEMEM_DEFAULT config ARCH_SELECT_MEMORY_MODEL def_bool ARCH_SPARSEMEM_ENABLE +config ARCH_FLATMEM_ENABLE + def_bool !NUMA + config HAVE_ARCH_PFN_VALID def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM @@ -791,8 +801,6 @@ config ARCH_WANT_HUGE_PMD_SHARE config ARCH_HAS_CACHE_LINE_SIZE def_bool y -source "mm/Kconfig" - config SECCOMP bool "Enable seccomp to safely compute untrusted bytecode" ---help--- @@ -1246,6 +1254,7 @@ config EFI bool "UEFI runtime support" depends on OF && !CPU_BIG_ENDIAN depends on KERNEL_MODE_NEON + select ARCH_SUPPORTS_ACPI select LIBFDT select UCS2_STRING select EFI_PARAMS_FROM_FDT @@ -1273,10 +1282,6 @@ config DMI endmenu -menu "Userspace binary formats" - -source "fs/Kconfig.binfmt" - config COMPAT bool "Kernel support for 32-bit EL0" depends on ARM64_4K_PAGES || EXPERT @@ -1300,8 +1305,6 @@ config SYSVIPC_COMPAT def_bool y depends on COMPAT && SYSVIPC -endmenu - menu "Power management options" source "kernel/power/Kconfig" @@ -1327,25 +1330,12 @@ source "drivers/cpufreq/Kconfig" endmenu -source "net/Kconfig" - -source "drivers/Kconfig" - source "drivers/firmware/Kconfig" source "drivers/acpi/Kconfig" -source "fs/Kconfig" - source "arch/arm64/kvm/Kconfig" -source "arch/arm64/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" if CRYPTO source "arch/arm64/crypto/Kconfig" endif - -source "lib/Kconfig" diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index cc6bd559af85..69c9170bdd24 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -1,6 +1,3 @@ -menu "Kernel hacking" - -source "lib/Kconfig.debug" config ARM64_PTDUMP_CORE def_bool n @@ -97,5 +94,3 @@ config ARM64_RELOC_TEST tristate "Relocation testing module" source "drivers/hwtracing/coresight/Kconfig" - -endmenu diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index e7101b19d590..efe61a2e4b5e 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -60,15 +60,16 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ AS += -EB -# We must use the linux target here, since distributions don't tend to package -# the ELF linker scripts with binutils, and this results in a build failure. -LDFLAGS += -EB -maarch64linuxb +# Prefer the baremetal ELF build target, but not all toolchains include +# it so fall back to the standard linux version if needed. +LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb) UTS_MACHINE := aarch64_be else KBUILD_CPPFLAGS += -mlittle-endian CHECKFLAGS += -D__AARCH64EL__ AS += -EL -LDFLAGS += -EL -maarch64linux # See comment above +# Same as above, prefer ELF but fall back to linux target if needed. +LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux) UTS_MACHINE := aarch64 endif diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index 4057197048dc..1a406a76c86a 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -482,9 +482,9 @@ status = "disabled"; }; - mdio_mux_iproc: mdio-mux@6602023c { + mdio_mux_iproc: mdio-mux@66020000 { compatible = "brcm,mdio-mux-iproc"; - reg = <0x6602023c 0x14>; + reg = <0x66020000 0x250>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi index b203152ad67c..a70e8ddbd66f 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi @@ -278,9 +278,9 @@ #include "stingray-pinctrl.dtsi" - mdio_mux_iproc: mdio-mux@2023c { + mdio_mux_iproc: mdio-mux@20000 { compatible = "brcm,mdio-mux-iproc"; - reg = <0x0002023c 0x14>; + reg = <0x00020000 0x250>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi index 4dd06767f839..4664c33e0763 100644 --- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi @@ -11,13 +11,14 @@ fman0: fman@1a00000 { #size-cells = <1>; cell-index = <0>; compatible = "fsl,fman"; - ranges = <0x0 0x0 0x1a00000 0x100000>; - reg = <0x0 0x1a00000 0x0 0x100000>; + ranges = <0x0 0x0 0x1a00000 0xfe000>; + reg = <0x0 0x1a00000 0x0 0xfe000>; interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clockgen 3 0>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; + ptimer-handle = <&ptp_timer0>; muram@0 { compatible = "fsl,fman-muram"; @@ -73,9 +74,11 @@ fman0: fman@1a00000 { compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xfd000 0x1000>; }; +}; - ptp_timer0: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer0: ptp-timer@1afe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x0 0x1afe000 0x0 0x1000>; + interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 3 0>; }; diff --git a/arch/arm64/boot/dts/hisilicon/hi3660.dtsi b/arch/arm64/boot/dts/hisilicon/hi3660.dtsi index 8d477dcbfa58..851190a719ea 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3660.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hi3660.dtsi @@ -1000,6 +1000,24 @@ reset-gpios = <&gpio11 1 0 >; }; + /* UFS */ + ufs: ufs@ff3b0000 { + compatible = "hisilicon,hi3660-ufs", "jedec,ufs-1.1"; + /* 0: HCI standard */ + /* 1: UFS SYS CTRL */ + reg = <0x0 0xff3b0000 0x0 0x1000>, + <0x0 0xff3b1000 0x0 0x1000>; + interrupt-parent = <&gic>; + interrupts = <GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&crg_ctrl HI3660_CLK_GATE_UFSIO_REF>, + <&crg_ctrl HI3660_CLK_GATE_UFSPHY_CFG>; + clock-names = "ref_clk", "phy_clk"; + freq-table-hz = <0 0>, <0 0>; + /* offset: 0x84; bit: 12 */ + resets = <&crg_rst 0x84 12>; + reset-names = "rst"; + }; + /* SD */ dwmmc1: dwmmc1@ff37f000 { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/hisilicon/hip07.dtsi b/arch/arm64/boot/dts/hisilicon/hip07.dtsi index 9c10030a07f8..c33adefc3061 100644 --- a/arch/arm64/boot/dts/hisilicon/hip07.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hip07.dtsi @@ -1049,7 +1049,74 @@ num-pins = <2>; }; }; + p0_mbigen_alg_a:interrupt-controller@d0080000 { + compatible = "hisilicon,mbigen-v2"; + reg = <0x0 0xd0080000 0x0 0x10000>; + p0_mbigen_sec_a: intc_sec { + msi-parent = <&p0_its_dsa_a 0x40400>; + interrupt-controller; + #interrupt-cells = <2>; + num-pins = <33>; + }; + p0_mbigen_smmu_alg_a: intc_smmu_alg { + msi-parent = <&p0_its_dsa_a 0x40b1b>; + interrupt-controller; + #interrupt-cells = <2>; + num-pins = <3>; + }; + }; + p0_mbigen_alg_b:interrupt-controller@8,d0080000 { + compatible = "hisilicon,mbigen-v2"; + reg = <0x8 0xd0080000 0x0 0x10000>; + + p0_mbigen_sec_b: intc_sec { + msi-parent = <&p0_its_dsa_b 0x42400>; + interrupt-controller; + #interrupt-cells = <2>; + num-pins = <33>; + }; + p0_mbigen_smmu_alg_b: intc_smmu_alg { + msi-parent = <&p0_its_dsa_b 0x42b1b>; + interrupt-controller; + #interrupt-cells = <2>; + num-pins = <3>; + }; + }; + p1_mbigen_alg_a:interrupt-controller@400,d0080000 { + compatible = "hisilicon,mbigen-v2"; + reg = <0x400 0xd0080000 0x0 0x10000>; + + p1_mbigen_sec_a: intc_sec { + msi-parent = <&p1_its_dsa_a 0x44400>; + interrupt-controller; + #interrupt-cells = <2>; + num-pins = <33>; + }; + p1_mbigen_smmu_alg_a: intc_smmu_alg { + msi-parent = <&p1_its_dsa_a 0x44b1b>; + interrupt-controller; + #interrupt-cells = <2>; + num-pins = <3>; + }; + }; + p1_mbigen_alg_b:interrupt-controller@408,d0080000 { + compatible = "hisilicon,mbigen-v2"; + reg = <0x408 0xd0080000 0x0 0x10000>; + + p1_mbigen_sec_b: intc_sec { + msi-parent = <&p1_its_dsa_b 0x46400>; + interrupt-controller; + #interrupt-cells = <2>; + num-pins = <33>; + }; + p1_mbigen_smmu_alg_b: intc_smmu_alg { + msi-parent = <&p1_its_dsa_b 0x46b1b>; + interrupt-controller; + #interrupt-cells = <2>; + num-pins = <3>; + }; + }; p0_mbigen_dsa_a: interrupt-controller@c0080000 { compatible = "hisilicon,mbigen-v2"; reg = <0x0 0xc0080000 0x0 0x10000>; @@ -1107,6 +1174,58 @@ hisilicon,broken-prefetch-cmd; status = "disabled"; }; + p0_smmu_alg_a: smmu_alg@d0040000 { + compatible = "arm,smmu-v3"; + reg = <0x0 0xd0040000 0x0 0x20000>; + interrupt-parent = <&p0_mbigen_smmu_alg_a>; + interrupts = <733 1>, + <734 1>, + <735 1>; + interrupt-names = "eventq", "gerror", "priq"; + #iommu-cells = <1>; + dma-coherent; + hisilicon,broken-prefetch-cmd; + /* smmu-cb-memtype = <0x0 0x1>;*/ + }; + p0_smmu_alg_b: smmu_alg@8,d0040000 { + compatible = "arm,smmu-v3"; + reg = <0x8 0xd0040000 0x0 0x20000>; + interrupt-parent = <&p0_mbigen_smmu_alg_b>; + interrupts = <733 1>, + <734 1>, + <735 1>; + interrupt-names = "eventq", "gerror", "priq"; + #iommu-cells = <1>; + dma-coherent; + hisilicon,broken-prefetch-cmd; + /* smmu-cb-memtype = <0x0 0x1>;*/ + }; + p1_smmu_alg_a: smmu_alg@400,d0040000 { + compatible = "arm,smmu-v3"; + reg = <0x400 0xd0040000 0x0 0x20000>; + interrupt-parent = <&p1_mbigen_smmu_alg_a>; + interrupts = <733 1>, + <734 1>, + <735 1>; + interrupt-names = "eventq", "gerror", "priq"; + #iommu-cells = <1>; + dma-coherent; + hisilicon,broken-prefetch-cmd; + /* smmu-cb-memtype = <0x0 0x1>;*/ + }; + p1_smmu_alg_b: smmu_alg@408,d0040000 { + compatible = "arm,smmu-v3"; + reg = <0x408 0xd0040000 0x0 0x20000>; + interrupt-parent = <&p1_mbigen_smmu_alg_b>; + interrupts = <733 1>, + <734 1>, + <735 1>; + interrupt-names = "eventq", "gerror", "priq"; + #iommu-cells = <1>; + dma-coherent; + hisilicon,broken-prefetch-cmd; + /* smmu-cb-memtype = <0x0 0x1>;*/ + }; soc { compatible = "simple-bus"; @@ -1603,5 +1722,170 @@ 0x0 0 0 4 &mbigen_pcie2_a 671 4>; status = "disabled"; }; + p0_sec_a: crypto@d2000000 { + compatible = "hisilicon,hip07-sec"; + reg = <0x0 0xd0000000 0x0 0x10000 + 0x0 0xd2000000 0x0 0x10000 + 0x0 0xd2010000 0x0 0x10000 + 0x0 0xd2020000 0x0 0x10000 + 0x0 0xd2030000 0x0 0x10000 + 0x0 0xd2040000 0x0 0x10000 + 0x0 0xd2050000 0x0 0x10000 + 0x0 0xd2060000 0x0 0x10000 + 0x0 0xd2070000 0x0 0x10000 + 0x0 0xd2080000 0x0 0x10000 + 0x0 0xd2090000 0x0 0x10000 + 0x0 0xd20a0000 0x0 0x10000 + 0x0 0xd20b0000 0x0 0x10000 + 0x0 0xd20c0000 0x0 0x10000 + 0x0 0xd20d0000 0x0 0x10000 + 0x0 0xd20e0000 0x0 0x10000 + 0x0 0xd20f0000 0x0 0x10000 + 0x0 0xd2100000 0x0 0x10000>; + interrupt-parent = <&p0_mbigen_sec_a>; + iommus = <&p0_smmu_alg_a 0x600>; + dma-coherent; + interrupts = <576 4>, + <577 1>, <578 4>, + <579 1>, <580 4>, + <581 1>, <582 4>, + <583 1>, <584 4>, + <585 1>, <586 4>, + <587 1>, <588 4>, + <589 1>, <590 4>, + <591 1>, <592 4>, + <593 1>, <594 4>, + <595 1>, <596 4>, + <597 1>, <598 4>, + <599 1>, <600 4>, + <601 1>, <602 4>, + <603 1>, <604 4>, + <605 1>, <606 4>, + <607 1>, <608 4>; + }; + p0_sec_b: crypto@8,d2000000 { + compatible = "hisilicon,hip07-sec"; + reg = <0x8 0xd0000000 0x0 0x10000 + 0x8 0xd2000000 0x0 0x10000 + 0x8 0xd2010000 0x0 0x10000 + 0x8 0xd2020000 0x0 0x10000 + 0x8 0xd2030000 0x0 0x10000 + 0x8 0xd2040000 0x0 0x10000 + 0x8 0xd2050000 0x0 0x10000 + 0x8 0xd2060000 0x0 0x10000 + 0x8 0xd2070000 0x0 0x10000 + 0x8 0xd2080000 0x0 0x10000 + 0x8 0xd2090000 0x0 0x10000 + 0x8 0xd20a0000 0x0 0x10000 + 0x8 0xd20b0000 0x0 0x10000 + 0x8 0xd20c0000 0x0 0x10000 + 0x8 0xd20d0000 0x0 0x10000 + 0x8 0xd20e0000 0x0 0x10000 + 0x8 0xd20f0000 0x0 0x10000 + 0x8 0xd2100000 0x0 0x10000>; + interrupt-parent = <&p0_mbigen_sec_b>; + iommus = <&p0_smmu_alg_b 0x600>; + dma-coherent; + interrupts = <576 4>, + <577 1>, <578 4>, + <579 1>, <580 4>, + <581 1>, <582 4>, + <583 1>, <584 4>, + <585 1>, <586 4>, + <587 1>, <588 4>, + <589 1>, <590 4>, + <591 1>, <592 4>, + <593 1>, <594 4>, + <595 1>, <596 4>, + <597 1>, <598 4>, + <599 1>, <600 4>, + <601 1>, <602 4>, + <603 1>, <604 4>, + <605 1>, <606 4>, + <607 1>, <608 4>; + }; + p1_sec_a: crypto@400,d2000000 { + compatible = "hisilicon,hip07-sec"; + reg = <0x400 0xd0000000 0x0 0x10000 + 0x400 0xd2000000 0x0 0x10000 + 0x400 0xd2010000 0x0 0x10000 + 0x400 0xd2020000 0x0 0x10000 + 0x400 0xd2030000 0x0 0x10000 + 0x400 0xd2040000 0x0 0x10000 + 0x400 0xd2050000 0x0 0x10000 + 0x400 0xd2060000 0x0 0x10000 + 0x400 0xd2070000 0x0 0x10000 + 0x400 0xd2080000 0x0 0x10000 + 0x400 0xd2090000 0x0 0x10000 + 0x400 0xd20a0000 0x0 0x10000 + 0x400 0xd20b0000 0x0 0x10000 + 0x400 0xd20c0000 0x0 0x10000 + 0x400 0xd20d0000 0x0 0x10000 + 0x400 0xd20e0000 0x0 0x10000 + 0x400 0xd20f0000 0x0 0x10000 + 0x400 0xd2100000 0x0 0x10000>; + interrupt-parent = <&p1_mbigen_sec_a>; + iommus = <&p1_smmu_alg_a 0x600>; + dma-coherent; + interrupts = <576 4>, + <577 1>, <578 4>, + <579 1>, <580 4>, + <581 1>, <582 4>, + <583 1>, <584 4>, + <585 1>, <586 4>, + <587 1>, <588 4>, + <589 1>, <590 4>, + <591 1>, <592 4>, + <593 1>, <594 4>, + <595 1>, <596 4>, + <597 1>, <598 4>, + <599 1>, <600 4>, + <601 1>, <602 4>, + <603 1>, <604 4>, + <605 1>, <606 4>, + <607 1>, <608 4>; + }; + p1_sec_b: crypto@408,d2000000 { + compatible = "hisilicon,hip07-sec"; + reg = <0x408 0xd0000000 0x0 0x10000 + 0x408 0xd2000000 0x0 0x10000 + 0x408 0xd2010000 0x0 0x10000 + 0x408 0xd2020000 0x0 0x10000 + 0x408 0xd2030000 0x0 0x10000 + 0x408 0xd2040000 0x0 0x10000 + 0x408 0xd2050000 0x0 0x10000 + 0x408 0xd2060000 0x0 0x10000 + 0x408 0xd2070000 0x0 0x10000 + 0x408 0xd2080000 0x0 0x10000 + 0x408 0xd2090000 0x0 0x10000 + 0x408 0xd20a0000 0x0 0x10000 + 0x408 0xd20b0000 0x0 0x10000 + 0x408 0xd20c0000 0x0 0x10000 + 0x408 0xd20d0000 0x0 0x10000 + 0x408 0xd20e0000 0x0 0x10000 + 0x408 0xd20f0000 0x0 0x10000 + 0x408 0xd2100000 0x0 0x10000>; + interrupt-parent = <&p1_mbigen_sec_b>; + iommus = <&p1_smmu_alg_b 0x600>; + dma-coherent; + interrupts = <576 4>, + <577 1>, <578 4>, + <579 1>, <580 4>, + <581 1>, <582 4>, + <583 1>, <584 4>, + <585 1>, <586 4>, + <587 1>, <588 4>, + <589 1>, <590 4>, + <591 1>, <592 4>, + <593 1>, <594 4>, + <595 1>, <596 4>, + <597 1>, <598 4>, + <599 1>, <600 4>, + <601 1>, <602 4>, + <603 1>, <604 4>, + <605 1>, <606 4>, + <607 1>, <608 4>; + }; + }; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index f9a186f6af8a..514787d45dee 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -193,6 +193,7 @@ CONFIG_SCSI_HISI_SAS=y CONFIG_SCSI_HISI_SAS_PCI=y CONFIG_SCSI_UFSHCD=m CONFIG_SCSI_UFSHCD_PLATFORM=m +CONFIG_SCSI_UFS_HISI=y CONFIG_SCSI_UFS_QCOM=m CONFIG_ATA=y CONFIG_SATA_AHCI=y @@ -372,8 +373,8 @@ CONFIG_UNIPHIER_WATCHDOG=y CONFIG_BCM2835_WDT=y CONFIG_MFD_AXP20X_RSB=y CONFIG_MFD_CROS_EC=y -CONFIG_MFD_CROS_EC_I2C=y -CONFIG_MFD_CROS_EC_SPI=y +CONFIG_CROS_EC_I2C=y +CONFIG_CROS_EC_SPI=y CONFIG_MFD_CROS_EC_CHARDEV=m CONFIG_MFD_EXYNOS_LPASS=m CONFIG_MFD_HI6421_PMIC=y diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S index 88f5aef7934c..e3a375c4cb83 100644 --- a/arch/arm64/crypto/aes-ce-ccm-core.S +++ b/arch/arm64/crypto/aes-ce-ccm-core.S @@ -19,33 +19,24 @@ * u32 *macp, u8 const rk[], u32 rounds); */ ENTRY(ce_aes_ccm_auth_data) - frame_push 7 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - - ldr w25, [x22] /* leftover from prev round? */ + ldr w8, [x3] /* leftover from prev round? */ ld1 {v0.16b}, [x0] /* load mac */ - cbz w25, 1f - sub w25, w25, #16 + cbz w8, 1f + sub w8, w8, #16 eor v1.16b, v1.16b, v1.16b -0: ldrb w7, [x20], #1 /* get 1 byte of input */ - subs w21, w21, #1 - add w25, w25, #1 +0: ldrb w7, [x1], #1 /* get 1 byte of input */ + subs w2, w2, #1 + add w8, w8, #1 ins v1.b[0], w7 ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */ beq 8f /* out of input? */ - cbnz w25, 0b + cbnz w8, 0b eor v0.16b, v0.16b, v1.16b -1: ld1 {v3.4s}, [x23] /* load first round key */ - prfm pldl1strm, [x20] - cmp w24, #12 /* which key size? */ - add x6, x23, #16 - sub w7, w24, #2 /* modified # of rounds */ +1: ld1 {v3.4s}, [x4] /* load first round key */ + prfm pldl1strm, [x1] + cmp w5, #12 /* which key size? */ + add x6, x4, #16 + sub w7, w5, #2 /* modified # of rounds */ bmi 2f bne 5f mov v5.16b, v3.16b @@ -64,43 +55,33 @@ ENTRY(ce_aes_ccm_auth_data) ld1 {v5.4s}, [x6], #16 /* load next round key */ bpl 3b aese v0.16b, v4.16b - subs w21, w21, #16 /* last data? */ + subs w2, w2, #16 /* last data? */ eor v0.16b, v0.16b, v5.16b /* final round */ bmi 6f - ld1 {v1.16b}, [x20], #16 /* load next input block */ + ld1 {v1.16b}, [x1], #16 /* load next input block */ eor v0.16b, v0.16b, v1.16b /* xor with mac */ - beq 6f - - if_will_cond_yield_neon - st1 {v0.16b}, [x19] /* store mac */ - do_cond_yield_neon - ld1 {v0.16b}, [x19] /* reload mac */ - endif_yield_neon - - b 1b -6: st1 {v0.16b}, [x19] /* store mac */ + bne 1b +6: st1 {v0.16b}, [x0] /* store mac */ beq 10f - adds w21, w21, #16 + adds w2, w2, #16 beq 10f - mov w25, w21 -7: ldrb w7, [x20], #1 + mov w8, w2 +7: ldrb w7, [x1], #1 umov w6, v0.b[0] eor w6, w6, w7 - strb w6, [x19], #1 - subs w21, w21, #1 + strb w6, [x0], #1 + subs w2, w2, #1 beq 10f ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */ b 7b -8: mov w7, w25 - add w25, w25, #16 +8: mov w7, w8 + add w8, w8, #16 9: ext v1.16b, v1.16b, v1.16b, #1 adds w7, w7, #1 bne 9b eor v0.16b, v0.16b, v1.16b - st1 {v0.16b}, [x19] -10: str w25, [x22] - - frame_pop + st1 {v0.16b}, [x0] +10: str w8, [x3] ret ENDPROC(ce_aes_ccm_auth_data) @@ -145,29 +126,19 @@ ENTRY(ce_aes_ccm_final) ENDPROC(ce_aes_ccm_final) .macro aes_ccm_do_crypt,enc - frame_push 8 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 - - ldr x26, [x25, #8] /* load lower ctr */ - ld1 {v0.16b}, [x24] /* load mac */ -CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ + ldr x8, [x6, #8] /* load lower ctr */ + ld1 {v0.16b}, [x5] /* load mac */ +CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */ 0: /* outer loop */ - ld1 {v1.8b}, [x25] /* load upper ctr */ - prfm pldl1strm, [x20] - add x26, x26, #1 - rev x9, x26 - cmp w23, #12 /* which key size? */ - sub w7, w23, #2 /* get modified # of rounds */ + ld1 {v1.8b}, [x6] /* load upper ctr */ + prfm pldl1strm, [x1] + add x8, x8, #1 + rev x9, x8 + cmp w4, #12 /* which key size? */ + sub w7, w4, #2 /* get modified # of rounds */ ins v1.d[1], x9 /* no carry in lower ctr */ - ld1 {v3.4s}, [x22] /* load first round key */ - add x10, x22, #16 + ld1 {v3.4s}, [x3] /* load first round key */ + add x10, x3, #16 bmi 1f bne 4f mov v5.16b, v3.16b @@ -194,9 +165,9 @@ CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ bpl 2b aese v0.16b, v4.16b aese v1.16b, v4.16b - subs w21, w21, #16 - bmi 7f /* partial block? */ - ld1 {v2.16b}, [x20], #16 /* load next input block */ + subs w2, w2, #16 + bmi 6f /* partial block? */ + ld1 {v2.16b}, [x1], #16 /* load next input block */ .if \enc == 1 eor v2.16b, v2.16b, v5.16b /* final round enc+mac */ eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */ @@ -205,29 +176,18 @@ CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ eor v1.16b, v2.16b, v5.16b /* final round enc */ .endif eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */ - st1 {v1.16b}, [x19], #16 /* write output block */ - beq 5f - - if_will_cond_yield_neon - st1 {v0.16b}, [x24] /* store mac */ - do_cond_yield_neon - ld1 {v0.16b}, [x24] /* reload mac */ - endif_yield_neon - - b 0b -5: -CPU_LE( rev x26, x26 ) - st1 {v0.16b}, [x24] /* store mac */ - str x26, [x25, #8] /* store lsb end of ctr (BE) */ - -6: frame_pop - ret - -7: eor v0.16b, v0.16b, v5.16b /* final round mac */ + st1 {v1.16b}, [x0], #16 /* write output block */ + bne 0b +CPU_LE( rev x8, x8 ) + st1 {v0.16b}, [x5] /* store mac */ + str x8, [x6, #8] /* store lsb end of ctr (BE) */ +5: ret + +6: eor v0.16b, v0.16b, v5.16b /* final round mac */ eor v1.16b, v1.16b, v5.16b /* final round enc */ - st1 {v0.16b}, [x24] /* store mac */ - add w21, w21, #16 /* process partial tail block */ -8: ldrb w9, [x20], #1 /* get 1 byte of input */ + st1 {v0.16b}, [x5] /* store mac */ + add w2, w2, #16 /* process partial tail block */ +7: ldrb w9, [x1], #1 /* get 1 byte of input */ umov w6, v1.b[0] /* get top crypted ctr byte */ umov w7, v0.b[0] /* get top mac byte */ .if \enc == 1 @@ -237,13 +197,13 @@ CPU_LE( rev x26, x26 ) eor w9, w9, w6 eor w7, w7, w9 .endif - strb w9, [x19], #1 /* store out byte */ - strb w7, [x24], #1 /* store mac byte */ - subs w21, w21, #1 - beq 6b + strb w9, [x0], #1 /* store out byte */ + strb w7, [x5], #1 /* store mac byte */ + subs w2, w2, #1 + beq 5b ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */ ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */ - b 8b + b 7b .endm /* diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index e3e50950a863..adcb83eb683c 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -567,7 +567,6 @@ static struct shash_alg mac_algs[] = { { .base.cra_name = "cmac(aes)", .base.cra_driver_name = "cmac-aes-" MODE, .base.cra_priority = PRIO, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct mac_tfm_ctx) + 2 * AES_BLOCK_SIZE, @@ -583,7 +582,6 @@ static struct shash_alg mac_algs[] = { { .base.cra_name = "xcbc(aes)", .base.cra_driver_name = "xcbc-aes-" MODE, .base.cra_priority = PRIO, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct mac_tfm_ctx) + 2 * AES_BLOCK_SIZE, @@ -599,7 +597,6 @@ static struct shash_alg mac_algs[] = { { .base.cra_name = "cbcmac(aes)", .base.cra_driver_name = "cbcmac-aes-" MODE, .base.cra_priority = PRIO, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = 1, .base.cra_ctxsize = sizeof(struct mac_tfm_ctx), .base.cra_module = THIS_MODULE, diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S index dcffb9e77589..1b319b716d5e 100644 --- a/arch/arm64/crypto/ghash-ce-core.S +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -1,7 +1,7 @@ /* * Accelerated GHASH implementation with ARMv8 PMULL instructions. * - * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -46,6 +46,19 @@ ss3 .req v26 ss4 .req v27 + XL2 .req v8 + XM2 .req v9 + XH2 .req v10 + XL3 .req v11 + XM3 .req v12 + XH3 .req v13 + TT3 .req v14 + TT4 .req v15 + HH .req v16 + HH3 .req v17 + HH4 .req v18 + HH34 .req v19 + .text .arch armv8-a+crypto @@ -134,11 +147,25 @@ .endm .macro __pmull_pre_p64 + add x8, x3, #16 + ld1 {HH.2d-HH4.2d}, [x8] + + trn1 SHASH2.2d, SHASH.2d, HH.2d + trn2 T1.2d, SHASH.2d, HH.2d + eor SHASH2.16b, SHASH2.16b, T1.16b + + trn1 HH34.2d, HH3.2d, HH4.2d + trn2 T1.2d, HH3.2d, HH4.2d + eor HH34.16b, HH34.16b, T1.16b + movi MASK.16b, #0xe1 shl MASK.2d, MASK.2d, #57 .endm .macro __pmull_pre_p8 + ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 + eor SHASH2.16b, SHASH2.16b, SHASH.16b + // k00_16 := 0x0000000000000000_000000000000ffff // k32_48 := 0x00000000ffffffff_0000ffffffffffff movi k32_48.2d, #0xffffffff @@ -213,31 +240,88 @@ .endm .macro __pmull_ghash, pn - frame_push 5 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - -0: ld1 {SHASH.2d}, [x22] - ld1 {XL.2d}, [x20] - ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 - eor SHASH2.16b, SHASH2.16b, SHASH.16b + ld1 {SHASH.2d}, [x3] + ld1 {XL.2d}, [x1] __pmull_pre_\pn /* do the head block first, if supplied */ - cbz x23, 1f - ld1 {T1.2d}, [x23] - mov x23, xzr - b 2f + cbz x4, 0f + ld1 {T1.2d}, [x4] + mov x4, xzr + b 3f + +0: .ifc \pn, p64 + tbnz w0, #0, 2f // skip until #blocks is a + tbnz w0, #1, 2f // round multiple of 4 + +1: ld1 {XM3.16b-TT4.16b}, [x2], #64 + + sub w0, w0, #4 + + rev64 T1.16b, XM3.16b + rev64 T2.16b, XH3.16b + rev64 TT4.16b, TT4.16b + rev64 TT3.16b, TT3.16b + + ext IN1.16b, TT4.16b, TT4.16b, #8 + ext XL3.16b, TT3.16b, TT3.16b, #8 + + eor TT4.16b, TT4.16b, IN1.16b + pmull2 XH2.1q, SHASH.2d, IN1.2d // a1 * b1 + pmull XL2.1q, SHASH.1d, IN1.1d // a0 * b0 + pmull XM2.1q, SHASH2.1d, TT4.1d // (a1 + a0)(b1 + b0) + + eor TT3.16b, TT3.16b, XL3.16b + pmull2 XH3.1q, HH.2d, XL3.2d // a1 * b1 + pmull XL3.1q, HH.1d, XL3.1d // a0 * b0 + pmull2 XM3.1q, SHASH2.2d, TT3.2d // (a1 + a0)(b1 + b0) + + ext IN1.16b, T2.16b, T2.16b, #8 + eor XL2.16b, XL2.16b, XL3.16b + eor XH2.16b, XH2.16b, XH3.16b + eor XM2.16b, XM2.16b, XM3.16b + + eor T2.16b, T2.16b, IN1.16b + pmull2 XH3.1q, HH3.2d, IN1.2d // a1 * b1 + pmull XL3.1q, HH3.1d, IN1.1d // a0 * b0 + pmull XM3.1q, HH34.1d, T2.1d // (a1 + a0)(b1 + b0) -1: ld1 {T1.2d}, [x21], #16 - sub w19, w19, #1 + eor XL2.16b, XL2.16b, XL3.16b + eor XH2.16b, XH2.16b, XH3.16b + eor XM2.16b, XM2.16b, XM3.16b -2: /* multiply XL by SHASH in GF(2^128) */ + ext IN1.16b, T1.16b, T1.16b, #8 + ext TT3.16b, XL.16b, XL.16b, #8 + eor XL.16b, XL.16b, IN1.16b + eor T1.16b, T1.16b, TT3.16b + + pmull2 XH.1q, HH4.2d, XL.2d // a1 * b1 + eor T1.16b, T1.16b, XL.16b + pmull XL.1q, HH4.1d, XL.1d // a0 * b0 + pmull2 XM.1q, HH34.2d, T1.2d // (a1 + a0)(b1 + b0) + + eor XL.16b, XL.16b, XL2.16b + eor XH.16b, XH.16b, XH2.16b + eor XM.16b, XM.16b, XM2.16b + + eor T2.16b, XL.16b, XH.16b + ext T1.16b, XL.16b, XH.16b, #8 + eor XM.16b, XM.16b, T2.16b + + __pmull_reduce_p64 + + eor T2.16b, T2.16b, XH.16b + eor XL.16b, XL.16b, T2.16b + + cbz w0, 5f + b 1b + .endif + +2: ld1 {T1.2d}, [x2], #16 + sub w0, w0, #1 + +3: /* multiply XL by SHASH in GF(2^128) */ CPU_LE( rev64 T1.16b, T1.16b ) ext T2.16b, XL.16b, XL.16b, #8 @@ -250,7 +334,7 @@ CPU_LE( rev64 T1.16b, T1.16b ) __pmull_\pn XL, XL, SHASH // a0 * b0 __pmull_\pn XM, T1, SHASH2 // (a1 + a0)(b1 + b0) - eor T2.16b, XL.16b, XH.16b +4: eor T2.16b, XL.16b, XH.16b ext T1.16b, XL.16b, XH.16b, #8 eor XM.16b, XM.16b, T2.16b @@ -259,18 +343,9 @@ CPU_LE( rev64 T1.16b, T1.16b ) eor T2.16b, T2.16b, XH.16b eor XL.16b, XL.16b, T2.16b - cbz w19, 3f + cbnz w0, 0b - if_will_cond_yield_neon - st1 {XL.2d}, [x20] - do_cond_yield_neon - b 0b - endif_yield_neon - - b 1b - -3: st1 {XL.2d}, [x20] - frame_pop +5: st1 {XL.2d}, [x1] ret .endm @@ -286,9 +361,10 @@ ENTRY(pmull_ghash_update_p8) __pmull_ghash p8 ENDPROC(pmull_ghash_update_p8) - KS .req v8 - CTR .req v9 - INP .req v10 + KS0 .req v12 + KS1 .req v13 + INP0 .req v14 + INP1 .req v15 .macro load_round_keys, rounds, rk cmp \rounds, #12 @@ -322,142 +398,153 @@ ENDPROC(pmull_ghash_update_p8) .endm .macro pmull_gcm_do_crypt, enc - frame_push 10 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 - mov x26, x7 - .if \enc == 1 - ldr x27, [sp, #96] // first stacked arg - .endif - - ldr x28, [x24, #8] // load lower counter -CPU_LE( rev x28, x28 ) - -0: mov x0, x25 - load_round_keys w26, x0 - ld1 {SHASH.2d}, [x23] - ld1 {XL.2d}, [x20] + ld1 {SHASH.2d}, [x4], #16 + ld1 {HH.2d}, [x4] + ld1 {XL.2d}, [x1] + ldr x8, [x5, #8] // load lower counter movi MASK.16b, #0xe1 - ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 + trn1 SHASH2.2d, SHASH.2d, HH.2d + trn2 T1.2d, SHASH.2d, HH.2d +CPU_LE( rev x8, x8 ) shl MASK.2d, MASK.2d, #57 - eor SHASH2.16b, SHASH2.16b, SHASH.16b + eor SHASH2.16b, SHASH2.16b, T1.16b .if \enc == 1 - ld1 {KS.16b}, [x27] + ldr x10, [sp] + ld1 {KS0.16b-KS1.16b}, [x10] .endif -1: ld1 {CTR.8b}, [x24] // load upper counter - ld1 {INP.16b}, [x22], #16 - rev x9, x28 - add x28, x28, #1 - sub w19, w19, #1 - ins CTR.d[1], x9 // set lower counter + cbnz x6, 4f + +0: ld1 {INP0.16b-INP1.16b}, [x3], #32 + + rev x9, x8 + add x11, x8, #1 + add x8, x8, #2 .if \enc == 1 - eor INP.16b, INP.16b, KS.16b // encrypt input - st1 {INP.16b}, [x21], #16 + eor INP0.16b, INP0.16b, KS0.16b // encrypt input + eor INP1.16b, INP1.16b, KS1.16b .endif - rev64 T1.16b, INP.16b + ld1 {KS0.8b}, [x5] // load upper counter + rev x11, x11 + sub w0, w0, #2 + mov KS1.8b, KS0.8b + ins KS0.d[1], x9 // set lower counter + ins KS1.d[1], x11 - cmp w26, #12 - b.ge 4f // AES-192/256? + rev64 T1.16b, INP1.16b -2: enc_round CTR, v21 + cmp w7, #12 + b.ge 2f // AES-192/256? - ext T2.16b, XL.16b, XL.16b, #8 +1: enc_round KS0, v21 ext IN1.16b, T1.16b, T1.16b, #8 - enc_round CTR, v22 + enc_round KS1, v21 + pmull2 XH2.1q, SHASH.2d, IN1.2d // a1 * b1 + + enc_round KS0, v22 + eor T1.16b, T1.16b, IN1.16b + + enc_round KS1, v22 + pmull XL2.1q, SHASH.1d, IN1.1d // a0 * b0 + enc_round KS0, v23 + pmull XM2.1q, SHASH2.1d, T1.1d // (a1 + a0)(b1 + b0) + + enc_round KS1, v23 + rev64 T1.16b, INP0.16b + ext T2.16b, XL.16b, XL.16b, #8 + + enc_round KS0, v24 + ext IN1.16b, T1.16b, T1.16b, #8 eor T1.16b, T1.16b, T2.16b - eor XL.16b, XL.16b, IN1.16b - enc_round CTR, v23 + enc_round KS1, v24 + eor XL.16b, XL.16b, IN1.16b - pmull2 XH.1q, SHASH.2d, XL.2d // a1 * b1 + enc_round KS0, v25 eor T1.16b, T1.16b, XL.16b - enc_round CTR, v24 + enc_round KS1, v25 + pmull2 XH.1q, HH.2d, XL.2d // a1 * b1 + + enc_round KS0, v26 + pmull XL.1q, HH.1d, XL.1d // a0 * b0 - pmull XL.1q, SHASH.1d, XL.1d // a0 * b0 - pmull XM.1q, SHASH2.1d, T1.1d // (a1 + a0)(b1 + b0) + enc_round KS1, v26 + pmull2 XM.1q, SHASH2.2d, T1.2d // (a1 + a0)(b1 + b0) - enc_round CTR, v25 + enc_round KS0, v27 + eor XL.16b, XL.16b, XL2.16b + eor XH.16b, XH.16b, XH2.16b + enc_round KS1, v27 + eor XM.16b, XM.16b, XM2.16b ext T1.16b, XL.16b, XH.16b, #8 + + enc_round KS0, v28 eor T2.16b, XL.16b, XH.16b eor XM.16b, XM.16b, T1.16b - enc_round CTR, v26 - + enc_round KS1, v28 eor XM.16b, XM.16b, T2.16b - pmull T2.1q, XL.1d, MASK.1d - enc_round CTR, v27 + enc_round KS0, v29 + pmull T2.1q, XL.1d, MASK.1d + enc_round KS1, v29 mov XH.d[0], XM.d[1] mov XM.d[1], XL.d[0] - enc_round CTR, v28 - + aese KS0.16b, v30.16b eor XL.16b, XM.16b, T2.16b - enc_round CTR, v29 - + aese KS1.16b, v30.16b ext T2.16b, XL.16b, XL.16b, #8 - aese CTR.16b, v30.16b - + eor KS0.16b, KS0.16b, v31.16b pmull XL.1q, XL.1d, MASK.1d eor T2.16b, T2.16b, XH.16b - eor KS.16b, CTR.16b, v31.16b - + eor KS1.16b, KS1.16b, v31.16b eor XL.16b, XL.16b, T2.16b .if \enc == 0 - eor INP.16b, INP.16b, KS.16b - st1 {INP.16b}, [x21], #16 + eor INP0.16b, INP0.16b, KS0.16b + eor INP1.16b, INP1.16b, KS1.16b .endif - cbz w19, 3f + st1 {INP0.16b-INP1.16b}, [x2], #32 - if_will_cond_yield_neon - st1 {XL.2d}, [x20] - .if \enc == 1 - st1 {KS.16b}, [x27] - .endif - do_cond_yield_neon - b 0b - endif_yield_neon + cbnz w0, 0b - b 1b +CPU_LE( rev x8, x8 ) + st1 {XL.2d}, [x1] + str x8, [x5, #8] // store lower counter -3: st1 {XL.2d}, [x20] .if \enc == 1 - st1 {KS.16b}, [x27] + st1 {KS0.16b-KS1.16b}, [x10] .endif -CPU_LE( rev x28, x28 ) - str x28, [x24, #8] // store lower counter - - frame_pop ret -4: b.eq 5f // AES-192? - enc_round CTR, v17 - enc_round CTR, v18 -5: enc_round CTR, v19 - enc_round CTR, v20 - b 2b +2: b.eq 3f // AES-192? + enc_round KS0, v17 + enc_round KS1, v17 + enc_round KS0, v18 + enc_round KS1, v18 +3: enc_round KS0, v19 + enc_round KS1, v19 + enc_round KS0, v20 + enc_round KS1, v20 + b 1b + +4: load_round_keys w7, x6 + b 0b .endm /* diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 7cf0b1aa6ea8..6e9f33d14930 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -1,7 +1,7 @@ /* * Accelerated GHASH implementation with ARMv8 PMULL instructions. * - * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -33,9 +33,12 @@ MODULE_ALIAS_CRYPTO("ghash"); #define GCM_IV_SIZE 12 struct ghash_key { - u64 a; - u64 b; - be128 k; + u64 h[2]; + u64 h2[2]; + u64 h3[2]; + u64 h4[2]; + + be128 k; }; struct ghash_desc_ctx { @@ -113,6 +116,9 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src, } } +/* avoid hogging the CPU for too long */ +#define MAX_BLOCKS (SZ_64K / GHASH_BLOCK_SIZE) + static int ghash_update(struct shash_desc *desc, const u8 *src, unsigned int len) { @@ -136,11 +142,16 @@ static int ghash_update(struct shash_desc *desc, const u8 *src, blocks = len / GHASH_BLOCK_SIZE; len %= GHASH_BLOCK_SIZE; - ghash_do_update(blocks, ctx->digest, src, key, - partial ? ctx->buf : NULL); + do { + int chunk = min(blocks, MAX_BLOCKS); - src += blocks * GHASH_BLOCK_SIZE; - partial = 0; + ghash_do_update(chunk, ctx->digest, src, key, + partial ? ctx->buf : NULL); + + blocks -= chunk; + src += chunk * GHASH_BLOCK_SIZE; + partial = 0; + } while (unlikely(blocks > 0)); } if (len) memcpy(ctx->buf + partial, src, len); @@ -166,23 +177,36 @@ static int ghash_final(struct shash_desc *desc, u8 *dst) return 0; } +static void ghash_reflect(u64 h[], const be128 *k) +{ + u64 carry = be64_to_cpu(k->a) & BIT(63) ? 1 : 0; + + h[0] = (be64_to_cpu(k->b) << 1) | carry; + h[1] = (be64_to_cpu(k->a) << 1) | (be64_to_cpu(k->b) >> 63); + + if (carry) + h[1] ^= 0xc200000000000000UL; +} + static int __ghash_setkey(struct ghash_key *key, const u8 *inkey, unsigned int keylen) { - u64 a, b; + be128 h; /* needed for the fallback */ memcpy(&key->k, inkey, GHASH_BLOCK_SIZE); - /* perform multiplication by 'x' in GF(2^128) */ - b = get_unaligned_be64(inkey); - a = get_unaligned_be64(inkey + 8); + ghash_reflect(key->h, &key->k); - key->a = (a << 1) | (b >> 63); - key->b = (b << 1) | (a >> 63); + h = key->k; + gf128mul_lle(&h, &key->k); + ghash_reflect(key->h2, &h); - if (b >> 63) - key->b ^= 0xc200000000000000UL; + gf128mul_lle(&h, &key->k); + ghash_reflect(key->h3, &h); + + gf128mul_lle(&h, &key->k); + ghash_reflect(key->h4, &h); return 0; } @@ -204,7 +228,6 @@ static struct shash_alg ghash_alg = { .base.cra_name = "ghash", .base.cra_driver_name = "ghash-ce", .base.cra_priority = 200, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = GHASH_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct ghash_key), .base.cra_module = THIS_MODULE, @@ -245,7 +268,7 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey, __aes_arm64_encrypt(ctx->aes_key.key_enc, key, (u8[AES_BLOCK_SIZE]){}, num_rounds(&ctx->aes_key)); - return __ghash_setkey(&ctx->ghash_key, key, sizeof(key)); + return __ghash_setkey(&ctx->ghash_key, key, sizeof(be128)); } static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize) @@ -349,9 +372,10 @@ static int gcm_encrypt(struct aead_request *req) struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead); struct skcipher_walk walk; u8 iv[AES_BLOCK_SIZE]; - u8 ks[AES_BLOCK_SIZE]; + u8 ks[2 * AES_BLOCK_SIZE]; u8 tag[AES_BLOCK_SIZE]; u64 dg[2] = {}; + int nrounds = num_rounds(&ctx->aes_key); int err; if (req->assoclen) @@ -360,39 +384,39 @@ static int gcm_encrypt(struct aead_request *req) memcpy(iv, req->iv, GCM_IV_SIZE); put_unaligned_be32(1, iv + GCM_IV_SIZE); - if (likely(may_use_simd())) { - kernel_neon_begin(); + err = skcipher_walk_aead_encrypt(&walk, req, false); - pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, - num_rounds(&ctx->aes_key)); + if (likely(may_use_simd() && walk.total >= 2 * AES_BLOCK_SIZE)) { + u32 const *rk = NULL; + + kernel_neon_begin(); + pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - pmull_gcm_encrypt_block(ks, iv, NULL, - num_rounds(&ctx->aes_key)); + pmull_gcm_encrypt_block(ks, iv, NULL, nrounds); put_unaligned_be32(3, iv + GCM_IV_SIZE); - kernel_neon_end(); + pmull_gcm_encrypt_block(ks + AES_BLOCK_SIZE, iv, NULL, nrounds); + put_unaligned_be32(4, iv + GCM_IV_SIZE); - err = skcipher_walk_aead_encrypt(&walk, req, false); + do { + int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2; - while (walk.nbytes >= AES_BLOCK_SIZE) { - int blocks = walk.nbytes / AES_BLOCK_SIZE; + if (rk) + kernel_neon_begin(); - kernel_neon_begin(); pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr, walk.src.virt.addr, &ctx->ghash_key, - iv, ctx->aes_key.key_enc, - num_rounds(&ctx->aes_key), ks); + iv, rk, nrounds, ks); kernel_neon_end(); err = skcipher_walk_done(&walk, - walk.nbytes % AES_BLOCK_SIZE); - } + walk.nbytes % (2 * AES_BLOCK_SIZE)); + + rk = ctx->aes_key.key_enc; + } while (walk.nbytes >= 2 * AES_BLOCK_SIZE); } else { - __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, - num_rounds(&ctx->aes_key)); + __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - err = skcipher_walk_aead_encrypt(&walk, req, false); - while (walk.nbytes >= AES_BLOCK_SIZE) { int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *dst = walk.dst.virt.addr; @@ -400,8 +424,7 @@ static int gcm_encrypt(struct aead_request *req) do { __aes_arm64_encrypt(ctx->aes_key.key_enc, - ks, iv, - num_rounds(&ctx->aes_key)); + ks, iv, nrounds); crypto_xor_cpy(dst, src, ks, AES_BLOCK_SIZE); crypto_inc(iv, AES_BLOCK_SIZE); @@ -418,19 +441,28 @@ static int gcm_encrypt(struct aead_request *req) } if (walk.nbytes) __aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv, - num_rounds(&ctx->aes_key)); + nrounds); } /* handle the tail */ if (walk.nbytes) { u8 buf[GHASH_BLOCK_SIZE]; + unsigned int nbytes = walk.nbytes; + u8 *dst = walk.dst.virt.addr; + u8 *head = NULL; crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, ks, walk.nbytes); - memcpy(buf, walk.dst.virt.addr, walk.nbytes); - memset(buf + walk.nbytes, 0, GHASH_BLOCK_SIZE - walk.nbytes); - ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL); + if (walk.nbytes > GHASH_BLOCK_SIZE) { + head = dst; + dst += GHASH_BLOCK_SIZE; + nbytes %= GHASH_BLOCK_SIZE; + } + + memcpy(buf, dst, nbytes); + memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes); + ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head); err = skcipher_walk_done(&walk, 0); } @@ -453,10 +485,11 @@ static int gcm_decrypt(struct aead_request *req) struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead); unsigned int authsize = crypto_aead_authsize(aead); struct skcipher_walk walk; - u8 iv[AES_BLOCK_SIZE]; + u8 iv[2 * AES_BLOCK_SIZE]; u8 tag[AES_BLOCK_SIZE]; - u8 buf[GHASH_BLOCK_SIZE]; + u8 buf[2 * GHASH_BLOCK_SIZE]; u64 dg[2] = {}; + int nrounds = num_rounds(&ctx->aes_key); int err; if (req->assoclen) @@ -465,39 +498,53 @@ static int gcm_decrypt(struct aead_request *req) memcpy(iv, req->iv, GCM_IV_SIZE); put_unaligned_be32(1, iv + GCM_IV_SIZE); - if (likely(may_use_simd())) { - kernel_neon_begin(); + err = skcipher_walk_aead_decrypt(&walk, req, false); + + if (likely(may_use_simd() && walk.total >= 2 * AES_BLOCK_SIZE)) { + u32 const *rk = NULL; - pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, - num_rounds(&ctx->aes_key)); + kernel_neon_begin(); + pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - kernel_neon_end(); - err = skcipher_walk_aead_decrypt(&walk, req, false); + do { + int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2; + int rem = walk.total - blocks * AES_BLOCK_SIZE; - while (walk.nbytes >= AES_BLOCK_SIZE) { - int blocks = walk.nbytes / AES_BLOCK_SIZE; + if (rk) + kernel_neon_begin(); - kernel_neon_begin(); pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr, walk.src.virt.addr, &ctx->ghash_key, - iv, ctx->aes_key.key_enc, - num_rounds(&ctx->aes_key)); + iv, rk, nrounds); + + /* check if this is the final iteration of the loop */ + if (rem < (2 * AES_BLOCK_SIZE)) { + u8 *iv2 = iv + AES_BLOCK_SIZE; + + if (rem > AES_BLOCK_SIZE) { + memcpy(iv2, iv, AES_BLOCK_SIZE); + crypto_inc(iv2, AES_BLOCK_SIZE); + } + + pmull_gcm_encrypt_block(iv, iv, NULL, nrounds); + + if (rem > AES_BLOCK_SIZE) + pmull_gcm_encrypt_block(iv2, iv2, NULL, + nrounds); + } + kernel_neon_end(); err = skcipher_walk_done(&walk, - walk.nbytes % AES_BLOCK_SIZE); - } - if (walk.nbytes) - pmull_gcm_encrypt_block(iv, iv, NULL, - num_rounds(&ctx->aes_key)); + walk.nbytes % (2 * AES_BLOCK_SIZE)); + + rk = ctx->aes_key.key_enc; + } while (walk.nbytes >= 2 * AES_BLOCK_SIZE); } else { - __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, - num_rounds(&ctx->aes_key)); + __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - err = skcipher_walk_aead_decrypt(&walk, req, false); - while (walk.nbytes >= AES_BLOCK_SIZE) { int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *dst = walk.dst.virt.addr; @@ -508,8 +555,7 @@ static int gcm_decrypt(struct aead_request *req) do { __aes_arm64_encrypt(ctx->aes_key.key_enc, - buf, iv, - num_rounds(&ctx->aes_key)); + buf, iv, nrounds); crypto_xor_cpy(dst, src, buf, AES_BLOCK_SIZE); crypto_inc(iv, AES_BLOCK_SIZE); @@ -522,14 +568,24 @@ static int gcm_decrypt(struct aead_request *req) } if (walk.nbytes) __aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv, - num_rounds(&ctx->aes_key)); + nrounds); } /* handle the tail */ if (walk.nbytes) { - memcpy(buf, walk.src.virt.addr, walk.nbytes); - memset(buf + walk.nbytes, 0, GHASH_BLOCK_SIZE - walk.nbytes); - ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL); + const u8 *src = walk.src.virt.addr; + const u8 *head = NULL; + unsigned int nbytes = walk.nbytes; + + if (walk.nbytes > GHASH_BLOCK_SIZE) { + head = src; + src += GHASH_BLOCK_SIZE; + nbytes %= GHASH_BLOCK_SIZE; + } + + memcpy(buf, src, nbytes); + memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes); + ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head); crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, iv, walk.nbytes); @@ -554,7 +610,7 @@ static int gcm_decrypt(struct aead_request *req) static struct aead_alg gcm_aes_alg = { .ivsize = GCM_IV_SIZE, - .chunksize = AES_BLOCK_SIZE, + .chunksize = 2 * AES_BLOCK_SIZE, .maxauthsize = AES_BLOCK_SIZE, .setkey = gcm_setkey, .setauthsize = gcm_setauthsize, diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index efbeb3e0dcfb..17fac2889f56 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -99,7 +99,6 @@ static struct shash_alg alg = { .cra_name = "sha1", .cra_driver_name = "sha1-ce", .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index fd1ff2b13dfa..261f5195cab7 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -114,7 +114,6 @@ static struct shash_alg algs[] = { { .cra_name = "sha224", .cra_driver_name = "sha224-ce", .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -129,7 +128,6 @@ static struct shash_alg algs[] = { { .cra_name = "sha256", .cra_driver_name = "sha256-ce", .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c index e8880ccdc71f..4aedeaefd61f 100644 --- a/arch/arm64/crypto/sha256-glue.c +++ b/arch/arm64/crypto/sha256-glue.c @@ -67,8 +67,7 @@ static struct shash_alg algs[] = { { .descsize = sizeof(struct sha256_state), .base.cra_name = "sha256", .base.cra_driver_name = "sha256-arm64", - .base.cra_priority = 100, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, + .base.cra_priority = 125, .base.cra_blocksize = SHA256_BLOCK_SIZE, .base.cra_module = THIS_MODULE, }, { @@ -80,8 +79,7 @@ static struct shash_alg algs[] = { { .descsize = sizeof(struct sha256_state), .base.cra_name = "sha224", .base.cra_driver_name = "sha224-arm64", - .base.cra_priority = 100, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, + .base.cra_priority = 125, .base.cra_blocksize = SHA224_BLOCK_SIZE, .base.cra_module = THIS_MODULE, } }; @@ -153,7 +151,6 @@ static struct shash_alg neon_algs[] = { { .base.cra_name = "sha256", .base.cra_driver_name = "sha256-arm64-neon", .base.cra_priority = 150, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA256_BLOCK_SIZE, .base.cra_module = THIS_MODULE, }, { @@ -166,7 +163,6 @@ static struct shash_alg neon_algs[] = { { .base.cra_name = "sha224", .base.cra_driver_name = "sha224-arm64-neon", .base.cra_priority = 150, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA224_BLOCK_SIZE, .base.cra_module = THIS_MODULE, } }; diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c index da8222e528bd..a336feac0f59 100644 --- a/arch/arm64/crypto/sha3-ce-glue.c +++ b/arch/arm64/crypto/sha3-ce-glue.c @@ -105,7 +105,6 @@ static struct shash_alg algs[] = { { .descsize = sizeof(struct sha3_state), .base.cra_name = "sha3-224", .base.cra_driver_name = "sha3-224-ce", - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA3_224_BLOCK_SIZE, .base.cra_module = THIS_MODULE, .base.cra_priority = 200, @@ -117,7 +116,6 @@ static struct shash_alg algs[] = { { .descsize = sizeof(struct sha3_state), .base.cra_name = "sha3-256", .base.cra_driver_name = "sha3-256-ce", - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA3_256_BLOCK_SIZE, .base.cra_module = THIS_MODULE, .base.cra_priority = 200, @@ -129,7 +127,6 @@ static struct shash_alg algs[] = { { .descsize = sizeof(struct sha3_state), .base.cra_name = "sha3-384", .base.cra_driver_name = "sha3-384-ce", - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA3_384_BLOCK_SIZE, .base.cra_module = THIS_MODULE, .base.cra_priority = 200, @@ -141,7 +138,6 @@ static struct shash_alg algs[] = { { .descsize = sizeof(struct sha3_state), .base.cra_name = "sha3-512", .base.cra_driver_name = "sha3-512-ce", - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA3_512_BLOCK_SIZE, .base.cra_module = THIS_MODULE, .base.cra_priority = 200, diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c index a77c8632a589..f2c5f28c622a 100644 --- a/arch/arm64/crypto/sha512-ce-glue.c +++ b/arch/arm64/crypto/sha512-ce-glue.c @@ -87,7 +87,6 @@ static struct shash_alg algs[] = { { .base.cra_name = "sha384", .base.cra_driver_name = "sha384-ce", .base.cra_priority = 200, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA512_BLOCK_SIZE, .base.cra_module = THIS_MODULE, }, { @@ -100,7 +99,6 @@ static struct shash_alg algs[] = { { .base.cra_name = "sha512", .base.cra_driver_name = "sha512-ce", .base.cra_priority = 200, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA512_BLOCK_SIZE, .base.cra_module = THIS_MODULE, } }; diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c index 27db4851e380..325b23b43a9b 100644 --- a/arch/arm64/crypto/sha512-glue.c +++ b/arch/arm64/crypto/sha512-glue.c @@ -63,7 +63,6 @@ static struct shash_alg algs[] = { { .base.cra_name = "sha512", .base.cra_driver_name = "sha512-arm64", .base.cra_priority = 150, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA512_BLOCK_SIZE, .base.cra_module = THIS_MODULE, }, { @@ -76,7 +75,6 @@ static struct shash_alg algs[] = { { .base.cra_name = "sha384", .base.cra_driver_name = "sha384-arm64", .base.cra_priority = 150, - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SHA384_BLOCK_SIZE, .base.cra_module = THIS_MODULE, } }; diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c index 3b4948f7e26f..88938a20d9b2 100644 --- a/arch/arm64/crypto/sm3-ce-glue.c +++ b/arch/arm64/crypto/sm3-ce-glue.c @@ -72,7 +72,6 @@ static struct shash_alg sm3_alg = { .descsize = sizeof(struct sm3_state), .base.cra_name = "sm3", .base.cra_driver_name = "sm3-ce", - .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, .base.cra_blocksize = SM3_BLOCK_SIZE, .base.cra_module = THIS_MODULE, .base.cra_priority = 200, diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 3a9b84d39d71..6cd5d77b6b44 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -16,6 +16,7 @@ generic-y += mm-arch-hooks.h generic-y += msi.h generic-y += preempt.h generic-y += qrwlock.h +generic-y += qspinlock.h generic-y += rwsem.h generic-y += segment.h generic-y += serial.h diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 0db62a4cbce2..709208dfdc8b 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -12,10 +12,12 @@ #ifndef _ASM_ACPI_H #define _ASM_ACPI_H +#include <linux/efi.h> #include <linux/memblock.h> #include <linux/psci.h> #include <asm/cputype.h> +#include <asm/io.h> #include <asm/smp_plat.h> #include <asm/tlbflush.h> @@ -29,18 +31,22 @@ /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI +pgprot_t __acpi_get_mem_attribute(phys_addr_t addr); + /* ACPI table mapping after acpi_permanent_mmap is set */ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) { + /* For normal memory we already have a cacheable mapping. */ + if (memblock_is_map_memory(phys)) + return (void __iomem *)__phys_to_virt(phys); + /* - * EFI's reserve_regions() call adds memory with the WB attribute - * to memblock via early_init_dt_add_memory_arch(). + * We should still honor the memory's attribute here because + * crash dump kernel possibly excludes some ACPI (reclaim) + * regions from memblock list. */ - if (!memblock_is_memory(phys)) - return ioremap(phys, size); - - return ioremap_cache(phys, size); + return __ioremap(phys, size, __acpi_get_mem_attribute(phys)); } #define acpi_os_ioremap acpi_os_ioremap @@ -129,15 +135,20 @@ static inline const char *acpi_get_enable_method(int cpu) * for compatibility. */ #define acpi_disable_cmcff 1 -pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr); +static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) +{ + return __acpi_get_mem_attribute(addr); +} #endif /* CONFIG_ACPI_APEI */ #ifdef CONFIG_ACPI_NUMA int arm64_acpi_numa_init(void); -int acpi_numa_get_nid(unsigned int cpu, u64 hwid); +int acpi_numa_get_nid(unsigned int cpu); +void acpi_map_cpus_to_nodes(void); #else static inline int arm64_acpi_numa_init(void) { return -ENOSYS; } -static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; } +static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } +static inline void acpi_map_cpus_to_nodes(void) { } #endif /* CONFIG_ACPI_NUMA */ #define ACPI_TABLE_UPGRADE_MAX_PHYS MEMBLOCK_ALLOC_ACCESSIBLE diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index c0235e0ff849..9bca54dda75c 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -40,17 +40,6 @@ #include <asm/cmpxchg.h> -#define ___atomic_add_unless(v, a, u, sfx) \ -({ \ - typeof((v)->counter) c, old; \ - \ - c = atomic##sfx##_read(v); \ - while (c != (u) && \ - (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c) \ - c = old; \ - c; \ - }) - #define ATOMIC_INIT(i) { (i) } #define atomic_read(v) READ_ONCE((v)->counter) @@ -61,21 +50,11 @@ #define atomic_add_return_release atomic_add_return_release #define atomic_add_return atomic_add_return -#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) -#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) -#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - #define atomic_sub_return_relaxed atomic_sub_return_relaxed #define atomic_sub_return_acquire atomic_sub_return_acquire #define atomic_sub_return_release atomic_sub_return_release #define atomic_sub_return atomic_sub_return -#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) -#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) -#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) - #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed #define atomic_fetch_add_acquire atomic_fetch_add_acquire #define atomic_fetch_add_release atomic_fetch_add_release @@ -119,13 +98,6 @@ cmpxchg_release(&((v)->counter), (old), (new)) #define atomic_cmpxchg(v, old, new) cmpxchg(&((v)->counter), (old), (new)) -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) -#define atomic_add_negative(i, v) (atomic_add_return((i), (v)) < 0) -#define __atomic_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) #define atomic_andnot atomic_andnot /* @@ -140,21 +112,11 @@ #define atomic64_add_return_release atomic64_add_return_release #define atomic64_add_return atomic64_add_return -#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) -#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) -#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed #define atomic64_sub_return_acquire atomic64_sub_return_acquire #define atomic64_sub_return_release atomic64_sub_return_release #define atomic64_sub_return atomic64_sub_return -#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) -#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) -#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) - #define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed #define atomic64_fetch_add_acquire atomic64_fetch_add_acquire #define atomic64_fetch_add_release atomic64_fetch_add_release @@ -195,16 +157,9 @@ #define atomic64_cmpxchg_release atomic_cmpxchg_release #define atomic64_cmpxchg atomic_cmpxchg -#define atomic64_inc(v) atomic64_add(1, (v)) -#define atomic64_dec(v) atomic64_sub(1, (v)) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) -#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) -#define atomic64_add_negative(i, v) (atomic64_add_return((i), (v)) < 0) -#define atomic64_add_unless(v, a, u) (___atomic_add_unless(v, a, u, 64) != u) #define atomic64_andnot atomic64_andnot -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif #endif diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index f11518af96a9..822a9192c551 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -128,6 +128,19 @@ do { \ __u.__val; \ }) +#define smp_cond_load_relaxed(ptr, cond_expr) \ +({ \ + typeof(ptr) __PTR = (ptr); \ + typeof(*ptr) VAL; \ + for (;;) { \ + VAL = READ_ONCE(*__PTR); \ + if (cond_expr) \ + break; \ + __cmpwait_relaxed(__PTR, VAL); \ + } \ + VAL; \ +}) + #define smp_cond_load_acquire(ptr, cond_expr) \ ({ \ typeof(ptr) __PTR = (ptr); \ diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h index 9c19594ce7cb..10d536b1af74 100644 --- a/arch/arm64/include/asm/bitops.h +++ b/arch/arm64/include/asm/bitops.h @@ -17,22 +17,11 @@ #define __ASM_BITOPS_H #include <linux/compiler.h> -#include <asm/barrier.h> #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif -/* - * Little endian assembly atomic bitops. - */ -extern void set_bit(int nr, volatile unsigned long *p); -extern void clear_bit(int nr, volatile unsigned long *p); -extern void change_bit(int nr, volatile unsigned long *p); -extern int test_and_set_bit(int nr, volatile unsigned long *p); -extern int test_and_clear_bit(int nr, volatile unsigned long *p); -extern int test_and_change_bit(int nr, volatile unsigned long *p); - #include <asm-generic/bitops/builtin-__ffs.h> #include <asm-generic/bitops/builtin-ffs.h> #include <asm-generic/bitops/builtin-__fls.h> @@ -44,15 +33,11 @@ extern int test_and_change_bit(int nr, volatile unsigned long *p); #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/hweight.h> -#include <asm-generic/bitops/lock.h> +#include <asm-generic/bitops/atomic.h> +#include <asm-generic/bitops/lock.h> #include <asm-generic/bitops/non-atomic.h> #include <asm-generic/bitops/le.h> - -/* - * Ext2 is defined to use little-endian byte ordering. - */ -#define ext2_set_bit_atomic(lock, nr, p) test_and_set_bit_le(nr, p) -#define ext2_clear_bit_atomic(lock, nr, p) test_and_clear_bit_le(nr, p) +#include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __ASM_BITOPS_H */ diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 5df5cfe1c143..5ee5bca8c24b 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -21,12 +21,16 @@ #define CTR_L1IP_SHIFT 14 #define CTR_L1IP_MASK 3 #define CTR_DMINLINE_SHIFT 16 +#define CTR_IMINLINE_SHIFT 0 #define CTR_ERG_SHIFT 20 #define CTR_CWG_SHIFT 24 #define CTR_CWG_MASK 15 #define CTR_IDC_SHIFT 28 #define CTR_DIC_SHIFT 29 +#define CTR_CACHE_MINLINE_MASK \ + (0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT) + #define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) #define ICACHE_POLICY_VPIPT 0 diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index d264a7274811..19844211a4e6 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -19,6 +19,7 @@ #ifndef __ASM_CACHEFLUSH_H #define __ASM_CACHEFLUSH_H +#include <linux/kgdb.h> #include <linux/mm.h> /* @@ -71,7 +72,7 @@ * - kaddr - page address * - size - region size */ -extern void flush_icache_range(unsigned long start, unsigned long end); +extern void __flush_icache_range(unsigned long start, unsigned long end); extern int invalidate_icache_range(unsigned long start, unsigned long end); extern void __flush_dcache_area(void *addr, size_t len); extern void __inval_dcache_area(void *addr, size_t len); @@ -81,6 +82,30 @@ extern void __clean_dcache_area_pou(void *addr, size_t len); extern long __flush_cache_user_range(unsigned long start, unsigned long end); extern void sync_icache_aliases(void *kaddr, unsigned long len); +static inline void flush_icache_range(unsigned long start, unsigned long end) +{ + __flush_icache_range(start, end); + + /* + * IPI all online CPUs so that they undergo a context synchronization + * event and are forced to refetch the new instructions. + */ +#ifdef CONFIG_KGDB + /* + * KGDB performs cache maintenance with interrupts disabled, so we + * will deadlock trying to IPI the secondary CPUs. In theory, we can + * set CACHE_FLUSH_IS_SAFE to 0 to avoid this known issue, but that + * just means that KGDB will elide the maintenance altogether! As it + * turns out, KGDB uses IPIs to round-up the secondary CPUs during + * the patching operation, so we don't need extra IPIs here anyway. + * In which case, add a KGDB-specific bodge and return early. + */ + if (kgdb_connected && irqs_disabled()) + return; +#endif + kick_all_cpus_sync(); +} + static inline void flush_cache_mm(struct mm_struct *mm) { } diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 8a699c708fc9..be3bf3d08916 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -49,7 +49,8 @@ #define ARM64_HAS_CACHE_DIC 28 #define ARM64_HW_DBM 29 #define ARM64_SSBD 30 +#define ARM64_MISMATCHED_CACHE_TYPE 31 -#define ARM64_NCAPS 31 +#define ARM64_NCAPS 32 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 192d791f1103..7ed320895d1f 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -87,6 +87,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (true) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index fa92747a49c8..dd1ad3950ef5 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -16,13 +16,15 @@ #ifndef __ASM_FP_H #define __ASM_FP_H -#include <asm/ptrace.h> #include <asm/errno.h> +#include <asm/ptrace.h> #include <asm/processor.h> #include <asm/sigcontext.h> +#include <asm/sysreg.h> #ifndef __ASSEMBLY__ +#include <linux/build_bug.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/stddef.h> @@ -102,6 +104,16 @@ extern int sve_set_vector_length(struct task_struct *task, extern int sve_set_current_vl(unsigned long arg); extern int sve_get_current_vl(void); +static inline void sve_user_disable(void) +{ + sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0); +} + +static inline void sve_user_enable(void) +{ + sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN); +} + /* * Probing and setup functions. * Calls to these functions must be serialised with one another. @@ -128,6 +140,9 @@ static inline int sve_get_current_vl(void) return -EINVAL; } +static inline void sve_user_disable(void) { BUILD_BUG(); } +static inline void sve_user_enable(void) { BUILD_BUG(); } + static inline void sve_init_vq_map(void) { } static inline void sve_update_vq_map(void) { } static inline int sve_verify_vq_map(void) { return 0; } diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index 41770766d964..6a53e59ced95 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -119,13 +119,16 @@ static inline void decode_ctrl_reg(u32 reg, struct task_struct; struct notifier_block; +struct perf_event_attr; struct perf_event; struct pmu; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, int *gen_len, int *gen_type, int *offset); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index f62c56b1793f..c6802dea6cab 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -446,8 +446,6 @@ u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base, s32 aarch64_get_branch_offset(u32 insn); u32 aarch64_set_branch_offset(u32 insn, s32 offset); -bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn); - int aarch64_insn_patch_text_nosync(void *addr, u32 insn); int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt); diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index a0fee6985e6a..b2b0c6405eb0 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -8,8 +8,6 @@ struct pt_regs; -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); - static inline int nr_legacy_irqs(void) { return 0; diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 6deb8d726041..d5a44cf859e9 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -48,7 +48,6 @@ struct kprobe_ctlblk { unsigned long saved_irqflag; struct prev_kprobe prev_kprobe; struct kprobe_step_ctx ss_ctx; - struct pt_regs jprobe_saved_regs; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 1dab3a984608..0c97e45d1dc3 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -140,7 +140,7 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) { - *vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT; + *vcpu_cpsr(vcpu) |= PSR_AA32_T_BIT; } /* @@ -190,8 +190,8 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu) u32 mode; if (vcpu_mode_is_32bit(vcpu)) { - mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK; - return mode > COMPAT_PSR_MODE_USR; + mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK; + return mode > PSR_AA32_MODE_USR; } mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK; @@ -329,7 +329,7 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { - *vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT; + *vcpu_cpsr(vcpu) |= PSR_AA32_E_BIT; } else { u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); sctlr |= (1 << 25); @@ -340,7 +340,7 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) - return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT); + return !!(*vcpu_cpsr(vcpu) & PSR_AA32_E_BIT); return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & (1 << 25)); } diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h index f922eaf780f9..fb9d137256a6 100644 --- a/arch/arm64/include/asm/neon.h +++ b/arch/arm64/include/asm/neon.h @@ -19,11 +19,4 @@ void kernel_neon_begin(void); void kernel_neon_end(void); -/* - * Temporary macro to allow the crypto code to compile. Note that the - * semantics of kernel_neon_begin_partial() are now different from the - * original as it does not allow being called in an interrupt context. - */ -#define kernel_neon_begin_partial(num_regs) kernel_neon_begin() - #endif /* ! __ASM_NEON_H */ diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h index 01bc46d5b43a..626ad01e83bf 100644 --- a/arch/arm64/include/asm/numa.h +++ b/arch/arm64/include/asm/numa.h @@ -35,10 +35,14 @@ void __init numa_set_distance(int from, int to, int distance); void __init numa_free_distance(void); void __init early_map_cpu_to_node(unsigned int cpu, int nid); void numa_store_cpu_info(unsigned int cpu); +void numa_add_cpu(unsigned int cpu); +void numa_remove_cpu(unsigned int cpu); #else /* CONFIG_NUMA */ static inline void numa_store_cpu_info(unsigned int cpu) { } +static inline void numa_add_cpu(unsigned int cpu) { } +static inline void numa_remove_cpu(unsigned int cpu) { } static inline void arm64_numa_init(void) { } static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index a73ae1e49200..79657ad91397 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -182,12 +182,12 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { start_thread_common(regs, pc); - regs->pstate = COMPAT_PSR_MODE_USR; + regs->pstate = PSR_AA32_MODE_USR; if (pc & 1) - regs->pstate |= COMPAT_PSR_T_BIT; + regs->pstate |= PSR_AA32_T_BIT; #ifdef __AARCH64EB__ - regs->pstate |= COMPAT_PSR_E_BIT; + regs->pstate |= PSR_AA32_E_BIT; #endif regs->compat_sp = sp; @@ -266,5 +266,20 @@ extern void __init minsigstksz_setup(void); #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() +/* + * For CONFIG_GCC_PLUGIN_STACKLEAK + * + * These need to be macros because otherwise we get stuck in a nightmare + * of header definitions for the use of task_stack_page. + */ + +#define current_top_of_stack() \ +({ \ + struct stack_info _info; \ + BUG_ON(!on_accessible_stack(current, current_stack_pointer, &_info)); \ + _info.high; \ +}) +#define on_thread_stack() (on_task_stack(current, current_stack_pointer, NULL)) + #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 6069d66e0bc2..177b851ca6d9 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -35,36 +35,39 @@ #define COMPAT_PTRACE_GETHBPREGS 29 #define COMPAT_PTRACE_SETHBPREGS 30 -/* AArch32 CPSR bits */ -#define COMPAT_PSR_MODE_MASK 0x0000001f -#define COMPAT_PSR_MODE_USR 0x00000010 -#define COMPAT_PSR_MODE_FIQ 0x00000011 -#define COMPAT_PSR_MODE_IRQ 0x00000012 -#define COMPAT_PSR_MODE_SVC 0x00000013 -#define COMPAT_PSR_MODE_ABT 0x00000017 -#define COMPAT_PSR_MODE_HYP 0x0000001a -#define COMPAT_PSR_MODE_UND 0x0000001b -#define COMPAT_PSR_MODE_SYS 0x0000001f -#define COMPAT_PSR_T_BIT 0x00000020 -#define COMPAT_PSR_F_BIT 0x00000040 -#define COMPAT_PSR_I_BIT 0x00000080 -#define COMPAT_PSR_A_BIT 0x00000100 -#define COMPAT_PSR_E_BIT 0x00000200 -#define COMPAT_PSR_J_BIT 0x01000000 -#define COMPAT_PSR_Q_BIT 0x08000000 -#define COMPAT_PSR_V_BIT 0x10000000 -#define COMPAT_PSR_C_BIT 0x20000000 -#define COMPAT_PSR_Z_BIT 0x40000000 -#define COMPAT_PSR_N_BIT 0x80000000 -#define COMPAT_PSR_IT_MASK 0x0600fc00 /* If-Then execution state mask */ -#define COMPAT_PSR_GE_MASK 0x000f0000 +/* SPSR_ELx bits for exceptions taken from AArch32 */ +#define PSR_AA32_MODE_MASK 0x0000001f +#define PSR_AA32_MODE_USR 0x00000010 +#define PSR_AA32_MODE_FIQ 0x00000011 +#define PSR_AA32_MODE_IRQ 0x00000012 +#define PSR_AA32_MODE_SVC 0x00000013 +#define PSR_AA32_MODE_ABT 0x00000017 +#define PSR_AA32_MODE_HYP 0x0000001a +#define PSR_AA32_MODE_UND 0x0000001b +#define PSR_AA32_MODE_SYS 0x0000001f +#define PSR_AA32_T_BIT 0x00000020 +#define PSR_AA32_F_BIT 0x00000040 +#define PSR_AA32_I_BIT 0x00000080 +#define PSR_AA32_A_BIT 0x00000100 +#define PSR_AA32_E_BIT 0x00000200 +#define PSR_AA32_DIT_BIT 0x01000000 +#define PSR_AA32_Q_BIT 0x08000000 +#define PSR_AA32_V_BIT 0x10000000 +#define PSR_AA32_C_BIT 0x20000000 +#define PSR_AA32_Z_BIT 0x40000000 +#define PSR_AA32_N_BIT 0x80000000 +#define PSR_AA32_IT_MASK 0x0600fc00 /* If-Then execution state mask */ +#define PSR_AA32_GE_MASK 0x000f0000 #ifdef CONFIG_CPU_BIG_ENDIAN -#define COMPAT_PSR_ENDSTATE COMPAT_PSR_E_BIT +#define PSR_AA32_ENDSTATE PSR_AA32_E_BIT #else -#define COMPAT_PSR_ENDSTATE 0 +#define PSR_AA32_ENDSTATE 0 #endif +/* AArch32 CPSR bits, as seen in AArch32 */ +#define COMPAT_PSR_DIT_BIT 0x00200000 + /* * These are 'magic' values for PTRACE_PEEKUSR that return info about where a * process is located in memory. @@ -111,6 +114,30 @@ #define compat_sp_fiq regs[29] #define compat_lr_fiq regs[30] +static inline unsigned long compat_psr_to_pstate(const unsigned long psr) +{ + unsigned long pstate; + + pstate = psr & ~COMPAT_PSR_DIT_BIT; + + if (psr & COMPAT_PSR_DIT_BIT) + pstate |= PSR_AA32_DIT_BIT; + + return pstate; +} + +static inline unsigned long pstate_to_compat_psr(const unsigned long pstate) +{ + unsigned long psr; + + psr = pstate & ~PSR_AA32_DIT_BIT; + + if (pstate & PSR_AA32_DIT_BIT) + psr |= COMPAT_PSR_DIT_BIT; + + return psr; +} + /* * This struct defines the way the registers are stored on the stack during an * exception. Note that sizeof(struct pt_regs) has to be a multiple of 16 (for @@ -156,7 +183,7 @@ static inline void forget_syscall(struct pt_regs *regs) #ifdef CONFIG_COMPAT #define compat_thumb_mode(regs) \ - (((regs)->pstate & COMPAT_PSR_T_BIT)) + (((regs)->pstate & PSR_AA32_T_BIT)) #else #define compat_thumb_mode(regs) (0) #endif diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h index e073e6886685..ffe47d766c25 100644 --- a/arch/arm64/include/asm/sdei.h +++ b/arch/arm64/include/asm/sdei.h @@ -40,15 +40,18 @@ asmlinkage unsigned long __sdei_handler(struct pt_regs *regs, unsigned long sdei_arch_get_entry_point(int conduit); #define sdei_arch_get_entry_point(x) sdei_arch_get_entry_point(x) -bool _on_sdei_stack(unsigned long sp); -static inline bool on_sdei_stack(unsigned long sp) +struct stack_info; + +bool _on_sdei_stack(unsigned long sp, struct stack_info *info); +static inline bool on_sdei_stack(unsigned long sp, + struct stack_info *info) { if (!IS_ENABLED(CONFIG_VMAP_STACK)) return false; if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE)) return false; if (in_nmi()) - return _on_sdei_stack(sp); + return _on_sdei_stack(sp, info); return false; } diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index 26c5bd7d88d8..38116008d18b 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -16,123 +16,8 @@ #ifndef __ASM_SPINLOCK_H #define __ASM_SPINLOCK_H -#include <asm/lse.h> -#include <asm/spinlock_types.h> -#include <asm/processor.h> - -/* - * Spinlock implementation. - * - * The memory barriers are implicit with the load-acquire and store-release - * instructions. - */ - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - unsigned int tmp; - arch_spinlock_t lockval, newval; - - asm volatile( - /* Atomically increment the next ticket. */ - ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ -" prfm pstl1strm, %3\n" -"1: ldaxr %w0, %3\n" -" add %w1, %w0, %w5\n" -" stxr %w2, %w1, %3\n" -" cbnz %w2, 1b\n", - /* LSE atomics */ -" mov %w2, %w5\n" -" ldadda %w2, %w0, %3\n" - __nops(3) - ) - - /* Did we get the lock? */ -" eor %w1, %w0, %w0, ror #16\n" -" cbz %w1, 3f\n" - /* - * No: spin on the owner. Send a local event to avoid missing an - * unlock before the exclusive load. - */ -" sevl\n" -"2: wfe\n" -" ldaxrh %w2, %4\n" -" eor %w1, %w2, %w0, lsr #16\n" -" cbnz %w1, 2b\n" - /* We got the lock. Critical section starts here. */ -"3:" - : "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock) - : "Q" (lock->owner), "I" (1 << TICKET_SHIFT) - : "memory"); -} - -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned int tmp; - arch_spinlock_t lockval; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - " prfm pstl1strm, %2\n" - "1: ldaxr %w0, %2\n" - " eor %w1, %w0, %w0, ror #16\n" - " cbnz %w1, 2f\n" - " add %w0, %w0, %3\n" - " stxr %w1, %w0, %2\n" - " cbnz %w1, 1b\n" - "2:", - /* LSE atomics */ - " ldr %w0, %2\n" - " eor %w1, %w0, %w0, ror #16\n" - " cbnz %w1, 1f\n" - " add %w1, %w0, %3\n" - " casa %w0, %w1, %2\n" - " sub %w1, %w1, %3\n" - " eor %w1, %w1, %w0\n" - "1:") - : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) - : "I" (1 << TICKET_SHIFT) - : "memory"); - - return !tmp; -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - unsigned long tmp; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - " ldrh %w1, %0\n" - " add %w1, %w1, #1\n" - " stlrh %w1, %0", - /* LSE atomics */ - " mov %w1, #1\n" - " staddlh %w1, %0\n" - __nops(1)) - : "=Q" (lock->owner), "=&r" (tmp) - : - : "memory"); -} - -static inline int arch_spin_value_unlocked(arch_spinlock_t lock) -{ - return lock.owner == lock.next; -} - -static inline int arch_spin_is_locked(arch_spinlock_t *lock) -{ - return !arch_spin_value_unlocked(READ_ONCE(*lock)); -} - -static inline int arch_spin_is_contended(arch_spinlock_t *lock) -{ - arch_spinlock_t lockval = READ_ONCE(*lock); - return (lockval.next - lockval.owner) > 1; -} -#define arch_spin_is_contended arch_spin_is_contended - #include <asm/qrwlock.h> +#include <asm/qspinlock.h> /* See include/linux/spinlock.h */ #define smp_mb__after_spinlock() smp_mb() diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h index 6b856012c51b..a157ff465e27 100644 --- a/arch/arm64/include/asm/spinlock_types.h +++ b/arch/arm64/include/asm/spinlock_types.h @@ -20,22 +20,7 @@ # error "please don't include this file directly" #endif -#include <linux/types.h> - -#define TICKET_SHIFT 16 - -typedef struct { -#ifdef __AARCH64EB__ - u16 next; - u16 owner; -#else - u16 owner; - u16 next; -#endif -} __aligned(4) arch_spinlock_t; - -#define __ARCH_SPIN_LOCK_UNLOCKED { 0 , 0 } - +#include <asm-generic/qspinlock_types.h> #include <asm-generic/qrwlock_types.h> #endif diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 902f9edacbea..e86737b7c924 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -32,6 +32,21 @@ struct stackframe { #endif }; +enum stack_type { + STACK_TYPE_UNKNOWN, + STACK_TYPE_TASK, + STACK_TYPE_IRQ, + STACK_TYPE_OVERFLOW, + STACK_TYPE_SDEI_NORMAL, + STACK_TYPE_SDEI_CRITICAL, +}; + +struct stack_info { + unsigned long low; + unsigned long high; + enum stack_type type; +}; + extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame); extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data); @@ -39,7 +54,8 @@ extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk); DECLARE_PER_CPU(unsigned long *, irq_stack_ptr); -static inline bool on_irq_stack(unsigned long sp) +static inline bool on_irq_stack(unsigned long sp, + struct stack_info *info) { unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr); unsigned long high = low + IRQ_STACK_SIZE; @@ -47,46 +63,79 @@ static inline bool on_irq_stack(unsigned long sp) if (!low) return false; - return (low <= sp && sp < high); + if (sp < low || sp >= high) + return false; + + if (info) { + info->low = low; + info->high = high; + info->type = STACK_TYPE_IRQ; + } + + return true; } -static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp) +static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp, + struct stack_info *info) { unsigned long low = (unsigned long)task_stack_page(tsk); unsigned long high = low + THREAD_SIZE; - return (low <= sp && sp < high); + if (sp < low || sp >= high) + return false; + + if (info) { + info->low = low; + info->high = high; + info->type = STACK_TYPE_TASK; + } + + return true; } #ifdef CONFIG_VMAP_STACK DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); -static inline bool on_overflow_stack(unsigned long sp) +static inline bool on_overflow_stack(unsigned long sp, + struct stack_info *info) { unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack); unsigned long high = low + OVERFLOW_STACK_SIZE; - return (low <= sp && sp < high); + if (sp < low || sp >= high) + return false; + + if (info) { + info->low = low; + info->high = high; + info->type = STACK_TYPE_OVERFLOW; + } + + return true; } #else -static inline bool on_overflow_stack(unsigned long sp) { return false; } +static inline bool on_overflow_stack(unsigned long sp, + struct stack_info *info) { return false; } #endif + /* * We can only safely access per-cpu stacks from current in a non-preemptible * context. */ -static inline bool on_accessible_stack(struct task_struct *tsk, unsigned long sp) +static inline bool on_accessible_stack(struct task_struct *tsk, + unsigned long sp, + struct stack_info *info) { - if (on_task_stack(tsk, sp)) + if (on_task_stack(tsk, sp, info)) return true; if (tsk != current || preemptible()) return false; - if (on_irq_stack(sp)) + if (on_irq_stack(sp, info)) return true; - if (on_overflow_stack(sp)) + if (on_overflow_stack(sp, info)) return true; - if (on_sdei_stack(sp)) + if (on_sdei_stack(sp, info)) return true; return false; diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 709a574468f0..ad8be16a39c9 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -20,7 +20,13 @@ #include <linux/compat.h> #include <linux/err.h> -extern const void *sys_call_table[]; +typedef long (*syscall_fn_t)(struct pt_regs *regs); + +extern const syscall_fn_t sys_call_table[]; + +#ifdef CONFIG_COMPAT +extern const syscall_fn_t compat_sys_call_table[]; +#endif static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h new file mode 100644 index 000000000000..a4477e515b79 --- /dev/null +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * syscall_wrapper.h - arm64 specific wrappers to syscall definitions + * + * Based on arch/x86/include/asm_syscall_wrapper.h + */ + +#ifndef __ASM_SYSCALL_WRAPPER_H +#define __ASM_SYSCALL_WRAPPER_H + +#define SC_ARM64_REGS_TO_ARGS(x, ...) \ + __MAP(x,__SC_ARGS \ + ,,regs->regs[0],,regs->regs[1],,regs->regs[2] \ + ,,regs->regs[3],,regs->regs[4],,regs->regs[5]) + +#ifdef CONFIG_COMPAT + +#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long __arm64_compat_sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__arm64_compat_sys##name, ERRNO); \ + static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long __arm64_compat_sys##name(const struct pt_regs *regs) \ + { \ + return __se_compat_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__)); \ + } \ + static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ + } \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#define COMPAT_SYSCALL_DEFINE0(sname) \ + asmlinkage long __arm64_compat_sys_##sname(void); \ + ALLOW_ERROR_INJECTION(__arm64_compat_sys_##sname, ERRNO); \ + asmlinkage long __arm64_compat_sys_##sname(void) + +#define COND_SYSCALL_COMPAT(name) \ + cond_syscall(__arm64_compat_sys_##name); + +#define COMPAT_SYS_NI(name) \ + SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers); + +#endif /* CONFIG_COMPAT */ + +#define __SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long __arm64_sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__arm64_sys##name, ERRNO); \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long __arm64_sys##name(const struct pt_regs *regs) \ + { \ + return __se_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__)); \ + } \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#ifndef SYSCALL_DEFINE0 +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __arm64_sys_##sname(void); \ + ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO); \ + asmlinkage long __arm64_sys_##sname(void) +#endif + +#ifndef COND_SYSCALL +#define COND_SYSCALL(name) cond_syscall(__arm64_sys_##name) +#endif + +#ifndef SYS_NI +#define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers); +#endif + +#endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index a8f84812c6e8..e205ec8489e9 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -436,7 +436,8 @@ #define SCTLR_EL2_RES0 ((1 << 6) | (1 << 7) | (1 << 8) | (1 << 9) | \ (1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \ (1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \ - (1 << 27) | (1 << 30) | (1 << 31)) + (1 << 27) | (1 << 30) | (1 << 31) | \ + (0xffffffffUL << 32)) #ifdef CONFIG_CPU_BIG_ENDIAN #define ENDIAN_SET_EL2 SCTLR_ELx_EE @@ -452,9 +453,9 @@ SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_WXN | \ ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0) -/* Check all the bits are accounted for */ -#define SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS BUILD_BUG_ON((SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != ~0) - +#if (SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != 0xffffffffffffffff +#error "Inconsistent SCTLR_EL2 set/clear bits" +#endif /* SCTLR_EL1 specific flags. */ #define SCTLR_EL1_UCI (1 << 26) @@ -473,7 +474,8 @@ #define SCTLR_EL1_RES1 ((1 << 11) | (1 << 20) | (1 << 22) | (1 << 28) | \ (1 << 29)) #define SCTLR_EL1_RES0 ((1 << 6) | (1 << 10) | (1 << 13) | (1 << 17) | \ - (1 << 27) | (1 << 30) | (1 << 31)) + (1 << 27) | (1 << 30) | (1 << 31) | \ + (0xffffffffUL << 32)) #ifdef CONFIG_CPU_BIG_ENDIAN #define ENDIAN_SET_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE) @@ -492,8 +494,9 @@ SCTLR_EL1_UMA | SCTLR_ELx_WXN | ENDIAN_CLEAR_EL1 |\ SCTLR_EL1_RES0) -/* Check all the bits are accounted for */ -#define SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS BUILD_BUG_ON((SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != ~0) +#if (SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != 0xffffffffffffffff +#error "Inconsistent SCTLR_EL1 set/clear bits" +#endif /* id_aa64isar0 */ #define ID_AA64ISAR0_TS_SHIFT 52 @@ -739,19 +742,6 @@ asm( write_sysreg(__scs_new, sysreg); \ } while (0) -static inline void config_sctlr_el1(u32 clear, u32 set) -{ - u32 val; - - SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS; - SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS; - - val = read_sysreg(sctlr_el1); - val &= ~clear; - val |= set; - write_sysreg(val, sctlr_el1); -} - #endif #endif /* __ASM_SYSREG_H */ diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index ffdaea7954bb..0ad1cf233470 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -37,7 +37,7 @@ static inline void __tlb_remove_table(void *_table) static inline void tlb_flush(struct mmu_gather *tlb) { - struct vm_area_struct vma = { .vm_mm = tlb->mm, }; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); /* * The ASID allocator will either invalidate the ASID or mark diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index dfc61d73f740..a4a1901140ee 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -218,6 +218,13 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm, dsb(ish); } +static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr) +{ + unsigned long addr = __TLBI_VADDR(kaddr, 0); + + __tlbi(vaae1is, addr); + dsb(ish); +} #endif #endif diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index df48212f767b..49a0fee4f89b 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -11,7 +11,7 @@ struct cpu_topology { int llc_id; cpumask_t thread_sibling; cpumask_t core_sibling; - cpumask_t llc_siblings; + cpumask_t llc_sibling; }; extern struct cpu_topology cpu_topology[NR_CPUS]; @@ -20,9 +20,11 @@ extern struct cpu_topology cpu_topology[NR_CPUS]; #define topology_core_id(cpu) (cpu_topology[cpu].core_id) #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) #define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) +#define topology_llc_cpumask(cpu) (&cpu_topology[cpu].llc_sibling) void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); +void remove_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); #ifdef CONFIG_NUMA diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index a0baa9af5487..e0d0f5b856e7 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -43,7 +43,7 @@ #define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2) #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5) -#define __NR_compat_syscalls 398 +#define __NR_compat_syscalls 399 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index ef292160748c..2cd6dcf8d246 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -260,7 +260,7 @@ __SYSCALL(117, sys_ni_syscall) #define __NR_fsync 118 __SYSCALL(__NR_fsync, sys_fsync) #define __NR_sigreturn 119 -__SYSCALL(__NR_sigreturn, compat_sys_sigreturn_wrapper) +__SYSCALL(__NR_sigreturn, compat_sys_sigreturn) #define __NR_clone 120 __SYSCALL(__NR_clone, sys_clone) #define __NR_setdomainname 121 @@ -368,7 +368,7 @@ __SYSCALL(__NR_getresgid, sys_getresgid16) #define __NR_prctl 172 __SYSCALL(__NR_prctl, sys_prctl) #define __NR_rt_sigreturn 173 -__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn_wrapper) +__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn) #define __NR_rt_sigaction 174 __SYSCALL(__NR_rt_sigaction, compat_sys_rt_sigaction) #define __NR_rt_sigprocmask 175 @@ -382,9 +382,9 @@ __SYSCALL(__NR_rt_sigqueueinfo, compat_sys_rt_sigqueueinfo) #define __NR_rt_sigsuspend 179 __SYSCALL(__NR_rt_sigsuspend, compat_sys_rt_sigsuspend) #define __NR_pread64 180 -__SYSCALL(__NR_pread64, compat_sys_pread64_wrapper) +__SYSCALL(__NR_pread64, compat_sys_aarch32_pread64) #define __NR_pwrite64 181 -__SYSCALL(__NR_pwrite64, compat_sys_pwrite64_wrapper) +__SYSCALL(__NR_pwrite64, compat_sys_aarch32_pwrite64) #define __NR_chown 182 __SYSCALL(__NR_chown, sys_chown16) #define __NR_getcwd 183 @@ -406,11 +406,11 @@ __SYSCALL(__NR_vfork, sys_vfork) #define __NR_ugetrlimit 191 /* SuS compliant getrlimit */ __SYSCALL(__NR_ugetrlimit, compat_sys_getrlimit) /* SuS compliant getrlimit */ #define __NR_mmap2 192 -__SYSCALL(__NR_mmap2, compat_sys_mmap2_wrapper) +__SYSCALL(__NR_mmap2, compat_sys_aarch32_mmap2) #define __NR_truncate64 193 -__SYSCALL(__NR_truncate64, compat_sys_truncate64_wrapper) +__SYSCALL(__NR_truncate64, compat_sys_aarch32_truncate64) #define __NR_ftruncate64 194 -__SYSCALL(__NR_ftruncate64, compat_sys_ftruncate64_wrapper) +__SYSCALL(__NR_ftruncate64, compat_sys_aarch32_ftruncate64) #define __NR_stat64 195 __SYSCALL(__NR_stat64, sys_stat64) #define __NR_lstat64 196 @@ -472,7 +472,7 @@ __SYSCALL(223, sys_ni_syscall) #define __NR_gettid 224 __SYSCALL(__NR_gettid, sys_gettid) #define __NR_readahead 225 -__SYSCALL(__NR_readahead, compat_sys_readahead_wrapper) +__SYSCALL(__NR_readahead, compat_sys_aarch32_readahead) #define __NR_setxattr 226 __SYSCALL(__NR_setxattr, sys_setxattr) #define __NR_lsetxattr 227 @@ -554,15 +554,15 @@ __SYSCALL(__NR_clock_getres, compat_sys_clock_getres) #define __NR_clock_nanosleep 265 __SYSCALL(__NR_clock_nanosleep, compat_sys_clock_nanosleep) #define __NR_statfs64 266 -__SYSCALL(__NR_statfs64, compat_sys_statfs64_wrapper) +__SYSCALL(__NR_statfs64, compat_sys_aarch32_statfs64) #define __NR_fstatfs64 267 -__SYSCALL(__NR_fstatfs64, compat_sys_fstatfs64_wrapper) +__SYSCALL(__NR_fstatfs64, compat_sys_aarch32_fstatfs64) #define __NR_tgkill 268 __SYSCALL(__NR_tgkill, sys_tgkill) #define __NR_utimes 269 __SYSCALL(__NR_utimes, compat_sys_utimes) #define __NR_arm_fadvise64_64 270 -__SYSCALL(__NR_arm_fadvise64_64, compat_sys_fadvise64_64_wrapper) +__SYSCALL(__NR_arm_fadvise64_64, compat_sys_aarch32_fadvise64_64) #define __NR_pciconfig_iobase 271 __SYSCALL(__NR_pciconfig_iobase, sys_pciconfig_iobase) #define __NR_pciconfig_read 272 @@ -704,7 +704,7 @@ __SYSCALL(__NR_get_robust_list, compat_sys_get_robust_list) #define __NR_splice 340 __SYSCALL(__NR_splice, sys_splice) #define __NR_sync_file_range2 341 -__SYSCALL(__NR_sync_file_range2, compat_sys_sync_file_range2_wrapper) +__SYSCALL(__NR_sync_file_range2, compat_sys_aarch32_sync_file_range2) #define __NR_tee 342 __SYSCALL(__NR_tee, sys_tee) #define __NR_vmsplice 343 @@ -726,7 +726,7 @@ __SYSCALL(__NR_timerfd_create, sys_timerfd_create) #define __NR_eventfd 351 __SYSCALL(__NR_eventfd, sys_eventfd) #define __NR_fallocate 352 -__SYSCALL(__NR_fallocate, compat_sys_fallocate_wrapper) +__SYSCALL(__NR_fallocate, compat_sys_aarch32_fallocate) #define __NR_timerfd_settime 353 __SYSCALL(__NR_timerfd_settime, compat_sys_timerfd_settime) #define __NR_timerfd_gettime 354 @@ -817,6 +817,8 @@ __SYSCALL(__NR_pkey_alloc, sys_pkey_alloc) __SYSCALL(__NR_pkey_free, sys_pkey_free) #define __NR_statx 397 __SYSCALL(__NR_statx, sys_statx) +#define __NR_rseq 398 +__SYSCALL(__NR_rseq, sys_rseq) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 0025f8691046..95ac7374d723 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -18,7 +18,8 @@ arm64-obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ hyp-stub.o psci.o cpu_ops.o insn.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ - smp.o smp_spin_table.o topology.o smccc-call.o + smp.o smp_spin_table.o topology.o smccc-call.o \ + syscall.o extra-$(CONFIG_EFI) := efi-entry.o @@ -27,7 +28,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE $(call if_changed,objcopy) arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ - sys_compat.o entry32.o + sys_compat.o arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o arm64-obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 7b09487ff8fb..ed46dc188b22 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -18,6 +18,7 @@ #include <linux/acpi.h> #include <linux/bootmem.h> #include <linux/cpumask.h> +#include <linux/efi.h> #include <linux/efi-bgrt.h> #include <linux/init.h> #include <linux/irq.h> @@ -29,13 +30,9 @@ #include <asm/cputype.h> #include <asm/cpu_ops.h> +#include <asm/pgtable.h> #include <asm/smp_plat.h> -#ifdef CONFIG_ACPI_APEI -# include <linux/efi.h> -# include <asm/pgtable.h> -#endif - int acpi_noirq = 1; /* skip ACPI IRQ initialization */ int acpi_disabled = 1; EXPORT_SYMBOL(acpi_disabled); @@ -239,8 +236,7 @@ done: } } -#ifdef CONFIG_ACPI_APEI -pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) +pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) { /* * According to "Table 8 Map: EFI memory types to AArch64 memory @@ -261,4 +257,3 @@ pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) return __pgprot(PROT_NORMAL_NC); return __pgprot(PROT_DEVICE_nGnRnE); } -#endif diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index d190a7b231bf..4f4f1815e047 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -26,36 +26,73 @@ #include <linux/module.h> #include <linux/topology.h> -#include <acpi/processor.h> #include <asm/numa.h> -static int cpus_in_srat; +static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; -struct __node_cpu_hwid { - u32 node_id; /* logical node containing this CPU */ - u64 cpu_hwid; /* MPIDR for this CPU */ -}; +int __init acpi_numa_get_nid(unsigned int cpu) +{ + return acpi_early_node_map[cpu]; +} + +static inline int get_cpu_for_acpi_id(u32 uid) +{ + int cpu; + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + if (uid == get_acpi_id_for_cpu(cpu)) + return cpu; -static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = { -[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} }; + return -EINVAL; +} -int acpi_numa_get_nid(unsigned int cpu, u64 hwid) +static int __init acpi_parse_gicc_pxm(struct acpi_subtable_header *header, + const unsigned long end) { - int i; + struct acpi_srat_gicc_affinity *pa; + int cpu, pxm, node; - for (i = 0; i < cpus_in_srat; i++) { - if (hwid == early_node_cpu_hwid[i].cpu_hwid) - return early_node_cpu_hwid[i].node_id; - } + if (srat_disabled()) + return -EINVAL; + + pa = (struct acpi_srat_gicc_affinity *)header; + if (!pa) + return -EINVAL; + + if (!(pa->flags & ACPI_SRAT_GICC_ENABLED)) + return 0; - return NUMA_NO_NODE; + pxm = pa->proximity_domain; + node = pxm_to_node(pxm); + + /* + * If we can't map the UID to a logical cpu this + * means that the UID is not part of possible cpus + * so we do not need a NUMA mapping for it, skip + * the SRAT entry and keep parsing. + */ + cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid); + if (cpu < 0) + return 0; + + acpi_early_node_map[cpu] = node; + pr_info("SRAT: PXM %d -> MPIDR 0x%llx -> Node %d\n", pxm, + cpu_logical_map(cpu), node); + + return 0; +} + +void __init acpi_map_cpus_to_nodes(void) +{ + acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), + ACPI_SRAT_TYPE_GICC_AFFINITY, + acpi_parse_gicc_pxm, 0); } /* Callback for Proximity Domain -> ACPI processor UID mapping */ void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { int pxm, node; - phys_cpuid_t mpidr; if (srat_disabled()) return; @@ -70,12 +107,6 @@ void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) if (!(pa->flags & ACPI_SRAT_GICC_ENABLED)) return; - if (cpus_in_srat >= NR_CPUS) { - pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n", - NR_CPUS); - return; - } - pxm = pa->proximity_domain; node = acpi_map_pxm_to_node(pxm); @@ -85,20 +116,7 @@ void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) return; } - mpidr = acpi_map_madt_entry(pa->acpi_processor_uid); - if (mpidr == PHYS_CPUID_INVALID) { - pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n", - pxm, pa->acpi_processor_uid); - bad_srat(); - return; - } - - early_node_cpu_hwid[cpus_in_srat].node_id = node; - early_node_cpu_hwid[cpus_in_srat].cpu_hwid = mpidr; node_set(node, numa_nodes_parsed); - cpus_in_srat++; - pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n", - pxm, mpidr, node); } int __init arm64_acpi_numa_init(void) diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 36fb069fd049..b5d603992d40 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -47,11 +47,11 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) unsigned long replptr; if (kernel_text_address(pc)) - return 1; + return true; replptr = (unsigned long)ALT_REPL_PTR(alt); if (pc >= replptr && pc <= (replptr + alt->alt_len)) - return 0; + return false; /* * Branching into *another* alternate sequence is doomed, and diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index d4707abb2f16..92be1d12d590 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -441,8 +441,8 @@ static struct undef_hook swp_hooks[] = { { .instr_mask = 0x0fb00ff0, .instr_val = 0x01000090, - .pstate_mask = COMPAT_PSR_MODE_MASK, - .pstate_val = COMPAT_PSR_MODE_USR, + .pstate_mask = PSR_AA32_MODE_MASK, + .pstate_val = PSR_AA32_MODE_USR, .fn = swp_handler }, { } @@ -511,9 +511,9 @@ ret: static int cp15_barrier_set_hw_mode(bool enable) { if (enable) - config_sctlr_el1(0, SCTLR_EL1_CP15BEN); + sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_CP15BEN); else - config_sctlr_el1(SCTLR_EL1_CP15BEN, 0); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_CP15BEN, 0); return 0; } @@ -521,15 +521,15 @@ static struct undef_hook cp15_barrier_hooks[] = { { .instr_mask = 0x0fff0fdf, .instr_val = 0x0e070f9a, - .pstate_mask = COMPAT_PSR_MODE_MASK, - .pstate_val = COMPAT_PSR_MODE_USR, + .pstate_mask = PSR_AA32_MODE_MASK, + .pstate_val = PSR_AA32_MODE_USR, .fn = cp15barrier_handler, }, { .instr_mask = 0x0fff0fff, .instr_val = 0x0e070f95, - .pstate_mask = COMPAT_PSR_MODE_MASK, - .pstate_val = COMPAT_PSR_MODE_USR, + .pstate_mask = PSR_AA32_MODE_MASK, + .pstate_val = PSR_AA32_MODE_USR, .fn = cp15barrier_handler, }, { } @@ -548,9 +548,9 @@ static int setend_set_hw_mode(bool enable) return -EINVAL; if (enable) - config_sctlr_el1(SCTLR_EL1_SED, 0); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_SED, 0); else - config_sctlr_el1(0, SCTLR_EL1_SED); + sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_SED); return 0; } @@ -562,10 +562,10 @@ static int compat_setend_handler(struct pt_regs *regs, u32 big_endian) if (big_endian) { insn = "setend be"; - regs->pstate |= COMPAT_PSR_E_BIT; + regs->pstate |= PSR_AA32_E_BIT; } else { insn = "setend le"; - regs->pstate &= ~COMPAT_PSR_E_BIT; + regs->pstate &= ~PSR_AA32_E_BIT; } trace_instruction_emulation(insn, regs->pc); @@ -593,16 +593,16 @@ static struct undef_hook setend_hooks[] = { { .instr_mask = 0xfffffdff, .instr_val = 0xf1010000, - .pstate_mask = COMPAT_PSR_MODE_MASK, - .pstate_val = COMPAT_PSR_MODE_USR, + .pstate_mask = PSR_AA32_MODE_MASK, + .pstate_val = PSR_AA32_MODE_USR, .fn = a32_setend_handler, }, { /* Thumb mode */ .instr_mask = 0x0000fff7, .instr_val = 0x0000b650, - .pstate_mask = (COMPAT_PSR_T_BIT | COMPAT_PSR_MODE_MASK), - .pstate_val = (COMPAT_PSR_T_BIT | COMPAT_PSR_MODE_USR), + .pstate_mask = (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK), + .pstate_val = (PSR_AA32_T_BIT | PSR_AA32_MODE_USR), .fn = t16_setend_handler, }, {} diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h index 6c2b1b4f57c9..fad90e4935fb 100644 --- a/arch/arm64/kernel/cpu-reset.h +++ b/arch/arm64/kernel/cpu-reset.h @@ -16,13 +16,14 @@ void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry, unsigned long arg0, unsigned long arg1, unsigned long arg2); -static inline void __noreturn cpu_soft_restart(unsigned long el2_switch, - unsigned long entry, unsigned long arg0, unsigned long arg1, - unsigned long arg2) +static inline void __noreturn cpu_soft_restart(unsigned long entry, + unsigned long arg0, + unsigned long arg1, + unsigned long arg2) { typeof(__cpu_soft_restart) *restart; - el2_switch = el2_switch && !is_kernel_in_hyp_mode() && + unsigned long el2_switch = !is_kernel_in_hyp_mode() && is_hyp_mode_available(); restart = (void *)__pa_symbol(__cpu_soft_restart); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 1d2b6d768efe..dec10898d688 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -65,19 +65,24 @@ is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope) } static bool -has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry, - int scope) +has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, + int scope) { + u64 mask = CTR_CACHE_MINLINE_MASK; + + /* Skip matching the min line sizes for cache type check */ + if (entry->capability == ARM64_MISMATCHED_CACHE_TYPE) + mask ^= arm64_ftr_reg_ctrel0.strict_mask; + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); - return (read_cpuid_cachetype() & arm64_ftr_reg_ctrel0.strict_mask) != - (arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask); + return (read_cpuid_cachetype() & mask) != + (arm64_ftr_reg_ctrel0.sys_val & mask); } static void cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused) { - /* Clear SCTLR_EL1.UCT */ - config_sctlr_el1(SCTLR_EL1_UCT, 0); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0); } atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1); @@ -101,7 +106,7 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start, for (i = 0; i < SZ_2K; i += 0x80) memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start); - flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K); + __flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K); } static void __install_bp_hardening_cb(bp_hardening_cb_t fn, @@ -613,7 +618,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "Mismatched cache line size", .capability = ARM64_MISMATCHED_CACHE_LINE_SIZE, - .matches = has_mismatched_cache_line_size, + .matches = has_mismatched_cache_type, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .cpu_enable = cpu_enable_trap_ctr_access, + }, + { + .desc = "Mismatched cache type", + .capability = ARM64_MISMATCHED_CACHE_TYPE, + .matches = has_mismatched_cache_type, .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .cpu_enable = cpu_enable_trap_ctr_access, }, @@ -649,7 +661,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, - .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .cpu_enable = enable_smccc_arch_workaround_1, ERRATA_MIDR_RANGE_LIST(arm64_bp_harden_smccc_cpus), }, @@ -658,7 +669,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "EL2 vector hardening", .capability = ARM64_HARDEN_EL2_VECTORS, - .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors), }, #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f24892a40d2c..611e8921c3d4 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -214,7 +214,7 @@ static const struct arm64_ftr_bits ftr_ctr[] = { * If we have differing I-cache policies, report it as the weakest - VIPT. */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_VIPT), /* L1Ip */ - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IMINLINE_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void update_cpu_capabilities(u16 scope_mask) { - __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); __update_cpu_capabilities(arm64_errata, scope_mask, "enabling workaround for"); + __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); } static int __enable_cpu_capability(void *arg) @@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void __init enable_cpu_capabilities(u16 scope_mask) { - __enable_cpu_capabilities(arm64_features, scope_mask); __enable_cpu_capabilities(arm64_errata, scope_mask); + __enable_cpu_capabilities(arm64_features, scope_mask); } /* @@ -1723,7 +1723,7 @@ static int emulate_mrs(struct pt_regs *regs, u32 insn) static struct undef_hook mrs_hook = { .instr_mask = 0xfff00000, .instr_val = 0xd5300000, - .pstate_mask = COMPAT_PSR_MODE_MASK, + .pstate_mask = PSR_AA32_MODE_MASK, .pstate_val = PSR_MODE_EL0t, .fn = emulate_mrs, }; diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 28ad8799406f..09dbea221a27 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -41,19 +41,9 @@ * Context tracking subsystem. Used to instrument transitions * between user and kernel mode. */ - .macro ct_user_exit, syscall = 0 + .macro ct_user_exit #ifdef CONFIG_CONTEXT_TRACKING bl context_tracking_user_exit - .if \syscall == 1 - /* - * Save/restore needed during syscalls. Restore syscall arguments from - * the values already saved on stack during kernel_entry. - */ - ldp x0, x1, [sp] - ldp x2, x3, [sp, #S_X2] - ldp x4, x5, [sp, #S_X4] - ldp x6, x7, [sp, #S_X6] - .endif #endif .endm @@ -63,6 +53,12 @@ #endif .endm + .macro clear_gp_regs + .irp n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29 + mov x\n, xzr + .endr + .endm + /* * Bad Abort numbers *----------------- @@ -140,20 +136,21 @@ alternative_else_nop_endif // This macro corrupts x0-x3. It is the caller's duty // to save/restore them if required. - .macro apply_ssbd, state, targ, tmp1, tmp2 + .macro apply_ssbd, state, tmp1, tmp2 #ifdef CONFIG_ARM64_SSBD alternative_cb arm64_enable_wa2_handling - b \targ + b .L__asm_ssbd_skip\@ alternative_cb_end ldr_this_cpu \tmp2, arm64_ssbd_callback_required, \tmp1 - cbz \tmp2, \targ + cbz \tmp2, .L__asm_ssbd_skip\@ ldr \tmp2, [tsk, #TSK_TI_FLAGS] - tbnz \tmp2, #TIF_SSBD, \targ + tbnz \tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 mov w1, #\state alternative_cb arm64_update_smccc_conduit nop // Patched to SMC/HVC #0 alternative_cb_end +.L__asm_ssbd_skip\@: #endif .endm @@ -178,20 +175,14 @@ alternative_cb_end stp x28, x29, [sp, #16 * 14] .if \el == 0 + clear_gp_regs mrs x21, sp_el0 ldr_this_cpu tsk, __entry_task, x20 // Ensure MDSCR_EL1.SS is clear, ldr x19, [tsk, #TSK_TI_FLAGS] // since we can unmask debug disable_step_tsk x19, x20 // exceptions when scheduling. - apply_ssbd 1, 1f, x22, x23 - -#ifdef CONFIG_ARM64_SSBD - ldp x0, x1, [sp, #16 * 0] - ldp x2, x3, [sp, #16 * 1] -#endif -1: + apply_ssbd 1, x22, x23 - mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE get_thread_info tsk @@ -331,8 +322,7 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif 3: - apply_ssbd 0, 5f, x0, x1 -5: + apply_ssbd 0, x0, x1 .endif msr elr_el1, x21 // set up the return data @@ -720,14 +710,9 @@ el0_sync_compat: b.ge el0_dbg b el0_inv el0_svc_compat: - /* - * AArch32 syscall handling - */ - ldr x16, [tsk, #TSK_TI_FLAGS] // load thread flags - adrp stbl, compat_sys_call_table // load compat syscall table pointer - mov wscno, w7 // syscall number in w7 (r7) - mov wsc_nr, #__NR_compat_syscalls - b el0_svc_naked + mov x0, sp + bl el0_svc_compat_handler + b ret_to_user .align 6 el0_irq_compat: @@ -896,25 +881,6 @@ el0_error_naked: b ret_to_user ENDPROC(el0_error) - -/* - * This is the fast syscall return path. We do as little as possible here, - * and this includes saving x0 back into the kernel stack. - */ -ret_fast_syscall: - disable_daif - str x0, [sp, #S_X0] // returned x0 - ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for syscall tracing - and x2, x1, #_TIF_SYSCALL_WORK - cbnz x2, ret_fast_syscall_trace - and x2, x1, #_TIF_WORK_MASK - cbnz x2, work_pending - enable_step_tsk x1, x2 - kernel_exit 0 -ret_fast_syscall_trace: - enable_daif - b __sys_trace_return_skipped // we already saved x0 - /* * Ok, we need to do extra processing, enter the slow path. */ @@ -936,6 +902,9 @@ ret_to_user: cbnz x2, work_pending finish_ret_to_user: enable_step_tsk x1, x2 +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + bl stackleak_erase +#endif kernel_exit 0 ENDPROC(ret_to_user) @@ -944,85 +913,10 @@ ENDPROC(ret_to_user) */ .align 6 el0_svc: - ldr x16, [tsk, #TSK_TI_FLAGS] // load thread flags - adrp stbl, sys_call_table // load syscall table pointer - mov wscno, w8 // syscall number in w8 - mov wsc_nr, #__NR_syscalls - -#ifdef CONFIG_ARM64_SVE -alternative_if_not ARM64_SVE - b el0_svc_naked -alternative_else_nop_endif - tbz x16, #TIF_SVE, el0_svc_naked // Skip unless TIF_SVE set: - bic x16, x16, #_TIF_SVE // discard SVE state - str x16, [tsk, #TSK_TI_FLAGS] - - /* - * task_fpsimd_load() won't be called to update CPACR_EL1 in - * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only - * happens if a context switch or kernel_neon_begin() or context - * modification (sigreturn, ptrace) intervenes. - * So, ensure that CPACR_EL1 is already correct for the fast-path case: - */ - mrs x9, cpacr_el1 - bic x9, x9, #CPACR_EL1_ZEN_EL0EN // disable SVE for el0 - msr cpacr_el1, x9 // synchronised by eret to el0 -#endif - -el0_svc_naked: // compat entry point - stp x0, xscno, [sp, #S_ORIG_X0] // save the original x0 and syscall number - enable_daif - ct_user_exit 1 - - tst x16, #_TIF_SYSCALL_WORK // check for syscall hooks - b.ne __sys_trace - cmp wscno, wsc_nr // check upper syscall limit - b.hs ni_sys - mask_nospec64 xscno, xsc_nr, x19 // enforce bounds for syscall number - ldr x16, [stbl, xscno, lsl #3] // address in the syscall table - blr x16 // call sys_* routine - b ret_fast_syscall -ni_sys: - mov x0, sp - bl do_ni_syscall - b ret_fast_syscall -ENDPROC(el0_svc) - - /* - * This is the really slow path. We're going to be doing context - * switches, and waiting for our parent to respond. - */ -__sys_trace: - cmp wscno, #NO_SYSCALL // user-issued syscall(-1)? - b.ne 1f - mov x0, #-ENOSYS // set default errno if so - str x0, [sp, #S_X0] -1: mov x0, sp - bl syscall_trace_enter - cmp w0, #NO_SYSCALL // skip the syscall? - b.eq __sys_trace_return_skipped - mov wscno, w0 // syscall number (possibly new) - mov x1, sp // pointer to regs - cmp wscno, wsc_nr // check upper syscall limit - b.hs __ni_sys_trace - ldp x0, x1, [sp] // restore the syscall args - ldp x2, x3, [sp, #S_X2] - ldp x4, x5, [sp, #S_X4] - ldp x6, x7, [sp, #S_X6] - ldr x16, [stbl, xscno, lsl #3] // address in the syscall table - blr x16 // call sys_* routine - -__sys_trace_return: - str x0, [sp, #S_X0] // save returned x0 -__sys_trace_return_skipped: mov x0, sp - bl syscall_trace_exit + bl el0_svc_handler b ret_to_user - -__ni_sys_trace: - mov x0, sp - bl do_ni_syscall - b __sys_trace_return +ENDPROC(el0_svc) .popsection // .entry.text @@ -1138,14 +1032,6 @@ __entry_tramp_data_start: #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ /* - * Special system call wrappers. - */ -ENTRY(sys_rt_sigreturn_wrapper) - mov x0, sp - b sys_rt_sigreturn -ENDPROC(sys_rt_sigreturn_wrapper) - -/* * Register switch for AArch64. The callee-saved registers need to be saved * and restored. On entry: * x0 = previous task_struct (must be preserved across the switch) diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S deleted file mode 100644 index f332d5d1f6b4..000000000000 --- a/arch/arm64/kernel/entry32.S +++ /dev/null @@ -1,121 +0,0 @@ -/* - * Compat system call wrappers - * - * Copyright (C) 2012 ARM Ltd. - * Authors: Will Deacon <will.deacon@arm.com> - * Catalin Marinas <catalin.marinas@arm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/linkage.h> -#include <linux/const.h> - -#include <asm/assembler.h> -#include <asm/asm-offsets.h> -#include <asm/errno.h> -#include <asm/page.h> - -/* - * System call wrappers for the AArch32 compatibility layer. - */ - -ENTRY(compat_sys_sigreturn_wrapper) - mov x0, sp - b compat_sys_sigreturn -ENDPROC(compat_sys_sigreturn_wrapper) - -ENTRY(compat_sys_rt_sigreturn_wrapper) - mov x0, sp - b compat_sys_rt_sigreturn -ENDPROC(compat_sys_rt_sigreturn_wrapper) - -ENTRY(compat_sys_statfs64_wrapper) - mov w3, #84 - cmp w1, #88 - csel w1, w3, w1, eq - b compat_sys_statfs64 -ENDPROC(compat_sys_statfs64_wrapper) - -ENTRY(compat_sys_fstatfs64_wrapper) - mov w3, #84 - cmp w1, #88 - csel w1, w3, w1, eq - b compat_sys_fstatfs64 -ENDPROC(compat_sys_fstatfs64_wrapper) - -/* - * Note: off_4k (w5) is always in units of 4K. If we can't do the - * requested offset because it is not page-aligned, we return -EINVAL. - */ -ENTRY(compat_sys_mmap2_wrapper) -#if PAGE_SHIFT > 12 - tst w5, #~PAGE_MASK >> 12 - b.ne 1f - lsr w5, w5, #PAGE_SHIFT - 12 -#endif - b sys_mmap_pgoff -1: mov x0, #-EINVAL - ret -ENDPROC(compat_sys_mmap2_wrapper) - -/* - * Wrappers for AArch32 syscalls that either take 64-bit parameters - * in registers or that take 32-bit parameters which require sign - * extension. - */ -ENTRY(compat_sys_pread64_wrapper) - regs_to_64 x3, x4, x5 - b sys_pread64 -ENDPROC(compat_sys_pread64_wrapper) - -ENTRY(compat_sys_pwrite64_wrapper) - regs_to_64 x3, x4, x5 - b sys_pwrite64 -ENDPROC(compat_sys_pwrite64_wrapper) - -ENTRY(compat_sys_truncate64_wrapper) - regs_to_64 x1, x2, x3 - b sys_truncate -ENDPROC(compat_sys_truncate64_wrapper) - -ENTRY(compat_sys_ftruncate64_wrapper) - regs_to_64 x1, x2, x3 - b sys_ftruncate -ENDPROC(compat_sys_ftruncate64_wrapper) - -ENTRY(compat_sys_readahead_wrapper) - regs_to_64 x1, x2, x3 - mov w2, w4 - b sys_readahead -ENDPROC(compat_sys_readahead_wrapper) - -ENTRY(compat_sys_fadvise64_64_wrapper) - mov w6, w1 - regs_to_64 x1, x2, x3 - regs_to_64 x2, x4, x5 - mov w3, w6 - b sys_fadvise64_64 -ENDPROC(compat_sys_fadvise64_64_wrapper) - -ENTRY(compat_sys_sync_file_range2_wrapper) - regs_to_64 x2, x2, x3 - regs_to_64 x3, x4, x5 - b sys_sync_file_range2 -ENDPROC(compat_sys_sync_file_range2_wrapper) - -ENTRY(compat_sys_fallocate_wrapper) - regs_to_64 x2, x2, x3 - regs_to_64 x3, x4, x5 - b sys_fallocate -ENDPROC(compat_sys_fallocate_wrapper) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 84c68b14f1b2..58c53bc96928 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -159,25 +159,6 @@ static void sve_free(struct task_struct *task) __sve_free(task); } -static void change_cpacr(u64 val, u64 mask) -{ - u64 cpacr = read_sysreg(CPACR_EL1); - u64 new = (cpacr & ~mask) | val; - - if (new != cpacr) - write_sysreg(new, CPACR_EL1); -} - -static void sve_user_disable(void) -{ - change_cpacr(0, CPACR_EL1_ZEN_EL0EN); -} - -static void sve_user_enable(void) -{ - change_cpacr(CPACR_EL1_ZEN_EL0EN, CPACR_EL1_ZEN_EL0EN); -} - /* * TIF_SVE controls whether a task can use SVE without trapping while * in userspace, and also the way a task's FPSIMD/SVE state is stored diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 413dbe530da8..8c9644376326 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -343,14 +343,13 @@ static int get_hbp_len(u8 hbp_len) /* * Check whether bp virtual address is in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->ctrl.len); + va = hw->address; + len = get_hbp_len(hw->ctrl.len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -421,53 +420,53 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->ctrl.type = ARM_BREAKPOINT_EXECUTE; + hw->ctrl.type = ARM_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->ctrl.type = ARM_BREAKPOINT_LOAD; + hw->ctrl.type = ARM_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->ctrl.type = ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; + hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->ctrl.len = ARM_BREAKPOINT_LEN_1; + hw->ctrl.len = ARM_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->ctrl.len = ARM_BREAKPOINT_LEN_2; + hw->ctrl.len = ARM_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_3: - info->ctrl.len = ARM_BREAKPOINT_LEN_3; + hw->ctrl.len = ARM_BREAKPOINT_LEN_3; break; case HW_BREAKPOINT_LEN_4: - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_5: - info->ctrl.len = ARM_BREAKPOINT_LEN_5; + hw->ctrl.len = ARM_BREAKPOINT_LEN_5; break; case HW_BREAKPOINT_LEN_6: - info->ctrl.len = ARM_BREAKPOINT_LEN_6; + hw->ctrl.len = ARM_BREAKPOINT_LEN_6; break; case HW_BREAKPOINT_LEN_7: - info->ctrl.len = ARM_BREAKPOINT_LEN_7; + hw->ctrl.len = ARM_BREAKPOINT_LEN_7; break; case HW_BREAKPOINT_LEN_8: - info->ctrl.len = ARM_BREAKPOINT_LEN_8; + hw->ctrl.len = ARM_BREAKPOINT_LEN_8; break; default: return -EINVAL; @@ -478,37 +477,37 @@ static int arch_build_bp_info(struct perf_event *bp) * AArch32 also requires breakpoints of length 2 for Thumb. * Watchpoints can be of length 1, 2, 4 or 8 bytes. */ - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) { if (is_compat_bp(bp)) { - if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 && - info->ctrl.len != ARM_BREAKPOINT_LEN_4) + if (hw->ctrl.len != ARM_BREAKPOINT_LEN_2 && + hw->ctrl.len != ARM_BREAKPOINT_LEN_4) return -EINVAL; - } else if (info->ctrl.len != ARM_BREAKPOINT_LEN_4) { + } else if (hw->ctrl.len != ARM_BREAKPOINT_LEN_4) { /* * FIXME: Some tools (I'm looking at you perf) assume * that breakpoints should be sizeof(long). This * is nonsense. For now, we fix up the parameter * but we should probably return -EINVAL instead. */ - info->ctrl.len = ARM_BREAKPOINT_LEN_4; + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; } } /* Address */ - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* * Privilege * Note that we disallow combined EL0/EL1 breakpoints because * that would complicate the stepping code. */ - if (arch_check_bp_in_kernelspace(bp)) - info->ctrl.privilege = AARCH64_BREAKPOINT_EL1; + if (arch_check_bp_in_kernelspace(hw)) + hw->ctrl.privilege = AARCH64_BREAKPOINT_EL1; else - info->ctrl.privilege = AARCH64_BREAKPOINT_EL0; + hw->ctrl.privilege = AARCH64_BREAKPOINT_EL0; /* Enabled? */ - info->ctrl.enabled = !bp->attr.disabled; + hw->ctrl.enabled = !attr->disabled; return 0; } @@ -516,14 +515,15 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings. */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); int ret; u64 alignment_mask, offset; /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; @@ -537,42 +537,42 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * that here. */ if (is_compat_bp(bp)) { - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; else alignment_mask = 0x3; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; switch (offset) { case 0: /* Aligned */ break; case 1: /* Allow single byte watchpoint. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) break; case 2: /* Allow halfword watchpoints and breakpoints. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_2) + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; default: return -EINVAL; } } else { - if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) alignment_mask = 0x3; else alignment_mask = 0x7; - offset = info->address & alignment_mask; + offset = hw->address & alignment_mask; } - info->address &= ~alignment_mask; - info->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; /* * Disallow per-task kernel breakpoints since these would * complicate the stepping code. */ - if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target) + if (hw->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target) return -EINVAL; return 0; diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 816d03c4c913..2b3413549734 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -149,20 +149,6 @@ int __kprobes aarch64_insn_write(void *addr, u32 insn) return __aarch64_insn_write(addr, cpu_to_le32(insn)); } -static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn) -{ - if (aarch64_get_insn_class(insn) != AARCH64_INSN_CLS_BR_SYS) - return false; - - return aarch64_insn_is_b(insn) || - aarch64_insn_is_bl(insn) || - aarch64_insn_is_svc(insn) || - aarch64_insn_is_hvc(insn) || - aarch64_insn_is_smc(insn) || - aarch64_insn_is_brk(insn) || - aarch64_insn_is_nop(insn); -} - bool __kprobes aarch64_insn_uses_literal(u32 insn) { /* ldr/ldrsw (literal), prfm */ @@ -189,22 +175,6 @@ bool __kprobes aarch64_insn_is_branch(u32 insn) aarch64_insn_is_bcond(insn); } -/* - * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a - * Section B2.6.5 "Concurrent modification and execution of instructions": - * Concurrent modification and execution of instructions can lead to the - * resulting instruction performing any behavior that can be achieved by - * executing any sequence of instructions that can be executed from the - * same Exception level, except where the instruction before modification - * and the instruction after modification is a B, BL, NOP, BKPT, SVC, HVC, - * or SMC instruction. - */ -bool __kprobes aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn) -{ - return __aarch64_insn_hotpatch_safe(old_insn) && - __aarch64_insn_hotpatch_safe(new_insn); -} - int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn) { u32 *tp = addr; @@ -216,8 +186,8 @@ int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn) ret = aarch64_insn_write(tp, insn); if (ret == 0) - flush_icache_range((uintptr_t)tp, - (uintptr_t)tp + AARCH64_INSN_SIZE); + __flush_icache_range((uintptr_t)tp, + (uintptr_t)tp + AARCH64_INSN_SIZE); return ret; } @@ -239,11 +209,6 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); - /* - * aarch64_insn_patch_text_nosync() calls flush_icache_range(), - * which ends with "dsb; isb" pair guaranteeing global - * visibility. - */ /* Notify other processors with an additional increment. */ atomic_inc(&pp->cpu_count); } else { @@ -255,8 +220,7 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) return ret; } -static -int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt) +int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt) { struct aarch64_insn_patch patch = { .text_addrs = addrs, @@ -272,34 +236,6 @@ int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt) cpu_online_mask); } -int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt) -{ - int ret; - u32 insn; - - /* Unsafe to patch multiple instructions without synchronizaiton */ - if (cnt == 1) { - ret = aarch64_insn_read(addrs[0], &insn); - if (ret) - return ret; - - if (aarch64_insn_hotpatch_safe(insn, insns[0])) { - /* - * ARMv8 architecture doesn't guarantee all CPUs see - * the new instruction after returning from function - * aarch64_insn_patch_text_nosync(). So send IPIs to - * all other CPUs to achieve instruction - * synchronization. - */ - ret = aarch64_insn_patch_text_nosync(addrs[0], insns[0]); - kick_all_cpus_sync(); - return ret; - } - } - - return aarch64_insn_patch_text_sync(addrs, insns, cnt); -} - static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type, u32 *maskp, int *shiftp) { diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 60e5fc661f74..780a12f59a8f 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -42,16 +42,6 @@ int arch_show_interrupts(struct seq_file *p, int prec) return 0; } -void (*handle_arch_irq)(struct pt_regs *) = NULL; - -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - if (handle_arch_irq) - return; - - handle_arch_irq = handle_irq; -} - #ifdef CONFIG_VMAP_STACK static void init_irq_stacks(void) { diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c index c2dd1ad3e648..e0756416e567 100644 --- a/arch/arm64/kernel/jump_label.c +++ b/arch/arm64/kernel/jump_label.c @@ -36,7 +36,7 @@ void arch_jump_label_transform(struct jump_entry *entry, insn = aarch64_insn_gen_nop(); } - aarch64_insn_patch_text(&addr, &insn, 1); + aarch64_insn_patch_text_nosync(addr, insn); } void arch_jump_label_transform_static(struct jump_entry *entry, diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index f76ea92dff91..f6a5c6bc1434 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -184,8 +184,15 @@ void machine_kexec(struct kimage *kimage) /* Flush the reboot_code_buffer in preparation for its execution. */ __flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size); - flush_icache_range((uintptr_t)reboot_code_buffer, - arm64_relocate_new_kernel_size); + + /* + * Although we've killed off the secondary CPUs, we don't update + * the online mask if we're handling a crash kernel and consequently + * need to avoid flush_icache_range(), which will attempt to IPI + * the offline CPUs. Therefore, we must use the __* variant here. + */ + __flush_icache_range((uintptr_t)reboot_code_buffer, + arm64_relocate_new_kernel_size); /* Flush the kimage list and its buffers. */ kexec_list_flush(kimage); @@ -207,8 +214,7 @@ void machine_kexec(struct kimage *kimage) * relocation is complete. */ - cpu_soft_restart(kimage != kexec_crash_image, - reboot_code_buffer_phys, kimage->head, kimage->start, 0); + cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, 0); BUG(); /* Should never get here. */ } @@ -361,4 +367,5 @@ void arch_crash_save_vmcoreinfo(void) kimage_voffset); vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", PHYS_OFFSET); + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 33147aacdafd..8e38d5267f22 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -25,6 +25,7 @@ #include <asm/virt.h> #include <linux/acpi.h> +#include <linux/clocksource.h> #include <linux/of.h> #include <linux/perf/arm_pmu.h> #include <linux/platform_device.h> @@ -446,9 +447,16 @@ static struct attribute_group armv8_pmuv3_events_attr_group = { }; PMU_FORMAT_ATTR(event, "config:0-15"); +PMU_FORMAT_ATTR(long, "config1:0"); + +static inline bool armv8pmu_event_is_64bit(struct perf_event *event) +{ + return event->attr.config1 & 0x1; +} static struct attribute *armv8_pmuv3_format_attrs[] = { &format_attr_event.attr, + &format_attr_long.attr, NULL, }; @@ -466,6 +474,21 @@ static struct attribute_group armv8_pmuv3_format_attr_group = { (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) /* + * We must chain two programmable counters for 64 bit events, + * except when we have allocated the 64bit cycle counter (for CPU + * cycles event). This must be called only when the event has + * a counter allocated. + */ +static inline bool armv8pmu_event_is_chained(struct perf_event *event) +{ + int idx = event->hw.idx; + + return !WARN_ON(idx < 0) && + armv8pmu_event_is_64bit(event) && + (idx != ARMV8_IDX_CYCLE_COUNTER); +} + +/* * ARMv8 low level PMU access */ @@ -503,34 +526,68 @@ static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx) return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx)); } -static inline int armv8pmu_select_counter(int idx) +static inline void armv8pmu_select_counter(int idx) { u32 counter = ARMV8_IDX_TO_COUNTER(idx); write_sysreg(counter, pmselr_el0); isb(); +} - return idx; +static inline u32 armv8pmu_read_evcntr(int idx) +{ + armv8pmu_select_counter(idx); + return read_sysreg(pmxevcntr_el0); +} + +static inline u64 armv8pmu_read_hw_counter(struct perf_event *event) +{ + int idx = event->hw.idx; + u64 val = 0; + + val = armv8pmu_read_evcntr(idx); + if (armv8pmu_event_is_chained(event)) + val = (val << 32) | armv8pmu_read_evcntr(idx - 1); + return val; } -static inline u32 armv8pmu_read_counter(struct perf_event *event) +static inline u64 armv8pmu_read_counter(struct perf_event *event) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; - u32 value = 0; + u64 value = 0; if (!armv8pmu_counter_valid(cpu_pmu, idx)) pr_err("CPU%u reading wrong counter %d\n", smp_processor_id(), idx); else if (idx == ARMV8_IDX_CYCLE_COUNTER) value = read_sysreg(pmccntr_el0); - else if (armv8pmu_select_counter(idx) == idx) - value = read_sysreg(pmxevcntr_el0); + else + value = armv8pmu_read_hw_counter(event); return value; } -static inline void armv8pmu_write_counter(struct perf_event *event, u32 value) +static inline void armv8pmu_write_evcntr(int idx, u32 value) +{ + armv8pmu_select_counter(idx); + write_sysreg(value, pmxevcntr_el0); +} + +static inline void armv8pmu_write_hw_counter(struct perf_event *event, + u64 value) +{ + int idx = event->hw.idx; + + if (armv8pmu_event_is_chained(event)) { + armv8pmu_write_evcntr(idx, upper_32_bits(value)); + armv8pmu_write_evcntr(idx - 1, lower_32_bits(value)); + } else { + armv8pmu_write_evcntr(idx, value); + } +} + +static inline void armv8pmu_write_counter(struct perf_event *event, u64 value) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; @@ -541,22 +598,43 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u32 value) smp_processor_id(), idx); else if (idx == ARMV8_IDX_CYCLE_COUNTER) { /* - * Set the upper 32bits as this is a 64bit counter but we only - * count using the lower 32bits and we want an interrupt when - * it overflows. + * The cycles counter is really a 64-bit counter. + * When treating it as a 32-bit counter, we only count + * the lower 32 bits, and set the upper 32-bits so that + * we get an interrupt upon 32-bit overflow. */ - u64 value64 = 0xffffffff00000000ULL | value; - - write_sysreg(value64, pmccntr_el0); - } else if (armv8pmu_select_counter(idx) == idx) - write_sysreg(value, pmxevcntr_el0); + if (!armv8pmu_event_is_64bit(event)) + value |= 0xffffffff00000000ULL; + write_sysreg(value, pmccntr_el0); + } else + armv8pmu_write_hw_counter(event, value); } static inline void armv8pmu_write_evtype(int idx, u32 val) { - if (armv8pmu_select_counter(idx) == idx) { - val &= ARMV8_PMU_EVTYPE_MASK; - write_sysreg(val, pmxevtyper_el0); + armv8pmu_select_counter(idx); + val &= ARMV8_PMU_EVTYPE_MASK; + write_sysreg(val, pmxevtyper_el0); +} + +static inline void armv8pmu_write_event_type(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + /* + * For chained events, the low counter is programmed to count + * the event of interest and the high counter is programmed + * with CHAIN event code with filters set to count at all ELs. + */ + if (armv8pmu_event_is_chained(event)) { + u32 chain_evt = ARMV8_PMUV3_PERFCTR_CHAIN | + ARMV8_PMU_INCLUDE_EL2; + + armv8pmu_write_evtype(idx - 1, hwc->config_base); + armv8pmu_write_evtype(idx, chain_evt); + } else { + armv8pmu_write_evtype(idx, hwc->config_base); } } @@ -567,6 +645,16 @@ static inline int armv8pmu_enable_counter(int idx) return idx; } +static inline void armv8pmu_enable_event_counter(struct perf_event *event) +{ + int idx = event->hw.idx; + + armv8pmu_enable_counter(idx); + if (armv8pmu_event_is_chained(event)) + armv8pmu_enable_counter(idx - 1); + isb(); +} + static inline int armv8pmu_disable_counter(int idx) { u32 counter = ARMV8_IDX_TO_COUNTER(idx); @@ -574,6 +662,16 @@ static inline int armv8pmu_disable_counter(int idx) return idx; } +static inline void armv8pmu_disable_event_counter(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (armv8pmu_event_is_chained(event)) + armv8pmu_disable_counter(idx - 1); + armv8pmu_disable_counter(idx); +} + static inline int armv8pmu_enable_intens(int idx) { u32 counter = ARMV8_IDX_TO_COUNTER(idx); @@ -581,6 +679,11 @@ static inline int armv8pmu_enable_intens(int idx) return idx; } +static inline int armv8pmu_enable_event_irq(struct perf_event *event) +{ + return armv8pmu_enable_intens(event->hw.idx); +} + static inline int armv8pmu_disable_intens(int idx) { u32 counter = ARMV8_IDX_TO_COUNTER(idx); @@ -593,6 +696,11 @@ static inline int armv8pmu_disable_intens(int idx) return idx; } +static inline int armv8pmu_disable_event_irq(struct perf_event *event) +{ + return armv8pmu_disable_intens(event->hw.idx); +} + static inline u32 armv8pmu_getreset_flags(void) { u32 value; @@ -610,10 +718,8 @@ static inline u32 armv8pmu_getreset_flags(void) static void armv8pmu_enable_event(struct perf_event *event) { unsigned long flags; - struct hw_perf_event *hwc = &event->hw; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); - int idx = hwc->idx; /* * Enable counter and interrupt, and set the counter to count @@ -624,22 +730,22 @@ static void armv8pmu_enable_event(struct perf_event *event) /* * Disable counter */ - armv8pmu_disable_counter(idx); + armv8pmu_disable_event_counter(event); /* * Set event (if destined for PMNx counters). */ - armv8pmu_write_evtype(idx, hwc->config_base); + armv8pmu_write_event_type(event); /* * Enable interrupt for this counter */ - armv8pmu_enable_intens(idx); + armv8pmu_enable_event_irq(event); /* * Enable counter */ - armv8pmu_enable_counter(idx); + armv8pmu_enable_event_counter(event); raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } @@ -647,10 +753,8 @@ static void armv8pmu_enable_event(struct perf_event *event) static void armv8pmu_disable_event(struct perf_event *event) { unsigned long flags; - struct hw_perf_event *hwc = &event->hw; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); - int idx = hwc->idx; /* * Disable counter and interrupt @@ -660,16 +764,38 @@ static void armv8pmu_disable_event(struct perf_event *event) /* * Disable counter */ - armv8pmu_disable_counter(idx); + armv8pmu_disable_event_counter(event); /* * Disable interrupt for this counter */ - armv8pmu_disable_intens(idx); + armv8pmu_disable_event_irq(event); raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } +static void armv8pmu_start(struct arm_pmu *cpu_pmu) +{ + unsigned long flags; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + /* Enable all counters */ + armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void armv8pmu_stop(struct arm_pmu *cpu_pmu) +{ + unsigned long flags; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + /* Disable all counters */ + armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu) { u32 pmovsr; @@ -694,6 +820,11 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu) */ regs = get_irq_regs(); + /* + * Stop the PMU while processing the counter overflows + * to prevent skews in group events. + */ + armv8pmu_stop(cpu_pmu); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -718,6 +849,7 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu) if (perf_event_overflow(event, &data, regs)) cpu_pmu->disable(event); } + armv8pmu_start(cpu_pmu); /* * Handle the pending perf events. @@ -731,32 +863,42 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu) return IRQ_HANDLED; } -static void armv8pmu_start(struct arm_pmu *cpu_pmu) +static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc, + struct arm_pmu *cpu_pmu) { - unsigned long flags; - struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx; - raw_spin_lock_irqsave(&events->pmu_lock, flags); - /* Enable all counters */ - armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E); - raw_spin_unlock_irqrestore(&events->pmu_lock, flags); + for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx ++) { + if (!test_and_set_bit(idx, cpuc->used_mask)) + return idx; + } + return -EAGAIN; } -static void armv8pmu_stop(struct arm_pmu *cpu_pmu) +static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc, + struct arm_pmu *cpu_pmu) { - unsigned long flags; - struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx; - raw_spin_lock_irqsave(&events->pmu_lock, flags); - /* Disable all counters */ - armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E); - raw_spin_unlock_irqrestore(&events->pmu_lock, flags); + /* + * Chaining requires two consecutive event counters, where + * the lower idx must be even. + */ + for (idx = ARMV8_IDX_COUNTER0 + 1; idx < cpu_pmu->num_events; idx += 2) { + if (!test_and_set_bit(idx, cpuc->used_mask)) { + /* Check if the preceding even counter is available */ + if (!test_and_set_bit(idx - 1, cpuc->used_mask)) + return idx; + /* Release the Odd counter */ + clear_bit(idx, cpuc->used_mask); + } + } + return -EAGAIN; } static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, struct perf_event *event) { - int idx; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT; @@ -770,13 +912,20 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, /* * Otherwise use events counters */ - for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) { - if (!test_and_set_bit(idx, cpuc->used_mask)) - return idx; - } + if (armv8pmu_event_is_64bit(event)) + return armv8pmu_get_chain_idx(cpuc, cpu_pmu); + else + return armv8pmu_get_single_idx(cpuc, cpu_pmu); +} - /* The counters are all in use. */ - return -EAGAIN; +static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + int idx = event->hw.idx; + + clear_bit(idx, cpuc->used_mask); + if (armv8pmu_event_is_chained(event)) + clear_bit(idx - 1, cpuc->used_mask); } /* @@ -851,6 +1000,9 @@ static int __armv8_pmuv3_map_event(struct perf_event *event, &armv8_pmuv3_perf_cache_map, ARMV8_PMU_EVTYPE_EVENT); + if (armv8pmu_event_is_64bit(event)) + event->hw.flags |= ARMPMU_EVT_64BIT; + /* Onl expose micro/arch events supported by this PMU */ if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) && test_bit(hw_event_id, armpmu->pmceid_bitmap)) { @@ -957,10 +1109,10 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->read_counter = armv8pmu_read_counter, cpu_pmu->write_counter = armv8pmu_write_counter, cpu_pmu->get_event_idx = armv8pmu_get_event_idx, + cpu_pmu->clear_event_idx = armv8pmu_clear_event_idx, cpu_pmu->start = armv8pmu_start, cpu_pmu->stop = armv8pmu_stop, cpu_pmu->reset = armv8pmu_reset, - cpu_pmu->max_period = (1LLU << 32) - 1, cpu_pmu->set_event_filter = armv8pmu_set_event_filter; return 0; @@ -1127,3 +1279,32 @@ static int __init armv8_pmu_driver_init(void) return arm_pmu_acpi_probe(armv8_pmuv3_init); } device_initcall(armv8_pmu_driver_init) + +void arch_perf_update_userpage(struct perf_event *event, + struct perf_event_mmap_page *userpg, u64 now) +{ + u32 freq; + u32 shift; + + /* + * Internal timekeeping for enabled/running/stopped times + * is always computed with the sched_clock. + */ + freq = arch_timer_get_rate(); + userpg->cap_user_time = 1; + + clocks_calc_mult_shift(&userpg->time_mult, &shift, freq, + NSEC_PER_SEC, 0); + /* + * time_shift is not expected to be greater than 31 due to + * the original published conversion algorithm shifting a + * 32-bit value (now specifies a 64-bit value) - refer + * perf_event_mmap_page documentation in perf_event.h. + */ + if (shift == 32) { + shift = 31; + userpg->time_mult >>= 1; + } + userpg->time_shift = (u16)shift; + userpg->time_offset = -now; +} diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d849d9804011..e78c3ef04d95 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -275,7 +275,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p, break; case KPROBE_HIT_SS: case KPROBE_REENTER: - pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr); + pr_warn("Unrecoverable kprobe detected.\n"); dump_kprobe(p); BUG(); break; @@ -395,9 +395,9 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry, - * so get out doing nothing more here. + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. * * pre_handler can hit a breakpoint and can step thru * before return, keep PSTATE D-flag enabled until @@ -405,16 +405,8 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs, kcb, 0); - return; - } - } - } else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) == - BRK64_OPCODE_KPROBES) && cur_kprobe) { - /* We probably hit a jprobe. Call its break handler. */ - if (cur_kprobe->break_handler && - cur_kprobe->break_handler(cur_kprobe, regs)) { - setup_singlestep(cur_kprobe, regs, kcb, 0); - return; + } else + reset_current_kprobe(); } } /* @@ -465,74 +457,6 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr) return DBG_HOOK_HANDLED; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - /* - * Since we can't be sure where in the stack frame "stacked" - * pass-by-value arguments are stored we just don't try to - * duplicate any of the stack. Do not use jprobes on functions that - * use more than 64 bytes (after padding each to an 8 byte boundary) - * of arguments, or pass individual arguments larger than 16 bytes. - */ - - instruction_pointer_set(regs, (unsigned long) jp->entry); - preempt_disable(); - pause_graph_tracing(); - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - /* - * Jprobe handler return by entering break exception, - * encoded same as kprobe, but with following conditions - * -a special PC to identify it from the other kprobes. - * -restore stack addr to original saved pt_regs - */ - asm volatile(" mov sp, %0 \n" - "jprobe_return_break: brk %1 \n" - : - : "r" (kcb->jprobe_saved_regs.sp), - "I" (BRK64_ESR_KPROBES) - : "memory"); - - unreachable(); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_addr = kcb->jprobe_saved_regs.sp; - long orig_sp = kernel_stack_pointer(regs); - struct jprobe *jp = container_of(p, struct jprobe, kp); - extern const char jprobe_return_break[]; - - if (instruction_pointer(regs) != (u64) jprobe_return_break) - return 0; - - if (orig_sp != stack_addr) { - struct pt_regs *saved_regs = - (struct pt_regs *)kcb->jprobe_saved_regs.sp; - pr_err("current sp %lx does not match saved sp %lx\n", - orig_sp, stack_addr); - pr_err("Saved registers for jprobe %p\n", jp); - __show_regs(saved_regs); - pr_err("Current registers\n"); - __show_regs(regs); - BUG(); - } - unpause_graph_tracing(); - *regs = kcb->jprobe_saved_regs; - preempt_enable_no_resched(); - return 1; -} - bool arch_within_kprobe_blacklist(unsigned long addr) { if ((addr >= (unsigned long)__kprobes_text_start && diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index e10bc363f533..7f1628effe6d 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -177,16 +177,16 @@ static void print_pstate(struct pt_regs *regs) if (compat_user_mode(regs)) { printk("pstate: %08llx (%c%c%c%c %c %s %s %c%c%c)\n", pstate, - pstate & COMPAT_PSR_N_BIT ? 'N' : 'n', - pstate & COMPAT_PSR_Z_BIT ? 'Z' : 'z', - pstate & COMPAT_PSR_C_BIT ? 'C' : 'c', - pstate & COMPAT_PSR_V_BIT ? 'V' : 'v', - pstate & COMPAT_PSR_Q_BIT ? 'Q' : 'q', - pstate & COMPAT_PSR_T_BIT ? "T32" : "A32", - pstate & COMPAT_PSR_E_BIT ? "BE" : "LE", - pstate & COMPAT_PSR_A_BIT ? 'A' : 'a', - pstate & COMPAT_PSR_I_BIT ? 'I' : 'i', - pstate & COMPAT_PSR_F_BIT ? 'F' : 'f'); + pstate & PSR_AA32_N_BIT ? 'N' : 'n', + pstate & PSR_AA32_Z_BIT ? 'Z' : 'z', + pstate & PSR_AA32_C_BIT ? 'C' : 'c', + pstate & PSR_AA32_V_BIT ? 'V' : 'v', + pstate & PSR_AA32_Q_BIT ? 'Q' : 'q', + pstate & PSR_AA32_T_BIT ? "T32" : "A32", + pstate & PSR_AA32_E_BIT ? "BE" : "LE", + pstate & PSR_AA32_A_BIT ? 'A' : 'a', + pstate & PSR_AA32_I_BIT ? 'I' : 'i', + pstate & PSR_AA32_F_BIT ? 'F' : 'f'); } else { printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n", pstate, @@ -493,3 +493,25 @@ void arch_setup_new_exec(void) { current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0; } + +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +void __used stackleak_check_alloca(unsigned long size) +{ + unsigned long stack_left; + unsigned long current_sp = current_stack_pointer; + struct stack_info info; + + BUG_ON(!on_accessible_stack(current, current_sp, &info)); + + stack_left = current_sp - info.low; + + /* + * There's a good chance we're almost out of stack space if this + * is true. Using panic() over BUG() is more likely to give + * reliable debugging output. + */ + if (size >= stack_left) + panic("alloca() over the kernel stack boundary\n"); +} +EXPORT_SYMBOL(stackleak_check_alloca); +#endif diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 5c338ce5a7fa..6219486fa25f 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -132,7 +132,7 @@ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) || - on_irq_stack(addr); + on_irq_stack(addr, NULL); } /** @@ -277,19 +277,22 @@ static int ptrace_hbp_set_event(unsigned int note_type, switch (note_type) { case NT_ARM_HW_BREAK: - if (idx < ARM_MAX_BRP) { - tsk->thread.debug.hbp_break[idx] = bp; - err = 0; - } + if (idx >= ARM_MAX_BRP) + goto out; + idx = array_index_nospec(idx, ARM_MAX_BRP); + tsk->thread.debug.hbp_break[idx] = bp; + err = 0; break; case NT_ARM_HW_WATCH: - if (idx < ARM_MAX_WRP) { - tsk->thread.debug.hbp_watch[idx] = bp; - err = 0; - } + if (idx >= ARM_MAX_WRP) + goto out; + idx = array_index_nospec(idx, ARM_MAX_WRP); + tsk->thread.debug.hbp_watch[idx] = bp; + err = 0; break; } +out: return err; } @@ -1076,6 +1079,7 @@ static int compat_gpr_get(struct task_struct *target, break; case 16: reg = task_pt_regs(target)->pstate; + reg = pstate_to_compat_psr(reg); break; case 17: reg = task_pt_regs(target)->orig_x0; @@ -1143,6 +1147,7 @@ static int compat_gpr_set(struct task_struct *target, newregs.pc = reg; break; case 16: + reg = compat_psr_to_pstate(reg); newregs.pstate = reg; break; case 17: @@ -1629,7 +1634,7 @@ static void tracehook_report_syscall(struct pt_regs *regs, regs->regs[regno] = saved_reg; } -asmlinkage int syscall_trace_enter(struct pt_regs *regs) +int syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); @@ -1647,7 +1652,7 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs) return regs->syscallno; } -asmlinkage void syscall_trace_exit(struct pt_regs *regs) +void syscall_trace_exit(struct pt_regs *regs) { audit_syscall_exit(regs); @@ -1656,18 +1661,24 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs) if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); + + rseq_syscall(regs); } /* - * Bits which are always architecturally RES0 per ARM DDI 0487A.h + * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487C.a + * We also take into account DIT (bit 24), which is not yet documented, and + * treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may be + * allocated an EL0 meaning in future. * Userspace cannot use these until they have an architectural meaning. + * Note that this follows the SPSR_ELx format, not the AArch32 PSR format. * We also reserve IL for the kernel; SS is handled dynamically. */ #define SPSR_EL1_AARCH64_RES0_BITS \ - (GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \ - GENMASK_ULL(5, 5)) + (GENMASK_ULL(63,32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \ + GENMASK_ULL(20, 10) | GENMASK_ULL(5, 5)) #define SPSR_EL1_AARCH32_RES0_BITS \ - (GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20)) + (GENMASK_ULL(63,32) | GENMASK_ULL(23, 22) | GENMASK_ULL(20,20)) static int valid_compat_regs(struct user_pt_regs *regs) { @@ -1675,15 +1686,15 @@ static int valid_compat_regs(struct user_pt_regs *regs) if (!system_supports_mixed_endian_el0()) { if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) - regs->pstate |= COMPAT_PSR_E_BIT; + regs->pstate |= PSR_AA32_E_BIT; else - regs->pstate &= ~COMPAT_PSR_E_BIT; + regs->pstate &= ~PSR_AA32_E_BIT; } if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) && - (regs->pstate & COMPAT_PSR_A_BIT) == 0 && - (regs->pstate & COMPAT_PSR_I_BIT) == 0 && - (regs->pstate & COMPAT_PSR_F_BIT) == 0) { + (regs->pstate & PSR_AA32_A_BIT) == 0 && + (regs->pstate & PSR_AA32_I_BIT) == 0 && + (regs->pstate & PSR_AA32_F_BIT) == 0) { return 1; } @@ -1691,11 +1702,11 @@ static int valid_compat_regs(struct user_pt_regs *regs) * Force PSR to a valid 32-bit EL0t, preserving the same bits as * arch/arm. */ - regs->pstate &= COMPAT_PSR_N_BIT | COMPAT_PSR_Z_BIT | - COMPAT_PSR_C_BIT | COMPAT_PSR_V_BIT | - COMPAT_PSR_Q_BIT | COMPAT_PSR_IT_MASK | - COMPAT_PSR_GE_MASK | COMPAT_PSR_E_BIT | - COMPAT_PSR_T_BIT; + regs->pstate &= PSR_AA32_N_BIT | PSR_AA32_Z_BIT | + PSR_AA32_C_BIT | PSR_AA32_V_BIT | + PSR_AA32_Q_BIT | PSR_AA32_IT_MASK | + PSR_AA32_GE_MASK | PSR_AA32_E_BIT | + PSR_AA32_T_BIT; regs->pstate |= PSR_MODE32_BIT; return 0; diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 6b8d90d5ceae..5ba4465e44f0 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -13,6 +13,7 @@ #include <asm/mmu.h> #include <asm/ptrace.h> #include <asm/sections.h> +#include <asm/stacktrace.h> #include <asm/sysreg.h> #include <asm/vmap_stack.h> @@ -88,23 +89,52 @@ static int init_sdei_stacks(void) return err; } -bool _on_sdei_stack(unsigned long sp) +static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info) { - unsigned long low, high; + unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr); + unsigned long high = low + SDEI_STACK_SIZE; - if (!IS_ENABLED(CONFIG_VMAP_STACK)) + if (sp < low || sp >= high) return false; - low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr); - high = low + SDEI_STACK_SIZE; + if (info) { + info->low = low; + info->high = high; + info->type = STACK_TYPE_SDEI_NORMAL; + } - if (low <= sp && sp < high) + return true; +} + +static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info) +{ + unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr); + unsigned long high = low + SDEI_STACK_SIZE; + + if (sp < low || sp >= high) + return false; + + if (info) { + info->low = low; + info->high = high; + info->type = STACK_TYPE_SDEI_CRITICAL; + } + + return true; +} + +bool _on_sdei_stack(unsigned long sp, struct stack_info *info) +{ + if (!IS_ENABLED(CONFIG_VMAP_STACK)) + return false; + + if (on_sdei_critical_stack(sp, info)) return true; - low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr); - high = low + SDEI_STACK_SIZE; + if (on_sdei_normal_stack(sp, info)) + return true; - return (low <= sp && sp < high); + return false; } unsigned long sdei_arch_get_entry_point(int conduit) diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 30ad2f085d1f..5b4fac434c84 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -241,6 +241,44 @@ static void __init request_standard_resources(void) } } +static int __init reserve_memblock_reserved_regions(void) +{ + phys_addr_t start, end, roundup_end = 0; + struct resource *mem, *res; + u64 i; + + for_each_reserved_mem_region(i, &start, &end) { + if (end <= roundup_end) + continue; /* done already */ + + start = __pfn_to_phys(PFN_DOWN(start)); + end = __pfn_to_phys(PFN_UP(end)) - 1; + roundup_end = end; + + res = kzalloc(sizeof(*res), GFP_ATOMIC); + if (WARN_ON(!res)) + return -ENOMEM; + res->start = start; + res->end = end; + res->name = "reserved"; + res->flags = IORESOURCE_MEM; + + mem = request_resource_conflict(&iomem_resource, res); + /* + * We expected memblock_reserve() regions to conflict with + * memory created by request_standard_resources(). + */ + if (WARN_ON_ONCE(!mem)) + continue; + kfree(res); + + reserve_region_with_split(mem, start, end, "reserved"); + } + + return 0; +} +arch_initcall(reserve_memblock_reserved_regions); + u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; void __init setup_arch(char **cmdline_p) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 511af13e8d8f..5dcc942906db 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -539,8 +539,9 @@ static int restore_sigframe(struct pt_regs *regs, return err; } -asmlinkage long sys_rt_sigreturn(struct pt_regs *regs) +SYSCALL_DEFINE0(rt_sigreturn) { + struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; /* Always make any pending restarted system calls return -EINTR */ @@ -802,6 +803,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) int usig = ksig->sig; int ret; + rseq_signal_deliver(ksig, regs); + /* * Set up the stack frame */ @@ -910,7 +913,7 @@ static void do_signal(struct pt_regs *regs) } asmlinkage void do_notify_resume(struct pt_regs *regs, - unsigned int thread_flags) + unsigned long thread_flags) { /* * The assembly code enters us with IRQs off, but it hasn't @@ -940,6 +943,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, if (thread_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } if (thread_flags & _TIF_FOREIGN_FPSTATE) diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 77b91f478995..24b09003f821 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -243,6 +243,7 @@ static int compat_restore_sigframe(struct pt_regs *regs, int err; sigset_t set; struct compat_aux_sigframe __user *aux; + unsigned long psr; err = get_sigset_t(&set, &sf->uc.uc_sigmask); if (err == 0) { @@ -266,7 +267,9 @@ static int compat_restore_sigframe(struct pt_regs *regs, __get_user_error(regs->compat_sp, &sf->uc.uc_mcontext.arm_sp, err); __get_user_error(regs->compat_lr, &sf->uc.uc_mcontext.arm_lr, err); __get_user_error(regs->pc, &sf->uc.uc_mcontext.arm_pc, err); - __get_user_error(regs->pstate, &sf->uc.uc_mcontext.arm_cpsr, err); + __get_user_error(psr, &sf->uc.uc_mcontext.arm_cpsr, err); + + regs->pstate = compat_psr_to_pstate(psr); /* * Avoid compat_sys_sigreturn() restarting. @@ -282,8 +285,9 @@ static int compat_restore_sigframe(struct pt_regs *regs, return err; } -asmlinkage int compat_sys_sigreturn(struct pt_regs *regs) +COMPAT_SYSCALL_DEFINE0(sigreturn) { + struct pt_regs *regs = current_pt_regs(); struct compat_sigframe __user *frame; /* Always make any pending restarted system calls return -EINTR */ @@ -312,8 +316,9 @@ badframe: return 0; } -asmlinkage int compat_sys_rt_sigreturn(struct pt_regs *regs) +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) { + struct pt_regs *regs = current_pt_regs(); struct compat_rt_sigframe __user *frame; /* Always make any pending restarted system calls return -EINTR */ @@ -372,22 +377,22 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka, { compat_ulong_t handler = ptr_to_compat(ka->sa.sa_handler); compat_ulong_t retcode; - compat_ulong_t spsr = regs->pstate & ~(PSR_f | COMPAT_PSR_E_BIT); + compat_ulong_t spsr = regs->pstate & ~(PSR_f | PSR_AA32_E_BIT); int thumb; /* Check if the handler is written for ARM or Thumb */ thumb = handler & 1; if (thumb) - spsr |= COMPAT_PSR_T_BIT; + spsr |= PSR_AA32_T_BIT; else - spsr &= ~COMPAT_PSR_T_BIT; + spsr &= ~PSR_AA32_T_BIT; /* The IT state must be cleared for both ARM and Thumb-2 */ - spsr &= ~COMPAT_PSR_IT_MASK; + spsr &= ~PSR_AA32_IT_MASK; /* Restore the original endianness */ - spsr |= COMPAT_PSR_ENDSTATE; + spsr |= PSR_AA32_ENDSTATE; if (ka->sa.sa_flags & SA_RESTORER) { retcode = ptr_to_compat(ka->sa.sa_restorer); @@ -414,6 +419,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) { struct compat_aux_sigframe __user *aux; + unsigned long psr = pstate_to_compat_psr(regs->pstate); int err = 0; __put_user_error(regs->regs[0], &sf->uc.uc_mcontext.arm_r0, err); @@ -432,7 +438,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf, __put_user_error(regs->compat_sp, &sf->uc.uc_mcontext.arm_sp, err); __put_user_error(regs->compat_lr, &sf->uc.uc_mcontext.arm_lr, err); __put_user_error(regs->pc, &sf->uc.uc_mcontext.arm_pc, err); - __put_user_error(regs->pstate, &sf->uc.uc_mcontext.arm_cpsr, err); + __put_user_error(psr, &sf->uc.uc_mcontext.arm_cpsr, err); __put_user_error((compat_ulong_t)0, &sf->uc.uc_mcontext.trap_no, err); /* set the compat FSR WnR */ diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 2faa9863d2e5..25fcd22a4bb2 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -225,6 +225,7 @@ asmlinkage notrace void secondary_start_kernel(void) notify_cpu_starting(cpu); store_cpu_topology(cpu); + numa_add_cpu(cpu); /* * OK, now it's safe to let the boot CPU continue. Wait for @@ -278,6 +279,9 @@ int __cpu_disable(void) if (ret) return ret; + remove_cpu_topology(cpu); + numa_remove_cpu(cpu); + /* * Take this CPU offline. Once we clear this, we can't return, * and we must not schedule until we're ready to give up the cpu. @@ -518,7 +522,6 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) } bootcpu_valid = true; cpu_madt_gicc[0] = *processor; - early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid)); return; } @@ -541,8 +544,6 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) */ acpi_set_mailbox_entry(cpu_count, processor); - early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid)); - cpu_count++; } @@ -562,8 +563,34 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, return 0; } + +static void __init acpi_parse_and_init_cpus(void) +{ + int i; + + /* + * do a walk of MADT to determine how many CPUs + * we have including disabled CPUs, and get information + * we need for SMP init. + */ + acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, + acpi_parse_gic_cpu_interface, 0); + + /* + * In ACPI, SMP and CPU NUMA information is provided in separate + * static tables, namely the MADT and the SRAT. + * + * Thus, it is simpler to first create the cpu logical map through + * an MADT walk and then map the logical cpus to their node ids + * as separate steps. + */ + acpi_map_cpus_to_nodes(); + + for (i = 0; i < nr_cpu_ids; i++) + early_map_cpu_to_node(i, acpi_numa_get_nid(i)); +} #else -#define acpi_table_parse_madt(...) do { } while (0) +#define acpi_parse_and_init_cpus(...) do { } while (0) #endif /* @@ -636,13 +663,7 @@ void __init smp_init_cpus(void) if (acpi_disabled) of_parse_and_init_cpus(); else - /* - * do a walk of MADT to determine how many CPUs - * we have including disabled CPUs, and get information - * we need for SMP init - */ - acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, - acpi_parse_gic_cpu_interface, 0); + acpi_parse_and_init_cpus(); if (cpu_count > nr_cpu_ids) pr_warn("Number of cores (%d) exceeds configured maximum of %u - clipping\n", @@ -679,6 +700,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) this_cpu = smp_processor_id(); store_cpu_topology(this_cpu); numa_store_cpu_info(this_cpu); + numa_add_cpu(this_cpu); /* * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index d5718a060672..4989f7ea1e59 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -50,7 +50,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) if (!tsk) tsk = current; - if (!on_accessible_stack(tsk, fp)) + if (!on_accessible_stack(tsk, fp, NULL)) return -EINVAL; frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c index 72981bae10eb..b44065fb1616 100644 --- a/arch/arm64/kernel/sys.c +++ b/arch/arm64/kernel/sys.c @@ -25,11 +25,13 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/syscalls.h> + #include <asm/cpufeature.h> +#include <asm/syscall.h> -asmlinkage long sys_mmap(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, off_t off) +SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, off_t, off) { if (offset_in_page(off) != 0) return -EINVAL; @@ -42,24 +44,25 @@ SYSCALL_DEFINE1(arm64_personality, unsigned int, personality) if (personality(personality) == PER_LINUX32 && !system_supports_32bit_el0()) return -EINVAL; - return sys_personality(personality); + return ksys_personality(personality); } /* * Wrappers to pass the pt_regs argument. */ -asmlinkage long sys_rt_sigreturn_wrapper(void); -#define sys_rt_sigreturn sys_rt_sigreturn_wrapper #define sys_personality sys_arm64_personality +asmlinkage long sys_ni_syscall(const struct pt_regs *); +#define __arm64_sys_ni_syscall sys_ni_syscall + #undef __SYSCALL -#define __SYSCALL(nr, sym) [nr] = sym, +#define __SYSCALL(nr, sym) asmlinkage long __arm64_##sym(const struct pt_regs *); +#include <asm/unistd.h> -/* - * The sys_call_table array must be 4K aligned to be accessible from - * kernel/entry.S. - */ -void * const sys_call_table[__NR_syscalls] __aligned(4096) = { - [0 ... __NR_syscalls - 1] = sys_ni_syscall, +#undef __SYSCALL +#define __SYSCALL(nr, sym) [nr] = (syscall_fn_t)__arm64_##sym, + +const syscall_fn_t sys_call_table[__NR_syscalls] = { + [0 ... __NR_syscalls - 1] = (syscall_fn_t)sys_ni_syscall, #include <asm/unistd.h> }; diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c index a40b1343b819..0f8bcb7de700 100644 --- a/arch/arm64/kernel/sys32.c +++ b/arch/arm64/kernel/sys32.c @@ -22,31 +22,128 @@ */ #define __COMPAT_SYSCALL_NR +#include <linux/compat.h> #include <linux/compiler.h> #include <linux/syscalls.h> -asmlinkage long compat_sys_sigreturn_wrapper(void); -asmlinkage long compat_sys_rt_sigreturn_wrapper(void); -asmlinkage long compat_sys_statfs64_wrapper(void); -asmlinkage long compat_sys_fstatfs64_wrapper(void); -asmlinkage long compat_sys_pread64_wrapper(void); -asmlinkage long compat_sys_pwrite64_wrapper(void); -asmlinkage long compat_sys_truncate64_wrapper(void); -asmlinkage long compat_sys_ftruncate64_wrapper(void); -asmlinkage long compat_sys_readahead_wrapper(void); -asmlinkage long compat_sys_fadvise64_64_wrapper(void); -asmlinkage long compat_sys_sync_file_range2_wrapper(void); -asmlinkage long compat_sys_fallocate_wrapper(void); -asmlinkage long compat_sys_mmap2_wrapper(void); +#include <asm/syscall.h> -#undef __SYSCALL -#define __SYSCALL(nr, sym) [nr] = sym, +asmlinkage long compat_sys_sigreturn(void); +asmlinkage long compat_sys_rt_sigreturn(void); + +COMPAT_SYSCALL_DEFINE3(aarch32_statfs64, const char __user *, pathname, + compat_size_t, sz, struct compat_statfs64 __user *, buf) +{ + /* + * 32-bit ARM applies an OABI compatibility fixup to statfs64 and + * fstatfs64 regardless of whether OABI is in use, and therefore + * arbitrary binaries may rely upon it, so we must do the same. + * For more details, see commit: + * + * 713c481519f19df9 ("[ARM] 3108/2: old ABI compat: statfs64 and + * fstatfs64") + */ + if (sz == 88) + sz = 84; + + return kcompat_sys_statfs64(pathname, sz, buf); +} + +COMPAT_SYSCALL_DEFINE3(aarch32_fstatfs64, unsigned int, fd, compat_size_t, sz, + struct compat_statfs64 __user *, buf) +{ + /* see aarch32_statfs64 */ + if (sz == 88) + sz = 84; + + return kcompat_sys_fstatfs64(fd, sz, buf); +} /* - * The sys_call_table array must be 4K aligned to be accessible from - * kernel/entry.S. + * Note: off_4k is always in units of 4K. If we can't do the + * requested offset because it is not page-aligned, we return -EINVAL. */ -void * const compat_sys_call_table[__NR_compat_syscalls] __aligned(4096) = { - [0 ... __NR_compat_syscalls - 1] = sys_ni_syscall, +COMPAT_SYSCALL_DEFINE6(aarch32_mmap2, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, off_4k) +{ + if (off_4k & (~PAGE_MASK >> 12)) + return -EINVAL; + + off_4k >>= (PAGE_SHIFT - 12); + + return ksys_mmap_pgoff(addr, len, prot, flags, fd, off_4k); +} + +#ifdef CONFIG_CPU_BIG_ENDIAN +#define arg_u32p(name) u32, name##_hi, u32, name##_lo +#else +#define arg_u32p(name) u32, name##_lo, u32, name##_hi +#endif + +#define arg_u64(name) (((u64)name##_hi << 32) | name##_lo) + +COMPAT_SYSCALL_DEFINE6(aarch32_pread64, unsigned int, fd, char __user *, buf, + size_t, count, u32, __pad, arg_u32p(pos)) +{ + return ksys_pread64(fd, buf, count, arg_u64(pos)); +} + +COMPAT_SYSCALL_DEFINE6(aarch32_pwrite64, unsigned int, fd, + const char __user *, buf, size_t, count, u32, __pad, + arg_u32p(pos)) +{ + return ksys_pwrite64(fd, buf, count, arg_u64(pos)); +} + +COMPAT_SYSCALL_DEFINE4(aarch32_truncate64, const char __user *, pathname, + u32, __pad, arg_u32p(length)) +{ + return ksys_truncate(pathname, arg_u64(length)); +} + +COMPAT_SYSCALL_DEFINE4(aarch32_ftruncate64, unsigned int, fd, u32, __pad, + arg_u32p(length)) +{ + return ksys_ftruncate(fd, arg_u64(length)); +} + +COMPAT_SYSCALL_DEFINE5(aarch32_readahead, int, fd, u32, __pad, + arg_u32p(offset), size_t, count) +{ + return ksys_readahead(fd, arg_u64(offset), count); +} + +COMPAT_SYSCALL_DEFINE6(aarch32_fadvise64_64, int, fd, int, advice, + arg_u32p(offset), arg_u32p(len)) +{ + return ksys_fadvise64_64(fd, arg_u64(offset), arg_u64(len), advice); +} + +COMPAT_SYSCALL_DEFINE6(aarch32_sync_file_range2, int, fd, unsigned int, flags, + arg_u32p(offset), arg_u32p(nbytes)) +{ + return ksys_sync_file_range(fd, arg_u64(offset), arg_u64(nbytes), + flags); +} + +COMPAT_SYSCALL_DEFINE6(aarch32_fallocate, int, fd, int, mode, + arg_u32p(offset), arg_u32p(len)) +{ + return ksys_fallocate(fd, mode, arg_u64(offset), arg_u64(len)); +} + +asmlinkage long sys_ni_syscall(const struct pt_regs *); +#define __arm64_sys_ni_syscall sys_ni_syscall + +#undef __SYSCALL +#define __SYSCALL(nr, sym) asmlinkage long __arm64_##sym(const struct pt_regs *); +#include <asm/unistd32.h> + +#undef __SYSCALL +#define __SYSCALL(nr, sym) [nr] = (syscall_fn_t)__arm64_##sym, + +const syscall_fn_t compat_sys_call_table[__NR_compat_syscalls] = { + [0 ... __NR_compat_syscalls - 1] = (syscall_fn_t)sys_ni_syscall, #include <asm/unistd32.h> }; diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c new file mode 100644 index 000000000000..032d22312881 --- /dev/null +++ b/arch/arm64/kernel/syscall.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/compiler.h> +#include <linux/context_tracking.h> +#include <linux/errno.h> +#include <linux/nospec.h> +#include <linux/ptrace.h> +#include <linux/syscalls.h> + +#include <asm/daifflags.h> +#include <asm/fpsimd.h> +#include <asm/syscall.h> +#include <asm/thread_info.h> +#include <asm/unistd.h> + +long compat_arm_syscall(struct pt_regs *regs); + +long sys_ni_syscall(void); + +asmlinkage long do_ni_syscall(struct pt_regs *regs) +{ +#ifdef CONFIG_COMPAT + long ret; + if (is_compat_task()) { + ret = compat_arm_syscall(regs); + if (ret != -ENOSYS) + return ret; + } +#endif + + return sys_ni_syscall(); +} + +static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn) +{ + return syscall_fn(regs); +} + +static void invoke_syscall(struct pt_regs *regs, unsigned int scno, + unsigned int sc_nr, + const syscall_fn_t syscall_table[]) +{ + long ret; + + if (scno < sc_nr) { + syscall_fn_t syscall_fn; + syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)]; + ret = __invoke_syscall(regs, syscall_fn); + } else { + ret = do_ni_syscall(regs); + } + + regs->regs[0] = ret; +} + +static inline bool has_syscall_work(unsigned long flags) +{ + return unlikely(flags & _TIF_SYSCALL_WORK); +} + +int syscall_trace_enter(struct pt_regs *regs); +void syscall_trace_exit(struct pt_regs *regs); + +static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, + const syscall_fn_t syscall_table[]) +{ + unsigned long flags = current_thread_info()->flags; + + regs->orig_x0 = regs->regs[0]; + regs->syscallno = scno; + + local_daif_restore(DAIF_PROCCTX); + user_exit(); + + if (has_syscall_work(flags)) { + /* set default errno for user-issued syscall(-1) */ + if (scno == NO_SYSCALL) + regs->regs[0] = -ENOSYS; + scno = syscall_trace_enter(regs); + if (scno == NO_SYSCALL) + goto trace_exit; + } + + invoke_syscall(regs, scno, sc_nr, syscall_table); + + /* + * The tracing status may have changed under our feet, so we have to + * check again. However, if we were tracing entry, then we always trace + * exit regardless, as the old entry assembly did. + */ + if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { + local_daif_mask(); + flags = current_thread_info()->flags; + if (!has_syscall_work(flags)) { + /* + * We're off to userspace, where interrupts are + * always enabled after we restore the flags from + * the SPSR. + */ + trace_hardirqs_on(); + return; + } + local_daif_restore(DAIF_PROCCTX); + } + +trace_exit: + syscall_trace_exit(regs); +} + +static inline void sve_user_discard(void) +{ + if (!system_supports_sve()) + return; + + clear_thread_flag(TIF_SVE); + + /* + * task_fpsimd_load() won't be called to update CPACR_EL1 in + * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only + * happens if a context switch or kernel_neon_begin() or context + * modification (sigreturn, ptrace) intervenes. + * So, ensure that CPACR_EL1 is already correct for the fast-path case. + */ + sve_user_disable(); +} + +asmlinkage void el0_svc_handler(struct pt_regs *regs) +{ + sve_user_discard(); + el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); +} + +#ifdef CONFIG_COMPAT +asmlinkage void el0_svc_compat_handler(struct pt_regs *regs) +{ + el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls, + compat_sys_call_table); +} +#endif diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index f845a8617812..0825c4a856e3 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -215,11 +215,16 @@ EXPORT_SYMBOL_GPL(cpu_topology); const struct cpumask *cpu_coregroup_mask(int cpu) { - const cpumask_t *core_mask = &cpu_topology[cpu].core_sibling; + const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); + /* Find the smaller of NUMA, core or LLC siblings */ + if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { + /* not numa in package, lets use the package siblings */ + core_mask = &cpu_topology[cpu].core_sibling; + } if (cpu_topology[cpu].llc_id != -1) { - if (cpumask_subset(&cpu_topology[cpu].llc_siblings, core_mask)) - core_mask = &cpu_topology[cpu].llc_siblings; + if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask)) + core_mask = &cpu_topology[cpu].llc_sibling; } return core_mask; @@ -231,27 +236,25 @@ static void update_siblings_masks(unsigned int cpuid) int cpu; /* update core and thread sibling masks */ - for_each_possible_cpu(cpu) { + for_each_online_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; if (cpuid_topo->llc_id == cpu_topo->llc_id) { - cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings); - cpumask_set_cpu(cpuid, &cpu_topo->llc_siblings); + cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); + cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); } if (cpuid_topo->package_id != cpu_topo->package_id) continue; cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); + cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); if (cpuid_topo->core_id != cpu_topo->core_id) continue; cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); + cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); } } @@ -293,6 +296,19 @@ topology_populated: update_siblings_masks(cpuid); } +static void clear_cpu_topology(int cpu) +{ + struct cpu_topology *cpu_topo = &cpu_topology[cpu]; + + cpumask_clear(&cpu_topo->llc_sibling); + cpumask_set_cpu(cpu, &cpu_topo->llc_sibling); + + cpumask_clear(&cpu_topo->core_sibling); + cpumask_set_cpu(cpu, &cpu_topo->core_sibling); + cpumask_clear(&cpu_topo->thread_sibling); + cpumask_set_cpu(cpu, &cpu_topo->thread_sibling); +} + static void __init reset_cpu_topology(void) { unsigned int cpu; @@ -303,18 +319,26 @@ static void __init reset_cpu_topology(void) cpu_topo->thread_id = -1; cpu_topo->core_id = 0; cpu_topo->package_id = -1; - cpu_topo->llc_id = -1; - cpumask_clear(&cpu_topo->llc_siblings); - cpumask_set_cpu(cpu, &cpu_topo->llc_siblings); - cpumask_clear(&cpu_topo->core_sibling); - cpumask_set_cpu(cpu, &cpu_topo->core_sibling); - cpumask_clear(&cpu_topo->thread_sibling); - cpumask_set_cpu(cpu, &cpu_topo->thread_sibling); + clear_cpu_topology(cpu); } } +void remove_cpu_topology(unsigned int cpu) +{ + int sibling; + + for_each_cpu(sibling, topology_core_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); + for_each_cpu(sibling, topology_llc_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling)); + + clear_cpu_topology(cpu); +} + #ifdef CONFIG_ACPI /* * Propagate the topology information of the processor_topology_node tree to the diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index d399d459397b..039e9ff379cc 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -411,7 +411,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) { - config_sctlr_el1(SCTLR_EL1_UCI, 0); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0); } #define __user_cache_maint(insn, address, res) \ @@ -547,22 +547,6 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) do_undefinstr(regs); } -long compat_arm_syscall(struct pt_regs *regs); - -asmlinkage long do_ni_syscall(struct pt_regs *regs) -{ -#ifdef CONFIG_COMPAT - long ret; - if (is_compat_task()) { - ret = compat_arm_syscall(regs); - if (ret != -ENOSYS) - return ret; - } -#endif - - return sys_ni_syscall(); -} - static const char *esr_class_str[] = { [0 ... ESR_ELx_EC_MAX] = "UNRECOGNIZED EC", [ESR_ELx_EC_UNKNOWN] = "Unknown/Uncategorized", diff --git a/arch/arm64/kernel/vdso/note.S b/arch/arm64/kernel/vdso/note.S index b82c85e5d972..e20483b104d9 100644 --- a/arch/arm64/kernel/vdso/note.S +++ b/arch/arm64/kernel/vdso/note.S @@ -22,7 +22,10 @@ #include <linux/uts.h> #include <linux/version.h> #include <linux/elfnote.h> +#include <linux/build-salt.h> ELFNOTE_START(Linux, 0, "a") .long LINUX_VERSION_CODE ELFNOTE_END + +BUILD_SALT diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 56a0260ceb11..cdd4d9d6d575 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -107,14 +107,14 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) { - u32 mode = (*(u32 *)valp) & COMPAT_PSR_MODE_MASK; + u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK; switch (mode) { - case COMPAT_PSR_MODE_USR: - case COMPAT_PSR_MODE_FIQ: - case COMPAT_PSR_MODE_IRQ: - case COMPAT_PSR_MODE_SVC: - case COMPAT_PSR_MODE_ABT: - case COMPAT_PSR_MODE_UND: + case PSR_AA32_MODE_USR: + case PSR_AA32_MODE_FIQ: + case PSR_AA32_MODE_IRQ: + case PSR_AA32_MODE_SVC: + case PSR_AA32_MODE_ABT: + case PSR_AA32_MODE_UND: case PSR_MODE_EL0t: case PSR_MODE_EL1t: case PSR_MODE_EL1h: diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index 4313f7475333..2fabc2dc1966 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -3,7 +3,8 @@ # Makefile for Kernel-based Virtual Machine module, HYP part # -ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING +ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \ + $(DISABLE_STACKLEAK_PLUGIN) KVM=../../../../virt/kvm diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index 39be799d0417..215c7c0eb3b0 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -27,7 +27,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) - return !!(read_sysreg_el2(spsr) & COMPAT_PSR_E_BIT); + return !!(read_sysreg_el2(spsr) & PSR_AA32_E_BIT); return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE); } diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c index eefe403a2e63..7a5173ea2276 100644 --- a/arch/arm64/kvm/regmap.c +++ b/arch/arm64/kvm/regmap.c @@ -112,22 +112,22 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = { unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num) { unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs; - unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK; + unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK; switch (mode) { - case COMPAT_PSR_MODE_USR ... COMPAT_PSR_MODE_SVC: + case PSR_AA32_MODE_USR ... PSR_AA32_MODE_SVC: mode &= ~PSR_MODE32_BIT; /* 0 ... 3 */ break; - case COMPAT_PSR_MODE_ABT: + case PSR_AA32_MODE_ABT: mode = 4; break; - case COMPAT_PSR_MODE_UND: + case PSR_AA32_MODE_UND: mode = 5; break; - case COMPAT_PSR_MODE_SYS: + case PSR_AA32_MODE_SYS: mode = 0; /* SYS maps to USR */ break; @@ -143,13 +143,13 @@ unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num) */ static int vcpu_spsr32_mode(const struct kvm_vcpu *vcpu) { - unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK; + unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK; switch (mode) { - case COMPAT_PSR_MODE_SVC: return KVM_SPSR_SVC; - case COMPAT_PSR_MODE_ABT: return KVM_SPSR_ABT; - case COMPAT_PSR_MODE_UND: return KVM_SPSR_UND; - case COMPAT_PSR_MODE_IRQ: return KVM_SPSR_IRQ; - case COMPAT_PSR_MODE_FIQ: return KVM_SPSR_FIQ; + case PSR_AA32_MODE_SVC: return KVM_SPSR_SVC; + case PSR_AA32_MODE_ABT: return KVM_SPSR_ABT; + case PSR_AA32_MODE_UND: return KVM_SPSR_UND; + case PSR_AA32_MODE_IRQ: return KVM_SPSR_IRQ; + case PSR_AA32_MODE_FIQ: return KVM_SPSR_FIQ; default: BUG(); } } diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index a74311beda35..4e4aedaf7ab7 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -42,8 +42,8 @@ static const struct kvm_regs default_regs_reset = { }; static const struct kvm_regs default_regs_reset32 = { - .regs.pstate = (COMPAT_PSR_MODE_SVC | COMPAT_PSR_A_BIT | - COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT), + .regs.pstate = (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | + PSR_AA32_I_BIT | PSR_AA32_F_BIT), }; static bool cpu_has_32bit_el1(void) diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 137710f4dac3..68755fd70dcf 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -lib-y := bitops.o clear_user.o delay.o copy_from_user.o \ +lib-y := clear_user.o delay.o copy_from_user.o \ copy_to_user.o copy_in_user.o copy_page.o \ clear_page.o memchr.o memcpy.o memmove.o memset.o \ memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S deleted file mode 100644 index 43ac736baa5b..000000000000 --- a/arch/arm64/lib/bitops.S +++ /dev/null @@ -1,76 +0,0 @@ -/* - * Based on arch/arm/lib/bitops.h - * - * Copyright (C) 2013 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/lse.h> - -/* - * x0: bits 5:0 bit offset - * bits 31:6 word offset - * x1: address - */ - .macro bitop, name, llsc, lse -ENTRY( \name ) - and w3, w0, #63 // Get bit offset - eor w0, w0, w3 // Clear low bits - mov x2, #1 - add x1, x1, x0, lsr #3 // Get word offset -alt_lse " prfm pstl1strm, [x1]", "nop" - lsl x3, x2, x3 // Create mask - -alt_lse "1: ldxr x2, [x1]", "\lse x3, [x1]" -alt_lse " \llsc x2, x2, x3", "nop" -alt_lse " stxr w0, x2, [x1]", "nop" -alt_lse " cbnz w0, 1b", "nop" - - ret -ENDPROC(\name ) - .endm - - .macro testop, name, llsc, lse -ENTRY( \name ) - and w3, w0, #63 // Get bit offset - eor w0, w0, w3 // Clear low bits - mov x2, #1 - add x1, x1, x0, lsr #3 // Get word offset -alt_lse " prfm pstl1strm, [x1]", "nop" - lsl x4, x2, x3 // Create mask - -alt_lse "1: ldxr x2, [x1]", "\lse x4, x2, [x1]" - lsr x0, x2, x3 -alt_lse " \llsc x2, x2, x4", "nop" -alt_lse " stlxr w5, x2, [x1]", "nop" -alt_lse " cbnz w5, 1b", "nop" -alt_lse " dmb ish", "nop" - - and x0, x0, #1 - ret -ENDPROC(\name ) - .endm - -/* - * Atomic bit operations. - */ - bitop change_bit, eor, steor - bitop clear_bit, bic, stclr - bitop set_bit, orr, stset - - testop test_and_change_bit, eor, ldeoral - testop test_and_clear_bit, bic, ldclral - testop test_and_set_bit, orr, ldsetal diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 30334d81b021..0c22ede52f90 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -35,7 +35,7 @@ * - start - virtual start address of region * - end - virtual end address of region */ -ENTRY(flush_icache_range) +ENTRY(__flush_icache_range) /* FALLTHROUGH */ /* @@ -77,7 +77,7 @@ alternative_else_nop_endif 9: mov x0, #-EFAULT b 1b -ENDPROC(flush_icache_range) +ENDPROC(__flush_icache_range) ENDPROC(__flush_cache_user_range) /* diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 61e93f0b5482..072c51fb07d7 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -355,7 +355,7 @@ static int __init atomic_pool_init(void) if (dev_get_cma_area(NULL)) page = dma_alloc_from_contiguous(NULL, nr_pages, - pool_size_order, GFP_KERNEL); + pool_size_order, false); else page = alloc_pages(GFP_DMA32, pool_size_order); @@ -573,7 +573,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, struct page *page; page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, - get_order(size), gfp); + get_order(size), gfp & __GFP_NOWARN); if (!page) return NULL; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index b8eecc7b9531..50b30ff30de4 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -379,12 +379,12 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re #define VM_FAULT_BADMAP 0x010000 #define VM_FAULT_BADACCESS 0x020000 -static int __do_page_fault(struct mm_struct *mm, unsigned long addr, +static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, struct task_struct *tsk) { struct vm_area_struct *vma; - int fault; + vm_fault_t fault; vma = find_vma(mm, addr); fault = VM_FAULT_BADMAP; @@ -427,7 +427,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, struct task_struct *tsk; struct mm_struct *mm; struct siginfo si; - int fault, major = 0; + vm_fault_t fault, major = 0; unsigned long vm_flags = VM_READ | VM_WRITE; unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; @@ -727,12 +727,7 @@ static const struct fault_info fault_info[] = { int handle_guest_sea(phys_addr_t addr, unsigned int esr) { - int ret = -ENOENT; - - if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) - ret = ghes_notify_sea(); - - return ret; + return ghes_notify_sea(); } asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, @@ -879,7 +874,7 @@ void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused) */ WARN_ON_ONCE(in_interrupt()); - config_sctlr_el1(SCTLR_EL1_SPAN, 0); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0); asm(SET_PSTATE_PAN(1)); } #endif /* CONFIG_ARM64_PAN */ diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 1059884f9a6f..30695a868107 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -66,6 +66,7 @@ void __sync_icache_dcache(pte_t pte) sync_icache_aliases(page_address(page), PAGE_SIZE << compound_order(page)); } +EXPORT_SYMBOL_GPL(__sync_icache_dcache); /* * This function is called when a page has been modified by the kernel. Mark @@ -82,7 +83,7 @@ EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ -EXPORT_SYMBOL(flush_icache_range); +EXPORT_SYMBOL(__flush_icache_range); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index ecc6818191df..192b3ba07075 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -108,7 +108,6 @@ static pte_t get_clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; pte_t orig_pte = huge_ptep_get(ptep); bool valid = pte_valid(orig_pte); unsigned long i, saddr = addr; @@ -125,8 +124,10 @@ static pte_t get_clear_flush(struct mm_struct *mm, orig_pte = pte_mkdirty(orig_pte); } - if (valid) + if (valid) { + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, saddr, addr); + } return orig_pte; } @@ -145,7 +146,7 @@ static void clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 325cfb3b858a..787e27964ab9 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -287,7 +287,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { - return memblock_is_map_memory(pfn << PAGE_SHIFT); + phys_addr_t addr = pfn << PAGE_SHIFT; + + if ((addr >> PAGE_SHIFT) != pfn) + return 0; + return memblock_is_map_memory(addr); } EXPORT_SYMBOL(pfn_valid); #endif @@ -611,11 +615,13 @@ void __init mem_init(void) BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Make sure we chose the upper bound of sizeof(struct page) - * correctly. + * correctly when sizing the VMEMMAP array. */ BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); +#endif if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 493ff75670ff..65f86271f02b 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -45,6 +45,7 @@ #include <asm/memblock.h> #include <asm/mmu_context.h> #include <asm/ptdump.h> +#include <asm/tlbflush.h> #define NO_BLOCK_MAPPINGS BIT(0) #define NO_CONT_MAPPINGS BIT(1) @@ -977,12 +978,51 @@ int pmd_clear_huge(pmd_t *pmdp) return 1; } -int pud_free_pmd_page(pud_t *pud) +int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) { - return pud_none(*pud); + pte_t *table; + pmd_t pmd; + + pmd = READ_ONCE(*pmdp); + + /* No-op for empty entry and WARN_ON for valid entry */ + if (!pmd_present(pmd) || !pmd_table(pmd)) { + VM_WARN_ON(!pmd_table(pmd)); + return 1; + } + + table = pte_offset_kernel(pmdp, addr); + pmd_clear(pmdp); + __flush_tlb_kernel_pgtable(addr); + pte_free_kernel(NULL, table); + return 1; } -int pmd_free_pte_page(pmd_t *pmd) +int pud_free_pmd_page(pud_t *pudp, unsigned long addr) { - return pmd_none(*pmd); + pmd_t *table; + pmd_t *pmdp; + pud_t pud; + unsigned long next, end; + + pud = READ_ONCE(*pudp); + + /* No-op for empty entry and WARN_ON for valid entry */ + if (!pud_present(pud) || !pud_table(pud)) { + VM_WARN_ON(!pud_table(pud)); + return 1; + } + + table = pmd_offset(pudp, addr); + pmdp = table; + next = addr; + end = addr + PUD_SIZE; + do { + pmd_free_pte_page(pmdp, next); + } while (pmdp++, next += PMD_SIZE, next != end); + + pud_clear(pudp); + __flush_tlb_kernel_pgtable(addr); + pmd_free(NULL, table); + return 1; } diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index dad128ba98bf..146c04ceaa51 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -70,19 +70,32 @@ EXPORT_SYMBOL(cpumask_of_node); #endif -static void map_cpu_to_node(unsigned int cpu, int nid) +static void numa_update_cpu(unsigned int cpu, bool remove) { - set_cpu_numa_node(cpu, nid); - if (nid >= 0) + int nid = cpu_to_node(cpu); + + if (nid == NUMA_NO_NODE) + return; + + if (remove) + cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]); + else cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); } -void numa_clear_node(unsigned int cpu) +void numa_add_cpu(unsigned int cpu) { - int nid = cpu_to_node(cpu); + numa_update_cpu(cpu, false); +} - if (nid >= 0) - cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]); +void numa_remove_cpu(unsigned int cpu) +{ + numa_update_cpu(cpu, true); +} + +void numa_clear_node(unsigned int cpu) +{ + numa_remove_cpu(cpu); set_cpu_numa_node(cpu, NUMA_NO_NODE); } @@ -116,7 +129,7 @@ static void __init setup_node_to_cpumask_map(void) */ void numa_store_cpu_info(unsigned int cpu) { - map_cpu_to_node(cpu, cpu_to_node_map[cpu]); + set_cpu_numa_node(cpu, cpu_to_node_map[cpu]); } void __init early_map_cpu_to_node(unsigned int cpu, int nid) diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c index 02b18f8b2905..24d786fc3a4c 100644 --- a/arch/arm64/mm/ptdump_debugfs.c +++ b/arch/arm64/mm/ptdump_debugfs.c @@ -10,18 +10,7 @@ static int ptdump_show(struct seq_file *m, void *v) ptdump_walk_pgd(m, info); return 0; } - -static int ptdump_open(struct inode *inode, struct file *file) -{ - return single_open(file, ptdump_show, inode->i_private); -} - -static const struct file_operations ptdump_fops = { - .open = ptdump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(ptdump); int ptdump_debugfs_register(struct ptdump_info *info, const char *name) { diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig index bf59855628ac..a641b0bf1611 100644 --- a/arch/c6x/Kconfig +++ b/arch/c6x/Kconfig @@ -53,12 +53,8 @@ config C6X_BIG_KERNEL If unsure, say N. -source "init/Kconfig" - # Use the generic interrupt handling code in kernel/irq/ -source "kernel/Kconfig.freezer" - config CMDLINE_BOOL bool "Default bootloader kernel arguments" @@ -114,43 +110,6 @@ config KERNEL_RAM_BASE_ADDRESS default 0xe0000000 if SOC_TMS320C6472 default 0x80000000 -source "mm/Kconfig" - -source "kernel/Kconfig.preempt" - source "kernel/Kconfig.hz" endmenu - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - -menu "Kernel hacking" - -source "lib/Kconfig.debug" - -config ACCESS_CHECK - bool "Check the user pointer address" - default y - help - Usually the pointer transfer from user space is checked to see if its - address is in the kernel space. - - Say N here to disable that check to improve the performance. - -endmenu diff --git a/arch/c6x/Kconfig.debug b/arch/c6x/Kconfig.debug new file mode 100644 index 000000000000..c299e0d8eca3 --- /dev/null +++ b/arch/c6x/Kconfig.debug @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 + +config ACCESS_CHECK + bool "Check the user pointer address" + default y + help + Usually the pointer transfer from user space is checked to see if its + address is in the kernel space. + + Say N here to disable that check to improve the performance. diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 091d6d04b5e5..5e89d40be8cd 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -48,40 +48,4 @@ config NR_CPUS int default 1 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - source "arch/h8300/Kconfig.cpu" - -menu "Kernel Features" - -source "kernel/Kconfig.preempt" - -source "mm/Kconfig" - -endmenu - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -menu "Kernel hacking" - -source "lib/Kconfig.debug" - -endmenu - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/h8300/Kconfig.debug b/arch/h8300/Kconfig.debug new file mode 100644 index 000000000000..22a162cd99e8 --- /dev/null +++ b/arch/h8300/Kconfig.debug @@ -0,0 +1 @@ +# dummy file, do not delete diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index 941e7554e886..c6b6a06231b2 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -2,8 +2,10 @@ #ifndef __ARCH_H8300_ATOMIC__ #define __ARCH_H8300_ATOMIC__ +#include <linux/compiler.h> #include <linux/types.h> #include <asm/cmpxchg.h> +#include <asm/irqflags.h> /* * Atomic operations that C can't guarantee us. Useful for @@ -15,8 +17,6 @@ #define atomic_read(v) READ_ONCE((v)->counter) #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#include <linux/kernel.h> - #define ATOMIC_OP_RETURN(op, c_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ @@ -69,18 +69,6 @@ ATOMIC_OPS(sub, -=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - -#define atomic_inc_return(v) atomic_add_return(1, v) -#define atomic_dec_return(v) atomic_sub_return(1, v) - -#define atomic_inc(v) (void)atomic_inc_return(v) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec(v) (void)atomic_dec_return(v) -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) - static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -94,7 +82,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return ret; } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int ret; h8300flags flags; @@ -106,5 +94,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) arch_local_irq_restore(flags); return ret; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #endif /* __ARCH_H8300_ATOMIC __ */ diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 37adb2003033..89a4b22f34d9 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -4,6 +4,7 @@ comment "Linux Kernel Configuration for Hexagon" config HEXAGON def_bool y + select ARCH_NO_PREEMPT select HAVE_OPROFILE # Other pending projects/to-do items. # select HAVE_REGS_AND_STACK_ACCESS_API @@ -146,26 +147,6 @@ config PAGE_SIZE_256KB endchoice -source "mm/Kconfig" - source "kernel/Kconfig.hz" endmenu - -source "init/Kconfig" -source "kernel/Kconfig.freezer" -source "drivers/Kconfig" -source "fs/Kconfig" - -menu "Executable File Formats" -source "fs/Kconfig.binfmt" -endmenu - -source "net/Kconfig" -source "security/Kconfig" -source "crypto/Kconfig" -source "lib/Kconfig" - -menu "Kernel hacking" -source "lib/Kconfig.debug" -endmenu diff --git a/arch/hexagon/Kconfig.debug b/arch/hexagon/Kconfig.debug new file mode 100644 index 000000000000..22a162cd99e8 --- /dev/null +++ b/arch/hexagon/Kconfig.debug @@ -0,0 +1 @@ +# dummy file, do not delete diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index fb3dfb2a667e..311b9894ccc8 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -164,7 +164,7 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer to value * @a: amount to add * @u: unless value is equal to u @@ -173,7 +173,7 @@ ATOMIC_OPS(xor) * */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int __oldval; register int tmp; @@ -196,18 +196,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) ); return __oldval; } - -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) - -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) - -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0) -#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) - -#define atomic_inc_return(v) (atomic_add_return(1, v)) -#define atomic_dec_return(v) (atomic_sub_return(1, v)) +#define atomic_fetch_add_unless atomic_fetch_add_unless #endif diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 933bbcef5363..eb263e61daf4 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -52,7 +52,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) struct mm_struct *mm = current->mm; int si_signo; int si_code = SEGV_MAPERR; - int fault; + vm_fault_t fault; const struct exception_table_entry *fixup; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index ff861420b8f5..2bf4ef792f2c 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -4,10 +4,6 @@ config PGTABLE_LEVELS range 3 4 if !IA64_PAGE_SIZE_64KB default 3 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - menu "Processor type and features" config IA64 @@ -16,6 +12,7 @@ config IA64 select ARCH_MIGHT_HAVE_PC_SERIO select PCI if (!IA64_HP_SIM) select ACPI if (!IA64_HP_SIM) + select ARCH_SUPPORTS_ACPI if (!IA64_HP_SIM) select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select HAVE_UNSTABLE_SCHED_CLOCK @@ -368,10 +365,6 @@ config FORCE_CPEI_RETARGET This option it useful to enable this feature on older BIOS's as well. You can also enable this by using boot command line option force_cpei=1. -source "kernel/Kconfig.preempt" - -source "mm/Kconfig" - config ARCH_SELECT_MEMORY_MODEL def_bool y @@ -532,8 +525,6 @@ config CRASH_DUMP source "drivers/firmware/Kconfig" -source "fs/Kconfig.binfmt" - endmenu menu "Power management and ACPI options" @@ -574,10 +565,6 @@ endmenu endif -source "net/Kconfig" - -source "drivers/Kconfig" - source "arch/ia64/hp/sim/Kconfig" config MSPEC @@ -588,13 +575,3 @@ config MSPEC If you have an ia64 and you want to enable memory special operations support (formerly known as fetchop), say Y here, otherwise say N. - -source "fs/Kconfig" - -source "arch/ia64/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/ia64/Kconfig.debug b/arch/ia64/Kconfig.debug index 677c409425df..1371efc9b005 100644 --- a/arch/ia64/Kconfig.debug +++ b/arch/ia64/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" choice prompt "Physical memory granularity" @@ -56,5 +53,3 @@ config IA64_DEBUG_IRQ Selecting this option turns on bug checking for the IA-64 irq_save and restore instructions. It's useful for tracking down spinlock problems, but slow! If you're unsure, select N. - -endmenu diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 2524fb60fbc2..206530d0751b 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -215,91 +215,10 @@ ATOMIC64_FETCH_OP(xor, ^) (cmpxchg(&((v)->counter), old, new)) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - - -static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -static __inline__ long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - -/* - * Atomically add I to V and return TRUE if the resulting value is - * negative. - */ -static __inline__ int -atomic_add_negative (int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} - -static __inline__ long -atomic64_add_negative (__s64 i, atomic64_t *v) -{ - return atomic64_add_return(i, v) < 0; -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) -#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) -#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0) - #define atomic_add(i,v) (void)atomic_add_return((i), (v)) #define atomic_sub(i,v) (void)atomic_sub_return((i), (v)) -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) #define atomic64_add(i,v) (void)atomic64_add_return((i), (v)) #define atomic64_sub(i,v) (void)atomic64_sub_return((i), (v)) -#define atomic64_inc(v) atomic64_add(1, (v)) -#define atomic64_dec(v) atomic64_sub(1, (v)) #endif /* _ASM_IA64_ATOMIC_H */ diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h index fb0651961e2c..1e6fef69bb01 100644 --- a/arch/ia64/include/asm/io.h +++ b/arch/ia64/include/asm/io.h @@ -83,12 +83,14 @@ virt_to_phys (volatile void *address) { return (unsigned long) address - PAGE_OFFSET; } +#define virt_to_phys virt_to_phys static inline void* phys_to_virt (unsigned long address) { return (void *) (address + PAGE_OFFSET); } +#define phys_to_virt phys_to_virt #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern u64 kern_mem_attribute (unsigned long phys_addr, unsigned long size); @@ -433,9 +435,11 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo { return ioremap(phys_addr, size); } +#define ioremap ioremap +#define ioremap_nocache ioremap_nocache #define ioremap_cache ioremap_cache #define ioremap_uc ioremap_nocache - +#define iounmap iounmap /* * String version of IO memory access ops: @@ -444,6 +448,14 @@ extern void memcpy_fromio(void *dst, const volatile void __iomem *src, long n); extern void memcpy_toio(volatile void __iomem *dst, const void *src, long n); extern void memset_io(volatile void __iomem *s, int c, long n); +#define memcpy_fromio memcpy_fromio +#define memcpy_toio memcpy_toio +#define memset_io memset_io +#define xlate_dev_kmem_ptr xlate_dev_kmem_ptr +#define xlate_dev_mem_ptr xlate_dev_mem_ptr +#include <asm-generic/io.h> +#undef PCI_IOBASE + # endif /* __KERNEL__ */ #endif /* _ASM_IA64_IO_H */ diff --git a/arch/ia64/include/asm/kprobes.h b/arch/ia64/include/asm/kprobes.h index 0302b3664789..580356a2eea6 100644 --- a/arch/ia64/include/asm/kprobes.h +++ b/arch/ia64/include/asm/kprobes.h @@ -82,8 +82,6 @@ struct prev_kprobe { #define ARCH_PREV_KPROBE_SZ 2 struct kprobe_ctlblk { unsigned long kprobe_status; - struct pt_regs jprobe_saved_regs; - unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE]; unsigned long *bsp; unsigned long cfm; atomic_t prev_kprobe_index; diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 44f0ac0df308..516355a774bf 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -115,12 +115,11 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned flush_tlb_all(); } else { /* - * XXX fix me: flush_tlb_range() should take an mm pointer instead of a - * vma pointer. + * flush_tlb_range() takes a vma instead of a mm pointer because + * some architectures want the vm_flags for ITLB/DTLB flush. */ - struct vm_area_struct vma; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); - vma.vm_mm = tlb->mm; /* flush the address range from the tlb: */ flush_tlb_range(&vma, start, end); /* now flush the virt. page-table area mapping the address range: */ diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h index 5d742bcb0018..4ca110f0a94b 100644 --- a/arch/ia64/include/uapi/asm/break.h +++ b/arch/ia64/include/uapi/asm/break.h @@ -14,7 +14,6 @@ */ #define __IA64_BREAK_KDB 0x80100 #define __IA64_BREAK_KPROBE 0x81000 /* .. 0x81fff */ -#define __IA64_BREAK_JPROBE 0x82000 /* * OS-specific break numbers: diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 3efba40adc54..c872c4e6bafb 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -114,4 +114,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 498f3da3f225..d0c0ccdd656a 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -25,7 +25,7 @@ obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_PERFMON) += perfmon_default_smpl.o obj-$(CONFIG_IA64_CYCLONE) += cyclone.o obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o -obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o +obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S deleted file mode 100644 index f69389c7be1d..000000000000 --- a/arch/ia64/kernel/jprobes.S +++ /dev/null @@ -1,90 +0,0 @@ -/* - * Jprobe specific operations - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) Intel Corporation, 2005 - * - * 2005-May Rusty Lynch <rusty.lynch@intel.com> and Anil S Keshavamurthy - * <anil.s.keshavamurthy@intel.com> initial implementation - * - * Jprobes (a.k.a. "jump probes" which is built on-top of kprobes) allow a - * probe to be inserted into the beginning of a function call. The fundamental - * difference between a jprobe and a kprobe is the jprobe handler is executed - * in the same context as the target function, while the kprobe handlers - * are executed in interrupt context. - * - * For jprobes we initially gain control by placing a break point in the - * first instruction of the targeted function. When we catch that specific - * break, we: - * * set the return address to our jprobe_inst_return() function - * * jump to the jprobe handler function - * - * Since we fixed up the return address, the jprobe handler will return to our - * jprobe_inst_return() function, giving us control again. At this point we - * are back in the parents frame marker, so we do yet another call to our - * jprobe_break() function to fix up the frame marker as it would normally - * exist in the target function. - * - * Our jprobe_return function then transfers control back to kprobes.c by - * executing a break instruction using one of our reserved numbers. When we - * catch that break in kprobes.c, we continue like we do for a normal kprobe - * by single stepping the emulated instruction, and then returning execution - * to the correct location. - */ -#include <asm/asmmacro.h> -#include <asm/break.h> - - /* - * void jprobe_break(void) - */ - .section .kprobes.text, "ax" -ENTRY(jprobe_break) - break.m __IA64_BREAK_JPROBE -END(jprobe_break) - - /* - * void jprobe_inst_return(void) - */ -GLOBAL_ENTRY(jprobe_inst_return) - br.call.sptk.many b0=jprobe_break -END(jprobe_inst_return) - -GLOBAL_ENTRY(invalidate_stacked_regs) - movl r16=invalidate_restore_cfm - ;; - mov b6=r16 - ;; - br.ret.sptk.many b6 - ;; -invalidate_restore_cfm: - mov r16=ar.rsc - ;; - mov ar.rsc=r0 - ;; - loadrs - ;; - mov ar.rsc=r16 - ;; - br.cond.sptk.many rp -END(invalidate_stacked_regs) - -GLOBAL_ENTRY(flush_register_stack) - // flush dirty regs to backing store (must be first in insn group) - flushrs - ;; - br.ret.sptk.many rp -END(flush_register_stack) - diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index f5f3a5e6fcd1..aa41bd5cf9b7 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -35,8 +35,6 @@ #include <asm/sections.h> #include <asm/exception.h> -extern void jprobe_inst_return(void); - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -480,12 +478,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) */ break; } - kretprobe_assert(ri, orig_ret_address, trampoline_address); - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); @@ -819,14 +814,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) prepare_ss(p, regs); kcb->kprobe_status = KPROBE_REENTER; return 1; - } else if (args->err == __IA64_BREAK_JPROBE) { - /* - * jprobe instrumented function just completed - */ - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - goto ss_probe; - } } else if (!is_ia64_break_inst(regs)) { /* The breakpoint instruction was removed by * another cpu right after we hit, no further @@ -861,15 +848,12 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) set_current_kprobe(p, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) - /* - * Our pre-handler is specifically requesting that we just - * do a return. This is used for both the jprobe pre-handler - * and the kretprobe trampoline - */ + if (p->pre_handler && p->pre_handler(p, regs)) { + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: #if !defined(CONFIG_PREEMPT) if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ @@ -992,7 +976,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, case DIE_BREAK: /* err is break number from ia64_bad_break() */ if ((args->err >> 12) == (__IA64_BREAK_KPROBE >> 12) - || args->err == __IA64_BREAK_JPROBE || args->err == 0) if (pre_kprobes_handler(args)) ret = NOTIFY_STOP; @@ -1040,74 +1023,6 @@ unsigned long arch_deref_entry_point(void *entry) return ((struct fnptr *)entry)->ip; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr = arch_deref_entry_point(jp->entry); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - struct param_bsp_cfm pa; - int bytes; - - /* - * Callee owns the argument space and could overwrite it, eg - * tail call optimization. So to be absolutely safe - * we save the argument space before transferring the control - * to instrumented jprobe function which runs in - * the process context - */ - pa.ip = regs->cr_iip; - unw_init_running(ia64_get_bsp_cfm, &pa); - bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f) - - (char *)pa.bsp; - memcpy( kcb->jprobes_saved_stacked_regs, - pa.bsp, - bytes ); - kcb->bsp = pa.bsp; - kcb->cfm = pa.cfm; - - /* save architectural state */ - kcb->jprobe_saved_regs = *regs; - - /* after rfi, execute the jprobe instrumented function */ - regs->cr_iip = addr & ~0xFULL; - ia64_psr(regs)->ri = addr & 0xf; - regs->r1 = ((struct fnptr *)(jp->entry))->gp; - - /* - * fix the return address to our jprobe_inst_return() function - * in the jprobes.S file - */ - regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip; - - return 1; -} - -/* ia64 does not need this */ -void __kprobes jprobe_return(void) -{ -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - int bytes; - - /* restoring architectural state */ - *regs = kcb->jprobe_saved_regs; - - /* restoring the original argument space */ - flush_register_stack(); - bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f) - - (char *)kcb->bsp; - memcpy( kcb->bsp, - kcb->jprobes_saved_stacked_regs, - bytes ); - invalidate_stacked_regs(); - - preempt_enable_no_resched(); - return 1; -} - static struct kprobe trampoline_p = { .pre_handler = trampoline_probe_handler }; diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 817fa120645f..a9d55ad8d67b 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -86,7 +86,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re struct vm_area_struct *vma, *prev_vma; struct mm_struct *mm = current->mm; unsigned long mask; - int fault; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT) diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index bdb14a369137..3b85c3ecac38 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -116,6 +116,7 @@ ia64_init_addr_space (void) */ vma = vm_area_alloc(current->mm); if (vma) { + vma_set_anonymous(vma); vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; @@ -133,6 +134,7 @@ ia64_init_addr_space (void) if (!(current->personality & MMAP_PAGE_ZERO)) { vma = vm_area_alloc(current->mm); if (vma) { + vma_set_anonymous(vma); vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | @@ -273,7 +275,7 @@ static struct vm_area_struct gate_vma; static int __init gate_vma_init(void) { - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 785612b576f7..070553791e97 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -2,8 +2,10 @@ config M68K bool default y + select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA select ARCH_MIGHT_HAVE_PC_PARPORT if ISA select ARCH_NO_COHERENT_DMA_MMAP if !MMU + select ARCH_NO_PREEMPT if !COLDFIRE select HAVE_IDE select HAVE_AOUT if MMU select HAVE_DEBUG_BUGVERBOSE @@ -24,6 +26,10 @@ config M68K select MODULES_USE_ELF_RELA select OLD_SIGSUSPEND3 select OLD_SIGACTION + select DMA_NONCOHERENT_OPS if HAS_DMA + select HAVE_MEMBLOCK + select ARCH_DISCARD_MEMBLOCK + select NO_BOOTMEM config CPU_BIG_ENDIAN def_bool y @@ -75,10 +81,6 @@ config PGTABLE_LEVELS default 2 if SUN3 || COLDFIRE default 3 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - config MMU bool "MMU-based Paged Memory Management Support" default y @@ -133,18 +135,6 @@ endmenu menu "Kernel Features" -if COLDFIRE -source "kernel/Kconfig.preempt" -endif - -source "mm/Kconfig" - -endmenu - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - endmenu if !MMU @@ -158,18 +148,4 @@ config PM endmenu endif -source "net/Kconfig" - -source "drivers/Kconfig" - source "arch/m68k/Kconfig.devices" - -source "fs/Kconfig" - -source "arch/m68k/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/m68k/Kconfig.debug b/arch/m68k/Kconfig.debug index 04690b179a6e..f43643111eaf 100644 --- a/arch/m68k/Kconfig.debug +++ b/arch/m68k/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config BOOTPARAM bool 'Compiled-in Kernel Boot Parameter' @@ -51,5 +48,3 @@ config BDM_DISABLE Disable the ColdFire CPU's BDM signals. endif - -endmenu diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c index b2a6bc63f8cd..aef8d42e078d 100644 --- a/arch/m68k/apollo/config.c +++ b/arch/m68k/apollo/config.c @@ -31,7 +31,6 @@ extern void dn_sched_init(irq_handler_t handler); extern void dn_init_IRQ(void); extern u32 dn_gettimeoffset(void); extern int dn_dummy_hwclk(int, struct rtc_time *); -extern int dn_dummy_set_clock_mmss(unsigned long); extern void dn_dummy_reset(void); #ifdef CONFIG_HEARTBEAT static void dn_heartbeat(int on); @@ -156,7 +155,6 @@ void __init config_apollo(void) arch_gettimeoffset = dn_gettimeoffset; mach_max_dma_address = 0xffffffff; mach_hwclk = dn_dummy_hwclk; /* */ - mach_set_clock_mmss = dn_dummy_set_clock_mmss; /* */ mach_reset = dn_dummy_reset; /* */ #ifdef CONFIG_HEARTBEAT mach_heartbeat = dn_heartbeat; @@ -240,12 +238,6 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) { } -int dn_dummy_set_clock_mmss(unsigned long nowtime) -{ - pr_info("set_clock_mmss\n"); - return 0; -} - void dn_dummy_reset(void) { dn_serial_print("The end !\n"); diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c index 565c6f06ab0b..bd96702a1ad0 100644 --- a/arch/m68k/atari/config.c +++ b/arch/m68k/atari/config.c @@ -81,9 +81,6 @@ extern void atari_sched_init(irq_handler_t); extern u32 atari_gettimeoffset(void); extern int atari_mste_hwclk (int, struct rtc_time *); extern int atari_tt_hwclk (int, struct rtc_time *); -extern int atari_mste_set_clock_mmss (unsigned long); -extern int atari_tt_set_clock_mmss (unsigned long); - /* ++roman: This is a more elaborate test for an SCC chip, since the plain * Medusa board generates DTACK at the SCC's standard addresses, but a SCC @@ -362,13 +359,11 @@ void __init config_atari(void) ATARIHW_SET(TT_CLK); pr_cont(" TT_CLK"); mach_hwclk = atari_tt_hwclk; - mach_set_clock_mmss = atari_tt_set_clock_mmss; } if (hwreg_present(&mste_rtc.sec_ones)) { ATARIHW_SET(MSTE_CLK); pr_cont(" MSTE_CLK"); mach_hwclk = atari_mste_hwclk; - mach_set_clock_mmss = atari_mste_set_clock_mmss; } if (!MACH_IS_MEDUSA && hwreg_present(&dma_wd.fdc_speed) && hwreg_write(&dma_wd.fdc_speed, 0)) { diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c index c549b48174ec..9cca64286464 100644 --- a/arch/m68k/atari/time.c +++ b/arch/m68k/atari/time.c @@ -285,69 +285,6 @@ int atari_tt_hwclk( int op, struct rtc_time *t ) return( 0 ); } - -int atari_mste_set_clock_mmss (unsigned long nowtime) -{ - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - struct MSTE_RTC val; - unsigned char rtc_minutes; - - mste_read(&val); - rtc_minutes= val.min_ones + val.min_tens * 10; - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - val.sec_ones = real_seconds % 10; - val.sec_tens = real_seconds / 10; - val.min_ones = real_minutes % 10; - val.min_tens = real_minutes / 10; - mste_write(&val); - } - else - return -1; - return 0; -} - -int atari_tt_set_clock_mmss (unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - unsigned char save_control, save_freq_select, rtc_minutes; - - save_control = RTC_READ (RTC_CONTROL); /* tell the clock it's being set */ - RTC_WRITE (RTC_CONTROL, save_control | RTC_SET); - - save_freq_select = RTC_READ (RTC_FREQ_SELECT); /* stop and reset prescaler */ - RTC_WRITE (RTC_FREQ_SELECT, save_freq_select | RTC_DIV_RESET2); - - rtc_minutes = RTC_READ (RTC_MINUTES); - if (!(save_control & RTC_DM_BINARY)) - rtc_minutes = bcd2bin(rtc_minutes); - - /* Since we're only adjusting minutes and seconds, don't interfere - with hour overflow. This avoids messing with unknown time zones - but requires your RTC not to be off by more than 30 minutes. */ - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - if (!(save_control & RTC_DM_BINARY)) - { - real_seconds = bin2bcd(real_seconds); - real_minutes = bin2bcd(real_minutes); - } - RTC_WRITE (RTC_SECONDS, real_seconds); - RTC_WRITE (RTC_MINUTES, real_minutes); - } - else - retval = -1; - - RTC_WRITE (RTC_FREQ_SELECT, save_freq_select); - RTC_WRITE (RTC_CONTROL, save_control); - return retval; -} - /* * Local variables: * c-indent-level: 4 diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c index 2cfff4765040..143ee9fa3893 100644 --- a/arch/m68k/bvme6000/config.c +++ b/arch/m68k/bvme6000/config.c @@ -41,7 +41,6 @@ static void bvme6000_get_model(char *model); extern void bvme6000_sched_init(irq_handler_t handler); extern u32 bvme6000_gettimeoffset(void); extern int bvme6000_hwclk (int, struct rtc_time *); -extern int bvme6000_set_clock_mmss (unsigned long); extern void bvme6000_reset (void); void bvme6000_set_vectors (void); @@ -113,7 +112,6 @@ void __init config_bvme6000(void) mach_init_IRQ = bvme6000_init_IRQ; arch_gettimeoffset = bvme6000_gettimeoffset; mach_hwclk = bvme6000_hwclk; - mach_set_clock_mmss = bvme6000_set_clock_mmss; mach_reset = bvme6000_reset; mach_get_model = bvme6000_get_model; @@ -305,46 +303,3 @@ int bvme6000_hwclk(int op, struct rtc_time *t) return 0; } - -/* - * Set the minutes and seconds from seconds value 'nowtime'. Fail if - * clock is out by > 30 minutes. Logic lifted from atari code. - * Algorithm is to wait for the 10ms register to change, and then to - * wait a short while, and then set it. - */ - -int bvme6000_set_clock_mmss (unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - unsigned char rtc_minutes, rtc_tenms; - volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE; - unsigned char msr = rtc->msr & 0xc0; - unsigned long flags; - volatile int i; - - rtc->msr = 0; /* Ensure clock accessible */ - rtc_minutes = bcd2bin (rtc->bcd_min); - - if ((rtc_minutes < real_minutes - ? real_minutes - rtc_minutes - : rtc_minutes - real_minutes) < 30) - { - local_irq_save(flags); - rtc_tenms = rtc->bcd_tenms; - while (rtc_tenms == rtc->bcd_tenms) - ; - for (i = 0; i < 1000; i++) - ; - rtc->bcd_min = bin2bcd(real_minutes); - rtc->bcd_sec = bin2bcd(real_seconds); - local_irq_restore(flags); - } - else - retval = -1; - - rtc->msr = msr; - - return retval; -} - diff --git a/arch/m68k/coldfire/clk.c b/arch/m68k/coldfire/clk.c index 849cd208e2ed..7bc666e482eb 100644 --- a/arch/m68k/coldfire/clk.c +++ b/arch/m68k/coldfire/clk.c @@ -129,4 +129,33 @@ unsigned long clk_get_rate(struct clk *clk) } EXPORT_SYMBOL(clk_get_rate); +/* dummy functions, should not be called */ +long clk_round_rate(struct clk *clk, unsigned long rate) +{ + WARN_ON(clk); + return 0; +} +EXPORT_SYMBOL(clk_round_rate); + +int clk_set_rate(struct clk *clk, unsigned long rate) +{ + WARN_ON(clk); + return 0; +} +EXPORT_SYMBOL(clk_set_rate); + +int clk_set_parent(struct clk *clk, struct clk *parent) +{ + WARN_ON(clk); + return 0; +} +EXPORT_SYMBOL(clk_set_parent); + +struct clk *clk_get_parent(struct clk *clk) +{ + WARN_ON(clk); + return NULL; +} +EXPORT_SYMBOL(clk_get_parent); + /***************************************************************************/ diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index a874e54404d1..1d5483f6e457 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -52,6 +52,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -98,18 +99,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -122,6 +119,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -200,7 +198,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -231,7 +228,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -260,7 +256,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -356,6 +352,7 @@ CONFIG_A2091_SCSI=y CONFIG_GVP11_SCSI=y CONFIG_SCSI_A4000T=y CONFIG_SCSI_ZORRO7XX=y +CONFIG_SCSI_ZORRO_ESP=y CONFIG_MD=y CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m @@ -363,6 +360,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -402,8 +400,8 @@ CONFIG_A2065=y CONFIG_ARIADNE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CIRRUS is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -412,8 +410,10 @@ CONFIG_ARIADNE=y # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set +CONFIG_XSURF100=y CONFIG_HYDRA=y CONFIG_APNE=y CONFIG_ZORRO8390=y @@ -426,9 +426,9 @@ CONFIG_ZORRO8390=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -478,6 +478,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -499,7 +500,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -600,6 +601,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -622,6 +624,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -657,6 +664,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 8ce39e23aa42..52a0af127951 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -381,14 +378,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -400,9 +398,9 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -440,6 +438,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -458,7 +457,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -559,6 +558,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -581,6 +581,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -616,6 +621,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 346c4e75edf8..b3103e51268a 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -391,14 +388,15 @@ CONFIG_VETH=m CONFIG_ATARILANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set CONFIG_NE2000=y @@ -411,9 +409,9 @@ CONFIG_NE2000=y CONFIG_SMC91X=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -480,7 +478,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -581,6 +579,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -603,6 +602,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -638,6 +642,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index fca9c7aa71a3..fb7d651a4cab 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index f9eab174915c..6b37f5537c39 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -382,14 +379,15 @@ CONFIG_VETH=m CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -401,9 +399,9 @@ CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -443,6 +441,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -460,7 +459,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -561,6 +560,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -583,6 +583,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -618,6 +623,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index b52e597899eb..c717bf879449 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -49,6 +49,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -95,18 +96,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -119,6 +116,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -197,7 +195,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -228,7 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -257,7 +253,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -369,7 +366,7 @@ CONFIG_TCM_PSCSI=m CONFIG_ADB=y CONFIG_ADB_MACII=y CONFIG_ADB_IOP=y -CONFIG_ADB_PMU68K=y +CONFIG_ADB_PMU=y CONFIG_ADB_CUDA=y CONFIG_INPUT_ADBHID=y CONFIG_MAC_EMUMOUSEBTN=y @@ -398,8 +395,8 @@ CONFIG_VETH=m CONFIG_MACMACE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -407,6 +404,7 @@ CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set CONFIG_MACSONIC=y # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -420,9 +418,9 @@ CONFIG_MAC8390=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -465,6 +463,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -482,7 +481,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -583,6 +582,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -605,6 +605,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -640,6 +645,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 2a84eeec5b02..226c994ce794 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -59,6 +59,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -105,18 +106,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -129,6 +126,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -207,7 +205,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -238,7 +235,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -267,7 +263,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -311,6 +306,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -373,6 +369,7 @@ CONFIG_A2091_SCSI=y CONFIG_GVP11_SCSI=y CONFIG_SCSI_A4000T=y CONFIG_SCSI_ZORRO7XX=y +CONFIG_SCSI_ZORRO_ESP=y CONFIG_ATARI_SCSI=y CONFIG_MAC_SCSI=y CONFIG_SCSI_MAC_ESP=y @@ -387,6 +384,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -402,7 +400,7 @@ CONFIG_TCM_PSCSI=m CONFIG_ADB=y CONFIG_ADB_MACII=y CONFIG_ADB_IOP=y -CONFIG_ADB_PMU68K=y +CONFIG_ADB_PMU=y CONFIG_ADB_CUDA=y CONFIG_INPUT_ADBHID=y CONFIG_MAC_EMUMOUSEBTN=y @@ -438,8 +436,8 @@ CONFIG_SUN3LANCE=y CONFIG_MACMACE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -449,9 +447,11 @@ CONFIG_BVME6000_NET=y CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set CONFIG_MACSONIC=y # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set +CONFIG_XSURF100=y CONFIG_HYDRA=y CONFIG_MAC8390=y CONFIG_NE2000=y @@ -466,9 +466,9 @@ CONFIG_ZORRO8390=y CONFIG_SMC91X=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -533,6 +533,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -562,7 +563,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -663,6 +664,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -685,6 +687,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -720,6 +727,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 476e69994340..b383327fd77a 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -47,6 +47,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -93,18 +94,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -117,6 +114,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -195,7 +193,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -226,7 +223,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -255,7 +251,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -296,6 +291,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -343,6 +339,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 1477cda9146e..9783d3deb9e9 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -380,14 +377,15 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -399,9 +397,9 @@ CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -433,6 +431,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index b3a543dc48a0..a35d10ee10cb 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -350,6 +346,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -388,8 +385,8 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CIRRUS is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set @@ -398,6 +395,7 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set CONFIG_NE2000=y @@ -410,9 +408,9 @@ CONFIG_NE2000=y # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PLIP=m CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m @@ -455,6 +453,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -473,7 +472,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -574,6 +573,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -596,6 +596,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -631,6 +636,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index d543ed5dfa96..573bf922d448 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -385,6 +382,7 @@ CONFIG_SUN3LANCE=y CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -397,9 +395,9 @@ CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -435,6 +433,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -574,6 +574,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -609,6 +614,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index a67e54246023..efb27a7fcc55 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m CONFIG_TLS=m CONFIG_XFRM_MIGRATE=y CONFIG_NET_KEY=y +CONFIG_XDP_SOCKETS=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y @@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_TABLES=m +CONFIG_NF_TABLES_SET=m CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m -CONFIG_NFT_RT=m CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m CONFIG_NFT_FLOW_OFFLOAD=m -CONFIG_NFT_SET_RBTREE=m -CONFIG_NFT_SET_HASH=m -CONFIG_NFT_SET_BITMAP=m CONFIG_NFT_COUNTER=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_MASQ=m @@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NFT_SOCKET=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NFT_FIB_NETDEV=m @@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_SOCKET_IPV4=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NFT_DUP_IPV4=m CONFIG_NFT_FIB_IPV4=m @@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_SOCKET_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_MASQ_IPV6=m @@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=y -CONFIG_NFT_BRIDGE_META=m CONFIG_NFT_BRIDGE_REJECT=m CONFIG_NF_LOG_BRIDGE=m CONFIG_BRIDGE_NF_EBTABLES=m @@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m +# CONFIG_BATMAN_ADV_BATMAN_V is not set CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_NC=y CONFIG_BATMAN_ADV_MCAST=y @@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_ERA=m CONFIG_DM_MIRROR=m CONFIG_DM_RAID=m @@ -378,14 +375,15 @@ CONFIG_VETH=m CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NI is not set @@ -397,9 +395,9 @@ CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -# CONFIG_NET_VENDOR_SYNOPSYS is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -435,6 +433,7 @@ CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set # CONFIG_HID_ITE is not set +# CONFIG_HID_REDRAGON is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y # CONFIG_RTC_NVMEM is not set @@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m CONFIG_FANOTIFY=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_OVERLAY_FS=m @@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_OVERFLOW=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_HASH=m CONFIG_TEST_USER_COPY=m @@ -575,6 +575,11 @@ CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -610,6 +615,7 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_DRBG_HASH=y CONFIG_CRYPTO_DRBG_CTR=y diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 4d8d68c4e3dd..a4b8d3331a9e 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,6 +1,7 @@ generic-y += barrier.h generic-y += compat.h generic-y += device.h +generic-y += dma-mapping.h generic-y += emergency-restart.h generic-y += exec.h generic-y += extable.h diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index e993e2860ee1..47228b0d4163 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -126,11 +126,13 @@ static inline void atomic_inc(atomic_t *v) { __asm__ __volatile__("addql #1,%0" : "+m" (*v)); } +#define atomic_inc atomic_inc static inline void atomic_dec(atomic_t *v) { __asm__ __volatile__("subql #1,%0" : "+m" (*v)); } +#define atomic_dec atomic_dec static inline int atomic_dec_and_test(atomic_t *v) { @@ -138,6 +140,7 @@ static inline int atomic_dec_and_test(atomic_t *v) __asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v)); return c != 0; } +#define atomic_dec_and_test atomic_dec_and_test static inline int atomic_dec_and_test_lt(atomic_t *v) { @@ -155,6 +158,7 @@ static inline int atomic_inc_and_test(atomic_t *v) __asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v)); return c != 0; } +#define atomic_inc_and_test atomic_inc_and_test #ifdef CONFIG_RMW_INSNS @@ -190,9 +194,6 @@ static inline int atomic_xchg(atomic_t *v, int new) #endif /* !CONFIG_RMW_INSNS */ -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - static inline int atomic_sub_and_test(int i, atomic_t *v) { char c; @@ -201,6 +202,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v) : ASM_DI (i)); return c != 0; } +#define atomic_sub_and_test atomic_sub_and_test static inline int atomic_add_negative(int i, atomic_t *v) { @@ -210,20 +212,6 @@ static inline int atomic_add_negative(int i, atomic_t *v) : ASM_DI (i)); return c != 0; } - -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} +#define atomic_add_negative atomic_add_negative #endif /* __ARCH_M68K_ATOMIC __ */ diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index 93b47b1f6fb4..d979f38af751 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -454,7 +454,7 @@ static inline unsigned long ffz(unsigned long word) */ #if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \ !defined(CONFIG_M68000) && !defined(CONFIG_MCPU32) -static inline int __ffs(int x) +static inline unsigned long __ffs(unsigned long x) { __asm__ __volatile__ ("bitrev %0; ff1 %0" : "=d" (x) @@ -493,7 +493,11 @@ static inline int ffs(int x) : "dm" (x & -x)); return 32 - cnt; } -#define __ffs(x) (ffs(x) - 1) + +static inline unsigned long __ffs(unsigned long x) +{ + return ffs(x) - 1; +} /* * fls: find last bit set. @@ -515,12 +519,16 @@ static inline int __fls(int x) #endif +/* Simple test-and-set bit locks */ +#define test_and_set_bit_lock test_and_set_bit +#define clear_bit_unlock clear_bit +#define __clear_bit_unlock clear_bit_unlock + #include <asm-generic/bitops/ext2-atomic.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/fls64.h> #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/hweight.h> -#include <asm-generic/bitops/lock.h> #endif /* __KERNEL__ */ #endif /* _M68K_BITOPS_H */ diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h deleted file mode 100644 index e3722ed04fbb..000000000000 --- a/arch/m68k/include/asm/dma-mapping.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _M68K_DMA_MAPPING_H -#define _M68K_DMA_MAPPING_H - -extern const struct dma_map_ops m68k_dma_ops; - -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return &m68k_dma_ops; -} - -#endif /* _M68K_DMA_MAPPING_H */ diff --git a/arch/m68k/include/asm/dma.h b/arch/m68k/include/asm/dma.h index b0978a23bad1..ae2021964e32 100644 --- a/arch/m68k/include/asm/dma.h +++ b/arch/m68k/include/asm/dma.h @@ -390,7 +390,7 @@ static __inline__ void set_dma_mode(unsigned int dmanr, char mode) #ifdef DEBUG_DMA printk("%s(%d): dmanr=%d DMR[%x]=%x DIR[%x]=%x\n", __FILE__, __LINE__, - dmanr, (int) &dmalp[MCFDMA_DMR], dmabp[MCFDMA_DMR], + dmanr, (int) &dmalp[MCFDMA_DMR], dmalp[MCFDMA_DMR], (int) &dmawp[MCFDMA_DIR], dmawp[MCFDMA_DIR]); #endif } @@ -421,7 +421,7 @@ static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a) #ifdef DEBUG_DMA printk("%s(%d): dmanr=%d DMR[%x]=%x SAR[%x]=%08x DAR[%x]=%08x\n", - __FILE__, __LINE__, dmanr, (int) &dmawp[MCFDMA_DMR], dmawp[MCFDMA_DMR], + __FILE__, __LINE__, dmanr, (int) &dmalp[MCFDMA_DMR], dmalp[MCFDMA_DMR], (int) &dmalp[MCFDMA_DSAR], dmalp[MCFDMA_DSAR], (int) &dmalp[MCFDMA_DDAR], dmalp[MCFDMA_DDAR]); #endif diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h index ca2849afb087..aabe6420ead2 100644 --- a/arch/m68k/include/asm/io.h +++ b/arch/m68k/include/asm/io.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _M68K_IO_H +#define _M68K_IO_H + #if defined(__uClinux__) || defined(CONFIG_COLDFIRE) #include <asm/io_no.h> #else #include <asm/io_mm.h> #endif + +#include <asm-generic/io.h> + +#endif /* _M68K_IO_H */ diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h index fe485f4f5fac..782b78f8a048 100644 --- a/arch/m68k/include/asm/io_mm.h +++ b/arch/m68k/include/asm/io_mm.h @@ -16,13 +16,11 @@ * isa_readX(),isa_writeX() are for ISA memory */ -#ifndef _IO_H -#define _IO_H +#ifndef _M68K_IO_MM_H +#define _M68K_IO_MM_H #ifdef __KERNEL__ -#define ARCH_HAS_IOREMAP_WT - #include <linux/compiler.h> #include <asm/raw_io.h> #include <asm/virtconvert.h> @@ -369,40 +367,6 @@ static inline void isa_delay(void) #define writew(val, addr) out_le16((addr), (val)) #endif /* CONFIG_ATARI_ROM_ISA */ -#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA) -/* - * We need to define dummy functions for GENERIC_IOMAP support. - */ -#define inb(port) 0xff -#define inb_p(port) 0xff -#define outb(val,port) ((void)0) -#define outb_p(val,port) ((void)0) -#define inw(port) 0xffff -#define inw_p(port) 0xffff -#define outw(val,port) ((void)0) -#define outw_p(val,port) ((void)0) -#define inl(port) 0xffffffffUL -#define inl_p(port) 0xffffffffUL -#define outl(val,port) ((void)0) -#define outl_p(val,port) ((void)0) - -#define insb(port,buf,nr) ((void)0) -#define outsb(port,buf,nr) ((void)0) -#define insw(port,buf,nr) ((void)0) -#define outsw(port,buf,nr) ((void)0) -#define insl(port,buf,nr) ((void)0) -#define outsl(port,buf,nr) ((void)0) - -/* - * These should be valid on any ioremap()ed region - */ -#define readb(addr) in_8(addr) -#define writeb(val,addr) out_8((addr),(val)) -#define readw(addr) in_le16(addr) -#define writew(val,addr) out_le16((addr),(val)) - -#endif /* !CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */ - #define readl(addr) in_le32(addr) #define writel(val,addr) out_le32((addr),(val)) @@ -444,4 +408,4 @@ static inline void isa_delay(void) #define writew_relaxed(b, addr) writew(b, addr) #define writel_relaxed(b, addr) writel(b, addr) -#endif /* _IO_H */ +#endif /* _M68K_IO_MM_H */ diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h index 83a0a6d449f4..0498192e1d98 100644 --- a/arch/m68k/include/asm/io_no.h +++ b/arch/m68k/include/asm/io_no.h @@ -131,19 +131,7 @@ static inline void writel(u32 value, volatile void __iomem *addr) #define PCI_SPACE_LIMIT PCI_IO_MASK #endif /* CONFIG_PCI */ -/* - * These are defined in kmap.h as static inline functions. To maintain - * previous behavior we put these define guards here so io_mm.h doesn't - * see them. - */ -#ifdef CONFIG_MMU -#define memset_io memset_io -#define memcpy_fromio memcpy_fromio -#define memcpy_toio memcpy_toio -#endif - #include <asm/kmap.h> #include <asm/virtconvert.h> -#include <asm-generic/io.h> #endif /* _M68KNOMMU_IO_H */ diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h index 84b8333db8ad..aac7f045f7f0 100644 --- a/arch/m68k/include/asm/kmap.h +++ b/arch/m68k/include/asm/kmap.h @@ -4,6 +4,8 @@ #ifdef CONFIG_MMU +#define ARCH_HAS_IOREMAP_WT + /* Values for nocacheflag and cmode */ #define IOMAP_FULL_CACHING 0 #define IOMAP_NOCACHE_SER 1 @@ -16,6 +18,7 @@ */ extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag); +#define iounmap iounmap extern void iounmap(void __iomem *addr); extern void __iounmap(void *addr, unsigned long size); @@ -33,31 +36,35 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, } #define ioremap_uc ioremap_nocache +#define ioremap_wt ioremap_wt static inline void __iomem *ioremap_wt(unsigned long physaddr, unsigned long size) { return __ioremap(physaddr, size, IOMAP_WRITETHROUGH); } -#define ioremap_fillcache ioremap_fullcache +#define ioremap_fullcache ioremap_fullcache static inline void __iomem *ioremap_fullcache(unsigned long physaddr, unsigned long size) { return __ioremap(physaddr, size, IOMAP_FULL_CACHING); } +#define memset_io memset_io static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count) { __builtin_memset((void __force *) addr, val, count); } +#define memcpy_fromio memcpy_fromio static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count) { __builtin_memcpy(dst, (void __force *) src, count); } +#define memcpy_toio memcpy_toio static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count) { diff --git a/arch/m68k/include/asm/machdep.h b/arch/m68k/include/asm/machdep.h index 1605da48ebf2..49bd3266b4b1 100644 --- a/arch/m68k/include/asm/machdep.h +++ b/arch/m68k/include/asm/machdep.h @@ -22,7 +22,6 @@ extern int (*mach_hwclk)(int, struct rtc_time*); extern unsigned int (*mach_get_ss)(void); extern int (*mach_get_rtc_pll)(struct rtc_pll_info *); extern int (*mach_set_rtc_pll)(struct rtc_pll_info *); -extern int (*mach_set_clock_mmss)(unsigned long); extern void (*mach_reset)( void ); extern void (*mach_halt)( void ); extern void (*mach_power_off)( void ); diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h index 9b840c03ebb7..08cee11180e6 100644 --- a/arch/m68k/include/asm/macintosh.h +++ b/arch/m68k/include/asm/macintosh.h @@ -57,7 +57,6 @@ struct mac_model #define MAC_SCSI_IIFX 5 #define MAC_SCSI_DUO 6 #define MAC_SCSI_LC 7 -#define MAC_SCSI_LATE 8 #define MAC_IDE_NONE 0 #define MAC_IDE_QUADRA 1 diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h index e644c4daf540..6bbe52025de3 100644 --- a/arch/m68k/include/asm/page_no.h +++ b/arch/m68k/include/asm/page_no.h @@ -18,7 +18,7 @@ extern unsigned long memory_end; #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE #define __pa(vaddr) ((unsigned long)(vaddr)) -#define __va(paddr) ((void *)(paddr)) +#define __va(paddr) ((void *)((unsigned long)(paddr))) #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define pfn_to_virt(pfn) __va((pfn) << PAGE_SHIFT) diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c index 463572c4943f..e99993c57d6b 100644 --- a/arch/m68k/kernel/dma.c +++ b/arch/m68k/kernel/dma.c @@ -6,7 +6,7 @@ #undef DEBUG -#include <linux/dma-mapping.h> +#include <linux/dma-noncoherent.h> #include <linux/device.h> #include <linux/kernel.h> #include <linux/platform_device.h> @@ -19,7 +19,7 @@ #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE) -static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t flag, unsigned long attrs) { struct page *page, **map; @@ -62,7 +62,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, return addr; } -static void m68k_dma_free(struct device *dev, size_t size, void *addr, +void arch_dma_free(struct device *dev, size_t size, void *addr, dma_addr_t handle, unsigned long attrs) { pr_debug("dma_free_coherent: %p, %x\n", addr, handle); @@ -73,8 +73,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *addr, #include <asm/cacheflush.h> -static void *m68k_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) { void *ret; @@ -89,7 +89,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, return ret; } -static void m68k_dma_free(struct device *dev, size_t size, void *vaddr, +void arch_dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { free_pages((unsigned long)vaddr, get_order(size)); @@ -97,8 +97,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *vaddr, #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */ -static void m68k_dma_sync_single_for_device(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle, + size_t size, enum dma_data_direction dir) { switch (dir) { case DMA_BIDIRECTIONAL: @@ -115,58 +115,6 @@ static void m68k_dma_sync_single_for_device(struct device *dev, } } -static void m68k_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sglist, int nents, enum dma_data_direction dir) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nents, i) { - dma_sync_single_for_device(dev, sg->dma_address, sg->length, - dir); - } -} - -static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t handle = page_to_phys(page) + offset; - - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_sync_single_for_device(dev, handle, size, dir); - - return handle; -} - -static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nents, i) { - sg->dma_address = sg_phys(sg); - - if (attrs & DMA_ATTR_SKIP_CPU_SYNC) - continue; - - dma_sync_single_for_device(dev, sg->dma_address, sg->length, - dir); - } - return nents; -} - -const struct dma_map_ops m68k_dma_ops = { - .alloc = m68k_dma_alloc, - .free = m68k_dma_free, - .map_page = m68k_dma_map_page, - .map_sg = m68k_dma_map_sg, - .sync_single_for_device = m68k_dma_sync_single_for_device, - .sync_sg_for_device = m68k_dma_sync_sg_for_device, -}; -EXPORT_SYMBOL(m68k_dma_ops); - void arch_setup_pdev_archdata(struct platform_device *pdev) { if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE && diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index f35e3ebd6331..5d3596c180f9 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/module.h> @@ -88,7 +89,6 @@ void (*mach_get_hardware_list) (struct seq_file *m); /* machine dependent timer functions */ int (*mach_hwclk) (int, struct rtc_time*); EXPORT_SYMBOL(mach_hwclk); -int (*mach_set_clock_mmss) (unsigned long); unsigned int (*mach_get_ss)(void); int (*mach_get_rtc_pll)(struct rtc_pll_info *); int (*mach_set_rtc_pll)(struct rtc_pll_info *); @@ -165,6 +165,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record) be32_to_cpu(m->addr); m68k_memory[m68k_num_memory].size = be32_to_cpu(m->size); + memblock_add(m68k_memory[m68k_num_memory].addr, + m68k_memory[m68k_num_memory].size); m68k_num_memory++; } else pr_warn("%s: too many memory chunks\n", @@ -224,10 +226,6 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record) void __init setup_arch(char **cmdline_p) { -#ifndef CONFIG_SUN3 - int i; -#endif - /* The bootinfo is located right after the kernel */ if (!CPU_IS_COLDFIRE) m68k_parse_bootinfo((const struct bi_record *)_end); @@ -356,14 +354,9 @@ void __init setup_arch(char **cmdline_p) #endif #ifndef CONFIG_SUN3 - for (i = 1; i < m68k_num_memory; i++) - free_bootmem_node(NODE_DATA(i), m68k_memory[i].addr, - m68k_memory[i].size); #ifdef CONFIG_BLK_DEV_INITRD if (m68k_ramdisk.size) { - reserve_bootmem_node(__virt_to_node(phys_to_virt(m68k_ramdisk.addr)), - m68k_ramdisk.addr, m68k_ramdisk.size, - BOOTMEM_DEFAULT); + memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size); initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr); initrd_end = initrd_start + m68k_ramdisk.size; pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end); diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index a98af1018201..cfd5475bfc31 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -28,6 +28,7 @@ #include <linux/errno.h> #include <linux/string.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/initrd.h> @@ -51,7 +52,6 @@ char __initdata command_line[COMMAND_LINE_SIZE]; /* machine dependent timer functions */ void (*mach_sched_init)(irq_handler_t handler) __initdata = NULL; -int (*mach_set_clock_mmss)(unsigned long); int (*mach_hwclk) (int, struct rtc_time*); /* machine dependent reboot functions */ @@ -86,8 +86,6 @@ void (*mach_power_off)(void); void __init setup_arch(char **cmdline_p) { - int bootmap_size; - memory_start = PAGE_ALIGN(_ramstart); memory_end = _ramend; @@ -142,6 +140,8 @@ void __init setup_arch(char **cmdline_p) pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ", __bss_stop, memory_start, memory_start, memory_end); + memblock_add(memory_start, memory_end - memory_start); + /* Keep a copy of command line */ *cmdline_p = &command_line[0]; memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); @@ -158,23 +158,10 @@ void __init setup_arch(char **cmdline_p) min_low_pfn = PFN_DOWN(memory_start); max_pfn = max_low_pfn = PFN_DOWN(memory_end); - bootmap_size = init_bootmem_node( - NODE_DATA(0), - min_low_pfn, /* map goes here */ - PFN_DOWN(PAGE_OFFSET), - max_pfn); - /* - * Free the usable memory, we have to make sure we do not free - * the bootmem bitmap so we then reserve it after freeing it :-) - */ - free_bootmem(memory_start, memory_end - memory_start); - reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT); - #if defined(CONFIG_UBOOT) && defined(CONFIG_BLK_DEV_INITRD) if ((initrd_start > 0) && (initrd_start < initrd_end) && (initrd_end < memory_end)) - reserve_bootmem(initrd_start, initrd_end - initrd_start, - BOOTMEM_DEFAULT); + memblock_reserve(initrd_start, initrd_end - initrd_start); #endif /* if defined(CONFIG_BLK_DEV_INITRD) */ /* diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index e522307db47c..cd9317d53276 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -57,7 +57,6 @@ static unsigned long mac_orig_videoaddr; /* Mac specific timer functions */ extern u32 mac_gettimeoffset(void); extern int mac_hwclk(int, struct rtc_time *); -extern int mac_set_clock_mmss(unsigned long); extern void iop_preinit(void); extern void iop_init(void); extern void via_init(void); @@ -158,7 +157,6 @@ void __init config_mac(void) mach_get_model = mac_get_model; arch_gettimeoffset = mac_gettimeoffset; mach_hwclk = mac_hwclk; - mach_set_clock_mmss = mac_set_clock_mmss; mach_reset = mac_reset; mach_halt = mac_poweroff; mach_power_off = mac_poweroff; @@ -709,7 +707,7 @@ static struct mac_model mac_data_table[] = { .name = "PowerBook 520", .adb_type = MAC_ADB_PB2, .via_type = MAC_VIA_QUADRA, - .scsi_type = MAC_SCSI_LATE, + .scsi_type = MAC_SCSI_OLD, .scc_type = MAC_SCC_QUADRA, .ether_type = MAC_ETHER_SONIC, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -891,7 +889,7 @@ static void __init mac_identify(void) #ifdef CONFIG_ADB_CUDA find_via_cuda(); #endif -#ifdef CONFIG_ADB_PMU68K +#ifdef CONFIG_ADB_PMU find_via_pmu(); #endif } @@ -943,18 +941,6 @@ static const struct resource mac_scsi_old_rsrc[] __initconst = { }, }; -static const struct resource mac_scsi_late_rsrc[] __initconst = { - { - .flags = IORESOURCE_IRQ, - .start = IRQ_MAC_SCSI, - .end = IRQ_MAC_SCSI, - }, { - .flags = IORESOURCE_MEM, - .start = 0x50010000, - .end = 0x50011FFF, - }, -}; - static const struct resource mac_scsi_ccl_rsrc[] __initconst = { { .flags = IORESOURCE_IRQ, @@ -1064,11 +1050,6 @@ int __init mac_platform_init(void) platform_device_register_simple("mac_scsi", 0, mac_scsi_old_rsrc, ARRAY_SIZE(mac_scsi_old_rsrc)); break; - case MAC_SCSI_LATE: - /* XXX PDMA support for PowerBook 500 series needs testing */ - platform_device_register_simple("mac_scsi", 0, - mac_scsi_late_rsrc, ARRAY_SIZE(mac_scsi_late_rsrc)); - break; case MAC_SCSI_LC: /* Addresses from Mac LC data in Designing Cards & Drivers 3ed. * Also from the Developer Notes for Classic II, LC III, diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index c68054361615..3534aa6a4dc2 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -26,33 +26,38 @@ #include <asm/machdep.h> -/* Offset between Unix time (1970-based) and Mac time (1904-based) */ +/* + * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU + * times wrap in 2040. If we need to handle later times, the read_time functions + * need to be changed to interpret wrapped times as post-2040. + */ #define RTC_OFFSET 2082844800 static void (*rom_reset)(void); #ifdef CONFIG_ADB_CUDA -static long cuda_read_time(void) +static time64_t cuda_read_time(void) { struct adb_request req; - long time; + time64_t time; if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0) return 0; while (!req.complete) cuda_poll(); - time = (req.reply[3] << 24) | (req.reply[4] << 16) | - (req.reply[5] << 8) | req.reply[6]; + time = (u32)((req.reply[3] << 24) | (req.reply[4] << 16) | + (req.reply[5] << 8) | req.reply[6]); + return time - RTC_OFFSET; } -static void cuda_write_time(long data) +static void cuda_write_time(time64_t time) { struct adb_request req; + u32 data = lower_32_bits(time + RTC_OFFSET); - data += RTC_OFFSET; if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME, (data >> 24) & 0xFF, (data >> 16) & 0xFF, (data >> 8) & 0xFF, data & 0xFF) < 0) @@ -85,27 +90,28 @@ static void cuda_write_pram(int offset, __u8 data) } #endif /* CONFIG_ADB_CUDA */ -#ifdef CONFIG_ADB_PMU68K -static long pmu_read_time(void) +#ifdef CONFIG_ADB_PMU +static time64_t pmu_read_time(void) { struct adb_request req; - long time; + time64_t time; if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) return 0; while (!req.complete) pmu_poll(); - time = (req.reply[1] << 24) | (req.reply[2] << 16) | - (req.reply[3] << 8) | req.reply[4]; + time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) | + (req.reply[3] << 8) | req.reply[4]); + return time - RTC_OFFSET; } -static void pmu_write_time(long data) +static void pmu_write_time(time64_t time) { struct adb_request req; + u32 data = lower_32_bits(time + RTC_OFFSET); - data += RTC_OFFSET; if (pmu_request(&req, NULL, 5, PMU_SET_RTC, (data >> 24) & 0xFF, (data >> 16) & 0xFF, (data >> 8) & 0xFF, data & 0xFF) < 0) @@ -136,7 +142,7 @@ static void pmu_write_pram(int offset, __u8 data) while (!req.complete) pmu_poll(); } -#endif /* CONFIG_ADB_PMU68K */ +#endif /* CONFIG_ADB_PMU */ /* * VIA PRAM/RTC access routines @@ -245,11 +251,11 @@ static void via_write_pram(int offset, __u8 data) * is basically any machine with Mac II-style ADB. */ -static long via_read_time(void) +static time64_t via_read_time(void) { union { __u8 cdata[4]; - long idata; + __u32 idata; } result, last_result; int count = 1; @@ -270,7 +276,7 @@ static long via_read_time(void) via_pram_command(0x8D, &result.cdata[0]); if (result.idata == last_result.idata) - return result.idata - RTC_OFFSET; + return (time64_t)result.idata - RTC_OFFSET; if (++count > 10) break; @@ -278,8 +284,8 @@ static long via_read_time(void) last_result.idata = result.idata; } - pr_err("via_read_time: failed to read a stable value; got 0x%08lx then 0x%08lx\n", - last_result.idata, result.idata); + pr_err("%s: failed to read a stable value; got 0x%08x then 0x%08x\n", + __func__, last_result.idata, result.idata); return 0; } @@ -291,11 +297,11 @@ static long via_read_time(void) * is basically any machine with Mac II-style ADB. */ -static void via_write_time(long time) +static void via_write_time(time64_t time) { union { __u8 cdata[4]; - long idata; + __u32 idata; } data; __u8 temp; @@ -304,7 +310,7 @@ static void via_write_time(long time) temp = 0x55; via_pram_command(0x35, &temp); - data.idata = time + RTC_OFFSET; + data.idata = lower_32_bits(time + RTC_OFFSET); via_pram_command(0x01, &data.cdata[3]); via_pram_command(0x05, &data.cdata[2]); via_pram_command(0x09, &data.cdata[1]); @@ -367,38 +373,6 @@ static void cuda_shutdown(void) } #endif /* CONFIG_ADB_CUDA */ -#ifdef CONFIG_ADB_PMU68K - -void pmu_restart(void) -{ - struct adb_request req; - if (pmu_request(&req, NULL, - 2, PMU_SET_INTR_MASK, PMU_INT_ADB|PMU_INT_TICK) < 0) - return; - while (!req.complete) - pmu_poll(); - if (pmu_request(&req, NULL, 1, PMU_RESET) < 0) - return; - while (!req.complete) - pmu_poll(); -} - -void pmu_shutdown(void) -{ - struct adb_request req; - if (pmu_request(&req, NULL, - 2, PMU_SET_INTR_MASK, PMU_INT_ADB|PMU_INT_TICK) < 0) - return; - while (!req.complete) - pmu_poll(); - if (pmu_request(&req, NULL, 5, PMU_SHUTDOWN, 'M', 'A', 'T', 'T') < 0) - return; - while (!req.complete) - pmu_poll(); -} - -#endif - /* *------------------------------------------------------------------- * Below this point are the generic routines; they'll dispatch to the @@ -423,7 +397,7 @@ void mac_pram_read(int offset, __u8 *buffer, int len) func = cuda_read_pram; break; #endif -#ifdef CONFIG_ADB_PMU68K +#ifdef CONFIG_ADB_PMU case MAC_ADB_PB2: func = pmu_read_pram; break; @@ -453,7 +427,7 @@ void mac_pram_write(int offset, __u8 *buffer, int len) func = cuda_write_pram; break; #endif -#ifdef CONFIG_ADB_PMU68K +#ifdef CONFIG_ADB_PMU case MAC_ADB_PB2: func = pmu_write_pram; break; @@ -477,9 +451,8 @@ void mac_poweroff(void) macintosh_config->adb_type == MAC_ADB_CUDA) { cuda_shutdown(); #endif -#ifdef CONFIG_ADB_PMU68K - } else if (macintosh_config->adb_type == MAC_ADB_PB1 - || macintosh_config->adb_type == MAC_ADB_PB2) { +#ifdef CONFIG_ADB_PMU + } else if (macintosh_config->adb_type == MAC_ADB_PB2) { pmu_shutdown(); #endif } @@ -519,9 +492,8 @@ void mac_reset(void) macintosh_config->adb_type == MAC_ADB_CUDA) { cuda_restart(); #endif -#ifdef CONFIG_ADB_PMU68K - } else if (macintosh_config->adb_type == MAC_ADB_PB1 - || macintosh_config->adb_type == MAC_ADB_PB2) { +#ifdef CONFIG_ADB_PMU + } else if (macintosh_config->adb_type == MAC_ADB_PB2) { pmu_restart(); #endif } else if (CPU_IS_030) { @@ -585,12 +557,15 @@ void mac_reset(void) * This function translates seconds since 1970 into a proper date. * * Algorithm cribbed from glibc2.1, __offtime(). + * + * This is roughly same as rtc_time64_to_tm(), which we should probably + * use here, but it's only available when CONFIG_RTC_LIB is enabled. */ #define SECS_PER_MINUTE (60) #define SECS_PER_HOUR (SECS_PER_MINUTE * 60) #define SECS_PER_DAY (SECS_PER_HOUR * 24) -static void unmktime(unsigned long time, long offset, +static void unmktime(time64_t time, long offset, int *yearp, int *monp, int *dayp, int *hourp, int *minp, int *secp) { @@ -602,11 +577,10 @@ static void unmktime(unsigned long time, long offset, /* Leap years. */ { 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 } }; - long int days, rem, y, wday, yday; + int days, rem, y, wday, yday; const unsigned short int *ip; - days = time / SECS_PER_DAY; - rem = time % SECS_PER_DAY; + days = div_u64_rem(time, SECS_PER_DAY, &rem); rem += offset; while (rem < 0) { rem += SECS_PER_DAY; @@ -657,7 +631,7 @@ static void unmktime(unsigned long time, long offset, int mac_hwclk(int op, struct rtc_time *t) { - unsigned long now; + time64_t now; if (!op) { /* read */ switch (macintosh_config->adb_type) { @@ -672,7 +646,7 @@ int mac_hwclk(int op, struct rtc_time *t) now = cuda_read_time(); break; #endif -#ifdef CONFIG_ADB_PMU68K +#ifdef CONFIG_ADB_PMU case MAC_ADB_PB2: now = pmu_read_time(); break; @@ -693,8 +667,8 @@ int mac_hwclk(int op, struct rtc_time *t) __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, t->tm_hour, t->tm_min, t->tm_sec); - now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, - t->tm_hour, t->tm_min, t->tm_sec); + now = mktime64(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, + t->tm_hour, t->tm_min, t->tm_sec); switch (macintosh_config->adb_type) { case MAC_ADB_IOP: @@ -708,7 +682,7 @@ int mac_hwclk(int op, struct rtc_time *t) cuda_write_time(now); break; #endif -#ifdef CONFIG_ADB_PMU68K +#ifdef CONFIG_ADB_PMU case MAC_ADB_PB2: pmu_write_time(now); break; @@ -719,19 +693,3 @@ int mac_hwclk(int op, struct rtc_time *t) } return 0; } - -/* - * Set minutes/seconds in the hardware clock - */ - -int mac_set_clock_mmss (unsigned long nowtime) -{ - struct rtc_time now; - - mac_hwclk(0, &now); - now.tm_sec = nowtime % 60; - now.tm_min = (nowtime / 60) % 60; - mac_hwclk(1, &now); - - return 0; -} diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index f2ff3779875a..9b6163c05a75 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -70,7 +70,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, { struct mm_struct *mm = current->mm; struct vm_area_struct * vma; - int fault; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; pr_debug("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n", @@ -136,7 +136,7 @@ good_area: */ fault = handle_mm_fault(vma, address, flags); - pr_debug("handle_mm_fault returns %d\n", fault); + pr_debug("handle_mm_fault returns %x\n", fault); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return 0; diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 8827b7f91402..38e2b272c220 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -71,7 +71,6 @@ void __init m68k_setup_node(int node) pg_data_table[i] = pg_data_map + node; } #endif - pg_data_map[node].bdata = bootmem_node_data + node; node_set_online(node); } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 2925d795d71a..70dde040779b 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/string.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/page.h> @@ -153,31 +154,31 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word) void __init cf_bootmem_alloc(void) { - unsigned long start_pfn; unsigned long memstart; /* _rambase and _ramend will be naturally page aligned */ m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; + memblock_add(m68k_memory[0].addr, m68k_memory[0].size); + /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); /* page numbers */ memstart = PAGE_ALIGN(_ramstart); min_low_pfn = PFN_DOWN(_rambase); - start_pfn = PFN_DOWN(memstart); max_pfn = max_low_pfn = PFN_DOWN(_ramend); high_memory = (void *)_ramend; + /* Reserve kernel text/data/bss */ + memblock_reserve(memstart, memstart - _rambase); + m68k_virt_to_node_shift = fls(_ramend - 1) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); - /* setup bootmem data */ + /* setup node data */ m68k_setup_node(0); - memstart += init_bootmem_node(NODE_DATA(0), start_pfn, - min_low_pfn, max_low_pfn); - free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart); } /* diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index e490ecc7842c..4e17ecb5928a 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/gfp.h> #include <asm/setup.h> @@ -208,7 +209,7 @@ void __init paging_init(void) { unsigned long zones_size[MAX_NR_ZONES] = { 0, }; unsigned long min_addr, max_addr; - unsigned long addr, size, end; + unsigned long addr; int i; #ifdef DEBUG @@ -253,34 +254,20 @@ void __init paging_init(void) min_low_pfn = availmem >> PAGE_SHIFT; max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT; - for (i = 0; i < m68k_num_memory; i++) { - addr = m68k_memory[i].addr; - end = addr + m68k_memory[i].size; - m68k_setup_node(i); - availmem = PAGE_ALIGN(availmem); - availmem += init_bootmem_node(NODE_DATA(i), - availmem >> PAGE_SHIFT, - addr >> PAGE_SHIFT, - end >> PAGE_SHIFT); - } + /* Reserve kernel text/data/bss and the memory allocated in head.S */ + memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr); /* * Map the physical memory available into the kernel virtual - * address space. First initialize the bootmem allocator with - * the memory we already mapped, so map_node() has something - * to allocate. + * address space. Make sure memblock will not try to allocate + * pages beyond the memory we already mapped in head.S */ - addr = m68k_memory[0].addr; - size = m68k_memory[0].size; - free_bootmem_node(NODE_DATA(0), availmem, - min(m68k_init_mapped_size, size) - (availmem - addr)); - map_node(0); - if (size > m68k_init_mapped_size) - free_bootmem_node(NODE_DATA(0), addr + m68k_init_mapped_size, - size - m68k_init_mapped_size); - - for (i = 1; i < m68k_num_memory; i++) + memblock_set_bottom_up(true); + + for (i = 0; i < m68k_num_memory; i++) { + m68k_setup_node(i); map_node(i); + } flush_tlb_all(); diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c index f8a710fd84cd..adea549d240e 100644 --- a/arch/m68k/mvme147/config.c +++ b/arch/m68k/mvme147/config.c @@ -40,7 +40,6 @@ static void mvme147_get_model(char *model); extern void mvme147_sched_init(irq_handler_t handler); extern u32 mvme147_gettimeoffset(void); extern int mvme147_hwclk (int, struct rtc_time *); -extern int mvme147_set_clock_mmss (unsigned long); extern void mvme147_reset (void); @@ -92,7 +91,6 @@ void __init config_mvme147(void) mach_init_IRQ = mvme147_init_IRQ; arch_gettimeoffset = mvme147_gettimeoffset; mach_hwclk = mvme147_hwclk; - mach_set_clock_mmss = mvme147_set_clock_mmss; mach_reset = mvme147_reset; mach_get_model = mvme147_get_model; @@ -164,8 +162,3 @@ int mvme147_hwclk(int op, struct rtc_time *t) } return 0; } - -int mvme147_set_clock_mmss (unsigned long nowtime) -{ - return 0; -} diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c index 4ffd9ef98de4..6ee36a5b528d 100644 --- a/arch/m68k/mvme16x/config.c +++ b/arch/m68k/mvme16x/config.c @@ -46,7 +46,6 @@ static void mvme16x_get_model(char *model); extern void mvme16x_sched_init(irq_handler_t handler); extern u32 mvme16x_gettimeoffset(void); extern int mvme16x_hwclk (int, struct rtc_time *); -extern int mvme16x_set_clock_mmss (unsigned long); extern void mvme16x_reset (void); int bcd2int (unsigned char b); @@ -280,7 +279,6 @@ void __init config_mvme16x(void) mach_init_IRQ = mvme16x_init_IRQ; arch_gettimeoffset = mvme16x_gettimeoffset; mach_hwclk = mvme16x_hwclk; - mach_set_clock_mmss = mvme16x_set_clock_mmss; mach_reset = mvme16x_reset; mach_get_model = mvme16x_get_model; mach_get_hardware_list = mvme16x_get_hardware_list; @@ -411,9 +409,3 @@ int mvme16x_hwclk(int op, struct rtc_time *t) } return 0; } - -int mvme16x_set_clock_mmss (unsigned long nowtime) -{ - return 0; -} - diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index 71c0867ecf20..96810d91da2b 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -43,7 +43,6 @@ extern void q40_sched_init(irq_handler_t handler); static u32 q40_gettimeoffset(void); static int q40_hwclk(int, struct rtc_time *); static unsigned int q40_get_ss(void); -static int q40_set_clock_mmss(unsigned long); static int q40_get_rtc_pll(struct rtc_pll_info *pll); static int q40_set_rtc_pll(struct rtc_pll_info *pll); @@ -175,7 +174,6 @@ void __init config_q40(void) mach_get_ss = q40_get_ss; mach_get_rtc_pll = q40_get_rtc_pll; mach_set_rtc_pll = q40_set_rtc_pll; - mach_set_clock_mmss = q40_set_clock_mmss; mach_reset = q40_reset; mach_get_model = q40_get_model; @@ -267,34 +265,6 @@ static unsigned int q40_get_ss(void) return bcd2bin(Q40_RTC_SECS); } -/* - * Set the minutes and seconds from seconds value 'nowtime'. Fail if - * clock is out by > 30 minutes. Logic lifted from atari code. - */ - -static int q40_set_clock_mmss(unsigned long nowtime) -{ - int retval = 0; - short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60; - - int rtc_minutes; - - rtc_minutes = bcd2bin(Q40_RTC_MINS); - - if ((rtc_minutes < real_minutes ? - real_minutes - rtc_minutes : - rtc_minutes - real_minutes) < 30) { - Q40_RTC_CTRL |= Q40_RTC_WRITE; - Q40_RTC_MINS = bin2bcd(real_minutes); - Q40_RTC_SECS = bin2bcd(real_seconds); - Q40_RTC_CTRL &= ~(Q40_RTC_WRITE); - } else - retval = -1; - - return retval; -} - - /* get and set PLL calibration of RTC clock */ #define Q40_RTC_PLL_MASK ((1<<5)-1) #define Q40_RTC_PLL_SIGN (1<<5) diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index 1d28d380e8cc..79a2bb857906 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -123,10 +123,6 @@ static void __init sun3_bootmem_alloc(unsigned long memory_start, availmem = memory_start; m68k_setup_node(0); - availmem += init_bootmem(start_page, num_pages); - availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK; - - free_bootmem(__pa(availmem), memory_end - (availmem)); } diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index d14782100088..6163a39ddeb6 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -1,5 +1,6 @@ config MICROBLAZE def_bool y + select ARCH_NO_SWAP select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_NO_COHERENT_DMA_MMAP if !MMU @@ -52,9 +53,6 @@ config CPU_LITTLE_ENDIAN endchoice -config SWAP - def_bool n - config RWSEM_GENERIC_SPINLOCK def_bool y @@ -85,16 +83,10 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - source "arch/microblaze/Kconfig.platform" menu "Processor type and features" -source "kernel/Kconfig.preempt" - source "kernel/Kconfig.hz" config MMU @@ -268,14 +260,6 @@ config MICROBLAZE_64K_PAGES endchoice -source "mm/Kconfig" - -endmenu - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - endmenu menu "Bus Options" @@ -299,17 +283,3 @@ config PCI_XILINX source "drivers/pci/Kconfig" endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "arch/microblaze/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/microblaze/Kconfig.debug b/arch/microblaze/Kconfig.debug index 93a737c8d1a6..dc2e3c45e8a2 100644 --- a/arch/microblaze/Kconfig.debug +++ b/arch/microblaze/Kconfig.debug @@ -1,11 +1,5 @@ # For a description of the syntax of this configuration file, # see Documentation/kbuild/kconfig-language.txt. -menu "Kernel hacking" - config TRACE_IRQFLAGS_SUPPORT def_bool y - -source "lib/Kconfig.debug" - -endmenu diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index af607447c683..202ad6a494f5 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -90,7 +90,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, struct mm_struct *mm = current->mm; int code = SEGV_MAPERR; int is_write = error_code & ESR_S; - int fault; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; regs->ear = address; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 08c10c518f83..2af13b162e5e 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -16,6 +16,7 @@ config MIPS select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select CPU_PM if CPU_IDLE + select DMA_DIRECT_OPS select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS select GENERIC_CMOS_UPDATE @@ -97,6 +98,7 @@ config MIPS_GENERIC select HW_HAS_PCI select IRQ_MIPS_CPU select LIBFDT + select MIPS_AUTO_PFN_OFFSET select MIPS_CPU_SCACHE select MIPS_GIC select MIPS_L1_CACHE_SHIFT_7 @@ -193,6 +195,7 @@ config ATH79 select CSRC_R4K select DMA_NONCOHERENT select GPIOLIB + select PINCTRL select HAVE_CLK select COMMON_CLK select CLKDEV_LOOKUP @@ -211,6 +214,8 @@ config ATH79 config BMIPS_GENERIC bool "Broadcom Generic BMIPS kernel" + select ARCH_HAS_SYNC_DMA_FOR_CPU_ALL + select ARCH_HAS_PHYS_TO_DMA select BOOT_RAW select NO_EXCEPT_FILL select USE_OF @@ -438,7 +443,6 @@ config MACH_LOONGSON32 config MACH_LOONGSON64 bool "Loongson-2/3 family of machines" - select ARCH_HAS_PHYS_TO_DMA select SYS_SUPPORTS_ZBOOT help This enables the support of Loongson-2/3 family of machines. @@ -662,11 +666,11 @@ config SGI_IP22 config SGI_IP27 bool "SGI IP27 (Origin200/2000)" + select ARCH_HAS_PHYS_TO_DMA select FW_ARC select FW_ARC64 select BOOT_ELF64 select DEFAULT_SGI_PARTITION - select DMA_COHERENT select SYS_HAS_EARLY_PRINTK select HW_HAS_PCI select NR_CPUS_DEFAULT_64 @@ -721,6 +725,7 @@ config SGI_IP28 config SGI_IP32 bool "SGI IP32 (O2)" + select ARCH_HAS_PHYS_TO_DMA select FW_ARC select FW_ARC32 select BOOT_ELF32 @@ -743,7 +748,6 @@ config SGI_IP32 config SIBYTE_CRHINE bool "Sibyte BCM91120C-CRhine" select BOOT_ELF32 - select DMA_COHERENT select SIBYTE_BCM1120 select SWAP_IO_SPACE select SYS_HAS_CPU_SB1 @@ -753,7 +757,6 @@ config SIBYTE_CRHINE config SIBYTE_CARMEL bool "Sibyte BCM91120x-Carmel" select BOOT_ELF32 - select DMA_COHERENT select SIBYTE_BCM1120 select SWAP_IO_SPACE select SYS_HAS_CPU_SB1 @@ -763,7 +766,6 @@ config SIBYTE_CARMEL config SIBYTE_CRHONE bool "Sibyte BCM91125C-CRhone" select BOOT_ELF32 - select DMA_COHERENT select SIBYTE_BCM1125 select SWAP_IO_SPACE select SYS_HAS_CPU_SB1 @@ -774,7 +776,6 @@ config SIBYTE_CRHONE config SIBYTE_RHONE bool "Sibyte BCM91125E-Rhone" select BOOT_ELF32 - select DMA_COHERENT select SIBYTE_BCM1125H select SWAP_IO_SPACE select SYS_HAS_CPU_SB1 @@ -784,7 +785,6 @@ config SIBYTE_RHONE config SIBYTE_SWARM bool "Sibyte BCM91250A-SWARM" select BOOT_ELF32 - select DMA_COHERENT select HAVE_PATA_PLATFORM select SIBYTE_SB1250 select SWAP_IO_SPACE @@ -797,7 +797,6 @@ config SIBYTE_SWARM config SIBYTE_LITTLESUR bool "Sibyte BCM91250C2-LittleSur" select BOOT_ELF32 - select DMA_COHERENT select HAVE_PATA_PLATFORM select SIBYTE_SB1250 select SWAP_IO_SPACE @@ -809,7 +808,6 @@ config SIBYTE_LITTLESUR config SIBYTE_SENTOSA bool "Sibyte BCM91250E-Sentosa" select BOOT_ELF32 - select DMA_COHERENT select SIBYTE_SB1250 select SWAP_IO_SPACE select SYS_HAS_CPU_SB1 @@ -819,7 +817,6 @@ config SIBYTE_SENTOSA config SIBYTE_BIGSUR bool "Sibyte BCM91480B-BigSur" select BOOT_ELF32 - select DMA_COHERENT select NR_CPUS_DEFAULT_4 select SIBYTE_BCM1x80 select SWAP_IO_SPACE @@ -895,8 +892,8 @@ config CAVIUM_OCTEON_SOC bool "Cavium Networks Octeon SoC based boards" select CEVT_R4K select ARCH_HAS_PHYS_TO_DMA + select HAS_RAPIDIO select PHYS_ADDR_T_64BIT - select DMA_COHERENT select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select EDAC_SUPPORT @@ -945,7 +942,6 @@ config NLM_XLR_BOARD select PHYS_ADDR_T_64BIT select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_HIGHMEM - select DMA_COHERENT select NR_CPUS_DEFAULT_32 select CEVT_R4K select CSRC_R4K @@ -973,7 +969,6 @@ config NLM_XLP_BOARD select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_HIGHMEM - select DMA_COHERENT select NR_CPUS_DEFAULT_32 select CEVT_R4K select CSRC_R4K @@ -992,7 +987,6 @@ config MIPS_PARAVIRT bool "Para-Virtualized guest system" select CEVT_R4K select CSRC_R4K - select DMA_COHERENT select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN @@ -1118,12 +1112,14 @@ config DMA_PERDEV_COHERENT bool select DMA_MAYBE_COHERENT -config DMA_COHERENT - bool - config DMA_NONCOHERENT bool + select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select ARCH_HAS_SYNC_DMA_FOR_CPU select NEED_DMA_MAP_STATE + select DMA_NONCOHERENT_MMAP + select DMA_NONCOHERENT_CACHE_SYNC + select DMA_NONCOHERENT_OPS config SYS_HAS_EARLY_PRINTK bool @@ -1365,6 +1361,7 @@ choice config CPU_LOONGSON3 bool "Loongson 3 CPU" depends on SYS_HAS_CPU_LOONGSON3 + select ARCH_HAS_PHYS_TO_DMA select CPU_SUPPORTS_64BIT_KERNEL select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_HUGEPAGES @@ -1427,7 +1424,8 @@ config CPU_LOONGSON1B select LEDS_GPIO_REGISTER help The Loongson 1B is a 32-bit SoC, which implements the MIPS32 - release 2 instruction set. + Release 1 instruction set and part of the MIPS32 Release 2 + instruction set. config CPU_LOONGSON1C bool "Loongson 1C" @@ -1436,7 +1434,8 @@ config CPU_LOONGSON1C select LEDS_GPIO_REGISTER help The Loongson 1C is a 32-bit SoC, which implements the MIPS32 - release 2 instruction set. + Release 1 instruction set and part of the MIPS32 Release 2 + instruction set. config CPU_MIPS32_R1 bool "MIPS32 Release 1" @@ -1831,11 +1830,12 @@ config CPU_LOONGSON2 select CPU_SUPPORTS_64BIT_KERNEL select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_HUGEPAGES + select ARCH_HAS_PHYS_TO_DMA config CPU_LOONGSON1 bool select CPU_MIPS32 - select CPU_MIPSR2 + select CPU_MIPSR1 select CPU_HAS_PREFETCH select CPU_SUPPORTS_32BIT_KERNEL select CPU_SUPPORTS_HIGHMEM @@ -1979,12 +1979,6 @@ config SYS_HAS_CPU_XLR config SYS_HAS_CPU_XLP bool -config MIPS_MALTA_PM - depends on MIPS_MALTA - depends on PCI - bool - default y - # # CPU may reorder R->R, R->W, W->R, W->W # Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC @@ -2641,8 +2635,6 @@ config HW_PERF_EVENTS Enable hardware performance counter support for perf events. If disabled, perf events will use software events only. -source "mm/Kconfig" - config SMP bool "Multi-Processing support" depends on SYS_SUPPORTS_SMP @@ -2820,8 +2812,6 @@ config HZ config SCHED_HRTICK def_bool HIGH_RES_TIMERS -source "kernel/Kconfig.preempt" - config KEXEC bool "Kexec system call" select KEXEC_CORE @@ -2994,9 +2984,8 @@ config PGTABLE_LEVELS default 3 if 64BIT && !PAGE_SIZE_64KB default 2 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" +config MIPS_AUTO_PFN_OFFSET + bool menu "Bus options (PCI, PCMCIA, EISA, ISA, TC)" @@ -3115,10 +3104,13 @@ config ZONE_DMA32 source "drivers/pcmcia/Kconfig" +config HAS_RAPIDIO + bool + default n + config RAPIDIO tristate "RapidIO support" - depends on PCI - default n + depends on HAS_RAPIDIO || PCI help If you say Y here, the kernel will include drivers and infrastructure code to support RapidIO interconnect devices. @@ -3127,10 +3119,6 @@ source "drivers/rapidio/Kconfig" endmenu -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - config TRAD_SIGNALS bool @@ -3176,8 +3164,6 @@ config BINFMT_ELF32 default y if MIPS32_O32 || MIPS32_N32 select ELFCORE -endmenu - menu "Power management options" config ARCH_HIBERNATION_POSSIBLE @@ -3205,20 +3191,6 @@ source "drivers/cpuidle/Kconfig" endmenu -source "net/Kconfig" - -source "drivers/Kconfig" - source "drivers/firmware/Kconfig" -source "fs/Kconfig" - -source "arch/mips/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - source "arch/mips/kvm/Kconfig" diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug index 0749c3724543..0c86b2a2adfc 100644 --- a/arch/mips/Kconfig.debug +++ b/arch/mips/Kconfig.debug @@ -1,12 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" config TRACE_IRQFLAGS_SUPPORT bool default y -source "lib/Kconfig.debug" - config EARLY_PRINTK bool "Early printk" if EXPERT depends on SYS_HAS_EARLY_PRINTK @@ -155,5 +152,3 @@ config MIPS_CPS_NS16550_SHIFT adjacent ns16550 registers in the system. endif # MIPS_CPS_NS16550_BOOL - -endmenu diff --git a/arch/mips/Makefile b/arch/mips/Makefile index e2122cca4ae2..5425df002a6b 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -122,12 +122,22 @@ cflags-y += -ffreestanding # are used, so we kludge that here. A bug has been filed at # http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29413. # +# clang doesn't suffer from these issues and our checks against -dumpmachine +# don't work so well when cross compiling, since without providing --target +# clang's output will be based upon the build machine. So for clang we simply +# unconditionally specify -EB or -EL as appropriate. +# +ifeq ($(cc-name),clang) +cflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB +cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -EL +else undef-all += -UMIPSEB -U_MIPSEB -U__MIPSEB -U__MIPSEB__ undef-all += -UMIPSEL -U_MIPSEL -U__MIPSEL -U__MIPSEL__ predef-be += -DMIPSEB -D_MIPSEB -D__MIPSEB -D__MIPSEB__ predef-le += -DMIPSEL -D_MIPSEL -D__MIPSEL -D__MIPSEL__ cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' && echo -EB $(undef-all) $(predef-be)) cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' || echo -EL $(undef-all) $(predef-le)) +endif cflags-$(CONFIG_SB1XXX_CORELIS) += $(call cc-option,-mno-sched-prolog) \ -fno-omit-frame-pointer @@ -155,15 +165,11 @@ cflags-$(CONFIG_CPU_R4300) += -march=r4300 -Wa,--trap cflags-$(CONFIG_CPU_VR41XX) += -march=r4100 -Wa,--trap cflags-$(CONFIG_CPU_R4X00) += -march=r4600 -Wa,--trap cflags-$(CONFIG_CPU_TX49XX) += -march=r4600 -Wa,--trap -cflags-$(CONFIG_CPU_MIPS32_R1) += $(call cc-option,-march=mips32,-mips32 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \ - -Wa,-mips32 -Wa,--trap -cflags-$(CONFIG_CPU_MIPS32_R2) += $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \ - -Wa,-mips32r2 -Wa,--trap +cflags-$(CONFIG_CPU_MIPS32_R1) += -march=mips32 -Wa,--trap +cflags-$(CONFIG_CPU_MIPS32_R2) += -march=mips32r2 -Wa,--trap cflags-$(CONFIG_CPU_MIPS32_R6) += -march=mips32r6 -Wa,--trap -modd-spreg -cflags-$(CONFIG_CPU_MIPS64_R1) += $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \ - -Wa,-mips64 -Wa,--trap -cflags-$(CONFIG_CPU_MIPS64_R2) += $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \ - -Wa,-mips64r2 -Wa,--trap +cflags-$(CONFIG_CPU_MIPS64_R1) += -march=mips64 -Wa,--trap +cflags-$(CONFIG_CPU_MIPS64_R2) += -march=mips64r2 -Wa,--trap cflags-$(CONFIG_CPU_MIPS64_R6) += -march=mips64r6 -Wa,--trap cflags-$(CONFIG_CPU_R5000) += -march=r5000 -Wa,--trap cflags-$(CONFIG_CPU_R5432) += $(call cc-option,-march=r5400,-march=r5000) \ diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c index fa75d75b5ba9..ddff9a02513d 100644 --- a/arch/mips/alchemy/board-gpr.c +++ b/arch/mips/alchemy/board-gpr.c @@ -34,6 +34,7 @@ #include <asm/bootinfo.h> #include <asm/idle.h> #include <asm/reboot.h> +#include <asm/setup.h> #include <asm/mach-au1x00/au1000.h> #include <asm/mach-au1x00/gpio-au1000.h> #include <prom.h> @@ -60,7 +61,7 @@ void __init prom_init(void) add_memory_region(0, memsize, BOOT_MEM_RAM); } -void prom_putchar(unsigned char c) +void prom_putchar(char c) { alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c); } diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c index aab55aaf3d62..d625e6f99ae7 100644 --- a/arch/mips/alchemy/board-mtx1.c +++ b/arch/mips/alchemy/board-mtx1.c @@ -31,6 +31,7 @@ #include <mtd/mtd-abi.h> #include <asm/bootinfo.h> #include <asm/reboot.h> +#include <asm/setup.h> #include <asm/mach-au1x00/au1000.h> #include <asm/mach-au1x00/gpio-au1000.h> #include <asm/mach-au1x00/au1xxx_eth.h> @@ -58,7 +59,7 @@ void __init prom_init(void) add_memory_region(0, memsize, BOOT_MEM_RAM); } -void prom_putchar(unsigned char c) +void prom_putchar(char c) { alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c); } diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c index 0fc53e08a894..5f05b8714385 100644 --- a/arch/mips/alchemy/board-xxs1500.c +++ b/arch/mips/alchemy/board-xxs1500.c @@ -29,6 +29,7 @@ #include <linux/pm.h> #include <asm/bootinfo.h> #include <asm/reboot.h> +#include <asm/setup.h> #include <asm/mach-au1x00/au1000.h> #include <prom.h> @@ -55,7 +56,7 @@ void __init prom_init(void) add_memory_region(0, memsize, BOOT_MEM_RAM); } -void prom_putchar(unsigned char c) +void prom_putchar(char c) { alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c); } diff --git a/arch/mips/alchemy/devboards/platform.c b/arch/mips/alchemy/devboards/platform.c index 203854ddd1bb..8d4b65c3268a 100644 --- a/arch/mips/alchemy/devboards/platform.c +++ b/arch/mips/alchemy/devboards/platform.c @@ -14,6 +14,7 @@ #include <asm/bootinfo.h> #include <asm/idle.h> #include <asm/reboot.h> +#include <asm/setup.h> #include <asm/mach-au1x00/au1000.h> #include <asm/mach-db1x00/bcsr.h> @@ -36,7 +37,7 @@ void __init prom_init(void) add_memory_region(0, memsize, BOOT_MEM_RAM); } -void prom_putchar(unsigned char c) +void prom_putchar(char c) { if (alchemy_get_cputype() == ALCHEMY_CPU_AU1300) alchemy_uart_putchar(AU1300_UART2_PHYS_ADDR, c); diff --git a/arch/mips/ar7/clock.c b/arch/mips/ar7/clock.c index 0137656107a9..6b64fd96dba8 100644 --- a/arch/mips/ar7/clock.c +++ b/arch/mips/ar7/clock.c @@ -476,3 +476,32 @@ void __init ar7_init_clocks(void) /* adjust vbus clock rate */ vbus_clk.rate = bus_clk.rate / 2; } + +/* dummy functions, should not be called */ +long clk_round_rate(struct clk *clk, unsigned long rate) +{ + WARN_ON(clk); + return 0; +} +EXPORT_SYMBOL(clk_round_rate); + +int clk_set_rate(struct clk *clk, unsigned long rate) +{ + WARN_ON(clk); + return 0; +} +EXPORT_SYMBOL(clk_set_rate); + +int clk_set_parent(struct clk *clk, struct clk *parent) +{ + WARN_ON(clk); + return 0; +} +EXPORT_SYMBOL(clk_set_parent); + +struct clk *clk_get_parent(struct clk *clk) +{ + WARN_ON(clk); + return NULL; +} +EXPORT_SYMBOL(clk_get_parent); diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c index dd53987a690f..2ec8d9ac91ec 100644 --- a/arch/mips/ar7/prom.c +++ b/arch/mips/ar7/prom.c @@ -25,6 +25,7 @@ #include <linux/string.h> #include <linux/io.h> #include <asm/bootinfo.h> +#include <asm/setup.h> #include <asm/mach-ar7/ar7.h> #include <asm/mach-ar7/prom.h> @@ -259,10 +260,9 @@ static inline void serial_out(int offset, int value) writel(value, (void *)PORT(offset)); } -int prom_putchar(char c) +void prom_putchar(char c) { while ((serial_in(UART_LSR) & UART_LSR_TEMT) == 0) ; serial_out(UART_TX, c); - return 1; } diff --git a/arch/mips/ath25/Kconfig b/arch/mips/ath25/Kconfig index 7070b4bcd01d..2c1dfd06c366 100644 --- a/arch/mips/ath25/Kconfig +++ b/arch/mips/ath25/Kconfig @@ -12,6 +12,7 @@ config SOC_AR2315 config PCI_AR2315 bool "Atheros AR2315 PCI controller support" depends on SOC_AR2315 + select ARCH_HAS_PHYS_TO_DMA select HW_HAS_PCI select PCI default y diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c index 6d11ae581ea7..989e71015ee6 100644 --- a/arch/mips/ath25/board.c +++ b/arch/mips/ath25/board.c @@ -146,10 +146,10 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size) pr_info("Fixing up empty mac addresses\n"); config->reset_config_gpio = 0xffff; config->sys_led_gpio = 0xffff; - random_ether_addr(config->wlan0_mac); + eth_random_addr(config->wlan0_mac); config->wlan0_mac[0] &= ~0x06; - random_ether_addr(config->enet0_mac); - random_ether_addr(config->enet1_mac); + eth_random_addr(config->enet0_mac); + eth_random_addr(config->enet1_mac); } } diff --git a/arch/mips/ath25/early_printk.c b/arch/mips/ath25/early_printk.c index 36035b628161..d534761e9cda 100644 --- a/arch/mips/ath25/early_printk.c +++ b/arch/mips/ath25/early_printk.c @@ -9,6 +9,7 @@ #include <linux/mm.h> #include <linux/io.h> #include <linux/serial_reg.h> +#include <asm/setup.h> #include "devices.h" #include "ar2315_regs.h" @@ -25,7 +26,7 @@ static inline unsigned char prom_uart_rr(void __iomem *base, unsigned reg) return __raw_readl(base + 4 * reg); } -void prom_putchar(unsigned char ch) +void prom_putchar(char ch) { static void __iomem *base; @@ -38,7 +39,7 @@ void prom_putchar(unsigned char ch) while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0) ; - prom_uart_wr(base, UART_TX, ch); + prom_uart_wr(base, UART_TX, (unsigned char)ch); while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0) ; } diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c index 6b1000b6a6a6..cf9158e3c2d9 100644 --- a/arch/mips/ath79/clock.c +++ b/arch/mips/ath79/clock.c @@ -355,6 +355,91 @@ static void __init ar934x_clocks_init(void) iounmap(dpll_base); } +static void __init qca953x_clocks_init(void) +{ + unsigned long ref_rate; + unsigned long cpu_rate; + unsigned long ddr_rate; + unsigned long ahb_rate; + u32 pll, out_div, ref_div, nint, frac, clk_ctrl, postdiv; + u32 cpu_pll, ddr_pll; + u32 bootstrap; + + bootstrap = ath79_reset_rr(QCA953X_RESET_REG_BOOTSTRAP); + if (bootstrap & QCA953X_BOOTSTRAP_REF_CLK_40) + ref_rate = 40 * 1000 * 1000; + else + ref_rate = 25 * 1000 * 1000; + + pll = ath79_pll_rr(QCA953X_PLL_CPU_CONFIG_REG); + out_div = (pll >> QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT) & + QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK; + ref_div = (pll >> QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT) & + QCA953X_PLL_CPU_CONFIG_REFDIV_MASK; + nint = (pll >> QCA953X_PLL_CPU_CONFIG_NINT_SHIFT) & + QCA953X_PLL_CPU_CONFIG_NINT_MASK; + frac = (pll >> QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT) & + QCA953X_PLL_CPU_CONFIG_NFRAC_MASK; + + cpu_pll = nint * ref_rate / ref_div; + cpu_pll += frac * (ref_rate >> 6) / ref_div; + cpu_pll /= (1 << out_div); + + pll = ath79_pll_rr(QCA953X_PLL_DDR_CONFIG_REG); + out_div = (pll >> QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT) & + QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK; + ref_div = (pll >> QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT) & + QCA953X_PLL_DDR_CONFIG_REFDIV_MASK; + nint = (pll >> QCA953X_PLL_DDR_CONFIG_NINT_SHIFT) & + QCA953X_PLL_DDR_CONFIG_NINT_MASK; + frac = (pll >> QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT) & + QCA953X_PLL_DDR_CONFIG_NFRAC_MASK; + + ddr_pll = nint * ref_rate / ref_div; + ddr_pll += frac * (ref_rate >> 6) / (ref_div << 4); + ddr_pll /= (1 << out_div); + + clk_ctrl = ath79_pll_rr(QCA953X_PLL_CLK_CTRL_REG); + + postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) & + QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK; + + if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS) + cpu_rate = ref_rate; + else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL) + cpu_rate = cpu_pll / (postdiv + 1); + else + cpu_rate = ddr_pll / (postdiv + 1); + + postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) & + QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK; + + if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS) + ddr_rate = ref_rate; + else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL) + ddr_rate = ddr_pll / (postdiv + 1); + else + ddr_rate = cpu_pll / (postdiv + 1); + + postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) & + QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK; + + if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS) + ahb_rate = ref_rate; + else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL) + ahb_rate = ddr_pll / (postdiv + 1); + else + ahb_rate = cpu_pll / (postdiv + 1); + + ath79_add_sys_clkdev("ref", ref_rate); + ath79_add_sys_clkdev("cpu", cpu_rate); + ath79_add_sys_clkdev("ddr", ddr_rate); + ath79_add_sys_clkdev("ahb", ahb_rate); + + clk_add_alias("wdt", NULL, "ref", NULL); + clk_add_alias("uart", NULL, "ref", NULL); +} + static void __init qca955x_clocks_init(void) { unsigned long ref_rate; @@ -440,6 +525,110 @@ static void __init qca955x_clocks_init(void) clk_add_alias("uart", NULL, "ref", NULL); } +static void __init qca956x_clocks_init(void) +{ + unsigned long ref_rate; + unsigned long cpu_rate; + unsigned long ddr_rate; + unsigned long ahb_rate; + u32 pll, out_div, ref_div, nint, hfrac, lfrac, clk_ctrl, postdiv; + u32 cpu_pll, ddr_pll; + u32 bootstrap; + + /* + * QCA956x timer init workaround has to be applied right before setting + * up the clock. Else, there will be no jiffies + */ + u32 misc; + + misc = ath79_reset_rr(AR71XX_RESET_REG_MISC_INT_ENABLE); + misc |= MISC_INT_MIPS_SI_TIMERINT_MASK; + ath79_reset_wr(AR71XX_RESET_REG_MISC_INT_ENABLE, misc); + + bootstrap = ath79_reset_rr(QCA956X_RESET_REG_BOOTSTRAP); + if (bootstrap & QCA956X_BOOTSTRAP_REF_CLK_40) + ref_rate = 40 * 1000 * 1000; + else + ref_rate = 25 * 1000 * 1000; + + pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG_REG); + out_div = (pll >> QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT) & + QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK; + ref_div = (pll >> QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT) & + QCA956X_PLL_CPU_CONFIG_REFDIV_MASK; + + pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG1_REG); + nint = (pll >> QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT) & + QCA956X_PLL_CPU_CONFIG1_NINT_MASK; + hfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT) & + QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK; + lfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT) & + QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK; + + cpu_pll = nint * ref_rate / ref_div; + cpu_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13); + cpu_pll += (hfrac >> 13) * ref_rate / ref_div; + cpu_pll /= (1 << out_div); + + pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG_REG); + out_div = (pll >> QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT) & + QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK; + ref_div = (pll >> QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT) & + QCA956X_PLL_DDR_CONFIG_REFDIV_MASK; + pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG1_REG); + nint = (pll >> QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT) & + QCA956X_PLL_DDR_CONFIG1_NINT_MASK; + hfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT) & + QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK; + lfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT) & + QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK; + + ddr_pll = nint * ref_rate / ref_div; + ddr_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13); + ddr_pll += (hfrac >> 13) * ref_rate / ref_div; + ddr_pll /= (1 << out_div); + + clk_ctrl = ath79_pll_rr(QCA956X_PLL_CLK_CTRL_REG); + + postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) & + QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK; + + if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS) + cpu_rate = ref_rate; + else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL) + cpu_rate = ddr_pll / (postdiv + 1); + else + cpu_rate = cpu_pll / (postdiv + 1); + + postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) & + QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK; + + if (clk_ctrl & QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS) + ddr_rate = ref_rate; + else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL) + ddr_rate = cpu_pll / (postdiv + 1); + else + ddr_rate = ddr_pll / (postdiv + 1); + + postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) & + QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK; + + if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS) + ahb_rate = ref_rate; + else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL) + ahb_rate = ddr_pll / (postdiv + 1); + else + ahb_rate = cpu_pll / (postdiv + 1); + + ath79_add_sys_clkdev("ref", ref_rate); + ath79_add_sys_clkdev("cpu", cpu_rate); + ath79_add_sys_clkdev("ddr", ddr_rate); + ath79_add_sys_clkdev("ahb", ahb_rate); + + clk_add_alias("wdt", NULL, "ref", NULL); + clk_add_alias("uart", NULL, "ref", NULL); +} + void __init ath79_clocks_init(void) { if (soc_is_ar71xx()) @@ -450,8 +639,12 @@ void __init ath79_clocks_init(void) ar933x_clocks_init(); else if (soc_is_ar934x()) ar934x_clocks_init(); + else if (soc_is_qca953x()) + qca953x_clocks_init(); else if (soc_is_qca955x()) qca955x_clocks_init(); + else if (soc_is_qca956x() || soc_is_tp9343()) + qca956x_clocks_init(); else BUG(); } diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c index 10a405d593df..cd6055f9e7a0 100644 --- a/arch/mips/ath79/common.c +++ b/arch/mips/ath79/common.c @@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init); void ath79_ddr_wb_flush(u32 reg) { - void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg; + void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4); /* Flush the DDR write buffer. */ __raw_writel(0x1, flush_reg); @@ -103,8 +103,12 @@ void ath79_device_reset_set(u32 mask) reg = AR933X_RESET_REG_RESET_MODULE; else if (soc_is_ar934x()) reg = AR934X_RESET_REG_RESET_MODULE; + else if (soc_is_qca953x()) + reg = QCA953X_RESET_REG_RESET_MODULE; else if (soc_is_qca955x()) reg = QCA955X_RESET_REG_RESET_MODULE; + else if (soc_is_qca956x() || soc_is_tp9343()) + reg = QCA956X_RESET_REG_RESET_MODULE; else BUG(); @@ -131,8 +135,12 @@ void ath79_device_reset_clear(u32 mask) reg = AR933X_RESET_REG_RESET_MODULE; else if (soc_is_ar934x()) reg = AR934X_RESET_REG_RESET_MODULE; + else if (soc_is_qca953x()) + reg = QCA953X_RESET_REG_RESET_MODULE; else if (soc_is_qca955x()) reg = QCA955X_RESET_REG_RESET_MODULE; + else if (soc_is_qca956x() || soc_is_tp9343()) + reg = QCA956X_RESET_REG_RESET_MODULE; else BUG(); diff --git a/arch/mips/ath79/early_printk.c b/arch/mips/ath79/early_printk.c index d1adc59af5bf..4b1063117ef7 100644 --- a/arch/mips/ath79/early_printk.c +++ b/arch/mips/ath79/early_printk.c @@ -13,12 +13,13 @@ #include <linux/errno.h> #include <linux/serial_reg.h> #include <asm/addrspace.h> +#include <asm/setup.h> #include <asm/mach-ath79/ath79.h> #include <asm/mach-ath79/ar71xx_regs.h> #include <asm/mach-ath79/ar933x_uart.h> -static void (*_prom_putchar) (unsigned char); +static void (*_prom_putchar)(char); static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val) { @@ -33,31 +34,72 @@ static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val) #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) -static void prom_putchar_ar71xx(unsigned char ch) +static void prom_putchar_ar71xx(char ch) { void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE)); prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY); - __raw_writel(ch, base + UART_TX * 4); + __raw_writel((unsigned char)ch, base + UART_TX * 4); prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY); } -static void prom_putchar_ar933x(unsigned char ch) +static void prom_putchar_ar933x(char ch) { void __iomem *base = (void __iomem *)(KSEG1ADDR(AR933X_UART_BASE)); prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR, AR933X_UART_DATA_TX_CSR); - __raw_writel(AR933X_UART_DATA_TX_CSR | ch, base + AR933X_UART_DATA_REG); + __raw_writel(AR933X_UART_DATA_TX_CSR | (unsigned char)ch, + base + AR933X_UART_DATA_REG); prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR, AR933X_UART_DATA_TX_CSR); } -static void prom_putchar_dummy(unsigned char ch) +static void prom_putchar_dummy(char ch) { /* nothing to do */ } +static void prom_enable_uart(u32 id) +{ + void __iomem *gpio_base; + u32 uart_en; + u32 t; + + switch (id) { + case REV_ID_MAJOR_AR71XX: + uart_en = AR71XX_GPIO_FUNC_UART_EN; + break; + + case REV_ID_MAJOR_AR7240: + case REV_ID_MAJOR_AR7241: + case REV_ID_MAJOR_AR7242: + uart_en = AR724X_GPIO_FUNC_UART_EN; + break; + + case REV_ID_MAJOR_AR913X: + uart_en = AR913X_GPIO_FUNC_UART_EN; + break; + + case REV_ID_MAJOR_AR9330: + case REV_ID_MAJOR_AR9331: + uart_en = AR933X_GPIO_FUNC_UART_EN; + break; + + case REV_ID_MAJOR_AR9341: + case REV_ID_MAJOR_AR9342: + case REV_ID_MAJOR_AR9344: + /* TODO */ + default: + return; + } + + gpio_base = (void __iomem *)KSEG1ADDR(AR71XX_GPIO_BASE); + t = __raw_readl(gpio_base + AR71XX_GPIO_REG_FUNC); + t |= uart_en; + __raw_writel(t, gpio_base + AR71XX_GPIO_REG_FUNC); +} + static void prom_putchar_init(void) { void __iomem *base; @@ -76,8 +118,12 @@ static void prom_putchar_init(void) case REV_ID_MAJOR_AR9341: case REV_ID_MAJOR_AR9342: case REV_ID_MAJOR_AR9344: + case REV_ID_MAJOR_QCA9533: + case REV_ID_MAJOR_QCA9533_V2: case REV_ID_MAJOR_QCA9556: case REV_ID_MAJOR_QCA9558: + case REV_ID_MAJOR_TP9343: + case REV_ID_MAJOR_QCA956X: _prom_putchar = prom_putchar_ar71xx; break; @@ -88,11 +134,13 @@ static void prom_putchar_init(void) default: _prom_putchar = prom_putchar_dummy; - break; + return; } + + prom_enable_uart(id); } -void prom_putchar(unsigned char ch) +void prom_putchar(char ch) { if (!_prom_putchar) prom_putchar_init(); diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index f206dafbb0a3..4c7a93f4039a 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -40,6 +40,7 @@ static char ath79_sys_type[ATH79_SYS_TYPE_LEN]; static void ath79_restart(char *command) { + local_irq_disable(); ath79_device_reset_set(AR71XX_RESET_FULL_CHIP); for (;;) if (cpu_wait) @@ -59,6 +60,7 @@ static void __init ath79_detect_sys_type(void) u32 major; u32 minor; u32 rev = 0; + u32 ver = 1; id = ath79_reset_rr(AR71XX_RESET_REG_REV_ID); major = id & REV_ID_MAJOR_MASK; @@ -151,6 +153,17 @@ static void __init ath79_detect_sys_type(void) rev = id & AR934X_REV_ID_REVISION_MASK; break; + case REV_ID_MAJOR_QCA9533_V2: + ver = 2; + ath79_soc_rev = 2; + /* drop through */ + + case REV_ID_MAJOR_QCA9533: + ath79_soc = ATH79_SOC_QCA9533; + chip = "9533"; + rev = id & QCA953X_REV_ID_REVISION_MASK; + break; + case REV_ID_MAJOR_QCA9556: ath79_soc = ATH79_SOC_QCA9556; chip = "9556"; @@ -163,14 +176,30 @@ static void __init ath79_detect_sys_type(void) rev = id & QCA955X_REV_ID_REVISION_MASK; break; + case REV_ID_MAJOR_QCA956X: + ath79_soc = ATH79_SOC_QCA956X; + chip = "956X"; + rev = id & QCA956X_REV_ID_REVISION_MASK; + break; + + case REV_ID_MAJOR_TP9343: + ath79_soc = ATH79_SOC_TP9343; + chip = "9343"; + rev = id & QCA956X_REV_ID_REVISION_MASK; + break; + default: panic("ath79: unknown SoC, id:0x%08x", id); } - ath79_soc_rev = rev; + if (ver == 1) + ath79_soc_rev = rev; - if (soc_is_qca955x()) - sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s rev %u", + if (soc_is_qca953x() || soc_is_qca955x() || soc_is_qca956x()) + sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s ver %u rev %u", + chip, ver, rev); + else if (soc_is_tp9343()) + sprintf(ath79_sys_type, "Qualcomm Atheros TP%s rev %u", chip, rev); else sprintf(ath79_sys_type, "Atheros AR%s rev %u", chip, rev); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 8c9cbf13d32a..6054d49e608e 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -212,12 +212,6 @@ static int __init bcm47xx_cpu_fixes(void) */ if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706) cpu_wait = NULL; - - /* - * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail" - * Enable ExternalSync for sync instruction to take effect - */ - set_c0_config7(MIPS_CONF7_ES); break; #endif } diff --git a/arch/mips/bcm63xx/early_printk.c b/arch/mips/bcm63xx/early_printk.c index 6092226a6d76..9e9ec27c282f 100644 --- a/arch/mips/bcm63xx/early_printk.c +++ b/arch/mips/bcm63xx/early_printk.c @@ -8,6 +8,7 @@ #include <bcm63xx_io.h> #include <linux/serial_bcm63xx.h> +#include <asm/setup.h> static void wait_xfered(void) { diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c index 6dec30842b2f..3d13c77c125f 100644 --- a/arch/mips/bmips/dma.c +++ b/arch/mips/bmips/dma.c @@ -17,7 +17,7 @@ #include <linux/printk.h> #include <linux/slab.h> #include <linux/types.h> -#include <dma-coherence.h> +#include <asm/bmips.h> /* * BCM338x has configurable address translation windows which allow the @@ -40,7 +40,7 @@ static struct bmips_dma_range *bmips_dma_ranges; #define FLUSH_RAC 0x100 -static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa) +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa) { struct bmips_dma_range *r; @@ -52,17 +52,7 @@ static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa) return pa; } -dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size) -{ - return bmips_phys_to_dma(dev, virt_to_phys(addr)); -} - -dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page) -{ - return bmips_phys_to_dma(dev, page_to_phys(page)); -} - -unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr) +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr) { struct bmips_dma_range *r; @@ -74,6 +64,22 @@ unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr) return dma_addr; } +void arch_sync_dma_for_cpu_all(struct device *dev) +{ + void __iomem *cbr = BMIPS_GET_CBR(); + u32 cfg; + + if (boot_cpu_type() != CPU_BMIPS3300 && + boot_cpu_type() != CPU_BMIPS4350 && + boot_cpu_type() != CPU_BMIPS4380) + return; + + /* Flush stale data out of the readahead cache */ + cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG); + __raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG); + __raw_readl(cbr + BMIPS_RAC_CONFIG); +} + static int __init bmips_init_dma_ranges(void) { struct device_node *np = diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index 3b6f687f177c..231fc5ce375e 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -202,13 +202,6 @@ void __init device_tree_init(void) of_node_put(np); } -int __init plat_of_setup(void) -{ - return __dt_register_buses("simple-bus", NULL); -} - -arch_initcall(plat_of_setup); - static int __init plat_dev_init(void) { of_clk_init(NULL); diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile index c22da16d67b8..35704c28a28b 100644 --- a/arch/mips/boot/Makefile +++ b/arch/mips/boot/Makefile @@ -105,28 +105,29 @@ $(obj)/uImage: $(obj)/uImage.$(suffix-y) # Flattened Image Tree (.itb) images # -targets += vmlinux.itb -targets += vmlinux.gz.itb -targets += vmlinux.bz2.itb -targets += vmlinux.lzma.itb -targets += vmlinux.lzo.itb - ifeq ($(ADDR_BITS),32) - itb_addr_cells = 1 +itb_addr_cells = 1 endif ifeq ($(ADDR_BITS),64) - itb_addr_cells = 2 +itb_addr_cells = 2 endif +targets += vmlinux.its.S + quiet_cmd_its_cat = CAT $@ - cmd_its_cat = cat $^ >$@ + cmd_its_cat = cat $(filter-out $(PHONY), $^) >$@ -$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS)) +$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS)) FORCE $(call if_changed,its_cat) +targets += vmlinux.its +targets += vmlinux.gz.its +targets += vmlinux.bz2.its +targets += vmlinux.lzmo.its +targets += vmlinux.lzo.its + quiet_cmd_cpp_its_S = ITS $@ - cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \ - -D__ASSEMBLY__ \ + cmd_cpp_its_S = $(CPP) -P -C -o $@ $< \ -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \ -DVMLINUX_BINARY="\"$(3)\"" \ -DVMLINUX_COMPRESSION="\"$(2)\"" \ @@ -136,19 +137,25 @@ quiet_cmd_cpp_its_S = ITS $@ -DADDR_CELLS=$(itb_addr_cells) $(obj)/vmlinux.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE - $(call if_changed_dep,cpp_its_S,none,vmlinux.bin) + $(call if_changed,cpp_its_S,none,vmlinux.bin) $(obj)/vmlinux.gz.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE - $(call if_changed_dep,cpp_its_S,gzip,vmlinux.bin.gz) + $(call if_changed,cpp_its_S,gzip,vmlinux.bin.gz) $(obj)/vmlinux.bz2.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE - $(call if_changed_dep,cpp_its_S,bzip2,vmlinux.bin.bz2) + $(call if_changed,cpp_its_S,bzip2,vmlinux.bin.bz2) $(obj)/vmlinux.lzma.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE - $(call if_changed_dep,cpp_its_S,lzma,vmlinux.bin.lzma) + $(call if_changed,cpp_its_S,lzma,vmlinux.bin.lzma) $(obj)/vmlinux.lzo.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE - $(call if_changed_dep,cpp_its_S,lzo,vmlinux.bin.lzo) + $(call if_changed,cpp_its_S,lzo,vmlinux.bin.lzo) + +targets += vmlinux.itb +targets += vmlinux.gz.itb +targets += vmlinux.bz2.itb +targets += vmlinux.lzma.itb +targets += vmlinux.lzo.itb quiet_cmd_itb-image = ITB $@ cmd_itb-image = \ @@ -162,14 +169,5 @@ quiet_cmd_itb-image = ITB $@ $(obj)/vmlinux.itb: $(obj)/vmlinux.its $(obj)/vmlinux.bin FORCE $(call if_changed,itb-image,$<) -$(obj)/vmlinux.gz.itb: $(obj)/vmlinux.gz.its $(obj)/vmlinux.bin.gz FORCE - $(call if_changed,itb-image,$<) - -$(obj)/vmlinux.bz2.itb: $(obj)/vmlinux.bz2.its $(obj)/vmlinux.bin.bz2 FORCE - $(call if_changed,itb-image,$<) - -$(obj)/vmlinux.lzma.itb: $(obj)/vmlinux.lzma.its $(obj)/vmlinux.bin.lzma FORCE - $(call if_changed,itb-image,$<) - -$(obj)/vmlinux.lzo.itb: $(obj)/vmlinux.lzo.its $(obj)/vmlinux.bin.lzo FORCE +$(obj)/vmlinux.%.itb: $(obj)/vmlinux.%.its $(obj)/vmlinux.bin.% FORCE $(call if_changed,itb-image,$<) diff --git a/arch/mips/boot/compressed/uart-prom.c b/arch/mips/boot/compressed/uart-prom.c index d6f0fee0a151..a8a0a32e05d1 100644 --- a/arch/mips/boot/compressed/uart-prom.c +++ b/arch/mips/boot/compressed/uart-prom.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 - -extern void prom_putchar(unsigned char ch); +#include <asm/setup.h> void putc(char c) { diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index aa4e8f75ff5d..ce93d57f1b4d 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -155,6 +155,25 @@ }; }; + spi_gpio { + compatible = "spi-gpio"; + #address-cells = <1>; + #size-cells = <0>; + num-chipselects = <2>; + + gpio-miso = <&gpe 14 0>; + gpio-sck = <&gpe 15 0>; + gpio-mosi = <&gpe 17 0>; + cs-gpios = <&gpe 16 0 + &gpe 18 0>; + + spidev@0 { + compatible = "spidev"; + reg = <0>; + spi-max-frequency = <1000000>; + }; + }; + uart0: serial@10030000 { compatible = "ingenic,jz4780-uart"; reg = <0x10030000 0x100>; diff --git a/arch/mips/boot/dts/mscc/Makefile b/arch/mips/boot/dts/mscc/Makefile index 3c6aed9f5439..9a9bb7ea0503 100644 --- a/arch/mips/boot/dts/mscc/Makefile +++ b/arch/mips/boot/dts/mscc/Makefile @@ -1,3 +1,3 @@ -dtb-$(CONFIG_LEGACY_BOARD_OCELOT) += ocelot_pcb123.dtb +dtb-$(CONFIG_MSCC_OCELOT) += ocelot_pcb123.dtb obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi index 4f33dbc67348..f7eb612b46ba 100644 --- a/arch/mips/boot/dts/mscc/ocelot.dtsi +++ b/arch/mips/boot/dts/mscc/ocelot.dtsi @@ -91,6 +91,17 @@ status = "disabled"; }; + spi: spi@101000 { + compatible = "mscc,ocelot-spi", "snps,dw-apb-ssi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x101000 0x100>, <0x3c 0x18>; + interrupts = <9>; + clocks = <&ahb_clk>; + + status = "disabled"; + }; + switch@1010000 { compatible = "mscc,vsc7514-switch"; reg = <0x1010000 0x10000>, @@ -168,6 +179,9 @@ gpio-controller; #gpio-cells = <2>; gpio-ranges = <&gpio 0 0 22>; + interrupt-controller; + interrupts = <13>; + #interrupt-cells = <2>; uart_pins: uart-pins { pins = "GPIO_6", "GPIO_7"; @@ -178,13 +192,18 @@ pins = "GPIO_12", "GPIO_13"; function = "uart2"; }; + + miim1: miim1 { + pins = "GPIO_14", "GPIO_15"; + function = "miim1"; + }; }; mdio0: mdio@107009c { #address-cells = <1>; #size-cells = <0>; compatible = "mscc,ocelot-miim"; - reg = <0x107009c 0x36>, <0x10700f0 0x8>; + reg = <0x107009c 0x24>, <0x10700f0 0x8>; interrupts = <14>; status = "disabled"; @@ -201,5 +220,16 @@ reg = <3>; }; }; + + mdio1: mdio@10700c0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "mscc,ocelot-miim"; + reg = <0x10700c0 0x24>; + interrupts = <15>; + pinctrl-names = "default"; + pinctrl-0 = <&miim1>; + status = "disabled"; + }; }; }; diff --git a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts index 4ccd65379059..2266027759f9 100644 --- a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts +++ b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts @@ -26,6 +26,16 @@ status = "okay"; }; +&spi { + status = "okay"; + + flash@0 { + compatible = "macronix,mx25l25635f", "jedec,spi-nor"; + spi-max-frequency = <20000000>; + reg = <0>; + }; +}; + &mdio0 { status = "okay"; }; diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi index 1fe561c5f90e..61dcfa5b6ca7 100644 --- a/arch/mips/boot/dts/qca/ar9132.dtsi +++ b/arch/mips/boot/dts/qca/ar9132.dtsi @@ -161,7 +161,7 @@ usb_phy: usb-phy { compatible = "qca,ar7100-usb-phy"; - reset-names = "usb-phy", "usb-suspend-override"; + reset-names = "phy", "suspend-override"; resets = <&rst 4>, <&rst 3>; #phy-cells = <0>; diff --git a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts index 3931033e47c8..7fccf6357225 100644 --- a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts +++ b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts @@ -22,11 +22,10 @@ }; gpio-keys { - compatible = "gpio-keys-polled"; + compatible = "gpio-keys"; #address-cells = <1>; #size-cells = <0>; - poll-interval = <20>; button@0 { label = "reset"; linux,code = <KEY_RESTART>; diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi index efd5f0722206..2bae201aa365 100644 --- a/arch/mips/boot/dts/qca/ar9331.dtsi +++ b/arch/mips/boot/dts/qca/ar9331.dtsi @@ -146,7 +146,7 @@ usb_phy: usb-phy { compatible = "qca,ar7100-usb-phy"; - reset-names = "usb-phy", "usb-suspend-override"; + reset-names = "phy", "suspend-override"; resets = <&rst 4>, <&rst 3>; #phy-cells = <0>; diff --git a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts index d4e4502daaa8..e7af2cf5f4c1 100644 --- a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts +++ b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts @@ -29,11 +29,10 @@ }; }; - gpio-keys-polled { - compatible = "gpio-keys-polled"; + gpio-keys { + compatible = "gpio-keys"; #address-cells = <1>; #size-cells = <0>; - poll-interval = <100>; button@0 { label = "reset"; diff --git a/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts b/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts index 4f95ccf17c4c..d38aa73f1a2e 100644 --- a/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts +++ b/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts @@ -47,11 +47,10 @@ }; }; - gpio-keys-polled { - compatible = "gpio-keys-polled"; + gpio-keys { + compatible = "gpio-keys"; #address-cells = <1>; #size-cells = <0>; - poll-interval = <100>; button@0 { label = "jumpstart"; diff --git a/arch/mips/boot/dts/qca/ar9331_omega.dts b/arch/mips/boot/dts/qca/ar9331_omega.dts index f70f79c4d0d5..11778abacf66 100644 --- a/arch/mips/boot/dts/qca/ar9331_omega.dts +++ b/arch/mips/boot/dts/qca/ar9331_omega.dts @@ -29,11 +29,10 @@ }; }; - gpio-keys-polled { - compatible = "gpio-keys-polled"; + gpio-keys { + compatible = "gpio-keys"; #address-cells = <1>; #size-cells = <0>; - poll-interval = <100>; button@0 { label = "reset"; diff --git a/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts b/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts index 748131aea22e..c8290d36cfbe 100644 --- a/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts +++ b/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts @@ -47,11 +47,10 @@ }; }; - gpio-keys-polled { - compatible = "gpio-keys-polled"; + gpio-keys { + compatible = "gpio-keys"; #address-cells = <1>; #size-cells = <0>; - poll-interval = <100>; button@0 { label = "wps"; diff --git a/arch/mips/boot/ecoff.h b/arch/mips/boot/ecoff.h index b3e73c22c345..5be79ebfc3f8 100644 --- a/arch/mips/boot/ecoff.h +++ b/arch/mips/boot/ecoff.h @@ -2,14 +2,17 @@ /* * Some ECOFF definitions. */ + +#include <stdint.h> + typedef struct filehdr { - unsigned short f_magic; /* magic number */ - unsigned short f_nscns; /* number of sections */ - long f_timdat; /* time & date stamp */ - long f_symptr; /* file pointer to symbolic header */ - long f_nsyms; /* sizeof(symbolic hdr) */ - unsigned short f_opthdr; /* sizeof(optional hdr) */ - unsigned short f_flags; /* flags */ + uint16_t f_magic; /* magic number */ + uint16_t f_nscns; /* number of sections */ + int32_t f_timdat; /* time & date stamp */ + int32_t f_symptr; /* file pointer to symbolic header */ + int32_t f_nsyms; /* sizeof(symbolic hdr) */ + uint16_t f_opthdr; /* sizeof(optional hdr) */ + uint16_t f_flags; /* flags */ } FILHDR; #define FILHSZ sizeof(FILHDR) @@ -18,32 +21,32 @@ typedef struct filehdr { typedef struct scnhdr { char s_name[8]; /* section name */ - long s_paddr; /* physical address, aliased s_nlib */ - long s_vaddr; /* virtual address */ - long s_size; /* section size */ - long s_scnptr; /* file ptr to raw data for section */ - long s_relptr; /* file ptr to relocation */ - long s_lnnoptr; /* file ptr to gp histogram */ - unsigned short s_nreloc; /* number of relocation entries */ - unsigned short s_nlnno; /* number of gp histogram entries */ - long s_flags; /* flags */ + int32_t s_paddr; /* physical address, aliased s_nlib */ + int32_t s_vaddr; /* virtual address */ + int32_t s_size; /* section size */ + int32_t s_scnptr; /* file ptr to raw data for section */ + int32_t s_relptr; /* file ptr to relocation */ + int32_t s_lnnoptr; /* file ptr to gp histogram */ + uint16_t s_nreloc; /* number of relocation entries */ + uint16_t s_nlnno; /* number of gp histogram entries */ + int32_t s_flags; /* flags */ } SCNHDR; #define SCNHSZ sizeof(SCNHDR) -#define SCNROUND ((long)16) +#define SCNROUND ((int32_t)16) typedef struct aouthdr { - short magic; /* see above */ - short vstamp; /* version stamp */ - long tsize; /* text size in bytes, padded to DW bdry*/ - long dsize; /* initialized data " " */ - long bsize; /* uninitialized data " " */ - long entry; /* entry pt. */ - long text_start; /* base of text used for this file */ - long data_start; /* base of data used for this file */ - long bss_start; /* base of bss used for this file */ - long gprmask; /* general purpose register mask */ - long cprmask[4]; /* co-processor register masks */ - long gp_value; /* the gp value used for this object */ + int16_t magic; /* see above */ + int16_t vstamp; /* version stamp */ + int32_t tsize; /* text size in bytes, padded to DW bdry*/ + int32_t dsize; /* initialized data " " */ + int32_t bsize; /* uninitialized data " " */ + int32_t entry; /* entry pt. */ + int32_t text_start; /* base of text used for this file */ + int32_t data_start; /* base of data used for this file */ + int32_t bss_start; /* base of bss used for this file */ + int32_t gprmask; /* general purpose register mask */ + int32_t cprmask[4]; /* co-processor register masks */ + int32_t gp_value; /* the gp value used for this object */ } AOUTHDR; #define AOUTHSZ sizeof(AOUTHDR) diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c index 266c8137e859..6972b97235da 100644 --- a/arch/mips/boot/elf2ecoff.c +++ b/arch/mips/boot/elf2ecoff.c @@ -43,6 +43,8 @@ #include <limits.h> #include <netinet/in.h> #include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> #include "ecoff.h" @@ -55,8 +57,8 @@ /* -------------------------------------------------------------------- */ struct sect { - unsigned long vaddr; - unsigned long len; + uint32_t vaddr; + uint32_t len; }; int *symTypeTable; @@ -153,16 +155,16 @@ static char *saveRead(int file, off_t offset, off_t len, char *name) } #define swab16(x) \ - ((unsigned short)( \ - (((unsigned short)(x) & (unsigned short)0x00ffU) << 8) | \ - (((unsigned short)(x) & (unsigned short)0xff00U) >> 8) )) + ((uint16_t)( \ + (((uint16_t)(x) & (uint16_t)0x00ffU) << 8) | \ + (((uint16_t)(x) & (uint16_t)0xff00U) >> 8) )) #define swab32(x) \ ((unsigned int)( \ - (((unsigned int)(x) & (unsigned int)0x000000ffUL) << 24) | \ - (((unsigned int)(x) & (unsigned int)0x0000ff00UL) << 8) | \ - (((unsigned int)(x) & (unsigned int)0x00ff0000UL) >> 8) | \ - (((unsigned int)(x) & (unsigned int)0xff000000UL) >> 24) )) + (((uint32_t)(x) & (uint32_t)0x000000ffUL) << 24) | \ + (((uint32_t)(x) & (uint32_t)0x0000ff00UL) << 8) | \ + (((uint32_t)(x) & (uint32_t)0x00ff0000UL) >> 8) | \ + (((uint32_t)(x) & (uint32_t)0xff000000UL) >> 24) )) static void convert_elf_hdr(Elf32_Ehdr * e) { @@ -274,7 +276,7 @@ int main(int argc, char *argv[]) struct aouthdr eah; struct scnhdr esecs[6]; int infile, outfile; - unsigned long cur_vma = ULONG_MAX; + uint32_t cur_vma = UINT32_MAX; int addflag = 0; int nosecs; @@ -518,7 +520,7 @@ int main(int argc, char *argv[]) for (i = 0; i < nosecs; i++) { printf - ("Section %d: %s phys %lx size %lx file offset %lx\n", + ("Section %d: %s phys %"PRIx32" size %"PRIx32"\t file offset %"PRIx32"\n", i, esecs[i].s_name, esecs[i].s_paddr, esecs[i].s_size, esecs[i].s_scnptr); } @@ -564,17 +566,16 @@ int main(int argc, char *argv[]) the section can be loaded before copying. */ if (ph[i].p_type == PT_LOAD && ph[i].p_filesz) { if (cur_vma != ph[i].p_vaddr) { - unsigned long gap = - ph[i].p_vaddr - cur_vma; + uint32_t gap = ph[i].p_vaddr - cur_vma; char obuf[1024]; if (gap > 65536) { fprintf(stderr, - "Intersegment gap (%ld bytes) too large.\n", + "Intersegment gap (%"PRId32" bytes) too large.\n", gap); exit(1); } fprintf(stderr, - "Warning: %ld byte intersegment gap.\n", + "Warning: %d byte intersegment gap.\n", gap); memset(obuf, 0, sizeof obuf); while (gap) { diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c index af4c712f7afc..d1ed066e1a17 100644 --- a/arch/mips/cavium-octeon/crypto/octeon-md5.c +++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c @@ -182,7 +182,6 @@ static struct shash_alg alg = { .cra_name = "md5", .cra_driver_name= "octeon-md5", .cra_priority = OCTEON_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = MD5_HMAC_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha1.c b/arch/mips/cavium-octeon/crypto/octeon-sha1.c index 2b74b5b67cae..80d71e775936 100644 --- a/arch/mips/cavium-octeon/crypto/octeon-sha1.c +++ b/arch/mips/cavium-octeon/crypto/octeon-sha1.c @@ -215,7 +215,6 @@ static struct shash_alg octeon_sha1_alg = { .cra_name = "sha1", .cra_driver_name= "octeon-sha1", .cra_priority = OCTEON_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha256.c b/arch/mips/cavium-octeon/crypto/octeon-sha256.c index 97e96fead08a..8b931e640926 100644 --- a/arch/mips/cavium-octeon/crypto/octeon-sha256.c +++ b/arch/mips/cavium-octeon/crypto/octeon-sha256.c @@ -239,7 +239,6 @@ static struct shash_alg octeon_sha256_algs[2] = { { .cra_name = "sha256", .cra_driver_name= "octeon-sha256", .cra_priority = OCTEON_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -252,7 +251,6 @@ static struct shash_alg octeon_sha256_algs[2] = { { .base = { .cra_name = "sha224", .cra_driver_name= "octeon-sha224", - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha512.c b/arch/mips/cavium-octeon/crypto/octeon-sha512.c index d5fb3c6f22ae..6c9561496257 100644 --- a/arch/mips/cavium-octeon/crypto/octeon-sha512.c +++ b/arch/mips/cavium-octeon/crypto/octeon-sha512.c @@ -235,7 +235,6 @@ static struct shash_alg octeon_sha512_algs[2] = { { .cra_name = "sha512", .cra_driver_name= "octeon-sha512", .cra_priority = OCTEON_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -249,7 +248,6 @@ static struct shash_alg octeon_sha512_algs[2] = { { .cra_name = "sha384", .cra_driver_name= "octeon-sha384", .cra_priority = OCTEON_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c index 7b335ab21697..236833be6fbe 100644 --- a/arch/mips/cavium-octeon/dma-octeon.c +++ b/arch/mips/cavium-octeon/dma-octeon.c @@ -11,9 +11,7 @@ * Copyright (C) 2010 Cavium Networks, Inc. */ #include <linux/dma-direct.h> -#include <linux/scatterlist.h> #include <linux/bootmem.h> -#include <linux/export.h> #include <linux/swiotlb.h> #include <linux/types.h> #include <linux/init.h> @@ -24,10 +22,16 @@ #include <asm/octeon/octeon.h> #ifdef CONFIG_PCI +#include <linux/pci.h> #include <asm/octeon/pci-octeon.h> #include <asm/octeon/cvmx-npi-defs.h> #include <asm/octeon/cvmx-pci-defs.h> +struct octeon_dma_map_ops { + dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr); + phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr); +}; + static dma_addr_t octeon_hole_phys_to_dma(phys_addr_t paddr) { if (paddr >= CVMX_PCIE_BAR1_PHYS_BASE && paddr < (CVMX_PCIE_BAR1_PHYS_BASE + CVMX_PCIE_BAR1_PHYS_SIZE)) @@ -61,6 +65,11 @@ static phys_addr_t octeon_gen1_dma_to_phys(struct device *dev, dma_addr_t daddr) return daddr; } +static const struct octeon_dma_map_ops octeon_gen1_ops = { + .phys_to_dma = octeon_gen1_phys_to_dma, + .dma_to_phys = octeon_gen1_dma_to_phys, +}; + static dma_addr_t octeon_gen2_phys_to_dma(struct device *dev, phys_addr_t paddr) { return octeon_hole_phys_to_dma(paddr); @@ -71,6 +80,11 @@ static phys_addr_t octeon_gen2_dma_to_phys(struct device *dev, dma_addr_t daddr) return octeon_hole_dma_to_phys(daddr); } +static const struct octeon_dma_map_ops octeon_gen2_ops = { + .phys_to_dma = octeon_gen2_phys_to_dma, + .dma_to_phys = octeon_gen2_dma_to_phys, +}; + static dma_addr_t octeon_big_phys_to_dma(struct device *dev, phys_addr_t paddr) { if (paddr >= 0x410000000ull && paddr < 0x420000000ull) @@ -93,6 +107,11 @@ static phys_addr_t octeon_big_dma_to_phys(struct device *dev, dma_addr_t daddr) return daddr; } +static const struct octeon_dma_map_ops octeon_big_ops = { + .phys_to_dma = octeon_big_phys_to_dma, + .dma_to_phys = octeon_big_dma_to_phys, +}; + static dma_addr_t octeon_small_phys_to_dma(struct device *dev, phys_addr_t paddr) { @@ -121,105 +140,51 @@ static phys_addr_t octeon_small_dma_to_phys(struct device *dev, return daddr; } -#endif /* CONFIG_PCI */ - -static dma_addr_t octeon_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction direction, - unsigned long attrs) -{ - dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size, - direction, attrs); - mb(); - - return daddr; -} - -static int octeon_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction direction, unsigned long attrs) -{ - int r = swiotlb_map_sg_attrs(dev, sg, nents, direction, attrs); - mb(); - return r; -} - -static void octeon_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) -{ - swiotlb_sync_single_for_device(dev, dma_handle, size, direction); - mb(); -} - -static void octeon_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nelems, enum dma_data_direction direction) -{ - swiotlb_sync_sg_for_device(dev, sg, nelems, direction); - mb(); -} - -static void *octeon_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) -{ - void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs); - - mb(); +static const struct octeon_dma_map_ops octeon_small_ops = { + .phys_to_dma = octeon_small_phys_to_dma, + .dma_to_phys = octeon_small_dma_to_phys, +}; - return ret; -} +static const struct octeon_dma_map_ops *octeon_pci_dma_ops; -static dma_addr_t octeon_unity_phys_to_dma(struct device *dev, phys_addr_t paddr) -{ - return paddr; -} - -static phys_addr_t octeon_unity_dma_to_phys(struct device *dev, dma_addr_t daddr) +void __init octeon_pci_dma_init(void) { - return daddr; + switch (octeon_dma_bar_type) { + case OCTEON_DMA_BAR_TYPE_PCIE: + octeon_pci_dma_ops = &octeon_gen1_ops; + break; + case OCTEON_DMA_BAR_TYPE_PCIE2: + octeon_pci_dma_ops = &octeon_gen2_ops; + break; + case OCTEON_DMA_BAR_TYPE_BIG: + octeon_pci_dma_ops = &octeon_big_ops; + break; + case OCTEON_DMA_BAR_TYPE_SMALL: + octeon_pci_dma_ops = &octeon_small_ops; + break; + default: + BUG(); + } } - -struct octeon_dma_map_ops { - const struct dma_map_ops dma_map_ops; - dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr); - phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr); -}; +#endif /* CONFIG_PCI */ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) { - struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev), - struct octeon_dma_map_ops, - dma_map_ops); - - return ops->phys_to_dma(dev, paddr); +#ifdef CONFIG_PCI + if (dev && dev_is_pci(dev)) + return octeon_pci_dma_ops->phys_to_dma(dev, paddr); +#endif + return paddr; } -EXPORT_SYMBOL(__phys_to_dma); phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr) { - struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev), - struct octeon_dma_map_ops, - dma_map_ops); - - return ops->dma_to_phys(dev, daddr); +#ifdef CONFIG_PCI + if (dev && dev_is_pci(dev)) + return octeon_pci_dma_ops->dma_to_phys(dev, daddr); +#endif + return daddr; } -EXPORT_SYMBOL(__dma_to_phys); - -static struct octeon_dma_map_ops octeon_linear_dma_map_ops = { - .dma_map_ops = { - .alloc = octeon_dma_alloc_coherent, - .free = swiotlb_free, - .map_page = octeon_dma_map_page, - .unmap_page = swiotlb_unmap_page, - .map_sg = octeon_dma_map_sg, - .unmap_sg = swiotlb_unmap_sg_attrs, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = octeon_dma_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = octeon_dma_sync_sg_for_device, - .mapping_error = swiotlb_dma_mapping_error, - .dma_supported = swiotlb_dma_supported - }, - .phys_to_dma = octeon_unity_phys_to_dma, - .dma_to_phys = octeon_unity_dma_to_phys -}; char *octeon_swiotlb; @@ -283,52 +248,4 @@ void __init plat_swiotlb_setup(void) if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM) panic("Cannot allocate SWIOTLB buffer"); - - mips_dma_map_ops = &octeon_linear_dma_map_ops.dma_map_ops; } - -#ifdef CONFIG_PCI -static struct octeon_dma_map_ops _octeon_pci_dma_map_ops = { - .dma_map_ops = { - .alloc = octeon_dma_alloc_coherent, - .free = swiotlb_free, - .map_page = octeon_dma_map_page, - .unmap_page = swiotlb_unmap_page, - .map_sg = octeon_dma_map_sg, - .unmap_sg = swiotlb_unmap_sg_attrs, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = octeon_dma_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = octeon_dma_sync_sg_for_device, - .mapping_error = swiotlb_dma_mapping_error, - .dma_supported = swiotlb_dma_supported - }, -}; - -const struct dma_map_ops *octeon_pci_dma_map_ops; - -void __init octeon_pci_dma_init(void) -{ - switch (octeon_dma_bar_type) { - case OCTEON_DMA_BAR_TYPE_PCIE2: - _octeon_pci_dma_map_ops.phys_to_dma = octeon_gen2_phys_to_dma; - _octeon_pci_dma_map_ops.dma_to_phys = octeon_gen2_dma_to_phys; - break; - case OCTEON_DMA_BAR_TYPE_PCIE: - _octeon_pci_dma_map_ops.phys_to_dma = octeon_gen1_phys_to_dma; - _octeon_pci_dma_map_ops.dma_to_phys = octeon_gen1_dma_to_phys; - break; - case OCTEON_DMA_BAR_TYPE_BIG: - _octeon_pci_dma_map_ops.phys_to_dma = octeon_big_phys_to_dma; - _octeon_pci_dma_map_ops.dma_to_phys = octeon_big_dma_to_phys; - break; - case OCTEON_DMA_BAR_TYPE_SMALL: - _octeon_pci_dma_map_ops.phys_to_dma = octeon_small_phys_to_dma; - _octeon_pci_dma_map_ops.dma_to_phys = octeon_small_dma_to_phys; - break; - default: - BUG(); - } - octeon_pci_dma_map_ops = &_octeon_pci_dma_map_ops.dma_map_ops; -} -#endif /* CONFIG_PCI */ diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c index d18ed5af62f4..b8898e2b8a6f 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2008 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -42,9 +42,6 @@ #include <asm/octeon/cvmx-asxx-defs.h> #include <asm/octeon/cvmx-dbg-defs.h> -void __cvmx_interrupt_gmxx_enable(int interface); -void __cvmx_interrupt_asxx_enable(int block); - /** * Probe RGMII ports and determine the number present * diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c index 578283350776..a176358c5a21 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2008 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -39,10 +39,7 @@ #include <asm/octeon/cvmx-gmxx-defs.h> #include <asm/octeon/cvmx-pcsx-defs.h> - -void __cvmx_interrupt_gmxx_enable(int interface); -void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block); -void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index); +#include <asm/octeon/cvmx-pcsxx-defs.h> /** * Perform initialization required only once for an SGMII port. diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c index ef16aa00167b..2a574d272671 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2008 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -25,10 +25,6 @@ * Contact Cavium Networks for more information ***********************license end**************************************/ -void __cvmx_interrupt_gmxx_enable(int interface); -void __cvmx_interrupt_spxx_int_msk_enable(int index); -void __cvmx_interrupt_stxx_int_msk_enable(int index); - /* * Functions for SPI initialization, configuration, * and monitoring. @@ -41,6 +37,8 @@ void __cvmx_interrupt_stxx_int_msk_enable(int index); #include <asm/octeon/cvmx-pip-defs.h> #include <asm/octeon/cvmx-pko-defs.h> +#include <asm/octeon/cvmx-spxx-defs.h> +#include <asm/octeon/cvmx-stxx-defs.h> /* * CVMX_HELPER_SPI_TIMEOUT is used to determine how long the SPI diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c index 19d54e02c185..2bb6912a580d 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2008 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -39,12 +39,9 @@ #include <asm/octeon/cvmx-pko-defs.h> #include <asm/octeon/cvmx-gmxx-defs.h> +#include <asm/octeon/cvmx-pcsx-defs.h> #include <asm/octeon/cvmx-pcsxx-defs.h> -void __cvmx_interrupt_gmxx_enable(int interface); -void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block); -void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index); - int __cvmx_helper_xaui_enumerate(int interface) { union cvmx_gmxx_hg2_control gmx_hg2_control; diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index b3aec101a65d..8272d8c648ca 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -814,7 +814,7 @@ static int octeon_irq_ciu_set_affinity(struct irq_data *data, pen = &per_cpu(octeon_irq_ciu1_en_mirror, cpu); if (cpumask_test_cpu(cpu, dest) && enable_one) { - enable_one = 0; + enable_one = false; __set_bit(cd->bit, pen); } else { __clear_bit(cd->bit, pen); diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c index 8505db478904..807cadaf554e 100644 --- a/arch/mips/cavium-octeon/octeon-platform.c +++ b/arch/mips/cavium-octeon/octeon-platform.c @@ -322,6 +322,7 @@ static int __init octeon_ehci_device_init(void) return 0; pd = of_find_device_by_node(ehci_node); + of_node_put(ehci_node); if (!pd) return 0; @@ -384,6 +385,7 @@ static int __init octeon_ohci_device_init(void) return 0; pd = of_find_device_by_node(ohci_node); + of_node_put(ohci_node); if (!pd) return 0; @@ -1067,6 +1069,6 @@ end_led: static int __init octeon_publish_devices(void) { - return of_platform_bus_probe(NULL, octeon_ids, NULL); + return of_platform_populate(NULL, octeon_ids, NULL, NULL); } arch_initcall(octeon_publish_devices); diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index a8034d0dcade..c2426232db06 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -36,6 +36,7 @@ #include <asm/mipsregs.h> #include <asm/bootinfo.h> #include <asm/sections.h> +#include <asm/setup.h> #include <asm/time.h> #include <asm/octeon/octeon.h> @@ -1108,7 +1109,7 @@ void __init plat_mem_setup(void) * Emit one character to the boot UART. Exported for use by the * watchdog timer. */ -int prom_putchar(char c) +void prom_putchar(char c) { uint64_t lsrval; @@ -1119,7 +1120,6 @@ int prom_putchar(char c) /* Write the byte */ cvmx_write_csr(CVMX_MIO_UARTX_THR(octeon_uart), c & 0xffull); - return 1; } EXPORT_SYMBOL(prom_putchar); @@ -1154,11 +1154,7 @@ void __init prom_free_prom_memory(void) } void __init octeon_fill_mac_addresses(void); -int octeon_prune_device_tree(void); -extern const char __appended_dtb; -extern const char __dtb_octeon_3xxx_begin; -extern const char __dtb_octeon_68xx_begin; void __init device_tree_init(void) { const void *fdt; diff --git a/arch/mips/configs/bcm47xx_defconfig b/arch/mips/configs/bcm47xx_defconfig index fad8e964f14c..ba800a892384 100644 --- a/arch/mips/configs/bcm47xx_defconfig +++ b/arch/mips/configs/bcm47xx_defconfig @@ -66,7 +66,6 @@ CONFIG_HW_RANDOM=y CONFIG_GPIO_SYSFS=y CONFIG_WATCHDOG=y CONFIG_BCM47XX_WDT=y -CONFIG_SSB_DEBUG=y CONFIG_SSB_DRIVER_GIGE=y CONFIG_BCMA_DRIVER_GMAC_CMN=y CONFIG_USB=y diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig index be23fd25eeaa..030ff9c205fb 100644 --- a/arch/mips/configs/ci20_defconfig +++ b/arch/mips/configs/ci20_defconfig @@ -92,6 +92,8 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_I2C=y CONFIG_I2C_JZ4780=y +CONFIG_SPI=y +CONFIG_SPI_GPIO=y CONFIG_GPIO_SYSFS=y CONFIG_GPIO_INGENIC=y # CONFIG_HWMON is not set diff --git a/arch/mips/configs/generic_defconfig b/arch/mips/configs/generic_defconfig index 26b1cd5ffbf5..684c9dcba126 100644 --- a/arch/mips/configs/generic_defconfig +++ b/arch/mips/configs/generic_defconfig @@ -43,9 +43,6 @@ CONFIG_NETFILTER=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_SCSI=y -# CONFIG_INPUT_MOUSEDEV is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_HW_RANDOM=y # CONFIG_HWMON is not set diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig index df8a9a15ca83..81058295d35f 100644 --- a/arch/mips/configs/malta_defconfig +++ b/arch/mips/configs/malta_defconfig @@ -317,6 +317,7 @@ CONFIG_MOUSE_PS2_ELANTECH=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig index 14df9ef15d40..5c10cddc39d3 100644 --- a/arch/mips/configs/malta_kvm_defconfig +++ b/arch/mips/configs/malta_kvm_defconfig @@ -328,6 +328,7 @@ CONFIG_INPUT_MOUSEDEV=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig index 25092e344574..bb694f5065f1 100644 --- a/arch/mips/configs/malta_kvm_guest_defconfig +++ b/arch/mips/configs/malta_kvm_guest_defconfig @@ -330,6 +330,7 @@ CONFIG_INPUT_MOUSEDEV=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig index 210bf609f785..5b5306b80576 100644 --- a/arch/mips/configs/malta_qemu_32r6_defconfig +++ b/arch/mips/configs/malta_qemu_32r6_defconfig @@ -133,6 +133,7 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig index e5934aa98397..85543599448f 100644 --- a/arch/mips/configs/maltaaprp_defconfig +++ b/arch/mips/configs/maltaaprp_defconfig @@ -133,6 +133,7 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig index cb2ca11c1789..067bb84ac916 100644 --- a/arch/mips/configs/maltasmvp_defconfig +++ b/arch/mips/configs/maltasmvp_defconfig @@ -134,6 +134,7 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig index be29fcec69fc..dfc78c3172a3 100644 --- a/arch/mips/configs/maltasmvp_eva_defconfig +++ b/arch/mips/configs/maltasmvp_eva_defconfig @@ -137,6 +137,7 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig index 40462d4c90a0..50a2288c69f8 100644 --- a/arch/mips/configs/maltaup_defconfig +++ b/arch/mips/configs/maltaup_defconfig @@ -132,6 +132,7 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig index 4e50176cb3df..99a19cf5f9ba 100644 --- a/arch/mips/configs/maltaup_xpa_defconfig +++ b/arch/mips/configs/maltaup_xpa_defconfig @@ -326,6 +326,7 @@ CONFIG_MOUSE_PS2_ELANTECH=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_PIIX4_POWEROFF=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/mips/fw/arc/arc_con.c b/arch/mips/fw/arc/arc_con.c index 769d4b9ac82e..365e3913231e 100644 --- a/arch/mips/fw/arc/arc_con.c +++ b/arch/mips/fw/arc/arc_con.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/console.h> #include <linux/fs.h> +#include <asm/setup.h> #include <asm/sgialib.h> static void prom_console_write(struct console *co, const char *s, diff --git a/arch/mips/fw/arc/promlib.c b/arch/mips/fw/arc/promlib.c index 7e8ba5ce95be..be381307fbb0 100644 --- a/arch/mips/fw/arc/promlib.c +++ b/arch/mips/fw/arc/promlib.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <asm/sgialib.h> #include <asm/bcache.h> +#include <asm/setup.h> /* * IP22 boardcache is not compatible with board caches. Thus we disable it diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c index 6aa264b9856a..8772617b64ce 100644 --- a/arch/mips/fw/sni/sniprom.c +++ b/arch/mips/fw/sni/sniprom.c @@ -19,6 +19,7 @@ #include <asm/mipsprom.h> #include <asm/mipsregs.h> #include <asm/bootinfo.h> +#include <asm/setup.h> /* special SNI prom calls */ /* diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig index ba9b2c8cce68..08e33c6b2539 100644 --- a/arch/mips/generic/Kconfig +++ b/arch/mips/generic/Kconfig @@ -35,13 +35,13 @@ config LEGACY_BOARD_OCELOT depends on LEGACY_BOARD_SEAD3=n select LEGACY_BOARDS select MSCC_OCELOT + select SYS_HAS_EARLY_PRINTK + select USE_GENERIC_EARLY_PRINTK_8250 config MSCC_OCELOT bool select GPIOLIB select MSCC_OCELOT_IRQ - select SYS_HAS_EARLY_PRINTK - select USE_GENERIC_EARLY_PRINTK_8250 comment "FIT/UHI Boards" @@ -65,6 +65,14 @@ config FIT_IMAGE_FDT_XILFPGA Enable this to include the FDT for the MIPSfpga platform from Imagination Technologies in the FIT kernel image. +config FIT_IMAGE_FDT_OCELOT_PCB123 + bool "Include FDT for Microsemi Ocelot PCB123" + select MSCC_OCELOT + help + Enable this to include the FDT for the Ocelot PCB123 platform + from Microsemi in the FIT kernel image. + This requires u-boot on the platform. + config VIRT_BOARD_RANCHU bool "Support Ranchu platform for Android emulator" help diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform index 0dd0d5d460a5..879cb80396c8 100644 --- a/arch/mips/generic/Platform +++ b/arch/mips/generic/Platform @@ -16,4 +16,5 @@ all-$(CONFIG_MIPS_GENERIC) := vmlinux.gz.itb its-y := vmlinux.its.S its-$(CONFIG_FIT_IMAGE_FDT_BOSTON) += board-boston.its.S its-$(CONFIG_FIT_IMAGE_FDT_NI169445) += board-ni169445.its.S +its-$(CONFIG_FIT_IMAGE_FDT_OCELOT_PCB123) += board-ocelot_pcb123.its.S its-$(CONFIG_FIT_IMAGE_FDT_XILFPGA) += board-xilfpga.its.S diff --git a/arch/mips/generic/board-ocelot_pcb123.its.S b/arch/mips/generic/board-ocelot_pcb123.its.S new file mode 100644 index 000000000000..5a7d5e1c878a --- /dev/null +++ b/arch/mips/generic/board-ocelot_pcb123.its.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/ { + images { + fdt@ocelot_pcb123 { + description = "MSCC Ocelot PCB123 Device Tree"; + data = /incbin/("boot/dts/mscc/ocelot_pcb123.dtb"); + type = "flat_dt"; + arch = "mips"; + compression = "none"; + hash@0 { + algo = "sha1"; + }; + }; + }; + + configurations { + conf@ocelot_pcb123 { + description = "Ocelot Linux kernel"; + kernel = "kernel@0"; + fdt = "fdt@ocelot_pcb123"; + }; + }; +}; diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c index 5ba6fcc26fa7..a106f8113842 100644 --- a/arch/mips/generic/init.c +++ b/arch/mips/generic/init.c @@ -14,7 +14,6 @@ #include <linux/init.h> #include <linux/irqchip.h> #include <linux/of_fdt.h> -#include <linux/of_platform.h> #include <asm/bootinfo.h> #include <asm/fw/fw.h> @@ -204,22 +203,11 @@ void __init arch_init_irq(void) "mti,cpu-interrupt-controller"); if (!cpu_has_veic && !intc_node) mips_cpu_irq_init(); + of_node_put(intc_node); irqchip_init(); } -static int __init publish_devices(void) -{ - if (!of_have_populated_dt()) - panic("Device-tree not present"); - - if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL)) - panic("Failed to populate DT"); - - return 0; -} -arch_initcall(publish_devices); - void __init prom_free_prom_memory(void) { } diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c index b408dac722ac..7ba4ad5cc1d6 100644 --- a/arch/mips/generic/yamon-dt.c +++ b/arch/mips/generic/yamon-dt.c @@ -28,8 +28,6 @@ __init int yamon_dt_append_cmdline(void *fdt) /* find or add chosen node */ chosen_off = fdt_path_offset(fdt, "/chosen"); if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_path_offset(fdt, "/chosen@0"); - if (chosen_off == -FDT_ERR_NOTFOUND) chosen_off = fdt_add_subnode(fdt, 0, "chosen"); if (chosen_off < 0) { pr_err("Unable to find or add DT chosen node: %d\n", @@ -221,8 +219,6 @@ __init int yamon_dt_serial_config(void *fdt) /* find or add chosen node */ chosen_off = fdt_path_offset(fdt, "/chosen"); if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_path_offset(fdt, "/chosen@0"); - if (chosen_off == -FDT_ERR_NOTFOUND) chosen_off = fdt_add_subnode(fdt, 0, "chosen"); if (chosen_off < 0) { pr_err("Unable to find or add DT chosen node: %d\n", diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 45d541baf359..58351e48421e 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -8,6 +8,7 @@ generic-y += irq_work.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h +generic-y += msi.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 0ab176bdb8e8..0269b3de8b51 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -22,6 +22,17 @@ #include <asm/cmpxchg.h> #include <asm/war.h> +/* + * Using a branch-likely instruction to check the result of an sc instruction + * works around a bug present in R10000 CPUs prior to revision 3.0 that could + * cause ll-sc sequences to execute non-atomically. + */ +#if R10000_LLSC_WAR +# define __scbeqz "beqzl" +#else +# define __scbeqz "beqz" +#endif + #define ATOMIC_INIT(i) { (i) } /* @@ -44,31 +55,18 @@ #define ATOMIC_OP(op, c_op, asm_op) \ static __inline__ void atomic_##op(int i, atomic_t * v) \ { \ - if (kernel_uses_llsc && R10000_LLSC_WAR) { \ + if (kernel_uses_llsc) { \ int temp; \ \ __asm__ __volatile__( \ - " .set arch=r4000 \n" \ + " .set "MIPS_ISA_LEVEL" \n" \ "1: ll %0, %1 # atomic_" #op " \n" \ " " #asm_op " %0, %2 \n" \ " sc %0, %1 \n" \ - " beqzl %0, 1b \n" \ + "\t" __scbeqz " %0, 1b \n" \ " .set mips0 \n" \ : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ : "Ir" (i)); \ - } else if (kernel_uses_llsc) { \ - int temp; \ - \ - do { \ - __asm__ __volatile__( \ - " .set "MIPS_ISA_LEVEL" \n" \ - " ll %0, %1 # atomic_" #op "\n" \ - " " #asm_op " %0, %2 \n" \ - " sc %0, %1 \n" \ - " .set mips0 \n" \ - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i)); \ - } while (unlikely(!temp)); \ } else { \ unsigned long flags; \ \ @@ -83,36 +81,20 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v) \ { \ int result; \ \ - if (kernel_uses_llsc && R10000_LLSC_WAR) { \ + if (kernel_uses_llsc) { \ int temp; \ \ __asm__ __volatile__( \ - " .set arch=r4000 \n" \ + " .set "MIPS_ISA_LEVEL" \n" \ "1: ll %1, %2 # atomic_" #op "_return \n" \ " " #asm_op " %0, %1, %3 \n" \ " sc %0, %2 \n" \ - " beqzl %0, 1b \n" \ + "\t" __scbeqz " %0, 1b \n" \ " " #asm_op " %0, %1, %3 \n" \ " .set mips0 \n" \ : "=&r" (result), "=&r" (temp), \ "+" GCC_OFF_SMALL_ASM() (v->counter) \ : "Ir" (i)); \ - } else if (kernel_uses_llsc) { \ - int temp; \ - \ - do { \ - __asm__ __volatile__( \ - " .set "MIPS_ISA_LEVEL" \n" \ - " ll %1, %2 # atomic_" #op "_return \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " sc %0, %2 \n" \ - " .set mips0 \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i)); \ - } while (unlikely(!result)); \ - \ - result = temp; result c_op i; \ } else { \ unsigned long flags; \ \ @@ -131,36 +113,20 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v) \ { \ int result; \ \ - if (kernel_uses_llsc && R10000_LLSC_WAR) { \ + if (kernel_uses_llsc) { \ int temp; \ \ __asm__ __volatile__( \ - " .set arch=r4000 \n" \ + " .set "MIPS_ISA_LEVEL" \n" \ "1: ll %1, %2 # atomic_fetch_" #op " \n" \ " " #asm_op " %0, %1, %3 \n" \ " sc %0, %2 \n" \ - " beqzl %0, 1b \n" \ + "\t" __scbeqz " %0, 1b \n" \ " move %0, %1 \n" \ " .set mips0 \n" \ : "=&r" (result), "=&r" (temp), \ "+" GCC_OFF_SMALL_ASM() (v->counter) \ : "Ir" (i)); \ - } else if (kernel_uses_llsc) { \ - int temp; \ - \ - do { \ - __asm__ __volatile__( \ - " .set "MIPS_ISA_LEVEL" \n" \ - " ll %1, %2 # atomic_fetch_" #op " \n" \ - " " #asm_op " %0, %1, %3 \n" \ - " sc %0, %2 \n" \ - " .set mips0 \n" \ - : "=&r" (result), "=&r" (temp), \ - "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i)); \ - } while (unlikely(!result)); \ - \ - result = temp; \ } else { \ unsigned long flags; \ \ @@ -218,38 +184,17 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) smp_mb__before_llsc(); - if (kernel_uses_llsc && R10000_LLSC_WAR) { - int temp; - - __asm__ __volatile__( - " .set arch=r4000 \n" - "1: ll %1, %2 # atomic_sub_if_positive\n" - " subu %0, %1, %3 \n" - " bltz %0, 1f \n" - " sc %0, %2 \n" - " .set noreorder \n" - " beqzl %0, 1b \n" - " subu %0, %1, %3 \n" - " .set reorder \n" - "1: \n" - " .set mips0 \n" - : "=&r" (result), "=&r" (temp), - "+" GCC_OFF_SMALL_ASM() (v->counter) - : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) - : "memory"); - } else if (kernel_uses_llsc) { + if (kernel_uses_llsc) { int temp; __asm__ __volatile__( " .set "MIPS_ISA_LEVEL" \n" "1: ll %1, %2 # atomic_sub_if_positive\n" " subu %0, %1, %3 \n" + " move %1, %0 \n" " bltz %0, 1f \n" - " sc %0, %2 \n" - " .set noreorder \n" - " beqz %0, 1b \n" - " subu %0, %1, %3 \n" - " .set reorder \n" + " sc %1, %2 \n" + "\t" __scbeqz " %1, 1b \n" "1: \n" " .set mips0 \n" : "=&r" (result), "=&r" (temp), @@ -274,97 +219,12 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) - -/* - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -/* - * atomic_dec_and_test - decrement by 1 and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) - /* * atomic_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t */ #define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v) -/* - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc(v) atomic_add(1, (v)) - -/* - * atomic_dec - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec(v) atomic_sub(1, (v)) - -/* - * atomic_add_negative - add and test if negative - * @v: pointer of type atomic_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) - #ifdef CONFIG_64BIT #define ATOMIC64_INIT(i) { (i) } @@ -386,31 +246,18 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) #define ATOMIC64_OP(op, c_op, asm_op) \ static __inline__ void atomic64_##op(long i, atomic64_t * v) \ { \ - if (kernel_uses_llsc && R10000_LLSC_WAR) { \ + if (kernel_uses_llsc) { \ long temp; \ \ __asm__ __volatile__( \ - " .set arch=r4000 \n" \ + " .set "MIPS_ISA_LEVEL" \n" \ "1: lld %0, %1 # atomic64_" #op " \n" \ " " #asm_op " %0, %2 \n" \ " scd %0, %1 \n" \ - " beqzl %0, 1b \n" \ + "\t" __scbeqz " %0, 1b \n" \ " .set mips0 \n" \ : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ : "Ir" (i)); \ - } else if (kernel_uses_llsc) { \ - long temp; \ - \ - do { \ - __asm__ __volatile__( \ - " .set "MIPS_ISA_LEVEL" \n" \ - " lld %0, %1 # atomic64_" #op "\n" \ - " " #asm_op " %0, %2 \n" \ - " scd %0, %1 \n" \ - " .set mips0 \n" \ - : "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i)); \ - } while (unlikely(!temp)); \ } else { \ unsigned long flags; \ \ @@ -425,37 +272,20 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \ { \ long result; \ \ - if (kernel_uses_llsc && R10000_LLSC_WAR) { \ + if (kernel_uses_llsc) { \ long temp; \ \ __asm__ __volatile__( \ - " .set arch=r4000 \n" \ + " .set "MIPS_ISA_LEVEL" \n" \ "1: lld %1, %2 # atomic64_" #op "_return\n" \ " " #asm_op " %0, %1, %3 \n" \ " scd %0, %2 \n" \ - " beqzl %0, 1b \n" \ + "\t" __scbeqz " %0, 1b \n" \ " " #asm_op " %0, %1, %3 \n" \ " .set mips0 \n" \ : "=&r" (result), "=&r" (temp), \ "+" GCC_OFF_SMALL_ASM() (v->counter) \ : "Ir" (i)); \ - } else if (kernel_uses_llsc) { \ - long temp; \ - \ - do { \ - __asm__ __volatile__( \ - " .set "MIPS_ISA_LEVEL" \n" \ - " lld %1, %2 # atomic64_" #op "_return\n" \ - " " #asm_op " %0, %1, %3 \n" \ - " scd %0, %2 \n" \ - " .set mips0 \n" \ - : "=&r" (result), "=&r" (temp), \ - "=" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) \ - : "memory"); \ - } while (unlikely(!result)); \ - \ - result = temp; result c_op i; \ } else { \ unsigned long flags; \ \ @@ -478,33 +308,16 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v) \ long temp; \ \ __asm__ __volatile__( \ - " .set arch=r4000 \n" \ + " .set "MIPS_ISA_LEVEL" \n" \ "1: lld %1, %2 # atomic64_fetch_" #op "\n" \ " " #asm_op " %0, %1, %3 \n" \ " scd %0, %2 \n" \ - " beqzl %0, 1b \n" \ + "\t" __scbeqz " %0, 1b \n" \ " move %0, %1 \n" \ " .set mips0 \n" \ : "=&r" (result), "=&r" (temp), \ "+" GCC_OFF_SMALL_ASM() (v->counter) \ : "Ir" (i)); \ - } else if (kernel_uses_llsc) { \ - long temp; \ - \ - do { \ - __asm__ __volatile__( \ - " .set "MIPS_ISA_LEVEL" \n" \ - " lld %1, %2 # atomic64_fetch_" #op "\n" \ - " " #asm_op " %0, %1, %3 \n" \ - " scd %0, %2 \n" \ - " .set mips0 \n" \ - : "=&r" (result), "=&r" (temp), \ - "=" GCC_OFF_SMALL_ASM() (v->counter) \ - : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) \ - : "memory"); \ - } while (unlikely(!result)); \ - \ - result = temp; \ } else { \ unsigned long flags; \ \ @@ -563,38 +376,17 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v) smp_mb__before_llsc(); - if (kernel_uses_llsc && R10000_LLSC_WAR) { - long temp; - - __asm__ __volatile__( - " .set arch=r4000 \n" - "1: lld %1, %2 # atomic64_sub_if_positive\n" - " dsubu %0, %1, %3 \n" - " bltz %0, 1f \n" - " scd %0, %2 \n" - " .set noreorder \n" - " beqzl %0, 1b \n" - " dsubu %0, %1, %3 \n" - " .set reorder \n" - "1: \n" - " .set mips0 \n" - : "=&r" (result), "=&r" (temp), - "=" GCC_OFF_SMALL_ASM() (v->counter) - : "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter) - : "memory"); - } else if (kernel_uses_llsc) { + if (kernel_uses_llsc) { long temp; __asm__ __volatile__( " .set "MIPS_ISA_LEVEL" \n" "1: lld %1, %2 # atomic64_sub_if_positive\n" " dsubu %0, %1, %3 \n" + " move %1, %0 \n" " bltz %0, 1f \n" - " scd %0, %2 \n" - " .set noreorder \n" - " beqz %0, 1b \n" - " dsubu %0, %1, %3 \n" - " .set reorder \n" + " scd %1, %2 \n" + "\t" __scbeqz " %1, 1b \n" "1: \n" " .set mips0 \n" : "=&r" (result), "=&r" (temp), @@ -620,99 +412,12 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v) ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new))) -/** - * atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns true iff @v was not @u. - */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1, (v)) - -/* - * atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) - -/* - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - -/* - * atomic64_dec_and_test - decrement by 1 and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0) - /* * atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic64_t */ #define atomic64_dec_if_positive(v) atomic64_sub_if_positive(1, v) -/* - * atomic64_inc - increment atomic variable - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1. - */ -#define atomic64_inc(v) atomic64_add(1, (v)) - -/* - * atomic64_dec - decrement and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1. - */ -#define atomic64_dec(v) atomic64_sub(1, (v)) - -/* - * atomic64_add_negative - add and test if negative - * @v: pointer of type atomic64_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0) - #endif /* CONFIG_64BIT */ #endif /* _ASM_ATOMIC_H */ diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h index b3e2975f83d3..bf6a8afd7ad2 100644 --- a/arch/mips/include/asm/bmips.h +++ b/arch/mips/include/asm/bmips.h @@ -123,22 +123,6 @@ static inline void bmips_write_zscm_reg(unsigned int offset, unsigned long data) barrier(); } -static inline void bmips_post_dma_flush(struct device *dev) -{ - void __iomem *cbr = BMIPS_GET_CBR(); - u32 cfg; - - if (boot_cpu_type() != CPU_BMIPS3300 && - boot_cpu_type() != CPU_BMIPS4350 && - boot_cpu_type() != CPU_BMIPS4380) - return; - - /* Flush stale data out of the readahead cache */ - cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG); - __raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG); - __raw_readl(cbr + BMIPS_RAC_CONFIG); -} - #endif /* !defined(__ASSEMBLY__) */ #endif /* _ASM_BMIPS_H */ diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index 9cdb4e4ce258..0edba3e75747 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -14,39 +14,77 @@ #include <asm/isa-rev.h> #include <cpu-feature-overrides.h> +#define __ase(ase) (cpu_data[0].ases & (ase)) +#define __opt(opt) (cpu_data[0].options & (opt)) + +/* + * Check if MIPS_ISA_REV is >= isa *and* an option or ASE is detected during + * boot (typically by cpu_probe()). + * + * Note that these should only be used in cases where a kernel built for an + * older ISA *cannot* run on a CPU which supports the feature in question. For + * example this may be used for features introduced with MIPSr6, since a kernel + * built for an older ISA cannot run on a MIPSr6 CPU. This should not be used + * for MIPSr2 features however, since a MIPSr1 or earlier kernel might run on a + * MIPSr2 CPU. + */ +#define __isa_ge_and_ase(isa, ase) ((MIPS_ISA_REV >= (isa)) && __ase(ase)) +#define __isa_ge_and_opt(isa, opt) ((MIPS_ISA_REV >= (isa)) && __opt(opt)) + +/* + * Check if MIPS_ISA_REV is >= isa *or* an option or ASE is detected during + * boot (typically by cpu_probe()). + * + * These are for use with features that are optional up until a particular ISA + * revision & then become required. + */ +#define __isa_ge_or_ase(isa, ase) ((MIPS_ISA_REV >= (isa)) || __ase(ase)) +#define __isa_ge_or_opt(isa, opt) ((MIPS_ISA_REV >= (isa)) || __opt(opt)) + +/* + * Check if MIPS_ISA_REV is < isa *and* an option or ASE is detected during + * boot (typically by cpu_probe()). + * + * These are for use with features that are optional up until a particular ISA + * revision & are then removed - ie. no longer present in any CPU implementing + * the given ISA revision. + */ +#define __isa_lt_and_ase(isa, ase) ((MIPS_ISA_REV < (isa)) && __ase(ase)) +#define __isa_lt_and_opt(isa, opt) ((MIPS_ISA_REV < (isa)) && __opt(opt)) + /* * SMP assumption: Options of CPU 0 are a superset of all processors. * This is true for all known MIPS systems. */ #ifndef cpu_has_tlb -#define cpu_has_tlb (cpu_data[0].options & MIPS_CPU_TLB) +#define cpu_has_tlb __opt(MIPS_CPU_TLB) #endif #ifndef cpu_has_ftlb -#define cpu_has_ftlb (cpu_data[0].options & MIPS_CPU_FTLB) +#define cpu_has_ftlb __opt(MIPS_CPU_FTLB) #endif #ifndef cpu_has_tlbinv -#define cpu_has_tlbinv (cpu_data[0].options & MIPS_CPU_TLBINV) +#define cpu_has_tlbinv __opt(MIPS_CPU_TLBINV) #endif #ifndef cpu_has_segments -#define cpu_has_segments (cpu_data[0].options & MIPS_CPU_SEGMENTS) +#define cpu_has_segments __opt(MIPS_CPU_SEGMENTS) #endif #ifndef cpu_has_eva -#define cpu_has_eva (cpu_data[0].options & MIPS_CPU_EVA) +#define cpu_has_eva __opt(MIPS_CPU_EVA) #endif #ifndef cpu_has_htw -#define cpu_has_htw (cpu_data[0].options & MIPS_CPU_HTW) +#define cpu_has_htw __opt(MIPS_CPU_HTW) #endif #ifndef cpu_has_ldpte -#define cpu_has_ldpte (cpu_data[0].options & MIPS_CPU_LDPTE) +#define cpu_has_ldpte __opt(MIPS_CPU_LDPTE) #endif #ifndef cpu_has_rixiex -#define cpu_has_rixiex (cpu_data[0].options & MIPS_CPU_RIXIEX) +#define cpu_has_rixiex __isa_ge_or_opt(6, MIPS_CPU_RIXIEX) #endif #ifndef cpu_has_maar -#define cpu_has_maar (cpu_data[0].options & MIPS_CPU_MAAR) +#define cpu_has_maar __opt(MIPS_CPU_MAAR) #endif #ifndef cpu_has_rw_llb -#define cpu_has_rw_llb (cpu_data[0].options & MIPS_CPU_RW_LLB) +#define cpu_has_rw_llb __isa_ge_or_opt(6, MIPS_CPU_RW_LLB) #endif /* @@ -59,18 +97,18 @@ #define cpu_has_3kex (!cpu_has_4kex) #endif #ifndef cpu_has_4kex -#define cpu_has_4kex (cpu_data[0].options & MIPS_CPU_4KEX) +#define cpu_has_4kex __isa_ge_or_opt(1, MIPS_CPU_4KEX) #endif #ifndef cpu_has_3k_cache -#define cpu_has_3k_cache (cpu_data[0].options & MIPS_CPU_3K_CACHE) +#define cpu_has_3k_cache __isa_lt_and_opt(1, MIPS_CPU_3K_CACHE) #endif #define cpu_has_6k_cache 0 #define cpu_has_8k_cache 0 #ifndef cpu_has_4k_cache -#define cpu_has_4k_cache (cpu_data[0].options & MIPS_CPU_4K_CACHE) +#define cpu_has_4k_cache __isa_ge_or_opt(1, MIPS_CPU_4K_CACHE) #endif #ifndef cpu_has_tx39_cache -#define cpu_has_tx39_cache (cpu_data[0].options & MIPS_CPU_TX39_CACHE) +#define cpu_has_tx39_cache __opt(MIPS_CPU_TX39_CACHE) #endif #ifndef cpu_has_octeon_cache #define cpu_has_octeon_cache 0 @@ -83,92 +121,92 @@ #define raw_cpu_has_fpu cpu_has_fpu #endif #ifndef cpu_has_32fpr -#define cpu_has_32fpr (cpu_data[0].options & MIPS_CPU_32FPR) +#define cpu_has_32fpr __isa_ge_or_opt(1, MIPS_CPU_32FPR) #endif #ifndef cpu_has_counter -#define cpu_has_counter (cpu_data[0].options & MIPS_CPU_COUNTER) +#define cpu_has_counter __opt(MIPS_CPU_COUNTER) #endif #ifndef cpu_has_watch -#define cpu_has_watch (cpu_data[0].options & MIPS_CPU_WATCH) +#define cpu_has_watch __opt(MIPS_CPU_WATCH) #endif #ifndef cpu_has_divec -#define cpu_has_divec (cpu_data[0].options & MIPS_CPU_DIVEC) +#define cpu_has_divec __isa_ge_or_opt(1, MIPS_CPU_DIVEC) #endif #ifndef cpu_has_vce -#define cpu_has_vce (cpu_data[0].options & MIPS_CPU_VCE) +#define cpu_has_vce __opt(MIPS_CPU_VCE) #endif #ifndef cpu_has_cache_cdex_p -#define cpu_has_cache_cdex_p (cpu_data[0].options & MIPS_CPU_CACHE_CDEX_P) +#define cpu_has_cache_cdex_p __opt(MIPS_CPU_CACHE_CDEX_P) #endif #ifndef cpu_has_cache_cdex_s -#define cpu_has_cache_cdex_s (cpu_data[0].options & MIPS_CPU_CACHE_CDEX_S) +#define cpu_has_cache_cdex_s __opt(MIPS_CPU_CACHE_CDEX_S) #endif #ifndef cpu_has_prefetch -#define cpu_has_prefetch (cpu_data[0].options & MIPS_CPU_PREFETCH) +#define cpu_has_prefetch __isa_ge_or_opt(1, MIPS_CPU_PREFETCH) #endif #ifndef cpu_has_mcheck -#define cpu_has_mcheck (cpu_data[0].options & MIPS_CPU_MCHECK) +#define cpu_has_mcheck __isa_ge_or_opt(1, MIPS_CPU_MCHECK) #endif #ifndef cpu_has_ejtag -#define cpu_has_ejtag (cpu_data[0].options & MIPS_CPU_EJTAG) +#define cpu_has_ejtag __opt(MIPS_CPU_EJTAG) #endif #ifndef cpu_has_llsc -#define cpu_has_llsc (cpu_data[0].options & MIPS_CPU_LLSC) +#define cpu_has_llsc __isa_ge_or_opt(1, MIPS_CPU_LLSC) #endif #ifndef cpu_has_bp_ghist -#define cpu_has_bp_ghist (cpu_data[0].options & MIPS_CPU_BP_GHIST) +#define cpu_has_bp_ghist __opt(MIPS_CPU_BP_GHIST) #endif #ifndef kernel_uses_llsc #define kernel_uses_llsc cpu_has_llsc #endif #ifndef cpu_has_guestctl0ext -#define cpu_has_guestctl0ext (cpu_data[0].options & MIPS_CPU_GUESTCTL0EXT) +#define cpu_has_guestctl0ext __opt(MIPS_CPU_GUESTCTL0EXT) #endif #ifndef cpu_has_guestctl1 -#define cpu_has_guestctl1 (cpu_data[0].options & MIPS_CPU_GUESTCTL1) +#define cpu_has_guestctl1 __opt(MIPS_CPU_GUESTCTL1) #endif #ifndef cpu_has_guestctl2 -#define cpu_has_guestctl2 (cpu_data[0].options & MIPS_CPU_GUESTCTL2) +#define cpu_has_guestctl2 __opt(MIPS_CPU_GUESTCTL2) #endif #ifndef cpu_has_guestid -#define cpu_has_guestid (cpu_data[0].options & MIPS_CPU_GUESTID) +#define cpu_has_guestid __opt(MIPS_CPU_GUESTID) #endif #ifndef cpu_has_drg -#define cpu_has_drg (cpu_data[0].options & MIPS_CPU_DRG) +#define cpu_has_drg __opt(MIPS_CPU_DRG) #endif #ifndef cpu_has_mips16 -#define cpu_has_mips16 (cpu_data[0].ases & MIPS_ASE_MIPS16) +#define cpu_has_mips16 __isa_lt_and_ase(6, MIPS_ASE_MIPS16) #endif #ifndef cpu_has_mips16e2 -#define cpu_has_mips16e2 (cpu_data[0].ases & MIPS_ASE_MIPS16E2) +#define cpu_has_mips16e2 __isa_lt_and_ase(6, MIPS_ASE_MIPS16E2) #endif #ifndef cpu_has_mdmx -#define cpu_has_mdmx (cpu_data[0].ases & MIPS_ASE_MDMX) +#define cpu_has_mdmx __isa_lt_and_ase(6, MIPS_ASE_MDMX) #endif #ifndef cpu_has_mips3d -#define cpu_has_mips3d (cpu_data[0].ases & MIPS_ASE_MIPS3D) +#define cpu_has_mips3d __isa_lt_and_ase(6, MIPS_ASE_MIPS3D) #endif #ifndef cpu_has_smartmips -#define cpu_has_smartmips (cpu_data[0].ases & MIPS_ASE_SMARTMIPS) +#define cpu_has_smartmips __isa_lt_and_ase(6, MIPS_ASE_SMARTMIPS) #endif #ifndef cpu_has_rixi -#define cpu_has_rixi (cpu_data[0].options & MIPS_CPU_RIXI) +#define cpu_has_rixi __isa_ge_or_opt(6, MIPS_CPU_RIXI) #endif #ifndef cpu_has_mmips # ifdef CONFIG_SYS_SUPPORTS_MICROMIPS -# define cpu_has_mmips (cpu_data[0].options & MIPS_CPU_MICROMIPS) +# define cpu_has_mmips __opt(MIPS_CPU_MICROMIPS) # else # define cpu_has_mmips 0 # endif #endif #ifndef cpu_has_lpa -#define cpu_has_lpa (cpu_data[0].options & MIPS_CPU_LPA) +#define cpu_has_lpa __opt(MIPS_CPU_LPA) #endif #ifndef cpu_has_mvh -#define cpu_has_mvh (cpu_data[0].options & MIPS_CPU_MVH) +#define cpu_has_mvh __opt(MIPS_CPU_MVH) #endif #ifndef cpu_has_xpa #define cpu_has_xpa (cpu_has_lpa && cpu_has_mvh) @@ -338,32 +376,32 @@ #endif #ifndef cpu_has_dsp -#define cpu_has_dsp (cpu_data[0].ases & MIPS_ASE_DSP) +#define cpu_has_dsp __ase(MIPS_ASE_DSP) #endif #ifndef cpu_has_dsp2 -#define cpu_has_dsp2 (cpu_data[0].ases & MIPS_ASE_DSP2P) +#define cpu_has_dsp2 __ase(MIPS_ASE_DSP2P) #endif #ifndef cpu_has_dsp3 -#define cpu_has_dsp3 (cpu_data[0].ases & MIPS_ASE_DSP3) +#define cpu_has_dsp3 __ase(MIPS_ASE_DSP3) #endif #ifndef cpu_has_mipsmt -#define cpu_has_mipsmt (cpu_data[0].ases & MIPS_ASE_MIPSMT) +#define cpu_has_mipsmt __isa_lt_and_ase(6, MIPS_ASE_MIPSMT) #endif #ifndef cpu_has_vp -#define cpu_has_vp (cpu_data[0].options & MIPS_CPU_VP) +#define cpu_has_vp __isa_ge_and_opt(6, MIPS_CPU_VP) #endif #ifndef cpu_has_userlocal -#define cpu_has_userlocal (cpu_data[0].options & MIPS_CPU_ULRI) +#define cpu_has_userlocal __isa_ge_or_opt(6, MIPS_CPU_ULRI) #endif #ifdef CONFIG_32BIT # ifndef cpu_has_nofpuex -# define cpu_has_nofpuex (cpu_data[0].options & MIPS_CPU_NOFPUEX) +# define cpu_has_nofpuex __isa_lt_and_opt(1, MIPS_CPU_NOFPUEX) # endif # ifndef cpu_has_64bits # define cpu_has_64bits (cpu_data[0].isa_level & MIPS_CPU_ISA_64BIT) @@ -405,19 +443,19 @@ #endif #if defined(CONFIG_CPU_MIPSR2_IRQ_VI) && !defined(cpu_has_vint) -# define cpu_has_vint (cpu_data[0].options & MIPS_CPU_VINT) +# define cpu_has_vint __opt(MIPS_CPU_VINT) #elif !defined(cpu_has_vint) # define cpu_has_vint 0 #endif #if defined(CONFIG_CPU_MIPSR2_IRQ_EI) && !defined(cpu_has_veic) -# define cpu_has_veic (cpu_data[0].options & MIPS_CPU_VEIC) +# define cpu_has_veic __opt(MIPS_CPU_VEIC) #elif !defined(cpu_has_veic) # define cpu_has_veic 0 #endif #ifndef cpu_has_inclusive_pcaches -#define cpu_has_inclusive_pcaches (cpu_data[0].options & MIPS_CPU_INCLUSIVE_CACHES) +#define cpu_has_inclusive_pcaches __opt(MIPS_CPU_INCLUSIVE_CACHES) #endif #ifndef cpu_dcache_line_size @@ -438,63 +476,63 @@ #endif #ifndef cpu_has_perf_cntr_intr_bit -#define cpu_has_perf_cntr_intr_bit (cpu_data[0].options & MIPS_CPU_PCI) +#define cpu_has_perf_cntr_intr_bit __opt(MIPS_CPU_PCI) #endif #ifndef cpu_has_vz -#define cpu_has_vz (cpu_data[0].ases & MIPS_ASE_VZ) +#define cpu_has_vz __ase(MIPS_ASE_VZ) #endif #if defined(CONFIG_CPU_HAS_MSA) && !defined(cpu_has_msa) -# define cpu_has_msa (cpu_data[0].ases & MIPS_ASE_MSA) +# define cpu_has_msa __ase(MIPS_ASE_MSA) #elif !defined(cpu_has_msa) # define cpu_has_msa 0 #endif #ifndef cpu_has_ufr -# define cpu_has_ufr (cpu_data[0].options & MIPS_CPU_UFR) +# define cpu_has_ufr __opt(MIPS_CPU_UFR) #endif #ifndef cpu_has_fre -# define cpu_has_fre (cpu_data[0].options & MIPS_CPU_FRE) +# define cpu_has_fre __opt(MIPS_CPU_FRE) #endif #ifndef cpu_has_cdmm -# define cpu_has_cdmm (cpu_data[0].options & MIPS_CPU_CDMM) +# define cpu_has_cdmm __opt(MIPS_CPU_CDMM) #endif #ifndef cpu_has_small_pages -# define cpu_has_small_pages (cpu_data[0].options & MIPS_CPU_SP) +# define cpu_has_small_pages __opt(MIPS_CPU_SP) #endif #ifndef cpu_has_nan_legacy -#define cpu_has_nan_legacy (cpu_data[0].options & MIPS_CPU_NAN_LEGACY) +#define cpu_has_nan_legacy __isa_lt_and_opt(6, MIPS_CPU_NAN_LEGACY) #endif #ifndef cpu_has_nan_2008 -#define cpu_has_nan_2008 (cpu_data[0].options & MIPS_CPU_NAN_2008) +#define cpu_has_nan_2008 __isa_ge_or_opt(6, MIPS_CPU_NAN_2008) #endif #ifndef cpu_has_ebase_wg -# define cpu_has_ebase_wg (cpu_data[0].options & MIPS_CPU_EBASE_WG) +# define cpu_has_ebase_wg __opt(MIPS_CPU_EBASE_WG) #endif #ifndef cpu_has_badinstr -# define cpu_has_badinstr (cpu_data[0].options & MIPS_CPU_BADINSTR) +# define cpu_has_badinstr __isa_ge_or_opt(6, MIPS_CPU_BADINSTR) #endif #ifndef cpu_has_badinstrp -# define cpu_has_badinstrp (cpu_data[0].options & MIPS_CPU_BADINSTRP) +# define cpu_has_badinstrp __isa_ge_or_opt(6, MIPS_CPU_BADINSTRP) #endif #ifndef cpu_has_contextconfig -# define cpu_has_contextconfig (cpu_data[0].options & MIPS_CPU_CTXTC) +# define cpu_has_contextconfig __opt(MIPS_CPU_CTXTC) #endif #ifndef cpu_has_perf -# define cpu_has_perf (cpu_data[0].options & MIPS_CPU_PERF) +# define cpu_has_perf __opt(MIPS_CPU_PERF) #endif -#if defined(CONFIG_SMP) && (MIPS_ISA_REV >= 6) +#ifdef CONFIG_SMP /* * Some systems share FTLB RAMs between threads within a core (siblings in * kernel parlance). This means that FTLB entries may become invalid at almost @@ -507,7 +545,7 @@ */ # ifndef cpu_has_shared_ftlb_ram # define cpu_has_shared_ftlb_ram \ - (current_cpu_data.options & MIPS_CPU_SHARED_FTLB_RAM) + __isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_RAM) # endif /* @@ -524,9 +562,9 @@ */ # ifndef cpu_has_shared_ftlb_entries # define cpu_has_shared_ftlb_entries \ - (current_cpu_data.options & MIPS_CPU_SHARED_FTLB_ENTRIES) + __isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_ENTRIES) # endif -#endif /* SMP && MIPS_ISA_REV >= 6 */ +#endif /* SMP */ #ifndef cpu_has_shared_ftlb_ram # define cpu_has_shared_ftlb_ram 0 @@ -537,7 +575,7 @@ #ifdef CONFIG_MIPS_MT_SMP # define cpu_has_mipsmt_pertccounters \ - (cpu_data[0].options & MIPS_CPU_MT_PER_TC_PERF_COUNTERS) + __isa_lt_and_opt(6, MIPS_CPU_MT_PER_TC_PERF_COUNTERS) #else # define cpu_has_mipsmt_pertccounters 0 #endif /* CONFIG_MIPS_MT_SMP */ diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 5b9d02ef4f60..dacbdb84516a 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -225,31 +225,32 @@ * Definitions for 7:0 on legacy processors */ -#define PRID_REV_TX4927 0x0022 -#define PRID_REV_TX4937 0x0030 -#define PRID_REV_R4400 0x0040 -#define PRID_REV_R3000A 0x0030 -#define PRID_REV_R3000 0x0020 -#define PRID_REV_R2000A 0x0010 -#define PRID_REV_TX3912 0x0010 -#define PRID_REV_TX3922 0x0030 -#define PRID_REV_TX3927 0x0040 -#define PRID_REV_VR4111 0x0050 -#define PRID_REV_VR4181 0x0050 /* Same as VR4111 */ -#define PRID_REV_VR4121 0x0060 -#define PRID_REV_VR4122 0x0070 -#define PRID_REV_VR4181A 0x0070 /* Same as VR4122 */ -#define PRID_REV_VR4130 0x0080 -#define PRID_REV_34K_V1_0_2 0x0022 -#define PRID_REV_LOONGSON1B 0x0020 -#define PRID_REV_LOONGSON1C 0x0020 /* Same as Loongson-1B */ -#define PRID_REV_LOONGSON2E 0x0002 -#define PRID_REV_LOONGSON2F 0x0003 -#define PRID_REV_LOONGSON3A_R1 0x0005 -#define PRID_REV_LOONGSON3B_R1 0x0006 -#define PRID_REV_LOONGSON3B_R2 0x0007 -#define PRID_REV_LOONGSON3A_R2 0x0008 -#define PRID_REV_LOONGSON3A_R3 0x0009 +#define PRID_REV_TX4927 0x0022 +#define PRID_REV_TX4937 0x0030 +#define PRID_REV_R4400 0x0040 +#define PRID_REV_R3000A 0x0030 +#define PRID_REV_R3000 0x0020 +#define PRID_REV_R2000A 0x0010 +#define PRID_REV_TX3912 0x0010 +#define PRID_REV_TX3922 0x0030 +#define PRID_REV_TX3927 0x0040 +#define PRID_REV_VR4111 0x0050 +#define PRID_REV_VR4181 0x0050 /* Same as VR4111 */ +#define PRID_REV_VR4121 0x0060 +#define PRID_REV_VR4122 0x0070 +#define PRID_REV_VR4181A 0x0070 /* Same as VR4122 */ +#define PRID_REV_VR4130 0x0080 +#define PRID_REV_34K_V1_0_2 0x0022 +#define PRID_REV_LOONGSON1B 0x0020 +#define PRID_REV_LOONGSON1C 0x0020 /* Same as Loongson-1B */ +#define PRID_REV_LOONGSON2E 0x0002 +#define PRID_REV_LOONGSON2F 0x0003 +#define PRID_REV_LOONGSON3A_R1 0x0005 +#define PRID_REV_LOONGSON3B_R1 0x0006 +#define PRID_REV_LOONGSON3B_R2 0x0007 +#define PRID_REV_LOONGSON3A_R2 0x0008 +#define PRID_REV_LOONGSON3A_R3_0 0x0009 +#define PRID_REV_LOONGSON3A_R3_1 0x000d /* * Older processors used to encode processor version and revision in two diff --git a/arch/mips/include/asm/dma-coherence.h b/arch/mips/include/asm/dma-coherence.h index 72d0eab02afc..8eda48748ed5 100644 --- a/arch/mips/include/asm/dma-coherence.h +++ b/arch/mips/include/asm/dma-coherence.h @@ -21,10 +21,10 @@ enum coherent_io_user_state { extern enum coherent_io_user_state coherentio; extern int hw_coherentio; #else -#ifdef CONFIG_DMA_COHERENT -#define coherentio IO_COHERENCE_ENABLED -#else +#ifdef CONFIG_DMA_NONCOHERENT #define coherentio IO_COHERENCE_DISABLED +#else +#define coherentio IO_COHERENCE_ENABLED #endif #define hw_coherentio 0 #endif /* CONFIG_DMA_MAYBE_COHERENT */ diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h index f32f15530aba..b5c240806e1b 100644 --- a/arch/mips/include/asm/dma-direct.h +++ b/arch/mips/include/asm/dma-direct.h @@ -1 +1,16 @@ -#include <asm/dma-coherence.h> +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MIPS_DMA_DIRECT_H +#define _MIPS_DMA_DIRECT_H 1 + +static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) +{ + if (!dev->dma_mask) + return false; + + return addr + size - 1 <= *dev->dma_mask; +} + +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr); +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr); + +#endif /* _MIPS_DMA_DIRECT_H */ diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h index 886e75a383f2..e81c4e97ff1a 100644 --- a/arch/mips/include/asm/dma-mapping.h +++ b/arch/mips/include/asm/dma-mapping.h @@ -2,19 +2,21 @@ #ifndef _ASM_DMA_MAPPING_H #define _ASM_DMA_MAPPING_H -#include <linux/scatterlist.h> -#include <asm/dma-coherence.h> -#include <asm/cache.h> +#include <linux/swiotlb.h> -#ifndef CONFIG_SGI_IP27 /* Kludge to fix 2.6.39 build for IP27 */ -#include <dma-coherence.h> -#endif - -extern const struct dma_map_ops *mips_dma_map_ops; +extern const struct dma_map_ops jazz_dma_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - return mips_dma_map_ops; +#if defined(CONFIG_MACH_JAZZ) + return &jazz_dma_ops; +#elif defined(CONFIG_SWIOTLB) + return &swiotlb_dma_ops; +#elif defined(CONFIG_DMA_NONCOHERENT_OPS) + return &dma_noncoherent_ops; +#else + return &dma_direct_ops; +#endif } #define arch_setup_dma_ops arch_setup_dma_ops diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index cea8ad864b3f..54c730aed327 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -12,6 +12,8 @@ #ifndef _ASM_IO_H #define _ASM_IO_H +#define ARCH_HAS_IOREMAP_WC + #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/types.h> @@ -141,14 +143,14 @@ static inline void * phys_to_virt(unsigned long address) /* * ISA I/O bus memory addresses are 1:1 with the physical address. */ -static inline unsigned long isa_virt_to_bus(volatile void * address) +static inline unsigned long isa_virt_to_bus(volatile void *address) { - return (unsigned long)address - PAGE_OFFSET; + return virt_to_phys(address); } -static inline void * isa_bus_to_virt(unsigned long address) +static inline void *isa_bus_to_virt(unsigned long address) { - return (void *)(address + PAGE_OFFSET); + return phys_to_virt(address); } #define isa_page_to_bus page_to_phys @@ -278,15 +280,25 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si #define ioremap_cache ioremap_cachable /* - * These two are MIPS specific ioremap variant. ioremap_cacheable_cow - * requests a cachable mapping, ioremap_uncached_accelerated requests a - * mapping using the uncached accelerated mode which isn't supported on - * all processors. + * ioremap_wc - map bus memory into CPU space + * @offset: bus address of the memory + * @size: size of the resource to map + * + * ioremap_wc performs a platform specific sequence of operations to + * make bus memory CPU accessible via the readb/readw/readl/writeb/ + * writew/writel functions and the other mmio helpers. The returned + * address is not guaranteed to be usable directly as a virtual + * address. + * + * This version of ioremap ensures that the memory is marked uncachable + * but accelerated by means of write-combining feature. It is specifically + * useful for PCIe prefetchable windows, which may vastly improve a + * communications performance. If it was determined on boot stage, what + * CPU CCA doesn't support UCA, the method shall fall-back to the + * _CACHE_UNCACHED option (see cpu_probe() method). */ -#define ioremap_cacheable_cow(offset, size) \ - __ioremap_mode((offset), (size), _CACHE_CACHABLE_COW) -#define ioremap_uncached_accelerated(offset, size) \ - __ioremap_mode((offset), (size), _CACHE_UNCACHED_ACCELERATED) +#define ioremap_wc(offset, size) \ + __ioremap_mode((offset), (size), boot_cpu_data.writecombine) static inline void iounmap(const volatile void __iomem *addr) { @@ -590,7 +602,7 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int * * This API used to be exported; it now is for arch code internal use only. */ -#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT) +#ifdef CONFIG_DMA_NONCOHERENT extern void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size); extern void (*_dma_cache_wback)(unsigned long start, unsigned long size); @@ -609,7 +621,7 @@ extern void (*_dma_cache_inv)(unsigned long start, unsigned long size); #define dma_cache_inv(start,size) \ do { (void) (start); (void) (size); } while (0) -#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */ +#endif /* CONFIG_DMA_NONCOHERENT */ /* * Read a 32-bit register that requires a 64-bit read cycle on the bus. diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h index ad1a99948f27..a72dfbf1babb 100644 --- a/arch/mips/include/asm/kprobes.h +++ b/arch/mips/include/asm/kprobes.h @@ -68,16 +68,6 @@ struct prev_kprobe { unsigned long saved_epc; }; -#define MAX_JPROBES_STACK_SIZE 128 -#define MAX_JPROBES_STACK_ADDR \ - (((unsigned long)current_thread_info()) + THREAD_SIZE - 32 - sizeof(struct pt_regs)) - -#define MIN_JPROBES_STACK_SIZE(ADDR) \ - ((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR) \ - ? MAX_JPROBES_STACK_ADDR - (ADDR) \ - : MAX_JPROBES_STACK_SIZE) - - #define SKIP_DELAYSLOT 0x0001 /* per-cpu kprobe control block */ @@ -86,12 +76,9 @@ struct kprobe_ctlblk { unsigned long kprobe_old_SR; unsigned long kprobe_saved_SR; unsigned long kprobe_saved_epc; - unsigned long jprobe_saved_sp; - struct pt_regs jprobe_saved_regs; /* Per-thread fields, used while emulating branches */ unsigned long flags; unsigned long target_epc; - u8 jprobes_stack[MAX_JPROBES_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/mips/include/asm/mach-ar7/spaces.h b/arch/mips/include/asm/mach-ar7/spaces.h index 660ab64c0fc9..a004d94dfbdd 100644 --- a/arch/mips/include/asm/mach-ar7/spaces.h +++ b/arch/mips/include/asm/mach-ar7/spaces.h @@ -17,9 +17,6 @@ #define PAGE_OFFSET _AC(0x94000000, UL) #define PHYS_OFFSET _AC(0x14000000, UL) -#define UNCAC_BASE _AC(0xb4000000, UL) /* 0xa0000000 + PHYS_OFFSET */ -#define IO_BASE UNCAC_BASE - #include <asm/mach-generic/spaces.h> #endif /* __ASM_AR7_SPACES_H */ diff --git a/arch/mips/include/asm/mach-ath25/dma-coherence.h b/arch/mips/include/asm/mach-ath25/dma-coherence.h deleted file mode 100644 index d5defdde32db..000000000000 --- a/arch/mips/include/asm/mach-ath25/dma-coherence.h +++ /dev/null @@ -1,76 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org> - * Copyright (C) 2007 Felix Fietkau <nbd@openwrt.org> - * - */ -#ifndef __ASM_MACH_ATH25_DMA_COHERENCE_H -#define __ASM_MACH_ATH25_DMA_COHERENCE_H - -#include <linux/device.h> - -/* - * We need some arbitrary non-zero value to be programmed to the BAR1 register - * of PCI host controller to enable DMA. The same value should be used as the - * offset to calculate the physical address of DMA buffer for PCI devices. - */ -#define AR2315_PCI_HOST_SDRAM_BASEADDR 0x20000000 - -static inline dma_addr_t ath25_dev_offset(struct device *dev) -{ -#ifdef CONFIG_PCI - extern struct bus_type pci_bus_type; - - if (dev && dev->bus == &pci_bus_type) - return AR2315_PCI_HOST_SDRAM_BASEADDR; -#endif - return 0; -} - -static inline dma_addr_t -plat_map_dma_mem(struct device *dev, void *addr, size_t size) -{ - return virt_to_phys(addr) + ath25_dev_offset(dev); -} - -static inline dma_addr_t -plat_map_dma_mem_page(struct device *dev, struct page *page) -{ - return page_to_phys(page) + ath25_dev_offset(dev); -} - -static inline unsigned long -plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr) -{ - return dma_addr - ath25_dev_offset(dev); -} - -static inline void -plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction direction) -{ -} - -static inline int plat_dma_supported(struct device *dev, u64 mask) -{ - return 1; -} - -static inline int plat_device_is_coherent(struct device *dev) -{ -#ifdef CONFIG_DMA_COHERENT - return 1; -#endif -#ifdef CONFIG_DMA_NONCOHERENT - return 0; -#endif -} - -static inline void plat_post_dma_flush(struct device *dev) -{ -} - -#endif /* __ASM_MACH_ATH25_DMA_COHERENCE_H */ diff --git a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h index d99ca862dae3..284b4fa23e03 100644 --- a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h +++ b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h @@ -20,6 +20,10 @@ #include <linux/bitops.h> #define AR71XX_APB_BASE 0x18000000 +#define AR71XX_GE0_BASE 0x19000000 +#define AR71XX_GE0_SIZE 0x10000 +#define AR71XX_GE1_BASE 0x1a000000 +#define AR71XX_GE1_SIZE 0x10000 #define AR71XX_EHCI_BASE 0x1b000000 #define AR71XX_EHCI_SIZE 0x1000 #define AR71XX_OHCI_BASE 0x1c000000 @@ -39,6 +43,8 @@ #define AR71XX_PLL_SIZE 0x100 #define AR71XX_RESET_BASE (AR71XX_APB_BASE + 0x00060000) #define AR71XX_RESET_SIZE 0x100 +#define AR71XX_MII_BASE (AR71XX_APB_BASE + 0x00070000) +#define AR71XX_MII_SIZE 0x100 #define AR71XX_PCI_MEM_BASE 0x10000000 #define AR71XX_PCI_MEM_SIZE 0x07000000 @@ -81,18 +87,39 @@ #define AR933X_UART_BASE (AR71XX_APB_BASE + 0x00020000) #define AR933X_UART_SIZE 0x14 +#define AR933X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000) +#define AR933X_GMAC_SIZE 0x04 #define AR933X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000) #define AR933X_WMAC_SIZE 0x20000 #define AR933X_EHCI_BASE 0x1b000000 #define AR933X_EHCI_SIZE 0x1000 +#define AR934X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000) +#define AR934X_GMAC_SIZE 0x14 #define AR934X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000) #define AR934X_WMAC_SIZE 0x20000 #define AR934X_EHCI_BASE 0x1b000000 #define AR934X_EHCI_SIZE 0x200 +#define AR934X_NFC_BASE 0x1b000200 +#define AR934X_NFC_SIZE 0xb8 #define AR934X_SRIF_BASE (AR71XX_APB_BASE + 0x00116000) #define AR934X_SRIF_SIZE 0x1000 +#define QCA953X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000) +#define QCA953X_GMAC_SIZE 0x14 +#define QCA953X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000) +#define QCA953X_WMAC_SIZE 0x20000 +#define QCA953X_EHCI_BASE 0x1b000000 +#define QCA953X_EHCI_SIZE 0x200 +#define QCA953X_SRIF_BASE (AR71XX_APB_BASE + 0x00116000) +#define QCA953X_SRIF_SIZE 0x1000 + +#define QCA953X_PCI_CFG_BASE0 0x14000000 +#define QCA953X_PCI_CTRL_BASE0 (AR71XX_APB_BASE + 0x000f0000) +#define QCA953X_PCI_CRP_BASE0 (AR71XX_APB_BASE + 0x000c0000) +#define QCA953X_PCI_MEM_BASE0 0x10000000 +#define QCA953X_PCI_MEM_SIZE 0x02000000 + #define QCA955X_PCI_MEM_BASE0 0x10000000 #define QCA955X_PCI_MEM_BASE1 0x12000000 #define QCA955X_PCI_MEM_SIZE 0x02000000 @@ -106,11 +133,72 @@ #define QCA955X_PCI_CTRL_BASE1 (AR71XX_APB_BASE + 0x00280000) #define QCA955X_PCI_CTRL_SIZE 0x100 +#define QCA955X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000) +#define QCA955X_GMAC_SIZE 0x40 #define QCA955X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000) #define QCA955X_WMAC_SIZE 0x20000 #define QCA955X_EHCI0_BASE 0x1b000000 #define QCA955X_EHCI1_BASE 0x1b400000 #define QCA955X_EHCI_SIZE 0x1000 +#define QCA955X_NFC_BASE 0x1b800200 +#define QCA955X_NFC_SIZE 0xb8 + +#define QCA956X_PCI_MEM_BASE1 0x12000000 +#define QCA956X_PCI_MEM_SIZE 0x02000000 +#define QCA956X_PCI_CFG_BASE1 0x16000000 +#define QCA956X_PCI_CFG_SIZE 0x1000 +#define QCA956X_PCI_CRP_BASE1 (AR71XX_APB_BASE + 0x00250000) +#define QCA956X_PCI_CRP_SIZE 0x1000 +#define QCA956X_PCI_CTRL_BASE1 (AR71XX_APB_BASE + 0x00280000) +#define QCA956X_PCI_CTRL_SIZE 0x100 + +#define QCA956X_WMAC_BASE (AR71XX_APB_BASE + 0x00100000) +#define QCA956X_WMAC_SIZE 0x20000 +#define QCA956X_EHCI0_BASE 0x1b000000 +#define QCA956X_EHCI1_BASE 0x1b400000 +#define QCA956X_EHCI_SIZE 0x200 +#define QCA956X_GMAC_SGMII_BASE (AR71XX_APB_BASE + 0x00070000) +#define QCA956X_GMAC_SGMII_SIZE 0x64 +#define QCA956X_PLL_BASE (AR71XX_APB_BASE + 0x00050000) +#define QCA956X_PLL_SIZE 0x50 +#define QCA956X_GMAC_BASE (AR71XX_APB_BASE + 0x00070000) +#define QCA956X_GMAC_SIZE 0x64 + +/* + * Hidden Registers + */ +#define QCA956X_MAC_CFG_BASE 0xb9000000 +#define QCA956X_MAC_CFG_SIZE 0x64 + +#define QCA956X_MAC_CFG1_REG 0x00 +#define QCA956X_MAC_CFG1_SOFT_RST BIT(31) +#define QCA956X_MAC_CFG1_RX_RST BIT(19) +#define QCA956X_MAC_CFG1_TX_RST BIT(18) +#define QCA956X_MAC_CFG1_LOOPBACK BIT(8) +#define QCA956X_MAC_CFG1_RX_EN BIT(2) +#define QCA956X_MAC_CFG1_TX_EN BIT(0) + +#define QCA956X_MAC_CFG2_REG 0x04 +#define QCA956X_MAC_CFG2_IF_1000 BIT(9) +#define QCA956X_MAC_CFG2_IF_10_100 BIT(8) +#define QCA956X_MAC_CFG2_HUGE_FRAME_EN BIT(5) +#define QCA956X_MAC_CFG2_LEN_CHECK BIT(4) +#define QCA956X_MAC_CFG2_PAD_CRC_EN BIT(2) +#define QCA956X_MAC_CFG2_FDX BIT(0) + +#define QCA956X_MAC_MII_MGMT_CFG_REG 0x20 +#define QCA956X_MGMT_CFG_CLK_DIV_20 0x07 + +#define QCA956X_MAC_FIFO_CFG0_REG 0x48 +#define QCA956X_MAC_FIFO_CFG1_REG 0x4c +#define QCA956X_MAC_FIFO_CFG2_REG 0x50 +#define QCA956X_MAC_FIFO_CFG3_REG 0x54 +#define QCA956X_MAC_FIFO_CFG4_REG 0x58 +#define QCA956X_MAC_FIFO_CFG5_REG 0x5c + +#define QCA956X_DAM_RESET_OFFSET 0xb90001bc +#define QCA956X_DAM_RESET_SIZE 0x4 +#define QCA956X_INLINE_CHKSUM_ENG BIT(27) /* * DDR_CTRL block @@ -149,6 +237,12 @@ #define AR934X_DDR_REG_FLUSH_PCIE 0xa8 #define AR934X_DDR_REG_FLUSH_WMAC 0xac +#define QCA953X_DDR_REG_FLUSH_GE0 0x9c +#define QCA953X_DDR_REG_FLUSH_GE1 0xa0 +#define QCA953X_DDR_REG_FLUSH_USB 0xa4 +#define QCA953X_DDR_REG_FLUSH_PCIE 0xa8 +#define QCA953X_DDR_REG_FLUSH_WMAC 0xac + /* * PLL block */ @@ -166,9 +260,15 @@ #define AR71XX_AHB_DIV_SHIFT 20 #define AR71XX_AHB_DIV_MASK 0x7 +#define AR71XX_ETH0_PLL_SHIFT 17 +#define AR71XX_ETH1_PLL_SHIFT 19 + #define AR724X_PLL_REG_CPU_CONFIG 0x00 #define AR724X_PLL_REG_PCIE_CONFIG 0x10 +#define AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS BIT(16) +#define AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET BIT(25) + #define AR724X_PLL_FB_SHIFT 0 #define AR724X_PLL_FB_MASK 0x3ff #define AR724X_PLL_REF_DIV_SHIFT 10 @@ -178,6 +278,8 @@ #define AR724X_DDR_DIV_SHIFT 22 #define AR724X_DDR_DIV_MASK 0x3 +#define AR7242_PLL_REG_ETH0_INT_CLOCK 0x2c + #define AR913X_PLL_REG_CPU_CONFIG 0x00 #define AR913X_PLL_REG_ETH_CONFIG 0x04 #define AR913X_PLL_REG_ETH0_INT_CLOCK 0x14 @@ -190,6 +292,9 @@ #define AR913X_AHB_DIV_SHIFT 19 #define AR913X_AHB_DIV_MASK 0x1 +#define AR913X_ETH0_PLL_SHIFT 20 +#define AR913X_ETH1_PLL_SHIFT 22 + #define AR933X_PLL_CPU_CONFIG_REG 0x00 #define AR933X_PLL_CLOCK_CTRL_REG 0x08 @@ -211,6 +316,8 @@ #define AR934X_PLL_CPU_CONFIG_REG 0x00 #define AR934X_PLL_DDR_CONFIG_REG 0x04 #define AR934X_PLL_CPU_DDR_CLK_CTRL_REG 0x08 +#define AR934X_PLL_SWITCH_CLOCK_CONTROL_REG 0x24 +#define AR934X_PLL_ETH_XMII_CONTROL_REG 0x2c #define AR934X_PLL_CPU_CONFIG_NFRAC_SHIFT 0 #define AR934X_PLL_CPU_CONFIG_NFRAC_MASK 0x3f @@ -243,9 +350,52 @@ #define AR934X_PLL_CPU_DDR_CLK_CTRL_DDRCLK_FROM_DDRPLL BIT(21) #define AR934X_PLL_CPU_DDR_CLK_CTRL_AHBCLK_FROM_DDRPLL BIT(24) +#define AR934X_PLL_SWITCH_CLOCK_CONTROL_MDIO_CLK_SEL BIT(6) + +#define QCA953X_PLL_CPU_CONFIG_REG 0x00 +#define QCA953X_PLL_DDR_CONFIG_REG 0x04 +#define QCA953X_PLL_CLK_CTRL_REG 0x08 +#define QCA953X_PLL_SWITCH_CLOCK_CONTROL_REG 0x24 +#define QCA953X_PLL_ETH_XMII_CONTROL_REG 0x2c +#define QCA953X_PLL_ETH_SGMII_CONTROL_REG 0x48 + +#define QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT 0 +#define QCA953X_PLL_CPU_CONFIG_NFRAC_MASK 0x3f +#define QCA953X_PLL_CPU_CONFIG_NINT_SHIFT 6 +#define QCA953X_PLL_CPU_CONFIG_NINT_MASK 0x3f +#define QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT 12 +#define QCA953X_PLL_CPU_CONFIG_REFDIV_MASK 0x1f +#define QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT 19 +#define QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK 0x7 + +#define QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT 0 +#define QCA953X_PLL_DDR_CONFIG_NFRAC_MASK 0x3ff +#define QCA953X_PLL_DDR_CONFIG_NINT_SHIFT 10 +#define QCA953X_PLL_DDR_CONFIG_NINT_MASK 0x3f +#define QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT 16 +#define QCA953X_PLL_DDR_CONFIG_REFDIV_MASK 0x1f +#define QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT 23 +#define QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK 0x7 + +#define QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS BIT(2) +#define QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS BIT(3) +#define QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS BIT(4) +#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT 5 +#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK 0x1f +#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT 10 +#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK 0x1f +#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT 15 +#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK 0x1f +#define QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL BIT(20) +#define QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL BIT(21) +#define QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL BIT(24) + #define QCA955X_PLL_CPU_CONFIG_REG 0x00 #define QCA955X_PLL_DDR_CONFIG_REG 0x04 #define QCA955X_PLL_CLK_CTRL_REG 0x08 +#define QCA955X_PLL_ETH_XMII_CONTROL_REG 0x28 +#define QCA955X_PLL_ETH_SGMII_CONTROL_REG 0x48 +#define QCA955X_PLL_ETH_SGMII_SERDES_REG 0x4c #define QCA955X_PLL_CPU_CONFIG_NFRAC_SHIFT 0 #define QCA955X_PLL_CPU_CONFIG_NFRAC_MASK 0x3f @@ -278,6 +428,81 @@ #define QCA955X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL BIT(21) #define QCA955X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL BIT(24) +#define QCA955X_PLL_ETH_SGMII_SERDES_LOCK_DETECT BIT(2) +#define QCA955X_PLL_ETH_SGMII_SERDES_PLL_REFCLK BIT(1) +#define QCA955X_PLL_ETH_SGMII_SERDES_EN_PLL BIT(0) + +#define QCA956X_PLL_CPU_CONFIG_REG 0x00 +#define QCA956X_PLL_CPU_CONFIG1_REG 0x04 +#define QCA956X_PLL_DDR_CONFIG_REG 0x08 +#define QCA956X_PLL_DDR_CONFIG1_REG 0x0c +#define QCA956X_PLL_CLK_CTRL_REG 0x10 +#define QCA956X_PLL_SWITCH_CLOCK_CONTROL_REG 0x28 +#define QCA956X_PLL_ETH_XMII_CONTROL_REG 0x30 +#define QCA956X_PLL_ETH_SGMII_SERDES_REG 0x4c + +#define QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT 12 +#define QCA956X_PLL_CPU_CONFIG_REFDIV_MASK 0x1f +#define QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT 19 +#define QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK 0x7 + +#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT 0 +#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK 0x1f +#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT 5 +#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK 0x1fff +#define QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT 18 +#define QCA956X_PLL_CPU_CONFIG1_NINT_MASK 0x1ff + +#define QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT 16 +#define QCA956X_PLL_DDR_CONFIG_REFDIV_MASK 0x1f +#define QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT 23 +#define QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK 0x7 + +#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT 0 +#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK 0x1f +#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT 5 +#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK 0x1fff +#define QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT 18 +#define QCA956X_PLL_DDR_CONFIG1_NINT_MASK 0x1ff + +#define QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS BIT(2) +#define QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS BIT(3) +#define QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS BIT(4) +#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT 5 +#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK 0x1f +#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT 10 +#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK 0x1f +#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT 15 +#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK 0x1f +#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL BIT(20) +#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL BIT(21) +#define QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL BIT(24) + +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_I2C_CLK_SELB BIT(5) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_1 BIT(6) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_UART1_CLK_SEL BIT(7) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_SHIFT 8 +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_MASK 0xf +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EN_PLL_TOP BIT(12) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_2 BIT(13) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_1 BIT(14) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_2 BIT(15) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCH_FUNC_TST_MODE BIT(16) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EEE_ENABLE BIT(17) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_OEN_CLK125M_PLL BIT(18) +#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCHCLK_SEL BIT(19) + +#define QCA956X_PLL_ETH_XMII_TX_INVERT BIT(1) +#define QCA956X_PLL_ETH_XMII_GIGE BIT(25) +#define QCA956X_PLL_ETH_XMII_RX_DELAY_SHIFT 28 +#define QCA956X_PLL_ETH_XMII_RX_DELAY_MASK 0x3 +#define QCA956X_PLL_ETH_XMII_TX_DELAY_SHIFT 26 +#define QCA956X_PLL_ETH_XMII_TX_DELAY_MASK 3 + +#define QCA956X_PLL_ETH_SGMII_SERDES_LOCK_DETECT BIT(2) +#define QCA956X_PLL_ETH_SGMII_SERDES_PLL_REFCLK BIT(1) +#define QCA956X_PLL_ETH_SGMII_SERDES_EN_PLL BIT(0) + /* * USB_CONFIG block */ @@ -317,10 +542,19 @@ #define AR934X_RESET_REG_BOOTSTRAP 0xb0 #define AR934X_RESET_REG_PCIE_WMAC_INT_STATUS 0xac +#define QCA953X_RESET_REG_RESET_MODULE 0x1c +#define QCA953X_RESET_REG_BOOTSTRAP 0xb0 +#define QCA953X_RESET_REG_PCIE_WMAC_INT_STATUS 0xac + #define QCA955X_RESET_REG_RESET_MODULE 0x1c #define QCA955X_RESET_REG_BOOTSTRAP 0xb0 #define QCA955X_RESET_REG_EXT_INT_STATUS 0xac +#define QCA956X_RESET_REG_RESET_MODULE 0x1c +#define QCA956X_RESET_REG_BOOTSTRAP 0xb0 +#define QCA956X_RESET_REG_EXT_INT_STATUS 0xac + +#define MISC_INT_MIPS_SI_TIMERINT_MASK BIT(28) #define MISC_INT_ETHSW BIT(12) #define MISC_INT_TIMER4 BIT(10) #define MISC_INT_TIMER3 BIT(9) @@ -370,16 +604,123 @@ #define AR913X_RESET_USB_HOST BIT(5) #define AR913X_RESET_USB_PHY BIT(4) +#define AR933X_RESET_GE1_MDIO BIT(23) +#define AR933X_RESET_GE0_MDIO BIT(22) +#define AR933X_RESET_GE1_MAC BIT(13) #define AR933X_RESET_WMAC BIT(11) +#define AR933X_RESET_GE0_MAC BIT(9) #define AR933X_RESET_USB_HOST BIT(5) #define AR933X_RESET_USB_PHY BIT(4) #define AR933X_RESET_USBSUS_OVERRIDE BIT(3) +#define AR934X_RESET_HOST BIT(31) +#define AR934X_RESET_SLIC BIT(30) +#define AR934X_RESET_HDMA BIT(29) +#define AR934X_RESET_EXTERNAL BIT(28) +#define AR934X_RESET_RTC BIT(27) +#define AR934X_RESET_PCIE_EP_INT BIT(26) +#define AR934X_RESET_CHKSUM_ACC BIT(25) +#define AR934X_RESET_FULL_CHIP BIT(24) +#define AR934X_RESET_GE1_MDIO BIT(23) +#define AR934X_RESET_GE0_MDIO BIT(22) +#define AR934X_RESET_CPU_NMI BIT(21) +#define AR934X_RESET_CPU_COLD BIT(20) +#define AR934X_RESET_HOST_RESET_INT BIT(19) +#define AR934X_RESET_PCIE_EP BIT(18) +#define AR934X_RESET_UART1 BIT(17) +#define AR934X_RESET_DDR BIT(16) +#define AR934X_RESET_USB_PHY_PLL_PWD_EXT BIT(15) +#define AR934X_RESET_NANDF BIT(14) +#define AR934X_RESET_GE1_MAC BIT(13) +#define AR934X_RESET_ETH_SWITCH_ANALOG BIT(12) #define AR934X_RESET_USB_PHY_ANALOG BIT(11) +#define AR934X_RESET_HOST_DMA_INT BIT(10) +#define AR934X_RESET_GE0_MAC BIT(9) +#define AR934X_RESET_ETH_SWITCH BIT(8) +#define AR934X_RESET_PCIE_PHY BIT(7) +#define AR934X_RESET_PCIE BIT(6) #define AR934X_RESET_USB_HOST BIT(5) #define AR934X_RESET_USB_PHY BIT(4) #define AR934X_RESET_USBSUS_OVERRIDE BIT(3) - +#define AR934X_RESET_LUT BIT(2) +#define AR934X_RESET_MBOX BIT(1) +#define AR934X_RESET_I2S BIT(0) + +#define QCA953X_RESET_USB_EXT_PWR BIT(29) +#define QCA953X_RESET_EXTERNAL BIT(28) +#define QCA953X_RESET_RTC BIT(27) +#define QCA953X_RESET_FULL_CHIP BIT(24) +#define QCA953X_RESET_GE1_MDIO BIT(23) +#define QCA953X_RESET_GE0_MDIO BIT(22) +#define QCA953X_RESET_CPU_NMI BIT(21) +#define QCA953X_RESET_CPU_COLD BIT(20) +#define QCA953X_RESET_DDR BIT(16) +#define QCA953X_RESET_USB_PHY_PLL_PWD_EXT BIT(15) +#define QCA953X_RESET_GE1_MAC BIT(13) +#define QCA953X_RESET_ETH_SWITCH_ANALOG BIT(12) +#define QCA953X_RESET_USB_PHY_ANALOG BIT(11) +#define QCA953X_RESET_GE0_MAC BIT(9) +#define QCA953X_RESET_ETH_SWITCH BIT(8) +#define QCA953X_RESET_PCIE_PHY BIT(7) +#define QCA953X_RESET_PCIE BIT(6) +#define QCA953X_RESET_USB_HOST BIT(5) +#define QCA953X_RESET_USB_PHY BIT(4) +#define QCA953X_RESET_USBSUS_OVERRIDE BIT(3) + +#define QCA955X_RESET_HOST BIT(31) +#define QCA955X_RESET_SLIC BIT(30) +#define QCA955X_RESET_HDMA BIT(29) +#define QCA955X_RESET_EXTERNAL BIT(28) +#define QCA955X_RESET_RTC BIT(27) +#define QCA955X_RESET_PCIE_EP_INT BIT(26) +#define QCA955X_RESET_CHKSUM_ACC BIT(25) +#define QCA955X_RESET_FULL_CHIP BIT(24) +#define QCA955X_RESET_GE1_MDIO BIT(23) +#define QCA955X_RESET_GE0_MDIO BIT(22) +#define QCA955X_RESET_CPU_NMI BIT(21) +#define QCA955X_RESET_CPU_COLD BIT(20) +#define QCA955X_RESET_HOST_RESET_INT BIT(19) +#define QCA955X_RESET_PCIE_EP BIT(18) +#define QCA955X_RESET_UART1 BIT(17) +#define QCA955X_RESET_DDR BIT(16) +#define QCA955X_RESET_USB_PHY_PLL_PWD_EXT BIT(15) +#define QCA955X_RESET_NANDF BIT(14) +#define QCA955X_RESET_GE1_MAC BIT(13) +#define QCA955X_RESET_SGMII_ANALOG BIT(12) +#define QCA955X_RESET_USB_PHY_ANALOG BIT(11) +#define QCA955X_RESET_HOST_DMA_INT BIT(10) +#define QCA955X_RESET_GE0_MAC BIT(9) +#define QCA955X_RESET_SGMII BIT(8) +#define QCA955X_RESET_PCIE_PHY BIT(7) +#define QCA955X_RESET_PCIE BIT(6) +#define QCA955X_RESET_USB_HOST BIT(5) +#define QCA955X_RESET_USB_PHY BIT(4) +#define QCA955X_RESET_USBSUS_OVERRIDE BIT(3) +#define QCA955X_RESET_LUT BIT(2) +#define QCA955X_RESET_MBOX BIT(1) +#define QCA955X_RESET_I2S BIT(0) + +#define QCA956X_RESET_EXTERNAL BIT(28) +#define QCA956X_RESET_FULL_CHIP BIT(24) +#define QCA956X_RESET_GE1_MDIO BIT(23) +#define QCA956X_RESET_GE0_MDIO BIT(22) +#define QCA956X_RESET_CPU_NMI BIT(21) +#define QCA956X_RESET_CPU_COLD BIT(20) +#define QCA956X_RESET_DMA BIT(19) +#define QCA956X_RESET_DDR BIT(16) +#define QCA956X_RESET_GE1_MAC BIT(13) +#define QCA956X_RESET_SGMII_ANALOG BIT(12) +#define QCA956X_RESET_USB_PHY_ANALOG BIT(11) +#define QCA956X_RESET_GE0_MAC BIT(9) +#define QCA956X_RESET_SGMII BIT(8) +#define QCA956X_RESET_USB_HOST BIT(5) +#define QCA956X_RESET_USB_PHY BIT(4) +#define QCA956X_RESET_USBSUS_OVERRIDE BIT(3) +#define QCA956X_RESET_SWITCH_ANALOG BIT(2) +#define QCA956X_RESET_SWITCH BIT(0) + +#define AR933X_BOOTSTRAP_MDIO_GPIO_EN BIT(18) +#define AR933X_BOOTSTRAP_EEPBUSY BIT(4) #define AR933X_BOOTSTRAP_REF_CLK_40 BIT(0) #define AR934X_BOOTSTRAP_SW_OPTION8 BIT(23) @@ -398,8 +739,17 @@ #define AR934X_BOOTSTRAP_SDRAM_DISABLED BIT(1) #define AR934X_BOOTSTRAP_DDR1 BIT(0) +#define QCA953X_BOOTSTRAP_SW_OPTION2 BIT(12) +#define QCA953X_BOOTSTRAP_SW_OPTION1 BIT(11) +#define QCA953X_BOOTSTRAP_EJTAG_MODE BIT(5) +#define QCA953X_BOOTSTRAP_REF_CLK_40 BIT(4) +#define QCA953X_BOOTSTRAP_SDRAM_DISABLED BIT(1) +#define QCA953X_BOOTSTRAP_DDR1 BIT(0) + #define QCA955X_BOOTSTRAP_REF_CLK_40 BIT(4) +#define QCA956X_BOOTSTRAP_REF_CLK_40 BIT(2) + #define AR934X_PCIE_WMAC_INT_WMAC_MISC BIT(0) #define AR934X_PCIE_WMAC_INT_WMAC_TX BIT(1) #define AR934X_PCIE_WMAC_INT_WMAC_RXLP BIT(2) @@ -418,6 +768,24 @@ AR934X_PCIE_WMAC_INT_PCIE_RC1 | AR934X_PCIE_WMAC_INT_PCIE_RC2 | \ AR934X_PCIE_WMAC_INT_PCIE_RC3) +#define QCA953X_PCIE_WMAC_INT_WMAC_MISC BIT(0) +#define QCA953X_PCIE_WMAC_INT_WMAC_TX BIT(1) +#define QCA953X_PCIE_WMAC_INT_WMAC_RXLP BIT(2) +#define QCA953X_PCIE_WMAC_INT_WMAC_RXHP BIT(3) +#define QCA953X_PCIE_WMAC_INT_PCIE_RC BIT(4) +#define QCA953X_PCIE_WMAC_INT_PCIE_RC0 BIT(5) +#define QCA953X_PCIE_WMAC_INT_PCIE_RC1 BIT(6) +#define QCA953X_PCIE_WMAC_INT_PCIE_RC2 BIT(7) +#define QCA953X_PCIE_WMAC_INT_PCIE_RC3 BIT(8) +#define QCA953X_PCIE_WMAC_INT_WMAC_ALL \ + (QCA953X_PCIE_WMAC_INT_WMAC_MISC | QCA953X_PCIE_WMAC_INT_WMAC_TX | \ + QCA953X_PCIE_WMAC_INT_WMAC_RXLP | QCA953X_PCIE_WMAC_INT_WMAC_RXHP) + +#define QCA953X_PCIE_WMAC_INT_PCIE_ALL \ + (QCA953X_PCIE_WMAC_INT_PCIE_RC | QCA953X_PCIE_WMAC_INT_PCIE_RC0 | \ + QCA953X_PCIE_WMAC_INT_PCIE_RC1 | QCA953X_PCIE_WMAC_INT_PCIE_RC2 | \ + QCA953X_PCIE_WMAC_INT_PCIE_RC3) + #define QCA955X_EXT_INT_WMAC_MISC BIT(0) #define QCA955X_EXT_INT_WMAC_TX BIT(1) #define QCA955X_EXT_INT_WMAC_RXLP BIT(2) @@ -449,6 +817,37 @@ QCA955X_EXT_INT_PCIE_RC2_INT1 | QCA955X_EXT_INT_PCIE_RC2_INT2 | \ QCA955X_EXT_INT_PCIE_RC2_INT3) +#define QCA956X_EXT_INT_WMAC_MISC BIT(0) +#define QCA956X_EXT_INT_WMAC_TX BIT(1) +#define QCA956X_EXT_INT_WMAC_RXLP BIT(2) +#define QCA956X_EXT_INT_WMAC_RXHP BIT(3) +#define QCA956X_EXT_INT_PCIE_RC1 BIT(4) +#define QCA956X_EXT_INT_PCIE_RC1_INT0 BIT(5) +#define QCA956X_EXT_INT_PCIE_RC1_INT1 BIT(6) +#define QCA956X_EXT_INT_PCIE_RC1_INT2 BIT(7) +#define QCA956X_EXT_INT_PCIE_RC1_INT3 BIT(8) +#define QCA956X_EXT_INT_PCIE_RC2 BIT(12) +#define QCA956X_EXT_INT_PCIE_RC2_INT0 BIT(13) +#define QCA956X_EXT_INT_PCIE_RC2_INT1 BIT(14) +#define QCA956X_EXT_INT_PCIE_RC2_INT2 BIT(15) +#define QCA956X_EXT_INT_PCIE_RC2_INT3 BIT(16) +#define QCA956X_EXT_INT_USB1 BIT(24) +#define QCA956X_EXT_INT_USB2 BIT(28) + +#define QCA956X_EXT_INT_WMAC_ALL \ + (QCA956X_EXT_INT_WMAC_MISC | QCA956X_EXT_INT_WMAC_TX | \ + QCA956X_EXT_INT_WMAC_RXLP | QCA956X_EXT_INT_WMAC_RXHP) + +#define QCA956X_EXT_INT_PCIE_RC1_ALL \ + (QCA956X_EXT_INT_PCIE_RC1 | QCA956X_EXT_INT_PCIE_RC1_INT0 | \ + QCA956X_EXT_INT_PCIE_RC1_INT1 | QCA956X_EXT_INT_PCIE_RC1_INT2 | \ + QCA956X_EXT_INT_PCIE_RC1_INT3) + +#define QCA956X_EXT_INT_PCIE_RC2_ALL \ + (QCA956X_EXT_INT_PCIE_RC2 | QCA956X_EXT_INT_PCIE_RC2_INT0 | \ + QCA956X_EXT_INT_PCIE_RC2_INT1 | QCA956X_EXT_INT_PCIE_RC2_INT2 | \ + QCA956X_EXT_INT_PCIE_RC2_INT3) + #define REV_ID_MAJOR_MASK 0xfff0 #define REV_ID_MAJOR_AR71XX 0x00a0 #define REV_ID_MAJOR_AR913X 0x00b0 @@ -460,8 +859,12 @@ #define REV_ID_MAJOR_AR9341 0x0120 #define REV_ID_MAJOR_AR9342 0x1120 #define REV_ID_MAJOR_AR9344 0x2120 +#define REV_ID_MAJOR_QCA9533 0x0140 +#define REV_ID_MAJOR_QCA9533_V2 0x0160 #define REV_ID_MAJOR_QCA9556 0x0130 #define REV_ID_MAJOR_QCA9558 0x1130 +#define REV_ID_MAJOR_TP9343 0x0150 +#define REV_ID_MAJOR_QCA956X 0x1150 #define AR71XX_REV_ID_MINOR_MASK 0x3 #define AR71XX_REV_ID_MINOR_AR7130 0x0 @@ -482,8 +885,12 @@ #define AR934X_REV_ID_REVISION_MASK 0xf +#define QCA953X_REV_ID_REVISION_MASK 0xf + #define QCA955X_REV_ID_REVISION_MASK 0xf +#define QCA956X_REV_ID_REVISION_MASK 0xf + /* * SPI block */ @@ -521,15 +928,63 @@ #define AR71XX_GPIO_REG_INT_ENABLE 0x24 #define AR71XX_GPIO_REG_FUNC 0x28 +#define AR934X_GPIO_REG_OUT_FUNC0 0x2c +#define AR934X_GPIO_REG_OUT_FUNC1 0x30 +#define AR934X_GPIO_REG_OUT_FUNC2 0x34 +#define AR934X_GPIO_REG_OUT_FUNC3 0x38 +#define AR934X_GPIO_REG_OUT_FUNC4 0x3c +#define AR934X_GPIO_REG_OUT_FUNC5 0x40 #define AR934X_GPIO_REG_FUNC 0x6c +#define QCA953X_GPIO_REG_OUT_FUNC0 0x2c +#define QCA953X_GPIO_REG_OUT_FUNC1 0x30 +#define QCA953X_GPIO_REG_OUT_FUNC2 0x34 +#define QCA953X_GPIO_REG_OUT_FUNC3 0x38 +#define QCA953X_GPIO_REG_OUT_FUNC4 0x3c +#define QCA953X_GPIO_REG_IN_ENABLE0 0x44 +#define QCA953X_GPIO_REG_FUNC 0x6c + +#define QCA953X_GPIO_OUT_MUX_SPI_CS1 10 +#define QCA953X_GPIO_OUT_MUX_SPI_CS2 11 +#define QCA953X_GPIO_OUT_MUX_SPI_CS0 9 +#define QCA953X_GPIO_OUT_MUX_SPI_CLK 8 +#define QCA953X_GPIO_OUT_MUX_SPI_MOSI 12 +#define QCA953X_GPIO_OUT_MUX_LED_LINK1 41 +#define QCA953X_GPIO_OUT_MUX_LED_LINK2 42 +#define QCA953X_GPIO_OUT_MUX_LED_LINK3 43 +#define QCA953X_GPIO_OUT_MUX_LED_LINK4 44 +#define QCA953X_GPIO_OUT_MUX_LED_LINK5 45 + +#define QCA955X_GPIO_REG_OUT_FUNC0 0x2c +#define QCA955X_GPIO_REG_OUT_FUNC1 0x30 +#define QCA955X_GPIO_REG_OUT_FUNC2 0x34 +#define QCA955X_GPIO_REG_OUT_FUNC3 0x38 +#define QCA955X_GPIO_REG_OUT_FUNC4 0x3c +#define QCA955X_GPIO_REG_OUT_FUNC5 0x40 +#define QCA955X_GPIO_REG_FUNC 0x6c + +#define QCA956X_GPIO_REG_OUT_FUNC0 0x2c +#define QCA956X_GPIO_REG_OUT_FUNC1 0x30 +#define QCA956X_GPIO_REG_OUT_FUNC2 0x34 +#define QCA956X_GPIO_REG_OUT_FUNC3 0x38 +#define QCA956X_GPIO_REG_OUT_FUNC4 0x3c +#define QCA956X_GPIO_REG_OUT_FUNC5 0x40 +#define QCA956X_GPIO_REG_IN_ENABLE0 0x44 +#define QCA956X_GPIO_REG_IN_ENABLE3 0x50 +#define QCA956X_GPIO_REG_FUNC 0x6c + +#define QCA956X_GPIO_OUT_MUX_GE0_MDO 32 +#define QCA956X_GPIO_OUT_MUX_GE0_MDC 33 + #define AR71XX_GPIO_COUNT 16 #define AR7240_GPIO_COUNT 18 #define AR7241_GPIO_COUNT 20 #define AR913X_GPIO_COUNT 22 #define AR933X_GPIO_COUNT 30 #define AR934X_GPIO_COUNT 23 +#define QCA953X_GPIO_COUNT 18 #define QCA955X_GPIO_COUNT 24 +#define QCA956X_GPIO_COUNT 23 /* * SRIF block @@ -552,4 +1007,318 @@ #define AR934X_SRIF_DPLL2_OUTDIV_SHIFT 13 #define AR934X_SRIF_DPLL2_OUTDIV_MASK 0x7 +#define QCA953X_SRIF_CPU_DPLL1_REG 0x1c0 +#define QCA953X_SRIF_CPU_DPLL2_REG 0x1c4 +#define QCA953X_SRIF_CPU_DPLL3_REG 0x1c8 + +#define QCA953X_SRIF_DDR_DPLL1_REG 0x240 +#define QCA953X_SRIF_DDR_DPLL2_REG 0x244 +#define QCA953X_SRIF_DDR_DPLL3_REG 0x248 + +#define QCA953X_SRIF_DPLL1_REFDIV_SHIFT 27 +#define QCA953X_SRIF_DPLL1_REFDIV_MASK 0x1f +#define QCA953X_SRIF_DPLL1_NINT_SHIFT 18 +#define QCA953X_SRIF_DPLL1_NINT_MASK 0x1ff +#define QCA953X_SRIF_DPLL1_NFRAC_MASK 0x0003ffff + +#define QCA953X_SRIF_DPLL2_LOCAL_PLL BIT(30) +#define QCA953X_SRIF_DPLL2_OUTDIV_SHIFT 13 +#define QCA953X_SRIF_DPLL2_OUTDIV_MASK 0x7 + +#define AR71XX_GPIO_FUNC_STEREO_EN BIT(17) +#define AR71XX_GPIO_FUNC_SLIC_EN BIT(16) +#define AR71XX_GPIO_FUNC_SPI_CS2_EN BIT(13) +#define AR71XX_GPIO_FUNC_SPI_CS1_EN BIT(12) +#define AR71XX_GPIO_FUNC_UART_EN BIT(8) +#define AR71XX_GPIO_FUNC_USB_OC_EN BIT(4) +#define AR71XX_GPIO_FUNC_USB_CLK_EN BIT(0) + +#define AR724X_GPIO_FUNC_GE0_MII_CLK_EN BIT(19) +#define AR724X_GPIO_FUNC_SPI_EN BIT(18) +#define AR724X_GPIO_FUNC_SPI_CS_EN2 BIT(14) +#define AR724X_GPIO_FUNC_SPI_CS_EN1 BIT(13) +#define AR724X_GPIO_FUNC_CLK_OBS5_EN BIT(12) +#define AR724X_GPIO_FUNC_CLK_OBS4_EN BIT(11) +#define AR724X_GPIO_FUNC_CLK_OBS3_EN BIT(10) +#define AR724X_GPIO_FUNC_CLK_OBS2_EN BIT(9) +#define AR724X_GPIO_FUNC_CLK_OBS1_EN BIT(8) +#define AR724X_GPIO_FUNC_ETH_SWITCH_LED4_EN BIT(7) +#define AR724X_GPIO_FUNC_ETH_SWITCH_LED3_EN BIT(6) +#define AR724X_GPIO_FUNC_ETH_SWITCH_LED2_EN BIT(5) +#define AR724X_GPIO_FUNC_ETH_SWITCH_LED1_EN BIT(4) +#define AR724X_GPIO_FUNC_ETH_SWITCH_LED0_EN BIT(3) +#define AR724X_GPIO_FUNC_UART_RTS_CTS_EN BIT(2) +#define AR724X_GPIO_FUNC_UART_EN BIT(1) +#define AR724X_GPIO_FUNC_JTAG_DISABLE BIT(0) + +#define AR913X_GPIO_FUNC_WMAC_LED_EN BIT(22) +#define AR913X_GPIO_FUNC_EXP_PORT_CS_EN BIT(21) +#define AR913X_GPIO_FUNC_I2S_REFCLKEN BIT(20) +#define AR913X_GPIO_FUNC_I2S_MCKEN BIT(19) +#define AR913X_GPIO_FUNC_I2S1_EN BIT(18) +#define AR913X_GPIO_FUNC_I2S0_EN BIT(17) +#define AR913X_GPIO_FUNC_SLIC_EN BIT(16) +#define AR913X_GPIO_FUNC_UART_RTSCTS_EN BIT(9) +#define AR913X_GPIO_FUNC_UART_EN BIT(8) +#define AR913X_GPIO_FUNC_USB_CLK_EN BIT(4) + +#define AR933X_GPIO_FUNC_SPDIF2TCK BIT(31) +#define AR933X_GPIO_FUNC_SPDIF_EN BIT(30) +#define AR933X_GPIO_FUNC_I2SO_22_18_EN BIT(29) +#define AR933X_GPIO_FUNC_I2S_MCK_EN BIT(27) +#define AR933X_GPIO_FUNC_I2SO_EN BIT(26) +#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_DUPL BIT(25) +#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_COLL BIT(24) +#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_ACT BIT(23) +#define AR933X_GPIO_FUNC_SPI_EN BIT(18) +#define AR933X_GPIO_FUNC_SPI_CS_EN2 BIT(14) +#define AR933X_GPIO_FUNC_SPI_CS_EN1 BIT(13) +#define AR933X_GPIO_FUNC_ETH_SWITCH_LED4_EN BIT(7) +#define AR933X_GPIO_FUNC_ETH_SWITCH_LED3_EN BIT(6) +#define AR933X_GPIO_FUNC_ETH_SWITCH_LED2_EN BIT(5) +#define AR933X_GPIO_FUNC_ETH_SWITCH_LED1_EN BIT(4) +#define AR933X_GPIO_FUNC_ETH_SWITCH_LED0_EN BIT(3) +#define AR933X_GPIO_FUNC_UART_RTS_CTS_EN BIT(2) +#define AR933X_GPIO_FUNC_UART_EN BIT(1) +#define AR933X_GPIO_FUNC_JTAG_DISABLE BIT(0) + +#define AR934X_GPIO_FUNC_CLK_OBS7_EN BIT(9) +#define AR934X_GPIO_FUNC_CLK_OBS6_EN BIT(8) +#define AR934X_GPIO_FUNC_CLK_OBS5_EN BIT(7) +#define AR934X_GPIO_FUNC_CLK_OBS4_EN BIT(6) +#define AR934X_GPIO_FUNC_CLK_OBS3_EN BIT(5) +#define AR934X_GPIO_FUNC_CLK_OBS2_EN BIT(4) +#define AR934X_GPIO_FUNC_CLK_OBS1_EN BIT(3) +#define AR934X_GPIO_FUNC_CLK_OBS0_EN BIT(2) +#define AR934X_GPIO_FUNC_JTAG_DISABLE BIT(1) + +#define AR934X_GPIO_OUT_GPIO 0 +#define AR934X_GPIO_OUT_SPI_CS1 7 +#define AR934X_GPIO_OUT_LED_LINK0 41 +#define AR934X_GPIO_OUT_LED_LINK1 42 +#define AR934X_GPIO_OUT_LED_LINK2 43 +#define AR934X_GPIO_OUT_LED_LINK3 44 +#define AR934X_GPIO_OUT_LED_LINK4 45 +#define AR934X_GPIO_OUT_EXT_LNA0 46 +#define AR934X_GPIO_OUT_EXT_LNA1 47 + +#define QCA955X_GPIO_FUNC_CLK_OBS7_EN BIT(9) +#define QCA955X_GPIO_FUNC_CLK_OBS6_EN BIT(8) +#define QCA955X_GPIO_FUNC_CLK_OBS5_EN BIT(7) +#define QCA955X_GPIO_FUNC_CLK_OBS4_EN BIT(6) +#define QCA955X_GPIO_FUNC_CLK_OBS3_EN BIT(5) +#define QCA955X_GPIO_FUNC_CLK_OBS2_EN BIT(4) +#define QCA955X_GPIO_FUNC_CLK_OBS1_EN BIT(3) +#define QCA955X_GPIO_FUNC_JTAG_DISABLE BIT(1) + +#define QCA955X_GPIO_OUT_GPIO 0 +#define QCA955X_MII_EXT_MDI 1 +#define QCA955X_SLIC_DATA_OUT 3 +#define QCA955X_SLIC_PCM_FS 4 +#define QCA955X_SLIC_PCM_CLK 5 +#define QCA955X_SPI_CLK 8 +#define QCA955X_SPI_CS_0 9 +#define QCA955X_SPI_CS_1 10 +#define QCA955X_SPI_CS_2 11 +#define QCA955X_SPI_MISO 12 +#define QCA955X_I2S_CLK 13 +#define QCA955X_I2S_WS 14 +#define QCA955X_I2S_SD 15 +#define QCA955X_I2S_MCK 16 +#define QCA955X_SPDIF_OUT 17 +#define QCA955X_UART1_TD 18 +#define QCA955X_UART1_RTS 19 +#define QCA955X_UART1_RD 20 +#define QCA955X_UART1_CTS 21 +#define QCA955X_UART0_SOUT 22 +#define QCA955X_SPDIF2_OUT 23 +#define QCA955X_LED_SGMII_SPEED0 24 +#define QCA955X_LED_SGMII_SPEED1 25 +#define QCA955X_LED_SGMII_DUPLEX 26 +#define QCA955X_LED_SGMII_LINK_UP 27 +#define QCA955X_SGMII_SPEED0_INVERT 28 +#define QCA955X_SGMII_SPEED1_INVERT 29 +#define QCA955X_SGMII_DUPLEX_INVERT 30 +#define QCA955X_SGMII_LINK_UP_INVERT 31 +#define QCA955X_GE1_MII_MDO 32 +#define QCA955X_GE1_MII_MDC 33 +#define QCA955X_SWCOM2 38 +#define QCA955X_SWCOM3 39 +#define QCA955X_MAC2_GPIO 40 +#define QCA955X_MAC3_GPIO 41 +#define QCA955X_ATT_LED 42 +#define QCA955X_PWR_LED 43 +#define QCA955X_TX_FRAME 44 +#define QCA955X_RX_CLEAR_EXTERNAL 45 +#define QCA955X_LED_NETWORK_EN 46 +#define QCA955X_LED_POWER_EN 47 +#define QCA955X_WMAC_GLUE_WOW 68 +#define QCA955X_RX_CLEAR_EXTENSION 70 +#define QCA955X_CP_NAND_CS1 73 +#define QCA955X_USB_SUSPEND 74 +#define QCA955X_ETH_TX_ERR 75 +#define QCA955X_DDR_DQ_OE 76 +#define QCA955X_CLKREQ_N_EP 77 +#define QCA955X_CLKREQ_N_RC 78 +#define QCA955X_CLK_OBS0 79 +#define QCA955X_CLK_OBS1 80 +#define QCA955X_CLK_OBS2 81 +#define QCA955X_CLK_OBS3 82 +#define QCA955X_CLK_OBS4 83 +#define QCA955X_CLK_OBS5 84 + +/* + * MII_CTRL block + */ +#define AR71XX_MII_REG_MII0_CTRL 0x00 +#define AR71XX_MII_REG_MII1_CTRL 0x04 + +#define AR71XX_MII_CTRL_IF_MASK 3 +#define AR71XX_MII_CTRL_SPEED_SHIFT 4 +#define AR71XX_MII_CTRL_SPEED_MASK 3 +#define AR71XX_MII_CTRL_SPEED_10 0 +#define AR71XX_MII_CTRL_SPEED_100 1 +#define AR71XX_MII_CTRL_SPEED_1000 2 + +#define AR71XX_MII0_CTRL_IF_GMII 0 +#define AR71XX_MII0_CTRL_IF_MII 1 +#define AR71XX_MII0_CTRL_IF_RGMII 2 +#define AR71XX_MII0_CTRL_IF_RMII 3 + +#define AR71XX_MII1_CTRL_IF_RGMII 0 +#define AR71XX_MII1_CTRL_IF_RMII 1 + +/* + * AR933X GMAC interface + */ +#define AR933X_GMAC_REG_ETH_CFG 0x00 + +#define AR933X_ETH_CFG_RGMII_GE0 BIT(0) +#define AR933X_ETH_CFG_MII_GE0 BIT(1) +#define AR933X_ETH_CFG_GMII_GE0 BIT(2) +#define AR933X_ETH_CFG_MII_GE0_MASTER BIT(3) +#define AR933X_ETH_CFG_MII_GE0_SLAVE BIT(4) +#define AR933X_ETH_CFG_MII_GE0_ERR_EN BIT(5) +#define AR933X_ETH_CFG_SW_PHY_SWAP BIT(7) +#define AR933X_ETH_CFG_SW_PHY_ADDR_SWAP BIT(8) +#define AR933X_ETH_CFG_RMII_GE0 BIT(9) +#define AR933X_ETH_CFG_RMII_GE0_SPD_10 0 +#define AR933X_ETH_CFG_RMII_GE0_SPD_100 BIT(10) + +/* + * AR934X GMAC Interface + */ +#define AR934X_GMAC_REG_ETH_CFG 0x00 + +#define AR934X_ETH_CFG_RGMII_GMAC0 BIT(0) +#define AR934X_ETH_CFG_MII_GMAC0 BIT(1) +#define AR934X_ETH_CFG_GMII_GMAC0 BIT(2) +#define AR934X_ETH_CFG_MII_GMAC0_MASTER BIT(3) +#define AR934X_ETH_CFG_MII_GMAC0_SLAVE BIT(4) +#define AR934X_ETH_CFG_MII_GMAC0_ERR_EN BIT(5) +#define AR934X_ETH_CFG_SW_ONLY_MODE BIT(6) +#define AR934X_ETH_CFG_SW_PHY_SWAP BIT(7) +#define AR934X_ETH_CFG_SW_APB_ACCESS BIT(9) +#define AR934X_ETH_CFG_RMII_GMAC0 BIT(10) +#define AR933X_ETH_CFG_MII_CNTL_SPEED BIT(11) +#define AR934X_ETH_CFG_RMII_GMAC0_MASTER BIT(12) +#define AR933X_ETH_CFG_SW_ACC_MSB_FIRST BIT(13) +#define AR934X_ETH_CFG_RXD_DELAY BIT(14) +#define AR934X_ETH_CFG_RXD_DELAY_MASK 0x3 +#define AR934X_ETH_CFG_RXD_DELAY_SHIFT 14 +#define AR934X_ETH_CFG_RDV_DELAY BIT(16) +#define AR934X_ETH_CFG_RDV_DELAY_MASK 0x3 +#define AR934X_ETH_CFG_RDV_DELAY_SHIFT 16 + +/* + * QCA953X GMAC Interface + */ +#define QCA953X_GMAC_REG_ETH_CFG 0x00 + +#define QCA953X_ETH_CFG_SW_ONLY_MODE BIT(6) +#define QCA953X_ETH_CFG_SW_PHY_SWAP BIT(7) +#define QCA953X_ETH_CFG_SW_APB_ACCESS BIT(9) +#define QCA953X_ETH_CFG_SW_ACC_MSB_FIRST BIT(13) + +/* + * QCA955X GMAC Interface + */ + +#define QCA955X_GMAC_REG_ETH_CFG 0x00 +#define QCA955X_GMAC_REG_SGMII_SERDES 0x18 + +#define QCA955X_ETH_CFG_RGMII_EN BIT(0) +#define QCA955X_ETH_CFG_MII_GE0 BIT(1) +#define QCA955X_ETH_CFG_GMII_GE0 BIT(2) +#define QCA955X_ETH_CFG_MII_GE0_MASTER BIT(3) +#define QCA955X_ETH_CFG_MII_GE0_SLAVE BIT(4) +#define QCA955X_ETH_CFG_GE0_ERR_EN BIT(5) +#define QCA955X_ETH_CFG_GE0_SGMII BIT(6) +#define QCA955X_ETH_CFG_RMII_GE0 BIT(10) +#define QCA955X_ETH_CFG_MII_CNTL_SPEED BIT(11) +#define QCA955X_ETH_CFG_RMII_GE0_MASTER BIT(12) +#define QCA955X_ETH_CFG_RXD_DELAY_MASK 0x3 +#define QCA955X_ETH_CFG_RXD_DELAY_SHIFT 14 +#define QCA955X_ETH_CFG_RDV_DELAY BIT(16) +#define QCA955X_ETH_CFG_RDV_DELAY_MASK 0x3 +#define QCA955X_ETH_CFG_RDV_DELAY_SHIFT 16 +#define QCA955X_ETH_CFG_TXD_DELAY_MASK 0x3 +#define QCA955X_ETH_CFG_TXD_DELAY_SHIFT 18 +#define QCA955X_ETH_CFG_TXE_DELAY_MASK 0x3 +#define QCA955X_ETH_CFG_TXE_DELAY_SHIFT 20 + +#define QCA955X_SGMII_SERDES_LOCK_DETECT_STATUS BIT(15) +#define QCA955X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23 +#define QCA955X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf +/* + * QCA956X GMAC Interface + */ + +#define QCA956X_GMAC_REG_ETH_CFG 0x00 +#define QCA956X_GMAC_REG_SGMII_RESET 0x14 +#define QCA956X_GMAC_REG_SGMII_SERDES 0x18 +#define QCA956X_GMAC_REG_MR_AN_CONTROL 0x1c +#define QCA956X_GMAC_REG_SGMII_CONFIG 0x34 +#define QCA956X_GMAC_REG_SGMII_DEBUG 0x58 + +#define QCA956X_ETH_CFG_RGMII_EN BIT(0) +#define QCA956X_ETH_CFG_GE0_SGMII BIT(6) +#define QCA956X_ETH_CFG_SW_ONLY_MODE BIT(7) +#define QCA956X_ETH_CFG_SW_PHY_SWAP BIT(8) +#define QCA956X_ETH_CFG_SW_PHY_ADDR_SWAP BIT(9) +#define QCA956X_ETH_CFG_SW_APB_ACCESS BIT(10) +#define QCA956X_ETH_CFG_SW_ACC_MSB_FIRST BIT(13) +#define QCA956X_ETH_CFG_RXD_DELAY_MASK 0x3 +#define QCA956X_ETH_CFG_RXD_DELAY_SHIFT 14 +#define QCA956X_ETH_CFG_RDV_DELAY_MASK 0x3 +#define QCA956X_ETH_CFG_RDV_DELAY_SHIFT 16 + +#define QCA956X_SGMII_RESET_RX_CLK_N_RESET 0x0 +#define QCA956X_SGMII_RESET_RX_CLK_N BIT(0) +#define QCA956X_SGMII_RESET_TX_CLK_N BIT(1) +#define QCA956X_SGMII_RESET_RX_125M_N BIT(2) +#define QCA956X_SGMII_RESET_TX_125M_N BIT(3) +#define QCA956X_SGMII_RESET_HW_RX_125M_N BIT(4) + +#define QCA956X_SGMII_SERDES_CDR_BW_MASK 0x3 +#define QCA956X_SGMII_SERDES_CDR_BW_SHIFT 1 +#define QCA956X_SGMII_SERDES_TX_DR_CTRL_MASK 0x7 +#define QCA956X_SGMII_SERDES_TX_DR_CTRL_SHIFT 4 +#define QCA956X_SGMII_SERDES_PLL_BW BIT(8) +#define QCA956X_SGMII_SERDES_VCO_FAST BIT(9) +#define QCA956X_SGMII_SERDES_VCO_SLOW BIT(10) +#define QCA956X_SGMII_SERDES_LOCK_DETECT_STATUS BIT(15) +#define QCA956X_SGMII_SERDES_EN_SIGNAL_DETECT BIT(16) +#define QCA956X_SGMII_SERDES_FIBER_SDO BIT(17) +#define QCA956X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23 +#define QCA956X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf +#define QCA956X_SGMII_SERDES_VCO_REG_SHIFT 27 +#define QCA956X_SGMII_SERDES_VCO_REG_MASK 0xf + +#define QCA956X_MR_AN_CONTROL_AN_ENABLE BIT(12) +#define QCA956X_MR_AN_CONTROL_PHY_RESET BIT(15) + +#define QCA956X_SGMII_CONFIG_MODE_CTRL_SHIFT 0 +#define QCA956X_SGMII_CONFIG_MODE_CTRL_MASK 0x7 + #endif /* __ASM_MACH_AR71XX_REGS_H */ diff --git a/arch/mips/include/asm/mach-ath79/ath79.h b/arch/mips/include/asm/mach-ath79/ath79.h index 441faa92c3cd..73dcd63b8243 100644 --- a/arch/mips/include/asm/mach-ath79/ath79.h +++ b/arch/mips/include/asm/mach-ath79/ath79.h @@ -32,8 +32,11 @@ enum ath79_soc_type { ATH79_SOC_AR9341, ATH79_SOC_AR9342, ATH79_SOC_AR9344, + ATH79_SOC_QCA9533, ATH79_SOC_QCA9556, ATH79_SOC_QCA9558, + ATH79_SOC_TP9343, + ATH79_SOC_QCA956X, }; extern enum ath79_soc_type ath79_soc; @@ -100,6 +103,16 @@ static inline int soc_is_ar934x(void) return soc_is_ar9341() || soc_is_ar9342() || soc_is_ar9344(); } +static inline int soc_is_qca9533(void) +{ + return ath79_soc == ATH79_SOC_QCA9533; +} + +static inline int soc_is_qca953x(void) +{ + return soc_is_qca9533(); +} + static inline int soc_is_qca9556(void) { return ath79_soc == ATH79_SOC_QCA9556; @@ -115,6 +128,26 @@ static inline int soc_is_qca955x(void) return soc_is_qca9556() || soc_is_qca9558(); } +static inline int soc_is_tp9343(void) +{ + return ath79_soc == ATH79_SOC_TP9343; +} + +static inline int soc_is_qca9561(void) +{ + return ath79_soc == ATH79_SOC_QCA956X; +} + +static inline int soc_is_qca9563(void) +{ + return ath79_soc == ATH79_SOC_QCA956X; +} + +static inline int soc_is_qca956x(void) +{ + return soc_is_qca9561() || soc_is_qca9563(); +} + void ath79_ddr_wb_flush(unsigned int reg); void ath79_ddr_set_pci_windows(void); @@ -134,6 +167,7 @@ static inline u32 ath79_pll_rr(unsigned reg) static inline void ath79_reset_wr(unsigned reg, u32 val) { __raw_writel(val, ath79_reset_base + reg); + (void) __raw_readl(ath79_reset_base + reg); /* flush */ } static inline u32 ath79_reset_rr(unsigned reg) diff --git a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h index 0089a740e5ae..026ad90c8ac0 100644 --- a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h @@ -36,6 +36,7 @@ #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 +#define cpu_has_rixi 0 #define cpu_has_mips32r1 1 #define cpu_has_mips32r2 1 @@ -43,6 +44,7 @@ #define cpu_has_mips64r2 0 #define cpu_has_mipsmt 0 +#define cpu_has_userlocal 0 #define cpu_has_64bits 0 #define cpu_has_64bit_zero_reg 0 @@ -51,5 +53,9 @@ #define cpu_dcache_line_size() 32 #define cpu_icache_line_size() 32 +#define cpu_has_vtag_icache 0 +#define cpu_has_dc_aliases 1 +#define cpu_has_ic_fills_f_dc 0 +#define cpu_has_pindexed_dcache 0 #endif /* __ASM_MACH_ATH79_CPU_FEATURE_OVERRIDES_H */ diff --git a/arch/mips/include/asm/mach-bmips/dma-coherence.h b/arch/mips/include/asm/mach-bmips/dma-coherence.h deleted file mode 100644 index d29781f02285..000000000000 --- a/arch/mips/include/asm/mach-bmips/dma-coherence.h +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org> - * Copyright (C) 2009 Broadcom Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef __ASM_MACH_BMIPS_DMA_COHERENCE_H -#define __ASM_MACH_BMIPS_DMA_COHERENCE_H - -#include <asm/bmips.h> -#include <asm/cpu-type.h> -#include <asm/cpu.h> - -struct device; - -extern dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size); -extern dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page); -extern unsigned long plat_dma_addr_to_phys(struct device *dev, - dma_addr_t dma_addr); - -static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction) -{ -} - -static inline int plat_dma_supported(struct device *dev, u64 mask) -{ - /* - * we fall back to GFP_DMA when the mask isn't all 1s, - * so we can't guarantee allocations that must be - * within a tighter range than GFP_DMA.. - */ - if (mask < DMA_BIT_MASK(24)) - return 0; - - return 1; -} - -static inline int plat_device_is_coherent(struct device *dev) -{ - return 0; -} - -#define plat_post_dma_flush bmips_post_dma_flush - -#endif /* __ASM_MACH_BMIPS_DMA_COHERENCE_H */ diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h deleted file mode 100644 index 6eb1ee548b11..000000000000 --- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h +++ /dev/null @@ -1,79 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org> - * - * - * Similar to mach-generic/dma-coherence.h except - * plat_device_is_coherent hard coded to return 1. - * - */ -#ifndef __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H -#define __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H - -#include <linux/bug.h> - -struct device; - -extern void octeon_pci_dma_init(void); - -static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, - size_t size) -{ - BUG(); - return 0; -} - -static inline dma_addr_t plat_map_dma_mem_page(struct device *dev, - struct page *page) -{ - BUG(); - return 0; -} - -static inline unsigned long plat_dma_addr_to_phys(struct device *dev, - dma_addr_t dma_addr) -{ - BUG(); - return 0; -} - -static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction) -{ - BUG(); -} - -static inline int plat_dma_supported(struct device *dev, u64 mask) -{ - BUG(); - return 0; -} - -static inline int plat_device_is_coherent(struct device *dev) -{ - return 1; -} - -static inline void plat_post_dma_flush(struct device *dev) -{ -} - -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - if (!dev->dma_mask) - return false; - - return addr + size - 1 <= *dev->dma_mask; -} - -dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr); -phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr); - -struct dma_map_ops; -extern const struct dma_map_ops *octeon_pci_dma_map_ops; -extern char *octeon_swiotlb; - -#endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */ diff --git a/arch/mips/include/asm/mach-generic/dma-coherence.h b/arch/mips/include/asm/mach-generic/dma-coherence.h deleted file mode 100644 index 8ad7a40ca786..000000000000 --- a/arch/mips/include/asm/mach-generic/dma-coherence.h +++ /dev/null @@ -1,73 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org> - * - */ -#ifndef __ASM_MACH_GENERIC_DMA_COHERENCE_H -#define __ASM_MACH_GENERIC_DMA_COHERENCE_H - -struct device; - -static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, - size_t size) -{ - return virt_to_phys(addr); -} - -static inline dma_addr_t plat_map_dma_mem_page(struct device *dev, - struct page *page) -{ - return page_to_phys(page); -} - -static inline unsigned long plat_dma_addr_to_phys(struct device *dev, - dma_addr_t dma_addr) -{ - return dma_addr; -} - -static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction) -{ -} - -static inline int plat_dma_supported(struct device *dev, u64 mask) -{ - /* - * we fall back to GFP_DMA when the mask isn't all 1s, - * so we can't guarantee allocations that must be - * within a tighter range than GFP_DMA.. - */ - if (mask < DMA_BIT_MASK(24)) - return 0; - - return 1; -} - -static inline int plat_device_is_coherent(struct device *dev) -{ -#ifdef CONFIG_DMA_PERDEV_COHERENT - return dev->archdata.dma_coherent; -#else - switch (coherentio) { - default: - case IO_COHERENCE_DEFAULT: - return hw_coherentio; - case IO_COHERENCE_ENABLED: - return 1; - case IO_COHERENCE_DISABLED: - return 0; - } -#endif -} - -#ifndef plat_post_dma_flush -static inline void plat_post_dma_flush(struct device *dev) -{ -} -#endif - -#endif /* __ASM_MACH_GENERIC_DMA_COHERENCE_H */ diff --git a/arch/mips/include/asm/mach-generic/kmalloc.h b/arch/mips/include/asm/mach-generic/kmalloc.h index 74207c7bd00d..649a98338886 100644 --- a/arch/mips/include/asm/mach-generic/kmalloc.h +++ b/arch/mips/include/asm/mach-generic/kmalloc.h @@ -2,8 +2,7 @@ #ifndef __ASM_MACH_GENERIC_KMALLOC_H #define __ASM_MACH_GENERIC_KMALLOC_H - -#ifndef CONFIG_DMA_COHERENT +#ifdef CONFIG_DMA_NONCOHERENT /* * Total overkill for most systems but need as a safe default. * Set this one if any device in the system might do non-coherent DMA. diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h index 952b0fdfda0e..ee5ebe98f6cf 100644 --- a/arch/mips/include/asm/mach-generic/spaces.h +++ b/arch/mips/include/asm/mach-generic/spaces.h @@ -17,9 +17,13 @@ /* * This gives the physical RAM offset. */ -#ifndef PHYS_OFFSET -#define PHYS_OFFSET _AC(0, UL) -#endif +#ifndef __ASSEMBLY__ +# if defined(CONFIG_MIPS_AUTO_PFN_OFFSET) +# define PHYS_OFFSET ((unsigned long)PFN_PHYS(ARCH_PFN_OFFSET)) +# elif !defined(PHYS_OFFSET) +# define PHYS_OFFSET _AC(0, UL) +# endif +#endif /* __ASSEMBLY__ */ #ifdef CONFIG_32BIT #ifdef CONFIG_KVM_GUEST diff --git a/arch/mips/include/asm/mach-ip27/dma-coherence.h b/arch/mips/include/asm/mach-ip27/dma-coherence.h deleted file mode 100644 index 04d862020ac9..000000000000 --- a/arch/mips/include/asm/mach-ip27/dma-coherence.h +++ /dev/null @@ -1,70 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org> - * - */ -#ifndef __ASM_MACH_IP27_DMA_COHERENCE_H -#define __ASM_MACH_IP27_DMA_COHERENCE_H - -#include <asm/pci/bridge.h> - -#define pdev_to_baddr(pdev, addr) \ - (BRIDGE_CONTROLLER(pdev->bus)->baddr + (addr)) -#define dev_to_baddr(dev, addr) \ - pdev_to_baddr(to_pci_dev(dev), (addr)) - -struct device; - -static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, - size_t size) -{ - dma_addr_t pa = dev_to_baddr(dev, virt_to_phys(addr)); - - return pa; -} - -static inline dma_addr_t plat_map_dma_mem_page(struct device *dev, - struct page *page) -{ - dma_addr_t pa = dev_to_baddr(dev, page_to_phys(page)); - - return pa; -} - -static inline unsigned long plat_dma_addr_to_phys(struct device *dev, - dma_addr_t dma_addr) -{ - return dma_addr & ~(0xffUL << 56); -} - -static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction) -{ -} - -static inline int plat_dma_supported(struct device *dev, u64 mask) -{ - /* - * we fall back to GFP_DMA when the mask isn't all 1s, - * so we can't guarantee allocations that must be - * within a tighter range than GFP_DMA.. - */ - if (mask < DMA_BIT_MASK(24)) - return 0; - - return 1; -} - -static inline void plat_post_dma_flush(struct device *dev) -{ -} - -static inline int plat_device_is_coherent(struct device *dev) -{ - return 1; /* IP27 non-coherent mode is unsupported */ -} - -#endif /* __ASM_MACH_IP27_DMA_COHERENCE_H */ diff --git a/arch/mips/include/asm/mach-ip32/dma-coherence.h b/arch/mips/include/asm/mach-ip32/dma-coherence.h deleted file mode 100644 index 7bdf212587a0..000000000000 --- a/arch/mips/include/asm/mach-ip32/dma-coherence.h +++ /dev/null @@ -1,92 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org> - * - */ -#ifndef __ASM_MACH_IP32_DMA_COHERENCE_H -#define __ASM_MACH_IP32_DMA_COHERENCE_H - -#include <asm/ip32/crime.h> - -struct device; - -/* - * Few notes. - * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M - * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for - * native-endian) - * 3. All other devices see memory as one big chunk at 0x40000000 - * 4. Non-PCI devices will pass NULL as struct device* - * - * Thus we translate differently, depending on device. - */ - -#define RAM_OFFSET_MASK 0x3fffffffUL - -static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, - size_t size) -{ - dma_addr_t pa = virt_to_phys(addr) & RAM_OFFSET_MASK; - - if (dev == NULL) - pa += CRIME_HI_MEM_BASE; - - return pa; -} - -static inline dma_addr_t plat_map_dma_mem_page(struct device *dev, - struct page *page) -{ - dma_addr_t pa; - - pa = page_to_phys(page) & RAM_OFFSET_MASK; - - if (dev == NULL) - pa += CRIME_HI_MEM_BASE; - - return pa; -} - -/* This is almost certainly wrong but it's what dma-ip32.c used to use */ -static inline unsigned long plat_dma_addr_to_phys(struct device *dev, - dma_addr_t dma_addr) -{ - unsigned long addr = dma_addr & RAM_OFFSET_MASK; - - if (dma_addr >= 256*1024*1024) - addr += CRIME_HI_MEM_BASE; - - return addr; -} - -static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction) -{ -} - -static inline int plat_dma_supported(struct device *dev, u64 mask) -{ - /* - * we fall back to GFP_DMA when the mask isn't all 1s, - * so we can't guarantee allocations that must be - * within a tighter range than GFP_DMA.. - */ - if (mask < DMA_BIT_MASK(24)) - return 0; - - return 1; -} - -static inline void plat_post_dma_flush(struct device *dev) -{ -} - -static inline int plat_device_is_coherent(struct device *dev) -{ - return 0; /* IP32 is non-coherent */ -} - -#endif /* __ASM_MACH_IP32_DMA_COHERENCE_H */ diff --git a/arch/mips/include/asm/mach-jazz/dma-coherence.h b/arch/mips/include/asm/mach-jazz/dma-coherence.h deleted file mode 100644 index dc347c25c343..000000000000 --- a/arch/mips/include/asm/mach-jazz/dma-coherence.h +++ /dev/null @@ -1,60 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org> - */ -#ifndef __ASM_MACH_JAZZ_DMA_COHERENCE_H -#define __ASM_MACH_JAZZ_DMA_COHERENCE_H - -#include <asm/jazzdma.h> - -struct device; - -static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size) -{ - return vdma_alloc(virt_to_phys(addr), size); -} - -static inline dma_addr_t plat_map_dma_mem_page(struct device *dev, - struct page *page) -{ - return vdma_alloc(page_to_phys(page), PAGE_SIZE); -} - -static inline unsigned long plat_dma_addr_to_phys(struct device *dev, - dma_addr_t dma_addr) -{ - return vdma_log2phys(dma_addr); -} - -static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction) -{ - vdma_free(dma_addr); -} - -static inline int plat_dma_supported(struct device *dev, u64 mask) -{ - /* - * we fall back to GFP_DMA when the mask isn't all 1s, - * so we can't guarantee allocations that must be - * within a tighter range than GFP_DMA.. - */ - if (mask < DMA_BIT_MASK(24)) - return 0; - - return 1; -} - -static inline void plat_post_dma_flush(struct device *dev) -{ -} - -static inline int plat_device_is_coherent(struct device *dev) -{ - return 0; -} - -#endif /* __ASM_MACH_JAZZ_DMA_COHERENCE_H */ diff --git a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h b/arch/mips/include/asm/mach-jz4740/jz4740_nand.h deleted file mode 100644 index f381d465e768..000000000000 --- a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h +++ /dev/null @@ -1,34 +0,0 @@ -/* - * Copyright (C) 2009-2010, Lars-Peter Clausen <lars@metafoo.de> - * JZ4740 SoC NAND controller driver - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ - -#ifndef __ASM_MACH_JZ4740_JZ4740_NAND_H__ -#define __ASM_MACH_JZ4740_JZ4740_NAND_H__ - -#include <linux/mtd/rawnand.h> -#include <linux/mtd/partitions.h> - -#define JZ_NAND_NUM_BANKS 4 - -struct jz_nand_platform_data { - int num_partitions; - struct mtd_partition *partitions; - - unsigned char banks[JZ_NAND_NUM_BANKS]; - - void (*ident_callback)(struct platform_device *, struct mtd_info *, - struct mtd_partition **, int *num_partitions); -}; - -#endif diff --git a/arch/mips/include/asm/mach-loongson64/dma-coherence.h b/arch/mips/include/asm/mach-loongson64/dma-coherence.h deleted file mode 100644 index 64fc44dec0a8..000000000000 --- a/arch/mips/include/asm/mach-loongson64/dma-coherence.h +++ /dev/null @@ -1,93 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006, 07 Ralf Baechle <ralf@linux-mips.org> - * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology - * Author: Fuxin Zhang, zhangfx@lemote.com - * - */ -#ifndef __ASM_MACH_LOONGSON64_DMA_COHERENCE_H -#define __ASM_MACH_LOONGSON64_DMA_COHERENCE_H - -#ifdef CONFIG_SWIOTLB -#include <linux/swiotlb.h> -#endif - -struct device; - -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - if (!dev->dma_mask) - return false; - - return addr + size - 1 <= *dev->dma_mask; -} - -extern dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr); -extern phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr); -static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, - size_t size) -{ -#ifdef CONFIG_CPU_LOONGSON3 - return __phys_to_dma(dev, virt_to_phys(addr)); -#else - return virt_to_phys(addr) | 0x80000000; -#endif -} - -static inline dma_addr_t plat_map_dma_mem_page(struct device *dev, - struct page *page) -{ -#ifdef CONFIG_CPU_LOONGSON3 - return __phys_to_dma(dev, page_to_phys(page)); -#else - return page_to_phys(page) | 0x80000000; -#endif -} - -static inline unsigned long plat_dma_addr_to_phys(struct device *dev, - dma_addr_t dma_addr) -{ -#if defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_64BIT) - return __dma_to_phys(dev, dma_addr); -#elif defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT) - return (dma_addr > 0x8fffffff) ? dma_addr : (dma_addr & 0x0fffffff); -#else - return dma_addr & 0x7fffffff; -#endif -} - -static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction) -{ -} - -static inline int plat_dma_supported(struct device *dev, u64 mask) -{ - /* - * we fall back to GFP_DMA when the mask isn't all 1s, - * so we can't guarantee allocations that must be - * within a tighter range than GFP_DMA.. - */ - if (mask < DMA_BIT_MASK(24)) - return 0; - - return 1; -} - -static inline int plat_device_is_coherent(struct device *dev) -{ -#ifdef CONFIG_DMA_NONCOHERENT - return 0; -#else - return 1; -#endif /* CONFIG_DMA_NONCOHERENT */ -} - -static inline void plat_post_dma_flush(struct device *dev) -{ -} - -#endif /* __ASM_MACH_LOONGSON64_DMA_COHERENCE_H */ diff --git a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h index 8393bc548987..312739117bb0 100644 --- a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h @@ -19,18 +19,18 @@ .set push .set mips64 /* Set LPA on LOONGSON3 config3 */ - mfc0 t0, $16, 3 + mfc0 t0, CP0_CONFIG3 or t0, (0x1 << 7) - mtc0 t0, $16, 3 + mtc0 t0, CP0_CONFIG3 /* Set ELPA on LOONGSON3 pagegrain */ - mfc0 t0, $5, 1 + mfc0 t0, CP0_PAGEGRAIN or t0, (0x1 << 29) - mtc0 t0, $5, 1 + mtc0 t0, CP0_PAGEGRAIN #ifdef CONFIG_LOONGSON3_ENHANCEMENT /* Enable STFill Buffer */ - mfc0 t0, $16, 6 + mfc0 t0, CP0_CONFIG6 or t0, 0x100 - mtc0 t0, $16, 6 + mtc0 t0, CP0_CONFIG6 #endif _ehb .set pop @@ -45,18 +45,18 @@ .set push .set mips64 /* Set LPA on LOONGSON3 config3 */ - mfc0 t0, $16, 3 + mfc0 t0, CP0_CONFIG3 or t0, (0x1 << 7) - mtc0 t0, $16, 3 + mtc0 t0, CP0_CONFIG3 /* Set ELPA on LOONGSON3 pagegrain */ - mfc0 t0, $5, 1 + mfc0 t0, CP0_PAGEGRAIN or t0, (0x1 << 29) - mtc0 t0, $5, 1 + mtc0 t0, CP0_PAGEGRAIN #ifdef CONFIG_LOONGSON3_ENHANCEMENT /* Enable STFill Buffer */ - mfc0 t0, $16, 6 + mfc0 t0, CP0_CONFIG6 or t0, 0x100 - mtc0 t0, $16, 6 + mtc0 t0, CP0_CONFIG6 #endif _ehb .set pop diff --git a/arch/mips/include/asm/mach-pic32/spaces.h b/arch/mips/include/asm/mach-pic32/spaces.h index 046a0a9aa8b3..a1b9783b76ea 100644 --- a/arch/mips/include/asm/mach-pic32/spaces.h +++ b/arch/mips/include/asm/mach-pic32/spaces.h @@ -16,7 +16,6 @@ #ifdef CONFIG_PIC32MZDA #define PHYS_OFFSET _AC(0x08000000, UL) -#define UNCAC_BASE _AC(0xa8000000, UL) #endif #include <asm/mach-generic/spaces.h> diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 0bc270806ec5..01df9ad62fb8 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -16,6 +16,7 @@ #include <linux/linkage.h> #include <linux/types.h> #include <asm/hazards.h> +#include <asm/isa-rev.h> #include <asm/war.h> /* @@ -51,6 +52,7 @@ #define CP0_GLOBALNUMBER $3, 1 #define CP0_CONTEXT $4 #define CP0_PAGEMASK $5 +#define CP0_PAGEGRAIN $5, 1 #define CP0_SEGCTL0 $5, 2 #define CP0_SEGCTL1 $5, 3 #define CP0_SEGCTL2 $5, 4 @@ -77,6 +79,7 @@ #define CP0_CONFIG $16 #define CP0_CONFIG3 $16, 3 #define CP0_CONFIG5 $16, 5 +#define CP0_CONFIG6 $16, 6 #define CP0_LLADDR $17 #define CP0_WATCHLO $18 #define CP0_WATCHHI $19 @@ -681,8 +684,6 @@ #define MIPS_CONF7_WII (_ULCAST_(1) << 31) #define MIPS_CONF7_RPS (_ULCAST_(1) << 2) -/* ExternalSync */ -#define MIPS_CONF7_ES (_ULCAST_(1) << 8) #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) @@ -1483,32 +1484,38 @@ do { \ #define __write_64bit_c0_split(source, sel, val) \ do { \ - unsigned long long __tmp; \ + unsigned long long __tmp = (val); \ unsigned long __flags; \ \ local_irq_save(__flags); \ - if (sel == 0) \ + if (MIPS_ISA_REV >= 2) \ + __asm__ __volatile__( \ + ".set\tpush\n\t" \ + ".set\t" MIPS_ISA_LEVEL "\n\t" \ + "dins\t%L0, %M0, 32, 32\n\t" \ + "dmtc0\t%L0, " #source ", " #sel "\n\t" \ + ".set\tpop" \ + : "+r" (__tmp)); \ + else if (sel == 0) \ __asm__ __volatile__( \ ".set\tmips64\n\t" \ - "dsll\t%L0, %L1, 32\n\t" \ + "dsll\t%L0, %L0, 32\n\t" \ "dsrl\t%L0, %L0, 32\n\t" \ - "dsll\t%M0, %M1, 32\n\t" \ + "dsll\t%M0, %M0, 32\n\t" \ "or\t%L0, %L0, %M0\n\t" \ "dmtc0\t%L0, " #source "\n\t" \ ".set\tmips0" \ - : "=&r,r" (__tmp) \ - : "r,0" (val)); \ + : "+r" (__tmp)); \ else \ __asm__ __volatile__( \ ".set\tmips64\n\t" \ - "dsll\t%L0, %L1, 32\n\t" \ + "dsll\t%L0, %L0, 32\n\t" \ "dsrl\t%L0, %L0, 32\n\t" \ - "dsll\t%M0, %M1, 32\n\t" \ + "dsll\t%M0, %M0, 32\n\t" \ "or\t%L0, %L0, %M0\n\t" \ "dmtc0\t%L0, " #source ", " #sel "\n\t" \ ".set\tmips0" \ - : "=&r,r" (__tmp) \ - : "r,0" (val)); \ + : "+r" (__tmp)); \ local_irq_restore(__flags); \ } while (0) @@ -2767,7 +2774,6 @@ __BUILD_SET_C0(status) __BUILD_SET_C0(cause) __BUILD_SET_C0(config) __BUILD_SET_C0(config5) -__BUILD_SET_C0(config7) __BUILD_SET_C0(intcontrol) __BUILD_SET_C0(intctl) __BUILD_SET_C0(srsmap) diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h index da2004cef2d5..b509371a6b0c 100644 --- a/arch/mips/include/asm/mmu_context.h +++ b/arch/mips/include/asm/mmu_context.h @@ -126,8 +126,6 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm) for_each_possible_cpu(i) cpu_context(i, mm) = 0; - atomic_set(&mm->context.fp_mode_switching, 0); - mm->context.bd_emupage_allocmap = NULL; spin_lock_init(&mm->context.bd_emupage_lock); init_waitqueue_head(&mm->context.bd_emupage_queue); diff --git a/arch/mips/include/asm/netlogic/xlr/fmn.h b/arch/mips/include/asm/netlogic/xlr/fmn.h index 5604db3d1836..d79c68fa78d9 100644 --- a/arch/mips/include/asm/netlogic/xlr/fmn.h +++ b/arch/mips/include/asm/netlogic/xlr/fmn.h @@ -301,8 +301,6 @@ static inline int nlm_fmn_send(unsigned int size, unsigned int code, for (i = 0; i < 8; i++) { nlm_msgsnd(dest); status = nlm_read_c2_status0(); - if ((status & 0x2) == 1) - pr_info("Send pending fail!\n"); if ((status & 0x4) == 0) return 0; } diff --git a/arch/mips/include/asm/octeon/cvmx-asxx-defs.h b/arch/mips/include/asm/octeon/cvmx-asxx-defs.h index a1e21a3854cf..1eef155979f3 100644 --- a/arch/mips/include/asm/octeon/cvmx-asxx-defs.h +++ b/arch/mips/include/asm/octeon/cvmx-asxx-defs.h @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2012 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -55,6 +55,8 @@ #define CVMX_ASXX_TX_HI_WATERX(offset, block_id) (CVMX_ADD_IO_SEG(0x00011800B0000080ull) + (((offset) & 3) + ((block_id) & 1) * 0x1000000ull) * 8) #define CVMX_ASXX_TX_PRT_EN(block_id) (CVMX_ADD_IO_SEG(0x00011800B0000008ull) + ((block_id) & 1) * 0x8000000ull) +void __cvmx_interrupt_asxx_enable(int block); + union cvmx_asxx_gmii_rx_clk_set { uint64_t u64; struct cvmx_asxx_gmii_rx_clk_set_s { diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h index 6e61792d9248..1d18be8cdddc 100644 --- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h +++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h @@ -1,10014 +1,176 @@ -/***********************license start*************** - * Author: Cavium Networks +/* SPDX-License-Identifier: GPL-2.0 */ +/* Octeon CIU definitions * - * Contact: support@caviumnetworks.com - * This file is part of the OCTEON SDK - * - * Copyright (c) 2003-2012 Cavium Networks - * - * This file is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License, Version 2, as - * published by the Free Software Foundation. - * - * This file is distributed in the hope that it will be useful, but - * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or - * NONINFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this file; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * or visit http://www.gnu.org/licenses/. - * - * This file may also be available under a different license from Cavium. - * Contact Cavium Networks for more information - ***********************license end**************************************/ + * Copyright (C) 2003-2018 Cavium, Inc. + */ #ifndef __CVMX_CIU_DEFS_H__ #define __CVMX_CIU_DEFS_H__ -#define CVMX_CIU_BIST (CVMX_ADD_IO_SEG(0x0001070000000730ull)) -#define CVMX_CIU_BLOCK_INT (CVMX_ADD_IO_SEG(0x00010700000007C0ull)) -#define CVMX_CIU_DINT (CVMX_ADD_IO_SEG(0x0001070000000720ull)) -#define CVMX_CIU_EN2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x000107000000A600ull) + ((offset) & 1) * 8) -#define CVMX_CIU_EN2_IOX_INT_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CE00ull) + ((offset) & 1) * 8) -#define CVMX_CIU_EN2_IOX_INT_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AE00ull) + ((offset) & 1) * 8) -#define CVMX_CIU_EN2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x000107000000A000ull) + ((offset) & 15) * 8) -#define CVMX_CIU_EN2_PPX_IP2_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000C800ull) + ((offset) & 15) * 8) -#define CVMX_CIU_EN2_PPX_IP2_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000A800ull) + ((offset) & 15) * 8) -#define CVMX_CIU_EN2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x000107000000A200ull) + ((offset) & 15) * 8) -#define CVMX_CIU_EN2_PPX_IP3_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CA00ull) + ((offset) & 15) * 8) -#define CVMX_CIU_EN2_PPX_IP3_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AA00ull) + ((offset) & 15) * 8) -#define CVMX_CIU_EN2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x000107000000A400ull) + ((offset) & 15) * 8) -#define CVMX_CIU_EN2_PPX_IP4_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CC00ull) + ((offset) & 15) * 8) -#define CVMX_CIU_EN2_PPX_IP4_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AC00ull) + ((offset) & 15) * 8) -#define CVMX_CIU_FUSE (CVMX_ADD_IO_SEG(0x0001070000000728ull)) -#define CVMX_CIU_GSTOP (CVMX_ADD_IO_SEG(0x0001070000000710ull)) -#define CVMX_CIU_INT33_SUM0 (CVMX_ADD_IO_SEG(0x0001070000000110ull)) -#define CVMX_CIU_INTX_EN0(offset) (CVMX_ADD_IO_SEG(0x0001070000000200ull) + ((offset) & 63) * 16) -#define CVMX_CIU_INTX_EN0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002200ull) + ((offset) & 63) * 16) -#define CVMX_CIU_INTX_EN0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006200ull) + ((offset) & 63) * 16) -#define CVMX_CIU_INTX_EN1(offset) (CVMX_ADD_IO_SEG(0x0001070000000208ull) + ((offset) & 63) * 16) -#define CVMX_CIU_INTX_EN1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002208ull) + ((offset) & 63) * 16) -#define CVMX_CIU_INTX_EN1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006208ull) + ((offset) & 63) * 16) -#define CVMX_CIU_INTX_EN4_0(offset) (CVMX_ADD_IO_SEG(0x0001070000000C80ull) + ((offset) & 15) * 16) -#define CVMX_CIU_INTX_EN4_0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C80ull) + ((offset) & 15) * 16) -#define CVMX_CIU_INTX_EN4_0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C80ull) + ((offset) & 15) * 16) -#define CVMX_CIU_INTX_EN4_1(offset) (CVMX_ADD_IO_SEG(0x0001070000000C88ull) + ((offset) & 15) * 16) -#define CVMX_CIU_INTX_EN4_1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C88ull) + ((offset) & 15) * 16) -#define CVMX_CIU_INTX_EN4_1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C88ull) + ((offset) & 15) * 16) -#define CVMX_CIU_INTX_SUM0(offset) (CVMX_ADD_IO_SEG(0x0001070000000000ull) + ((offset) & 63) * 8) -#define CVMX_CIU_INTX_SUM4(offset) (CVMX_ADD_IO_SEG(0x0001070000000C00ull) + ((offset) & 15) * 8) -#define CVMX_CIU_INT_DBG_SEL (CVMX_ADD_IO_SEG(0x00010700000007D0ull)) -#define CVMX_CIU_INT_SUM1 (CVMX_ADD_IO_SEG(0x0001070000000108ull)) -static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned long offset) +#include <asm/bitfield.h> + +#define CVMX_CIU_ADDR(addr, coreid, coremask, offset) \ + (CVMX_ADD_IO_SEG(0x0001070000000000ull + addr##ull) + \ + (((coreid) & (coremask)) * offset)) + +#define CVMX_CIU_EN2_PPX_IP4(c) CVMX_CIU_ADDR(0xA400, c, 0x0F, 8) +#define CVMX_CIU_EN2_PPX_IP4_W1C(c) CVMX_CIU_ADDR(0xCC00, c, 0x0F, 8) +#define CVMX_CIU_EN2_PPX_IP4_W1S(c) CVMX_CIU_ADDR(0xAC00, c, 0x0F, 8) +#define CVMX_CIU_FUSE CVMX_CIU_ADDR(0x0728, 0, 0x00, 0) +#define CVMX_CIU_INT_SUM1 CVMX_CIU_ADDR(0x0108, 0, 0x00, 0) +#define CVMX_CIU_INTX_EN0(c) CVMX_CIU_ADDR(0x0200, c, 0x3F, 16) +#define CVMX_CIU_INTX_EN0_W1C(c) CVMX_CIU_ADDR(0x2200, c, 0x3F, 16) +#define CVMX_CIU_INTX_EN0_W1S(c) CVMX_CIU_ADDR(0x6200, c, 0x3F, 16) +#define CVMX_CIU_INTX_EN1(c) CVMX_CIU_ADDR(0x0208, c, 0x3F, 16) +#define CVMX_CIU_INTX_EN1_W1C(c) CVMX_CIU_ADDR(0x2208, c, 0x3F, 16) +#define CVMX_CIU_INTX_EN1_W1S(c) CVMX_CIU_ADDR(0x6208, c, 0x3F, 16) +#define CVMX_CIU_INTX_SUM0(c) CVMX_CIU_ADDR(0x0000, c, 0x3F, 8) +#define CVMX_CIU_NMI CVMX_CIU_ADDR(0x0718, 0, 0x00, 0) +#define CVMX_CIU_PCI_INTA CVMX_CIU_ADDR(0x0750, 0, 0x00, 0) +#define CVMX_CIU_PP_BIST_STAT CVMX_CIU_ADDR(0x07E0, 0, 0x00, 0) +#define CVMX_CIU_PP_DBG CVMX_CIU_ADDR(0x0708, 0, 0x00, 0) +#define CVMX_CIU_PP_RST CVMX_CIU_ADDR(0x0700, 0, 0x00, 0) +#define CVMX_CIU_QLM0 CVMX_CIU_ADDR(0x0780, 0, 0x00, 0) +#define CVMX_CIU_QLM1 CVMX_CIU_ADDR(0x0788, 0, 0x00, 0) +#define CVMX_CIU_QLM_JTGC CVMX_CIU_ADDR(0x0768, 0, 0x00, 0) +#define CVMX_CIU_QLM_JTGD CVMX_CIU_ADDR(0x0770, 0, 0x00, 0) +#define CVMX_CIU_SOFT_BIST CVMX_CIU_ADDR(0x0738, 0, 0x00, 0) +#define CVMX_CIU_SOFT_PRST1 CVMX_CIU_ADDR(0x0758, 0, 0x00, 0) +#define CVMX_CIU_SOFT_PRST CVMX_CIU_ADDR(0x0748, 0, 0x00, 0) +#define CVMX_CIU_SOFT_RST CVMX_CIU_ADDR(0x0740, 0, 0x00, 0) +#define CVMX_CIU_SUM2_PPX_IP4(c) CVMX_CIU_ADDR(0x8C00, c, 0x0F, 8) +#define CVMX_CIU_TIM_MULTI_CAST CVMX_CIU_ADDR(0xC200, 0, 0x00, 0) +#define CVMX_CIU_TIMX(c) CVMX_CIU_ADDR(0x0480, c, 0x0F, 8) + +static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned int coreid) { - switch (cvmx_get_octeon_family()) { - case OCTEON_CN30XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8; - case OCTEON_CN52XX & OCTEON_FAMILY_MASK: - case OCTEON_CNF71XX & OCTEON_FAMILY_MASK: - case OCTEON_CN61XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8; - case OCTEON_CN31XX & OCTEON_FAMILY_MASK: - case OCTEON_CN50XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8; - case OCTEON_CN38XX & OCTEON_FAMILY_MASK: - case OCTEON_CN58XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8; - case OCTEON_CN56XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8; - case OCTEON_CN66XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8; - case OCTEON_CN63XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8; - case OCTEON_CN68XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070100100600ull) + (offset) * 8; - } - return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8; + if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK)) + return CVMX_CIU_ADDR(0x100100600, coreid, 0x0F, 8); + else + return CVMX_CIU_ADDR(0x000000680, coreid, 0x0F, 8); } -static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned long offset) +static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned int coreid) { - switch (cvmx_get_octeon_family()) { - case OCTEON_CN30XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8; - case OCTEON_CN52XX & OCTEON_FAMILY_MASK: - case OCTEON_CNF71XX & OCTEON_FAMILY_MASK: - case OCTEON_CN61XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8; - case OCTEON_CN31XX & OCTEON_FAMILY_MASK: - case OCTEON_CN50XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8; - case OCTEON_CN38XX & OCTEON_FAMILY_MASK: - case OCTEON_CN58XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8; - case OCTEON_CN56XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8; - case OCTEON_CN66XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8; - case OCTEON_CN63XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8; - case OCTEON_CN68XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070100100400ull) + (offset) * 8; - } - return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8; + if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK)) + return CVMX_CIU_ADDR(0x100100400, coreid, 0x0F, 8); + else + return CVMX_CIU_ADDR(0x000000600, coreid, 0x0F, 8); } -#define CVMX_CIU_NMI (CVMX_ADD_IO_SEG(0x0001070000000718ull)) -#define CVMX_CIU_PCI_INTA (CVMX_ADD_IO_SEG(0x0001070000000750ull)) -#define CVMX_CIU_PP_BIST_STAT (CVMX_ADD_IO_SEG(0x00010700000007E0ull)) -#define CVMX_CIU_PP_DBG (CVMX_ADD_IO_SEG(0x0001070000000708ull)) -static inline uint64_t CVMX_CIU_PP_POKEX(unsigned long offset) +static inline uint64_t CVMX_CIU_PP_POKEX(unsigned int coreid) { switch (cvmx_get_octeon_family()) { - case OCTEON_CN30XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8; - case OCTEON_CN52XX & OCTEON_FAMILY_MASK: - case OCTEON_CNF71XX & OCTEON_FAMILY_MASK: - case OCTEON_CN61XX & OCTEON_FAMILY_MASK: - case OCTEON_CN70XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8; - case OCTEON_CN31XX & OCTEON_FAMILY_MASK: - case OCTEON_CN50XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8; - case OCTEON_CN38XX & OCTEON_FAMILY_MASK: - case OCTEON_CN58XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8; - case OCTEON_CN56XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8; - case OCTEON_CN66XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8; - case OCTEON_CN63XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8; case OCTEON_CN68XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070100100200ull) + (offset) * 8; + return CVMX_CIU_ADDR(0x100100200, coreid, 0x0F, 8); case OCTEON_CNF75XX & OCTEON_FAMILY_MASK: case OCTEON_CN73XX & OCTEON_FAMILY_MASK: case OCTEON_CN78XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001010000030000ull) + (offset) * 8; + return CVMX_CIU_ADDR(0x000030000, coreid, 0x0F, 8) - + 0x60000000000ull; + default: + return CVMX_CIU_ADDR(0x000000580, coreid, 0x0F, 8); } - return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8; } -#define CVMX_CIU_PP_RST (CVMX_ADD_IO_SEG(0x0001070000000700ull)) -#define CVMX_CIU_QLM0 (CVMX_ADD_IO_SEG(0x0001070000000780ull)) -#define CVMX_CIU_QLM1 (CVMX_ADD_IO_SEG(0x0001070000000788ull)) -#define CVMX_CIU_QLM2 (CVMX_ADD_IO_SEG(0x0001070000000790ull)) -#define CVMX_CIU_QLM3 (CVMX_ADD_IO_SEG(0x0001070000000798ull)) -#define CVMX_CIU_QLM4 (CVMX_ADD_IO_SEG(0x00010700000007A0ull)) -#define CVMX_CIU_QLM_DCOK (CVMX_ADD_IO_SEG(0x0001070000000760ull)) -#define CVMX_CIU_QLM_JTGC (CVMX_ADD_IO_SEG(0x0001070000000768ull)) -#define CVMX_CIU_QLM_JTGD (CVMX_ADD_IO_SEG(0x0001070000000770ull)) -#define CVMX_CIU_SOFT_BIST (CVMX_ADD_IO_SEG(0x0001070000000738ull)) -#define CVMX_CIU_SOFT_PRST (CVMX_ADD_IO_SEG(0x0001070000000748ull)) -#define CVMX_CIU_SOFT_PRST1 (CVMX_ADD_IO_SEG(0x0001070000000758ull)) -#define CVMX_CIU_SOFT_PRST2 (CVMX_ADD_IO_SEG(0x00010700000007D8ull)) -#define CVMX_CIU_SOFT_PRST3 (CVMX_ADD_IO_SEG(0x00010700000007E0ull)) -#define CVMX_CIU_SOFT_RST (CVMX_ADD_IO_SEG(0x0001070000000740ull)) -#define CVMX_CIU_SUM1_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008600ull) + ((offset) & 1) * 8) -#define CVMX_CIU_SUM1_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008000ull) + ((offset) & 15) * 8) -#define CVMX_CIU_SUM1_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008200ull) + ((offset) & 15) * 8) -#define CVMX_CIU_SUM1_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008400ull) + ((offset) & 15) * 8) -#define CVMX_CIU_SUM2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008E00ull) + ((offset) & 1) * 8) -#define CVMX_CIU_SUM2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008800ull) + ((offset) & 15) * 8) -#define CVMX_CIU_SUM2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008A00ull) + ((offset) & 15) * 8) -#define CVMX_CIU_SUM2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008C00ull) + ((offset) & 15) * 8) -#define CVMX_CIU_TIMX(offset) (CVMX_ADD_IO_SEG(0x0001070000000480ull) + ((offset) & 15) * 8) -#define CVMX_CIU_TIM_MULTI_CAST (CVMX_ADD_IO_SEG(0x000107000000C200ull)) -static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset) +static inline uint64_t CVMX_CIU_WDOGX(unsigned int coreid) { switch (cvmx_get_octeon_family()) { - case OCTEON_CN30XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8; - case OCTEON_CN52XX & OCTEON_FAMILY_MASK: - case OCTEON_CNF71XX & OCTEON_FAMILY_MASK: - case OCTEON_CN61XX & OCTEON_FAMILY_MASK: - case OCTEON_CN70XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8; - case OCTEON_CN31XX & OCTEON_FAMILY_MASK: - case OCTEON_CN50XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8; - case OCTEON_CN38XX & OCTEON_FAMILY_MASK: - case OCTEON_CN58XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8; - case OCTEON_CN56XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8; - case OCTEON_CN66XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8; - case OCTEON_CN63XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8; case OCTEON_CN68XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001070100100000ull) + (offset) * 8; + return CVMX_CIU_ADDR(0x100100000, coreid, 0x0F, 8); case OCTEON_CNF75XX & OCTEON_FAMILY_MASK: case OCTEON_CN73XX & OCTEON_FAMILY_MASK: case OCTEON_CN78XX & OCTEON_FAMILY_MASK: - return CVMX_ADD_IO_SEG(0x0001010000020000ull) + (offset) * 8; + return CVMX_CIU_ADDR(0x000020000, coreid, 0x0F, 8) - + 0x60000000000ull; + default: + return CVMX_CIU_ADDR(0x000000500, coreid, 0x0F, 8); } - return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8; } -union cvmx_ciu_bist { - uint64_t u64; - struct cvmx_ciu_bist_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_7_63:57; - uint64_t bist:7; -#else - uint64_t bist:7; - uint64_t reserved_7_63:57; -#endif - } s; - struct cvmx_ciu_bist_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_4_63:60; - uint64_t bist:4; -#else - uint64_t bist:4; - uint64_t reserved_4_63:60; -#endif - } cn30xx; - struct cvmx_ciu_bist_cn30xx cn31xx; - struct cvmx_ciu_bist_cn30xx cn38xx; - struct cvmx_ciu_bist_cn30xx cn38xxp2; - struct cvmx_ciu_bist_cn50xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t bist:2; -#else - uint64_t bist:2; - uint64_t reserved_2_63:62; -#endif - } cn50xx; - struct cvmx_ciu_bist_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_3_63:61; - uint64_t bist:3; -#else - uint64_t bist:3; - uint64_t reserved_3_63:61; -#endif - } cn52xx; - struct cvmx_ciu_bist_cn52xx cn52xxp1; - struct cvmx_ciu_bist_cn30xx cn56xx; - struct cvmx_ciu_bist_cn30xx cn56xxp1; - struct cvmx_ciu_bist_cn30xx cn58xx; - struct cvmx_ciu_bist_cn30xx cn58xxp1; - struct cvmx_ciu_bist_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_6_63:58; - uint64_t bist:6; -#else - uint64_t bist:6; - uint64_t reserved_6_63:58; -#endif - } cn61xx; - struct cvmx_ciu_bist_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_5_63:59; - uint64_t bist:5; -#else - uint64_t bist:5; - uint64_t reserved_5_63:59; -#endif - } cn63xx; - struct cvmx_ciu_bist_cn63xx cn63xxp1; - struct cvmx_ciu_bist_cn61xx cn66xx; - struct cvmx_ciu_bist_s cn68xx; - struct cvmx_ciu_bist_s cn68xxp1; - struct cvmx_ciu_bist_cn61xx cnf71xx; -}; - -union cvmx_ciu_block_int { - uint64_t u64; - struct cvmx_ciu_block_int_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_62_63:2; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_43_59:17; - uint64_t ptp:1; - uint64_t dpi:1; - uint64_t dfm:1; - uint64_t reserved_34_39:6; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t reserved_31_31:1; - uint64_t iob:1; - uint64_t reserved_29_29:1; - uint64_t agl:1; - uint64_t reserved_27_27:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t reserved_24_24:1; - uint64_t asxpcs1:1; - uint64_t asxpcs0:1; - uint64_t reserved_21_21:1; - uint64_t pip:1; - uint64_t reserved_18_19:2; - uint64_t lmc0:1; - uint64_t l2c:1; - uint64_t reserved_15_15:1; - uint64_t rad:1; - uint64_t usb:1; - uint64_t pow:1; - uint64_t tim:1; - uint64_t pko:1; - uint64_t ipd:1; - uint64_t reserved_8_8:1; - uint64_t zip:1; - uint64_t dfa:1; - uint64_t fpa:1; - uint64_t key:1; - uint64_t sli:1; - uint64_t gmx1:1; - uint64_t gmx0:1; - uint64_t mio:1; -#else - uint64_t mio:1; - uint64_t gmx0:1; - uint64_t gmx1:1; - uint64_t sli:1; - uint64_t key:1; - uint64_t fpa:1; - uint64_t dfa:1; - uint64_t zip:1; - uint64_t reserved_8_8:1; - uint64_t ipd:1; - uint64_t pko:1; - uint64_t tim:1; - uint64_t pow:1; - uint64_t usb:1; - uint64_t rad:1; - uint64_t reserved_15_15:1; - uint64_t l2c:1; - uint64_t lmc0:1; - uint64_t reserved_18_19:2; - uint64_t pip:1; - uint64_t reserved_21_21:1; - uint64_t asxpcs0:1; - uint64_t asxpcs1:1; - uint64_t reserved_24_24:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_27_27:1; - uint64_t agl:1; - uint64_t reserved_29_29:1; - uint64_t iob:1; - uint64_t reserved_31_31:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t reserved_34_39:6; - uint64_t dfm:1; - uint64_t dpi:1; - uint64_t ptp:1; - uint64_t reserved_43_59:17; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_63:2; -#endif - } s; - struct cvmx_ciu_block_int_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_43_63:21; - uint64_t ptp:1; - uint64_t dpi:1; - uint64_t reserved_31_40:10; - uint64_t iob:1; - uint64_t reserved_29_29:1; - uint64_t agl:1; - uint64_t reserved_27_27:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t reserved_24_24:1; - uint64_t asxpcs1:1; - uint64_t asxpcs0:1; - uint64_t reserved_21_21:1; - uint64_t pip:1; - uint64_t reserved_18_19:2; - uint64_t lmc0:1; - uint64_t l2c:1; - uint64_t reserved_15_15:1; - uint64_t rad:1; - uint64_t usb:1; - uint64_t pow:1; - uint64_t tim:1; - uint64_t pko:1; - uint64_t ipd:1; - uint64_t reserved_8_8:1; - uint64_t zip:1; - uint64_t dfa:1; - uint64_t fpa:1; - uint64_t key:1; - uint64_t sli:1; - uint64_t gmx1:1; - uint64_t gmx0:1; - uint64_t mio:1; -#else - uint64_t mio:1; - uint64_t gmx0:1; - uint64_t gmx1:1; - uint64_t sli:1; - uint64_t key:1; - uint64_t fpa:1; - uint64_t dfa:1; - uint64_t zip:1; - uint64_t reserved_8_8:1; - uint64_t ipd:1; - uint64_t pko:1; - uint64_t tim:1; - uint64_t pow:1; - uint64_t usb:1; - uint64_t rad:1; - uint64_t reserved_15_15:1; - uint64_t l2c:1; - uint64_t lmc0:1; - uint64_t reserved_18_19:2; - uint64_t pip:1; - uint64_t reserved_21_21:1; - uint64_t asxpcs0:1; - uint64_t asxpcs1:1; - uint64_t reserved_24_24:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_27_27:1; - uint64_t agl:1; - uint64_t reserved_29_29:1; - uint64_t iob:1; - uint64_t reserved_31_40:10; - uint64_t dpi:1; - uint64_t ptp:1; - uint64_t reserved_43_63:21; -#endif - } cn61xx; - struct cvmx_ciu_block_int_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_43_63:21; - uint64_t ptp:1; - uint64_t dpi:1; - uint64_t dfm:1; - uint64_t reserved_34_39:6; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t reserved_31_31:1; - uint64_t iob:1; - uint64_t reserved_29_29:1; - uint64_t agl:1; - uint64_t reserved_27_27:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t reserved_23_24:2; - uint64_t asxpcs0:1; - uint64_t reserved_21_21:1; - uint64_t pip:1; - uint64_t reserved_18_19:2; - uint64_t lmc0:1; - uint64_t l2c:1; - uint64_t reserved_15_15:1; - uint64_t rad:1; - uint64_t usb:1; - uint64_t pow:1; - uint64_t tim:1; - uint64_t pko:1; - uint64_t ipd:1; - uint64_t reserved_8_8:1; - uint64_t zip:1; - uint64_t dfa:1; - uint64_t fpa:1; - uint64_t key:1; - uint64_t sli:1; - uint64_t reserved_2_2:1; - uint64_t gmx0:1; - uint64_t mio:1; -#else - uint64_t mio:1; - uint64_t gmx0:1; - uint64_t reserved_2_2:1; - uint64_t sli:1; - uint64_t key:1; - uint64_t fpa:1; - uint64_t dfa:1; - uint64_t zip:1; - uint64_t reserved_8_8:1; - uint64_t ipd:1; - uint64_t pko:1; - uint64_t tim:1; - uint64_t pow:1; - uint64_t usb:1; - uint64_t rad:1; - uint64_t reserved_15_15:1; - uint64_t l2c:1; - uint64_t lmc0:1; - uint64_t reserved_18_19:2; - uint64_t pip:1; - uint64_t reserved_21_21:1; - uint64_t asxpcs0:1; - uint64_t reserved_23_24:2; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_27_27:1; - uint64_t agl:1; - uint64_t reserved_29_29:1; - uint64_t iob:1; - uint64_t reserved_31_31:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t reserved_34_39:6; - uint64_t dfm:1; - uint64_t dpi:1; - uint64_t ptp:1; - uint64_t reserved_43_63:21; -#endif - } cn63xx; - struct cvmx_ciu_block_int_cn63xx cn63xxp1; - struct cvmx_ciu_block_int_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_62_63:2; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_43_59:17; - uint64_t ptp:1; - uint64_t dpi:1; - uint64_t dfm:1; - uint64_t reserved_33_39:7; - uint64_t srio0:1; - uint64_t reserved_31_31:1; - uint64_t iob:1; - uint64_t reserved_29_29:1; - uint64_t agl:1; - uint64_t reserved_27_27:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t reserved_24_24:1; - uint64_t asxpcs1:1; - uint64_t asxpcs0:1; - uint64_t reserved_21_21:1; - uint64_t pip:1; - uint64_t reserved_18_19:2; - uint64_t lmc0:1; - uint64_t l2c:1; - uint64_t reserved_15_15:1; - uint64_t rad:1; - uint64_t usb:1; - uint64_t pow:1; - uint64_t tim:1; - uint64_t pko:1; - uint64_t ipd:1; - uint64_t reserved_8_8:1; - uint64_t zip:1; - uint64_t dfa:1; - uint64_t fpa:1; - uint64_t key:1; - uint64_t sli:1; - uint64_t gmx1:1; - uint64_t gmx0:1; - uint64_t mio:1; -#else - uint64_t mio:1; - uint64_t gmx0:1; - uint64_t gmx1:1; - uint64_t sli:1; - uint64_t key:1; - uint64_t fpa:1; - uint64_t dfa:1; - uint64_t zip:1; - uint64_t reserved_8_8:1; - uint64_t ipd:1; - uint64_t pko:1; - uint64_t tim:1; - uint64_t pow:1; - uint64_t usb:1; - uint64_t rad:1; - uint64_t reserved_15_15:1; - uint64_t l2c:1; - uint64_t lmc0:1; - uint64_t reserved_18_19:2; - uint64_t pip:1; - uint64_t reserved_21_21:1; - uint64_t asxpcs0:1; - uint64_t asxpcs1:1; - uint64_t reserved_24_24:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_27_27:1; - uint64_t agl:1; - uint64_t reserved_29_29:1; - uint64_t iob:1; - uint64_t reserved_31_31:1; - uint64_t srio0:1; - uint64_t reserved_33_39:7; - uint64_t dfm:1; - uint64_t dpi:1; - uint64_t ptp:1; - uint64_t reserved_43_59:17; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_63:2; -#endif - } cn66xx; - struct cvmx_ciu_block_int_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_43_63:21; - uint64_t ptp:1; - uint64_t dpi:1; - uint64_t reserved_31_40:10; - uint64_t iob:1; - uint64_t reserved_27_29:3; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t reserved_23_24:2; - uint64_t asxpcs0:1; - uint64_t reserved_21_21:1; - uint64_t pip:1; - uint64_t reserved_18_19:2; - uint64_t lmc0:1; - uint64_t l2c:1; - uint64_t reserved_15_15:1; - uint64_t rad:1; - uint64_t usb:1; - uint64_t pow:1; - uint64_t tim:1; - uint64_t pko:1; - uint64_t ipd:1; - uint64_t reserved_6_8:3; - uint64_t fpa:1; - uint64_t key:1; - uint64_t sli:1; - uint64_t reserved_2_2:1; - uint64_t gmx0:1; - uint64_t mio:1; -#else - uint64_t mio:1; - uint64_t gmx0:1; - uint64_t reserved_2_2:1; - uint64_t sli:1; - uint64_t key:1; - uint64_t fpa:1; - uint64_t reserved_6_8:3; - uint64_t ipd:1; - uint64_t pko:1; - uint64_t tim:1; - uint64_t pow:1; - uint64_t usb:1; - uint64_t rad:1; - uint64_t reserved_15_15:1; - uint64_t l2c:1; - uint64_t lmc0:1; - uint64_t reserved_18_19:2; - uint64_t pip:1; - uint64_t reserved_21_21:1; - uint64_t asxpcs0:1; - uint64_t reserved_23_24:2; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_27_29:3; - uint64_t iob:1; - uint64_t reserved_31_40:10; - uint64_t dpi:1; - uint64_t ptp:1; - uint64_t reserved_43_63:21; -#endif - } cnf71xx; -}; - -union cvmx_ciu_dint { - uint64_t u64; - struct cvmx_ciu_dint_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t dint:32; -#else - uint64_t dint:32; - uint64_t reserved_32_63:32; -#endif - } s; - struct cvmx_ciu_dint_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t dint:1; -#else - uint64_t dint:1; - uint64_t reserved_1_63:63; -#endif - } cn30xx; - struct cvmx_ciu_dint_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t dint:2; -#else - uint64_t dint:2; - uint64_t reserved_2_63:62; -#endif - } cn31xx; - struct cvmx_ciu_dint_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t dint:16; -#else - uint64_t dint:16; - uint64_t reserved_16_63:48; -#endif - } cn38xx; - struct cvmx_ciu_dint_cn38xx cn38xxp2; - struct cvmx_ciu_dint_cn31xx cn50xx; - struct cvmx_ciu_dint_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_4_63:60; - uint64_t dint:4; -#else - uint64_t dint:4; - uint64_t reserved_4_63:60; -#endif - } cn52xx; - struct cvmx_ciu_dint_cn52xx cn52xxp1; - struct cvmx_ciu_dint_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t dint:12; -#else - uint64_t dint:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_dint_cn56xx cn56xxp1; - struct cvmx_ciu_dint_cn38xx cn58xx; - struct cvmx_ciu_dint_cn38xx cn58xxp1; - struct cvmx_ciu_dint_cn52xx cn61xx; - struct cvmx_ciu_dint_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_6_63:58; - uint64_t dint:6; -#else - uint64_t dint:6; - uint64_t reserved_6_63:58; -#endif - } cn63xx; - struct cvmx_ciu_dint_cn63xx cn63xxp1; - struct cvmx_ciu_dint_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t dint:10; -#else - uint64_t dint:10; - uint64_t reserved_10_63:54; -#endif - } cn66xx; - struct cvmx_ciu_dint_s cn68xx; - struct cvmx_ciu_dint_s cn68xxp1; - struct cvmx_ciu_dint_cn52xx cnf71xx; -}; - -union cvmx_ciu_en2_iox_int { - uint64_t u64; - struct cvmx_ciu_en2_iox_int_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_iox_int_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_iox_int_cn61xx cn66xx; - struct cvmx_ciu_en2_iox_int_s cnf71xx; -}; - -union cvmx_ciu_en2_iox_int_w1c { - uint64_t u64; - struct cvmx_ciu_en2_iox_int_w1c_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_iox_int_w1c_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_iox_int_w1c_cn61xx cn66xx; - struct cvmx_ciu_en2_iox_int_w1c_s cnf71xx; -}; - -union cvmx_ciu_en2_iox_int_w1s { - uint64_t u64; - struct cvmx_ciu_en2_iox_int_w1s_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_iox_int_w1s_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_iox_int_w1s_cn61xx cn66xx; - struct cvmx_ciu_en2_iox_int_w1s_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip2 { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip2_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip2_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip2_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip2_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip2_w1c { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip2_w1c_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip2_w1c_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip2_w1s { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip2_w1s_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip2_w1s_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip3 { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip3_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip3_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip3_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip3_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip3_w1c { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip3_w1c_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip3_w1c_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip3_w1s { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip3_w1s_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip3_w1s_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip4 { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip4_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip4_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip4_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip4_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip4_w1c { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip4_w1c_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip4_w1c_s cnf71xx; -}; - -union cvmx_ciu_en2_ppx_ip4_w1s { - uint64_t u64; - struct cvmx_ciu_en2_ppx_ip4_w1s_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx cn66xx; - struct cvmx_ciu_en2_ppx_ip4_w1s_s cnf71xx; -}; - -union cvmx_ciu_fuse { - uint64_t u64; - struct cvmx_ciu_fuse_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t fuse:32; -#else - uint64_t fuse:32; - uint64_t reserved_32_63:32; -#endif - } s; - struct cvmx_ciu_fuse_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t fuse:1; -#else - uint64_t fuse:1; - uint64_t reserved_1_63:63; -#endif - } cn30xx; - struct cvmx_ciu_fuse_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t fuse:2; -#else - uint64_t fuse:2; - uint64_t reserved_2_63:62; -#endif - } cn31xx; - struct cvmx_ciu_fuse_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t fuse:16; -#else - uint64_t fuse:16; - uint64_t reserved_16_63:48; -#endif - } cn38xx; - struct cvmx_ciu_fuse_cn38xx cn38xxp2; - struct cvmx_ciu_fuse_cn31xx cn50xx; - struct cvmx_ciu_fuse_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_4_63:60; - uint64_t fuse:4; -#else - uint64_t fuse:4; - uint64_t reserved_4_63:60; -#endif - } cn52xx; - struct cvmx_ciu_fuse_cn52xx cn52xxp1; - struct cvmx_ciu_fuse_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t fuse:12; -#else - uint64_t fuse:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_fuse_cn56xx cn56xxp1; - struct cvmx_ciu_fuse_cn38xx cn58xx; - struct cvmx_ciu_fuse_cn38xx cn58xxp1; - struct cvmx_ciu_fuse_cn52xx cn61xx; - struct cvmx_ciu_fuse_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_6_63:58; - uint64_t fuse:6; -#else - uint64_t fuse:6; - uint64_t reserved_6_63:58; -#endif - } cn63xx; - struct cvmx_ciu_fuse_cn63xx cn63xxp1; - struct cvmx_ciu_fuse_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t fuse:10; -#else - uint64_t fuse:10; - uint64_t reserved_10_63:54; -#endif - } cn66xx; - struct cvmx_ciu_fuse_s cn68xx; - struct cvmx_ciu_fuse_s cn68xxp1; - struct cvmx_ciu_fuse_cn52xx cnf71xx; -}; - -union cvmx_ciu_gstop { - uint64_t u64; - struct cvmx_ciu_gstop_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t gstop:1; -#else - uint64_t gstop:1; - uint64_t reserved_1_63:63; -#endif - } s; - struct cvmx_ciu_gstop_s cn30xx; - struct cvmx_ciu_gstop_s cn31xx; - struct cvmx_ciu_gstop_s cn38xx; - struct cvmx_ciu_gstop_s cn38xxp2; - struct cvmx_ciu_gstop_s cn50xx; - struct cvmx_ciu_gstop_s cn52xx; - struct cvmx_ciu_gstop_s cn52xxp1; - struct cvmx_ciu_gstop_s cn56xx; - struct cvmx_ciu_gstop_s cn56xxp1; - struct cvmx_ciu_gstop_s cn58xx; - struct cvmx_ciu_gstop_s cn58xxp1; - struct cvmx_ciu_gstop_s cn61xx; - struct cvmx_ciu_gstop_s cn63xx; - struct cvmx_ciu_gstop_s cn63xxp1; - struct cvmx_ciu_gstop_s cn66xx; - struct cvmx_ciu_gstop_s cn68xx; - struct cvmx_ciu_gstop_s cn68xxp1; - struct cvmx_ciu_gstop_s cnf71xx; -}; - -union cvmx_ciu_intx_en0 { - uint64_t u64; - struct cvmx_ciu_intx_en0_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_intx_en0_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_59_63:5; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t reserved_47_47:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t reserved_47_47:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t reserved_59_63:5; -#endif - } cn30xx; - struct cvmx_ciu_intx_en0_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_59_63:5; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t reserved_59_63:5; -#endif - } cn31xx; - struct cvmx_ciu_intx_en0_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_56_63:8; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t reserved_56_63:8; -#endif - } cn38xx; - struct cvmx_ciu_intx_en0_cn38xx cn38xxp2; - struct cvmx_ciu_intx_en0_cn30xx cn50xx; - struct cvmx_ciu_intx_en0_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn52xx; - struct cvmx_ciu_intx_en0_cn52xx cn52xxp1; - struct cvmx_ciu_intx_en0_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn56xx; - struct cvmx_ciu_intx_en0_cn56xx cn56xxp1; - struct cvmx_ciu_intx_en0_cn38xx cn58xx; - struct cvmx_ciu_intx_en0_cn38xx cn58xxp1; - struct cvmx_ciu_intx_en0_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en0_cn52xx cn63xx; - struct cvmx_ciu_intx_en0_cn52xx cn63xxp1; - struct cvmx_ciu_intx_en0_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en0_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en0_w1c { - uint64_t u64; - struct cvmx_ciu_intx_en0_w1c_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_intx_en0_w1c_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn52xx; - struct cvmx_ciu_intx_en0_w1c_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn56xx; - struct cvmx_ciu_intx_en0_w1c_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_56_63:8; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t reserved_56_63:8; -#endif - } cn58xx; - struct cvmx_ciu_intx_en0_w1c_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xx; - struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xxp1; - struct cvmx_ciu_intx_en0_w1c_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en0_w1c_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en0_w1s { - uint64_t u64; - struct cvmx_ciu_intx_en0_w1s_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_intx_en0_w1s_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn52xx; - struct cvmx_ciu_intx_en0_w1s_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn56xx; - struct cvmx_ciu_intx_en0_w1s_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_56_63:8; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t reserved_56_63:8; -#endif - } cn58xx; - struct cvmx_ciu_intx_en0_w1s_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xx; - struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xxp1; - struct cvmx_ciu_intx_en0_w1s_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en0_w1s_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en1 { - uint64_t u64; - struct cvmx_ciu_intx_en1_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_intx_en1_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t wdog:1; -#else - uint64_t wdog:1; - uint64_t reserved_1_63:63; -#endif - } cn30xx; - struct cvmx_ciu_intx_en1_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t wdog:2; -#else - uint64_t wdog:2; - uint64_t reserved_2_63:62; -#endif - } cn31xx; - struct cvmx_ciu_intx_en1_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t reserved_16_63:48; -#endif - } cn38xx; - struct cvmx_ciu_intx_en1_cn38xx cn38xxp2; - struct cvmx_ciu_intx_en1_cn31xx cn50xx; - struct cvmx_ciu_intx_en1_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_20_63:44; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t reserved_20_63:44; -#endif - } cn52xx; - struct cvmx_ciu_intx_en1_cn52xxp1 { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_19_63:45; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t reserved_19_63:45; -#endif - } cn52xxp1; - struct cvmx_ciu_intx_en1_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t wdog:12; -#else - uint64_t wdog:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_intx_en1_cn56xx cn56xxp1; - struct cvmx_ciu_intx_en1_cn38xx cn58xx; - struct cvmx_ciu_intx_en1_cn38xx cn58xxp1; - struct cvmx_ciu_intx_en1_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en1_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_57_62:6; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_37_45:9; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_6_17:12; - uint64_t wdog:6; -#else - uint64_t wdog:6; - uint64_t reserved_6_17:12; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_45:9; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_62:6; - uint64_t rst:1; -#endif - } cn63xx; - struct cvmx_ciu_intx_en1_cn63xx cn63xxp1; - struct cvmx_ciu_intx_en1_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en1_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en1_w1c { - uint64_t u64; - struct cvmx_ciu_intx_en1_w1c_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_intx_en1_w1c_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_20_63:44; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t reserved_20_63:44; -#endif - } cn52xx; - struct cvmx_ciu_intx_en1_w1c_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t wdog:12; -#else - uint64_t wdog:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_intx_en1_w1c_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t reserved_16_63:48; -#endif - } cn58xx; - struct cvmx_ciu_intx_en1_w1c_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en1_w1c_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_57_62:6; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_37_45:9; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_6_17:12; - uint64_t wdog:6; -#else - uint64_t wdog:6; - uint64_t reserved_6_17:12; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_45:9; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_62:6; - uint64_t rst:1; -#endif - } cn63xx; - struct cvmx_ciu_intx_en1_w1c_cn63xx cn63xxp1; - struct cvmx_ciu_intx_en1_w1c_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en1_w1c_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en1_w1s { - uint64_t u64; - struct cvmx_ciu_intx_en1_w1s_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_intx_en1_w1s_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_20_63:44; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t reserved_20_63:44; -#endif - } cn52xx; - struct cvmx_ciu_intx_en1_w1s_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t wdog:12; -#else - uint64_t wdog:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_intx_en1_w1s_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t reserved_16_63:48; -#endif - } cn58xx; - struct cvmx_ciu_intx_en1_w1s_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en1_w1s_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_57_62:6; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_37_45:9; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_6_17:12; - uint64_t wdog:6; -#else - uint64_t wdog:6; - uint64_t reserved_6_17:12; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_45:9; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_62:6; - uint64_t rst:1; -#endif - } cn63xx; - struct cvmx_ciu_intx_en1_w1s_cn63xx cn63xxp1; - struct cvmx_ciu_intx_en1_w1s_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en1_w1s_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en4_0 { - uint64_t u64; - struct cvmx_ciu_intx_en4_0_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_intx_en4_0_cn50xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_59_63:5; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t reserved_47_47:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t reserved_47_47:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t reserved_59_63:5; -#endif - } cn50xx; - struct cvmx_ciu_intx_en4_0_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn52xx; - struct cvmx_ciu_intx_en4_0_cn52xx cn52xxp1; - struct cvmx_ciu_intx_en4_0_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn56xx; - struct cvmx_ciu_intx_en4_0_cn56xx cn56xxp1; - struct cvmx_ciu_intx_en4_0_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_56_63:8; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t reserved_56_63:8; -#endif - } cn58xx; - struct cvmx_ciu_intx_en4_0_cn58xx cn58xxp1; - struct cvmx_ciu_intx_en4_0_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en4_0_cn52xx cn63xx; - struct cvmx_ciu_intx_en4_0_cn52xx cn63xxp1; - struct cvmx_ciu_intx_en4_0_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en4_0_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en4_0_w1c { - uint64_t u64; - struct cvmx_ciu_intx_en4_0_w1c_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_intx_en4_0_w1c_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn52xx; - struct cvmx_ciu_intx_en4_0_w1c_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn56xx; - struct cvmx_ciu_intx_en4_0_w1c_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_56_63:8; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t reserved_56_63:8; -#endif - } cn58xx; - struct cvmx_ciu_intx_en4_0_w1c_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xx; - struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xxp1; - struct cvmx_ciu_intx_en4_0_w1c_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en4_0_w1c_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en4_0_w1s { - uint64_t u64; - struct cvmx_ciu_intx_en4_0_w1s_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_intx_en4_0_w1s_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn52xx; - struct cvmx_ciu_intx_en4_0_w1s_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn56xx; - struct cvmx_ciu_intx_en4_0_w1s_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_56_63:8; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t reserved_56_63:8; -#endif - } cn58xx; - struct cvmx_ciu_intx_en4_0_w1s_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xx; - struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xxp1; - struct cvmx_ciu_intx_en4_0_w1s_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en4_0_w1s_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t reserved_44_44:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t reserved_44_44:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en4_1 { - uint64_t u64; - struct cvmx_ciu_intx_en4_1_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_intx_en4_1_cn50xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t wdog:2; -#else - uint64_t wdog:2; - uint64_t reserved_2_63:62; -#endif - } cn50xx; - struct cvmx_ciu_intx_en4_1_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_20_63:44; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t reserved_20_63:44; -#endif - } cn52xx; - struct cvmx_ciu_intx_en4_1_cn52xxp1 { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_19_63:45; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t reserved_19_63:45; -#endif - } cn52xxp1; - struct cvmx_ciu_intx_en4_1_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t wdog:12; -#else - uint64_t wdog:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_intx_en4_1_cn56xx cn56xxp1; - struct cvmx_ciu_intx_en4_1_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t reserved_16_63:48; -#endif - } cn58xx; - struct cvmx_ciu_intx_en4_1_cn58xx cn58xxp1; - struct cvmx_ciu_intx_en4_1_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en4_1_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_57_62:6; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_37_45:9; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_6_17:12; - uint64_t wdog:6; -#else - uint64_t wdog:6; - uint64_t reserved_6_17:12; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_45:9; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_62:6; - uint64_t rst:1; -#endif - } cn63xx; - struct cvmx_ciu_intx_en4_1_cn63xx cn63xxp1; - struct cvmx_ciu_intx_en4_1_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en4_1_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en4_1_w1c { - uint64_t u64; - struct cvmx_ciu_intx_en4_1_w1c_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_intx_en4_1_w1c_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_20_63:44; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t reserved_20_63:44; -#endif - } cn52xx; - struct cvmx_ciu_intx_en4_1_w1c_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t wdog:12; -#else - uint64_t wdog:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_intx_en4_1_w1c_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t reserved_16_63:48; -#endif - } cn58xx; - struct cvmx_ciu_intx_en4_1_w1c_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en4_1_w1c_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_57_62:6; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_37_45:9; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_6_17:12; - uint64_t wdog:6; -#else - uint64_t wdog:6; - uint64_t reserved_6_17:12; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_45:9; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_62:6; - uint64_t rst:1; -#endif - } cn63xx; - struct cvmx_ciu_intx_en4_1_w1c_cn63xx cn63xxp1; - struct cvmx_ciu_intx_en4_1_w1c_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en4_1_w1c_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_en4_1_w1s { - uint64_t u64; - struct cvmx_ciu_intx_en4_1_w1s_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_intx_en4_1_w1s_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_20_63:44; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t reserved_20_63:44; -#endif - } cn52xx; - struct cvmx_ciu_intx_en4_1_w1s_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t wdog:12; -#else - uint64_t wdog:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_intx_en4_1_w1s_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t reserved_16_63:48; -#endif - } cn58xx; - struct cvmx_ciu_intx_en4_1_w1s_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_en4_1_w1s_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_57_62:6; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_37_45:9; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_6_17:12; - uint64_t wdog:6; -#else - uint64_t wdog:6; - uint64_t reserved_6_17:12; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_45:9; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_62:6; - uint64_t rst:1; -#endif - } cn63xx; - struct cvmx_ciu_intx_en4_1_w1s_cn63xx cn63xxp1; - struct cvmx_ciu_intx_en4_1_w1s_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_en4_1_w1s_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_sum0 { - uint64_t u64; - struct cvmx_ciu_intx_sum0_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_intx_sum0_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_59_63:5; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t reserved_47_47:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t reserved_47_47:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t reserved_59_63:5; -#endif - } cn30xx; - struct cvmx_ciu_intx_sum0_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_59_63:5; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t reserved_59_63:5; -#endif - } cn31xx; - struct cvmx_ciu_intx_sum0_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_56_63:8; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t reserved_56_63:8; -#endif - } cn38xx; - struct cvmx_ciu_intx_sum0_cn38xx cn38xxp2; - struct cvmx_ciu_intx_sum0_cn30xx cn50xx; - struct cvmx_ciu_intx_sum0_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn52xx; - struct cvmx_ciu_intx_sum0_cn52xx cn52xxp1; - struct cvmx_ciu_intx_sum0_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn56xx; - struct cvmx_ciu_intx_sum0_cn56xx cn56xxp1; - struct cvmx_ciu_intx_sum0_cn38xx cn58xx; - struct cvmx_ciu_intx_sum0_cn38xx cn58xxp1; - struct cvmx_ciu_intx_sum0_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_sum0_cn52xx cn63xx; - struct cvmx_ciu_intx_sum0_cn52xx cn63xxp1; - struct cvmx_ciu_intx_sum0_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_sum0_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_intx_sum4 { - uint64_t u64; - struct cvmx_ciu_intx_sum4_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_intx_sum4_cn50xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_59_63:5; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t reserved_47_47:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t reserved_47_47:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t reserved_59_63:5; -#endif - } cn50xx; - struct cvmx_ciu_intx_sum4_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn52xx; - struct cvmx_ciu_intx_sum4_cn52xx cn52xxp1; - struct cvmx_ciu_intx_sum4_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn56xx; - struct cvmx_ciu_intx_sum4_cn56xx cn56xxp1; - struct cvmx_ciu_intx_sum4_cn58xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_56_63:8; - uint64_t timer:4; - uint64_t key_zero:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t key_zero:1; - uint64_t timer:4; - uint64_t reserved_56_63:8; -#endif - } cn58xx; - struct cvmx_ciu_intx_sum4_cn58xx cn58xxp1; - struct cvmx_ciu_intx_sum4_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn61xx; - struct cvmx_ciu_intx_sum4_cn52xx cn63xx; - struct cvmx_ciu_intx_sum4_cn52xx cn63xxp1; - struct cvmx_ciu_intx_sum4_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_intx_sum4_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_int33_sum0 { - uint64_t u64; - struct cvmx_ciu_int33_sum0_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } s; - struct cvmx_ciu_int33_sum0_s cn61xx; - struct cvmx_ciu_int33_sum0_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t reserved_57_58:2; - uint64_t usb:1; - uint64_t timer:4; - uint64_t reserved_51_51:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t reserved_51_51:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_58:2; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn63xx; - struct cvmx_ciu_int33_sum0_cn63xx cn63xxp1; - struct cvmx_ciu_int33_sum0_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t mii:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t reserved_57_57:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t gmx_drp:2; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:2; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t reserved_57_57:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t mii:1; - uint64_t bootdma:1; -#endif - } cn66xx; - struct cvmx_ciu_int33_sum0_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t bootdma:1; - uint64_t reserved_62_62:1; - uint64_t ipdppthr:1; - uint64_t powiq:1; - uint64_t twsi2:1; - uint64_t mpi:1; - uint64_t pcm:1; - uint64_t usb:1; - uint64_t timer:4; - uint64_t sum2:1; - uint64_t ipd_drp:1; - uint64_t reserved_49_49:1; - uint64_t gmx_drp:1; - uint64_t trace:1; - uint64_t rml:1; - uint64_t twsi:1; - uint64_t wdog_sum:1; - uint64_t pci_msi:4; - uint64_t pci_int:4; - uint64_t uart:2; - uint64_t mbox:2; - uint64_t gpio:16; - uint64_t workq:16; -#else - uint64_t workq:16; - uint64_t gpio:16; - uint64_t mbox:2; - uint64_t uart:2; - uint64_t pci_int:4; - uint64_t pci_msi:4; - uint64_t wdog_sum:1; - uint64_t twsi:1; - uint64_t rml:1; - uint64_t trace:1; - uint64_t gmx_drp:1; - uint64_t reserved_49_49:1; - uint64_t ipd_drp:1; - uint64_t sum2:1; - uint64_t timer:4; - uint64_t usb:1; - uint64_t pcm:1; - uint64_t mpi:1; - uint64_t twsi2:1; - uint64_t powiq:1; - uint64_t ipdppthr:1; - uint64_t reserved_62_62:1; - uint64_t bootdma:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_int_dbg_sel { - uint64_t u64; - struct cvmx_ciu_int_dbg_sel_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_19_63:45; - uint64_t sel:3; - uint64_t reserved_10_15:6; - uint64_t irq:2; - uint64_t reserved_5_7:3; - uint64_t pp:5; -#else - uint64_t pp:5; - uint64_t reserved_5_7:3; - uint64_t irq:2; - uint64_t reserved_10_15:6; - uint64_t sel:3; - uint64_t reserved_19_63:45; -#endif - } s; - struct cvmx_ciu_int_dbg_sel_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_19_63:45; - uint64_t sel:3; - uint64_t reserved_10_15:6; - uint64_t irq:2; - uint64_t reserved_4_7:4; - uint64_t pp:4; -#else - uint64_t pp:4; - uint64_t reserved_4_7:4; - uint64_t irq:2; - uint64_t reserved_10_15:6; - uint64_t sel:3; - uint64_t reserved_19_63:45; -#endif - } cn61xx; - struct cvmx_ciu_int_dbg_sel_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_19_63:45; - uint64_t sel:3; - uint64_t reserved_10_15:6; - uint64_t irq:2; - uint64_t reserved_3_7:5; - uint64_t pp:3; -#else - uint64_t pp:3; - uint64_t reserved_3_7:5; - uint64_t irq:2; - uint64_t reserved_10_15:6; - uint64_t sel:3; - uint64_t reserved_19_63:45; -#endif - } cn63xx; - struct cvmx_ciu_int_dbg_sel_cn61xx cn66xx; - struct cvmx_ciu_int_dbg_sel_s cn68xx; - struct cvmx_ciu_int_dbg_sel_s cn68xxp1; - struct cvmx_ciu_int_dbg_sel_cn61xx cnf71xx; -}; - -union cvmx_ciu_int_sum1 { - uint64_t u64; - struct cvmx_ciu_int_sum1_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_int_sum1_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t wdog:1; -#else - uint64_t wdog:1; - uint64_t reserved_1_63:63; -#endif - } cn30xx; - struct cvmx_ciu_int_sum1_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t wdog:2; -#else - uint64_t wdog:2; - uint64_t reserved_2_63:62; -#endif - } cn31xx; - struct cvmx_ciu_int_sum1_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t wdog:16; -#else - uint64_t wdog:16; - uint64_t reserved_16_63:48; -#endif - } cn38xx; - struct cvmx_ciu_int_sum1_cn38xx cn38xxp2; - struct cvmx_ciu_int_sum1_cn31xx cn50xx; - struct cvmx_ciu_int_sum1_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_20_63:44; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t reserved_20_63:44; -#endif - } cn52xx; - struct cvmx_ciu_int_sum1_cn52xxp1 { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_19_63:45; - uint64_t mii1:1; - uint64_t usb1:1; - uint64_t uart2:1; - uint64_t reserved_4_15:12; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_15:12; - uint64_t uart2:1; - uint64_t usb1:1; - uint64_t mii1:1; - uint64_t reserved_19_63:45; -#endif - } cn52xxp1; - struct cvmx_ciu_int_sum1_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t wdog:12; -#else - uint64_t wdog:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_int_sum1_cn56xx cn56xxp1; - struct cvmx_ciu_int_sum1_cn38xx cn58xx; - struct cvmx_ciu_int_sum1_cn38xx cn58xxp1; - struct cvmx_ciu_int_sum1_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_int_sum1_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_57_62:6; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t srio1:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_37_45:9; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_6_17:12; - uint64_t wdog:6; -#else - uint64_t wdog:6; - uint64_t reserved_6_17:12; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_45:9; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t srio1:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_62:6; - uint64_t rst:1; -#endif - } cn63xx; - struct cvmx_ciu_int_sum1_cn63xx cn63xxp1; - struct cvmx_ciu_int_sum1_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_int_sum1_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_37_46:10; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_46:10; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_mbox_clrx { - uint64_t u64; - struct cvmx_ciu_mbox_clrx_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t bits:32; -#else - uint64_t bits:32; - uint64_t reserved_32_63:32; -#endif - } s; - struct cvmx_ciu_mbox_clrx_s cn30xx; - struct cvmx_ciu_mbox_clrx_s cn31xx; - struct cvmx_ciu_mbox_clrx_s cn38xx; - struct cvmx_ciu_mbox_clrx_s cn38xxp2; - struct cvmx_ciu_mbox_clrx_s cn50xx; - struct cvmx_ciu_mbox_clrx_s cn52xx; - struct cvmx_ciu_mbox_clrx_s cn52xxp1; - struct cvmx_ciu_mbox_clrx_s cn56xx; - struct cvmx_ciu_mbox_clrx_s cn56xxp1; - struct cvmx_ciu_mbox_clrx_s cn58xx; - struct cvmx_ciu_mbox_clrx_s cn58xxp1; - struct cvmx_ciu_mbox_clrx_s cn61xx; - struct cvmx_ciu_mbox_clrx_s cn63xx; - struct cvmx_ciu_mbox_clrx_s cn63xxp1; - struct cvmx_ciu_mbox_clrx_s cn66xx; - struct cvmx_ciu_mbox_clrx_s cn68xx; - struct cvmx_ciu_mbox_clrx_s cn68xxp1; - struct cvmx_ciu_mbox_clrx_s cnf71xx; -}; - -union cvmx_ciu_mbox_setx { - uint64_t u64; - struct cvmx_ciu_mbox_setx_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t bits:32; -#else - uint64_t bits:32; - uint64_t reserved_32_63:32; -#endif - } s; - struct cvmx_ciu_mbox_setx_s cn30xx; - struct cvmx_ciu_mbox_setx_s cn31xx; - struct cvmx_ciu_mbox_setx_s cn38xx; - struct cvmx_ciu_mbox_setx_s cn38xxp2; - struct cvmx_ciu_mbox_setx_s cn50xx; - struct cvmx_ciu_mbox_setx_s cn52xx; - struct cvmx_ciu_mbox_setx_s cn52xxp1; - struct cvmx_ciu_mbox_setx_s cn56xx; - struct cvmx_ciu_mbox_setx_s cn56xxp1; - struct cvmx_ciu_mbox_setx_s cn58xx; - struct cvmx_ciu_mbox_setx_s cn58xxp1; - struct cvmx_ciu_mbox_setx_s cn61xx; - struct cvmx_ciu_mbox_setx_s cn63xx; - struct cvmx_ciu_mbox_setx_s cn63xxp1; - struct cvmx_ciu_mbox_setx_s cn66xx; - struct cvmx_ciu_mbox_setx_s cn68xx; - struct cvmx_ciu_mbox_setx_s cn68xxp1; - struct cvmx_ciu_mbox_setx_s cnf71xx; -}; - -union cvmx_ciu_nmi { - uint64_t u64; - struct cvmx_ciu_nmi_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t nmi:32; -#else - uint64_t nmi:32; - uint64_t reserved_32_63:32; -#endif - } s; - struct cvmx_ciu_nmi_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t nmi:1; -#else - uint64_t nmi:1; - uint64_t reserved_1_63:63; -#endif - } cn30xx; - struct cvmx_ciu_nmi_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t nmi:2; -#else - uint64_t nmi:2; - uint64_t reserved_2_63:62; -#endif - } cn31xx; - struct cvmx_ciu_nmi_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t nmi:16; -#else - uint64_t nmi:16; - uint64_t reserved_16_63:48; -#endif - } cn38xx; - struct cvmx_ciu_nmi_cn38xx cn38xxp2; - struct cvmx_ciu_nmi_cn31xx cn50xx; - struct cvmx_ciu_nmi_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_4_63:60; - uint64_t nmi:4; -#else - uint64_t nmi:4; - uint64_t reserved_4_63:60; -#endif - } cn52xx; - struct cvmx_ciu_nmi_cn52xx cn52xxp1; - struct cvmx_ciu_nmi_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t nmi:12; -#else - uint64_t nmi:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_nmi_cn56xx cn56xxp1; - struct cvmx_ciu_nmi_cn38xx cn58xx; - struct cvmx_ciu_nmi_cn38xx cn58xxp1; - struct cvmx_ciu_nmi_cn52xx cn61xx; - struct cvmx_ciu_nmi_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_6_63:58; - uint64_t nmi:6; -#else - uint64_t nmi:6; - uint64_t reserved_6_63:58; -#endif - } cn63xx; - struct cvmx_ciu_nmi_cn63xx cn63xxp1; - struct cvmx_ciu_nmi_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t nmi:10; -#else - uint64_t nmi:10; - uint64_t reserved_10_63:54; -#endif - } cn66xx; - struct cvmx_ciu_nmi_s cn68xx; - struct cvmx_ciu_nmi_s cn68xxp1; - struct cvmx_ciu_nmi_cn52xx cnf71xx; -}; - -union cvmx_ciu_pci_inta { - uint64_t u64; - struct cvmx_ciu_pci_inta_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t intr:2; -#else - uint64_t intr:2; - uint64_t reserved_2_63:62; -#endif - } s; - struct cvmx_ciu_pci_inta_s cn30xx; - struct cvmx_ciu_pci_inta_s cn31xx; - struct cvmx_ciu_pci_inta_s cn38xx; - struct cvmx_ciu_pci_inta_s cn38xxp2; - struct cvmx_ciu_pci_inta_s cn50xx; - struct cvmx_ciu_pci_inta_s cn52xx; - struct cvmx_ciu_pci_inta_s cn52xxp1; - struct cvmx_ciu_pci_inta_s cn56xx; - struct cvmx_ciu_pci_inta_s cn56xxp1; - struct cvmx_ciu_pci_inta_s cn58xx; - struct cvmx_ciu_pci_inta_s cn58xxp1; - struct cvmx_ciu_pci_inta_s cn61xx; - struct cvmx_ciu_pci_inta_s cn63xx; - struct cvmx_ciu_pci_inta_s cn63xxp1; - struct cvmx_ciu_pci_inta_s cn66xx; - struct cvmx_ciu_pci_inta_s cn68xx; - struct cvmx_ciu_pci_inta_s cn68xxp1; - struct cvmx_ciu_pci_inta_s cnf71xx; -}; - -union cvmx_ciu_pp_bist_stat { - uint64_t u64; - struct cvmx_ciu_pp_bist_stat_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t pp_bist:32; -#else - uint64_t pp_bist:32; - uint64_t reserved_32_63:32; -#endif - } s; - struct cvmx_ciu_pp_bist_stat_s cn68xx; - struct cvmx_ciu_pp_bist_stat_s cn68xxp1; -}; - -union cvmx_ciu_pp_dbg { - uint64_t u64; - struct cvmx_ciu_pp_dbg_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t ppdbg:32; -#else - uint64_t ppdbg:32; - uint64_t reserved_32_63:32; -#endif - } s; - struct cvmx_ciu_pp_dbg_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t ppdbg:1; -#else - uint64_t ppdbg:1; - uint64_t reserved_1_63:63; -#endif - } cn30xx; - struct cvmx_ciu_pp_dbg_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t ppdbg:2; -#else - uint64_t ppdbg:2; - uint64_t reserved_2_63:62; -#endif - } cn31xx; - struct cvmx_ciu_pp_dbg_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t ppdbg:16; -#else - uint64_t ppdbg:16; - uint64_t reserved_16_63:48; -#endif - } cn38xx; - struct cvmx_ciu_pp_dbg_cn38xx cn38xxp2; - struct cvmx_ciu_pp_dbg_cn31xx cn50xx; - struct cvmx_ciu_pp_dbg_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_4_63:60; - uint64_t ppdbg:4; -#else - uint64_t ppdbg:4; - uint64_t reserved_4_63:60; -#endif - } cn52xx; - struct cvmx_ciu_pp_dbg_cn52xx cn52xxp1; - struct cvmx_ciu_pp_dbg_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t ppdbg:12; -#else - uint64_t ppdbg:12; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_pp_dbg_cn56xx cn56xxp1; - struct cvmx_ciu_pp_dbg_cn38xx cn58xx; - struct cvmx_ciu_pp_dbg_cn38xx cn58xxp1; - struct cvmx_ciu_pp_dbg_cn52xx cn61xx; - struct cvmx_ciu_pp_dbg_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_6_63:58; - uint64_t ppdbg:6; -#else - uint64_t ppdbg:6; - uint64_t reserved_6_63:58; -#endif - } cn63xx; - struct cvmx_ciu_pp_dbg_cn63xx cn63xxp1; - struct cvmx_ciu_pp_dbg_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t ppdbg:10; -#else - uint64_t ppdbg:10; - uint64_t reserved_10_63:54; -#endif - } cn66xx; - struct cvmx_ciu_pp_dbg_s cn68xx; - struct cvmx_ciu_pp_dbg_s cn68xxp1; - struct cvmx_ciu_pp_dbg_cn52xx cnf71xx; -}; - -union cvmx_ciu_pp_pokex { - uint64_t u64; - struct cvmx_ciu_pp_pokex_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t poke:64; -#else - uint64_t poke:64; -#endif - } s; - struct cvmx_ciu_pp_pokex_s cn30xx; - struct cvmx_ciu_pp_pokex_s cn31xx; - struct cvmx_ciu_pp_pokex_s cn38xx; - struct cvmx_ciu_pp_pokex_s cn38xxp2; - struct cvmx_ciu_pp_pokex_s cn50xx; - struct cvmx_ciu_pp_pokex_s cn52xx; - struct cvmx_ciu_pp_pokex_s cn52xxp1; - struct cvmx_ciu_pp_pokex_s cn56xx; - struct cvmx_ciu_pp_pokex_s cn56xxp1; - struct cvmx_ciu_pp_pokex_s cn58xx; - struct cvmx_ciu_pp_pokex_s cn58xxp1; - struct cvmx_ciu_pp_pokex_s cn61xx; - struct cvmx_ciu_pp_pokex_s cn63xx; - struct cvmx_ciu_pp_pokex_s cn63xxp1; - struct cvmx_ciu_pp_pokex_s cn66xx; - struct cvmx_ciu_pp_pokex_s cn68xx; - struct cvmx_ciu_pp_pokex_s cn68xxp1; - struct cvmx_ciu_pp_pokex_s cnf71xx; -}; - -union cvmx_ciu_pp_rst { - uint64_t u64; - struct cvmx_ciu_pp_rst_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t rst:31; - uint64_t rst0:1; -#else - uint64_t rst0:1; - uint64_t rst:31; - uint64_t reserved_32_63:32; -#endif - } s; - struct cvmx_ciu_pp_rst_cn30xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t rst0:1; -#else - uint64_t rst0:1; - uint64_t reserved_1_63:63; -#endif - } cn30xx; - struct cvmx_ciu_pp_rst_cn31xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t rst:1; - uint64_t rst0:1; -#else - uint64_t rst0:1; - uint64_t rst:1; - uint64_t reserved_2_63:62; -#endif - } cn31xx; - struct cvmx_ciu_pp_rst_cn38xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_16_63:48; - uint64_t rst:15; - uint64_t rst0:1; -#else - uint64_t rst0:1; - uint64_t rst:15; - uint64_t reserved_16_63:48; -#endif - } cn38xx; - struct cvmx_ciu_pp_rst_cn38xx cn38xxp2; - struct cvmx_ciu_pp_rst_cn31xx cn50xx; - struct cvmx_ciu_pp_rst_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_4_63:60; - uint64_t rst:3; - uint64_t rst0:1; -#else - uint64_t rst0:1; - uint64_t rst:3; - uint64_t reserved_4_63:60; -#endif - } cn52xx; - struct cvmx_ciu_pp_rst_cn52xx cn52xxp1; - struct cvmx_ciu_pp_rst_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_12_63:52; - uint64_t rst:11; - uint64_t rst0:1; -#else - uint64_t rst0:1; - uint64_t rst:11; - uint64_t reserved_12_63:52; -#endif - } cn56xx; - struct cvmx_ciu_pp_rst_cn56xx cn56xxp1; - struct cvmx_ciu_pp_rst_cn38xx cn58xx; - struct cvmx_ciu_pp_rst_cn38xx cn58xxp1; - struct cvmx_ciu_pp_rst_cn52xx cn61xx; - struct cvmx_ciu_pp_rst_cn63xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_6_63:58; - uint64_t rst:5; - uint64_t rst0:1; -#else - uint64_t rst0:1; - uint64_t rst:5; - uint64_t reserved_6_63:58; -#endif - } cn63xx; - struct cvmx_ciu_pp_rst_cn63xx cn63xxp1; - struct cvmx_ciu_pp_rst_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t rst:9; - uint64_t rst0:1; -#else - uint64_t rst0:1; - uint64_t rst:9; - uint64_t reserved_10_63:54; -#endif - } cn66xx; - struct cvmx_ciu_pp_rst_s cn68xx; - struct cvmx_ciu_pp_rst_s cn68xxp1; - struct cvmx_ciu_pp_rst_cn52xx cnf71xx; -}; - -union cvmx_ciu_qlm0 { - uint64_t u64; - struct cvmx_ciu_qlm0_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t g2bypass:1; - uint64_t reserved_53_62:10; - uint64_t g2deemph:5; - uint64_t reserved_45_47:3; - uint64_t g2margin:5; - uint64_t reserved_32_39:8; - uint64_t txbypass:1; - uint64_t reserved_21_30:10; - uint64_t txdeemph:5; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:5; - uint64_t reserved_21_30:10; - uint64_t txbypass:1; - uint64_t reserved_32_39:8; - uint64_t g2margin:5; - uint64_t reserved_45_47:3; - uint64_t g2deemph:5; - uint64_t reserved_53_62:10; - uint64_t g2bypass:1; -#endif - } s; - struct cvmx_ciu_qlm0_s cn61xx; - struct cvmx_ciu_qlm0_s cn63xx; - struct cvmx_ciu_qlm0_cn63xxp1 { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t txbypass:1; - uint64_t reserved_20_30:11; - uint64_t txdeemph:4; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:4; - uint64_t reserved_20_30:11; - uint64_t txbypass:1; - uint64_t reserved_32_63:32; -#endif - } cn63xxp1; - struct cvmx_ciu_qlm0_s cn66xx; - struct cvmx_ciu_qlm0_cn68xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t txbypass:1; - uint64_t reserved_21_30:10; - uint64_t txdeemph:5; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:5; - uint64_t reserved_21_30:10; - uint64_t txbypass:1; - uint64_t reserved_32_63:32; -#endif - } cn68xx; - struct cvmx_ciu_qlm0_cn68xx cn68xxp1; - struct cvmx_ciu_qlm0_s cnf71xx; -}; - -union cvmx_ciu_qlm1 { - uint64_t u64; - struct cvmx_ciu_qlm1_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t g2bypass:1; - uint64_t reserved_53_62:10; - uint64_t g2deemph:5; - uint64_t reserved_45_47:3; - uint64_t g2margin:5; - uint64_t reserved_32_39:8; - uint64_t txbypass:1; - uint64_t reserved_21_30:10; - uint64_t txdeemph:5; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:5; - uint64_t reserved_21_30:10; - uint64_t txbypass:1; - uint64_t reserved_32_39:8; - uint64_t g2margin:5; - uint64_t reserved_45_47:3; - uint64_t g2deemph:5; - uint64_t reserved_53_62:10; - uint64_t g2bypass:1; -#endif - } s; - struct cvmx_ciu_qlm1_s cn61xx; - struct cvmx_ciu_qlm1_s cn63xx; - struct cvmx_ciu_qlm1_cn63xxp1 { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t txbypass:1; - uint64_t reserved_20_30:11; - uint64_t txdeemph:4; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:4; - uint64_t reserved_20_30:11; - uint64_t txbypass:1; - uint64_t reserved_32_63:32; -#endif - } cn63xxp1; - struct cvmx_ciu_qlm1_s cn66xx; - struct cvmx_ciu_qlm1_s cn68xx; - struct cvmx_ciu_qlm1_s cn68xxp1; - struct cvmx_ciu_qlm1_s cnf71xx; -}; - -union cvmx_ciu_qlm2 { - uint64_t u64; - struct cvmx_ciu_qlm2_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t g2bypass:1; - uint64_t reserved_53_62:10; - uint64_t g2deemph:5; - uint64_t reserved_45_47:3; - uint64_t g2margin:5; - uint64_t reserved_32_39:8; - uint64_t txbypass:1; - uint64_t reserved_21_30:10; - uint64_t txdeemph:5; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:5; - uint64_t reserved_21_30:10; - uint64_t txbypass:1; - uint64_t reserved_32_39:8; - uint64_t g2margin:5; - uint64_t reserved_45_47:3; - uint64_t g2deemph:5; - uint64_t reserved_53_62:10; - uint64_t g2bypass:1; -#endif - } s; - struct cvmx_ciu_qlm2_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t txbypass:1; - uint64_t reserved_21_30:10; - uint64_t txdeemph:5; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:5; - uint64_t reserved_21_30:10; - uint64_t txbypass:1; - uint64_t reserved_32_63:32; -#endif - } cn61xx; - struct cvmx_ciu_qlm2_cn61xx cn63xx; - struct cvmx_ciu_qlm2_cn63xxp1 { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_32_63:32; - uint64_t txbypass:1; - uint64_t reserved_20_30:11; - uint64_t txdeemph:4; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:4; - uint64_t reserved_20_30:11; - uint64_t txbypass:1; - uint64_t reserved_32_63:32; -#endif - } cn63xxp1; - struct cvmx_ciu_qlm2_cn61xx cn66xx; - struct cvmx_ciu_qlm2_s cn68xx; - struct cvmx_ciu_qlm2_s cn68xxp1; - struct cvmx_ciu_qlm2_cn61xx cnf71xx; -}; -union cvmx_ciu_qlm3 { +union cvmx_ciu_qlm { uint64_t u64; - struct cvmx_ciu_qlm3_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t g2bypass:1; - uint64_t reserved_53_62:10; - uint64_t g2deemph:5; - uint64_t reserved_45_47:3; - uint64_t g2margin:5; - uint64_t reserved_32_39:8; - uint64_t txbypass:1; - uint64_t reserved_21_30:10; - uint64_t txdeemph:5; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:5; - uint64_t reserved_21_30:10; - uint64_t txbypass:1; - uint64_t reserved_32_39:8; - uint64_t g2margin:5; - uint64_t reserved_45_47:3; - uint64_t g2deemph:5; - uint64_t reserved_53_62:10; - uint64_t g2bypass:1; -#endif + struct cvmx_ciu_qlm_s { + __BITFIELD_FIELD(uint64_t g2bypass:1, + __BITFIELD_FIELD(uint64_t reserved_53_62:10, + __BITFIELD_FIELD(uint64_t g2deemph:5, + __BITFIELD_FIELD(uint64_t reserved_45_47:3, + __BITFIELD_FIELD(uint64_t g2margin:5, + __BITFIELD_FIELD(uint64_t reserved_32_39:8, + __BITFIELD_FIELD(uint64_t txbypass:1, + __BITFIELD_FIELD(uint64_t reserved_21_30:10, + __BITFIELD_FIELD(uint64_t txdeemph:5, + __BITFIELD_FIELD(uint64_t reserved_13_15:3, + __BITFIELD_FIELD(uint64_t txmargin:5, + __BITFIELD_FIELD(uint64_t reserved_4_7:4, + __BITFIELD_FIELD(uint64_t lane_en:4, + ;))))))))))))) } s; - struct cvmx_ciu_qlm3_s cn68xx; - struct cvmx_ciu_qlm3_s cn68xxp1; -}; - -union cvmx_ciu_qlm4 { - uint64_t u64; - struct cvmx_ciu_qlm4_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t g2bypass:1; - uint64_t reserved_53_62:10; - uint64_t g2deemph:5; - uint64_t reserved_45_47:3; - uint64_t g2margin:5; - uint64_t reserved_32_39:8; - uint64_t txbypass:1; - uint64_t reserved_21_30:10; - uint64_t txdeemph:5; - uint64_t reserved_13_15:3; - uint64_t txmargin:5; - uint64_t reserved_4_7:4; - uint64_t lane_en:4; -#else - uint64_t lane_en:4; - uint64_t reserved_4_7:4; - uint64_t txmargin:5; - uint64_t reserved_13_15:3; - uint64_t txdeemph:5; - uint64_t reserved_21_30:10; - uint64_t txbypass:1; - uint64_t reserved_32_39:8; - uint64_t g2margin:5; - uint64_t reserved_45_47:3; - uint64_t g2deemph:5; - uint64_t reserved_53_62:10; - uint64_t g2bypass:1; -#endif - } s; - struct cvmx_ciu_qlm4_s cn68xx; - struct cvmx_ciu_qlm4_s cn68xxp1; -}; - -union cvmx_ciu_qlm_dcok { - uint64_t u64; - struct cvmx_ciu_qlm_dcok_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_4_63:60; - uint64_t qlm_dcok:4; -#else - uint64_t qlm_dcok:4; - uint64_t reserved_4_63:60; -#endif - } s; - struct cvmx_ciu_qlm_dcok_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_2_63:62; - uint64_t qlm_dcok:2; -#else - uint64_t qlm_dcok:2; - uint64_t reserved_2_63:62; -#endif - } cn52xx; - struct cvmx_ciu_qlm_dcok_cn52xx cn52xxp1; - struct cvmx_ciu_qlm_dcok_s cn56xx; - struct cvmx_ciu_qlm_dcok_s cn56xxp1; }; union cvmx_ciu_qlm_jtgc { uint64_t u64; struct cvmx_ciu_qlm_jtgc_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_17_63:47; - uint64_t bypass_ext:1; - uint64_t reserved_11_15:5; - uint64_t clk_div:3; - uint64_t reserved_7_7:1; - uint64_t mux_sel:3; - uint64_t bypass:4; -#else - uint64_t bypass:4; - uint64_t mux_sel:3; - uint64_t reserved_7_7:1; - uint64_t clk_div:3; - uint64_t reserved_11_15:5; - uint64_t bypass_ext:1; - uint64_t reserved_17_63:47; -#endif + __BITFIELD_FIELD(uint64_t reserved_17_63:47, + __BITFIELD_FIELD(uint64_t bypass_ext:1, + __BITFIELD_FIELD(uint64_t reserved_11_15:5, + __BITFIELD_FIELD(uint64_t clk_div:3, + __BITFIELD_FIELD(uint64_t reserved_7_7:1, + __BITFIELD_FIELD(uint64_t mux_sel:3, + __BITFIELD_FIELD(uint64_t bypass:4, + ;))))))) } s; - struct cvmx_ciu_qlm_jtgc_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_11_63:53; - uint64_t clk_div:3; - uint64_t reserved_5_7:3; - uint64_t mux_sel:1; - uint64_t reserved_2_3:2; - uint64_t bypass:2; -#else - uint64_t bypass:2; - uint64_t reserved_2_3:2; - uint64_t mux_sel:1; - uint64_t reserved_5_7:3; - uint64_t clk_div:3; - uint64_t reserved_11_63:53; -#endif - } cn52xx; - struct cvmx_ciu_qlm_jtgc_cn52xx cn52xxp1; - struct cvmx_ciu_qlm_jtgc_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_11_63:53; - uint64_t clk_div:3; - uint64_t reserved_6_7:2; - uint64_t mux_sel:2; - uint64_t bypass:4; -#else - uint64_t bypass:4; - uint64_t mux_sel:2; - uint64_t reserved_6_7:2; - uint64_t clk_div:3; - uint64_t reserved_11_63:53; -#endif - } cn56xx; - struct cvmx_ciu_qlm_jtgc_cn56xx cn56xxp1; - struct cvmx_ciu_qlm_jtgc_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_11_63:53; - uint64_t clk_div:3; - uint64_t reserved_6_7:2; - uint64_t mux_sel:2; - uint64_t reserved_3_3:1; - uint64_t bypass:3; -#else - uint64_t bypass:3; - uint64_t reserved_3_3:1; - uint64_t mux_sel:2; - uint64_t reserved_6_7:2; - uint64_t clk_div:3; - uint64_t reserved_11_63:53; -#endif - } cn61xx; - struct cvmx_ciu_qlm_jtgc_cn61xx cn63xx; - struct cvmx_ciu_qlm_jtgc_cn61xx cn63xxp1; - struct cvmx_ciu_qlm_jtgc_cn61xx cn66xx; - struct cvmx_ciu_qlm_jtgc_s cn68xx; - struct cvmx_ciu_qlm_jtgc_s cn68xxp1; - struct cvmx_ciu_qlm_jtgc_cn61xx cnf71xx; }; union cvmx_ciu_qlm_jtgd { uint64_t u64; struct cvmx_ciu_qlm_jtgd_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t capture:1; - uint64_t shift:1; - uint64_t update:1; - uint64_t reserved_45_60:16; - uint64_t select:5; - uint64_t reserved_37_39:3; - uint64_t shft_cnt:5; - uint64_t shft_reg:32; -#else - uint64_t shft_reg:32; - uint64_t shft_cnt:5; - uint64_t reserved_37_39:3; - uint64_t select:5; - uint64_t reserved_45_60:16; - uint64_t update:1; - uint64_t shift:1; - uint64_t capture:1; -#endif - } s; - struct cvmx_ciu_qlm_jtgd_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t capture:1; - uint64_t shift:1; - uint64_t update:1; - uint64_t reserved_42_60:19; - uint64_t select:2; - uint64_t reserved_37_39:3; - uint64_t shft_cnt:5; - uint64_t shft_reg:32; -#else - uint64_t shft_reg:32; - uint64_t shft_cnt:5; - uint64_t reserved_37_39:3; - uint64_t select:2; - uint64_t reserved_42_60:19; - uint64_t update:1; - uint64_t shift:1; - uint64_t capture:1; -#endif - } cn52xx; - struct cvmx_ciu_qlm_jtgd_cn52xx cn52xxp1; - struct cvmx_ciu_qlm_jtgd_cn56xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t capture:1; - uint64_t shift:1; - uint64_t update:1; - uint64_t reserved_44_60:17; - uint64_t select:4; - uint64_t reserved_37_39:3; - uint64_t shft_cnt:5; - uint64_t shft_reg:32; -#else - uint64_t shft_reg:32; - uint64_t shft_cnt:5; - uint64_t reserved_37_39:3; - uint64_t select:4; - uint64_t reserved_44_60:17; - uint64_t update:1; - uint64_t shift:1; - uint64_t capture:1; -#endif - } cn56xx; - struct cvmx_ciu_qlm_jtgd_cn56xxp1 { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t capture:1; - uint64_t shift:1; - uint64_t update:1; - uint64_t reserved_37_60:24; - uint64_t shft_cnt:5; - uint64_t shft_reg:32; -#else - uint64_t shft_reg:32; - uint64_t shft_cnt:5; - uint64_t reserved_37_60:24; - uint64_t update:1; - uint64_t shift:1; - uint64_t capture:1; -#endif - } cn56xxp1; - struct cvmx_ciu_qlm_jtgd_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t capture:1; - uint64_t shift:1; - uint64_t update:1; - uint64_t reserved_43_60:18; - uint64_t select:3; - uint64_t reserved_37_39:3; - uint64_t shft_cnt:5; - uint64_t shft_reg:32; -#else - uint64_t shft_reg:32; - uint64_t shft_cnt:5; - uint64_t reserved_37_39:3; - uint64_t select:3; - uint64_t reserved_43_60:18; - uint64_t update:1; - uint64_t shift:1; - uint64_t capture:1; -#endif - } cn61xx; - struct cvmx_ciu_qlm_jtgd_cn61xx cn63xx; - struct cvmx_ciu_qlm_jtgd_cn61xx cn63xxp1; - struct cvmx_ciu_qlm_jtgd_cn61xx cn66xx; - struct cvmx_ciu_qlm_jtgd_s cn68xx; - struct cvmx_ciu_qlm_jtgd_s cn68xxp1; - struct cvmx_ciu_qlm_jtgd_cn61xx cnf71xx; -}; - -union cvmx_ciu_soft_bist { - uint64_t u64; - struct cvmx_ciu_soft_bist_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t soft_bist:1; -#else - uint64_t soft_bist:1; - uint64_t reserved_1_63:63; -#endif + __BITFIELD_FIELD(uint64_t capture:1, + __BITFIELD_FIELD(uint64_t shift:1, + __BITFIELD_FIELD(uint64_t update:1, + __BITFIELD_FIELD(uint64_t reserved_45_60:16, + __BITFIELD_FIELD(uint64_t select:5, + __BITFIELD_FIELD(uint64_t reserved_37_39:3, + __BITFIELD_FIELD(uint64_t shft_cnt:5, + __BITFIELD_FIELD(uint64_t shft_reg:32, + ;)))))))) } s; - struct cvmx_ciu_soft_bist_s cn30xx; - struct cvmx_ciu_soft_bist_s cn31xx; - struct cvmx_ciu_soft_bist_s cn38xx; - struct cvmx_ciu_soft_bist_s cn38xxp2; - struct cvmx_ciu_soft_bist_s cn50xx; - struct cvmx_ciu_soft_bist_s cn52xx; - struct cvmx_ciu_soft_bist_s cn52xxp1; - struct cvmx_ciu_soft_bist_s cn56xx; - struct cvmx_ciu_soft_bist_s cn56xxp1; - struct cvmx_ciu_soft_bist_s cn58xx; - struct cvmx_ciu_soft_bist_s cn58xxp1; - struct cvmx_ciu_soft_bist_s cn61xx; - struct cvmx_ciu_soft_bist_s cn63xx; - struct cvmx_ciu_soft_bist_s cn63xxp1; - struct cvmx_ciu_soft_bist_s cn66xx; - struct cvmx_ciu_soft_bist_s cn68xx; - struct cvmx_ciu_soft_bist_s cn68xxp1; - struct cvmx_ciu_soft_bist_s cnf71xx; }; union cvmx_ciu_soft_prst { uint64_t u64; struct cvmx_ciu_soft_prst_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_3_63:61; - uint64_t host64:1; - uint64_t npi:1; - uint64_t soft_prst:1; -#else - uint64_t soft_prst:1; - uint64_t npi:1; - uint64_t host64:1; - uint64_t reserved_3_63:61; -#endif - } s; - struct cvmx_ciu_soft_prst_s cn30xx; - struct cvmx_ciu_soft_prst_s cn31xx; - struct cvmx_ciu_soft_prst_s cn38xx; - struct cvmx_ciu_soft_prst_s cn38xxp2; - struct cvmx_ciu_soft_prst_s cn50xx; - struct cvmx_ciu_soft_prst_cn52xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t soft_prst:1; -#else - uint64_t soft_prst:1; - uint64_t reserved_1_63:63; -#endif - } cn52xx; - struct cvmx_ciu_soft_prst_cn52xx cn52xxp1; - struct cvmx_ciu_soft_prst_cn52xx cn56xx; - struct cvmx_ciu_soft_prst_cn52xx cn56xxp1; - struct cvmx_ciu_soft_prst_s cn58xx; - struct cvmx_ciu_soft_prst_s cn58xxp1; - struct cvmx_ciu_soft_prst_cn52xx cn61xx; - struct cvmx_ciu_soft_prst_cn52xx cn63xx; - struct cvmx_ciu_soft_prst_cn52xx cn63xxp1; - struct cvmx_ciu_soft_prst_cn52xx cn66xx; - struct cvmx_ciu_soft_prst_cn52xx cn68xx; - struct cvmx_ciu_soft_prst_cn52xx cn68xxp1; - struct cvmx_ciu_soft_prst_cn52xx cnf71xx; -}; - -union cvmx_ciu_soft_prst1 { - uint64_t u64; - struct cvmx_ciu_soft_prst1_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t soft_prst:1; -#else - uint64_t soft_prst:1; - uint64_t reserved_1_63:63; -#endif - } s; - struct cvmx_ciu_soft_prst1_s cn52xx; - struct cvmx_ciu_soft_prst1_s cn52xxp1; - struct cvmx_ciu_soft_prst1_s cn56xx; - struct cvmx_ciu_soft_prst1_s cn56xxp1; - struct cvmx_ciu_soft_prst1_s cn61xx; - struct cvmx_ciu_soft_prst1_s cn63xx; - struct cvmx_ciu_soft_prst1_s cn63xxp1; - struct cvmx_ciu_soft_prst1_s cn66xx; - struct cvmx_ciu_soft_prst1_s cn68xx; - struct cvmx_ciu_soft_prst1_s cn68xxp1; - struct cvmx_ciu_soft_prst1_s cnf71xx; -}; - -union cvmx_ciu_soft_prst2 { - uint64_t u64; - struct cvmx_ciu_soft_prst2_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t soft_prst:1; -#else - uint64_t soft_prst:1; - uint64_t reserved_1_63:63; -#endif - } s; - struct cvmx_ciu_soft_prst2_s cn66xx; -}; - -union cvmx_ciu_soft_prst3 { - uint64_t u64; - struct cvmx_ciu_soft_prst3_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t soft_prst:1; -#else - uint64_t soft_prst:1; - uint64_t reserved_1_63:63; -#endif - } s; - struct cvmx_ciu_soft_prst3_s cn66xx; -}; - -union cvmx_ciu_soft_rst { - uint64_t u64; - struct cvmx_ciu_soft_rst_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t soft_rst:1; -#else - uint64_t soft_rst:1; - uint64_t reserved_1_63:63; -#endif - } s; - struct cvmx_ciu_soft_rst_s cn30xx; - struct cvmx_ciu_soft_rst_s cn31xx; - struct cvmx_ciu_soft_rst_s cn38xx; - struct cvmx_ciu_soft_rst_s cn38xxp2; - struct cvmx_ciu_soft_rst_s cn50xx; - struct cvmx_ciu_soft_rst_s cn52xx; - struct cvmx_ciu_soft_rst_s cn52xxp1; - struct cvmx_ciu_soft_rst_s cn56xx; - struct cvmx_ciu_soft_rst_s cn56xxp1; - struct cvmx_ciu_soft_rst_s cn58xx; - struct cvmx_ciu_soft_rst_s cn58xxp1; - struct cvmx_ciu_soft_rst_s cn61xx; - struct cvmx_ciu_soft_rst_s cn63xx; - struct cvmx_ciu_soft_rst_s cn63xxp1; - struct cvmx_ciu_soft_rst_s cn66xx; - struct cvmx_ciu_soft_rst_s cn68xx; - struct cvmx_ciu_soft_rst_s cn68xxp1; - struct cvmx_ciu_soft_rst_s cnf71xx; -}; - -union cvmx_ciu_sum1_iox_int { - uint64_t u64; - struct cvmx_ciu_sum1_iox_int_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif + __BITFIELD_FIELD(uint64_t reserved_3_63:61, + __BITFIELD_FIELD(uint64_t host64:1, + __BITFIELD_FIELD(uint64_t npi:1, + __BITFIELD_FIELD(uint64_t soft_prst:1, + ;)))) } s; - struct cvmx_ciu_sum1_iox_int_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_sum1_iox_int_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_sum1_iox_int_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_sum1_ppx_ip2 { - uint64_t u64; - struct cvmx_ciu_sum1_ppx_ip2_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_sum1_ppx_ip2_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_sum1_ppx_ip2_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_sum1_ppx_ip2_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_sum1_ppx_ip3 { - uint64_t u64; - struct cvmx_ciu_sum1_ppx_ip3_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_sum1_ppx_ip3_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_sum1_ppx_ip3_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_sum1_ppx_ip3_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_sum1_ppx_ip4 { - uint64_t u64; - struct cvmx_ciu_sum1_ppx_ip4_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } s; - struct cvmx_ciu_sum1_ppx_ip4_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_41_45:5; - uint64_t dpi_dma:1; - uint64_t reserved_38_39:2; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_4_17:14; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_17:14; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_39:2; - uint64_t dpi_dma:1; - uint64_t reserved_41_45:5; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cn61xx; - struct cvmx_ciu_sum1_ppx_ip4_cn66xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_62_62:1; - uint64_t srio3:1; - uint64_t srio2:1; - uint64_t reserved_57_59:3; - uint64_t dfm:1; - uint64_t reserved_53_55:3; - uint64_t lmc0:1; - uint64_t reserved_51_51:1; - uint64_t srio0:1; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t agl:1; - uint64_t reserved_38_45:8; - uint64_t agx1:1; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t dfa:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t zip:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t mii1:1; - uint64_t reserved_10_17:8; - uint64_t wdog:10; -#else - uint64_t wdog:10; - uint64_t reserved_10_17:8; - uint64_t mii1:1; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t zip:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t dfa:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t agx1:1; - uint64_t reserved_38_45:8; - uint64_t agl:1; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t srio0:1; - uint64_t reserved_51_51:1; - uint64_t lmc0:1; - uint64_t reserved_53_55:3; - uint64_t dfm:1; - uint64_t reserved_57_59:3; - uint64_t srio2:1; - uint64_t srio3:1; - uint64_t reserved_62_62:1; - uint64_t rst:1; -#endif - } cn66xx; - struct cvmx_ciu_sum1_ppx_ip4_cnf71xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t rst:1; - uint64_t reserved_53_62:10; - uint64_t lmc0:1; - uint64_t reserved_50_51:2; - uint64_t pem1:1; - uint64_t pem0:1; - uint64_t ptp:1; - uint64_t reserved_41_46:6; - uint64_t dpi_dma:1; - uint64_t reserved_37_39:3; - uint64_t agx0:1; - uint64_t dpi:1; - uint64_t sli:1; - uint64_t usb:1; - uint64_t reserved_32_32:1; - uint64_t key:1; - uint64_t rad:1; - uint64_t tim:1; - uint64_t reserved_28_28:1; - uint64_t pko:1; - uint64_t pip:1; - uint64_t ipd:1; - uint64_t l2c:1; - uint64_t pow:1; - uint64_t fpa:1; - uint64_t iob:1; - uint64_t mio:1; - uint64_t nand:1; - uint64_t reserved_4_18:15; - uint64_t wdog:4; -#else - uint64_t wdog:4; - uint64_t reserved_4_18:15; - uint64_t nand:1; - uint64_t mio:1; - uint64_t iob:1; - uint64_t fpa:1; - uint64_t pow:1; - uint64_t l2c:1; - uint64_t ipd:1; - uint64_t pip:1; - uint64_t pko:1; - uint64_t reserved_28_28:1; - uint64_t tim:1; - uint64_t rad:1; - uint64_t key:1; - uint64_t reserved_32_32:1; - uint64_t usb:1; - uint64_t sli:1; - uint64_t dpi:1; - uint64_t agx0:1; - uint64_t reserved_37_39:3; - uint64_t dpi_dma:1; - uint64_t reserved_41_46:6; - uint64_t ptp:1; - uint64_t pem0:1; - uint64_t pem1:1; - uint64_t reserved_50_51:2; - uint64_t lmc0:1; - uint64_t reserved_53_62:10; - uint64_t rst:1; -#endif - } cnf71xx; -}; - -union cvmx_ciu_sum2_iox_int { - uint64_t u64; - struct cvmx_ciu_sum2_iox_int_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_sum2_iox_int_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_sum2_iox_int_cn61xx cn66xx; - struct cvmx_ciu_sum2_iox_int_s cnf71xx; -}; - -union cvmx_ciu_sum2_ppx_ip2 { - uint64_t u64; - struct cvmx_ciu_sum2_ppx_ip2_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_sum2_ppx_ip2_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_sum2_ppx_ip2_cn61xx cn66xx; - struct cvmx_ciu_sum2_ppx_ip2_s cnf71xx; -}; - -union cvmx_ciu_sum2_ppx_ip3 { - uint64_t u64; - struct cvmx_ciu_sum2_ppx_ip3_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_sum2_ppx_ip3_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_sum2_ppx_ip3_cn61xx cn66xx; - struct cvmx_ciu_sum2_ppx_ip3_s cnf71xx; -}; - -union cvmx_ciu_sum2_ppx_ip4 { - uint64_t u64; - struct cvmx_ciu_sum2_ppx_ip4_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_15_63:49; - uint64_t endor:2; - uint64_t eoi:1; - uint64_t reserved_10_11:2; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_11:2; - uint64_t eoi:1; - uint64_t endor:2; - uint64_t reserved_15_63:49; -#endif - } s; - struct cvmx_ciu_sum2_ppx_ip4_cn61xx { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_10_63:54; - uint64_t timer:6; - uint64_t reserved_0_3:4; -#else - uint64_t reserved_0_3:4; - uint64_t timer:6; - uint64_t reserved_10_63:54; -#endif - } cn61xx; - struct cvmx_ciu_sum2_ppx_ip4_cn61xx cn66xx; - struct cvmx_ciu_sum2_ppx_ip4_s cnf71xx; }; union cvmx_ciu_timx { uint64_t u64; struct cvmx_ciu_timx_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_37_63:27; - uint64_t one_shot:1; - uint64_t len:36; -#else - uint64_t len:36; - uint64_t one_shot:1; - uint64_t reserved_37_63:27; -#endif - } s; - struct cvmx_ciu_timx_s cn30xx; - struct cvmx_ciu_timx_s cn31xx; - struct cvmx_ciu_timx_s cn38xx; - struct cvmx_ciu_timx_s cn38xxp2; - struct cvmx_ciu_timx_s cn50xx; - struct cvmx_ciu_timx_s cn52xx; - struct cvmx_ciu_timx_s cn52xxp1; - struct cvmx_ciu_timx_s cn56xx; - struct cvmx_ciu_timx_s cn56xxp1; - struct cvmx_ciu_timx_s cn58xx; - struct cvmx_ciu_timx_s cn58xxp1; - struct cvmx_ciu_timx_s cn61xx; - struct cvmx_ciu_timx_s cn63xx; - struct cvmx_ciu_timx_s cn63xxp1; - struct cvmx_ciu_timx_s cn66xx; - struct cvmx_ciu_timx_s cn68xx; - struct cvmx_ciu_timx_s cn68xxp1; - struct cvmx_ciu_timx_s cnf71xx; -}; - -union cvmx_ciu_tim_multi_cast { - uint64_t u64; - struct cvmx_ciu_tim_multi_cast_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_1_63:63; - uint64_t en:1; -#else - uint64_t en:1; - uint64_t reserved_1_63:63; -#endif + __BITFIELD_FIELD(uint64_t reserved_37_63:27, + __BITFIELD_FIELD(uint64_t one_shot:1, + __BITFIELD_FIELD(uint64_t len:36, + ;))) } s; - struct cvmx_ciu_tim_multi_cast_s cn61xx; - struct cvmx_ciu_tim_multi_cast_s cn66xx; - struct cvmx_ciu_tim_multi_cast_s cnf71xx; }; union cvmx_ciu_wdogx { uint64_t u64; struct cvmx_ciu_wdogx_s { -#ifdef __BIG_ENDIAN_BITFIELD - uint64_t reserved_46_63:18; - uint64_t gstopen:1; - uint64_t dstop:1; - uint64_t cnt:24; - uint64_t len:16; - uint64_t state:2; - uint64_t mode:2; -#else - uint64_t mode:2; - uint64_t state:2; - uint64_t len:16; - uint64_t cnt:24; - uint64_t dstop:1; - uint64_t gstopen:1; - uint64_t reserved_46_63:18; -#endif + __BITFIELD_FIELD(uint64_t reserved_46_63:18, + __BITFIELD_FIELD(uint64_t gstopen:1, + __BITFIELD_FIELD(uint64_t dstop:1, + __BITFIELD_FIELD(uint64_t cnt:24, + __BITFIELD_FIELD(uint64_t len:16, + __BITFIELD_FIELD(uint64_t state:2, + __BITFIELD_FIELD(uint64_t mode:2, + ;))))))) } s; - struct cvmx_ciu_wdogx_s cn30xx; - struct cvmx_ciu_wdogx_s cn31xx; - struct cvmx_ciu_wdogx_s cn38xx; - struct cvmx_ciu_wdogx_s cn38xxp2; - struct cvmx_ciu_wdogx_s cn50xx; - struct cvmx_ciu_wdogx_s cn52xx; - struct cvmx_ciu_wdogx_s cn52xxp1; - struct cvmx_ciu_wdogx_s cn56xx; - struct cvmx_ciu_wdogx_s cn56xxp1; - struct cvmx_ciu_wdogx_s cn58xx; - struct cvmx_ciu_wdogx_s cn58xxp1; - struct cvmx_ciu_wdogx_s cn61xx; - struct cvmx_ciu_wdogx_s cn63xx; - struct cvmx_ciu_wdogx_s cn63xxp1; - struct cvmx_ciu_wdogx_s cn66xx; - struct cvmx_ciu_wdogx_s cn68xx; - struct cvmx_ciu_wdogx_s cn68xxp1; - struct cvmx_ciu_wdogx_s cnf71xx; }; -#endif +#endif /* __CVMX_CIU_DEFS_H__ */ diff --git a/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h b/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h index e347496a33c3..80e4f8358b81 100644 --- a/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h +++ b/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2012 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -2070,6 +2070,8 @@ static inline uint64_t CVMX_GMXX_XAUI_EXT_LOOPBACK(unsigned long block_id) return CVMX_ADD_IO_SEG(0x0001180008000540ull) + (block_id) * 0x8000000ull; } +void __cvmx_interrupt_gmxx_enable(int interface); + union cvmx_gmxx_bad_reg { uint64_t u64; struct cvmx_gmxx_bad_reg_s { diff --git a/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h b/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h index a5e8fd861c37..39da7f9d7b3f 100644 --- a/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h +++ b/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2012 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -334,6 +334,8 @@ static inline uint64_t CVMX_PCSX_TX_RXX_POLARITY_REG(unsigned long offset, unsig return CVMX_ADD_IO_SEG(0x00011800B0001048ull) + ((offset) + (block_id) * 0x20000ull) * 1024; } +void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block); + union cvmx_pcsx_anx_adv_reg { uint64_t u64; struct cvmx_pcsx_anx_adv_reg_s { diff --git a/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h b/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h index b5b45d26f1c5..847dd9dca6ea 100644 --- a/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h +++ b/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2012 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -268,6 +268,8 @@ static inline uint64_t CVMX_PCSXX_TX_RX_STATES_REG(unsigned long block_id) return CVMX_ADD_IO_SEG(0x00011800B0000830ull) + (block_id) * 0x1000000ull; } +void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index); + union cvmx_pcsxx_10gbx_status_reg { uint64_t u64; struct cvmx_pcsxx_10gbx_status_reg_s { diff --git a/arch/mips/include/asm/octeon/cvmx-spxx-defs.h b/arch/mips/include/asm/octeon/cvmx-spxx-defs.h index c7d601d9446e..f4c4e8051160 100644 --- a/arch/mips/include/asm/octeon/cvmx-spxx-defs.h +++ b/arch/mips/include/asm/octeon/cvmx-spxx-defs.h @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2012 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -45,6 +45,8 @@ #define CVMX_SPXX_TPA_SEL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000328ull) + ((block_id) & 1) * 0x8000000ull) #define CVMX_SPXX_TRN4_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000360ull) + ((block_id) & 1) * 0x8000000ull) +void __cvmx_interrupt_spxx_int_msk_enable(int index); + union cvmx_spxx_bckprs_cnt { uint64_t u64; struct cvmx_spxx_bckprs_cnt_s { diff --git a/arch/mips/include/asm/octeon/cvmx-stxx-defs.h b/arch/mips/include/asm/octeon/cvmx-stxx-defs.h index 146354005d3b..3c409a854d91 100644 --- a/arch/mips/include/asm/octeon/cvmx-stxx-defs.h +++ b/arch/mips/include/asm/octeon/cvmx-stxx-defs.h @@ -4,7 +4,7 @@ * Contact: support@caviumnetworks.com * This file is part of the OCTEON SDK * - * Copyright (c) 2003-2012 Cavium Networks + * Copyright (C) 2003-2018 Cavium, Inc. * * This file is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, Version 2, as @@ -45,6 +45,8 @@ #define CVMX_STXX_STAT_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000638ull) + ((block_id) & 1) * 0x8000000ull) #define CVMX_STXX_STAT_PKT_XMT(block_id) (CVMX_ADD_IO_SEG(0x0001180090000640ull) + ((block_id) & 1) * 0x8000000ull) +void __cvmx_interrupt_stxx_int_msk_enable(int index); + union cvmx_stxx_arb_ctl { uint64_t u64; struct cvmx_stxx_arb_ctl_s { diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h index c99c4b6a79f4..60481502826a 100644 --- a/arch/mips/include/asm/octeon/octeon.h +++ b/arch/mips/include/asm/octeon/octeon.h @@ -279,13 +279,12 @@ union octeon_cvmemctl { } s; }; -extern void octeon_write_lcd(const char *s); extern void octeon_check_cpu_bist(void); -extern int octeon_get_boot_uart(void); -struct uart_port; -extern unsigned int octeon_serial_in(struct uart_port *, int); -extern void octeon_serial_out(struct uart_port *, int, int); +int octeon_prune_device_tree(void); +extern const char __appended_dtb; +extern const char __dtb_octeon_3xxx_begin; +extern const char __dtb_octeon_68xx_begin; /** * Write a 32bit value to the Octeon NPI register space diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h index 1884609741a8..b12d9a3fbfb6 100644 --- a/arch/mips/include/asm/octeon/pci-octeon.h +++ b/arch/mips/include/asm/octeon/pci-octeon.h @@ -63,4 +63,7 @@ enum octeon_dma_bar_type { */ extern enum octeon_dma_bar_type octeon_dma_bar_type; +void octeon_pci_dma_init(void); +extern char *octeon_swiotlb; + #endif diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index ad461216b5a1..e8cc328fce2d 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -80,7 +80,12 @@ extern void build_copy_page(void); * used in our early mem init code for all memory models. * So always define it. */ -#define ARCH_PFN_OFFSET PFN_UP(PHYS_OFFSET) +#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET +extern unsigned long ARCH_PFN_OFFSET; +# define ARCH_PFN_OFFSET ARCH_PFN_OFFSET +#else +# define ARCH_PFN_OFFSET PFN_UP(PHYS_OFFSET) +#endif extern void clear_page(void * page); extern void copy_page(void * to, void * from); @@ -252,8 +257,8 @@ extern int __virt_addr_valid(const volatile void *kaddr); ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define UNCAC_ADDR(addr) ((addr) - PAGE_OFFSET + UNCAC_BASE) -#define CAC_ADDR(addr) ((addr) - UNCAC_BASE + PAGE_OFFSET) +#define UNCAC_ADDR(addr) (UNCAC_BASE + __pa(addr)) +#define CAC_ADDR(addr) ((unsigned long)__va((addr) - UNCAC_BASE)) #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index af34afbc32d9..b2fa62922d88 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -141,7 +141,7 @@ struct mips_fpu_struct { #define NUM_DSP_REGS 6 -typedef __u32 dspreg_t; +typedef unsigned long dspreg_t; struct mips_dsp_state { dspreg_t dspr[NUM_DSP_REGS]; @@ -386,7 +386,20 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29]) #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status) +#ifdef CONFIG_CPU_LOONGSON3 +/* + * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a + * tight read loop is executed, because reads take priority over writes & the + * hardware (incorrectly) doesn't ensure that writes will eventually occur. + * + * Since spin loops of any kind should have a cpu_relax() in them, force an SFB + * flush from cpu_relax() such that any pending writes will become visible as + * expected. + */ +#define cpu_relax() smp_mb() +#else #define cpu_relax() barrier() +#endif /* * Return_address is a replacement for __builtin_return_address(count) diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h index d49d247d48a1..bb36a400203d 100644 --- a/arch/mips/include/asm/setup.h +++ b/arch/mips/include/asm/setup.h @@ -2,8 +2,10 @@ #ifndef _MIPS_SETUP_H #define _MIPS_SETUP_H +#include <linux/types.h> #include <uapi/asm/setup.h> +extern void prom_putchar(char); extern void setup_early_printk(void); #ifdef CONFIG_EARLY_PRINTK_8250 diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h index 195db5045ae5..0d9fad5915fe 100644 --- a/arch/mips/include/asm/sgialib.h +++ b/arch/mips/include/asm/sgialib.h @@ -31,7 +31,6 @@ extern int prom_flags; #define PROM_FLAG_DONT_FREE_TEMP 4 /* Simple char-by-char console I/O. */ -extern void prom_putchar(char c); extern char prom_getchar(void); /* Get next memory descriptor after CURR, returns first descriptor diff --git a/arch/mips/include/asm/sim.h b/arch/mips/include/asm/sim.h index 91831800c480..59f31a95facd 100644 --- a/arch/mips/include/asm/sim.h +++ b/arch/mips/include/asm/sim.h @@ -39,8 +39,6 @@ __asm__( \ ".end\t__" #symbol "\n\t" \ ".size\t__" #symbol",. - __" #symbol) -#define nabi_no_regargs - #endif /* CONFIG_32BIT */ #ifdef CONFIG_64BIT @@ -67,16 +65,6 @@ __asm__( \ ".end\t__" #symbol "\n\t" \ ".size\t__" #symbol",. - __" #symbol) -#define nabi_no_regargs \ - unsigned long __dummy0, \ - unsigned long __dummy1, \ - unsigned long __dummy2, \ - unsigned long __dummy3, \ - unsigned long __dummy4, \ - unsigned long __dummy5, \ - unsigned long __dummy6, \ - unsigned long __dummy7, - #endif /* CONFIG_64BIT */ #endif /* _ASM_SIM_H */ diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 88ebd83b3bf9..056a6bf13491 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -25,7 +25,17 @@ extern cpumask_t cpu_sibling_map[]; extern cpumask_t cpu_core_map[]; extern cpumask_t cpu_foreign_map[]; -#define raw_smp_processor_id() (current_thread_info()->cpu) +static inline int raw_smp_processor_id(void) +{ +#if defined(__VDSO__) + extern int vdso_smp_processor_id(void) + __compiletime_error("VDSO should not call smp_processor_id()"); + return vdso_smp_processor_id(); +#else + return current_thread_info()->cpu; +#endif +} +#define raw_smp_processor_id raw_smp_processor_id /* Map from cpu id to sequential logical cpu number. This will only not be idempotent when cpus failed to come on-line. */ diff --git a/arch/mips/include/asm/txx9/generic.h b/arch/mips/include/asm/txx9/generic.h index 64887d3c7ec3..9a2c47bf3c40 100644 --- a/arch/mips/include/asm/txx9/generic.h +++ b/arch/mips/include/asm/txx9/generic.h @@ -49,7 +49,6 @@ void txx9_spi_init(int busid, unsigned long base, int irq); void txx9_ethaddr_init(unsigned int id, unsigned char *ethaddr); void txx9_sio_init(unsigned long baseaddr, int irq, unsigned int line, unsigned int sclk, int nocts); -void prom_putchar(char c); #ifdef CONFIG_EARLY_PRINTK extern void (*txx9_prom_putchar)(char c); void txx9_sio_putchar_init(unsigned long baseaddr); diff --git a/arch/mips/include/asm/txx9/ndfmc.h b/arch/mips/include/asm/txx9/ndfmc.h deleted file mode 100644 index fa67f3df78fc..000000000000 --- a/arch/mips/include/asm/txx9/ndfmc.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * (C) Copyright TOSHIBA CORPORATION 2007 - */ -#ifndef __ASM_TXX9_NDFMC_H -#define __ASM_TXX9_NDFMC_H - -#define NDFMC_PLAT_FLAG_USE_BSPRT 0x01 -#define NDFMC_PLAT_FLAG_NO_RSTR 0x02 -#define NDFMC_PLAT_FLAG_HOLDADD 0x04 -#define NDFMC_PLAT_FLAG_DUMMYWRITE 0x08 - -struct txx9ndfmc_platform_data { - unsigned int shift; - unsigned int gbus_clock; - unsigned int hold; /* hold time in nanosecond */ - unsigned int spw; /* strobe pulse width in nanosecond */ - unsigned int flags; - unsigned char ch_mask; /* available channel bitmask */ - unsigned char wp_mask; /* write-protect bitmask */ - unsigned char wide_mask; /* 16bit-nand bitmask */ -}; - -void txx9_ndfmc_init(unsigned long baseaddr, - const struct txx9ndfmc_platform_data *plat_data); - -#endif /* __ASM_TXX9_NDFMC_H */ diff --git a/arch/mips/include/asm/txx9/tx4939.h b/arch/mips/include/asm/txx9/tx4939.h index 6d667087f2aa..00805ac6e9fc 100644 --- a/arch/mips/include/asm/txx9/tx4939.h +++ b/arch/mips/include/asm/txx9/tx4939.h @@ -101,13 +101,6 @@ struct tx4939_irc_reg { struct tx4939_le_reg maskext; }; -struct tx4939_rtc_reg { - __u32 ctl; - __u32 adr; - __u32 dat; - __u32 tbc; -}; - struct tx4939_crypto_reg { struct tx4939_le_reg csr; struct tx4939_le_reg idesptr; @@ -370,26 +363,6 @@ struct tx4939_vpc_desc { #define TX4939_CLKCTR_CYPRST 0x00000001 /* - * RTC - */ -#define TX4939_RTCCTL_ALME 0x00000080 -#define TX4939_RTCCTL_ALMD 0x00000040 -#define TX4939_RTCCTL_BUSY 0x00000020 - -#define TX4939_RTCCTL_COMMAND 0x00000007 -#define TX4939_RTCCTL_COMMAND_NOP 0x00000000 -#define TX4939_RTCCTL_COMMAND_GETTIME 0x00000001 -#define TX4939_RTCCTL_COMMAND_SETTIME 0x00000002 -#define TX4939_RTCCTL_COMMAND_GETALARM 0x00000003 -#define TX4939_RTCCTL_COMMAND_SETALARM 0x00000004 - -#define TX4939_RTCTBC_PM 0x00000080 -#define TX4939_RTCTBC_COMP 0x0000007f - -#define TX4939_RTC_REG_RAMSIZE 0x00000100 -#define TX4939_RTC_REG_RWBSIZE 0x00000006 - -/* * CRYPTO */ #define TX4939_CRYPTO_CSR_SAESO 0x08000000 @@ -498,8 +471,6 @@ struct tx4939_vpc_desc { #define tx4939_ccfgptr \ ((struct tx4939_ccfg_reg __iomem *)TX4939_CCFG_REG) #define tx4939_sramcptr tx4938_sramcptr -#define tx4939_rtcptr \ - ((struct tx4939_rtc_reg __iomem *)TX4939_RTC_REG) #define tx4939_cryptoptr \ ((struct tx4939_crypto_reg __iomem *)TX4939_CRYPTO_REG) #define tx4939_vpcptr ((struct tx4939_vpc_reg __iomem *)TX4939_VPC_REG) diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 49c3d4795963..71370fb3ceef 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -123,4 +123,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c index d626a9a391cc..d31bc2f01208 100644 --- a/arch/mips/jazz/jazzdma.c +++ b/arch/mips/jazz/jazzdma.c @@ -16,6 +16,8 @@ #include <linux/bootmem.h> #include <linux/spinlock.h> #include <linux/gfp.h> +#include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> #include <asm/mipsregs.h> #include <asm/jazz.h> #include <asm/io.h> @@ -86,6 +88,7 @@ static int __init vdma_init(void) printk(KERN_INFO "VDMA: R4030 DMA pagetables initialized.\n"); return 0; } +arch_initcall(vdma_init); /* * Allocate DMA pagetables using a simple first-fit algorithm @@ -556,4 +559,140 @@ int vdma_get_enable(int channel) return enable; } -arch_initcall(vdma_init); +static void *jazz_dma_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + void *ret; + + ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs); + if (!ret) + return NULL; + + *dma_handle = vdma_alloc(virt_to_phys(ret), size); + if (*dma_handle == VDMA_ERROR) { + dma_direct_free(dev, size, ret, *dma_handle, attrs); + return NULL; + } + + if (!(attrs & DMA_ATTR_NON_CONSISTENT)) { + dma_cache_wback_inv((unsigned long)ret, size); + ret = (void *)UNCAC_ADDR(ret); + } + return ret; +} + +static void jazz_dma_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, unsigned long attrs) +{ + vdma_free(dma_handle); + if (!(attrs & DMA_ATTR_NON_CONSISTENT)) + vaddr = (void *)CAC_ADDR((unsigned long)vaddr); + return dma_direct_free(dev, size, vaddr, dma_handle, attrs); +} + +static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + phys_addr_t phys = page_to_phys(page) + offset; + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(dev, phys, size, dir); + return vdma_alloc(phys, size); +} + +static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_cpu(dev, vdma_log2phys(dma_addr), size, dir); + vdma_free(dma_addr); +} + +static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sglist, sg, nents, i) { + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, + dir); + sg->dma_address = vdma_alloc(sg_phys(sg), sg->length); + if (sg->dma_address == VDMA_ERROR) + return 0; + sg_dma_len(sg) = sg->length; + } + + return nents; +} + +static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sglist, sg, nents, i) { + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, + dir); + vdma_free(sg->dma_address); + } +} + +static void jazz_dma_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + arch_sync_dma_for_device(dev, vdma_log2phys(addr), size, dir); +} + +static void jazz_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + arch_sync_dma_for_cpu(dev, vdma_log2phys(addr), size, dir); +} + +static void jazz_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); +} + +static void jazz_dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); +} + +static int jazz_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr == VDMA_ERROR; +} + +const struct dma_map_ops jazz_dma_ops = { + .alloc = jazz_dma_alloc, + .free = jazz_dma_free, + .mmap = arch_dma_mmap, + .map_page = jazz_dma_map_page, + .unmap_page = jazz_dma_unmap_page, + .map_sg = jazz_dma_map_sg, + .unmap_sg = jazz_dma_unmap_sg, + .sync_single_for_cpu = jazz_dma_sync_single_for_cpu, + .sync_single_for_device = jazz_dma_sync_single_for_device, + .sync_sg_for_cpu = jazz_dma_sync_sg_for_cpu, + .sync_sg_for_device = jazz_dma_sync_sg_for_device, + .dma_supported = dma_direct_supported, + .cache_sync = arch_dma_cache_sync, + .mapping_error = jazz_dma_mapping_error, +}; +EXPORT_SYMBOL(jazz_dma_ops); diff --git a/arch/mips/jazz/setup.c b/arch/mips/jazz/setup.c index 448fd41792e4..1b5e121c3f0d 100644 --- a/arch/mips/jazz/setup.c +++ b/arch/mips/jazz/setup.c @@ -16,6 +16,7 @@ #include <linux/screen_info.h> #include <linux/platform_device.h> #include <linux/serial_8250.h> +#include <linux/dma-mapping.h> #include <asm/jazz.h> #include <asm/jazzdma.h> @@ -136,10 +137,16 @@ static struct resource jazz_esp_rsrc[] = { } }; +static u64 jazz_esp_dma_mask = DMA_BIT_MASK(32); + static struct platform_device jazz_esp_pdev = { .name = "jazz_esp", .num_resources = ARRAY_SIZE(jazz_esp_rsrc), - .resource = jazz_esp_rsrc + .resource = jazz_esp_rsrc, + .dev = { + .dma_mask = &jazz_esp_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + } }; static struct resource jazz_sonic_rsrc[] = { @@ -155,10 +162,16 @@ static struct resource jazz_sonic_rsrc[] = { } }; +static u64 jazz_sonic_dma_mask = DMA_BIT_MASK(32); + static struct platform_device jazz_sonic_pdev = { .name = "jazzsonic", .num_resources = ARRAY_SIZE(jazz_sonic_rsrc), - .resource = jazz_sonic_rsrc + .resource = jazz_sonic_rsrc, + .dev = { + .dma_mask = &jazz_sonic_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + } }; static struct resource jazz_cmos_rsrc[] = { diff --git a/arch/mips/jz4740/Platform b/arch/mips/jz4740/Platform index 28448d358c10..a2a5a85ea1f9 100644 --- a/arch/mips/jz4740/Platform +++ b/arch/mips/jz4740/Platform @@ -1,4 +1,4 @@ platform-$(CONFIG_MACH_INGENIC) += jz4740/ cflags-$(CONFIG_MACH_INGENIC) += -I$(srctree)/arch/mips/include/asm/mach-jz4740 load-$(CONFIG_MACH_INGENIC) += 0xffffffff80010000 -zload-$(CONFIG_MACH_INGENIC) += 0xffffffff80600000 +zload-$(CONFIG_MACH_INGENIC) += 0xffffffff81000000 diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c index 60f0767507c6..af0c8ace0141 100644 --- a/arch/mips/jz4740/board-qi_lb60.c +++ b/arch/mips/jz4740/board-qi_lb60.c @@ -29,10 +29,11 @@ #include <linux/power/gpio-charger.h> #include <linux/pwm.h> +#include <linux/platform_data/jz4740/jz4740_nand.h> + #include <asm/mach-jz4740/gpio.h> #include <asm/mach-jz4740/jz4740_fb.h> #include <asm/mach-jz4740/jz4740_mmc.h> -#include <asm/mach-jz4740/jz4740_nand.h> #include <linux/regulator/fixed.h> #include <linux/regulator/machine.h> diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index b2509c19cfb5..d535fc706a8b 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1849,7 +1849,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); break; - case PRID_REV_LOONGSON3A_R3: + case PRID_REV_LOONGSON3A_R3_0: + case PRID_REV_LOONGSON3A_R3_1: c->cputype = CPU_LOONGSON3; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); diff --git a/arch/mips/kernel/early_printk.c b/arch/mips/kernel/early_printk.c index 505cb77d1280..4a1647ddfbd9 100644 --- a/arch/mips/kernel/early_printk.c +++ b/arch/mips/kernel/early_printk.c @@ -14,8 +14,6 @@ #include <asm/setup.h> -extern void prom_putchar(char); - static void early_console_write(struct console *con, const char *s, unsigned n) { while (n-- && *s) { diff --git a/arch/mips/kernel/early_printk_8250.c b/arch/mips/kernel/early_printk_8250.c index 83cea3767556..ea26614afac6 100644 --- a/arch/mips/kernel/early_printk_8250.c +++ b/arch/mips/kernel/early_printk_8250.c @@ -20,6 +20,7 @@ #include <linux/io.h> #include <linux/serial_core.h> #include <linux/serial_reg.h> +#include <asm/setup.h> static void __iomem *serial8250_base; static unsigned int serial8250_reg_shift; diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 37b9383eacd3..6c257b52f57f 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -354,16 +354,56 @@ NESTED(ejtag_debug_handler, PT_SIZE, sp) sll k0, k0, 30 # Check for SDBBP. bgez k0, ejtag_return +#ifdef CONFIG_SMP +1: PTR_LA k0, ejtag_debug_buffer_spinlock + ll k0, 0(k0) + bnez k0, 1b + PTR_LA k0, ejtag_debug_buffer_spinlock + sc k0, 0(k0) + beqz k0, 1b +# ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC + sync +# endif + + PTR_LA k0, ejtag_debug_buffer + LONG_S k1, 0(k0) + + ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG + PTR_SRL k1, SMP_CPUID_PTRSHIFT + PTR_SLL k1, LONGLOG + PTR_LA k0, ejtag_debug_buffer_per_cpu + PTR_ADDU k0, k1 + + PTR_LA k1, ejtag_debug_buffer + LONG_L k1, 0(k1) + LONG_S k1, 0(k0) + + PTR_LA k0, ejtag_debug_buffer_spinlock + sw zero, 0(k0) +#else PTR_LA k0, ejtag_debug_buffer LONG_S k1, 0(k0) +#endif + SAVE_ALL move a0, sp jal ejtag_exception_handler RESTORE_ALL + +#ifdef CONFIG_SMP + ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG + PTR_SRL k1, SMP_CPUID_PTRSHIFT + PTR_SLL k1, LONGLOG + PTR_LA k0, ejtag_debug_buffer_per_cpu + PTR_ADDU k0, k1 + LONG_L k1, 0(k0) +#else PTR_LA k0, ejtag_debug_buffer LONG_L k1, 0(k0) +#endif ejtag_return: + back_to_back_c0_hazard MFC0 k0, CP0_DESAVE .set mips32 deret @@ -377,6 +417,12 @@ ejtag_return: .data EXPORT(ejtag_debug_buffer) .fill LONGSIZE +#ifdef CONFIG_SMP +EXPORT(ejtag_debug_buffer_spinlock) + .fill LONGSIZE +EXPORT(ejtag_debug_buffer_per_cpu) + .fill LONGSIZE * NR_CPUS +#endif .previous __INIT diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 7c246b69c545..046846999efd 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -33,21 +33,21 @@ void (*cpu_wait)(void); EXPORT_SYMBOL(cpu_wait); -static void r3081_wait(void) +static void __cpuidle r3081_wait(void) { unsigned long cfg = read_c0_conf(); write_c0_conf(cfg | R30XX_CONF_HALT); local_irq_enable(); } -static void r39xx_wait(void) +static void __cpuidle r39xx_wait(void) { if (!need_resched()) write_c0_conf(read_c0_conf() | TX39_CONF_HALT); local_irq_enable(); } -void r4k_wait(void) +void __cpuidle r4k_wait(void) { local_irq_enable(); __r4k_wait(); @@ -60,7 +60,7 @@ void r4k_wait(void) * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes * using this version a gamble. */ -void r4k_wait_irqoff(void) +void __cpuidle r4k_wait_irqoff(void) { if (!need_resched()) __asm__( @@ -75,7 +75,7 @@ void r4k_wait_irqoff(void) * The RM7000 variant has to handle erratum 38. The workaround is to not * have any pending stores when the WAIT instruction is executed. */ -static void rm7k_wait_irqoff(void) +static void __cpuidle rm7k_wait_irqoff(void) { if (!need_resched()) __asm__( @@ -96,7 +96,7 @@ static void rm7k_wait_irqoff(void) * since coreclock (and the cp0 counter) stops upon executing it. Only an * interrupt can wake it, so they must be enabled before entering idle modes. */ -static void au1k_wait(void) +static void __cpuidle au1k_wait(void) { unsigned long c0status = read_c0_status() | 1; /* irqs on */ diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index f5c8bce70db2..54cd675c5d1d 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -326,19 +326,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_enable_no_resched(); } return 1; - } else { - if (addr->word != breakpoint_insn.word) { - /* - * The breakpoint instruction was removed by - * another cpu right after we hit, no further - * handling of this interrupt is appropriate - */ - ret = 1; - goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) - goto ss_probe; + } else if (addr->word != breakpoint_insn.word) { + /* + * The breakpoint instruction was removed by + * another cpu right after we hit, no further + * handling of this interrupt is appropriate + */ + ret = 1; } goto no_kprobe; } @@ -364,10 +358,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) if (p->pre_handler && p->pre_handler(p, regs)) { /* handler has already set things up, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; } -ss_probe: prepare_singlestep(p, regs, kcb); if (kcb->flags & SKIP_DELAYSLOT) { kcb->kprobe_status = KPROBE_HIT_SSDONE; @@ -468,51 +463,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_sp = regs->regs[29]; - - memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp, - MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp)); - - regs->cp0_epc = (unsigned long)(jp->entry); - - return 1; -} - -/* Defined in the inline asm below. */ -void jprobe_return_end(void); - -void __kprobes jprobe_return(void) -{ - /* Assembler quirk necessitates this '0,code' business. */ - asm volatile( - "break 0,%0\n\t" - ".globl jprobe_return_end\n" - "jprobe_return_end:\n" - : : "n" (BRK_KPROBE_BP) : "memory"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (regs->cp0_epc >= (unsigned long)jprobe_return && - regs->cp0_epc <= (unsigned long)jprobe_return_end) { - *regs = kcb->jprobe_saved_regs; - memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack, - MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp)); - preempt_enable_no_resched(); - - return 1; - } - return 0; -} - /* * Function return probe trampoline: * - init_kprobes() establishes a probepoint here @@ -595,9 +545,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); instruction_pointer(regs) = orig_ret_address; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 318f1c05c5b3..6b61be486303 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -43,17 +43,6 @@ #include <asm/mmu_context.h> #include <asm/mman.h> -/* Use this to get at 32-bit user passed pointers. */ -/* A() macro should be used for places where you e.g. - have some internal variable u32 and just want to get - rid of a compiler warning. AA() has to be used in - places where you want to convert a function argument - to 32bit pointer or when you e.g. access pt_regs - structure and want to consider 32bit registers only. - */ -#define A(__x) ((unsigned long)(__x)) -#define AA(__x) ((unsigned long)((int)__x)) - #ifdef __MIPSEB__ #define merge_64(r1, r2) ((((r1) & 0xffffffffUL) << 32) + ((r2) & 0xffffffffUL)) #endif @@ -61,24 +50,6 @@ #define merge_64(r1, r2) ((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL)) #endif -SYSCALL_DEFINE6(32_mmap2, unsigned long, addr, unsigned long, len, - unsigned long, prot, unsigned long, flags, unsigned long, fd, - unsigned long, pgoff) -{ - if (pgoff & (~PAGE_MASK >> 12)) - return -EINVAL; - return ksys_mmap_pgoff(addr, len, prot, flags, fd, - pgoff >> (PAGE_SHIFT-12)); -} - -#define RLIM_INFINITY32 0x7fffffff -#define RESOURCE32(x) ((x > RLIM_INFINITY32) ? RLIM_INFINITY32 : x) - -struct rlimit32 { - int rlim_cur; - int rlim_max; -}; - SYSCALL_DEFINE4(32_truncate64, const char __user *, path, unsigned long, __dummy, unsigned long, a2, unsigned long, a3) { diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 9670e70139fd..8fc69891e117 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -30,6 +30,7 @@ #include <linux/random.h> #include <linux/prctl.h> #include <linux/nmi.h> +#include <linux/cpu.h> #include <asm/asm.h> #include <asm/bootinfo.h> @@ -706,19 +707,25 @@ int mips_get_process_fp_mode(struct task_struct *task) return value; } -static void prepare_for_fp_mode_switch(void *info) +static long prepare_for_fp_mode_switch(void *unused) { - struct mm_struct *mm = info; - - if (current->mm == mm) - lose_fpu(1); + /* + * This is icky, but we use this to simply ensure that all CPUs have + * context switched, regardless of whether they were previously running + * kernel or user code. This ensures that no CPU currently has its FPU + * enabled, or is about to attempt to enable it through any path other + * than enable_restore_fp_context() which will wait appropriately for + * fp_mode_switching to be zero. + */ + return 0; } int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) { const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE; struct task_struct *t; - int max_users; + struct cpumask process_cpus; + int cpu; /* If nothing to change, return right away, successfully. */ if (value == mips_get_process_fp_mode(task)) @@ -751,35 +758,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6) return -EOPNOTSUPP; - /* Proceed with the mode switch */ - preempt_disable(); - - /* Save FP & vector context, then disable FPU & MSA */ - if (task->signal == current->signal) - lose_fpu(1); - - /* Prevent any threads from obtaining live FP context */ - atomic_set(&task->mm->context.fp_mode_switching, 1); - smp_mb__after_atomic(); - - /* - * If there are multiple online CPUs then force any which are running - * threads in this process to lose their FPU context, which they can't - * regain until fp_mode_switching is cleared later. - */ - if (num_online_cpus() > 1) { - /* No need to send an IPI for the local CPU */ - max_users = (task->mm == current->mm) ? 1 : 0; - - if (atomic_read(¤t->mm->mm_users) > max_users) - smp_call_function(prepare_for_fp_mode_switch, - (void *)current->mm, 1); - } - - /* - * There are now no threads of the process with live FP context, so it - * is safe to proceed with the FP mode switch. - */ + /* Indicate the new FP mode in each thread */ for_each_thread(task, t) { /* Update desired FP register width */ if (value & PR_FP_MODE_FR) { @@ -796,9 +775,34 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS); } - /* Allow threads to use FP again */ - atomic_set(&task->mm->context.fp_mode_switching, 0); - preempt_enable(); + /* + * We need to ensure that all threads in the process have switched mode + * before returning, in order to allow userland to not worry about + * races. We can do this by forcing all CPUs that any thread in the + * process may be running on to schedule something else - in this case + * prepare_for_fp_mode_switch(). + * + * We begin by generating a mask of all CPUs that any thread in the + * process may be running on. + */ + cpumask_clear(&process_cpus); + for_each_thread(task, t) + cpumask_set_cpu(task_cpu(t), &process_cpus); + + /* + * Now we schedule prepare_for_fp_mode_switch() on each of those CPUs. + * + * The CPUs may have rescheduled already since we switched mode or + * generated the cpumask, but that doesn't matter. If the task in this + * process is scheduled out then our scheduling + * prepare_for_fp_mode_switch() will simply be redundant. If it's + * scheduled in then it will already have picked up the new FP mode + * whilst doing so. + */ + get_online_cpus(); + for_each_cpu_and(cpu, &process_cpus, cpu_online_mask) + work_on_cpu(cpu, prepare_for_fp_mode_switch, NULL); + put_online_cpus(); wake_up_var(&task->mm->context.fp_mode_switching); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 9f6c3f2aa2e2..e5ba56c01ee0 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -41,6 +41,7 @@ #include <asm/mipsmtregs.h> #include <asm/pgtable.h> #include <asm/page.h> +#include <asm/processor.h> #include <asm/syscall.h> #include <linux/uaccess.h> #include <asm/bootinfo.h> @@ -589,9 +590,226 @@ static int fpr_set(struct task_struct *target, return err; } +#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32) + +/* + * Copy the DSP context to the supplied 32-bit NT_MIPS_DSP buffer. + */ +static int dsp32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + unsigned int start, num_regs, i; + u32 dspregs[NUM_DSP_REGS + 1]; + + BUG_ON(count % sizeof(u32)); + + if (!cpu_has_dsp) + return -EIO; + + start = pos / sizeof(u32); + num_regs = count / sizeof(u32); + + if (start + num_regs > NUM_DSP_REGS + 1) + return -EIO; + + for (i = start; i < num_regs; i++) + switch (i) { + case 0 ... NUM_DSP_REGS - 1: + dspregs[i] = target->thread.dsp.dspr[i]; + break; + case NUM_DSP_REGS: + dspregs[i] = target->thread.dsp.dspcontrol; + break; + } + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0, + sizeof(dspregs)); +} + +/* + * Copy the supplied 32-bit NT_MIPS_DSP buffer to the DSP context. + */ +static int dsp32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned int start, num_regs, i; + u32 dspregs[NUM_DSP_REGS + 1]; + int err; + + BUG_ON(count % sizeof(u32)); + + if (!cpu_has_dsp) + return -EIO; + + start = pos / sizeof(u32); + num_regs = count / sizeof(u32); + + if (start + num_regs > NUM_DSP_REGS + 1) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0, + sizeof(dspregs)); + if (err) + return err; + + for (i = start; i < num_regs; i++) + switch (i) { + case 0 ... NUM_DSP_REGS - 1: + target->thread.dsp.dspr[i] = (s32)dspregs[i]; + break; + case NUM_DSP_REGS: + target->thread.dsp.dspcontrol = (s32)dspregs[i]; + break; + } + + return 0; +} + +#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */ + +#ifdef CONFIG_64BIT + +/* + * Copy the DSP context to the supplied 64-bit NT_MIPS_DSP buffer. + */ +static int dsp64_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + unsigned int start, num_regs, i; + u64 dspregs[NUM_DSP_REGS + 1]; + + BUG_ON(count % sizeof(u64)); + + if (!cpu_has_dsp) + return -EIO; + + start = pos / sizeof(u64); + num_regs = count / sizeof(u64); + + if (start + num_regs > NUM_DSP_REGS + 1) + return -EIO; + + for (i = start; i < num_regs; i++) + switch (i) { + case 0 ... NUM_DSP_REGS - 1: + dspregs[i] = target->thread.dsp.dspr[i]; + break; + case NUM_DSP_REGS: + dspregs[i] = target->thread.dsp.dspcontrol; + break; + } + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0, + sizeof(dspregs)); +} + +/* + * Copy the supplied 64-bit NT_MIPS_DSP buffer to the DSP context. + */ +static int dsp64_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned int start, num_regs, i; + u64 dspregs[NUM_DSP_REGS + 1]; + int err; + + BUG_ON(count % sizeof(u64)); + + if (!cpu_has_dsp) + return -EIO; + + start = pos / sizeof(u64); + num_regs = count / sizeof(u64); + + if (start + num_regs > NUM_DSP_REGS + 1) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0, + sizeof(dspregs)); + if (err) + return err; + + for (i = start; i < num_regs; i++) + switch (i) { + case 0 ... NUM_DSP_REGS - 1: + target->thread.dsp.dspr[i] = dspregs[i]; + break; + case NUM_DSP_REGS: + target->thread.dsp.dspcontrol = dspregs[i]; + break; + } + + return 0; +} + +#endif /* CONFIG_64BIT */ + +/* + * Determine whether the DSP context is present. + */ +static int dsp_active(struct task_struct *target, + const struct user_regset *regset) +{ + return cpu_has_dsp ? NUM_DSP_REGS + 1 : -ENODEV; +} + +/* Copy the FP mode setting to the supplied NT_MIPS_FP_MODE buffer. */ +static int fp_mode_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int fp_mode; + + fp_mode = mips_get_process_fp_mode(target); + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fp_mode, 0, + sizeof(fp_mode)); +} + +/* + * Copy the supplied NT_MIPS_FP_MODE buffer to the FP mode setting. + * + * We optimize for the case where `count % sizeof(int) == 0', which + * is supposed to have been guaranteed by the kernel before calling + * us, e.g. in `ptrace_regset'. We enforce that requirement, so + * that we can safely avoid preinitializing temporaries for partial + * mode writes. + */ +static int fp_mode_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int fp_mode; + int err; + + BUG_ON(count % sizeof(int)); + + if (pos + count > sizeof(fp_mode)) + return -EIO; + + err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fp_mode, 0, + sizeof(fp_mode)); + if (err) + return err; + + if (count > 0) + err = mips_set_process_fp_mode(target, fp_mode); + + return err; +} + enum mips_regset { REGSET_GPR, REGSET_FPR, + REGSET_DSP, + REGSET_FP_MODE, }; struct pt_regs_offset { @@ -697,6 +915,23 @@ static const struct user_regset mips_regsets[] = { .get = fpr_get, .set = fpr_set, }, + [REGSET_DSP] = { + .core_note_type = NT_MIPS_DSP, + .n = NUM_DSP_REGS + 1, + .size = sizeof(u32), + .align = sizeof(u32), + .get = dsp32_get, + .set = dsp32_set, + .active = dsp_active, + }, + [REGSET_FP_MODE] = { + .core_note_type = NT_MIPS_FP_MODE, + .n = 1, + .size = sizeof(int), + .align = sizeof(int), + .get = fp_mode_get, + .set = fp_mode_set, + }, }; static const struct user_regset_view user_mips_view = { @@ -728,6 +963,23 @@ static const struct user_regset mips64_regsets[] = { .get = fpr_get, .set = fpr_set, }, + [REGSET_DSP] = { + .core_note_type = NT_MIPS_DSP, + .n = NUM_DSP_REGS + 1, + .size = sizeof(u64), + .align = sizeof(u64), + .get = dsp64_get, + .set = dsp64_set, + .active = dsp_active, + }, + [REGSET_FP_MODE] = { + .core_note_type = NT_MIPS_FP_MODE, + .n = 1, + .size = sizeof(int), + .align = sizeof(int), + .get = fp_mode_get, + .set = fp_mode_set, + }, }; static const struct user_regset_view user_mips64_view = { @@ -856,7 +1108,7 @@ long arch_ptrace(struct task_struct *child, long request, goto out; } dregs = __get_dsp_regs(child); - tmp = (unsigned long) (dregs[addr - DSP_BASE]); + tmp = dregs[addr - DSP_BASE]; break; } case DSP_CONTROL: diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c index 7edc629304c8..bc348d44d151 100644 --- a/arch/mips/kernel/ptrace32.c +++ b/arch/mips/kernel/ptrace32.c @@ -142,7 +142,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, goto out; } dregs = __get_dsp_regs(child); - tmp = (unsigned long) (dregs[addr - DSP_BASE]); + tmp = dregs[addr - DSP_BASE]; break; } case DSP_CONTROL: diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S index c6bbf2165051..419c92197b2f 100644 --- a/arch/mips/kernel/relocate_kernel.S +++ b/arch/mips/kernel/relocate_kernel.S @@ -85,7 +85,7 @@ done: #ifdef CONFIG_CPU_CAVIUM_OCTEON /* We need to flush I-cache before jumping to new kernel. - * Unfortunatelly, this code is cpu-specific. + * Unfortunately, this code is cpu-specific. */ .set push .set noreorder @@ -145,7 +145,7 @@ LEAF(kexec_smp_wait) #endif /* All parameters to new kernel are passed in registers a0-a3. - * kexec_args[0..3] are uses to prepare register values. + * kexec_args[0..3] are used to prepare register values. */ kexec_args: diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 2c96c0c68116..c71d1eb7da59 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -36,6 +36,7 @@ #include <asm/cdmm.h> #include <asm/cpu.h> #include <asm/debug.h> +#include <asm/dma-coherence.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/smp-ops.h> @@ -84,6 +85,11 @@ static struct resource bss_resource = { .name = "Kernel bss", }; static void *detect_magic __initdata = detect_memory_region; +#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET +unsigned long ARCH_PFN_OFFSET; +EXPORT_SYMBOL(ARCH_PFN_OFFSET); +#endif + void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type) { int x = boot_mem_map.nr_map; @@ -441,6 +447,12 @@ static void __init bootmem_init(void) mapstart = max(reserved_end, start); } + if (min_low_pfn >= max_low_pfn) + panic("Incorrect memory mapping !!!"); + +#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET + ARCH_PFN_OFFSET = PFN_UP(ramstart); +#else /* * Reserve any memory between the start of RAM and PHYS_OFFSET */ @@ -448,8 +460,6 @@ static void __init bootmem_init(void) add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET, BOOT_MEM_RESERVED); - if (min_low_pfn >= max_low_pfn) - panic("Incorrect memory mapping !!!"); if (min_low_pfn > ARCH_PFN_OFFSET) { pr_info("Wasting %lu bytes for tracking %lu unused pages\n", (min_low_pfn - ARCH_PFN_OFFSET) * sizeof(struct page), @@ -459,6 +469,7 @@ static void __init bootmem_init(void) ARCH_PFN_OFFSET - min_low_pfn); } min_low_pfn = ARCH_PFN_OFFSET; +#endif /* * Determine low and high memory ranges @@ -1055,3 +1066,26 @@ static int __init debugfs_mips(void) } arch_initcall(debugfs_mips); #endif + +#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT) +/* User defined DMA coherency from command line. */ +enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT; +EXPORT_SYMBOL_GPL(coherentio); +int hw_coherentio = 0; /* Actual hardware supported DMA coherency setting. */ + +static int __init setcoherentio(char *str) +{ + coherentio = IO_COHERENCE_ENABLED; + pr_info("Hardware DMA cache coherency (command line)\n"); + return 0; +} +early_param("coherentio", setcoherentio); + +static int __init setnocoherentio(char *str) +{ + coherentio = IO_COHERENCE_DISABLED; + pr_info("Software DMA cache coherency (command line)\n"); + return 0; +} +early_param("nocoherentio", setnocoherentio); +#endif diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 0a9cfe7a0372..109ed163a6a6 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -592,13 +592,15 @@ SYSCALL_DEFINE3(sigaction, int, sig, const struct sigaction __user *, act, #endif #ifdef CONFIG_TRAD_SIGNALS -asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs) +asmlinkage void sys_sigreturn(void) { struct sigframe __user *frame; + struct pt_regs *regs; sigset_t blocked; int sig; - frame = (struct sigframe __user *) regs.regs[29]; + regs = current_pt_regs(); + frame = (struct sigframe __user *)regs->regs[29]; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; if (__copy_from_user(&blocked, &frame->sf_mask, sizeof(blocked))) @@ -606,7 +608,7 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs) set_current_blocked(&blocked); - sig = restore_sigcontext(®s, &frame->sf_sc); + sig = restore_sigcontext(regs, &frame->sf_sc); if (sig < 0) goto badframe; else if (sig) @@ -618,8 +620,8 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs) __asm__ __volatile__( "move\t$29, %0\n\t" "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); + : /* no outputs */ + : "r" (regs)); /* Unreached */ badframe: @@ -627,13 +629,15 @@ badframe: } #endif /* CONFIG_TRAD_SIGNALS */ -asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs) +asmlinkage void sys_rt_sigreturn(void) { struct rt_sigframe __user *frame; + struct pt_regs *regs; sigset_t set; int sig; - frame = (struct rt_sigframe __user *) regs.regs[29]; + regs = current_pt_regs(); + frame = (struct rt_sigframe __user *)regs->regs[29]; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; if (__copy_from_user(&set, &frame->rs_uc.uc_sigmask, sizeof(set))) @@ -641,7 +645,7 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs) set_current_blocked(&set); - sig = restore_sigcontext(®s, &frame->rs_uc.uc_mcontext); + sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext); if (sig < 0) goto badframe; else if (sig) @@ -656,8 +660,8 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs) __asm__ __volatile__( "move\t$29, %0\n\t" "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); + : /* no outputs */ + : "r" (regs)); /* Unreached */ badframe: diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c index b672cebb4a1a..8f65aaf9206d 100644 --- a/arch/mips/kernel/signal_n32.c +++ b/arch/mips/kernel/signal_n32.c @@ -64,13 +64,15 @@ struct rt_sigframe_n32 { struct ucontextn32 rs_uc; }; -asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) +asmlinkage void sysn32_rt_sigreturn(void) { struct rt_sigframe_n32 __user *frame; + struct pt_regs *regs; sigset_t set; int sig; - frame = (struct rt_sigframe_n32 __user *) regs.regs[29]; + regs = current_pt_regs(); + frame = (struct rt_sigframe_n32 __user *)regs->regs[29]; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask)) @@ -78,7 +80,7 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) set_current_blocked(&set); - sig = restore_sigcontext(®s, &frame->rs_uc.uc_mcontext); + sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext); if (sig < 0) goto badframe; else if (sig) @@ -93,8 +95,8 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) __asm__ __volatile__( "move\t$29, %0\n\t" "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); + : /* no outputs */ + : "r" (regs)); /* Unreached */ badframe: diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c index 2b3572fb5f1b..b6e3ddef48a0 100644 --- a/arch/mips/kernel/signal_o32.c +++ b/arch/mips/kernel/signal_o32.c @@ -151,13 +151,15 @@ static int setup_frame_32(void *sig_return, struct ksignal *ksig, return 0; } -asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) +asmlinkage void sys32_rt_sigreturn(void) { struct rt_sigframe32 __user *frame; + struct pt_regs *regs; sigset_t set; int sig; - frame = (struct rt_sigframe32 __user *) regs.regs[29]; + regs = current_pt_regs(); + frame = (struct rt_sigframe32 __user *)regs->regs[29]; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask)) @@ -165,7 +167,7 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) set_current_blocked(&set); - sig = restore_sigcontext32(®s, &frame->rs_uc.uc_mcontext); + sig = restore_sigcontext32(regs, &frame->rs_uc.uc_mcontext); if (sig < 0) goto badframe; else if (sig) @@ -180,8 +182,8 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) __asm__ __volatile__( "move\t$29, %0\n\t" "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); + : /* no outputs */ + : "r" (regs)); /* Unreached */ badframe: @@ -251,13 +253,15 @@ struct mips_abi mips_abi_32 = { }; -asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs) +asmlinkage void sys32_sigreturn(void) { struct sigframe32 __user *frame; + struct pt_regs *regs; sigset_t blocked; int sig; - frame = (struct sigframe32 __user *) regs.regs[29]; + regs = current_pt_regs(); + frame = (struct sigframe32 __user *)regs->regs[29]; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask)) @@ -265,7 +269,7 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs) set_current_blocked(&blocked); - sig = restore_sigcontext32(®s, &frame->sf_sc); + sig = restore_sigcontext32(regs, &frame->sf_sc); if (sig < 0) goto badframe; else if (sig) @@ -277,8 +281,8 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs) __asm__ __volatile__( "move\t$29, %0\n\t" "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); + : /* no outputs */ + : "r" (regs)); /* Unreached */ badframe: diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 8d505a21396e..f8871d5b7eb3 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1221,13 +1221,6 @@ static int enable_restore_fp_context(int msa) { int err, was_fpu_owner, prior_msa; - /* - * If an FP mode switch is currently underway, wait for it to - * complete before proceeding. - */ - wait_var_event(¤t->mm->context.fp_mode_switching, - !atomic_read(¤t->mm->context.fp_mode_switching)); - if (!used_math()) { /* First time FP context user. */ preempt_disable(); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 7cd76f93a438..f7ea8e21656b 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -515,7 +515,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, dvcpu->arch.wait = 0; if (swq_has_sleeper(&dvcpu->wq)) - swake_up(&dvcpu->wq); + swake_up_one(&dvcpu->wq); return 0; } @@ -1204,7 +1204,7 @@ static void kvm_mips_comparecount_func(unsigned long data) vcpu->arch.wait = 0; if (swq_has_sleeper(&vcpu->wq)) - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); } /* low level hrtimer wake routine */ diff --git a/arch/mips/lantiq/early_printk.c b/arch/mips/lantiq/early_printk.c index 44bccaee822b..c4aa140b7c91 100644 --- a/arch/mips/lantiq/early_printk.c +++ b/arch/mips/lantiq/early_printk.c @@ -8,6 +8,7 @@ #include <linux/cpu.h> #include <lantiq_soc.h> +#include <asm/setup.h> #define ASC_BUF 1024 #define LTQ_ASC_FSTAT ((u32 *)(LTQ_EARLY_ASC + 0x0048)) diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index 9ff7ccde9de0..d984bd5c2ec5 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -9,7 +9,6 @@ #include <linux/export.h> #include <linux/clk.h> #include <linux/bootmem.h> -#include <linux/of_platform.h> #include <linux/of_fdt.h> #include <asm/bootinfo.h> @@ -114,10 +113,3 @@ void __init prom_init(void) panic("failed to register_vsmp_smp_ops()"); #endif } - -int __init plat_of_setup(void) -{ - return of_platform_default_populate(NULL, NULL, NULL); -} - -arch_initcall(plat_of_setup); diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c index 805b3a6ab2d6..4b9fbb6744ad 100644 --- a/arch/mips/lantiq/xway/dma.c +++ b/arch/mips/lantiq/xway/dma.c @@ -130,10 +130,9 @@ ltq_dma_alloc(struct ltq_dma_channel *ch) unsigned long flags; ch->desc = 0; - ch->desc_base = dma_alloc_coherent(NULL, + ch->desc_base = dma_zalloc_coherent(NULL, LTQ_DESC_NUM * LTQ_DESC_SIZE, &ch->phys, GFP_ATOMIC); - memset(ch->desc_base, 0, LTQ_DESC_NUM * LTQ_DESC_SIZE); spin_lock_irqsave(<q_dma_lock, flags); ltq_dma_w32(ch->nr, LTQ_DMA_CS); diff --git a/arch/mips/lasat/prom.c b/arch/mips/lasat/prom.c index 17e15b50a551..37b8fc5b9ac9 100644 --- a/arch/mips/lasat/prom.c +++ b/arch/mips/lasat/prom.c @@ -13,6 +13,7 @@ #include <asm/bootinfo.h> #include <asm/lasat/lasat.h> #include <asm/cpu.h> +#include <asm/setup.h> #include "at93c.h" #include <asm/lasat/eeprom.h> diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index 1cc306520a55..3a6f34ef5ffc 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -195,6 +195,7 @@ #endif #else PTR_SUBU t0, $0, a2 + move a2, zero /* No remaining longs */ PTR_ADDIU t0, 1 STORE_BYTE(0) STORE_BYTE(1) @@ -231,16 +232,25 @@ #ifdef CONFIG_CPU_MIPSR6 .Lbyte_fixup\@: - PTR_SUBU a2, $0, t0 + /* + * unset_bytes = (#bytes - (#unaligned bytes)) - (-#unaligned bytes remaining + 1) + 1 + * a2 = a2 - t0 + 1 + */ + PTR_SUBU a2, t0 jr ra PTR_ADDIU a2, 1 #endif /* CONFIG_CPU_MIPSR6 */ .Lfirst_fixup\@: + /* unset_bytes already in a2 */ jr ra nop .Lfwd_fixup\@: + /* + * unset_bytes = partial_start_addr + #bytes - fault_addr + * a2 = t1 + (a2 & 3f) - $28->task->BUADDR + */ PTR_L t0, TI_TASK($28) andi a2, 0x3f LONG_L t0, THREAD_BUADDR(t0) @@ -249,6 +259,10 @@ LONG_SUBU a2, t0 .Lpartial_fixup\@: + /* + * unset_bytes = partial_end_addr + #bytes - fault_addr + * a2 = a0 + (a2 & STORMASK) - $28->task->BUADDR + */ PTR_L t0, TI_TASK($28) andi a2, STORMASK LONG_L t0, THREAD_BUADDR(t0) @@ -257,10 +271,15 @@ LONG_SUBU a2, t0 .Llast_fixup\@: + /* unset_bytes already in a2 */ jr ra nop .Lsmall_fixup\@: + /* + * unset_bytes = end_addr - current_addr + 1 + * a2 = t1 - a0 + 1 + */ PTR_SUBU a2, t1, a0 jr ra PTR_ADDIU a2, 1 diff --git a/arch/mips/loongson32/Platform b/arch/mips/loongson32/Platform index ffe01c6d0037..a0dbb3b2f2de 100644 --- a/arch/mips/loongson32/Platform +++ b/arch/mips/loongson32/Platform @@ -1,8 +1,4 @@ -cflags-$(CONFIG_CPU_LOONGSON1) += \ - $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \ - -Wa,-mips32r2 -Wa,--trap - +cflags-$(CONFIG_CPU_LOONGSON1) += -march=mips32 -Wa,--trap platform-$(CONFIG_MACH_LOONGSON32) += loongson32/ cflags-$(CONFIG_MACH_LOONGSON32) += -I$(srctree)/arch/mips/include/asm/mach-loongson32 -load-$(CONFIG_LOONGSON1_LS1B) += 0xffffffff80100000 -load-$(CONFIG_LOONGSON1_LS1C) += 0xffffffff80100000 +load-$(CONFIG_CPU_LOONGSON1) += 0xffffffff80100000 diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig index c79e6a565572..c865b4b9b775 100644 --- a/arch/mips/loongson64/Kconfig +++ b/arch/mips/loongson64/Kconfig @@ -91,7 +91,6 @@ config LOONGSON_MACH3X select LOONGSON_MC146818 select ZONE_DMA32 select LEFI_FIRMWARE_INTERFACE - select PHYS48_TO_HT40 help Generic Loongson 3 family machines utilize the 3A/3B revision of Loongson processor and RS780/SBX00 chipset. @@ -130,10 +129,6 @@ config LOONGSON_UART_BASE default y depends on EARLY_PRINTK || SERIAL_8250 -config PHYS48_TO_HT40 - bool - default y if CPU_LOONGSON3 - config LOONGSON_MC146818 bool default n diff --git a/arch/mips/loongson64/common/Makefile b/arch/mips/loongson64/common/Makefile index 8235ac7eac95..57ee03022941 100644 --- a/arch/mips/loongson64/common/Makefile +++ b/arch/mips/loongson64/common/Makefile @@ -6,6 +6,7 @@ obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \ bonito-irq.o mem.o machtype.o platform.o serial.o obj-$(CONFIG_PCI) += pci.o +obj-$(CONFIG_CPU_LOONGSON2) += dma.o # # Serial port support @@ -25,8 +26,3 @@ obj-$(CONFIG_CS5536) += cs5536/ # obj-$(CONFIG_SUSPEND) += pm.o - -# -# Big Memory (SWIOTLB) Support -# -obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c index f7c905e50dc4..92dc6bafc127 100644 --- a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c +++ b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c @@ -138,7 +138,7 @@ u32 pci_ohci_read_reg(int reg) break; case PCI_OHCI_INT_REG: _rdmsr(DIVIL_MSR_REG(PIC_YSEL_LOW), &hi, &lo); - if ((lo & 0x00000f00) == CS5536_USB_INTR) + if (((lo >> PIC_YSEL_LOW_USB_SHIFT) & 0xf) == CS5536_USB_INTR) conf_data = 1; break; default: diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c deleted file mode 100644 index 6a739f8ae110..000000000000 --- a/arch/mips/loongson64/common/dma-swiotlb.c +++ /dev/null @@ -1,109 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/mm.h> -#include <linux/init.h> -#include <linux/dma-mapping.h> -#include <linux/scatterlist.h> -#include <linux/swiotlb.h> -#include <linux/bootmem.h> - -#include <asm/bootinfo.h> -#include <boot_param.h> -#include <dma-coherence.h> - -static void *loongson_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) -{ - void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs); - - mb(); - return ret; -} - -static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size, - dir, attrs); - mb(); - return daddr; -} - -static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs); - mb(); - - return r; -} - -static void loongson_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction dir) -{ - swiotlb_sync_single_for_device(dev, dma_handle, size, dir); - mb(); -} - -static void loongson_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nents, - enum dma_data_direction dir) -{ - swiotlb_sync_sg_for_device(dev, sg, nents, dir); - mb(); -} - -static int loongson_dma_supported(struct device *dev, u64 mask) -{ - if (mask > DMA_BIT_MASK(loongson_sysconf.dma_mask_bits)) - return 0; - return swiotlb_dma_supported(dev, mask); -} - -dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) -{ - long nid; -#ifdef CONFIG_PHYS48_TO_HT40 - /* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from - * Loongson-3's 48bit address space and embed it into 40bit */ - nid = (paddr >> 44) & 0x3; - paddr = ((nid << 44) ^ paddr) | (nid << 37); -#endif - return paddr; -} - -phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr) -{ - long nid; -#ifdef CONFIG_PHYS48_TO_HT40 - /* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from - * Loongson-3's 48bit address space and embed it into 40bit */ - nid = (daddr >> 37) & 0x3; - daddr = ((nid << 37) ^ daddr) | (nid << 44); -#endif - return daddr; -} - -static const struct dma_map_ops loongson_dma_map_ops = { - .alloc = loongson_dma_alloc_coherent, - .free = swiotlb_free, - .map_page = loongson_dma_map_page, - .unmap_page = swiotlb_unmap_page, - .map_sg = loongson_dma_map_sg, - .unmap_sg = swiotlb_unmap_sg_attrs, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = loongson_dma_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = loongson_dma_sync_sg_for_device, - .mapping_error = swiotlb_dma_mapping_error, - .dma_supported = loongson_dma_supported, -}; - -void __init plat_swiotlb_setup(void) -{ - swiotlb_init(1); - mips_dma_map_ops = &loongson_dma_map_ops; -} diff --git a/arch/mips/loongson64/common/dma.c b/arch/mips/loongson64/common/dma.c new file mode 100644 index 000000000000..48f04126bde2 --- /dev/null +++ b/arch/mips/loongson64/common/dma.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/dma-direct.h> + +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + return paddr | 0x80000000; +} + +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr) +{ +#if defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT) + if (dma_addr > 0x8fffffff) + return dma_addr; + return dma_addr & 0x0fffffff; +#else + return dma_addr & 0x7fffffff; +#endif +} diff --git a/arch/mips/loongson64/common/early_printk.c b/arch/mips/loongson64/common/early_printk.c index 6ca632e529dc..a782e2b24747 100644 --- a/arch/mips/loongson64/common/early_printk.c +++ b/arch/mips/loongson64/common/early_printk.c @@ -10,6 +10,7 @@ * option) any later version. */ #include <linux/serial_reg.h> +#include <asm/setup.h> #include <loongson.h> diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c index 1e8a955ae5a8..8f68ee02a8c2 100644 --- a/arch/mips/loongson64/common/env.c +++ b/arch/mips/loongson64/common/env.c @@ -198,7 +198,8 @@ void __init prom_init_env(void) break; case PRID_REV_LOONGSON3A_R1: case PRID_REV_LOONGSON3A_R2: - case PRID_REV_LOONGSON3A_R3: + case PRID_REV_LOONGSON3A_R3_0: + case PRID_REV_LOONGSON3A_R3_1: cpu_clock_freq = 900000000; break; case PRID_REV_LOONGSON3B_R1: diff --git a/arch/mips/loongson64/loongson-3/Makefile b/arch/mips/loongson64/loongson-3/Makefile index 44bc1482158b..b5a0c2fa5446 100644 --- a/arch/mips/loongson64/loongson-3/Makefile +++ b/arch/mips/loongson64/loongson-3/Makefile @@ -1,7 +1,7 @@ # # Makefile for Loongson-3 family machines # -obj-y += irq.o cop2-ex.o platform.o acpi_init.o +obj-y += irq.o cop2-ex.o platform.o acpi_init.o dma.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/mips/loongson64/loongson-3/dma.c b/arch/mips/loongson64/loongson-3/dma.c new file mode 100644 index 000000000000..5e86635f71db --- /dev/null +++ b/arch/mips/loongson64/loongson-3/dma.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/dma-direct.h> +#include <linux/init.h> +#include <linux/swiotlb.h> + +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + /* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from + * Loongson-3's 48bit address space and embed it into 40bit */ + long nid = (paddr >> 44) & 0x3; + return ((nid << 44) ^ paddr) | (nid << 37); +} + +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr) +{ + /* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from + * Loongson-3's 48bit address space and embed it into 40bit */ + long nid = (daddr >> 37) & 0x3; + return ((nid << 37) ^ daddr) | (nid << 44); +} + +void __init plat_swiotlb_setup(void) +{ + swiotlb_init(1); +} diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 8501109bb0f0..fea95d003269 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -682,7 +682,8 @@ void play_dead(void) (void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead); break; case PRID_REV_LOONGSON3A_R2: - case PRID_REV_LOONGSON3A_R3: + case PRID_REV_LOONGSON3A_R3_0: + case PRID_REV_LOONGSON3A_R3_1: play_dead_at_ckseg1 = (void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead); break; diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile index c463bdad45c7..3e5bb203c95a 100644 --- a/arch/mips/mm/Makefile +++ b/arch/mips/mm/Makefile @@ -3,7 +3,7 @@ # Makefile for the Linux/MIPS-specific parts of the memory manager. # -obj-y += cache.o dma-default.o extable.o fault.o \ +obj-y += cache.o extable.o fault.o \ gup.o init.o mmap.o page.o page-funcs.o \ pgtable.o tlbex.o tlbex-fault.o tlb-funcs.o @@ -17,6 +17,7 @@ obj-$(CONFIG_32BIT) += ioremap.o pgtable-32.o obj-$(CONFIG_64BIT) += pgtable-64.o obj-$(CONFIG_HIGHMEM) += highmem.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o +obj-$(CONFIG_DMA_NONCOHERENT) += dma-noncoherent.o obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o obj-$(CONFIG_CPU_R3000) += c-r3k.o tlb-r3k.o diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index e12dfa48b478..a9ef057c79fe 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -830,12 +830,13 @@ static void r4k_flush_icache_user_range(unsigned long start, unsigned long end) return __r4k_flush_icache_range(start, end, true); } -#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT) +#ifdef CONFIG_DMA_NONCOHERENT static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) { /* Catch bad driver code */ - BUG_ON(size == 0); + if (WARN_ON(size == 0)) + return; preempt_disable(); if (cpu_has_inclusive_pcaches) { @@ -871,7 +872,8 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) { /* Catch bad driver code */ - BUG_ON(size == 0); + if (WARN_ON(size == 0)) + return; preempt_disable(); if (cpu_has_inclusive_pcaches) { @@ -904,7 +906,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) bc_inv(addr, size); __sync(); } -#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */ +#endif /* CONFIG_DMA_NONCOHERENT */ struct flush_cache_sigtramp_args { struct mm_struct *mm; @@ -1505,6 +1507,14 @@ static void probe_pcache(void) if (c->dcache.flags & MIPS_CACHE_PINDEX) c->dcache.flags &= ~MIPS_CACHE_ALIASES; + /* + * In systems with CM the icache fills from L2 or closer caches, and + * thus sees remote stores without needing to write them back any + * further than that. + */ + if (mips_cm_present()) + c->icache.flags |= MIPS_IC_SNOOPS_REMOTE; + switch (current_cpu_type()) { case CPU_20KC: /* diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 0d3c656feba0..70a523151ff3 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(local_flush_data_cache_page); EXPORT_SYMBOL(flush_data_cache_page); EXPORT_SYMBOL(flush_icache_all); -#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT) +#ifdef CONFIG_DMA_NONCOHERENT /* DMA cache operations. */ void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size); @@ -65,7 +65,7 @@ void (*_dma_cache_inv)(unsigned long start, unsigned long size); EXPORT_SYMBOL(_dma_cache_wback_inv); -#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */ +#endif /* CONFIG_DMA_NONCOHERENT */ /* * We could optimize the case where the cache argument is not BCACHE but diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c deleted file mode 100644 index f9fef0028ca2..000000000000 --- a/arch/mips/mm/dma-default.c +++ /dev/null @@ -1,404 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2000 Ani Joshi <ajoshi@unixbox.com> - * Copyright (C) 2000, 2001, 06 Ralf Baechle <ralf@linux-mips.org> - * swiped from i386, and cloned for MIPS by Geert, polished by Ralf. - */ - -#include <linux/types.h> -#include <linux/dma-mapping.h> -#include <linux/mm.h> -#include <linux/export.h> -#include <linux/scatterlist.h> -#include <linux/string.h> -#include <linux/gfp.h> -#include <linux/highmem.h> -#include <linux/dma-contiguous.h> - -#include <asm/cache.h> -#include <asm/cpu-type.h> -#include <asm/io.h> - -#include <dma-coherence.h> - -#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT) -/* User defined DMA coherency from command line. */ -enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT; -EXPORT_SYMBOL_GPL(coherentio); -int hw_coherentio = 0; /* Actual hardware supported DMA coherency setting. */ - -static int __init setcoherentio(char *str) -{ - coherentio = IO_COHERENCE_ENABLED; - pr_info("Hardware DMA cache coherency (command line)\n"); - return 0; -} -early_param("coherentio", setcoherentio); - -static int __init setnocoherentio(char *str) -{ - coherentio = IO_COHERENCE_DISABLED; - pr_info("Software DMA cache coherency (command line)\n"); - return 0; -} -early_param("nocoherentio", setnocoherentio); -#endif - -static inline struct page *dma_addr_to_page(struct device *dev, - dma_addr_t dma_addr) -{ - return pfn_to_page( - plat_dma_addr_to_phys(dev, dma_addr) >> PAGE_SHIFT); -} - -/* - * The affected CPUs below in 'cpu_needs_post_dma_flush()' can - * speculatively fill random cachelines with stale data at any time, - * requiring an extra flush post-DMA. - * - * Warning on the terminology - Linux calls an uncached area coherent; - * MIPS terminology calls memory areas with hardware maintained coherency - * coherent. - * - * Note that the R14000 and R16000 should also be checked for in this - * condition. However this function is only called on non-I/O-coherent - * systems and only the R10000 and R12000 are used in such systems, the - * SGI IP28 Indigo² rsp. SGI IP32 aka O2. - */ -static inline bool cpu_needs_post_dma_flush(struct device *dev) -{ - if (plat_device_is_coherent(dev)) - return false; - - switch (boot_cpu_type()) { - case CPU_R10000: - case CPU_R12000: - case CPU_BMIPS5000: - return true; - - default: - /* - * Presence of MAARs suggests that the CPU supports - * speculatively prefetching data, and therefore requires - * the post-DMA flush/invalidate. - */ - return cpu_has_maar; - } -} - -static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp) -{ - gfp_t dma_flag; - -#ifdef CONFIG_ISA - if (dev == NULL) - dma_flag = __GFP_DMA; - else -#endif -#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA) - if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(32)) - dma_flag = __GFP_DMA; - else if (dev->coherent_dma_mask < DMA_BIT_MASK(64)) - dma_flag = __GFP_DMA32; - else -#endif -#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA) - if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(64)) - dma_flag = __GFP_DMA32; - else -#endif -#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32) - if (dev == NULL || - dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8)) - dma_flag = __GFP_DMA; - else -#endif - dma_flag = 0; - - /* Don't invoke OOM killer */ - gfp |= __GFP_NORETRY; - - return gfp | dma_flag; -} - -static void *mips_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) -{ - void *ret; - struct page *page = NULL; - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; - - gfp = massage_gfp_flags(dev, gfp); - - if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp)) - page = dma_alloc_from_contiguous(dev, count, get_order(size), - gfp); - if (!page) - page = alloc_pages(gfp, get_order(size)); - - if (!page) - return NULL; - - ret = page_address(page); - memset(ret, 0, size); - *dma_handle = plat_map_dma_mem(dev, ret, size); - if (!(attrs & DMA_ATTR_NON_CONSISTENT) && - !plat_device_is_coherent(dev)) { - dma_cache_wback_inv((unsigned long) ret, size); - ret = UNCAC_ADDR(ret); - } - - return ret; -} - -static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - unsigned long addr = (unsigned long) vaddr; - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; - struct page *page = NULL; - - plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL); - - if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !plat_device_is_coherent(dev)) - addr = CAC_ADDR(addr); - - page = virt_to_page((void *) addr); - - if (!dma_release_from_contiguous(dev, page, count)) - __free_pages(page, get_order(size)); -} - -static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - unsigned long user_count = vma_pages(vma); - unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; - unsigned long addr = (unsigned long)cpu_addr; - unsigned long off = vma->vm_pgoff; - unsigned long pfn; - int ret = -ENXIO; - - if (!plat_device_is_coherent(dev)) - addr = CAC_ADDR(addr); - - pfn = page_to_pfn(virt_to_page((void *)addr)); - - if (attrs & DMA_ATTR_WRITE_COMBINE) - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); - else - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - - if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) - return ret; - - if (off < count && user_count <= (count - off)) { - ret = remap_pfn_range(vma, vma->vm_start, - pfn + off, - user_count << PAGE_SHIFT, - vma->vm_page_prot); - } - - return ret; -} - -static inline void __dma_sync_virtual(void *addr, size_t size, - enum dma_data_direction direction) -{ - switch (direction) { - case DMA_TO_DEVICE: - dma_cache_wback((unsigned long)addr, size); - break; - - case DMA_FROM_DEVICE: - dma_cache_inv((unsigned long)addr, size); - break; - - case DMA_BIDIRECTIONAL: - dma_cache_wback_inv((unsigned long)addr, size); - break; - - default: - BUG(); - } -} - -/* - * A single sg entry may refer to multiple physically contiguous - * pages. But we still need to process highmem pages individually. - * If highmem is not configured then the bulk of this loop gets - * optimized out. - */ -static inline void __dma_sync(struct page *page, - unsigned long offset, size_t size, enum dma_data_direction direction) -{ - size_t left = size; - - do { - size_t len = left; - - if (PageHighMem(page)) { - void *addr; - - if (offset + len > PAGE_SIZE) { - if (offset >= PAGE_SIZE) { - page += offset >> PAGE_SHIFT; - offset &= ~PAGE_MASK; - } - len = PAGE_SIZE - offset; - } - - addr = kmap_atomic(page); - __dma_sync_virtual(addr + offset, len, direction); - kunmap_atomic(addr); - } else - __dma_sync_virtual(page_address(page) + offset, - size, direction); - offset = 0; - page++; - left -= len; - } while (left); -} - -static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction, unsigned long attrs) -{ - if (cpu_needs_post_dma_flush(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - __dma_sync(dma_addr_to_page(dev, dma_addr), - dma_addr & ~PAGE_MASK, size, direction); - plat_post_dma_flush(dev); - plat_unmap_dma_mem(dev, dma_addr, size, direction); -} - -static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction direction, unsigned long attrs) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nents, i) { - if (!plat_device_is_coherent(dev) && - !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - __dma_sync(sg_page(sg), sg->offset, sg->length, - direction); -#ifdef CONFIG_NEED_SG_DMA_LENGTH - sg->dma_length = sg->length; -#endif - sg->dma_address = plat_map_dma_mem_page(dev, sg_page(sg)) + - sg->offset; - } - - return nents; -} - -static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction direction, - unsigned long attrs) -{ - if (!plat_device_is_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - __dma_sync(page, offset, size, direction); - - return plat_map_dma_mem_page(dev, page) + offset; -} - -static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, - int nhwentries, enum dma_data_direction direction, - unsigned long attrs) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nhwentries, i) { - if (!plat_device_is_coherent(dev) && - !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - direction != DMA_TO_DEVICE) - __dma_sync(sg_page(sg), sg->offset, sg->length, - direction); - plat_unmap_dma_mem(dev, sg->dma_address, sg->length, direction); - } -} - -static void mips_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) -{ - if (cpu_needs_post_dma_flush(dev)) - __dma_sync(dma_addr_to_page(dev, dma_handle), - dma_handle & ~PAGE_MASK, size, direction); - plat_post_dma_flush(dev); -} - -static void mips_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) -{ - if (!plat_device_is_coherent(dev)) - __dma_sync(dma_addr_to_page(dev, dma_handle), - dma_handle & ~PAGE_MASK, size, direction); -} - -static void mips_dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sglist, int nelems, - enum dma_data_direction direction) -{ - int i; - struct scatterlist *sg; - - if (cpu_needs_post_dma_flush(dev)) { - for_each_sg(sglist, sg, nelems, i) { - __dma_sync(sg_page(sg), sg->offset, sg->length, - direction); - } - } - plat_post_dma_flush(dev); -} - -static void mips_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sglist, int nelems, - enum dma_data_direction direction) -{ - int i; - struct scatterlist *sg; - - if (!plat_device_is_coherent(dev)) { - for_each_sg(sglist, sg, nelems, i) { - __dma_sync(sg_page(sg), sg->offset, sg->length, - direction); - } - } -} - -static int mips_dma_supported(struct device *dev, u64 mask) -{ - return plat_dma_supported(dev, mask); -} - -static void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction direction) -{ - BUG_ON(direction == DMA_NONE); - - if (!plat_device_is_coherent(dev)) - __dma_sync_virtual(vaddr, size, direction); -} - -static const struct dma_map_ops mips_default_dma_map_ops = { - .alloc = mips_dma_alloc_coherent, - .free = mips_dma_free_coherent, - .mmap = mips_dma_mmap, - .map_page = mips_dma_map_page, - .unmap_page = mips_dma_unmap_page, - .map_sg = mips_dma_map_sg, - .unmap_sg = mips_dma_unmap_sg, - .sync_single_for_cpu = mips_dma_sync_single_for_cpu, - .sync_single_for_device = mips_dma_sync_single_for_device, - .sync_sg_for_cpu = mips_dma_sync_sg_for_cpu, - .sync_sg_for_device = mips_dma_sync_sg_for_device, - .dma_supported = mips_dma_supported, - .cache_sync = mips_dma_cache_sync, -}; - -const struct dma_map_ops *mips_dma_map_ops = &mips_default_dma_map_ops; -EXPORT_SYMBOL(mips_dma_map_ops); diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c new file mode 100644 index 000000000000..2aca1236af36 --- /dev/null +++ b/arch/mips/mm/dma-noncoherent.c @@ -0,0 +1,208 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2000 Ani Joshi <ajoshi@unixbox.com> + * Copyright (C) 2000, 2001, 06 Ralf Baechle <ralf@linux-mips.org> + * swiped from i386, and cloned for MIPS by Geert, polished by Ralf. + */ +#include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> +#include <linux/dma-contiguous.h> +#include <linux/highmem.h> + +#include <asm/cache.h> +#include <asm/cpu-type.h> +#include <asm/dma-coherence.h> +#include <asm/io.h> + +#ifdef CONFIG_DMA_PERDEV_COHERENT +static inline int dev_is_coherent(struct device *dev) +{ + return dev->archdata.dma_coherent; +} +#else +static inline int dev_is_coherent(struct device *dev) +{ + switch (coherentio) { + default: + case IO_COHERENCE_DEFAULT: + return hw_coherentio; + case IO_COHERENCE_ENABLED: + return 1; + case IO_COHERENCE_DISABLED: + return 0; + } +} +#endif /* CONFIG_DMA_PERDEV_COHERENT */ + +/* + * The affected CPUs below in 'cpu_needs_post_dma_flush()' can speculatively + * fill random cachelines with stale data at any time, requiring an extra + * flush post-DMA. + * + * Warning on the terminology - Linux calls an uncached area coherent; MIPS + * terminology calls memory areas with hardware maintained coherency coherent. + * + * Note that the R14000 and R16000 should also be checked for in this condition. + * However this function is only called on non-I/O-coherent systems and only the + * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp. + * SGI IP32 aka O2. + */ +static inline bool cpu_needs_post_dma_flush(struct device *dev) +{ + if (dev_is_coherent(dev)) + return false; + + switch (boot_cpu_type()) { + case CPU_R10000: + case CPU_R12000: + case CPU_BMIPS5000: + return true; + default: + /* + * Presence of MAARs suggests that the CPU supports + * speculatively prefetching data, and therefore requires + * the post-DMA flush/invalidate. + */ + return cpu_has_maar; + } +} + +void *arch_dma_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + void *ret; + + ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs); + if (!ret) + return NULL; + + if (!dev_is_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT)) { + dma_cache_wback_inv((unsigned long) ret, size); + ret = (void *)UNCAC_ADDR(ret); + } + + return ret; +} + +void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_addr, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !dev_is_coherent(dev)) + cpu_addr = (void *)CAC_ADDR((unsigned long)cpu_addr); + dma_direct_free(dev, size, cpu_addr, dma_addr, attrs); +} + +int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + unsigned long user_count = vma_pages(vma); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned long addr = (unsigned long)cpu_addr; + unsigned long off = vma->vm_pgoff; + unsigned long pfn; + int ret = -ENXIO; + + if (!dev_is_coherent(dev)) + addr = CAC_ADDR(addr); + + pfn = page_to_pfn(virt_to_page((void *)addr)); + + if (attrs & DMA_ATTR_WRITE_COMBINE) + vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); + else + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + + if (off < count && user_count <= (count - off)) { + ret = remap_pfn_range(vma, vma->vm_start, + pfn + off, + user_count << PAGE_SHIFT, + vma->vm_page_prot); + } + + return ret; +} + +static inline void dma_sync_virt(void *addr, size_t size, + enum dma_data_direction dir) +{ + switch (dir) { + case DMA_TO_DEVICE: + dma_cache_wback((unsigned long)addr, size); + break; + + case DMA_FROM_DEVICE: + dma_cache_inv((unsigned long)addr, size); + break; + + case DMA_BIDIRECTIONAL: + dma_cache_wback_inv((unsigned long)addr, size); + break; + + default: + BUG(); + } +} + +/* + * A single sg entry may refer to multiple physically contiguous pages. But + * we still need to process highmem pages individually. If highmem is not + * configured then the bulk of this loop gets optimized out. + */ +static inline void dma_sync_phys(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) +{ + struct page *page = pfn_to_page(paddr >> PAGE_SHIFT); + unsigned long offset = paddr & ~PAGE_MASK; + size_t left = size; + + do { + size_t len = left; + + if (PageHighMem(page)) { + void *addr; + + if (offset + len > PAGE_SIZE) { + if (offset >= PAGE_SIZE) { + page += offset >> PAGE_SHIFT; + offset &= ~PAGE_MASK; + } + len = PAGE_SIZE - offset; + } + + addr = kmap_atomic(page); + dma_sync_virt(addr + offset, len, dir); + kunmap_atomic(addr); + } else + dma_sync_virt(page_address(page) + offset, size, dir); + offset = 0; + page++; + left -= len; + } while (left); +} + +void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) +{ + if (!dev_is_coherent(dev)) + dma_sync_phys(paddr, size, dir); +} + +void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) +{ + if (cpu_needs_post_dma_flush(dev)) + dma_sync_phys(paddr, size, dir); +} + +void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction direction) +{ + BUG_ON(direction == DMA_NONE); + + if (!dev_is_coherent(dev)) + dma_sync_virt(vaddr, size, direction); +} diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 5f71f2b903b7..73d8a0f0b810 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -43,7 +43,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, struct mm_struct *mm = tsk->mm; const int field = sizeof(unsigned long) * 2; int si_code; - int fault; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c index d5d02993aa21..56e4f8bffd4c 100644 --- a/arch/mips/mm/page.c +++ b/arch/mips/mm/page.c @@ -623,21 +623,6 @@ struct dmadscr { u64 pad_b; } ____cacheline_aligned_in_smp page_descr[DM_NUM_CHANNELS]; -void sb1_dma_init(void) -{ - int i; - - for (i = 0; i < DM_NUM_CHANNELS; i++) { - const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) | - V_DM_DSCR_BASE_RINGSZ(1); - void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE)); - - __raw_writeq(base_val, base_reg); - __raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg); - __raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg); - } -} - void clear_page(void *page) { u64 to_phys = CPHYSADDR((unsigned long)page); diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 79b9f2ad3ff5..49312a14cd17 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1509,7 +1509,7 @@ static void setup_pw(void) #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT write_c0_pwctl(1 << 6 | psn); #endif - write_c0_kpgd(swapper_pg_dir); + write_c0_kpgd((long)swapper_pg_dir); kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */ } diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c index 9bb6baa45da3..24e5b0d06899 100644 --- a/arch/mips/mm/uasm-micromips.c +++ b/arch/mips/mm/uasm-micromips.c @@ -19,7 +19,6 @@ #include <asm/inst.h> #include <asm/elf.h> #include <asm/bugs.h> -#define UASM_ISA _UASM_ISA_MICROMIPS #include <asm/uasm.h> #define RS_MASK 0x1f diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c index 9fea6c6bbf49..60ceb93c71a0 100644 --- a/arch/mips/mm/uasm-mips.c +++ b/arch/mips/mm/uasm-mips.c @@ -19,7 +19,6 @@ #include <asm/inst.h> #include <asm/elf.h> #include <asm/bugs.h> -#define UASM_ISA _UASM_ISA_CLASSIC #include <asm/uasm.h> #define RS_MASK 0x1f diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile index 63940bdce698..17c7fd471a27 100644 --- a/arch/mips/mti-malta/Makefile +++ b/arch/mips/mti-malta/Makefile @@ -13,11 +13,9 @@ obj-y += malta-init.o obj-y += malta-int.o obj-y += malta-memory.o obj-y += malta-platform.o -obj-y += malta-reset.o obj-y += malta-setup.o obj-y += malta-time.o obj-$(CONFIG_MIPS_CMP) += malta-amon.o -obj-$(CONFIG_MIPS_MALTA_PM) += malta-pm.o CFLAGS_malta-dtshim.o = -I$(src)/../../../scripts/dtc/libfdt diff --git a/arch/mips/mti-malta/malta-pm.c b/arch/mips/mti-malta/malta-pm.c deleted file mode 100644 index efbd659fb602..000000000000 --- a/arch/mips/mti-malta/malta-pm.c +++ /dev/null @@ -1,96 +0,0 @@ -/* - * Copyright (C) 2014 Imagination Technologies - * Author: Paul Burton <paul.burton@mips.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/io.h> -#include <linux/pci.h> - -#include <asm/mach-malta/malta-pm.h> - -static struct pci_bus *pm_pci_bus; -static resource_size_t pm_io_offset; - -int mips_pm_suspend(unsigned state) -{ - int spec_devid; - u16 sts; - - if (!pm_pci_bus || !pm_io_offset) - return -ENODEV; - - /* Ensure the power button status is clear */ - while (1) { - sts = inw(pm_io_offset + PIIX4_FUNC3IO_PMSTS); - if (!(sts & PIIX4_FUNC3IO_PMSTS_PWRBTN_STS)) - break; - outw(sts, pm_io_offset + PIIX4_FUNC3IO_PMSTS); - } - - /* Enable entry to suspend */ - outw(state | PIIX4_FUNC3IO_PMCNTRL_SUS_EN, - pm_io_offset + PIIX4_FUNC3IO_PMCNTRL); - - /* If the special cycle occurs too soon this doesn't work... */ - mdelay(10); - - /* - * The PIIX4 will enter the suspend state only after seeing a special - * cycle with the correct magic data on the PCI bus. Generate that - * cycle now. - */ - spec_devid = PCI_DEVID(0, PCI_DEVFN(0x1f, 0x7)); - pci_bus_write_config_dword(pm_pci_bus, spec_devid, 0, - PIIX4_SUSPEND_MAGIC); - - /* Give the system some time to power down */ - mdelay(1000); - - return 0; -} - -static int __init malta_pm_setup(void) -{ - struct pci_dev *dev; - int res, io_region = PCI_BRIDGE_RESOURCES; - - /* Find a reference to the PCI bus */ - pm_pci_bus = pci_find_next_bus(NULL); - if (!pm_pci_bus) { - pr_warn("malta-pm: failed to find reference to PCI bus\n"); - return -ENODEV; - } - - /* Find the PIIX4 PM device */ - dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID, - PCI_ANY_ID, NULL); - if (!dev) { - pr_warn("malta-pm: failed to find PIIX4 PM\n"); - return -ENODEV; - } - - /* Request access to the PIIX4 PM IO registers */ - res = pci_request_region(dev, io_region, "PIIX4 PM IO registers"); - if (res) { - pr_warn("malta-pm: failed to request PM IO registers (%d)\n", - res); - pci_dev_put(dev); - return -ENODEV; - } - - /* Find the offset to the PIIX4 PM IO registers */ - pm_io_offset = pci_resource_start(dev, io_region); - - pci_dev_put(dev); - return 0; -} - -late_initcall(malta_pm_setup); diff --git a/arch/mips/mti-malta/malta-reset.c b/arch/mips/mti-malta/malta-reset.c deleted file mode 100644 index dd6f62ad4417..000000000000 --- a/arch/mips/mti-malta/malta-reset.c +++ /dev/null @@ -1,30 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Carsten Langgaard, carstenl@mips.com - * Copyright (C) 1999,2000 MIPS Technologies, Inc. All rights reserved. - */ -#include <linux/io.h> -#include <linux/pm.h> -#include <linux/reboot.h> - -#include <asm/reboot.h> -#include <asm/mach-malta/malta-pm.h> - -static void mips_machine_power_off(void) -{ - mips_pm_suspend(PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF); - - pr_info("Failed to power down, resetting\n"); - machine_restart(NULL); -} - -static int __init mips_reboot_setup(void) -{ - pm_power_off = mips_machine_power_off; - - return 0; -} -arch_initcall(mips_reboot_setup); diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index 7b63914d2e58..5d4c5e5fbd69 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -26,6 +26,7 @@ #include <linux/screen_info.h> #include <linux/time.h> +#include <asm/dma-coherence.h> #include <asm/fw/fw.h> #include <asm/mach-malta/malta-dtshim.h> #include <asm/mips-cps.h> @@ -144,12 +145,6 @@ static int __init plat_enable_iocoherency(void) static void __init plat_setup_iocoherency(void) { -#ifdef CONFIG_DMA_NONCOHERENT - /* - * Kernel has been configured with software coherency - * but we might choose to turn it off and use hardware - * coherency instead. - */ if (plat_enable_iocoherency()) { if (coherentio == IO_COHERENCE_DISABLED) pr_info("Hardware DMA cache coherency disabled\n"); @@ -161,10 +156,6 @@ static void __init plat_setup_iocoherency(void) else pr_info("Software DMA cache coherency enabled\n"); } -#else - if (!plat_enable_iocoherency()) - panic("Hardware DMA cache coherency not supported!"); -#endif } static void __init pci_clock_check(void) @@ -226,29 +217,6 @@ static void __init bonito_quirks_setup(void) pr_info("Enabled Bonito debug mode\n"); } else BONITO_BONGENCFG &= ~BONITO_BONGENCFG_DEBUGMODE; - -#ifdef CONFIG_DMA_COHERENT - if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) { - BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN; - pr_info("Enabled Bonito CPU coherency\n"); - - argptr = fw_getcmdline(); - if (strstr(argptr, "iobcuncached")) { - BONITO_PCICACHECTRL &= ~BONITO_PCICACHECTRL_IOBCCOH_EN; - BONITO_PCIMEMBASECFG = BONITO_PCIMEMBASECFG & - ~(BONITO_PCIMEMBASECFG_MEMBASE0_CACHED | - BONITO_PCIMEMBASECFG_MEMBASE1_CACHED); - pr_info("Disabled Bonito IOBC coherency\n"); - } else { - BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_IOBCCOH_EN; - BONITO_PCIMEMBASECFG |= - (BONITO_PCIMEMBASECFG_MEMBASE0_CACHED | - BONITO_PCIMEMBASECFG_MEMBASE1_CACHED); - pr_info("Enabled Bonito IOBC coherency\n"); - } - } else - panic("Hardware DMA cache coherency not supported"); -#endif } void __init *plat_get_fdt(void) @@ -279,11 +247,6 @@ void __init plat_mem_setup(void) */ enable_dma(4); -#ifdef CONFIG_DMA_COHERENT - if (mips_revision_sconid != MIPS_REVISION_SCON_BONITO) - panic("Hardware DMA cache coherency not supported"); -#endif - if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO) bonito_quirks_setup(); diff --git a/arch/mips/netlogic/common/earlycons.c b/arch/mips/netlogic/common/earlycons.c index 769f93032c53..8f5bc1597550 100644 --- a/arch/mips/netlogic/common/earlycons.c +++ b/arch/mips/netlogic/common/earlycons.c @@ -36,6 +36,7 @@ #include <linux/serial_reg.h> #include <asm/mipsregs.h> +#include <asm/setup.h> #include <asm/netlogic/haldefs.h> #include <asm/netlogic/common.h> diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c index 856a6e6d296e..b5ba83f4c646 100644 --- a/arch/mips/netlogic/xlp/dt.c +++ b/arch/mips/netlogic/xlp/dt.c @@ -93,17 +93,3 @@ void __init device_tree_init(void) { unflatten_and_copy_device_tree(); } - -static struct of_device_id __initdata xlp_ids[] = { - { .compatible = "simple-bus", }, - {}, -}; - -int __init xlp8xx_ds_publish_devices(void) -{ - if (!of_have_populated_dt()) - return 0; - return of_platform_bus_probe(NULL, xlp_ids, NULL); -} - -device_initcall(xlp8xx_ds_publish_devices); diff --git a/arch/mips/paravirt/serial.c b/arch/mips/paravirt/serial.c index 02b665c02272..a37b6f9f0ede 100644 --- a/arch/mips/paravirt/serial.c +++ b/arch/mips/paravirt/serial.c @@ -9,16 +9,15 @@ #include <linux/kernel.h> #include <linux/virtio_console.h> #include <linux/kvm_para.h> +#include <asm/setup.h> /* * Emit one character to the boot console. */ -int prom_putchar(char c) +void prom_putchar(char c) { kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, 0 /* port 0 */, (unsigned long)&c, 1 /* len == 1 */); - - return 1; } #ifdef CONFIG_VIRTIO_CONSOLE diff --git a/arch/mips/pci/ops-bridge.c b/arch/mips/pci/ops-bridge.c index 57e1463fcd02..a1d2c4ae0d1b 100644 --- a/arch/mips/pci/ops-bridge.c +++ b/arch/mips/pci/ops-bridge.c @@ -167,7 +167,7 @@ oh_my_gawd: static int pci_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 * value) { - if (bus->number > 0) + if (!pci_is_root_bus(bus)) return pci_conf1_read_config(bus, devfn, where, size, value); return pci_conf0_read_config(bus, devfn, where, size, value); @@ -310,7 +310,7 @@ oh_my_gawd: static int pci_write_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 value) { - if (bus->number > 0) + if (!pci_is_root_bus(bus)) return pci_conf1_write_config(bus, devfn, where, size, value); return pci_conf0_write_config(bus, devfn, where, size, value); diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c index b4fa6413c4e5..c539d0d2b0cf 100644 --- a/arch/mips/pci/pci-ar2315.c +++ b/arch/mips/pci/pci-ar2315.c @@ -149,6 +149,13 @@ #define AR2315_PCI_HOST_SLOT 3 #define AR2315_PCI_HOST_DEVID ((0xff18 << 16) | PCI_VENDOR_ID_ATHEROS) +/* + * We need some arbitrary non-zero value to be programmed to the BAR1 register + * of PCI host controller to enable DMA. The same value should be used as the + * offset to calculate the physical address of DMA buffer for PCI devices. + */ +#define AR2315_PCI_HOST_SDRAM_BASEADDR 0x20000000 + /* ??? access BAR */ #define AR2315_PCI_HOST_MBAR0 0x10000000 /* RAM access BAR */ @@ -167,6 +174,23 @@ struct ar2315_pci_ctrl { struct resource io_res; }; +static inline dma_addr_t ar2315_dev_offset(struct device *dev) +{ + if (dev && dev_is_pci(dev)) + return AR2315_PCI_HOST_SDRAM_BASEADDR; + return 0; +} + +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + return paddr + ar2315_dev_offset(dev); +} + +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr - ar2315_dev_offset(dev); +} + static inline struct ar2315_pci_ctrl *ar2315_pci_bus_to_apc(struct pci_bus *bus) { struct pci_controller *hose = bus->sysdata; diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c index 1e23c8d587bd..64b58cc48a91 100644 --- a/arch/mips/pci/pci-ar724x.c +++ b/arch/mips/pci/pci-ar724x.c @@ -12,14 +12,18 @@ #include <linux/irq.h> #include <linux/pci.h> #include <linux/init.h> +#include <linux/delay.h> #include <linux/platform_device.h> #include <asm/mach-ath79/ath79.h> #include <asm/mach-ath79/ar71xx_regs.h> +#define AR724X_PCI_REG_APP 0x00 #define AR724X_PCI_REG_RESET 0x18 #define AR724X_PCI_REG_INT_STATUS 0x4c #define AR724X_PCI_REG_INT_MASK 0x50 +#define AR724X_PCI_APP_LTSSM_ENABLE BIT(0) + #define AR724X_PCI_RESET_LINK_UP BIT(0) #define AR724X_PCI_INT_DEV0 BIT(14) @@ -325,6 +329,37 @@ static void ar724x_pci_irq_init(struct ar724x_pci_controller *apc, apc); } +static void ar724x_pci_hw_init(struct ar724x_pci_controller *apc) +{ + u32 ppl, app; + int wait = 0; + + /* deassert PCIe host controller and PCIe PHY reset */ + ath79_device_reset_clear(AR724X_RESET_PCIE); + ath79_device_reset_clear(AR724X_RESET_PCIE_PHY); + + /* remove the reset of the PCIE PLL */ + ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG); + ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET; + ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl); + + /* deassert bypass for the PCIE PLL */ + ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG); + ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS; + ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl); + + /* set PCIE Application Control to ready */ + app = __raw_readl(apc->ctrl_base + AR724X_PCI_REG_APP); + app |= AR724X_PCI_APP_LTSSM_ENABLE; + __raw_writel(app, apc->ctrl_base + AR724X_PCI_REG_APP); + + /* wait up to 100ms for PHY link up */ + do { + mdelay(10); + wait++; + } while (wait < 10 && !ar724x_pci_check_link(apc)); +} + static int ar724x_pci_probe(struct platform_device *pdev) { struct ar724x_pci_controller *apc; @@ -383,6 +418,13 @@ static int ar724x_pci_probe(struct platform_device *pdev) apc->pci_controller.io_resource = &apc->io_res; apc->pci_controller.mem_resource = &apc->mem_res; + /* + * Do the full PCIE Root Complex Initialization Sequence if the PCIe + * host controller is in reset. + */ + if (ath79_reset_rr(AR724X_RESET_REG_RESET_MODULE) & AR724X_RESET_PCIE) + ar724x_pci_hw_init(apc); + apc->link_up = ar724x_pci_check_link(apc); if (!apc->link_up) dev_warn(&pdev->dev, "PCIe link is down\n"); diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c index 0f09eafa5e3a..c94a66070a60 100644 --- a/arch/mips/pci/pci-ip27.c +++ b/arch/mips/pci/pci-ip27.c @@ -11,6 +11,7 @@ #include <linux/export.h> #include <linux/pci.h> #include <linux/smp.h> +#include <linux/dma-direct.h> #include <asm/sn/arch.h> #include <asm/pci/bridge.h> #include <asm/paccess.h> @@ -182,6 +183,19 @@ int pcibios_plat_dev_init(struct pci_dev *dev) return 0; } +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus); + + return bc->baddr + paddr; +} + +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr & ~(0xffUL << 56); +} + /* * Device might live on a subordinate PCI bus. XXX Walk up the chain of buses * to find the slot number in sense of the bridge device register. @@ -200,17 +214,6 @@ static inline void pci_disable_swapping(struct pci_dev *dev) bridge->b_widget.w_tflush; /* Flush */ } -static inline void pci_enable_swapping(struct pci_dev *dev) -{ - struct bridge_controller *bc = BRIDGE_CONTROLLER(dev->bus); - bridge_t *bridge = bc->base; - int slot = PCI_SLOT(dev->devfn); - - /* Turn on byte swapping */ - bridge->b_device[slot].reg |= BRIDGE_DEV_SWAP_DIR; - bridge->b_widget.w_tflush; /* Flush */ -} - static void pci_fixup_ioc3(struct pci_dev *d) { pci_disable_swapping(d); diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c index 3e92a06fa772..5017d5843c5a 100644 --- a/arch/mips/pci/pci-octeon.c +++ b/arch/mips/pci/pci-octeon.c @@ -21,8 +21,6 @@ #include <asm/octeon/cvmx-pci-defs.h> #include <asm/octeon/pci-octeon.h> -#include <dma-coherence.h> - #define USE_OCTEON_INTERNAL_ARBITER /* @@ -166,8 +164,6 @@ int pcibios_plat_dev_init(struct pci_dev *dev) pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, dconfig); } - dev->dev.dma_ops = octeon_pci_dma_map_ops; - return 0; } diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 9632436d74d7..c2e94cf5ecda 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, phys_addr_t size = resource_size(rsrc); *start = fixup_bigphys_addr(rsrc->start, size); - *end = rsrc->start + size; + *end = rsrc->start + size - 1; } diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c index 87ba86bd8696..d919a0d813a1 100644 --- a/arch/mips/pci/pcie-octeon.c +++ b/arch/mips/pci/pcie-octeon.c @@ -94,8 +94,6 @@ union cvmx_pcie_address { static int cvmx_pcie_rc_initialize(int pcie_port); -#include <dma-coherence.h> - /** * Return the Core virtual base address for PCIe IO access. IOs are * read/written as an offset from this address. @@ -1239,14 +1237,14 @@ static int __cvmx_pcie_rc_initialize_gen2(int pcie_port) /* CN63XX Pass 1.0 errata G-14395 requires the QLM De-emphasis be programmed */ if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_0)) { if (pcie_port) { - union cvmx_ciu_qlm1 ciu_qlm; + union cvmx_ciu_qlm ciu_qlm; ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM1); ciu_qlm.s.txbypass = 1; ciu_qlm.s.txdeemph = 5; ciu_qlm.s.txmargin = 0x17; cvmx_write_csr(CVMX_CIU_QLM1, ciu_qlm.u64); } else { - union cvmx_ciu_qlm0 ciu_qlm; + union cvmx_ciu_qlm ciu_qlm; ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM0); ciu_qlm.s.txbypass = 1; ciu_qlm.s.txdeemph = 5; diff --git a/arch/mips/pic32/pic32mzda/early_console.c b/arch/mips/pic32/pic32mzda/early_console.c index d7b783463fac..8ed4961b1271 100644 --- a/arch/mips/pic32/pic32mzda/early_console.c +++ b/arch/mips/pic32/pic32mzda/early_console.c @@ -13,6 +13,7 @@ */ #include <asm/mach-pic32/pic32.h> #include <asm/fw/fw.h> +#include <asm/setup.h> #include "pic32mzda.h" #include "early_pin.h" @@ -157,7 +158,7 @@ void __init fw_init_early_console(char port) setup_early_console(port, baud); } -int prom_putchar(char c) +void prom_putchar(char c) { if (console_port >= 0) { while (__raw_readl( @@ -166,6 +167,4 @@ int prom_putchar(char c) __raw_writel(c, uart_base + U_TXR(console_port)); } - - return 1; } diff --git a/arch/mips/ralink/early_printk.c b/arch/mips/ralink/early_printk.c index 3c59ffe5f5f5..ecd30ddfb3db 100644 --- a/arch/mips/ralink/early_printk.c +++ b/arch/mips/ralink/early_printk.c @@ -10,6 +10,7 @@ #include <linux/serial_reg.h> #include <asm/addrspace.h> +#include <asm/setup.h> #ifdef CONFIG_SOC_RT288X #define EARLY_UART_BASE 0x300c00 @@ -68,7 +69,7 @@ static void find_uart_base(void) } } -void prom_putchar(unsigned char ch) +void prom_putchar(char ch) { if (!init_complete) { find_uart_base(); @@ -76,13 +77,13 @@ void prom_putchar(unsigned char ch) } if (IS_ENABLED(CONFIG_SOC_MT7621) || soc_is_mt7628()) { - uart_w32(ch, UART_TX); + uart_w32((unsigned char)ch, UART_TX); while ((uart_r32(UART_REG_LSR) & UART_LSR_THRE) == 0) ; } else { while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0) ; - uart_w32(ch, UART_REG_TX); + uart_w32((unsigned char)ch, UART_REG_TX); while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0) ; } diff --git a/arch/mips/sgi-ip27/ip27-console.c b/arch/mips/sgi-ip27/ip27-console.c index 45fdfbcbd4c6..6bdb48d41276 100644 --- a/arch/mips/sgi-ip27/ip27-console.c +++ b/arch/mips/sgi-ip27/ip27-console.c @@ -7,6 +7,7 @@ */ #include <asm/page.h> +#include <asm/setup.h> #include <asm/sn/addrs.h> #include <asm/sn/sn0/hub.h> #include <asm/sn/klconfig.h> diff --git a/arch/mips/sgi-ip32/Makefile b/arch/mips/sgi-ip32/Makefile index 60f0227425e7..4745cd94df11 100644 --- a/arch/mips/sgi-ip32/Makefile +++ b/arch/mips/sgi-ip32/Makefile @@ -4,4 +4,4 @@ # obj-y += ip32-berr.o ip32-irq.o ip32-platform.o ip32-setup.o ip32-reset.o \ - crime.o ip32-memory.o + crime.o ip32-memory.o ip32-dma.o diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c new file mode 100644 index 000000000000..fa7b17cb5385 --- /dev/null +++ b/arch/mips/sgi-ip32/ip32-dma.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org> + */ +#include <linux/dma-direct.h> +#include <asm/ip32/crime.h> + +/* + * Few notes. + * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M + * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for + * native-endian) + * 3. All other devices see memory as one big chunk at 0x40000000 + * 4. Non-PCI devices will pass NULL as struct device* + * + * Thus we translate differently, depending on device. + */ + +#define RAM_OFFSET_MASK 0x3fffffffUL + +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK; + + if (!dev) + dma_addr += CRIME_HI_MEM_BASE; + return dma_addr; +} + +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr) +{ + phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK; + + if (dma_addr >= 256*1024*1024) + paddr += CRIME_HI_MEM_BASE; + return paddr; +} diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig index f4dbce25bc6a..7ec278d72096 100644 --- a/arch/mips/sibyte/Kconfig +++ b/arch/mips/sibyte/Kconfig @@ -70,7 +70,6 @@ config SIBYTE_BCM1x55 config SIBYTE_SB1xxx_SOC bool - select DMA_COHERENT select IRQ_MIPS_CPU select SWAP_IO_SPACE select SYS_SUPPORTS_32BIT_KERNEL diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c index 115399202eab..092fb2a6ec4a 100644 --- a/arch/mips/sibyte/common/cfe.c +++ b/arch/mips/sibyte/common/cfe.c @@ -27,6 +27,7 @@ #include <asm/bootinfo.h> #include <asm/reboot.h> +#include <asm/setup.h> #include <asm/sibyte/board.h> #include <asm/smp-ops.h> diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index 1791a44ee570..f6d9182ef82a 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -20,6 +20,7 @@ #include <linux/err.h> #include <linux/gpio/driver.h> #include <linux/platform_device.h> +#include <linux/platform_data/txx9/ndfmc.h> #include <linux/serial_core.h> #include <linux/mtd/physmap.h> #include <linux/leds.h> @@ -32,10 +33,10 @@ #include <asm/reboot.h> #include <asm/r4kcache.h> #include <asm/sections.h> +#include <asm/setup.h> #include <asm/txx9/generic.h> #include <asm/txx9/pci.h> #include <asm/txx9tmr.h> -#include <asm/txx9/ndfmc.h> #include <asm/txx9/dmac.h> #ifdef CONFIG_CPU_TX49XX #include <asm/txx9/tx4938.h> diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c index 85d1795652da..17395d5d15ca 100644 --- a/arch/mips/txx9/generic/setup_tx4938.c +++ b/arch/mips/txx9/generic/setup_tx4938.c @@ -17,13 +17,13 @@ #include <linux/ptrace.h> #include <linux/mtd/physmap.h> #include <linux/platform_device.h> +#include <linux/platform_data/txx9/ndfmc.h> #include <asm/reboot.h> #include <asm/traps.h> #include <asm/txx9irq.h> #include <asm/txx9tmr.h> #include <asm/txx9pio.h> #include <asm/txx9/generic.h> -#include <asm/txx9/ndfmc.h> #include <asm/txx9/dmac.h> #include <asm/txx9/tx4938.h> diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c index 274928987a21..360c388f4c82 100644 --- a/arch/mips/txx9/generic/setup_tx4939.c +++ b/arch/mips/txx9/generic/setup_tx4939.c @@ -21,13 +21,13 @@ #include <linux/ptrace.h> #include <linux/mtd/physmap.h> #include <linux/platform_device.h> +#include <linux/platform_data/txx9/ndfmc.h> #include <asm/bootinfo.h> #include <asm/reboot.h> #include <asm/traps.h> #include <asm/txx9irq.h> #include <asm/txx9tmr.h> #include <asm/txx9/generic.h> -#include <asm/txx9/ndfmc.h> #include <asm/txx9/dmac.h> #include <asm/txx9/tx4939.h> diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index ce196046ac3e..34605ca21498 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -7,7 +7,13 @@ ccflags-vdso := \ $(filter -I%,$(KBUILD_CFLAGS)) \ $(filter -E%,$(KBUILD_CFLAGS)) \ $(filter -mmicromips,$(KBUILD_CFLAGS)) \ - $(filter -march=%,$(KBUILD_CFLAGS)) + $(filter -march=%,$(KBUILD_CFLAGS)) \ + -D__VDSO__ + +ifeq ($(cc-name),clang) +ccflags-vdso += $(filter --target=%,$(KBUILD_CFLAGS)) +endif + cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ -O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ @@ -38,6 +44,7 @@ endif # VDSO linker flags. VDSO_LDFLAGS := \ -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \ + $(addprefix -Wl$(comma),$(filter -E%,$(KBUILD_CFLAGS))) \ -nostdlib -shared \ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ $(call cc-ldoption, -Wl$(comma)--build-id) diff --git a/arch/mips/vdso/genvdso.h b/arch/mips/vdso/genvdso.h index 94334727059a..611b06f01a3c 100644 --- a/arch/mips/vdso/genvdso.h +++ b/arch/mips/vdso/genvdso.h @@ -15,8 +15,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso) ELF(Shdr) *shdr; char *shstrtab, *name; uint16_t sh_count, sh_entsize, i; - unsigned int local_gotno, symtabno, gotsym; - ELF(Dyn) *dyn = NULL; shdrs = vdso + FUNC(swap_uint)(ehdr->e_shoff); sh_count = swap_uint16(ehdr->e_shnum); @@ -41,9 +39,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso) "%s: '%s' contains relocation sections\n", program_name, path); return false; - case SHT_DYNAMIC: - dyn = vdso + FUNC(swap_uint)(shdr->sh_offset); - break; } /* Check for existing sections. */ @@ -61,52 +56,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso) } } - /* - * Ensure the GOT has no entries other than the standard 2, for the same - * reason we check that there's no relocation sections above. - * The standard two entries are: - * - Lazy resolver - * - Module pointer - */ - if (dyn) { - local_gotno = symtabno = gotsym = 0; - - while (FUNC(swap_uint)(dyn->d_tag) != DT_NULL) { - switch (FUNC(swap_uint)(dyn->d_tag)) { - /* - * This member holds the number of local GOT entries. - */ - case DT_MIPS_LOCAL_GOTNO: - local_gotno = FUNC(swap_uint)(dyn->d_un.d_val); - break; - /* - * This member holds the number of entries in the - * .dynsym section. - */ - case DT_MIPS_SYMTABNO: - symtabno = FUNC(swap_uint)(dyn->d_un.d_val); - break; - /* - * This member holds the index of the first dynamic - * symbol table entry that corresponds to an entry in - * the GOT. - */ - case DT_MIPS_GOTSYM: - gotsym = FUNC(swap_uint)(dyn->d_un.d_val); - break; - } - - dyn++; - } - - if (local_gotno > 2 || symtabno - gotsym) { - fprintf(stderr, - "%s: '%s' contains unexpected GOT entries\n", - program_name, path); - return false; - } - } - return true; } diff --git a/arch/mips/vr41xx/common/pmu.c b/arch/mips/vr41xx/common/pmu.c index 39a0db3e2b34..16e684b59875 100644 --- a/arch/mips/vr41xx/common/pmu.c +++ b/arch/mips/vr41xx/common/pmu.c @@ -17,6 +17,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/cpu.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/ioport.h> @@ -46,7 +47,7 @@ static void __iomem *pmu_base; #define pmu_read(offset) readw(pmu_base + (offset)) #define pmu_write(offset, value) writew((value), pmu_base + (offset)) -static void vr41xx_cpu_wait(void) +static void __cpuidle vr41xx_cpu_wait(void) { local_irq_disable(); if (!need_resched()) diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 34f7222c5efe..1d4248fa55e9 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -71,8 +71,6 @@ config FIX_EARLYCON_MEM config PGTABLE_LEVELS default 2 -source "init/Kconfig" - menu "System Type" source "arch/nds32/Kconfig.cpu" config NR_CPUS @@ -90,24 +88,5 @@ config NDS32_BUILTIN_DTB endmenu menu "Kernel Features" -source "kernel/Kconfig.preempt" -source "kernel/Kconfig.freezer" -source "mm/Kconfig" source "kernel/Kconfig.hz" endmenu - -menu "Executable file formats" -source "fs/Kconfig.binfmt" -endmenu - -source "net/Kconfig" -source "drivers/Kconfig" -source "fs/Kconfig" - -menu "Kernel hacking" -source "lib/Kconfig.debug" -endmenu - -source "security/Kconfig" -source "crypto/Kconfig" -source "lib/Kconfig" diff --git a/arch/nds32/Kconfig.debug b/arch/nds32/Kconfig.debug new file mode 100644 index 000000000000..22a162cd99e8 --- /dev/null +++ b/arch/nds32/Kconfig.debug @@ -0,0 +1 @@ +# dummy file, do not delete diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c index 9bdb7c3ecbb6..b740534b152c 100644 --- a/arch/nds32/mm/fault.c +++ b/arch/nds32/mm/fault.c @@ -73,7 +73,7 @@ void do_page_fault(unsigned long entry, unsigned long addr, struct mm_struct *mm; struct vm_area_struct *vma; int si_code; - int fault; + vm_fault_t fault; unsigned int mask = VM_READ | VM_WRITE | VM_EXEC; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 3d4ec88f1db1..f4ad1138e6b9 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 config NIOS2 def_bool y + select ARCH_HAS_SYNC_DMA_FOR_CPU + select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select ARCH_NO_SWAP + select DMA_NONCOHERENT_OPS select TIMER_OF select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS @@ -38,27 +42,16 @@ config HAS_DMA config FPU def_bool n -config SWAP - def_bool n - config RWSEM_GENERIC_SPINLOCK def_bool y config TRACE_IRQFLAGS_SUPPORT def_bool n -source "init/Kconfig" - menu "Kernel features" -source "kernel/Kconfig.preempt" - -source "kernel/Kconfig.freezer" - source "kernel/Kconfig.hz" -source "mm/Kconfig" - config FORCE_MAX_ZONEORDER int "Maximum zone order" range 9 20 @@ -195,23 +188,3 @@ config NIOS2_IO_REGION_BASE default "0xe0000000" endmenu - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "arch/nios2/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug index edfeef049a51..7a49f0d28d14 100644 --- a/arch/nios2/Kconfig.debug +++ b/arch/nios2/Kconfig.debug @@ -1,11 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" config TRACE_IRQFLAGS_SUPPORT def_bool y -source "lib/Kconfig.debug" - config DEBUG_STACK_USAGE bool "Enable stack utilization instrumentation" depends on DEBUG_KERNEL @@ -24,5 +21,3 @@ config EARLY_PRINTK This is useful for kernel debugging when your machine crashes very early before the console code is initialized. You should normally say N here, unless you want to debug such a crash. - -endmenu diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 64ed3d656956..8fde4fa2c34f 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -9,6 +9,7 @@ generic-y += current.h generic-y += device.h generic-y += div64.h generic-y += dma.h +generic-y += dma-mapping.h generic-y += emergency-restart.h generic-y += exec.h generic-y += extable.h diff --git a/arch/nios2/include/asm/dma-mapping.h b/arch/nios2/include/asm/dma-mapping.h deleted file mode 100644 index 6ceb92251da0..000000000000 --- a/arch/nios2/include/asm/dma-mapping.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * Copyright (C) 2011 Tobias Klauser <tklauser@distanz.ch> - * Copyright (C) 2009 Wind River Systems Inc - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file COPYING in the main directory of this - * archive for more details. - */ - -#ifndef _ASM_NIOS2_DMA_MAPPING_H -#define _ASM_NIOS2_DMA_MAPPING_H - -extern const struct dma_map_ops nios2_dma_ops; - -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return &nios2_dma_ops; -} - -#endif /* _ASM_NIOS2_DMA_MAPPING_H */ diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c index 4be815519dd4..4af9e5b5ba1c 100644 --- a/arch/nios2/mm/dma-mapping.c +++ b/arch/nios2/mm/dma-mapping.c @@ -12,18 +12,18 @@ #include <linux/types.h> #include <linux/mm.h> -#include <linux/export.h> #include <linux/string.h> -#include <linux/scatterlist.h> #include <linux/dma-mapping.h> #include <linux/io.h> #include <linux/cache.h> #include <asm/cacheflush.h> -static inline void __dma_sync_for_device(void *vaddr, size_t size, - enum dma_data_direction direction) +void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) { - switch (direction) { + void *vaddr = phys_to_virt(paddr); + + switch (dir) { case DMA_FROM_DEVICE: invalidate_dcache_range((unsigned long)vaddr, (unsigned long)(vaddr + size)); @@ -42,10 +42,12 @@ static inline void __dma_sync_for_device(void *vaddr, size_t size, } } -static inline void __dma_sync_for_cpu(void *vaddr, size_t size, - enum dma_data_direction direction) +void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) { - switch (direction) { + void *vaddr = phys_to_virt(paddr); + + switch (dir) { case DMA_BIDIRECTIONAL: case DMA_FROM_DEVICE: invalidate_dcache_range((unsigned long)vaddr, @@ -58,8 +60,8 @@ static inline void __dma_sync_for_cpu(void *vaddr, size_t size, } } -static void *nios2_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) { void *ret; @@ -80,125 +82,10 @@ static void *nios2_dma_alloc(struct device *dev, size_t size, return ret; } -static void nios2_dma_free(struct device *dev, size_t size, void *vaddr, +void arch_dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { unsigned long addr = (unsigned long) CAC_ADDR((unsigned long) vaddr); free_pages(addr, get_order(size)); } - -static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction direction, - unsigned long attrs) -{ - int i; - - for_each_sg(sg, sg, nents, i) { - void *addr = sg_virt(sg); - - if (!addr) - continue; - - sg->dma_address = sg_phys(sg); - - if (attrs & DMA_ATTR_SKIP_CPU_SYNC) - continue; - - __dma_sync_for_device(addr, sg->length, direction); - } - - return nents; -} - -static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction, - unsigned long attrs) -{ - void *addr = page_address(page) + offset; - - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - __dma_sync_for_device(addr, size, direction); - - return page_to_phys(page) + offset; -} - -static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address, - size_t size, enum dma_data_direction direction, - unsigned long attrs) -{ - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - __dma_sync_for_cpu(phys_to_virt(dma_address), size, direction); -} - -static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg, - int nhwentries, enum dma_data_direction direction, - unsigned long attrs) -{ - void *addr; - int i; - - if (direction == DMA_TO_DEVICE) - return; - - if (attrs & DMA_ATTR_SKIP_CPU_SYNC) - return; - - for_each_sg(sg, sg, nhwentries, i) { - addr = sg_virt(sg); - if (addr) - __dma_sync_for_cpu(addr, sg->length, direction); - } -} - -static void nios2_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction) -{ - __dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction); -} - -static void nios2_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction) -{ - __dma_sync_for_device(phys_to_virt(dma_handle), size, direction); -} - -static void nios2_dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sg, int nelems, - enum dma_data_direction direction) -{ - int i; - - /* Make sure that gcc doesn't leave the empty loop body. */ - for_each_sg(sg, sg, nelems, i) - __dma_sync_for_cpu(sg_virt(sg), sg->length, direction); -} - -static void nios2_dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nelems, - enum dma_data_direction direction) -{ - int i; - - /* Make sure that gcc doesn't leave the empty loop body. */ - for_each_sg(sg, sg, nelems, i) - __dma_sync_for_device(sg_virt(sg), sg->length, direction); - -} - -const struct dma_map_ops nios2_dma_ops = { - .alloc = nios2_dma_alloc, - .free = nios2_dma_free, - .map_page = nios2_dma_map_page, - .unmap_page = nios2_dma_unmap_page, - .map_sg = nios2_dma_map_sg, - .unmap_sg = nios2_dma_unmap_sg, - .sync_single_for_device = nios2_dma_sync_single_for_device, - .sync_single_for_cpu = nios2_dma_sync_single_for_cpu, - .sync_sg_for_cpu = nios2_dma_sync_sg_for_cpu, - .sync_sg_for_device = nios2_dma_sync_sg_for_device, -}; -EXPORT_SYMBOL(nios2_dma_ops); diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index b804dd06ea1c..24fd84cf6006 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -47,7 +47,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; int code = SEGV_MAPERR; - int fault; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; cause >>= 2; diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index 9ecad05bfc73..ed5f32d8fbd8 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -27,7 +27,6 @@ config OPENRISC select GENERIC_STRNLEN_USER select GENERIC_SMP_IDLE_THREAD select MODULES_USE_ELF_RELA - select MULTI_IRQ_HANDLER select HAVE_DEBUG_STACKOVERFLOW select OR1K_PIC select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1 @@ -36,6 +35,7 @@ config OPENRISC select ARCH_USE_QUEUED_RWLOCKS select OMPIC if SMP select ARCH_WANT_FRAME_POINTERS + select GENERIC_IRQ_MULTI_HANDLER config CPU_BIG_ENDIAN def_bool y @@ -69,13 +69,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config MULTI_IRQ_HANDLER - def_bool y - -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - menu "Processor type and features" choice @@ -147,8 +140,6 @@ config SMP If you don't know what to do here, say N. source kernel/Kconfig.hz -source kernel/Kconfig.preempt -source "mm/Kconfig" config OPENRISC_NO_SPR_SR_DSX bool "use SPR_SR_DSX software emulation" if OR1K_1200 @@ -206,27 +197,3 @@ config OPENRISC_ESR_EXCEPTION_BUG_CHECK endmenu endmenu - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - -menu "Kernel hacking" - -source "lib/Kconfig.debug" - -endmenu diff --git a/arch/openrisc/Kconfig.debug b/arch/openrisc/Kconfig.debug new file mode 100644 index 000000000000..22a162cd99e8 --- /dev/null +++ b/arch/openrisc/Kconfig.debug @@ -0,0 +1 @@ +# dummy file, do not delete diff --git a/arch/openrisc/Makefile b/arch/openrisc/Makefile index 89076a66eee2..70e06d34006c 100644 --- a/arch/openrisc/Makefile +++ b/arch/openrisc/Makefile @@ -19,7 +19,6 @@ KBUILD_DEFCONFIG := or1ksim_defconfig -LDFLAGS := OBJCOPYFLAGS := -O binary -R .note -R .comment -S LDFLAGS_vmlinux := LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h index 146e1660f00e..b589fac39b92 100644 --- a/arch/openrisc/include/asm/atomic.h +++ b/arch/openrisc/include/asm/atomic.h @@ -100,7 +100,7 @@ ATOMIC_OP(xor) * * This is often used through atomic_inc_not_zero() */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int old, tmp; @@ -119,7 +119,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return old; } -#define __atomic_add_unless __atomic_add_unless +#define atomic_fetch_add_unless atomic_fetch_add_unless #include <asm-generic/atomic.h> diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h index d29f7db53906..f9cd43a39d72 100644 --- a/arch/openrisc/include/asm/cmpxchg.h +++ b/arch/openrisc/include/asm/cmpxchg.h @@ -16,8 +16,9 @@ #ifndef __ASM_OPENRISC_CMPXCHG_H #define __ASM_OPENRISC_CMPXCHG_H +#include <linux/bits.h> +#include <linux/compiler.h> #include <linux/types.h> -#include <linux/bitops.h> #define __HAVE_ARCH_CMPXCHG 1 diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h index d9eee0a2b7b4..eb612b1865d2 100644 --- a/arch/openrisc/include/asm/irq.h +++ b/arch/openrisc/include/asm/irq.h @@ -24,6 +24,4 @@ #define NO_IRQ (-1) -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); - #endif /* __ASM_OPENRISC_IRQ_H__ */ diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c index 35e478a93116..5f9445effaf8 100644 --- a/arch/openrisc/kernel/irq.c +++ b/arch/openrisc/kernel/irq.c @@ -41,13 +41,6 @@ void __init init_IRQ(void) irqchip_init(); } -static void (*handle_arch_irq)(struct pt_regs *); - -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - handle_arch_irq = handle_irq; -} - void __irq_entry do_IRQ(struct pt_regs *regs) { handle_arch_irq(regs); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 9f011d16cc46..dc4dbafc1d83 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -53,7 +53,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, struct mm_struct *mm; struct vm_area_struct *vma; int si_code; - int fault; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; tsk = current; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 17526bebcbd2..8e6d83f79e72 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -11,7 +11,6 @@ config PARISC select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_WANTS_UBSAN_NO_NULL select ARCH_SUPPORTS_MEMORY_FAILURE select RTC_CLASS select RTC_DRV_GENERIC @@ -46,6 +45,7 @@ config PARISC select HAVE_ARCH_HASH select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK + select HAVE_REGS_AND_STACK_ACCESS_API select GENERIC_SCHED_CLOCK select HAVE_UNSTABLE_SCHED_CLOCK if SMP select GENERIC_CLOCKEVENTS @@ -129,10 +129,6 @@ config PGTABLE_LEVELS config SYS_SUPPORTS_HUGETLBFS def_bool y if PA20 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - menu "Processor type and features" @@ -188,6 +184,10 @@ config PA20 config PA11 def_bool y depends on PA7000 || PA7100LC || PA7200 || PA7300LC + select ARCH_HAS_SYNC_DMA_FOR_CPU + select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select DMA_NONCOHERENT_OPS + select DMA_NONCOHERENT_CACHE_SYNC config PREFETCH def_bool y @@ -195,7 +195,7 @@ config PREFETCH config MLONGCALLS bool "Enable the -mlong-calls compiler option for big kernels" - def_bool y if (!MODULES) + default y depends on PA8X00 help If you configure the kernel to include many drivers built-in instead @@ -327,9 +327,7 @@ config NODES_SHIFT default "3" depends on NEED_MULTIPLE_NODES -source "kernel/Kconfig.preempt" source "kernel/Kconfig.hz" -source "mm/Kconfig" config COMPAT def_bool y @@ -354,21 +352,6 @@ endmenu source "drivers/parisc/Kconfig" - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "arch/parisc/Kconfig.debug" - config SECCOMP def_bool y prompt "Enable seccomp to safely compute untrusted bytecode" @@ -384,9 +367,3 @@ config SECCOMP defined by each seccomp mode. If unsure, say Y. Only embedded should say N here. - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/parisc/Kconfig.debug b/arch/parisc/Kconfig.debug index fb3507f9b14a..1478ded0e247 100644 --- a/arch/parisc/Kconfig.debug +++ b/arch/parisc/Kconfig.debug @@ -1,9 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config TRACE_IRQFLAGS_SUPPORT def_bool y - -endmenu diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 60e6f07b7e32..e9c6385ef0d1 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -36,6 +36,7 @@ #define RP_OFFSET 16 #define FRAME_SIZE 128 #define CALLEE_REG_FRAME_SIZE 144 +#define REG_SZ 8 #define ASM_ULONG_INSN .dword #else /* CONFIG_64BIT */ #define LDREG ldw @@ -50,6 +51,7 @@ #define RP_OFFSET 20 #define FRAME_SIZE 64 #define CALLEE_REG_FRAME_SIZE 128 +#define REG_SZ 4 #define ASM_ULONG_INSN .word #endif diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 88bae6676c9b..118953d41763 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -77,30 +77,6 @@ static __inline__ int atomic_read(const atomic_t *v) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define ATOMIC_OP(op, c_op) \ static __inline__ void atomic_##op(int i, atomic_t *v) \ { \ @@ -160,28 +136,6 @@ ATOMIC_OPS(xor, ^=) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_inc(v) (atomic_add( 1,(v))) -#define atomic_dec(v) (atomic_add( -1,(v))) - -#define atomic_inc_return(v) (atomic_add_return( 1,(v))) -#define atomic_dec_return(v) (atomic_add_return( -1,(v))) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) - #define ATOMIC_INIT(i) { (i) } #ifdef CONFIG_64BIT @@ -264,72 +218,11 @@ atomic64_read(const atomic64_t *v) return READ_ONCE((v)->counter); } -#define atomic64_inc(v) (atomic64_add( 1,(v))) -#define atomic64_dec(v) (atomic64_add( -1,(v))) - -#define atomic64_inc_return(v) (atomic64_add_return( 1,(v))) -#define atomic64_dec_return(v) (atomic64_add_return( -1,(v))) - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) -#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i),(v)) == 0) - /* exported interface */ #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - -/* - * atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - #endif /* !CONFIG_64BIT */ diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h new file mode 100644 index 000000000000..dbaaca84f27f --- /dev/null +++ b/arch/parisc/include/asm/barrier.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_BARRIER_H +#define __ASM_BARRIER_H + +#ifndef __ASSEMBLY__ + +/* The synchronize caches instruction executes as a nop on systems in + which all memory references are performed in order. */ +#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory") + +#if defined(CONFIG_SMP) +#define mb() do { synchronize_caches(); } while (0) +#define rmb() mb() +#define wmb() mb() +#define dma_rmb() mb() +#define dma_wmb() mb() +#else +#define mb() barrier() +#define rmb() barrier() +#define wmb() barrier() +#define dma_rmb() barrier() +#define dma_wmb() barrier() +#endif + +#define __smp_mb() mb() +#define __smp_rmb() mb() +#define __smp_wmb() mb() + +#include <asm-generic/barrier.h> + +#endif /* !__ASSEMBLY__ */ +#endif /* __ASM_BARRIER_H */ diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h index 01e1fc057c83..44a9f97194aa 100644 --- a/arch/parisc/include/asm/dma-mapping.h +++ b/arch/parisc/include/asm/dma-mapping.h @@ -21,11 +21,6 @@ ** flush/purge and allocate "regular" cacheable pages for everything. */ -#ifdef CONFIG_PA11 -extern const struct dma_map_ops pcxl_dma_ops; -extern const struct dma_map_ops pcx_dma_ops; -#endif - extern const struct dma_map_ops *hppa_dma_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) diff --git a/arch/parisc/include/asm/linkage.h b/arch/parisc/include/asm/linkage.h index 9a69bf6fc4b6..49f6f3d772cc 100644 --- a/arch/parisc/include/asm/linkage.h +++ b/arch/parisc/include/asm/linkage.h @@ -18,9 +18,9 @@ #ifdef __ASSEMBLY__ #define ENTRY(name) \ - .export name !\ - ALIGN !\ -name: + ALIGN !\ +name: ASM_NL\ + .export name #ifdef CONFIG_64BIT #define ENDPROC(name) \ @@ -31,13 +31,18 @@ name: END(name) #endif -#define ENTRY_CFI(name) \ +#define ENTRY_CFI(name, ...) \ ENTRY(name) ASM_NL\ + .proc ASM_NL\ + .callinfo __VA_ARGS__ ASM_NL\ + .entry ASM_NL\ CFI_STARTPROC #define ENDPROC_CFI(name) \ - ENDPROC(name) ASM_NL\ - CFI_ENDPROC + CFI_ENDPROC ASM_NL\ + .exit ASM_NL\ + .procend ASM_NL\ + ENDPROC(name) #endif /* __ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/ptrace.h b/arch/parisc/include/asm/ptrace.h index 46da07670c2b..2a27b275ab09 100644 --- a/arch/parisc/include/asm/ptrace.h +++ b/arch/parisc/include/asm/ptrace.h @@ -25,4 +25,15 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->gr[20]; } +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->iaoq[0] = val; +} + +/* Query offset/name of register from its name/offset */ +extern int regs_query_register_offset(const char *name); +extern const char *regs_query_register_name(unsigned int offset); +#define MAX_REG_OFFSET (offsetof(struct pt_regs, ipsw)) + #endif diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index 6f84b6acc86e..8a63515f03bf 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -20,7 +20,6 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x, { volatile unsigned int *a; - mb(); a = __ldcw_align(x); while (__ldcw(a) == 0) while (*a == 0) @@ -30,17 +29,16 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x, local_irq_disable(); } else cpu_relax(); - mb(); } #define arch_spin_lock_flags arch_spin_lock_flags static inline void arch_spin_unlock(arch_spinlock_t *x) { volatile unsigned int *a; - mb(); + a = __ldcw_align(x); - *a = 1; mb(); + *a = 1; } static inline int arch_spin_trylock(arch_spinlock_t *x) @@ -48,10 +46,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *x) volatile unsigned int *a; int ret; - mb(); a = __ldcw_align(x); ret = __ldcw(a) != 0; - mb(); return ret; } diff --git a/arch/parisc/include/asm/unwind.h b/arch/parisc/include/asm/unwind.h index c73a3ee20226..f133b7efbebb 100644 --- a/arch/parisc/include/asm/unwind.h +++ b/arch/parisc/include/asm/unwind.h @@ -4,6 +4,9 @@ #include <linux/list.h> +/* Max number of levels to backtrace */ +#define MAX_UNWIND_ENTRIES 30 + /* From ABI specifications */ struct unwind_table_entry { unsigned int region_start; diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h index fc0df353ff0d..87245c584784 100644 --- a/arch/parisc/include/uapi/asm/errno.h +++ b/arch/parisc/include/uapi/asm/errno.h @@ -113,7 +113,6 @@ #define ELOOP 249 /* Too many symbolic links encountered */ #define ENOSYS 251 /* Function not implemented */ -#define ENOTSUP 252 /* Function not implemented (POSIX.4 / HPUX) */ #define ECANCELLED 253 /* aio request was canceled before complete (POSIX.4 / HPUX) */ #define ECANCELED ECANCELLED /* SuSv3 and Solaris wants one 'L' */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 1d0fdc3b5d22..061b9cf2a779 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -104,4 +104,7 @@ #define SO_ZEROCOPY 0x4035 +#define SO_TXTIME 0x4036 +#define SCM_TXTIME SO_TXTIME + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index e95207c0565e..c7508f5717fb 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -482,6 +482,8 @@ .macro tlb_unlock0 spc,tmp #ifdef CONFIG_SMP or,COND(=) %r0,\spc,%r0 + sync + or,COND(=) %r0,\spc,%r0 stw \spc,0(\tmp) #endif .endm @@ -764,7 +766,6 @@ END(fault_vector_11) #endif /* Fault vector is separately protected and *must* be on its own page */ .align PAGE_SIZE -ENTRY(end_fault_vector) .import handle_interruption,code .import do_cpu_irq_mask,code @@ -776,7 +777,6 @@ ENTRY(end_fault_vector) */ ENTRY_CFI(ret_from_kernel_thread) - /* Call schedule_tail first though */ BL schedule_tail, %r2 nop @@ -815,8 +815,9 @@ ENTRY_CFI(_switch_to) LDREG TASK_THREAD_INFO(%r25), %r25 bv %r0(%r2) mtctl %r25,%cr30 +ENDPROC_CFI(_switch_to) -_switch_to_ret: +ENTRY_CFI(_switch_to_ret) mtctl %r0, %cr0 /* Needed for single stepping */ callee_rest callee_rest_float @@ -824,7 +825,7 @@ _switch_to_ret: LDREG -RP_OFFSET(%r30), %r2 bv %r0(%r2) copy %r26, %r28 -ENDPROC_CFI(_switch_to) +ENDPROC_CFI(_switch_to_ret) /* * Common rfi return path for interruptions, kernel execve, and @@ -885,12 +886,14 @@ ENTRY_CFI(syscall_exit_rfi) STREG %r19,PT_SR5(%r16) STREG %r19,PT_SR6(%r16) STREG %r19,PT_SR7(%r16) +ENDPROC_CFI(syscall_exit_rfi) -intr_return: +ENTRY_CFI(intr_return) /* check for reschedule */ mfctl %cr30,%r1 LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */ bb,<,n %r19,31-TIF_NEED_RESCHED,intr_do_resched /* forward */ +ENDPROC_CFI(intr_return) .import do_notify_resume,code intr_check_sig: @@ -1046,7 +1049,6 @@ intr_extint: b do_cpu_irq_mask ldo R%intr_return(%r2), %r2 /* return to intr_return, not here */ -ENDPROC_CFI(syscall_exit_rfi) /* Generic interruptions (illegal insn, unaligned, page fault, etc) */ @@ -1997,12 +1999,9 @@ ENDPROC_CFI(syscall_exit) .align L1_CACHE_BYTES .globl mcount .type mcount, @function -ENTRY(mcount) +ENTRY_CFI(mcount, caller) _mcount: .export _mcount,data - .proc - .callinfo caller,frame=0 - .entry /* * The 64bit mcount() function pointer needs 4 dwords, of which the * first two are free. We optimize it here and put 2 instructions for @@ -2024,18 +2023,13 @@ ftrace_stub: .dword mcount .dword 0 /* code in head.S puts value of global gp here */ #endif - .exit - .procend -ENDPROC(mcount) +ENDPROC_CFI(mcount) #ifdef CONFIG_FUNCTION_GRAPH_TRACER .align 8 .globl return_to_handler .type return_to_handler, @function -ENTRY_CFI(return_to_handler) - .proc - .callinfo caller,frame=FRAME_SIZE - .entry +ENTRY_CFI(return_to_handler, caller,frame=FRAME_SIZE) .export parisc_return_to_handler,data parisc_return_to_handler: copy %r3,%r1 @@ -2074,8 +2068,6 @@ parisc_return_to_handler: bv %r0(%rp) #endif LDREGM -FRAME_SIZE(%sp),%r3 - .exit - .procend ENDPROC_CFI(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -2085,31 +2077,30 @@ ENDPROC_CFI(return_to_handler) #ifdef CONFIG_IRQSTACKS /* void call_on_stack(unsigned long param1, void *func, unsigned long new_stack) */ -ENTRY_CFI(call_on_stack) +ENTRY_CFI(call_on_stack, FRAME=2*FRAME_SIZE,CALLS,SAVE_RP,SAVE_SP) copy %sp, %r1 /* Regarding the HPPA calling conventions for function pointers, we assume the PIC register is not changed across call. For CONFIG_64BIT, the argument pointer is left to point at the argument region allocated for the call to call_on_stack. */ + + /* Switch to new stack. We allocate two frames. */ + ldo 2*FRAME_SIZE(%arg2), %sp # ifdef CONFIG_64BIT - /* Switch to new stack. We allocate two 128 byte frames. */ - ldo 256(%arg2), %sp /* Save previous stack pointer and return pointer in frame marker */ - STREG %rp, -144(%sp) + STREG %rp, -FRAME_SIZE-RP_OFFSET(%sp) /* Calls always use function descriptor */ LDREG 16(%arg1), %arg1 bve,l (%arg1), %rp - STREG %r1, -136(%sp) - LDREG -144(%sp), %rp + STREG %r1, -FRAME_SIZE-REG_SZ(%sp) + LDREG -FRAME_SIZE-RP_OFFSET(%sp), %rp bve (%rp) - LDREG -136(%sp), %sp + LDREG -FRAME_SIZE-REG_SZ(%sp), %sp # else - /* Switch to new stack. We allocate two 64 byte frames. */ - ldo 128(%arg2), %sp /* Save previous stack pointer and return pointer in frame marker */ - STREG %r1, -68(%sp) - STREG %rp, -84(%sp) + STREG %r1, -FRAME_SIZE-REG_SZ(%sp) + STREG %rp, -FRAME_SIZE-RP_OFFSET(%sp) /* Calls use function descriptor if PLABEL bit is set */ bb,>=,n %arg1, 30, 1f depwi 0,31,2, %arg1 @@ -2117,9 +2108,9 @@ ENTRY_CFI(call_on_stack) 1: be,l 0(%sr4,%arg1), %sr0, %r31 copy %r31, %rp - LDREG -84(%sp), %rp + LDREG -FRAME_SIZE-RP_OFFSET(%sp), %rp bv (%rp) - LDREG -68(%sp), %sp + LDREG -FRAME_SIZE-REG_SZ(%sp), %sp # endif /* CONFIG_64BIT */ ENDPROC_CFI(call_on_stack) #endif /* CONFIG_IRQSTACKS */ diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 22e6374ece44..f33bf2d306d6 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -44,10 +44,6 @@ .align 16 ENTRY_CFI(flush_tlb_all_local) - .proc - .callinfo NO_CALLS - .entry - /* * The pitlbe and pdtlbe instructions should only be used to * flush the entire tlb. Also, there needs to be no intervening @@ -189,18 +185,11 @@ fdtdone: 2: bv %r0(%r2) nop - - .exit - .procend ENDPROC_CFI(flush_tlb_all_local) .import cache_info,data ENTRY_CFI(flush_instruction_cache_local) - .proc - .callinfo NO_CALLS - .entry - load32 cache_info, %r1 /* Flush Instruction Cache */ @@ -256,18 +245,11 @@ fisync: mtsm %r22 /* restore I-bit */ bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_instruction_cache_local) .import cache_info, data ENTRY_CFI(flush_data_cache_local) - .proc - .callinfo NO_CALLS - .entry - load32 cache_info, %r1 /* Flush Data Cache */ @@ -324,9 +306,6 @@ fdsync: mtsm %r22 /* restore I-bit */ bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_data_cache_local) /* Macros to serialize TLB purge operations on SMP. */ @@ -353,6 +332,7 @@ ENDPROC_CFI(flush_data_cache_local) .macro tlb_unlock la,flags,tmp #ifdef CONFIG_SMP ldi 1,\tmp + sync stw \tmp,0(\la) mtsm \flags #endif @@ -361,10 +341,6 @@ ENDPROC_CFI(flush_data_cache_local) /* Clear page using kernel mapping. */ ENTRY_CFI(clear_page_asm) - .proc - .callinfo NO_CALLS - .entry - #ifdef CONFIG_64BIT /* Unroll the loop. */ @@ -423,18 +399,11 @@ ENTRY_CFI(clear_page_asm) #endif bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(clear_page_asm) /* Copy page using kernel mapping. */ ENTRY_CFI(copy_page_asm) - .proc - .callinfo NO_CALLS - .entry - #ifdef CONFIG_64BIT /* PA8x00 CPUs can consume 2 loads or 1 store per cycle. * Unroll the loop by hand and arrange insn appropriately. @@ -541,9 +510,6 @@ ENTRY_CFI(copy_page_asm) #endif bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(copy_page_asm) /* @@ -597,10 +563,6 @@ ENDPROC_CFI(copy_page_asm) */ ENTRY_CFI(copy_user_page_asm) - .proc - .callinfo NO_CALLS - .entry - /* Convert virtual `to' and `from' addresses to physical addresses. Move `from' physical address to non shadowed register. */ ldil L%(__PAGE_OFFSET), %r1 @@ -749,16 +711,9 @@ ENTRY_CFI(copy_user_page_asm) bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(copy_user_page_asm) ENTRY_CFI(clear_user_page_asm) - .proc - .callinfo NO_CALLS - .entry - tophys_r1 %r26 ldil L%(TMPALIAS_MAP_START), %r28 @@ -835,16 +790,9 @@ ENTRY_CFI(clear_user_page_asm) bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(clear_user_page_asm) ENTRY_CFI(flush_dcache_page_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%(TMPALIAS_MAP_START), %r28 #ifdef CONFIG_64BIT #if (TMPALIAS_MAP_START >= 0x80000000) @@ -902,16 +850,9 @@ ENTRY_CFI(flush_dcache_page_asm) sync bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_dcache_page_asm) ENTRY_CFI(flush_icache_page_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%(TMPALIAS_MAP_START), %r28 #ifdef CONFIG_64BIT #if (TMPALIAS_MAP_START >= 0x80000000) @@ -976,16 +917,9 @@ ENTRY_CFI(flush_icache_page_asm) sync bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_icache_page_asm) ENTRY_CFI(flush_kernel_dcache_page_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%dcache_stride, %r1 ldw R%dcache_stride(%r1), %r23 @@ -1019,16 +953,9 @@ ENTRY_CFI(flush_kernel_dcache_page_asm) sync bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_kernel_dcache_page_asm) ENTRY_CFI(purge_kernel_dcache_page_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%dcache_stride, %r1 ldw R%dcache_stride(%r1), %r23 @@ -1061,16 +988,9 @@ ENTRY_CFI(purge_kernel_dcache_page_asm) sync bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(purge_kernel_dcache_page_asm) ENTRY_CFI(flush_user_dcache_range_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%dcache_stride, %r1 ldw R%dcache_stride(%r1), %r23 ldo -1(%r23), %r21 @@ -1082,16 +1002,9 @@ ENTRY_CFI(flush_user_dcache_range_asm) sync bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_user_dcache_range_asm) ENTRY_CFI(flush_kernel_dcache_range_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%dcache_stride, %r1 ldw R%dcache_stride(%r1), %r23 ldo -1(%r23), %r21 @@ -1104,16 +1017,9 @@ ENTRY_CFI(flush_kernel_dcache_range_asm) syncdma bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_kernel_dcache_range_asm) ENTRY_CFI(purge_kernel_dcache_range_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%dcache_stride, %r1 ldw R%dcache_stride(%r1), %r23 ldo -1(%r23), %r21 @@ -1126,16 +1032,9 @@ ENTRY_CFI(purge_kernel_dcache_range_asm) syncdma bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(purge_kernel_dcache_range_asm) ENTRY_CFI(flush_user_icache_range_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%icache_stride, %r1 ldw R%icache_stride(%r1), %r23 ldo -1(%r23), %r21 @@ -1147,16 +1046,9 @@ ENTRY_CFI(flush_user_icache_range_asm) sync bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_user_icache_range_asm) ENTRY_CFI(flush_kernel_icache_page) - .proc - .callinfo NO_CALLS - .entry - ldil L%icache_stride, %r1 ldw R%icache_stride(%r1), %r23 @@ -1190,16 +1082,9 @@ ENTRY_CFI(flush_kernel_icache_page) sync bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(flush_kernel_icache_page) ENTRY_CFI(flush_kernel_icache_range_asm) - .proc - .callinfo NO_CALLS - .entry - ldil L%icache_stride, %r1 ldw R%icache_stride(%r1), %r23 ldo -1(%r23), %r21 @@ -1211,8 +1096,6 @@ ENTRY_CFI(flush_kernel_icache_range_asm) sync bv %r0(%r2) nop - .exit - .procend ENDPROC_CFI(flush_kernel_icache_range_asm) __INIT @@ -1222,10 +1105,6 @@ ENDPROC_CFI(flush_kernel_icache_range_asm) */ .align 256 ENTRY_CFI(disable_sr_hashing_asm) - .proc - .callinfo NO_CALLS - .entry - /* * Switch to real mode */ @@ -1307,9 +1186,6 @@ srdis_done: 2: bv %r0(%r2) nop - .exit - - .procend ENDPROC_CFI(disable_sr_hashing_asm) .end diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 6df07ce4f3c2..04c48f1ef3fb 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -21,13 +21,12 @@ #include <linux/init.h> #include <linux/gfp.h> #include <linux/mm.h> -#include <linux/pci.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/types.h> -#include <linux/scatterlist.h> -#include <linux/export.h> +#include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> #include <asm/cacheflush.h> #include <asm/dma.h> /* for DMA_CHUNK_SIZE */ @@ -395,7 +394,7 @@ pcxl_dma_init(void) __initcall(pcxl_dma_init); -static void *pa11_dma_alloc(struct device *dev, size_t size, +static void *pcxl_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { unsigned long vaddr; @@ -422,190 +421,60 @@ static void *pa11_dma_alloc(struct device *dev, size_t size, return (void *)vaddr; } -static void pa11_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) +static void *pcx_dma_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { - int order; - - order = get_order(size); - size = 1 << (order + PAGE_SHIFT); - unmap_uncached_pages((unsigned long)vaddr, size); - pcxl_free_range((unsigned long)vaddr, size); - free_pages((unsigned long)__va(dma_handle), order); -} + void *addr; -static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction, unsigned long attrs) -{ - void *addr = page_address(page) + offset; - BUG_ON(direction == DMA_NONE); + if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) + return NULL; - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - flush_kernel_dcache_range((unsigned long) addr, size); + addr = (void *)__get_free_pages(flag, get_order(size)); + if (addr) + *dma_handle = (dma_addr_t)virt_to_phys(addr); - return virt_to_phys(addr); + return addr; } -static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, - size_t size, enum dma_data_direction direction, - unsigned long attrs) +void *arch_dma_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { - BUG_ON(direction == DMA_NONE); - - if (attrs & DMA_ATTR_SKIP_CPU_SYNC) - return; - if (direction == DMA_TO_DEVICE) - return; - - /* - * For PCI_DMA_FROMDEVICE this flush is not necessary for the - * simple map/unmap case. However, it IS necessary if if - * pci_dma_sync_single_* has been called and the buffer reused. - */ - - flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), size); + if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) + return pcxl_dma_alloc(dev, size, dma_handle, gfp, attrs); + else + return pcx_dma_alloc(dev, size, dma_handle, gfp, attrs); } -static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction direction, - unsigned long attrs) +void arch_dma_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, unsigned long attrs) { - int i; - struct scatterlist *sg; - - BUG_ON(direction == DMA_NONE); + int order = get_order(size); - for_each_sg(sglist, sg, nents, i) { - unsigned long vaddr = (unsigned long)sg_virt(sg); + if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) { + size = 1 << (order + PAGE_SHIFT); + unmap_uncached_pages((unsigned long)vaddr, size); + pcxl_free_range((unsigned long)vaddr, size); - sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr); - sg_dma_len(sg) = sg->length; - - if (attrs & DMA_ATTR_SKIP_CPU_SYNC) - continue; - - flush_kernel_dcache_range(vaddr, sg->length); + vaddr = __va(dma_handle); } - return nents; -} - -static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction direction, - unsigned long attrs) -{ - int i; - struct scatterlist *sg; - - BUG_ON(direction == DMA_NONE); - - if (attrs & DMA_ATTR_SKIP_CPU_SYNC) - return; - - if (direction == DMA_TO_DEVICE) - return; - - /* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */ - - for_each_sg(sglist, sg, nents, i) - flush_kernel_vmap_range(sg_virt(sg), sg->length); -} - -static void pa11_dma_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction) -{ - BUG_ON(direction == DMA_NONE); - - flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), - size); -} - -static void pa11_dma_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction) -{ - BUG_ON(direction == DMA_NONE); - - flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), - size); + free_pages((unsigned long)vaddr, get_order(size)); } -static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction) +void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) { - int i; - struct scatterlist *sg; - - /* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */ - - for_each_sg(sglist, sg, nents, i) - flush_kernel_vmap_range(sg_virt(sg), sg->length); + flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); } -static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction) +void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) { - int i; - struct scatterlist *sg; - - /* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */ - - for_each_sg(sglist, sg, nents, i) - flush_kernel_vmap_range(sg_virt(sg), sg->length); + flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); } -static void pa11_dma_cache_sync(struct device *dev, void *vaddr, size_t size, +void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction) { flush_kernel_dcache_range((unsigned long)vaddr, size); } - -const struct dma_map_ops pcxl_dma_ops = { - .alloc = pa11_dma_alloc, - .free = pa11_dma_free, - .map_page = pa11_dma_map_page, - .unmap_page = pa11_dma_unmap_page, - .map_sg = pa11_dma_map_sg, - .unmap_sg = pa11_dma_unmap_sg, - .sync_single_for_cpu = pa11_dma_sync_single_for_cpu, - .sync_single_for_device = pa11_dma_sync_single_for_device, - .sync_sg_for_cpu = pa11_dma_sync_sg_for_cpu, - .sync_sg_for_device = pa11_dma_sync_sg_for_device, - .cache_sync = pa11_dma_cache_sync, -}; - -static void *pcx_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) -{ - void *addr; - - if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) - return NULL; - - addr = (void *)__get_free_pages(flag, get_order(size)); - if (addr) - *dma_handle = (dma_addr_t)virt_to_phys(addr); - - return addr; -} - -static void pcx_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t iova, unsigned long attrs) -{ - free_pages((unsigned long)vaddr, get_order(size)); - return; -} - -const struct dma_map_ops pcx_dma_ops = { - .alloc = pcx_dma_alloc, - .free = pcx_dma_free, - .map_page = pa11_dma_map_page, - .unmap_page = pa11_dma_unmap_page, - .map_sg = pa11_dma_map_sg, - .unmap_sg = pa11_dma_unmap_sg, - .sync_single_for_cpu = pa11_dma_sync_single_for_cpu, - .sync_single_for_device = pa11_dma_sync_single_for_device, - .sync_sg_for_cpu = pa11_dma_sync_sg_for_cpu, - .sync_sg_for_device = pa11_dma_sync_sg_for_device, - .cache_sync = pa11_dma_cache_sync, -}; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index b931745815e0..eb39e7e380d7 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -302,7 +302,7 @@ get_wchan(struct task_struct *p) ip = info.ip; if (!in_sched_functions(ip)) return ip; - } while (count++ < 16); + } while (count++ < MAX_UNWIND_ENTRIES); return 0; } diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 7aa1d4d0d444..2582df1c529b 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -676,3 +676,103 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) #endif return &user_parisc_native_view; } + + +/* HAVE_REGS_AND_STACK_ACCESS_API feature */ + +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_INDEX(r,i) {.name = #r#i, .offset = offsetof(struct pt_regs, r[i])} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_INDEX(gr,0), + REG_OFFSET_INDEX(gr,1), + REG_OFFSET_INDEX(gr,2), + REG_OFFSET_INDEX(gr,3), + REG_OFFSET_INDEX(gr,4), + REG_OFFSET_INDEX(gr,5), + REG_OFFSET_INDEX(gr,6), + REG_OFFSET_INDEX(gr,7), + REG_OFFSET_INDEX(gr,8), + REG_OFFSET_INDEX(gr,9), + REG_OFFSET_INDEX(gr,10), + REG_OFFSET_INDEX(gr,11), + REG_OFFSET_INDEX(gr,12), + REG_OFFSET_INDEX(gr,13), + REG_OFFSET_INDEX(gr,14), + REG_OFFSET_INDEX(gr,15), + REG_OFFSET_INDEX(gr,16), + REG_OFFSET_INDEX(gr,17), + REG_OFFSET_INDEX(gr,18), + REG_OFFSET_INDEX(gr,19), + REG_OFFSET_INDEX(gr,20), + REG_OFFSET_INDEX(gr,21), + REG_OFFSET_INDEX(gr,22), + REG_OFFSET_INDEX(gr,23), + REG_OFFSET_INDEX(gr,24), + REG_OFFSET_INDEX(gr,25), + REG_OFFSET_INDEX(gr,26), + REG_OFFSET_INDEX(gr,27), + REG_OFFSET_INDEX(gr,28), + REG_OFFSET_INDEX(gr,29), + REG_OFFSET_INDEX(gr,30), + REG_OFFSET_INDEX(gr,31), + REG_OFFSET_INDEX(sr,0), + REG_OFFSET_INDEX(sr,1), + REG_OFFSET_INDEX(sr,2), + REG_OFFSET_INDEX(sr,3), + REG_OFFSET_INDEX(sr,4), + REG_OFFSET_INDEX(sr,5), + REG_OFFSET_INDEX(sr,6), + REG_OFFSET_INDEX(sr,7), + REG_OFFSET_INDEX(iasq,0), + REG_OFFSET_INDEX(iasq,1), + REG_OFFSET_INDEX(iaoq,0), + REG_OFFSET_INDEX(iaoq,1), + REG_OFFSET_NAME(cr27), + REG_OFFSET_NAME(ksp), + REG_OFFSET_NAME(kpc), + REG_OFFSET_NAME(sar), + REG_OFFSET_NAME(iir), + REG_OFFSET_NAME(isr), + REG_OFFSET_NAME(ior), + REG_OFFSET_NAME(ipsw), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_query_register_name() - query register name from its offset + * @offset: the offset of a register in struct pt_regs. + * + * regs_query_register_name() returns the name of a register from its + * offset in struct pt_regs. If the @offset is invalid, this returns NULL; + */ +const char *regs_query_register_name(unsigned int offset) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (roff->offset == offset) + return roff->name; + return NULL; +} diff --git a/arch/parisc/kernel/real2.S b/arch/parisc/kernel/real2.S index cc9963421a19..2b16d8d6598f 100644 --- a/arch/parisc/kernel/real2.S +++ b/arch/parisc/kernel/real2.S @@ -35,12 +35,6 @@ real32_stack: real64_stack: .block 8192 -#ifdef CONFIG_64BIT -# define REG_SZ 8 -#else -# define REG_SZ 4 -#endif - #define N_SAVED_REGS 9 save_cr_space: diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 8d3a7b80ac42..4e87c35c22b7 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -97,14 +97,12 @@ void __init dma_ops_init(void) panic( "PA-RISC Linux currently only supports machines that conform to\n" "the PA-RISC 1.1 or 2.0 architecture specification.\n"); - case pcxs: - case pcxt: - hppa_dma_ops = &pcx_dma_ops; - break; case pcxl2: pa7300lc_init(); case pcxl: /* falls through */ - hppa_dma_ops = &pcxl_dma_ops; + case pcxs: + case pcxt: + hppa_dma_ops = &dma_noncoherent_ops; break; default: break; diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index e775f80ae28c..5f7e57fcaeef 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -629,11 +629,12 @@ cas_action: stw %r1, 4(%sr2,%r20) #endif /* The load and store could fail */ -1: ldw,ma 0(%r26), %r28 +1: ldw 0(%r26), %r28 sub,<> %r28, %r25, %r0 -2: stw,ma %r24, 0(%r26) +2: stw %r24, 0(%r26) /* Free lock */ - stw,ma %r20, 0(%sr2,%r20) + sync + stw %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG /* Clear thread register indicator */ stw %r0, 4(%sr2,%r20) @@ -647,6 +648,7 @@ cas_action: 3: /* Error occurred on load or store */ /* Free lock */ + sync stw %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG stw %r0, 4(%sr2,%r20) @@ -796,30 +798,30 @@ cas2_action: ldo 1(%r0),%r28 /* 8bit CAS */ -13: ldb,ma 0(%r26), %r29 +13: ldb 0(%r26), %r29 sub,= %r29, %r25, %r0 b,n cas2_end -14: stb,ma %r24, 0(%r26) +14: stb %r24, 0(%r26) b cas2_end copy %r0, %r28 nop nop /* 16bit CAS */ -15: ldh,ma 0(%r26), %r29 +15: ldh 0(%r26), %r29 sub,= %r29, %r25, %r0 b,n cas2_end -16: sth,ma %r24, 0(%r26) +16: sth %r24, 0(%r26) b cas2_end copy %r0, %r28 nop nop /* 32bit CAS */ -17: ldw,ma 0(%r26), %r29 +17: ldw 0(%r26), %r29 sub,= %r29, %r25, %r0 b,n cas2_end -18: stw,ma %r24, 0(%r26) +18: stw %r24, 0(%r26) b cas2_end copy %r0, %r28 nop @@ -827,10 +829,10 @@ cas2_action: /* 64bit CAS */ #ifdef CONFIG_64BIT -19: ldd,ma 0(%r26), %r29 +19: ldd 0(%r26), %r29 sub,*= %r29, %r25, %r0 b,n cas2_end -20: std,ma %r24, 0(%r26) +20: std %r24, 0(%r26) copy %r0, %r28 #else /* Compare first word */ @@ -848,7 +850,8 @@ cas2_action: cas2_end: /* Free lock */ - stw,ma %r20, 0(%sr2,%r20) + sync + stw %r20, 0(%sr2,%r20) /* Enable interrupts */ ssm PSW_SM_I, %r0 /* Return to userspace, set no error */ @@ -858,6 +861,7 @@ cas2_end: 22: /* Error occurred on load or store */ /* Free lock */ + sync stw %r20, 0(%sr2,%r20) ssm PSW_SM_I, %r0 ldo 1(%r0),%r28 diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 4309ad31a874..318815212518 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -172,7 +172,7 @@ static void do_show_stack(struct unwind_frame_info *info) int i = 1; printk(KERN_CRIT "Backtrace:\n"); - while (i <= 16) { + while (i <= MAX_UNWIND_ENTRIES) { if (unwind_once(info) < 0 || info->ip == 0) break; diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 2ef83d78eec4..5cdf13069dd9 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -13,7 +13,6 @@ #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> -#include <linux/kallsyms.h> #include <linux/sort.h> #include <linux/uaccess.h> @@ -117,7 +116,8 @@ unwind_table_init(struct unwind_table *table, const char *name, for (; start <= end; start++) { if (start < end && start->region_end > (start+1)->region_start) { - printk("WARNING: Out of order unwind entry! %p and %p\n", start, start+1); + pr_warn("Out of order unwind entry! %px and %px\n", + start, start+1); } start->region_start += base_addr; @@ -203,25 +203,60 @@ int __init unwind_init(void) return 0; } -#ifdef CONFIG_64BIT -#define get_func_addr(fptr) fptr[2] -#else -#define get_func_addr(fptr) fptr[0] -#endif - static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int frame_size) { - extern void handle_interruption(int, struct pt_regs *); - static unsigned long *hi = (unsigned long *)&handle_interruption; - - if (pc == get_func_addr(hi)) { + /* + * We have to use void * instead of a function pointer, because + * function pointers aren't a pointer to the function on 64-bit. + * Make them const so the compiler knows they live in .text + */ + extern void * const handle_interruption; + extern void * const ret_from_kernel_thread; + extern void * const syscall_exit; + extern void * const intr_return; + extern void * const _switch_to_ret; +#ifdef CONFIG_IRQSTACKS + extern void * const call_on_stack; +#endif /* CONFIG_IRQSTACKS */ + + if (pc == (unsigned long) &handle_interruption) { struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN); dbg("Unwinding through handle_interruption()\n"); info->prev_sp = regs->gr[30]; info->prev_ip = regs->iaoq[0]; + return 1; + } + + if (pc == (unsigned long) &ret_from_kernel_thread || + pc == (unsigned long) &syscall_exit) { + info->prev_sp = info->prev_ip = 0; + return 1; + } + + if (pc == (unsigned long) &intr_return) { + struct pt_regs *regs; + + dbg("Found intr_return()\n"); + regs = (struct pt_regs *)(info->sp - PT_SZ_ALGN); + info->prev_sp = regs->gr[30]; + info->prev_ip = regs->iaoq[0]; + info->rp = regs->gr[2]; + return 1; + } + + if (pc == (unsigned long) &_switch_to_ret) { + info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE; + info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET); + return 1; + } +#ifdef CONFIG_IRQSTACKS + if (pc == (unsigned long) &call_on_stack) { + info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ); + info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET); return 1; } +#endif return 0; } @@ -238,34 +273,8 @@ static void unwind_frame_regs(struct unwind_frame_info *info) if (e == NULL) { unsigned long sp; - dbg("Cannot find unwind entry for 0x%lx; forced unwinding\n", info->ip); - -#ifdef CONFIG_KALLSYMS - /* Handle some frequent special cases.... */ - { - char symname[KSYM_NAME_LEN]; - char *modname; - - kallsyms_lookup(info->ip, NULL, NULL, &modname, - symname); - - dbg("info->ip = 0x%lx, name = %s\n", info->ip, symname); - - if (strcmp(symname, "_switch_to_ret") == 0) { - info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE; - info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET); - dbg("_switch_to_ret @ %lx - setting " - "prev_sp=%lx prev_ip=%lx\n", - info->ip, info->prev_sp, - info->prev_ip); - return; - } else if (strcmp(symname, "ret_from_kernel_thread") == 0 || - strcmp(symname, "syscall_exit") == 0) { - info->prev_ip = info->prev_sp = 0; - return; - } - } -#endif + dbg("Cannot find unwind entry for %pS; forced unwinding\n", + (void *) info->ip); /* Since we are doing the unwinding blind, we don't know if we are adjusting the stack correctly or extracting the rp @@ -439,8 +448,8 @@ unsigned long return_address(unsigned int level) /* initialize unwind info */ asm volatile ("copy %%r30, %0" : "=r"(sp)); memset(&r, 0, sizeof(struct pt_regs)); - r.iaoq[0] = (unsigned long) current_text_addr(); - r.gr[2] = (unsigned long) __builtin_return_address(0); + r.iaoq[0] = _THIS_IP_; + r.gr[2] = _RET_IP_; r.gr[30] = sp; unwind_frame_init(&info, current, &r); diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S index d4fe19806d57..b53fb6fedf06 100644 --- a/arch/parisc/lib/lusercopy.S +++ b/arch/parisc/lib/lusercopy.S @@ -64,9 +64,6 @@ */ ENTRY_CFI(lclear_user) - .proc - .callinfo NO_CALLS - .entry comib,=,n 0,%r25,$lclu_done get_sr $lclu_loop: @@ -81,13 +78,9 @@ $lclu_done: ldo 1(%r25),%r25 ASM_EXCEPTIONTABLE_ENTRY(1b,2b) - - .exit ENDPROC_CFI(lclear_user) - .procend - /* * long lstrnlen_user(char *s, long n) * @@ -97,9 +90,6 @@ ENDPROC_CFI(lclear_user) */ ENTRY_CFI(lstrnlen_user) - .proc - .callinfo NO_CALLS - .entry comib,= 0,%r25,$lslen_nzero copy %r26,%r24 get_sr @@ -111,7 +101,6 @@ $lslen_loop: $lslen_done: bv %r0(%r2) sub %r26,%r24,%r28 - .exit $lslen_nzero: b $lslen_done @@ -125,9 +114,6 @@ $lslen_nzero: ENDPROC_CFI(lstrnlen_user) - .procend - - /* * unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len) @@ -186,10 +172,6 @@ ENDPROC_CFI(lstrnlen_user) save_len = r31 ENTRY_CFI(pa_memcpy) - .proc - .callinfo NO_CALLS - .entry - /* Last destination address */ add dst,len,end @@ -439,9 +421,6 @@ ENTRY_CFI(pa_memcpy) b .Lcopy_done 10: stw,ma t1,4(dstspc,dst) ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done) - - .exit ENDPROC_CFI(pa_memcpy) - .procend .end diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index a80117980fc2..c8e8b7c05558 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -262,7 +262,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, struct task_struct *tsk; struct mm_struct *mm; unsigned long acc_type; - int fault = 0; + vm_fault_t fault = 0; unsigned int flags; if (faulthandler_disabled()) diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 2607d2d33405..74842d28a7a1 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -19,7 +19,6 @@ #include <linux/gfp.h> #include <linux/delay.h> #include <linux/init.h> -#include <linux/pci.h> /* for hppa_dma_ops and pcxl_dma_ops */ #include <linux/initrd.h> #include <linux/swap.h> #include <linux/unistd.h> @@ -616,17 +615,13 @@ void __init mem_init(void) free_all_bootmem(); #ifdef CONFIG_PA11 - if (hppa_dma_ops == &pcxl_dma_ops) { + if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) { pcxl_dma_start = (unsigned long)SET_MAP_OFFSET(MAP_START); parisc_vmalloc_start = SET_MAP_OFFSET(pcxl_dma_start + PCXL_DMA_MAP_SIZE); - } else { - pcxl_dma_start = 0; - parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START); - } -#else - parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START); + } else #endif + parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START); mem_init_print_info(NULL); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 9f2b75fe2c2d..a80669209155 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -165,7 +165,7 @@ config PPC select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE - select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64 + select GENERIC_CPU_VULNERABILITIES if PPC_BARRIER_NOSPEC select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_SMP_IDLE_THREAD @@ -197,6 +197,7 @@ config PPC select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_KERNEL_GZIP + select HAVE_KERNEL_XZ if PPC_BOOK3S select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES @@ -225,6 +226,7 @@ config PPC select IRQ_DOMAIN select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA + select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE select NEED_SG_DMA_LENGTH select NO_BOOTMEM select OF @@ -240,6 +242,11 @@ config PPC # Please keep this list sorted alphabetically. # +config PPC_BARRIER_NOSPEC + bool + default y + depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E + config GENERIC_CSUM def_bool n @@ -383,10 +390,6 @@ config PGTABLE_LEVELS default 3 if PPC_64K_PAGES && !PPC_BOOK3S_64 default 4 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - source "arch/powerpc/sysdev/Kconfig" source "arch/powerpc/platforms/Kconfig" @@ -397,8 +400,6 @@ config HIGHMEM depends on PPC32 source kernel/Kconfig.hz -source kernel/Kconfig.preempt -source "fs/Kconfig.binfmt" config HUGETLB_PAGE_SIZE_VARIABLE bool @@ -641,8 +642,6 @@ config ILLEGAL_POINTER_VALUE default 0x5deadbeef0000000 if PPC64 default 0 -source "mm/Kconfig" - config ARCH_MEMORY_PROBE def_bool y depends on MEMORY_HOTPLUG @@ -884,9 +883,6 @@ config ZONE_DMA bool default y -config NEED_DMA_MAP_STATE - def_bool (PPC64 || NOT_COHERENT_CACHE) - config GENERIC_ISA_DMA bool depends on ISA_DMA_API @@ -1201,20 +1197,6 @@ endif config ARCH_RANDOM def_bool n -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "lib/Kconfig" - -source "arch/powerpc/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - config PPC_LIB_RHEAP bool diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index c45424c64e19..fd63cd914a74 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config PPC_DISABLE_WERROR bool "Don't build arch/powerpc code with -Werror" @@ -379,5 +376,3 @@ config PPC_FAST_ENDIAN_SWITCH depends on DEBUG_KERNEL && PPC_BOOK3S_64 help If you're unsure what this is, say N. - -endmenu diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index fb96206de317..8397c7bd5880 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -36,7 +36,7 @@ else KBUILD_DEFCONFIG := ppc64_defconfig endif -ifeq ($(CONFIG_PPC64),y) +ifdef CONFIG_PPC64 new_nm := $(shell if $(NM) --help 2>&1 | grep -- '--synthetic' > /dev/null; then echo y; else echo n; fi) ifeq ($(new_nm),y) @@ -74,7 +74,7 @@ KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o endif endif -ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) +ifdef CONFIG_CPU_LITTLE_ENDIAN KBUILD_CFLAGS += -mlittle-endian LDFLAGS += -EL LDEMULATION := lppc @@ -117,7 +117,7 @@ LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) LDFLAGS_vmlinux += $(call ld-option,--orphan-handling=warn) -ifeq ($(CONFIG_PPC64),y) +ifdef CONFIG_PPC64 ifeq ($(call cc-option-yn,-mcmodel=medium),y) # -mcmodel=medium breaks modules because it uses 32bit offsets from # the TOC pointer to create pointers where possible. Pointers into the @@ -134,7 +134,7 @@ endif endif CFLAGS-$(CONFIG_PPC64) := $(call cc-option,-mtraceback=no) -ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) +ifdef CONFIG_CPU_LITTLE_ENDIAN CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc)) AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2) else @@ -148,8 +148,8 @@ CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 $(MULTIPLEWORD) CFLAGS-$(CONFIG_PPC32) += $(call cc-option,-mno-readonly-in-sdata) -ifeq ($(CONFIG_PPC_BOOK3S_64),y) -ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) +ifdef CONFIG_PPC_BOOK3S_64 +ifdef CONFIG_CPU_LITTLE_ENDIAN CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=power8 CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power9,-mtune=power8) else @@ -164,16 +164,10 @@ ifdef CONFIG_MPROFILE_KERNEL CC_FLAGS_FTRACE := -pg -mprofile-kernel endif -CFLAGS-$(CONFIG_CELL_CPU) += $(call cc-option,-mcpu=cell) -CFLAGS-$(CONFIG_POWER5_CPU) += $(call cc-option,-mcpu=power5) -CFLAGS-$(CONFIG_POWER6_CPU) += $(call cc-option,-mcpu=power6) -CFLAGS-$(CONFIG_POWER7_CPU) += $(call cc-option,-mcpu=power7) -CFLAGS-$(CONFIG_POWER8_CPU) += $(call cc-option,-mcpu=power8) -CFLAGS-$(CONFIG_POWER9_CPU) += $(call cc-option,-mcpu=power9) -CFLAGS-$(CONFIG_PPC_8xx) += $(call cc-option,-mcpu=860) +CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU)) # Altivec option not allowed with e500mc64 in GCC. -ifeq ($(CONFIG_ALTIVEC),y) +ifdef CONFIG_ALTIVEC E5500_CPU := -mcpu=powerpc64 else E5500_CPU := $(call cc-option,-mcpu=e500mc64,-mcpu=powerpc64) @@ -181,8 +175,8 @@ endif CFLAGS-$(CONFIG_E5500_CPU) += $(E5500_CPU) CFLAGS-$(CONFIG_E6500_CPU) += $(call cc-option,-mcpu=e6500,$(E5500_CPU)) -ifeq ($(CONFIG_PPC32),y) -ifeq ($(CONFIG_PPC_E500MC),y) +ifdef CONFIG_PPC32 +ifdef CONFIG_PPC_E500MC CFLAGS-y += $(call cc-option,-mcpu=e500mc,-mcpu=powerpc) else CFLAGS-$(CONFIG_E500) += $(call cc-option,-mcpu=8540 -msoft-float,-mcpu=powerpc) @@ -204,7 +198,7 @@ else CHECKFLAGS += -D__LITTLE_ENDIAN__ endif -ifeq ($(CONFIG_476FPE_ERR46),y) +ifdef CONFIG_476FPE_ERR46 KBUILD_LDFLAGS_MODULE += --ppc476-workaround \ -T $(srctree)/arch/powerpc/platforms/44x/ppc476_modules.lds endif @@ -231,12 +225,12 @@ KBUILD_CFLAGS += $(call cc-option,-fno-dwarf2-cfi-asm) # often slow when they are implemented at all KBUILD_CFLAGS += $(call cc-option,-mno-string) -ifeq ($(CONFIG_6xx),y) +ifdef CONFIG_6xx KBUILD_CFLAGS += -mcpu=powerpc endif # Work around a gcc code-gen bug with -fno-omit-frame-pointer. -ifeq ($(CONFIG_FUNCTION_TRACER),y) +ifdef CONFIG_FUNCTION_TRACER KBUILD_CFLAGS += -mno-sched-epilog endif @@ -355,6 +349,21 @@ mpc86xx_smp_defconfig: $(call merge_into_defconfig,mpc86xx_basic_defconfig,\ 86xx-smp 86xx-hw fsl-emb-nonhw) +PHONY += ppc32_allmodconfig +ppc32_allmodconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/book3s_32.config \ + -f $(srctree)/Makefile allmodconfig + +PHONY += ppc64le_allmodconfig +ppc64le_allmodconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/le.config \ + -f $(srctree)/Makefile allmodconfig + +PHONY += ppc64_book3e_allmodconfig +ppc64_book3e_allmodconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/85xx-64bit.config \ + -f $(srctree)/Makefile allmodconfig + define archhelp @echo '* zImage - Build default images selected by kernel config' @echo ' zImage.* - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)' @@ -381,7 +390,7 @@ install: $(Q)$(MAKE) $(build)=$(boot) install vdso_install: -ifeq ($(CONFIG_PPC64),y) +ifdef CONFIG_PPC64 $(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso64 $@ endif $(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso32 $@ diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index deea20c334df..0fb96c26136f 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -354,7 +354,7 @@ image-$(CONFIG_AMIGAONE) += cuImage.amigaone # For 32-bit powermacs, build the COFF and miboot images # as well as the ELF images. -ifeq ($(CONFIG_PPC32),y) +ifdef CONFIG_PPC32 image-$(CONFIG_PPC_PMAC) += zImage.coff zImage.miboot endif diff --git a/arch/powerpc/boot/dts/ac14xx.dts b/arch/powerpc/boot/dts/ac14xx.dts index 83bcfd865167..0be5c4f3265d 100644 --- a/arch/powerpc/boot/dts/ac14xx.dts +++ b/arch/powerpc/boot/dts/ac14xx.dts @@ -176,12 +176,12 @@ clock-frequency = <400000>; at24@30 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x30>; }; at24@31 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x31>; }; @@ -191,42 +191,42 @@ }; at24@50 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x50>; }; at24@51 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x51>; }; at24@52 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x52>; }; at24@53 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x53>; }; at24@54 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x54>; }; at24@55 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x55>; }; at24@56 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x56>; }; at24@57 { - compatible = "at24,24c01"; + compatible = "atmel,24c01"; reg = <0x57>; }; diff --git a/arch/powerpc/boot/dts/fsl/kmcent2.dts b/arch/powerpc/boot/dts/fsl/kmcent2.dts index 5922c1ea0e96..3094df05f5ea 100644 --- a/arch/powerpc/boot/dts/fsl/kmcent2.dts +++ b/arch/powerpc/boot/dts/fsl/kmcent2.dts @@ -130,7 +130,7 @@ #size-cells = <0>; eeprom@54 { - compatible = "24c02"; + compatible = "atmel,24c02"; reg = <0x54>; pagesize = <2>; read-only; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi index abd01d466de4..9b6cf9149937 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi @@ -37,12 +37,13 @@ fman0: fman@400000 { #size-cells = <1>; cell-index = <0>; compatible = "fsl,fman"; - ranges = <0 0x400000 0x100000>; - reg = <0x400000 0x100000>; + ranges = <0 0x400000 0xfe000>; + reg = <0x400000 0xfe000>; interrupts = <96 2 0 0>, <16 2 1 1>; clocks = <&clockgen 3 0>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x40 0xc>; + ptimer-handle = <&ptp_timer0>; muram@0 { compatible = "fsl,fman-muram"; @@ -93,9 +94,11 @@ fman0: fman@400000 { reg = <0x87000 0x1000>; status = "disabled"; }; +}; - ptp_timer0: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer0: ptp-timer@4fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x4fe000 0x1000>; + interrupts = <96 2 0 0>; + clocks = <&clockgen 3 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi index debea75fd3f0..e95c11ff0417 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi @@ -37,12 +37,13 @@ fman1: fman@500000 { #size-cells = <1>; cell-index = <1>; compatible = "fsl,fman"; - ranges = <0 0x500000 0x100000>; - reg = <0x500000 0x100000>; + ranges = <0 0x500000 0xfe000>; + reg = <0x500000 0xfe000>; interrupts = <97 2 0 0>, <16 2 1 0>; clocks = <&clockgen 3 1>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x60 0xc>; + ptimer-handle = <&ptp_timer1>; muram@0 { compatible = "fsl,fman-muram"; @@ -93,9 +94,11 @@ fman1: fman@500000 { reg = <0x87000 0x1000>; status = "disabled"; }; +}; - ptp_timer1: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer1: ptp-timer@5fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x5fe000 0x1000>; + interrupts = <97 2 0 0>; + clocks = <&clockgen 3 1>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi index 3a20e0d1a6d2..d62b36c5a329 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi @@ -37,12 +37,13 @@ fman0: fman@400000 { #size-cells = <1>; cell-index = <0>; compatible = "fsl,fman"; - ranges = <0 0x400000 0x100000>; - reg = <0x400000 0x100000>; + ranges = <0 0x400000 0xfe000>; + reg = <0x400000 0xfe000>; interrupts = <96 2 0 0>, <16 2 1 1>; clocks = <&clockgen 3 0>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; + ptimer-handle = <&ptp_timer0>; muram@0 { compatible = "fsl,fman-muram"; @@ -98,9 +99,11 @@ fman0: fman@400000 { compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xfd000 0x1000>; }; +}; - ptp_timer0: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer0: ptp-timer@4fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x4fe000 0x1000>; + interrupts = <96 2 0 0>; + clocks = <&clockgen 3 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi index 82750ac944c7..310232460500 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi @@ -37,12 +37,13 @@ fman1: fman@500000 { #size-cells = <1>; cell-index = <1>; compatible = "fsl,fman"; - ranges = <0 0x500000 0x100000>; - reg = <0x500000 0x100000>; + ranges = <0 0x500000 0xfe000>; + reg = <0x500000 0xfe000>; interrupts = <97 2 0 0>, <16 2 1 0>; clocks = <&clockgen 3 1>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x820 0x10>; + ptimer-handle = <&ptp_timer1>; muram@0 { compatible = "fsl,fman-muram"; @@ -98,9 +99,11 @@ fman1: fman@500000 { compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xfd000 0x1000>; }; +}; - ptp_timer1: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer1: ptp-timer@5fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x5fe000 0x1000>; + interrupts = <97 2 0 0>; + clocks = <&clockgen 3 1>; }; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi index 7f60b6060176..c90702b04a53 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi @@ -37,12 +37,13 @@ fman0: fman@400000 { #size-cells = <1>; cell-index = <0>; compatible = "fsl,fman"; - ranges = <0 0x400000 0x100000>; - reg = <0x400000 0x100000>; + ranges = <0 0x400000 0xfe000>; + reg = <0x400000 0xfe000>; interrupts = <96 2 0 0>, <16 2 1 1>; clocks = <&clockgen 3 0>; clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; + ptimer-handle = <&ptp_timer0>; muram@0 { compatible = "fsl,fman-muram"; @@ -86,9 +87,11 @@ fman0: fman@400000 { compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xfd000 0x1000>; }; +}; - ptp_timer0: ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; +ptp_timer0: ptp-timer@4fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0x4fe000 0x1000>; + interrupts = <96 2 0 0>; + clocks = <&clockgen 3 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/t2080rdb.dts b/arch/powerpc/boot/dts/fsl/t2080rdb.dts index 836e4c965b22..55c0210a771d 100644 --- a/arch/powerpc/boot/dts/fsl/t2080rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t2080rdb.dts @@ -97,12 +97,12 @@ mdio@fd000 { xg_cs4315_phy1: ethernet-phy@c { - compatible = "ethernet-phy-ieee802.3-c45"; + compatible = "ethernet-phy-id13e5.1002"; reg = <0xc>; }; xg_cs4315_phy2: ethernet-phy@d { - compatible = "ethernet-phy-ieee802.3-c45"; + compatible = "ethernet-phy-id13e5.1002"; reg = <0xd>; }; diff --git a/arch/powerpc/boot/dts/fsl/t4240rdb.dts b/arch/powerpc/boot/dts/fsl/t4240rdb.dts index 15eb0a3f7290..a56a705d41f7 100644 --- a/arch/powerpc/boot/dts/fsl/t4240rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t4240rdb.dts @@ -267,22 +267,22 @@ mdio@fd000 { xfiphy1: ethernet-phy@10 { - compatible = "ethernet-phy-ieee802.3-c45"; + compatible = "ethernet-phy-id13e5.1002"; reg = <0x10>; }; xfiphy2: ethernet-phy@11 { - compatible = "ethernet-phy-ieee802.3-c45"; + compatible = "ethernet-phy-id13e5.1002"; reg = <0x11>; }; xfiphy3: ethernet-phy@13 { - compatible = "ethernet-phy-ieee802.3-c45"; + compatible = "ethernet-phy-id13e5.1002"; reg = <0x13>; }; xfiphy4: ethernet-phy@12 { - compatible = "ethernet-phy-ieee802.3-c45"; + compatible = "ethernet-phy-id13e5.1002"; reg = <0x12>; }; }; diff --git a/arch/powerpc/boot/dts/pdm360ng.dts b/arch/powerpc/boot/dts/pdm360ng.dts index 445b88114009..df1283b63d9b 100644 --- a/arch/powerpc/boot/dts/pdm360ng.dts +++ b/arch/powerpc/boot/dts/pdm360ng.dts @@ -98,7 +98,7 @@ fsl,preserve-clocking; eeprom@50 { - compatible = "at,24c01"; + compatible = "atmel,24c01"; reg = <0x50>; }; diff --git a/arch/powerpc/configs/book3s_32.config b/arch/powerpc/configs/book3s_32.config new file mode 100644 index 000000000000..8721eb7b1294 --- /dev/null +++ b/arch/powerpc/configs/book3s_32.config @@ -0,0 +1,2 @@ +CONFIG_PPC64=n +CONFIG_PPC_BOOK3S_32=y diff --git a/arch/powerpc/configs/dpaa.config b/arch/powerpc/configs/dpaa.config index 2fe76f5e938a..4ffacafe4036 100644 --- a/arch/powerpc/configs/dpaa.config +++ b/arch/powerpc/configs/dpaa.config @@ -2,3 +2,4 @@ CONFIG_FSL_DPAA=y CONFIG_FSL_PAMU=y CONFIG_FSL_FMAN=y CONFIG_FSL_DPAA_ETH=y +CONFIG_CORTINA_PHY=y diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index 10940533da71..f5c366b02828 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -78,7 +78,6 @@ CONFIG_GPIO_HLWD=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_GPIO=y # CONFIG_HWMON is not set -CONFIG_SSB_DEBUG=y CONFIG_FB=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y diff --git a/arch/powerpc/crypto/md5-asm.S b/arch/powerpc/crypto/md5-asm.S index 10cdf5bceebb..1834065362c7 100644 --- a/arch/powerpc/crypto/md5-asm.S +++ b/arch/powerpc/crypto/md5-asm.S @@ -11,6 +11,7 @@ */ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> +#include <asm/asm-compat.h> #define rHP r3 #define rWP r4 diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c index 92289679b4c4..7e44cec37bdb 100644 --- a/arch/powerpc/crypto/md5-glue.c +++ b/arch/powerpc/crypto/md5-glue.c @@ -139,7 +139,6 @@ static struct shash_alg alg = { .cra_name = "md5", .cra_driver_name= "md5-ppc", .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = MD5_HMAC_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/powerpc/crypto/sha1-powerpc-asm.S b/arch/powerpc/crypto/sha1-powerpc-asm.S index c8951ce0dcc4..23e248beff71 100644 --- a/arch/powerpc/crypto/sha1-powerpc-asm.S +++ b/arch/powerpc/crypto/sha1-powerpc-asm.S @@ -7,6 +7,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> +#include <asm/asm-compat.h> #ifdef __BIG_ENDIAN__ #define LWZ(rt, d, ra) \ diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c index f9ebc38d3fe7..9e1814d99318 100644 --- a/arch/powerpc/crypto/sha1-spe-glue.c +++ b/arch/powerpc/crypto/sha1-spe-glue.c @@ -185,7 +185,6 @@ static struct shash_alg alg = { .cra_name = "sha1", .cra_driver_name= "sha1-ppc-spe", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c index c154cebc1041..3911d5c254fa 100644 --- a/arch/powerpc/crypto/sha1.c +++ b/arch/powerpc/crypto/sha1.c @@ -132,7 +132,6 @@ static struct shash_alg alg = { .base = { .cra_name = "sha1", .cra_driver_name= "sha1-powerpc", - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c index 718a079dcdbf..6227888dcf7e 100644 --- a/arch/powerpc/crypto/sha256-spe-glue.c +++ b/arch/powerpc/crypto/sha256-spe-glue.c @@ -231,7 +231,6 @@ static struct shash_alg algs[2] = { { .cra_name = "sha256", .cra_driver_name= "sha256-ppc-spe", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -248,7 +247,6 @@ static struct shash_alg algs[2] = { { .cra_name = "sha224", .cra_driver_name= "sha224-ppc-spe", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/powerpc/include/asm/asm-405.h b/arch/powerpc/include/asm/asm-405.h new file mode 100644 index 000000000000..7270d3ae7c8e --- /dev/null +++ b/arch/powerpc/include/asm/asm-405.h @@ -0,0 +1,19 @@ +#ifndef _ASM_POWERPC_ASM_405_H +#define _ASM_POWERPC_ASM_405_H + +#include <asm/asm-const.h> + +#ifdef __KERNEL__ +#ifdef CONFIG_IBM405_ERR77 +/* Erratum #77 on the 405 means we need a sync or dcbt before every + * stwcx. The old ATOMIC_SYNC_FIX covered some but not all of this. + */ +#define PPC405_ERR77(ra,rb) stringify_in_c(dcbt ra, rb;) +#define PPC405_ERR77_SYNC stringify_in_c(sync;) +#else +#define PPC405_ERR77(ra,rb) +#define PPC405_ERR77_SYNC +#endif +#endif + +#endif /* _ASM_POWERPC_ASM_405_H */ diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index 7f2a7702596c..19b70c5b5f18 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -1,21 +1,10 @@ #ifndef _ASM_POWERPC_ASM_COMPAT_H #define _ASM_POWERPC_ASM_COMPAT_H +#include <asm/asm-const.h> #include <asm/types.h> #include <asm/ppc-opcode.h> -#ifdef __ASSEMBLY__ -# define stringify_in_c(...) __VA_ARGS__ -# define ASM_CONST(x) x -#else -/* This version of stringify will deal with commas... */ -# define __stringify_in_c(...) #__VA_ARGS__ -# define stringify_in_c(...) __stringify_in_c(__VA_ARGS__) " " -# define __ASM_CONST(x) x##UL -# define ASM_CONST(x) __ASM_CONST(x) -#endif - - #ifdef __powerpc64__ /* operations for longs and pointers */ @@ -70,17 +59,4 @@ #endif -#ifdef __KERNEL__ -#ifdef CONFIG_IBM405_ERR77 -/* Erratum #77 on the 405 means we need a sync or dcbt before every - * stwcx. The old ATOMIC_SYNC_FIX covered some but not all of this. - */ -#define PPC405_ERR77(ra,rb) stringify_in_c(dcbt ra, rb;) -#define PPC405_ERR77_SYNC stringify_in_c(sync;) -#else -#define PPC405_ERR77(ra,rb) -#define PPC405_ERR77_SYNC -#endif -#endif - #endif /* _ASM_POWERPC_ASM_COMPAT_H */ diff --git a/arch/powerpc/include/asm/asm-const.h b/arch/powerpc/include/asm/asm-const.h new file mode 100644 index 000000000000..082c1538c562 --- /dev/null +++ b/arch/powerpc/include/asm/asm-const.h @@ -0,0 +1,14 @@ +#ifndef _ASM_POWERPC_ASM_CONST_H +#define _ASM_POWERPC_ASM_CONST_H + +#ifdef __ASSEMBLY__ +# define stringify_in_c(...) __VA_ARGS__ +# define ASM_CONST(x) x +#else +/* This version of stringify will deal with commas... */ +# define __stringify_in_c(...) #__VA_ARGS__ +# define stringify_in_c(...) __stringify_in_c(__VA_ARGS__) " " +# define __ASM_CONST(x) x##UL +# define ASM_CONST(x) __ASM_CONST(x) +#endif +#endif /* _ASM_POWERPC_ASM_CONST_H */ diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 7841b8a60657..1f4691ce4126 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -48,8 +48,8 @@ void __trace_opal_exit(long opcode, unsigned long retval); /* VMX copying */ int enter_vmx_usercopy(void); int exit_vmx_usercopy(void); -int enter_vmx_copy(void); -void * exit_vmx_copy(void *dest); +int enter_vmx_ops(void); +void *exit_vmx_ops(void *dest); /* Traps */ long machine_check_early(struct pt_regs *regs); @@ -143,4 +143,11 @@ struct kvm_vcpu; void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); +/* Patch sites */ +extern s32 patch__call_flush_count_cache; +extern s32 patch__flush_count_cache_return; +extern s32 patch__memset_nocache, patch__memcpy_nocache; + +extern long flush_count_cache; + #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 682b3e6a1e21..52eafaf74054 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -10,6 +10,7 @@ #include <linux/types.h> #include <asm/cmpxchg.h> #include <asm/barrier.h> +#include <asm/asm-405.h> #define ATOMIC_INIT(i) { (i) } @@ -18,18 +19,11 @@ * a "bne-" instruction at the end, so an isync is enough as a acquire barrier * on the platform without lwsync. */ -#define __atomic_op_acquire(op, args...) \ -({ \ - typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory"); \ - __ret; \ -}) - -#define __atomic_op_release(op, args...) \ -({ \ - __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory"); \ - op##_relaxed(args); \ -}) +#define __atomic_acquire_fence() \ + __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory") static __inline__ int atomic_read(const atomic_t *v) { @@ -129,8 +123,6 @@ ATOMIC_OPS(xor, xor) #undef ATOMIC_OP_RETURN_RELAXED #undef ATOMIC_OP -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - static __inline__ void atomic_inc(atomic_t *v) { int t; @@ -145,6 +137,7 @@ static __inline__ void atomic_inc(atomic_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic_inc atomic_inc static __inline__ int atomic_inc_return_relaxed(atomic_t *v) { @@ -163,16 +156,6 @@ static __inline__ int atomic_inc_return_relaxed(atomic_t *v) return t; } -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - static __inline__ void atomic_dec(atomic_t *v) { int t; @@ -187,6 +170,7 @@ static __inline__ void atomic_dec(atomic_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic_dec atomic_dec static __inline__ int atomic_dec_return_relaxed(atomic_t *v) { @@ -218,7 +202,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** - * __atomic_add_unless - add unless the number is a given value + * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -226,13 +210,13 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) +static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int t; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER -"1: lwarx %0,0,%1 # __atomic_add_unless\n\ +"1: lwarx %0,0,%1 # atomic_fetch_add_unless\n\ cmpw 0,%0,%3 \n\ beq 2f \n\ add %0,%2,%0 \n" @@ -248,6 +232,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) return t; } +#define atomic_fetch_add_unless atomic_fetch_add_unless /** * atomic_inc_not_zero - increment unless the number is zero @@ -280,9 +265,6 @@ static __inline__ int atomic_inc_not_zero(atomic_t *v) } #define atomic_inc_not_zero(v) atomic_inc_not_zero((v)) -#define atomic_sub_and_test(a, v) (atomic_sub_return((a), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_dec_return((v)) == 0) - /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1, even if @@ -412,8 +394,6 @@ ATOMIC64_OPS(xor, xor) #undef ATOMIC64_OP_RETURN_RELAXED #undef ATOMIC64_OP -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) - static __inline__ void atomic64_inc(atomic64_t *v) { long t; @@ -427,6 +407,7 @@ static __inline__ void atomic64_inc(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic64_inc atomic64_inc static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) { @@ -444,16 +425,6 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v) return t; } -/* - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - static __inline__ void atomic64_dec(atomic64_t *v) { long t; @@ -467,6 +438,7 @@ static __inline__ void atomic64_dec(atomic64_t *v) : "r" (&v->counter) : "cc", "xer"); } +#define atomic64_dec atomic64_dec static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) { @@ -487,9 +459,6 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v) #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) - /* * Atomically test *v and decrement if it is greater than 0. * The function returns the old value of *v minus 1. @@ -513,6 +482,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) return t; } +#define atomic64_dec_if_positive atomic64_dec_if_positive #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic64_cmpxchg_relaxed(v, o, n) \ @@ -524,7 +494,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) /** - * atomic64_add_unless - add unless the number is a given value + * atomic64_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -532,13 +502,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) +static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { long t; __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER -"1: ldarx %0,0,%1 # __atomic_add_unless\n\ +"1: ldarx %0,0,%1 # atomic64_fetch_add_unless\n\ cmpd 0,%0,%3 \n\ beq 2f \n\ add %0,%2,%0 \n" @@ -551,8 +521,9 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) : "r" (&v->counter), "r" (a), "r" (u) : "cc", "memory"); - return t != u; + return t; } +#define atomic64_fetch_add_unless atomic64_fetch_add_unless /** * atomic_inc64_not_zero - increment unless the number is zero @@ -582,6 +553,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v) return t1 != 0; } +#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v)) #endif /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index f67b3f6e36be..fbe8df433019 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -5,6 +5,8 @@ #ifndef _ASM_POWERPC_BARRIER_H #define _ASM_POWERPC_BARRIER_H +#include <asm/asm-const.h> + /* * Memory barrier. * The sync instruction guarantees that all memory accesses initiated @@ -77,19 +79,25 @@ do { \ }) #ifdef CONFIG_PPC_BOOK3S_64 +#define NOSPEC_BARRIER_SLOT nop +#elif defined(CONFIG_PPC_FSL_BOOK3E) +#define NOSPEC_BARRIER_SLOT nop; nop +#endif + +#ifdef CONFIG_PPC_BARRIER_NOSPEC /* * Prevent execution of subsequent instructions until preceding branches have * been fully resolved and are no longer executing speculatively. */ -#define barrier_nospec_asm NOSPEC_BARRIER_FIXUP_SECTION; nop +#define barrier_nospec_asm NOSPEC_BARRIER_FIXUP_SECTION; NOSPEC_BARRIER_SLOT // This also acts as a compiler barrier due to the memory clobber. #define barrier_nospec() asm (stringify_in_c(barrier_nospec_asm) ::: "memory") -#else /* !CONFIG_PPC_BOOK3S_64 */ +#else /* !CONFIG_PPC_BARRIER_NOSPEC */ #define barrier_nospec_asm #define barrier_nospec() -#endif +#endif /* CONFIG_PPC_BARRIER_NOSPEC */ #include <asm-generic/barrier.h> diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index b750ffef83c7..ff71566dadee 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -45,6 +45,7 @@ #include <linux/compiler.h> #include <asm/asm-compat.h> #include <asm/synch.h> +#include <asm/asm-405.h> /* PPC bit number conversion */ #define PPC_BITLSHIFT(be) (BITS_PER_LONG - 1 - (be)) diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 02f5acd7ccc4..751cf931bb3f 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -84,17 +84,12 @@ * of RAM. -- Cort */ #define VMALLOC_OFFSET (0x1000000) /* 16M */ -#ifdef PPC_PIN_SIZE -#define VMALLOC_START (((_ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) -#else #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) -#endif #define VMALLOC_END ioremap_bot #ifndef __ASSEMBLY__ #include <linux/sched.h> #include <linux/threads.h> -#include <asm/io.h> /* For sub-arch specific PPC_PIN_SIZE */ extern unsigned long ioremap_bot; @@ -164,7 +159,6 @@ static inline unsigned long pte_update(pte_t *p, 1: lwarx %0,0,%3\n\ andc %1,%0,%4\n\ or %1,%1,%5\n" - PPC405_ERR77(0,%3) " stwcx. %1,0,%3\n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*p) @@ -186,7 +180,6 @@ static inline unsigned long long pte_update(pte_t *p, lwzx %0,0,%3\n\ andc %1,%L0,%5\n\ or %1,%1,%6\n" - PPC405_ERR77(0,%3) " stwcx. %1,0,%4\n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*p) diff --git a/arch/powerpc/include/asm/book3s/32/tlbflush.h b/arch/powerpc/include/asm/book3s/32/tlbflush.h new file mode 100644 index 000000000000..068085b709fb --- /dev/null +++ b/arch/powerpc/include/asm/book3s/32/tlbflush.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H +#define _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H + +#define MMU_NO_CONTEXT (0) +/* + * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx + */ +extern void flush_tlb_mm(struct mm_struct *mm); +extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr); +extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +static inline void local_flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ + flush_tlb_page(vma, vmaddr); +} +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + flush_tlb_mm(mm); +} + +#endif /* _ASM_POWERPC_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index c81793d47af9..f82ee8a3b561 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -137,10 +137,9 @@ extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index); shift = mmu_psize_defs[psize].shift; \ for (index = 0; vpn < __end; index++, \ vpn += (1L << (shift - VPN_SHIFT))) { \ - if (!__split || __rpte_sub_valid(rpte, index)) \ - do { + if (!__split || __rpte_sub_valid(rpte, index)) -#define pte_iterate_hashed_end() } while(0); } } while(0) +#define pte_iterate_hashed_end() } } while(0) #define pte_pagesize_index(mm, addr, pte) \ (((pte) & H_PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K) diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 0387b155f13d..d52a51b2ce7b 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -3,6 +3,8 @@ #define _ASM_POWERPC_BOOK3S_64_HASH_H #ifdef __KERNEL__ +#include <asm/asm-const.h> + /* * Common bits between 4K and 64K pages in a linux-style PTE. * Additional bits may be defined in pgtable-hash64-*.h diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index c459f937d484..50888388a359 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -32,26 +32,6 @@ static inline int hstate_get_psize(struct hstate *hstate) } } -#define arch_make_huge_pte arch_make_huge_pte -static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writable) -{ - unsigned long page_shift; - - if (!cpu_has_feature(CPU_FTR_POWER9_DD1)) - return entry; - - page_shift = huge_page_shift(hstate_vma(vma)); - /* - * We don't support 1G hugetlb pages yet. - */ - VM_WARN_ON(page_shift == mmu_psize_defs[MMU_PAGE_1G].shift); - if (page_shift == mmu_psize_defs[MMU_PAGE_2M].shift) - return __pte(pte_val(entry) | R_PAGE_LARGE); - else - return entry; -} - #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE static inline bool gigantic_page_supported(void) { diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 50ed64fba4ae..b3520b549cba 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -12,9 +12,9 @@ * 2 of the License, or (at your option) any later version. */ -#include <asm/asm-compat.h> #include <asm/page.h> #include <asm/bug.h> +#include <asm/asm-const.h> /* * This is necessary to get the definition of PGTABLE_RANGE which we @@ -364,6 +364,16 @@ static inline unsigned long hpte_new_to_old_r(unsigned long r) return r & ~HPTE_R_3_0_SSIZE_MASK; } +static inline unsigned long hpte_get_old_v(struct hash_pte *hptep) +{ + unsigned long hpte_v; + + hpte_v = be64_to_cpu(hptep->v); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r)); + return hpte_v; +} + /* * This function sets the AVPN and L fields of the HPTE appropriately * using the base page size and actual page size. @@ -487,6 +497,9 @@ extern void hpte_init_native(void); extern void slb_initialize(void); extern void slb_flush_and_rebolt(void); +void slb_flush_all_realmode(void); +void __slb_restore_bolted_realmode(void); +void slb_restore_bolted_realmode(void); extern void slb_vmalloc_update(void); extern void slb_set_size(u16 size); diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 01ee40f11f3a..391ed2c3b697 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -9,6 +9,7 @@ #include <linux/slab.h> #include <linux/cpumask.h> +#include <linux/kmemleak.h> #include <linux/percpu.h> struct vmemmap_backing { @@ -83,6 +84,13 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), pgtable_gfp_flags(mm, GFP_KERNEL)); /* + * Don't scan the PGD for pointers, it contains references to PUDs but + * those references are not full pointers and so can't be recognised by + * kmemleak. + */ + kmemleak_no_scan(pgd); + + /* * With hugetlb, we don't clear the second half of the page table. * If we share the same slab cache with the pmd or pud level table, * we need to make sure we zero out the full table on alloc. @@ -110,8 +118,19 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX), - pgtable_gfp_flags(mm, GFP_KERNEL)); + pud_t *pud; + + pud = kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX), + pgtable_gfp_flags(mm, GFP_KERNEL)); + /* + * Tell kmemleak to ignore the PUD, that means don't scan it for + * pointers and don't consider it a leak. PUDs are typically only + * referred to by their PGD, but kmemleak is not able to recognise those + * as pointers, leading to false leak reports. + */ + kmemleak_ignore(pud); + + return pud; } static inline void pud_free(struct mm_struct *mm, pud_t *pud) @@ -208,4 +227,11 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, #define check_pgt_cache() do { } while (0) +extern atomic_long_t direct_pages_count[MMU_PAGE_COUNT]; +static inline void update_page_count(int psize, long count) +{ + if (IS_ENABLED(CONFIG_PROC_FS)) + atomic_long_add(count, &direct_pages_count[psize]); +} + #endif /* _ASM_POWERPC_BOOK3S_64_PGALLOC_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 42aafba7a308..676118743a06 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -479,9 +479,8 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, { if (full && radix_enabled()) { /* - * Let's skip the DD1 style pte update here. We know that - * this is a full mm pte clear and hence can be sure there is - * no parallel set_pte. + * We know that this is a full mm pte clear and + * hence can be sure there is no parallel set_pte. */ return radix__ptep_get_and_clear_full(mm, addr, ptep, full); } diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index ef9f96742ce1..7d1a3d1543fc 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_PGTABLE_RADIX_H #define _ASM_POWERPC_PGTABLE_RADIX_H +#include <asm/asm-const.h> + #ifndef __ASSEMBLY__ #include <asm/cmpxchg.h> #endif @@ -12,12 +14,6 @@ #include <asm/book3s/64/radix-4k.h> #endif -/* - * For P9 DD1 only, we need to track whether the pte's huge. - */ -#define R_PAGE_LARGE _RPAGE_RSV1 - - #ifndef __ASSEMBLY__ #include <asm/book3s/64/tlbflush-radix.h> #include <asm/cpu_has_feature.h> @@ -36,6 +32,9 @@ #define RADIX_PUD_BAD_BITS 0x60000000000000e0UL #define RADIX_PGD_BAD_BITS 0x60000000000000e0UL +#define RADIX_PMD_SHIFT (PAGE_SHIFT + RADIX_PTE_INDEX_SIZE) +#define RADIX_PUD_SHIFT (RADIX_PMD_SHIFT + RADIX_PMD_INDEX_SIZE) +#define RADIX_PGD_SHIFT (RADIX_PUD_SHIFT + RADIX_PUD_INDEX_SIZE) /* * Size of EA range mapped by our pagetables. */ @@ -154,20 +153,7 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm, { unsigned long old_pte; - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { - - unsigned long new_pte; - - old_pte = __radix_pte_update(ptep, ~0ul, 0); - /* - * new value of pte - */ - new_pte = (old_pte | set) & ~clr; - radix__flush_tlb_pte_p9_dd1(old_pte, mm, addr); - if (new_pte) - __radix_pte_update(ptep, 0, new_pte); - } else - old_pte = __radix_pte_update(ptep, clr, set); + old_pte = __radix_pte_update(ptep, clr, set); if (!huge) assert_pte_locked(mm, addr); @@ -253,8 +239,6 @@ static inline int radix__pmd_trans_huge(pmd_t pmd) static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) { - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - return __pmd(pmd_val(pmd) | _PAGE_PTE | R_PAGE_LARGE); return __pmd(pmd_val(pmd) | _PAGE_PTE); } @@ -285,18 +269,14 @@ static inline unsigned long radix__get_tree_size(void) unsigned long rts_field; /* * We support 52 bits, hence: - * DD1 52-28 = 24, 0b11000 - * Others 52-31 = 21, 0b10101 + * bits 52 - 31 = 21, 0b10101 * RTS encoding details * bits 0 - 3 of rts -> bits 6 - 8 unsigned long * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long */ - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - rts_field = (0x3UL << 61); - else { - rts_field = (0x5UL << 5); /* 6 - 8 bits */ - rts_field |= (0x2UL << 61); - } + rts_field = (0x5UL << 5); /* 6 - 8 bits */ + rts_field |= (0x2UL << 61); + return rts_field; } diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index ef5c3f2994c9..1154a6dc6d26 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -48,8 +48,6 @@ extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmad extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr); extern void radix__flush_tlb_all(void); -extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm, - unsigned long address); extern void radix__flush_tlb_lpid_page(unsigned int lpid, unsigned long addr, diff --git a/arch/powerpc/include/asm/book3s/tlbflush.h b/arch/powerpc/include/asm/book3s/tlbflush.h new file mode 100644 index 000000000000..dec11de41055 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/tlbflush.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_TLBFLUSH_H +#define _ASM_POWERPC_BOOK3S_TLBFLUSH_H + +#ifdef CONFIG_PPC64 +#include <asm/book3s/64/tlbflush.h> +#else +#include <asm/book3s/32/tlbflush.h> +#endif + +#endif /* _ASM_POWERPC_BOOK3S_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 0d72ec75da63..d5a8d7bf0759 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -11,7 +11,6 @@ #include <linux/mm.h> #include <asm/cputable.h> -#include <asm/cpu_has_feature.h> /* * No cache flushing is required when address mappings are changed, diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index 9b001f1f6b32..27183871eb3b 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -5,8 +5,8 @@ #ifdef __KERNEL__ #include <linux/compiler.h> #include <asm/synch.h> -#include <asm/asm-compat.h> #include <linux/bug.h> +#include <asm/asm-405.h> #ifdef __BIG_ENDIAN #define BITOFF_CAL(size, off) ((sizeof(u32) - size - off) * BITS_PER_BYTE) diff --git a/arch/powerpc/include/asm/code-patching-asm.h b/arch/powerpc/include/asm/code-patching-asm.h new file mode 100644 index 000000000000..ed7b1448493a --- /dev/null +++ b/arch/powerpc/include/asm/code-patching-asm.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2018, Michael Ellerman, IBM Corporation. + */ +#ifndef _ASM_POWERPC_CODE_PATCHING_ASM_H +#define _ASM_POWERPC_CODE_PATCHING_ASM_H + +/* Define a "site" that can be patched */ +.macro patch_site label name + .pushsection ".rodata" + .balign 4 + .global \name +\name: + .4byte \label - . + .popsection +.endm + +#endif /* _ASM_POWERPC_CODE_PATCHING_ASM_H */ diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 812535f40124..31733a95bbd0 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -14,6 +14,7 @@ #include <asm/ppc-opcode.h> #include <linux/string.h> #include <linux/kallsyms.h> +#include <asm/asm-compat.h> /* Flags for create_branch: * "b" == create_branch(addr, target, 0); @@ -32,6 +33,8 @@ unsigned int create_cond_branch(const unsigned int *addr, int patch_branch(unsigned int *addr, unsigned long target, int flags); int patch_instruction(unsigned int *addr, unsigned int instr); int raw_patch_instruction(unsigned int *addr, unsigned int instr); +int patch_instruction_site(s32 *addr, unsigned int instr); +int patch_branch_site(s32 *site, unsigned long target, int flags); int instr_is_relative_branch(unsigned int instr); int instr_is_relative_link_branch(unsigned int instr); diff --git a/arch/powerpc/include/asm/copro.h b/arch/powerpc/include/asm/copro.h index ce216df31381..48616fe7ea75 100644 --- a/arch/powerpc/include/asm/copro.h +++ b/arch/powerpc/include/asm/copro.h @@ -10,13 +10,15 @@ #ifndef _ASM_POWERPC_COPRO_H #define _ASM_POWERPC_COPRO_H +#include <linux/mm_types.h> + struct copro_slb { u64 esid, vsid; }; int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, - unsigned long dsisr, unsigned *flt); + unsigned long dsisr, vm_fault_t *flt); int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb); diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index e210a83eb196..43e5f31fe64d 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -79,6 +79,19 @@ struct stop_sprs { u64 mmcra; }; +#define PNV_IDLE_NAME_LEN 16 +struct pnv_idle_states_t { + char name[PNV_IDLE_NAME_LEN]; + u32 latency_ns; + u32 residency_ns; + u64 psscr_val; + u64 psscr_mask; + u32 flags; + bool valid; +}; + +extern struct pnv_idle_states_t *pnv_idle_states; +extern int nr_pnv_idle_states; extern u32 pnv_fastsleep_workaround_at_entry[]; extern u32 pnv_fastsleep_workaround_at_exit[]; diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 9c0a3083571b..29f49a35d6ee 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -4,9 +4,8 @@ #include <linux/types.h> -#include <asm/asm-compat.h> -#include <asm/feature-fixups.h> #include <uapi/asm/cputable.h> +#include <asm/asm-const.h> #ifndef __ASSEMBLY__ @@ -210,7 +209,6 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_DAWR LONG_ASM_CONST(0x0000008000000000) #define CPU_FTR_DABRX LONG_ASM_CONST(0x0000010000000000) #define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x0000020000000000) -#define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x0000040000000000) #define CPU_FTR_POWER9_DD2_1 LONG_ASM_CONST(0x0000080000000000) #define CPU_FTR_P9_TM_HV_ASSIST LONG_ASM_CONST(0x0000100000000000) #define CPU_FTR_P9_TM_XER_SO_BUG LONG_ASM_CONST(0x0000200000000000) @@ -452,7 +450,6 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_PKEY) #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG) -#define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL) #define CPU_FTRS_POWER9 (CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -464,8 +461,6 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \ CPU_FTR_P9_TLBIE_BUG | CPU_FTR_P9_TIDR) -#define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \ - (~CPU_FTR_SAO)) #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9 #define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1) #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \ @@ -488,17 +483,15 @@ static inline void cpu_feature_keys_init(void) { } #ifdef CONFIG_CPU_LITTLE_ENDIAN #define CPU_FTRS_POSSIBLE \ (CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \ - CPU_FTRS_POWER8_DD1 | CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | \ - CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \ - CPU_FTRS_POWER9_DD2_2) + CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | CPU_FTRS_POWER9 | \ + CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2) #else #define CPU_FTRS_POSSIBLE \ (CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \ CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \ - CPU_FTRS_POWER8 | CPU_FTRS_POWER8_DD1 | CPU_FTRS_CELL | \ - CPU_FTRS_PA6T | CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \ - CPU_FTRS_POWER9_DD2_2) + CPU_FTRS_POWER8 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \ + CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | CPU_FTRS_POWER9 | \ + CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2) #endif /* CONFIG_CPU_LITTLE_ENDIAN */ #endif #else @@ -566,17 +559,15 @@ enum { #ifdef CONFIG_CPU_LITTLE_ENDIAN #define CPU_FTRS_ALWAYS \ (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & CPU_FTRS_POWER7 & \ - CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & CPU_FTRS_POWER8_DD1 & \ - CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD1 & CPU_FTRS_POWER9_DD2_1 & \ - CPU_FTRS_DT_CPU_BASE) + CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & CPU_FTRS_POWER9 & \ + CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_DT_CPU_BASE) #else #define CPU_FTRS_ALWAYS \ (CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \ CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \ CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \ - CPU_FTRS_POWER8_DD1 & ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & \ - CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD1 & CPU_FTRS_POWER9_DD2_1 & \ - CPU_FTRS_DT_CPU_BASE) + ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & CPU_FTRS_POWER9 & \ + CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_DT_CPU_BASE) #endif /* CONFIG_CPU_LITTLE_ENDIAN */ #endif #else diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index bc4903badb3f..133672744b2e 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -23,7 +23,6 @@ #include <asm/div64.h> #include <asm/time.h> #include <asm/param.h> -#include <asm/cpu_has_feature.h> typedef u64 __nocast cputime_t; typedef u64 __nocast cputime64_t; diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h index 9f2ae0d25e15..99b84db23e8c 100644 --- a/arch/powerpc/include/asm/dbell.h +++ b/arch/powerpc/include/asm/dbell.h @@ -16,7 +16,7 @@ #include <linux/threads.h> #include <asm/ppc-opcode.h> -#include <asm/cpu_has_feature.h> +#include <asm/feature-fixups.h> #define PPC_DBELL_MSG_BRDCAST (0x04000000) #define PPC_DBELL_TYPE(x) (((x) & 0xf) << (63-36)) diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h index 4a2beef74277..151dff555f50 100644 --- a/arch/powerpc/include/asm/dcr-native.h +++ b/arch/powerpc/include/asm/dcr-native.h @@ -25,6 +25,7 @@ #include <linux/spinlock.h> #include <asm/cputable.h> #include <asm/cpu_has_feature.h> +#include <linux/stringify.h> typedef struct { unsigned int base; diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index ce5da214ffe5..7756026b95ca 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -45,7 +45,6 @@ static inline int debugger_break_match(struct pt_regs *regs) { return 0; } static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; } #endif -void set_breakpoint(struct arch_hw_breakpoint *brk); void __set_breakpoint(struct arch_hw_breakpoint *brk); bool ppc_breakpoint_available(void); #ifdef CONFIG_PPC_ADV_DEBUG_REGS diff --git a/arch/powerpc/include/asm/dt_cpu_ftrs.h b/arch/powerpc/include/asm/dt_cpu_ftrs.h index 71515d909ed1..0c729e2d0e8a 100644 --- a/arch/powerpc/include/asm/dt_cpu_ftrs.h +++ b/arch/powerpc/include/asm/dt_cpu_ftrs.h @@ -10,8 +10,6 @@ */ #include <linux/types.h> -#include <asm/asm-compat.h> -#include <asm/feature-fixups.h> #include <uapi/asm/cputable.h> #ifdef CONFIG_PPC_DT_CPU_FTRS diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 677102baf3cd..219637ea69a1 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -36,13 +36,14 @@ struct pci_dn; #ifdef CONFIG_EEH /* EEH subsystem flags */ -#define EEH_ENABLED 0x01 /* EEH enabled */ -#define EEH_FORCE_DISABLED 0x02 /* EEH disabled */ -#define EEH_PROBE_MODE_DEV 0x04 /* From PCI device */ -#define EEH_PROBE_MODE_DEVTREE 0x08 /* From device tree */ -#define EEH_VALID_PE_ZERO 0x10 /* PE#0 is valid */ -#define EEH_ENABLE_IO_FOR_LOG 0x20 /* Enable IO for log */ -#define EEH_EARLY_DUMP_LOG 0x40 /* Dump log immediately */ +#define EEH_ENABLED 0x01 /* EEH enabled */ +#define EEH_FORCE_DISABLED 0x02 /* EEH disabled */ +#define EEH_PROBE_MODE_DEV 0x04 /* From PCI device */ +#define EEH_PROBE_MODE_DEVTREE 0x08 /* From device tree */ +#define EEH_VALID_PE_ZERO 0x10 /* PE#0 is valid */ +#define EEH_ENABLE_IO_FOR_LOG 0x20 /* Enable IO for log */ +#define EEH_EARLY_DUMP_LOG 0x40 /* Dump log immediately */ +#define EEH_POSTPONED_PROBE 0x80 /* Powernv may postpone device probe */ /* * Delay for PE reset, all in ms diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index c40b4380951c..a86feddddad0 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -35,6 +35,7 @@ * implementations as possible. */ #include <asm/head-64.h> +#include <asm/feature-fixups.h> /* PACA save area offsets (exgen, exmc, etc) */ #define EX_R9 0 @@ -156,7 +157,7 @@ b hrfi_flush_fallback #ifdef CONFIG_RELOCATABLE -#define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ +#define __EXCEPTION_PROLOG_2_RELON(label, h) \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ LOAD_HANDLER(r12,label); \ mtctr r12; \ @@ -166,25 +167,26 @@ bctr; #else /* If not relocatable, we can jump directly -- and save messing with LR */ -#define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ +#define __EXCEPTION_PROLOG_2_RELON(label, h) \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ li r10,MSR_RI; \ mtmsrd r10,1; /* Set RI (EE=0) */ \ b label; #endif -#define EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ - __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ +#define EXCEPTION_PROLOG_2_RELON(label, h) \ + __EXCEPTION_PROLOG_2_RELON(label, h) /* - * As EXCEPTION_PROLOG_PSERIES(), except we've already got relocation on - * so no need to rfid. Save lr in case we're CONFIG_RELOCATABLE, in which - * case EXCEPTION_RELON_PROLOG_PSERIES_1 will be using lr. + * As EXCEPTION_PROLOG(), except we've already got relocation on so no need to + * rfid. Save LR in case we're CONFIG_RELOCATABLE, in which case + * EXCEPTION_PROLOG_2_RELON will be using LR. */ -#define EXCEPTION_RELON_PROLOG_PSERIES(area, label, h, extra, vec) \ +#define EXCEPTION_RELON_PROLOG(area, label, h, extra, vec) \ + SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(area); \ EXCEPTION_PROLOG_1(area, extra, vec); \ - EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) + EXCEPTION_PROLOG_2_RELON(label, h) /* * We're short on space and time in the exception prolog, so we can't @@ -315,7 +317,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define EXCEPTION_PROLOG_1(area, extra, vec) \ _EXCEPTION_PROLOG_1(area, extra, vec) -#define __EXCEPTION_PROLOG_PSERIES_1(label, h) \ +#define __EXCEPTION_PROLOG_2(label, h) \ ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ LOAD_HANDLER(r12,label) \ @@ -324,11 +326,11 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtspr SPRN_##h##SRR1,r10; \ h##RFI_TO_KERNEL; \ b . /* prevent speculative execution */ -#define EXCEPTION_PROLOG_PSERIES_1(label, h) \ - __EXCEPTION_PROLOG_PSERIES_1(label, h) +#define EXCEPTION_PROLOG_2(label, h) \ + __EXCEPTION_PROLOG_2(label, h) /* _NORI variant keeps MSR_RI clear */ -#define __EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) \ +#define __EXCEPTION_PROLOG_2_NORI(label, h) \ ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ xori r10,r10,MSR_RI; /* Clear MSR_RI */ \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ @@ -339,13 +341,14 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) h##RFI_TO_KERNEL; \ b . /* prevent speculative execution */ -#define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) \ - __EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) +#define EXCEPTION_PROLOG_2_NORI(label, h) \ + __EXCEPTION_PROLOG_2_NORI(label, h) -#define EXCEPTION_PROLOG_PSERIES(area, label, h, extra, vec) \ +#define EXCEPTION_PROLOG(area, label, h, extra, vec) \ + SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(area); \ EXCEPTION_PROLOG_1(area, extra, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label, h); + EXCEPTION_PROLOG_2(label, h); #define __KVMTEST(h, n) \ lbz r10,HSTATE_IN_GUEST(r13); \ @@ -416,10 +419,10 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #endif /* Do not enable RI */ -#define EXCEPTION_PROLOG_PSERIES_NORI(area, label, h, extra, vec) \ +#define EXCEPTION_PROLOG_NORI(area, label, h, extra, vec) \ EXCEPTION_PROLOG_0(area); \ EXCEPTION_PROLOG_1(area, extra, vec); \ - EXCEPTION_PROLOG_PSERIES_1_NORI(label, h); + EXCEPTION_PROLOG_2_NORI(label, h); #define __KVM_HANDLER(area, h, n) \ @@ -550,10 +553,8 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) /* * Exception vectors. */ -#define STD_EXCEPTION_PSERIES(vec, label) \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label, \ - EXC_STD, KVMTEST_PR, vec); \ +#define STD_EXCEPTION(vec, label) \ + EXCEPTION_PROLOG(PACA_EXGEN, label, EXC_STD, KVMTEST_PR, vec); /* Version of above for when we have to branch out-of-line */ #define __OOL_EXCEPTION(vec, label, hdlr) \ @@ -561,36 +562,31 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) EXCEPTION_PROLOG_0(PACA_EXGEN) \ b hdlr; -#define STD_EXCEPTION_PSERIES_OOL(vec, label) \ +#define STD_EXCEPTION_OOL(vec, label) \ EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD) + EXCEPTION_PROLOG_2(label, EXC_STD) #define STD_EXCEPTION_HV(loc, vec, label) \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label, \ - EXC_HV, KVMTEST_HV, vec); + EXCEPTION_PROLOG(PACA_EXGEN, label, EXC_HV, KVMTEST_HV, vec); #define STD_EXCEPTION_HV_OOL(vec, label) \ EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec); \ - EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV) + EXCEPTION_PROLOG_2(label, EXC_HV) -#define STD_RELON_EXCEPTION_PSERIES(loc, vec, label) \ +#define STD_RELON_EXCEPTION(loc, vec, label) \ /* No guest interrupts come through here */ \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label, EXC_STD, NOTEST, vec); + EXCEPTION_RELON_PROLOG(PACA_EXGEN, label, EXC_STD, NOTEST, vec); -#define STD_RELON_EXCEPTION_PSERIES_OOL(vec, label) \ +#define STD_RELON_EXCEPTION_OOL(vec, label) \ EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \ - EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_STD) + EXCEPTION_PROLOG_2_RELON(label, EXC_STD) #define STD_RELON_EXCEPTION_HV(loc, vec, label) \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label, \ - EXC_HV, KVMTEST_HV, vec); + EXCEPTION_RELON_PROLOG(PACA_EXGEN, label, EXC_HV, KVMTEST_HV, vec); #define STD_RELON_EXCEPTION_HV_OOL(vec, label) \ EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec); \ - EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) + EXCEPTION_PROLOG_2_RELON(label, EXC_HV) /* This associate vector numbers with bits in paca->irq_happened */ #define SOFTEN_VALUE_0x500 PACA_IRQ_EE @@ -627,55 +623,45 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define SOFTEN_NOTEST_PR(vec, bitmask) _SOFTEN_TEST(EXC_STD, vec, bitmask) #define SOFTEN_NOTEST_HV(vec, bitmask) _SOFTEN_TEST(EXC_HV, vec, bitmask) -#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) \ +#define __MASKABLE_EXCEPTION(vec, label, h, extra, bitmask) \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask); \ - EXCEPTION_PROLOG_PSERIES_1(label, h); + EXCEPTION_PROLOG_2(label, h); -#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) \ - __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) +#define MASKABLE_EXCEPTION(vec, label, bitmask) \ + __MASKABLE_EXCEPTION(vec, label, EXC_STD, SOFTEN_TEST_PR, bitmask) -#define MASKABLE_EXCEPTION_PSERIES(loc, vec, label, bitmask) \ - _MASKABLE_EXCEPTION_PSERIES(vec, label, \ - EXC_STD, SOFTEN_TEST_PR, bitmask) - -#define MASKABLE_EXCEPTION_PSERIES_OOL(vec, label, bitmask) \ +#define MASKABLE_EXCEPTION_OOL(vec, label, bitmask) \ MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_PR, vec, bitmask);\ - EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD) + EXCEPTION_PROLOG_2(label, EXC_STD) -#define MASKABLE_EXCEPTION_HV(loc, vec, label, bitmask) \ - _MASKABLE_EXCEPTION_PSERIES(vec, label, \ - EXC_HV, SOFTEN_TEST_HV, bitmask) +#define MASKABLE_EXCEPTION_HV(vec, label, bitmask) \ + __MASKABLE_EXCEPTION(vec, label, EXC_HV, SOFTEN_TEST_HV, bitmask) #define MASKABLE_EXCEPTION_HV_OOL(vec, label, bitmask) \ MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ - EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV) + EXCEPTION_PROLOG_2(label, EXC_HV) -#define __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) \ +#define __MASKABLE_RELON_EXCEPTION(vec, label, h, extra, bitmask) \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask); \ - EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) - -#define _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask)\ - __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) + EXCEPTION_PROLOG_2_RELON(label, h) -#define MASKABLE_RELON_EXCEPTION_PSERIES(loc, vec, label, bitmask) \ - _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, \ - EXC_STD, SOFTEN_NOTEST_PR, bitmask) +#define MASKABLE_RELON_EXCEPTION(vec, label, bitmask) \ + __MASKABLE_RELON_EXCEPTION(vec, label, EXC_STD, SOFTEN_NOTEST_PR, bitmask) -#define MASKABLE_RELON_EXCEPTION_PSERIES_OOL(vec, label, bitmask) \ +#define MASKABLE_RELON_EXCEPTION_OOL(vec, label, bitmask) \ MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_PR, vec, bitmask);\ - EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD); + EXCEPTION_PROLOG_2(label, EXC_STD); -#define MASKABLE_RELON_EXCEPTION_HV(loc, vec, label, bitmask) \ - _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, \ - EXC_HV, SOFTEN_TEST_HV, bitmask) +#define MASKABLE_RELON_EXCEPTION_HV(vec, label, bitmask) \ + __MASKABLE_RELON_EXCEPTION(vec, label, EXC_HV, SOFTEN_TEST_HV, bitmask) #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask) \ MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ - EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) + EXCEPTION_PROLOG_2_RELON(label, EXC_HV) /* * Our exception common code can be passed various "additions" diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index 5a23010af600..1e7a33592e29 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -195,9 +195,6 @@ struct fadump_crash_info_header { struct cpumask online_mask; }; -/* Crash memory ranges */ -#define INIT_CRASHMEM_RANGES (INIT_MEMBLOCK_REGIONS + 2) - struct fad_crash_memory_ranges { unsigned long long base; unsigned long long size; diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index fcfd05672b1b..33b6f9c892c8 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -1,6 +1,8 @@ #ifndef __ASM_POWERPC_FEATURE_FIXUPS_H #define __ASM_POWERPC_FEATURE_FIXUPS_H +#include <asm/asm-const.h> + /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 535add3f7791..7a051bd21f87 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -14,8 +14,7 @@ #ifdef __KERNEL__ -#include <asm/asm-compat.h> -#include <asm/feature-fixups.h> +#include <asm/asm-const.h> /* firmware feature bitmask values */ diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 6c40dfda5912..41cc15c14eee 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -15,7 +15,6 @@ #define _ASM_FIXMAP_H #ifndef __ASSEMBLY__ -#include <linux/kernel.h> #include <asm/page.h> #include <asm/pgtable.h> #ifdef CONFIG_HIGHMEM diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index 1a944c18c539..94542776a62d 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -8,7 +8,7 @@ #include <linux/uaccess.h> #include <asm/errno.h> #include <asm/synch.h> -#include <asm/asm-compat.h> +#include <asm/asm-405.h> #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ __asm__ __volatile ( \ diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index 7e0e93f24cb7..a4f947888744 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -260,22 +260,22 @@ name: #define EXC_REAL(name, start, size) \ EXC_REAL_BEGIN(name, start, size); \ - STD_EXCEPTION_PSERIES(start, name##_common); \ + STD_EXCEPTION(start, name##_common); \ EXC_REAL_END(name, start, size); #define EXC_VIRT(name, start, size, realvec) \ EXC_VIRT_BEGIN(name, start, size); \ - STD_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ + STD_RELON_EXCEPTION(start, realvec, name##_common); \ EXC_VIRT_END(name, start, size); #define EXC_REAL_MASKABLE(name, start, size, bitmask) \ EXC_REAL_BEGIN(name, start, size); \ - MASKABLE_EXCEPTION_PSERIES(start, start, name##_common, bitmask);\ + MASKABLE_EXCEPTION(start, name##_common, bitmask); \ EXC_REAL_END(name, start, size); #define EXC_VIRT_MASKABLE(name, start, size, realvec, bitmask) \ EXC_VIRT_BEGIN(name, start, size); \ - MASKABLE_RELON_EXCEPTION_PSERIES(start, realvec, name##_common, bitmask);\ + MASKABLE_RELON_EXCEPTION(realvec, name##_common, bitmask); \ EXC_VIRT_END(name, start, size); #define EXC_REAL_HV(name, start, size) \ @@ -295,7 +295,7 @@ name: #define __TRAMP_REAL_OOL(name, vec) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ - STD_EXCEPTION_PSERIES_OOL(vec, name##_common); \ + STD_EXCEPTION_OOL(vec, name##_common); #define EXC_REAL_OOL(name, start, size) \ __EXC_REAL_OOL(name, start, size); \ @@ -306,7 +306,7 @@ name: #define __TRAMP_REAL_OOL_MASKABLE(name, vec, bitmask) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ - MASKABLE_EXCEPTION_PSERIES_OOL(vec, name##_common, bitmask); \ + MASKABLE_EXCEPTION_OOL(vec, name##_common, bitmask); #define EXC_REAL_OOL_MASKABLE(name, start, size, bitmask) \ __EXC_REAL_OOL_MASKABLE(name, start, size); \ @@ -346,7 +346,7 @@ name: #define __TRAMP_VIRT_OOL(name, realvec) \ TRAMP_VIRT_BEGIN(tramp_virt_##name); \ - STD_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common); \ + STD_RELON_EXCEPTION_OOL(realvec, name##_common); #define EXC_VIRT_OOL(name, start, size, realvec) \ __EXC_VIRT_OOL(name, start, size); \ @@ -357,7 +357,7 @@ name: #define __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask) \ TRAMP_VIRT_BEGIN(tramp_virt_##name); \ - MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common, bitmask);\ + MASKABLE_RELON_EXCEPTION_OOL(realvec, name##_common, bitmask); #define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec, bitmask) \ __EXC_VIRT_OOL_MASKABLE(name, start, size); \ diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index cec820f961da..a4b65b186ec6 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -25,7 +25,7 @@ #include <linux/interrupt.h> #include <asm/kmap_types.h> -#include <asm/tlbflush.h> +#include <asm/cacheflush.h> #include <asm/page.h> #include <asm/fixmap.h> diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 3225eb6402cc..2d00cc530083 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -84,9 +84,6 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, return dir + idx; } -pte_t *huge_pte_offset_and_shift(struct mm_struct *mm, - unsigned long addr, unsigned *shift); - void flush_dcache_icache_hugepage(struct page *page); int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 662c8347d699..a0b17f9f1ea4 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -342,10 +342,12 @@ #define H_CPU_CHAR_BRANCH_HINTS_HONORED (1ull << 58) // IBM bit 5 #define H_CPU_CHAR_THREAD_RECONFIG_CTRL (1ull << 57) // IBM bit 6 #define H_CPU_CHAR_COUNT_CACHE_DISABLED (1ull << 56) // IBM bit 7 +#define H_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) // IBM bit 9 #define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 #define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 +#define H_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) // IBM bit 5 /* Flag values used in H_REGISTER_PROC_TBL hcall */ #define PROC_TABLE_OP_MASK 0x18 diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 8e7b09703ca4..ece4dc89c90b 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -52,16 +52,20 @@ struct arch_hw_breakpoint { #include <asm/reg.h> #include <asm/debug.h> +struct perf_event_attr; struct perf_event; struct pmu; struct perf_sample_data; +struct task_struct; #define HW_BREAKPOINT_ALIGN 0x7 extern int hw_breakpoint_slots(int type); extern int arch_bp_generic_fields(int type, int *gen_bp_type); -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); int arch_install_hw_breakpoint(struct perf_event *bp); diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index e151774cb577..32a18f2f49bc 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -253,14 +253,16 @@ static inline bool lazy_irq_pending(void) /* * This is called by asynchronous interrupts to conditionally - * re-enable hard interrupts when soft-disabled after having - * cleared the source of the interrupt + * re-enable hard interrupts after having cleared the source + * of the interrupt. They are kept disabled if there is a different + * soft-masked interrupt pending that requires hard masking. */ static inline void may_hard_irq_enable(void) { - get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; - if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) + if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) { + get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; __hard_irq_enable(); + } } static inline bool arch_irq_disabled_regs(struct pt_regs *regs) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 20febe0b7f32..ab3a4fba38e3 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -30,6 +30,7 @@ #include <asm/machdep.h> #include <asm/types.h> #include <asm/pci-bridge.h> +#include <asm/asm-const.h> #define IOMMU_PAGE_SHIFT_4K 12 #define IOMMU_PAGE_SIZE_4K (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K) @@ -69,6 +70,8 @@ struct iommu_table_ops { long index, unsigned long *hpa, enum dma_data_direction *direction); + + __be64 *(*useraddrptr)(struct iommu_table *tbl, long index, bool alloc); #endif void (*clear)(struct iommu_table *tbl, long index, long npages); @@ -117,15 +120,16 @@ struct iommu_table { unsigned long *it_map; /* A simple allocation bitmap for now */ unsigned long it_page_shift;/* table iommu page size */ struct list_head it_group_list;/* List of iommu_table_group_link */ - unsigned long *it_userspace; /* userspace view of the table */ + __be64 *it_userspace; /* userspace view of the table */ struct iommu_table_ops *it_ops; struct kref it_kref; + int it_nid; }; +#define IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry) \ + ((tbl)->it_ops->useraddrptr((tbl), (entry), false)) #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \ - ((tbl)->it_userspace ? \ - &((tbl)->it_userspace[(entry) - (tbl)->it_offset]) : \ - NULL) + ((tbl)->it_ops->useraddrptr((tbl), (entry), true)) /* Pure 2^n version of get_order */ static inline __attribute_const__ diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 9a287e0ac8b1..a3b2cf940b4e 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -14,7 +14,7 @@ #include <linux/types.h> #include <asm/feature-fixups.h> -#include <asm/asm-compat.h> +#include <asm/asm-const.h> #define JUMP_ENTRY_TYPE stringify_in_c(FTR_ENTRY_LONG) #define JUMP_LABEL_NOP_SIZE 4 diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 9f3be5c8a4a3..785c464b6588 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -88,7 +88,6 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_saved_msr; - struct pt_regs jprobe_saved_regs; struct prev_kprobe prev_kprobe; }; @@ -103,17 +102,6 @@ extern int kprobe_exceptions_notify(struct notifier_block *self, extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_handler(struct pt_regs *regs); extern int kprobe_post_handler(struct pt_regs *regs); -#ifdef CONFIG_KPROBES_ON_FTRACE -extern int __is_active_jprobe(unsigned long addr); -extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb); -#else -static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - return 0; -} -#endif #else static inline int kprobe_handler(struct pt_regs *regs) { return 0; } static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; } diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 1f345a0b6ba2..83a9aa3cf689 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -390,4 +390,51 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu); #define SPLIT_HACK_MASK 0xff000000 #define SPLIT_HACK_OFFS 0xfb000000 +/* + * This packs a VCPU ID from the [0..KVM_MAX_VCPU_ID) space down to the + * [0..KVM_MAX_VCPUS) space, using knowledge of the guest's core stride + * (but not its actual threading mode, which is not available) to avoid + * collisions. + * + * The implementation leaves VCPU IDs from the range [0..KVM_MAX_VCPUS) (block + * 0) unchanged: if the guest is filling each VCORE completely then it will be + * using consecutive IDs and it will fill the space without any packing. + * + * For higher VCPU IDs, the packed ID is based on the VCPU ID modulo + * KVM_MAX_VCPUS (effectively masking off the top bits) and then an offset is + * added to avoid collisions. + * + * VCPU IDs in the range [KVM_MAX_VCPUS..(KVM_MAX_VCPUS*2)) (block 1) are only + * possible if the guest is leaving at least 1/2 of each VCORE empty, so IDs + * can be safely packed into the second half of each VCORE by adding an offset + * of (stride / 2). + * + * Similarly, if VCPU IDs in the range [(KVM_MAX_VCPUS*2)..(KVM_MAX_VCPUS*4)) + * (blocks 2 and 3) are seen, the guest must be leaving at least 3/4 of each + * VCORE empty so packed IDs can be offset by (stride / 4) and (stride * 3 / 4). + * + * Finally, VCPU IDs from blocks 5..7 will only be seen if the guest is using a + * stride of 8 and 1 thread per core so the remaining offsets of 1, 5, 3 and 7 + * must be free to use. + * + * (The offsets for each block are stored in block_offsets[], indexed by the + * block number if the stride is 8. For cases where the guest's stride is less + * than 8, we can re-use the block_offsets array by multiplying the block + * number by (MAX_SMT_THREADS / stride) to reach the correct entry.) + */ +static inline u32 kvmppc_pack_vcpu_id(struct kvm *kvm, u32 id) +{ + const int block_offsets[MAX_SMT_THREADS] = {0, 4, 2, 6, 1, 5, 3, 7}; + int stride = kvm->arch.emul_smt_mode; + int block = (id / KVM_MAX_VCPUS) * (MAX_SMT_THREADS / stride); + u32 packed_id; + + if (WARN_ONCE(block >= MAX_SMT_THREADS, "VCPU ID too large to pack")) + return 0; + packed_id = (id % KVM_MAX_VCPUS) + block_offsets[block]; + if (WARN_ONCE(packed_id >= KVM_MAX_VCPUS, "VCPU ID packing failed")) + return 0; + return packed_id; +} + #endif /* __ASM_KVM_BOOK3S_H__ */ diff --git a/arch/powerpc/include/asm/kvm_booke_hv_asm.h b/arch/powerpc/include/asm/kvm_booke_hv_asm.h index e5f048bbcb7c..931260b59ac6 100644 --- a/arch/powerpc/include/asm/kvm_booke_hv_asm.h +++ b/arch/powerpc/include/asm/kvm_booke_hv_asm.h @@ -9,6 +9,8 @@ #ifndef ASM_KVM_BOOKE_HV_ASM_H #define ASM_KVM_BOOKE_HV_ASM_H +#include <asm/feature-fixups.h> + #ifdef __ASSEMBLY__ /* diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index fa4efa7e88f7..906bcbdfd2a1 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -42,7 +42,14 @@ #define KVM_USER_MEM_SLOTS 512 #include <asm/cputhreads.h> -#define KVM_MAX_VCPU_ID (threads_per_subcore * KVM_MAX_VCORES) + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +#include <asm/kvm_book3s_asm.h> /* for MAX_SMT_THREADS */ +#define KVM_MAX_VCPU_ID (MAX_SMT_THREADS * KVM_MAX_VCORES) + +#else +#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -672,7 +679,7 @@ struct kvm_vcpu_arch { gva_t vaddr_accessed; pgd_t *pgdir; - u8 io_gpr; /* GPR used as IO source/target */ + u16 io_gpr; /* GPR used as IO source/target */ u8 mmio_host_swabbed; u8 mmio_sign_extend; /* conversion between single and double precision */ @@ -688,7 +695,6 @@ struct kvm_vcpu_arch { */ u8 mmio_vsx_copy_nums; u8 mmio_vsx_offset; - u8 mmio_vsx_tx_sx_enabled; u8 mmio_vmx_copy_nums; u8 mmio_vmx_offset; u8 mmio_copy_type; @@ -801,14 +807,14 @@ struct kvm_vcpu_arch { #define KVMPPC_VCPU_BUSY_IN_HOST 2 /* Values for vcpu->arch.io_gpr */ -#define KVM_MMIO_REG_MASK 0x001f -#define KVM_MMIO_REG_EXT_MASK 0xffe0 +#define KVM_MMIO_REG_MASK 0x003f +#define KVM_MMIO_REG_EXT_MASK 0xffc0 #define KVM_MMIO_REG_GPR 0x0000 -#define KVM_MMIO_REG_FPR 0x0020 -#define KVM_MMIO_REG_QPR 0x0040 -#define KVM_MMIO_REG_FQPR 0x0060 -#define KVM_MMIO_REG_VSX 0x0080 -#define KVM_MMIO_REG_VMX 0x00c0 +#define KVM_MMIO_REG_FPR 0x0040 +#define KVM_MMIO_REG_QPR 0x0080 +#define KVM_MMIO_REG_FQPR 0x00c0 +#define KVM_MMIO_REG_VSX 0x0100 +#define KVM_MMIO_REG_VMX 0x0180 #define __KVM_HAVE_ARCH_WQP #define __KVM_HAVE_CREATE_DEVICE diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h index cb57f29f531d..295b3dbb2698 100644 --- a/arch/powerpc/include/asm/mmu-44x.h +++ b/arch/powerpc/include/asm/mmu-44x.h @@ -5,7 +5,7 @@ * PPC440 support */ -#include <asm/page.h> +#include <asm/asm-const.h> #define PPC44x_MMUCR_TID 0x000000ff #define PPC44x_MMUCR_STS 0x00010000 @@ -124,19 +124,19 @@ typedef struct { /* Size of the TLBs used for pinning in lowmem */ #define PPC_PIN_SIZE (1 << 28) /* 256M */ -#if (PAGE_SHIFT == 12) +#if defined(CONFIG_PPC_4K_PAGES) #define PPC44x_TLBE_SIZE PPC44x_TLB_4K #define PPC47x_TLBE_SIZE PPC47x_TLB0_4K #define mmu_virtual_psize MMU_PAGE_4K -#elif (PAGE_SHIFT == 14) +#elif defined(CONFIG_PPC_16K_PAGES) #define PPC44x_TLBE_SIZE PPC44x_TLB_16K #define PPC47x_TLBE_SIZE PPC47x_TLB0_16K #define mmu_virtual_psize MMU_PAGE_16K -#elif (PAGE_SHIFT == 16) +#elif defined(CONFIG_PPC_64K_PAGES) #define PPC44x_TLBE_SIZE PPC44x_TLB_64K #define PPC47x_TLBE_SIZE PPC47x_TLB0_64K #define mmu_virtual_psize MMU_PAGE_64K -#elif (PAGE_SHIFT == 18) +#elif defined(CONFIG_PPC_256K_PAGES) #define PPC44x_TLBE_SIZE PPC44x_TLB_256K #define mmu_virtual_psize MMU_PAGE_256K #else diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 61d15ce92278..13ea441ac531 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -5,8 +5,7 @@ #include <linux/types.h> -#include <asm/asm-compat.h> -#include <asm/feature-fixups.h> +#include <asm/asm-const.h> /* * MMU features bit definitions diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 79d570cbf332..b2f89b621b15 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -143,24 +143,33 @@ static inline void mm_context_remove_copro(struct mm_struct *mm) { int c; - c = atomic_dec_if_positive(&mm->context.copros); - - /* Detect imbalance between add and remove */ - WARN_ON(c < 0); - /* - * Need to broadcast a global flush of the full mm before - * decrementing active_cpus count, as the next TLBI may be - * local and the nMMU and/or PSL need to be cleaned up. - * Should be rare enough so that it's acceptable. + * When removing the last copro, we need to broadcast a global + * flush of the full mm, as the next TLBI may be local and the + * nMMU and/or PSL need to be cleaned up. + * + * Both the 'copros' and 'active_cpus' counts are looked at in + * flush_all_mm() to determine the scope (local/global) of the + * TLBIs, so we need to flush first before decrementing + * 'copros'. If this API is used by several callers for the + * same context, it can lead to over-flushing. It's hopefully + * not common enough to be a problem. * * Skip on hash, as we don't know how to do the proper flush * for the time being. Invalidations will remain global if - * used on hash. + * used on hash. Note that we can't drop 'copros' either, as + * it could make some invalidations local with no flush + * in-between. */ - if (c == 0 && radix_enabled()) { + if (radix_enabled()) { flush_all_mm(mm); - dec_mm_active_cpus(mm); + + c = atomic_dec_if_positive(&mm->context.copros); + /* Detect imbalance between add and remove */ + WARN_ON(c < 0); + + if (c == 0) + dec_mm_active_cpus(mm); } } #else diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 7c46a98cc7f4..a507a65b0866 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -8,7 +8,8 @@ #ifndef __ASSEMBLY__ #include <linux/sched.h> #include <linux/threads.h> -#include <asm/io.h> /* For sub-arch specific PPC_PIN_SIZE */ +#include <asm/mmu.h> /* For sub-arch specific PPC_PIN_SIZE */ +#include <asm/asm-405.h> extern unsigned long ioremap_bot; @@ -222,10 +223,6 @@ static inline unsigned long long pte_update(pte_t *p, } #endif /* CONFIG_PTE_64BIT */ -/* - * 2.6 calls this without flushing the TLB entry; this is wrong - * for our hash-based implementation, we fix that up here. - */ #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep) { diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index dd0c7236208f..7cd6809f4d33 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -3,11 +3,12 @@ #define _ASM_POWERPC_NOHASH_64_PGTABLE_H /* * This file contains the functions and defines necessary to modify and use - * the ppc64 hashed page table. + * the ppc64 non-hashed page table. */ #include <asm/nohash/64/pgtable-4k.h> #include <asm/barrier.h> +#include <asm/asm-const.h> #ifdef CONFIG_PPC_64K_PAGES #error "Page size not supported" @@ -37,7 +38,7 @@ /* * The vmalloc space starts at the beginning of that region, and - * occupies half of it on hash CPUs and a quarter of it on Book3E + * occupies a quarter of it on Book3E * (we keep a quarter for the virtual memmap) */ #define VMALLOC_START KERN_VIRT_START @@ -77,7 +78,7 @@ /* * Defines the address of the vmemap area, in its own region on - * hash table CPUs and after the vmalloc space on Book3E + * after the vmalloc space on Book3E */ #define VMEMMAP_BASE VMALLOC_END #define VMEMMAP_END KERN_IO_START @@ -247,14 +248,6 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); } -/* - * We currently remove entries from the hashtable regardless of whether - * the entry was young or dirty. The generic routines only flush if the - * entry was young or dirty which is not good enough. - * - * We should be more intelligent about this but for the moment we override - * these functions and force a tlb flush unconditionally - */ #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young(__vma, __address, __ptep) \ ({ \ @@ -278,9 +271,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, } -/* Set the dirty and/or accessed bits atomically in a linux PTE, this - * function doesn't need to flush the hash entry - */ +/* Set the dirty and/or accessed bits atomically in a linux PTE */ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, diff --git a/arch/powerpc/include/asm/nohash/tlbflush.h b/arch/powerpc/include/asm/nohash/tlbflush.h new file mode 100644 index 000000000000..b1d8fec29169 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/tlbflush.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_NOHASH_TLBFLUSH_H +#define _ASM_POWERPC_NOHASH_TLBFLUSH_H + +/* + * TLB flushing: + * + * - flush_tlb_mm(mm) flushes the specified mm context TLB's + * - flush_tlb_page(vma, vmaddr) flushes one page + * - local_flush_tlb_mm(mm, full) flushes the specified mm context on + * the local processor + * - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor + * - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB + * - flush_tlb_range(vma, start, end) flushes a range of pages + * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages + * + */ + +/* + * TLB flushing for software loaded TLB chips + * + * TODO: (CONFIG_FSL_BOOKE) determine if flush_tlb_range & + * flush_tlb_kernel_range are best implemented as tlbia vs + * specific tlbie's + */ + +struct vm_area_struct; +struct mm_struct; + +#define MMU_NO_CONTEXT ((unsigned int)-1) + +extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); + +extern void local_flush_tlb_mm(struct mm_struct *mm); +extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); + +extern void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, + int tsize, int ind); + +#ifdef CONFIG_SMP +extern void flush_tlb_mm(struct mm_struct *mm); +extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +extern void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, + int tsize, int ind); +#else +#define flush_tlb_mm(mm) local_flush_tlb_mm(mm) +#define flush_tlb_page(vma,addr) local_flush_tlb_page(vma,addr) +#define __flush_tlb_page(mm,addr,p,i) __local_flush_tlb_page(mm,addr,p,i) +#endif + +#endif /* _ASM_POWERPC_NOHASH_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 3bab299eda49..8365353330b4 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -206,9 +206,11 @@ #define OPAL_NPU_SPA_CLEAR_CACHE 160 #define OPAL_NPU_TL_SET 161 #define OPAL_SENSOR_READ_U64 162 +#define OPAL_SENSOR_GROUP_ENABLE 163 #define OPAL_PCI_GET_PBCQ_TUNNEL_BAR 164 #define OPAL_PCI_SET_PBCQ_TUNNEL_BAR 165 -#define OPAL_LAST 165 +#define OPAL_NX_COPROC_INIT 167 +#define OPAL_LAST 167 #define QUIESCE_HOLD 1 /* Spin all calls at entry */ #define QUIESCE_REJECT 2 /* Fail all calls with OPAL_BUSY */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index e1b2910c6e81..834e7e29f1e4 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -292,6 +292,8 @@ int opal_set_powercap(u32 handle, int token, u32 pcap); int opal_get_power_shift_ratio(u32 handle, int token, u32 *psr); int opal_set_power_shift_ratio(u32 handle, int token, u32 psr); int opal_sensor_group_clear(u32 group_hndl, int token); +int opal_sensor_group_enable(u32 group_hndl, int token, bool enable); +int opal_nx_coproc_init(uint32_t chip_id, uint32_t ct); s64 opal_signal_system_reset(s32 cpu); s64 opal_quiesce(u64 shutdown_type, s32 cpu); @@ -305,6 +307,8 @@ extern void opal_configure_cores(void); extern int opal_get_chars(uint32_t vtermno, char *buf, int count); extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len); +extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len); +extern int opal_flush_console(uint32_t vtermno); extern void hvc_opal_init_early(void); @@ -326,6 +330,7 @@ extern int opal_async_wait_response_interruptible(uint64_t token, struct opal_msg *msg); extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data); extern int opal_get_sensor_data_u64(u32 sensor_hndl, u64 *sensor_data); +extern int sensor_group_enable(u32 grp_hndl, bool enable); struct rtc_time; extern time64_t opal_get_boot_time(void); diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 6d34bd71139d..ad4f16164619 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -187,11 +187,6 @@ struct paca_struct { u8 subcore_sibling_mask; /* Flag to request this thread not to stop */ atomic_t dont_stop; - /* - * Pointer to an array which contains pointer - * to the sibling threads' paca. - */ - struct paca_struct **thread_sibling_pacas; /* The PSSCR value that the kernel requested before going to stop */ u64 requested_psscr; @@ -252,6 +247,9 @@ struct paca_struct { void *rfi_flush_fallback_area; u64 l1d_flush_size; #endif +#ifdef CONFIG_PPC_PSERIES + u8 *mce_data_buf; /* buffer to hold per cpu rtas errlog */ +#endif /* CONFIG_PPC_PSERIES */ } ____cacheline_aligned; extern void copy_mm_to_paca(struct mm_struct *mm); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index db7be0779d55..f6a1265face2 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -16,8 +16,7 @@ #else #include <asm/types.h> #endif -#include <asm/asm-compat.h> -#include <asm/kdump.h> +#include <asm/asm-const.h> /* * On regular PPC32 page size is 4K (but we support 4K/16K/64K/256K pages diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index af04acdb873f..c0ce17e909ef 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -10,6 +10,8 @@ * 2 of the License, or (at your option) any later version. */ +#include <asm/asm-const.h> + /* * We always define HW_PAGE_SHIFT to 12 as use of 64K pages remains Linux * specific, every notion of page number shared with the firmware, TCEs, diff --git a/arch/powerpc/include/asm/pkeys.h b/arch/powerpc/include/asm/pkeys.h index 5ba80cffb505..20ebf153c871 100644 --- a/arch/powerpc/include/asm/pkeys.h +++ b/arch/powerpc/include/asm/pkeys.h @@ -13,7 +13,8 @@ DECLARE_STATIC_KEY_TRUE(pkey_disabled); extern int pkeys_total; /* total pkeys as per device tree */ -extern u32 initial_allocation_mask; /* bits set for reserved keys */ +extern u32 initial_allocation_mask; /* bits set for the initially allocated keys */ +extern u32 reserved_allocation_mask; /* bits set for reserved keys */ #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | \ VM_PKEY_BIT3 | VM_PKEY_BIT4) @@ -83,19 +84,21 @@ static inline u16 pte_to_pkey_bits(u64 pteflags) #define __mm_pkey_is_allocated(mm, pkey) \ (mm_pkey_allocation_map(mm) & pkey_alloc_mask(pkey)) -#define __mm_pkey_is_reserved(pkey) (initial_allocation_mask & \ +#define __mm_pkey_is_reserved(pkey) (reserved_allocation_mask & \ pkey_alloc_mask(pkey)) static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { - /* A reserved key is never considered as 'explicitly allocated' */ - return ((pkey < arch_max_pkey()) && - !__mm_pkey_is_reserved(pkey) && - __mm_pkey_is_allocated(mm, pkey)); + if (pkey < 0 || pkey >= arch_max_pkey()) + return false; + + /* Reserved keys are never allocated. */ + if (__mm_pkey_is_reserved(pkey)) + return false; + + return __mm_pkey_is_allocated(mm, pkey); } -extern void __arch_activate_pkey(int pkey); -extern void __arch_deactivate_pkey(int pkey); /* * Returns a positive, 5-bit key on success, or -1 on failure. * Relies on the mmap_sem to protect against concurrency in mm_pkey_alloc() and @@ -124,11 +127,6 @@ static inline int mm_pkey_alloc(struct mm_struct *mm) ret = ffz((u32)mm_pkey_allocation_map(mm)); __mm_pkey_allocated(mm, ret); - /* - * Enable the key in the hardware - */ - if (ret > 0) - __arch_activate_pkey(ret); return ret; } @@ -140,10 +138,6 @@ static inline int mm_pkey_free(struct mm_struct *mm, int pkey) if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; - /* - * Disable the key in the hardware - */ - __arch_deactivate_pkey(pkey); __mm_pkey_free(mm, pkey); return 0; @@ -187,6 +181,16 @@ static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, { if (static_branch_likely(&pkey_disabled)) return -EINVAL; + + /* + * userspace should not change pkey-0 permissions. + * pkey-0 is associated with every page in the kernel. + * If userspace denies any permission on pkey-0, the + * kernel cannot operate. + */ + if (pkey == 0) + return init_val ? -EINVAL : 0; + return __arch_set_user_pkey_access(tsk, pkey, init_val); } diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h index d2d8c28db336..7f627e3f4da4 100644 --- a/arch/powerpc/include/asm/pnv-pci.h +++ b/arch/powerpc/include/asm/pnv-pci.h @@ -50,13 +50,6 @@ int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs, struct pci_dev *dev, int num); void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs, struct pci_dev *dev); - -/* Support for the cxl kernel api on the real PHB (instead of vPHB) */ -int pnv_cxl_enable_phb_kernel_api(struct pci_controller *hose, bool enable); -bool pnv_pci_on_cxl_phb(struct pci_dev *dev); -struct cxl_afu *pnv_cxl_phb_to_afu(struct pci_controller *hose); -void pnv_cxl_phb_set_peer_afu(struct pci_dev *dev, struct cxl_afu *afu); - #endif struct pnv_php_slot { diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 4436887bc415..665af14850e4 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -12,8 +12,7 @@ #ifndef _ASM_POWERPC_PPC_OPCODE_H #define _ASM_POWERPC_PPC_OPCODE_H -#include <linux/stringify.h> -#include <asm/asm-compat.h> +#include <asm/asm-const.h> #define __REG_R0 0 #define __REG_R1 1 @@ -367,6 +366,8 @@ #define PPC_INST_STFDX 0x7c0005ae #define PPC_INST_LVX 0x7c0000ce #define PPC_INST_STVX 0x7c0001ce +#define PPC_INST_VCMPEQUD 0x100000c7 +#define PPC_INST_VCMPEQUB 0x10000006 /* macros to insert fields into opcodes */ #define ___PPC_RA(a) (((a) & 0x1f) << 16) @@ -397,6 +398,7 @@ #define __PPC_BI(s) (((s) & 0x1f) << 16) #define __PPC_CT(t) (((t) & 0x0f) << 21) #define __PPC_SPR(r) ((((r) & 0x1f) << 16) | ((((r) >> 5) & 0x1f) << 11)) +#define __PPC_RC21 (0x1 << 10) /* * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a @@ -568,4 +570,12 @@ ((IH & 0x7) << 21)) #define PPC_INVALIDATE_ERAT PPC_SLBIA(7) +#define VCMPEQUD_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUD | \ + ___PPC_RT(vrt) | ___PPC_RA(vra) | \ + ___PPC_RB(vrb) | __PPC_RC21) + +#define VCMPEQUB_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUB | \ + ___PPC_RT(vrt) | ___PPC_RA(vra) | \ + ___PPC_RB(vrb) | __PPC_RC21) + #endif /* _ASM_POWERPC_PPC_OPCODE_H */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 75ece56dcd62..b5d023680801 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -9,6 +9,7 @@ #include <asm/processor.h> #include <asm/ppc-opcode.h> #include <asm/firmware.h> +#include <asm/feature-fixups.h> #ifdef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 5debe337ea9d..52fadded5c1e 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -39,10 +39,9 @@ #endif /* CONFIG_PPC64 */ #ifndef __ASSEMBLY__ -#include <linux/compiler.h> -#include <linux/cache.h> +#include <linux/types.h> +#include <asm/thread_info.h> #include <asm/ptrace.h> -#include <asm/types.h> #include <asm/hw_breakpoint.h> /* We do _not_ want to define new machine types at all, those must die diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index e4923686e43a..447cbd1bee99 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -24,6 +24,7 @@ #define _ASM_POWERPC_PTRACE_H #include <uapi/asm/ptrace.h> +#include <asm/asm-const.h> #ifdef __powerpc64__ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 562568414cf4..e5b314ed054e 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -13,6 +13,8 @@ #include <linux/stringify.h> #include <asm/cputable.h> +#include <asm/asm-const.h> +#include <asm/feature-fixups.h> /* Pickup Book E specific registers. */ #if defined(CONFIG_BOOKE) || defined(CONFIG_40x) @@ -161,7 +163,7 @@ #define PSSCR_ESL 0x00200000 /* Enable State Loss */ #define PSSCR_SD 0x00400000 /* Status Disable */ #define PSSCR_PLS 0xf000000000000000 /* Power-saving Level Status */ -#define PSSCR_GUEST_VIS 0xf0000000000003ff /* Guest-visible PSSCR fields */ +#define PSSCR_GUEST_VIS 0xf0000000000003ffUL /* Guest-visible PSSCR fields */ #define PSSCR_FAKE_SUSPEND 0x00000400 /* Fake-suspend bit (P9 DD2.2) */ #define PSSCR_FAKE_SUSPEND_LG 10 /* Fake-suspend bit position */ diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h index 3ba9c6f096fc..74c2c57c492a 100644 --- a/arch/powerpc/include/asm/reg_a2.h +++ b/arch/powerpc/include/asm/reg_a2.h @@ -12,6 +12,8 @@ #ifndef __ASM_POWERPC_REG_A2_H__ #define __ASM_POWERPC_REG_A2_H__ +#include <asm/asm-const.h> + #define SPRN_TENSR 0x1b5 #define SPRN_TENS 0x1b6 /* Thread ENable Set */ #define SPRN_TENC 0x1b7 /* Thread ENable Clear */ diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index d7ccf93e6279..a21f529c43d9 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -7,6 +7,8 @@ #ifndef __ASM_POWERPC_REG_FSL_EMB_H__ #define __ASM_POWERPC_REG_FSL_EMB_H__ +#include <linux/stringify.h> + #ifndef __ASSEMBLY__ /* Performance Monitor Registers */ #define mfpmr(rn) ({unsigned int rval; \ diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 44989b22383c..759597bf0fd8 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -22,6 +22,7 @@ enum stf_barrier_type { void setup_stf_barrier(void); void do_stf_barrier_fixups(enum stf_barrier_type types); +void setup_count_cache_flush(void); static inline void security_ftr_set(unsigned long feature) { @@ -59,6 +60,9 @@ static inline bool security_ftr_enabled(unsigned long feature) // Indirect branch prediction cache disabled #define SEC_FTR_COUNT_CACHE_DISABLED 0x0000000000000020ull +// bcctr 2,0,0 triggers a hardware assisted count cache flush +#define SEC_FTR_BCCTR_FLUSH_ASSIST 0x0000000000000800ull + // Features indicating need for Spectre/Meltdown mitigations @@ -74,6 +78,9 @@ static inline bool security_ftr_enabled(unsigned long feature) // Firmware configuration indicates user favours security over performance #define SEC_FTR_FAVOUR_SECURITY 0x0000000000000200ull +// Software required to flush count cache on context switch +#define SEC_FTR_FLUSH_COUNT_CACHE 0x0000000000000400ull + // Features enabled by default #define SEC_FTR_DEFAULT \ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 8721fd004291..1a951b00465d 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -52,11 +52,15 @@ enum l1d_flush_type { void setup_rfi_flush(enum l1d_flush_type, bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); +#ifdef CONFIG_PPC_BARRIER_NOSPEC void setup_barrier_nospec(void); +#else +static inline void setup_barrier_nospec(void) { }; +#endif void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_BARRIER_NOSPEC void do_barrier_nospec_fixups_range(bool enable, void *start, void *end); #else static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 29ffaabdf75b..95b66a0c639b 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -56,7 +56,6 @@ struct smp_ops_t { int (*cpu_bootable)(unsigned int nr); }; -extern void smp_flush_nmi_ipi(u64 delay_us); extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern int smp_send_safe_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern void smp_send_debugger_break(void); diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index bc66712bdc3c..28f5dae25db6 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -6,13 +6,20 @@ #ifdef CONFIG_SPARSEMEM /* * SECTION_SIZE_BITS 2^N: how big each section will be - * MAX_PHYSADDR_BITS 2^N: how much physical address space we have * MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space */ #define SECTION_SIZE_BITS 24 - -#define MAX_PHYSADDR_BITS 46 +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. + */ +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define MAX_PHYSMEM_BITS 47 +#else #define MAX_PHYSMEM_BITS 46 +#endif #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 72dc4ddc2972..685c72310f5d 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -24,9 +24,9 @@ #include <asm/paca.h> #include <asm/hvcall.h> #endif -#include <asm/asm-compat.h> #include <asm/synch.h> #include <asm/ppc-opcode.h> +#include <asm/asm-405.h> #ifdef CONFIG_PPC64 /* use 0x800000yy when locked, where yy == CPU number */ diff --git a/arch/powerpc/include/asm/stacktrace.h b/arch/powerpc/include/asm/stacktrace.h new file mode 100644 index 000000000000..6149b53b3bc8 --- /dev/null +++ b/arch/powerpc/include/asm/stacktrace.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Stack trace functions. + * + * Copyright 2018, Murilo Opsfelder Araujo, IBM Corporation. + */ + +#ifndef _ASM_POWERPC_STACKTRACE_H +#define _ASM_POWERPC_STACKTRACE_H + +void show_user_instructions(struct pt_regs *regs); + +#endif /* _ASM_POWERPC_STACKTRACE_H */ diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index 9b8cedf618f4..1647de15a31e 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -50,6 +50,8 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n) return __memset64(p, v, n * 8); } #else +#define __HAVE_ARCH_STRLEN + extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index 6ec546090ba1..aca70fb43147 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -3,8 +3,8 @@ #define _ASM_POWERPC_SYNCH_H #ifdef __KERNEL__ -#include <linux/stringify.h> #include <asm/feature-fixups.h> +#include <asm/asm-const.h> #ifndef __ASSEMBLY__ extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index f308dfeb2746..3c0002044bc9 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -9,6 +9,8 @@ #ifndef _ASM_POWERPC_THREAD_INFO_H #define _ASM_POWERPC_THREAD_INFO_H +#include <asm/asm-const.h> + #ifdef __KERNEL__ #define THREAD_SHIFT CONFIG_THREAD_SHIFT @@ -25,7 +27,6 @@ #include <linux/cache.h> #include <asm/processor.h> #include <asm/page.h> -#include <linux/stringify.h> #include <asm/accounting.h> /* diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 9138baccebb0..f0e571b2dc7c 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -17,7 +17,6 @@ #include <asm/pgtable.h> #endif #include <asm/pgalloc.h> -#include <asm/tlbflush.h> #ifndef __powerpc64__ #include <asm/page.h> #include <asm/mmu.h> @@ -53,7 +52,8 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, if (!tlb->page_size) tlb->page_size = page_size; else if (tlb->page_size != page_size) { - tlb_flush_mmu(tlb); + if (!tlb->fullmm) + tlb_flush_mmu(tlb); /* * update the page size after flush for the new * mmu_gather. diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 7d5a157c7832..61fba43bf8b2 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -1,87 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_TLBFLUSH_H #define _ASM_POWERPC_TLBFLUSH_H -/* - * TLB flushing: - * - * - flush_tlb_mm(mm) flushes the specified mm context TLB's - * - flush_tlb_page(vma, vmaddr) flushes one page - * - local_flush_tlb_mm(mm, full) flushes the specified mm context on - * the local processor - * - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor - * - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB - * - flush_tlb_range(vma, start, end) flushes a range of pages - * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#ifdef __KERNEL__ - -#ifdef CONFIG_PPC_MMU_NOHASH -/* - * TLB flushing for software loaded TLB chips - * - * TODO: (CONFIG_FSL_BOOKE) determine if flush_tlb_range & - * flush_tlb_kernel_range are best implemented as tlbia vs - * specific tlbie's - */ - -struct vm_area_struct; -struct mm_struct; - -#define MMU_NO_CONTEXT ((unsigned int)-1) - -extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end); -extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); - -extern void local_flush_tlb_mm(struct mm_struct *mm); -extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); - -extern void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, - int tsize, int ind); - -#ifdef CONFIG_SMP -extern void flush_tlb_mm(struct mm_struct *mm); -extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, - int tsize, int ind); -#else -#define flush_tlb_mm(mm) local_flush_tlb_mm(mm) -#define flush_tlb_page(vma,addr) local_flush_tlb_page(vma,addr) -#define __flush_tlb_page(mm,addr,p,i) __local_flush_tlb_page(mm,addr,p,i) -#endif - -#elif defined(CONFIG_PPC_STD_MMU_32) - -#define MMU_NO_CONTEXT (0) -/* - * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx - */ -extern void flush_tlb_mm(struct mm_struct *mm); -extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr); -extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end); -extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -static inline void local_flush_tlb_page(struct vm_area_struct *vma, - unsigned long vmaddr) -{ - flush_tlb_page(vma, vmaddr); -} -static inline void local_flush_tlb_mm(struct mm_struct *mm) -{ - flush_tlb_mm(mm); -} - -#elif defined(CONFIG_PPC_BOOK3S_64) -#include <asm/book3s/64/tlbflush.h> +#ifdef CONFIG_PPC_BOOK3S +#include <asm/book3s/tlbflush.h> #else -#error Unsupported MMU type -#endif +#include <asm/nohash/tlbflush.h> +#endif /* !CONFIG_PPC_BOOK3S */ -#endif /*__KERNEL__ */ #endif /* _ASM_POWERPC_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 468653ce844c..bac225bb7f64 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -2,7 +2,6 @@ #ifndef _ARCH_POWERPC_UACCESS_H #define _ARCH_POWERPC_UACCESS_H -#include <asm/asm-compat.h> #include <asm/ppc_asm.h> #include <asm/processor.h> #include <asm/page.h> @@ -250,10 +249,17 @@ do { \ } \ } while (0) +/* + * This is a type: either unsigned long, if the argument fits into + * that type, or otherwise unsigned long long. + */ +#define __long_type(x) \ + __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) + #define __get_user_nocheck(x, ptr, size) \ ({ \ long __gu_err; \ - unsigned long __gu_val; \ + __long_type(*(ptr)) __gu_val; \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ @@ -267,7 +273,7 @@ do { \ #define __get_user_check(x, ptr, size) \ ({ \ long __gu_err = -EFAULT; \ - unsigned long __gu_val = 0; \ + __long_type(*(ptr)) __gu_val = 0; \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ might_fault(); \ if (access_ok(VERIFY_READ, __gu_addr, (size))) { \ @@ -281,7 +287,7 @@ do { \ #define __get_user_nosleep(x, ptr, size) \ ({ \ long __gu_err; \ - unsigned long __gu_val; \ + __long_type(*(ptr)) __gu_val; \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ barrier_nospec(); \ diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index 8d1a2792484f..3c704f5dd3ae 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -87,7 +87,6 @@ extern int xive_smp_prepare_cpu(unsigned int cpu); extern void xive_smp_setup_cpu(void); extern void xive_smp_disable_cpu(void); extern void xive_teardown_cpu(void); -extern void xive_kexec_teardown_cpu(int secondary); extern void xive_shutdown(void); extern void xive_flush_interrupt(void); diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 2b4c40b255e4..3b66f2c19c84 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -7,10 +7,10 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror -ifeq ($(CONFIG_PPC64),y) +ifdef CONFIG_PPC64 CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) endif -ifeq ($(CONFIG_PPC32),y) +ifdef CONFIG_PPC32 CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC endif @@ -42,9 +42,10 @@ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o -obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o security.o +obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o +obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o @@ -62,13 +63,13 @@ obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \ obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_FA_DUMP) += fadump.o -ifeq ($(CONFIG_PPC32),y) +ifdef CONFIG_PPC32 obj-$(CONFIG_E500) += idle_e500.o endif obj-$(CONFIG_6xx) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o obj-$(CONFIG_TAU) += tau_6xx.o obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o -ifeq ($(CONFIG_FSL_BOOKE),y) +ifdef CONFIG_FSL_BOOKE obj-$(CONFIG_HIBERNATION) += swsusp_booke.o else obj-$(CONFIG_HIBERNATION) += swsusp_$(BITS).o @@ -109,9 +110,11 @@ obj-$(CONFIG_PCI_MSI) += msi.o obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o crash.o \ machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file_$(BITS).o kexec_elf_$(BITS).o -ifeq ($(CONFIG_HAVE_IMA_KEXEC)$(CONFIG_IMA),yy) +ifdef CONFIG_HAVE_IMA_KEXEC +ifdef CONFIG_IMA obj-y += ima_kexec.o endif +endif obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o @@ -164,7 +167,7 @@ PHONY += systbl_chk systbl_chk: $(src)/systbl_chk.sh $(obj)/systbl_chk.i $(call cmd,systbl_chk) -ifeq ($(CONFIG_PPC_OF_BOOT_TRAMPOLINE),y) +ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE $(obj)/built-in.a: prom_init_check quiet_cmd_prom_init_check = CALL $< diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0a0544335950..89cf15566c4e 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -766,7 +766,6 @@ int main(void) OFFSET(PACA_THREAD_IDLE_STATE, paca_struct, thread_idle_state); OFFSET(PACA_THREAD_MASK, paca_struct, thread_mask); OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask); - OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas); OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr); OFFSET(PACA_DONT_STOP, paca_struct, dont_stop); #define STOP_SPR(x, f) OFFSET(x, paca_struct, stop_sprs.f) diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index a9f3970693e1..fa3c2c91290c 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -16,6 +16,7 @@ #include <asm/asm-offsets.h> #include <asm/cache.h> #include <asm/mmu.h> +#include <asm/feature-fixups.h> _GLOBAL(__setup_cpu_603) mflr r5 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index c8fc9691f8c7..2da01340c84c 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -447,25 +447,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, - { /* Power8 DD1: Does not support doorbell IPIs */ - .pvr_mask = 0xffffff00, - .pvr_value = 0x004d0100, - .cpu_name = "POWER8 (raw)", - .cpu_features = CPU_FTRS_POWER8_DD1, - .cpu_user_features = COMMON_USER_POWER8, - .cpu_user_features2 = COMMON_USER2_POWER8, - .mmu_features = MMU_FTRS_POWER8, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", - .oprofile_type = PPC_OPROFILE_INVALID, - .cpu_setup = __setup_cpu_power8, - .cpu_restore = __restore_cpu_power8, - .machine_check_early = __machine_check_early_realmode_p8, - .platform = "power8", - }, { /* Power8 */ .pvr_mask = 0xffff0000, .pvr_value = 0x004d0000, @@ -485,25 +466,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, - { /* Power9 DD1*/ - .pvr_mask = 0xffffff00, - .pvr_value = 0x004e0100, - .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD1, - .cpu_user_features = COMMON_USER_POWER9, - .cpu_user_features2 = COMMON_USER2_POWER9, - .mmu_features = MMU_FTRS_POWER9, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 6, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", - .oprofile_type = PPC_OPROFILE_INVALID, - .cpu_setup = __setup_cpu_power9, - .cpu_restore = __restore_cpu_power9, - .machine_check_early = __machine_check_early_realmode_p9, - .platform = "power9", - }, { /* Power9 DD2.0 */ .pvr_mask = 0xffffefff, .pvr_value = 0x004e0200, diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 17c8b99680f2..43a3ce2301e8 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -23,7 +23,6 @@ #include <asm/processor.h> #include <asm/machdep.h> #include <asm/kexec.h> -#include <asm/kdump.h> #include <asm/prom.h> #include <asm/smp.h> #include <asm/setjmp.h> diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 155170d70324..dbfc7056d7df 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -357,9 +357,6 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask); static int __init dma_init(void) { -#ifdef CONFIG_PCI - dma_debug_add_bus(&pci_bus_type); -#endif #ifdef CONFIG_IBMVIO dma_debug_add_bus(&vio_bus_type); #endif diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 96dd3d871986..f432054234a4 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -701,9 +701,7 @@ static __init void cpufeatures_cpu_quirks(void) /* * Not all quirks can be derived from the cpufeatures device tree. */ - if ((version & 0xffffff00) == 0x004e0100) - cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1; - else if ((version & 0xffffefff) == 0x004e0200) + if ((version & 0xffffefff) == 0x004e0200) ; /* DD2.0 has no feature flag */ else if ((version & 0xffffefff) == 0x004e0201) cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 5746809cfaad..6ebba3e48b01 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1087,7 +1087,7 @@ static int eeh_init(void) if (eeh_enabled()) pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); - else + else if (!eeh_has_flag(EEH_POSTPONED_PROBE)) pr_info("EEH: No capable adapters found\n"); return ret; diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 973577f2141c..e58c3f467db5 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -33,6 +33,9 @@ #include <asm/unistd.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/asm-405.h> +#include <asm/feature-fixups.h> +#include <asm/barrier.h> /* * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE. @@ -358,6 +361,15 @@ syscall_dotrace_cont: ori r10,r10,sys_call_table@l slwi r0,r0,2 bge- 66f + + barrier_nospec_asm + /* + * Prevent the load of the handler below (based on the user-passed + * system call number) being speculatively executed until the test + * against NR_syscalls and branch to .66f above has + * committed. + */ + lwzx r10,r10,r0 /* Fetch system call handler [ptr] */ mtlr r10 addi r9,r1,STACK_FRAME_OVERHEAD diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 729e9ef4d3bb..2206912ea4f0 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -25,6 +25,7 @@ #include <asm/page.h> #include <asm/mmu.h> #include <asm/thread_info.h> +#include <asm/code-patching-asm.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/cputable.h> @@ -38,11 +39,13 @@ #include <asm/ppc-opcode.h> #include <asm/barrier.h> #include <asm/export.h> +#include <asm/asm-compat.h> #ifdef CONFIG_PPC_BOOK3S #include <asm/exception-64s.h> #else #include <asm/exception-64e.h> #endif +#include <asm/feature-fixups.h> /* * System calls. @@ -504,6 +507,57 @@ _GLOBAL(ret_from_kernel_thread) li r3,0 b .Lsyscall_exit +#ifdef CONFIG_PPC_BOOK3S_64 + +#define FLUSH_COUNT_CACHE \ +1: nop; \ + patch_site 1b, patch__call_flush_count_cache + + +#define BCCTR_FLUSH .long 0x4c400420 + +.macro nops number + .rept \number + nop + .endr +.endm + +.balign 32 +.global flush_count_cache +flush_count_cache: + /* Save LR into r9 */ + mflr r9 + + .rept 64 + bl .+4 + .endr + b 1f + nops 6 + + .balign 32 + /* Restore LR */ +1: mtlr r9 + li r9,0x7fff + mtctr r9 + + BCCTR_FLUSH + +2: nop + patch_site 2b patch__flush_count_cache_return + + nops 3 + + .rept 278 + .balign 32 + BCCTR_FLUSH + nops 7 + .endr + + blr +#else +#define FLUSH_COUNT_CACHE +#endif /* CONFIG_PPC_BOOK3S_64 */ + /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state @@ -535,6 +589,8 @@ _GLOBAL(_switch) std r23,_CCR(r1) std r1,KSP(r3) /* Set old stack pointer */ + FLUSH_COUNT_CACHE + /* * On SMP kernels, care must be taken because a task may be * scheduled off CPUx and on to CPUy. Memory ordering must be @@ -993,6 +1049,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) std r4,_TRAP(r1) /* + * PACA_IRQ_HARD_DIS won't always be set here, so set it now + * to reconcile the IRQ state. Tracing is already accounted for. + */ + lbz r4,PACAIRQHAPPENED(r13) + ori r4,r4,PACA_IRQ_HARD_DIS + stb r4,PACAIRQHAPPENED(r13) + + /* * Then find the right handler and call it. Interrupts are * still soft-disabled and we keep them that way. */ diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 9b6e653e501a..6d6e144a28ce 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -27,6 +27,7 @@ #include <asm/hw_irq.h> #include <asm/kvm_asm.h> #include <asm/kvm_booke_hv_asm.h> +#include <asm/feature-fixups.h> /* XXX This will ultimately add space for a special exception save * structure used to save things like SRR0/SRR1, SPRGs, MAS, etc... @@ -949,7 +950,11 @@ kernel_dbg_exc: .macro masked_interrupt_book3e paca_irq full_mask lbz r10,PACAIRQHAPPENED(r13) + .if \full_mask == 1 + ori r10,r10,\paca_irq | PACA_IRQ_HARD_DIS + .else ori r10,r10,\paca_irq + .endif stb r10,PACAIRQHAPPENED(r13) .if \full_mask == 1 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 285c6465324a..ea04dfb8c092 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -18,6 +18,7 @@ #include <asm/ptrace.h> #include <asm/cpuidle.h> #include <asm/head-64.h> +#include <asm/feature-fixups.h> /* * There are a few constraints to be concerned with. @@ -126,8 +127,8 @@ EXC_REAL_BEGIN(system_reset, 0x100, 0x100) * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is * being used, so a nested NMI exception would corrupt it. */ - EXCEPTION_PROLOG_PSERIES_NORI(PACA_EXNMI, system_reset_common, EXC_STD, - IDLETEST, 0x100) + EXCEPTION_PROLOG_NORI(PACA_EXNMI, system_reset_common, EXC_STD, + IDLETEST, 0x100) EXC_REAL_END(system_reset, 0x100, 0x100) EXC_VIRT_NONE(0x4100, 0x100) @@ -230,8 +231,8 @@ EXC_COMMON_BEGIN(system_reset_common) TRAMP_REAL_BEGIN(system_reset_fwnmi) SET_SCRATCH0(r13) /* save r13 */ /* See comment at system_reset exception */ - EXCEPTION_PROLOG_PSERIES_NORI(PACA_EXNMI, system_reset_common, - EXC_STD, NOTEST, 0x100) + EXCEPTION_PROLOG_NORI(PACA_EXNMI, system_reset_common, EXC_STD, + NOTEST, 0x100) #endif /* CONFIG_PPC_PSERIES */ @@ -276,9 +277,7 @@ BEGIN_FTR_SECTION * * This interrupt can wake directly from idle. If that is the case, * the machine check is handled then the idle wakeup code is called - * to restore state. In that case, the POWER9 DD1 idle PACA workaround - * is not applied in the early machine check code, which will cause - * bugs. + * to restore state. */ mr r11,r1 /* Save r1 */ lhz r10,PACA_IN_MCE(r13) @@ -339,7 +338,7 @@ machine_check_pSeries_0: * nested machine check corrupts it. machine_check_common enables * MSR_RI. */ - EXCEPTION_PROLOG_PSERIES_1_NORI(machine_check_common, EXC_STD) + EXCEPTION_PROLOG_2_NORI(machine_check_common, EXC_STD) TRAMP_KVM_SKIP(PACA_EXMC, 0x200) @@ -769,13 +768,9 @@ EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100) .globl hardware_interrupt_hv; hardware_interrupt_hv: BEGIN_FTR_SECTION - _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, - EXC_HV, SOFTEN_TEST_HV, - IRQS_DISABLED) + MASKABLE_EXCEPTION_HV(0x500, hardware_interrupt_common, IRQS_DISABLED) FTR_SECTION_ELSE - _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, - EXC_STD, SOFTEN_TEST_PR, - IRQS_DISABLED) + MASKABLE_EXCEPTION(0x500, hardware_interrupt_common, IRQS_DISABLED) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) EXC_REAL_END(hardware_interrupt, 0x500, 0x100) @@ -783,13 +778,11 @@ EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100) .globl hardware_interrupt_relon_hv; hardware_interrupt_relon_hv: BEGIN_FTR_SECTION - _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, - EXC_HV, SOFTEN_TEST_HV, - IRQS_DISABLED) + MASKABLE_RELON_EXCEPTION_HV(0x500, hardware_interrupt_common, + IRQS_DISABLED) FTR_SECTION_ELSE - _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, - EXC_STD, SOFTEN_TEST_PR, - IRQS_DISABLED) + __MASKABLE_RELON_EXCEPTION(0x500, hardware_interrupt_common, + EXC_STD, SOFTEN_TEST_PR, IRQS_DISABLED) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100) @@ -1328,7 +1321,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) #endif KVMTEST_HV(0x1500) - EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV) + EXCEPTION_PROLOG_2(denorm_common, EXC_HV) EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100) #ifdef CONFIG_PPC_DENORMALISATION @@ -1448,7 +1441,7 @@ EXC_VIRT_NONE(0x5800, 0x100) std r12,PACA_EXGEN+EX_R12(r13); \ GET_SCRATCH0(r10); \ std r10,PACA_EXGEN+EX_R13(r13); \ - EXCEPTION_PROLOG_PSERIES_1(soft_nmi_common, _H) + EXCEPTION_PROLOG_2(soft_nmi_common, _H) /* * Branch to soft_nmi_interrupt using the emergency stack. The emergency @@ -1500,7 +1493,10 @@ masked_##_H##interrupt: \ mfspr r10,SPRN_##_H##SRR1; \ xori r10,r10,MSR_EE; /* clear MSR_EE */ \ mtspr SPRN_##_H##SRR1,r10; \ -2: mtcrf 0x80,r9; \ + ori r11,r11,PACA_IRQ_HARD_DIS; \ + stb r11,PACAIRQHAPPENED(r13); \ +2: /* done */ \ + mtcrf 0x80,r9; \ std r1,PACAR1(r13); \ ld r9,PACA_EXGEN+EX_R9(r13); \ ld r10,PACA_EXGEN+EX_R10(r13); \ @@ -1526,6 +1522,8 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback) TRAMP_REAL_BEGIN(rfi_flush_fallback) SET_SCRATCH0(r13); GET_PACA(r13); + std r1,PACA_EXRFI+EX_R12(r13) + ld r1,PACAKSAVE(r13) std r9,PACA_EXRFI+EX_R9(r13) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) @@ -1560,12 +1558,15 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) ld r11,PACA_EXRFI+EX_R11(r13) + ld r1,PACA_EXRFI+EX_R12(r13) GET_SCRATCH0(r13); rfid TRAMP_REAL_BEGIN(hrfi_flush_fallback) SET_SCRATCH0(r13); GET_PACA(r13); + std r1,PACA_EXRFI+EX_R12(r13) + ld r1,PACAKSAVE(r13) std r9,PACA_EXRFI+EX_R9(r13) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) @@ -1600,6 +1601,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) ld r11,PACA_EXRFI+EX_R11(r13) + ld r1,PACA_EXRFI+EX_R12(r13) GET_SCRATCH0(r13); hrfid diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 07e8396d472b..986ec476fd5d 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -47,8 +47,10 @@ static struct fadump_mem_struct fdm; static const struct fadump_mem_struct *fdm_active; static DEFINE_MUTEX(fadump_mutex); -struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES]; +struct fad_crash_memory_ranges *crash_memory_ranges; +int crash_memory_ranges_size; int crash_mem_ranges; +int max_crash_mem_ranges; /* Scan the Firmware Assisted dump configuration details. */ int __init early_init_dt_scan_fw_dump(unsigned long node, @@ -868,38 +870,107 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active) return 0; } -static inline void fadump_add_crash_memory(unsigned long long base, - unsigned long long end) +static void free_crash_memory_ranges(void) +{ + kfree(crash_memory_ranges); + crash_memory_ranges = NULL; + crash_memory_ranges_size = 0; + max_crash_mem_ranges = 0; +} + +/* + * Allocate or reallocate crash memory ranges array in incremental units + * of PAGE_SIZE. + */ +static int allocate_crash_memory_ranges(void) { + struct fad_crash_memory_ranges *new_array; + u64 new_size; + + new_size = crash_memory_ranges_size + PAGE_SIZE; + pr_debug("Allocating %llu bytes of memory for crash memory ranges\n", + new_size); + + new_array = krealloc(crash_memory_ranges, new_size, GFP_KERNEL); + if (new_array == NULL) { + pr_err("Insufficient memory for setting up crash memory ranges\n"); + free_crash_memory_ranges(); + return -ENOMEM; + } + + crash_memory_ranges = new_array; + crash_memory_ranges_size = new_size; + max_crash_mem_ranges = (new_size / + sizeof(struct fad_crash_memory_ranges)); + return 0; +} + +static inline int fadump_add_crash_memory(unsigned long long base, + unsigned long long end) +{ + u64 start, size; + bool is_adjacent = false; + if (base == end) - return; + return 0; + + /* + * Fold adjacent memory ranges to bring down the memory ranges/ + * PT_LOAD segments count. + */ + if (crash_mem_ranges) { + start = crash_memory_ranges[crash_mem_ranges - 1].base; + size = crash_memory_ranges[crash_mem_ranges - 1].size; + + if ((start + size) == base) + is_adjacent = true; + } + if (!is_adjacent) { + /* resize the array on reaching the limit */ + if (crash_mem_ranges == max_crash_mem_ranges) { + int ret; + + ret = allocate_crash_memory_ranges(); + if (ret) + return ret; + } + start = base; + crash_memory_ranges[crash_mem_ranges].base = start; + crash_mem_ranges++; + } + + crash_memory_ranges[crash_mem_ranges - 1].size = (end - start); pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n", - crash_mem_ranges, base, end - 1, (end - base)); - crash_memory_ranges[crash_mem_ranges].base = base; - crash_memory_ranges[crash_mem_ranges].size = end - base; - crash_mem_ranges++; + (crash_mem_ranges - 1), start, end - 1, (end - start)); + return 0; } -static void fadump_exclude_reserved_area(unsigned long long start, +static int fadump_exclude_reserved_area(unsigned long long start, unsigned long long end) { unsigned long long ra_start, ra_end; + int ret = 0; ra_start = fw_dump.reserve_dump_area_start; ra_end = ra_start + fw_dump.reserve_dump_area_size; if ((ra_start < end) && (ra_end > start)) { if ((start < ra_start) && (end > ra_end)) { - fadump_add_crash_memory(start, ra_start); - fadump_add_crash_memory(ra_end, end); + ret = fadump_add_crash_memory(start, ra_start); + if (ret) + return ret; + + ret = fadump_add_crash_memory(ra_end, end); } else if (start < ra_start) { - fadump_add_crash_memory(start, ra_start); + ret = fadump_add_crash_memory(start, ra_start); } else if (ra_end < end) { - fadump_add_crash_memory(ra_end, end); + ret = fadump_add_crash_memory(ra_end, end); } } else - fadump_add_crash_memory(start, end); + ret = fadump_add_crash_memory(start, end); + + return ret; } static int fadump_init_elfcore_header(char *bufp) @@ -939,13 +1010,22 @@ static int fadump_init_elfcore_header(char *bufp) * Traverse through memblock structure and setup crash memory ranges. These * ranges will be used create PT_LOAD program headers in elfcore header. */ -static void fadump_setup_crash_memory_ranges(void) +static int fadump_setup_crash_memory_ranges(void) { struct memblock_region *reg; unsigned long long start, end; + int ret; pr_debug("Setup crash memory ranges.\n"); crash_mem_ranges = 0; + + /* allocate memory for crash memory ranges for the first time */ + if (!max_crash_mem_ranges) { + ret = allocate_crash_memory_ranges(); + if (ret) + return ret; + } + /* * add the first memory chunk (RMA_START through boot_memory_size) as * a separate memory chunk. The reason is, at the time crash firmware @@ -953,7 +1033,9 @@ static void fadump_setup_crash_memory_ranges(void) * specified during fadump registration. We need to create a separate * program header for this chunk with the correct offset. */ - fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size); + ret = fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size); + if (ret) + return ret; for_each_memblock(memory, reg) { start = (unsigned long long)reg->base; @@ -973,8 +1055,12 @@ static void fadump_setup_crash_memory_ranges(void) } /* add this range excluding the reserved dump area. */ - fadump_exclude_reserved_area(start, end); + ret = fadump_exclude_reserved_area(start, end); + if (ret) + return ret; } + + return 0; } /* @@ -1097,6 +1183,7 @@ static int register_fadump(void) { unsigned long addr; void *vaddr; + int ret; /* * If no memory is reserved then we can not register for firmware- @@ -1105,7 +1192,9 @@ static int register_fadump(void) if (!fw_dump.reserve_dump_area_size) return -ENODEV; - fadump_setup_crash_memory_ranges(); + ret = fadump_setup_crash_memory_ranges(); + if (ret) + return ret; addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len); /* Initialize fadump crash info header. */ @@ -1183,6 +1272,7 @@ void fadump_cleanup(void) } else if (fw_dump.dump_registered) { /* Un-register Firmware-assisted dump if it was registered. */ fadump_unregister_dump(&fdm); + free_crash_memory_ranges(); } } diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 6c509f39bbde..529dcc21c3f9 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -25,6 +25,8 @@ #include <asm/asm-offsets.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> #ifdef CONFIG_VSX #define __REST_32FPVSRS(n,c,base) \ diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 29b2fed93289..61ca27929355 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -35,6 +35,7 @@ #include <asm/bug.h> #include <asm/kvm_book3s_asm.h> #include <asm/export.h> +#include <asm/feature-fixups.h> /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */ #define LOAD_BAT(n, reg, RA, RB) \ diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 41374a468d1c..b19d78410511 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -42,6 +42,7 @@ #include <asm/asm-offsets.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/asm-405.h> /* As with the other PowerPC ports, it is expected that when code * execution begins here, the following registers contain valid, yet diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 6eca15f25c73..4898e9491a1c 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -44,6 +44,7 @@ #include <asm/cputhreads.h> #include <asm/ppc-opcode.h> #include <asm/export.h> +#include <asm/feature-fixups.h> /* The physical memory is laid out such that the secondary processor * spin code sits at 0x0000...0x00ff. On server, the vectors follow diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 6cab07e76732..6582f824d620 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -30,7 +30,6 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> -#include <asm/fixmap.h> #include <asm/export.h> #if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000 @@ -873,6 +872,10 @@ start_here: li r0,0 stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) + lis r6, swapper_pg_dir@ha + tophys(r6,r6) + mtspr SPRN_M_TW, r6 + bl early_init /* We have to do this with MMU on */ /* @@ -893,9 +896,6 @@ start_here: * init's THREAD like the context switch code does, but this is * easier......until someone changes init's static structures. */ - lis r6, swapper_pg_dir@ha - tophys(r6,r6) - mtspr SPRN_M_TW, r6 lis r4,2f@h ori r4,r4,2f@l tophys(r4,r4) diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index bf4c6021515f..e2750b856c8f 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -43,6 +43,7 @@ #include <asm/cache.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/feature-fixups.h> #include "head_booke.h" /* As with the other PowerPC ports, it is expected that when code diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 80547dad37da..fec8a6773119 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -119,11 +119,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp) /* * Check for virtual address in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - return is_kernel_addr(info->address); + return is_kernel_addr(hw->address); } int arch_bp_generic_fields(int type, int *gen_bp_type) @@ -141,30 +139,31 @@ int arch_bp_generic_fields(int type, int *gen_bp_type) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { int ret = -EINVAL, length_max; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); if (!bp) return ret; - info->type = HW_BRK_TYPE_TRANSLATE; - if (bp->attr.bp_type & HW_BREAKPOINT_R) - info->type |= HW_BRK_TYPE_READ; - if (bp->attr.bp_type & HW_BREAKPOINT_W) - info->type |= HW_BRK_TYPE_WRITE; - if (info->type == HW_BRK_TYPE_TRANSLATE) + hw->type = HW_BRK_TYPE_TRANSLATE; + if (attr->bp_type & HW_BREAKPOINT_R) + hw->type |= HW_BRK_TYPE_READ; + if (attr->bp_type & HW_BREAKPOINT_W) + hw->type |= HW_BRK_TYPE_WRITE; + if (hw->type == HW_BRK_TYPE_TRANSLATE) /* must set alteast read or write */ return ret; - if (!(bp->attr.exclude_user)) - info->type |= HW_BRK_TYPE_USER; - if (!(bp->attr.exclude_kernel)) - info->type |= HW_BRK_TYPE_KERNEL; - if (!(bp->attr.exclude_hv)) - info->type |= HW_BRK_TYPE_HYP; - info->address = bp->attr.bp_addr; - info->len = bp->attr.bp_len; + if (!attr->exclude_user) + hw->type |= HW_BRK_TYPE_USER; + if (!attr->exclude_kernel) + hw->type |= HW_BRK_TYPE_KERNEL; + if (!attr->exclude_hv) + hw->type |= HW_BRK_TYPE_HYP; + hw->address = attr->bp_addr; + hw->len = attr->bp_len; /* * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8) @@ -178,12 +177,12 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) if (cpu_has_feature(CPU_FTR_DAWR)) { length_max = 512 ; /* 64 doublewords */ /* DAWR region can't cross 512 boundary */ - if ((bp->attr.bp_addr >> 9) != - ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9)) + if ((attr->bp_addr >> 9) != + ((attr->bp_addr + attr->bp_len - 1) >> 9)) return -EINVAL; } - if (info->len > - (length_max - (info->address & HW_BREAKPOINT_ALIGN))) + if (hw->len > + (length_max - (hw->address & HW_BREAKPOINT_ALIGN))) return -EINVAL; return 0; } diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S index 1686916cc7f0..ff026c9d3cab 100644 --- a/arch/powerpc/kernel/idle_6xx.S +++ b/arch/powerpc/kernel/idle_6xx.S @@ -20,6 +20,7 @@ #include <asm/thread_info.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> +#include <asm/feature-fixups.h> .text diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S index 2b269315d377..4e0d94d02030 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_book3e.S @@ -36,7 +36,7 @@ _GLOBAL(\name) */ lbz r3,PACAIRQHAPPENED(r13) cmpwi cr0,r3,0 - bnelr + bne 2f /* Now we are going to mark ourselves as soft and hard enabled in * order to be able to take interrupts while asleep. We inform lockdep @@ -72,6 +72,11 @@ _GLOBAL(\name) wrteei 1 \loop +2: + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,PACA_IRQ_HARD_DIS + stb r10,PACAIRQHAPPENED(r13) + blr .endm .macro BOOK3E_IDLE_LOOP diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 689306118b48..7f5ac2e8581b 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -23,6 +23,8 @@ #include <asm/exception-64s.h> #include <asm/book3s/64/mmu-hash.h> #include <asm/mmu.h> +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> #undef DEBUG @@ -469,43 +471,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG) #endif /* - * On waking up from stop 0,1,2 with ESL=1 on POWER9 DD1, - * HSPRG0 will be set to the HSPRG0 value of one of the - * threads in this core. Thus the value we have in r13 - * may not be this thread's paca pointer. - * - * Fortunately, the TIR remains invariant. Since this thread's - * paca pointer is recorded in all its sibling's paca, we can - * correctly recover this thread's paca pointer if we - * know the index of this thread in the core. - * - * This index can be obtained from the TIR. - * - * i.e, thread's position in the core = TIR. - * If this value is i, then this thread's paca is - * paca->thread_sibling_pacas[i]. - */ -power9_dd1_recover_paca: - mfspr r4, SPRN_TIR - /* - * Since each entry in thread_sibling_pacas is 8 bytes - * we need to left-shift by 3 bits. Thus r4 = i * 8 - */ - sldi r4, r4, 3 - /* Get &paca->thread_sibling_pacas[0] in r5 */ - ld r5, PACA_SIBLING_PACA_PTRS(r13) - /* Load paca->thread_sibling_pacas[i] into r13 */ - ldx r13, r4, r5 - SET_PACA(r13) - /* - * Indicate that we have lost NVGPR state - * which needs to be restored from the stack. - */ - li r3, 1 - stb r3,PACA_NAPSTATELOST(r13) - blr - -/* * Called from machine check handler for powersave wakeups. * Low level machine check processing has already been done. Now just * go through the wake up path to get everything in order. @@ -539,9 +504,6 @@ pnv_powersave_wakeup: ld r2, PACATOC(r13) BEGIN_FTR_SECTION -BEGIN_FTR_SECTION_NESTED(70) - bl power9_dd1_recover_paca -END_FTR_SECTION_NESTED_IFSET(CPU_FTR_POWER9_DD1, 70) bl pnv_restore_hyp_resource_arch300 FTR_SECTION_ELSE bl pnv_restore_hyp_resource_arch207 @@ -604,22 +566,12 @@ END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1) LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state) ld r4,ADDROFF(pnv_first_deep_stop_state)(r5) -BEGIN_FTR_SECTION_NESTED(71) - /* - * Assume that we are waking up from the state - * same as the Requested Level (RL) in the PSSCR - * which are Bits 60-63 - */ - ld r5,PACA_REQ_PSSCR(r13) - rldicl r5,r5,0,60 -FTR_SECTION_ELSE_NESTED(71) /* * 0-3 bits correspond to Power-Saving Level Status * which indicates the idle state we are waking up from */ mfspr r5, SPRN_PSSCR rldicl r5,r5,4,60 -ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_POWER9_DD1, 71) li r0, 0 /* clear requested_psscr to say we're awake */ std r0, PACA_REQ_PSSCR(r13) cmpd cr4,r5,r4 diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S index b9b6ef510be1..583e55ac7d26 100644 --- a/arch/powerpc/kernel/idle_e500.S +++ b/arch/powerpc/kernel/idle_e500.S @@ -17,6 +17,7 @@ #include <asm/thread_info.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> +#include <asm/feature-fixups.h> .text diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S index 08faa93755f9..dd7471fe20bd 100644 --- a/arch/powerpc/kernel/idle_power4.S +++ b/arch/powerpc/kernel/idle_power4.S @@ -16,6 +16,7 @@ #include <asm/asm-offsets.h> #include <asm/irqflags.h> #include <asm/hw_irq.h> +#include <asm/feature-fixups.h> #undef DEBUG diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 0682fef1f385..916ddc4aac44 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -145,8 +145,20 @@ notrace unsigned int __check_irq_replay(void) trace_hardirqs_on(); trace_hardirqs_off(); + /* + * We are always hard disabled here, but PACA_IRQ_HARD_DIS may + * not be set, which means interrupts have only just been hard + * disabled as part of the local_irq_restore or interrupt return + * code. In that case, skip the decrementr check becaus it's + * expensive to read the TB. + * + * HARD_DIS then gets cleared here, but it's reconciled later. + * Either local_irq_disable will replay the interrupt and that + * will reconcile state like other hard interrupts. Or interrupt + * retur will replay the interrupt and in that case it sets + * PACA_IRQ_HARD_DIS by hand (see comments in entry_64.S). + */ if (happened & PACA_IRQ_HARD_DIS) { - /* Clear bit 0 which we wouldn't clear otherwise */ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; /* @@ -248,24 +260,33 @@ notrace void arch_local_irq_restore(unsigned long mask) * cannot have preempted. */ irq_happened = get_irq_happened(); - if (!irq_happened) + if (!irq_happened) { + /* + * FIXME. Here we'd like to be able to do: + * + * #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + * WARN_ON(!(mfmsr() & MSR_EE)); + * #endif + * + * But currently it hits in a few paths, we should fix those and + * enable the warning. + */ return; + } /* * We need to hard disable to get a trusted value from * __check_irq_replay(). We also need to soft-disable * again to avoid warnings in there due to the use of * per-cpu variables. - * - * We know that if the value in irq_happened is exactly 0x01 - * then we are already hard disabled (there are other less - * common cases that we'll ignore for now), so we skip the - * (expensive) mtmsrd. */ - if (unlikely(irq_happened != PACA_IRQ_HARD_DIS)) + if (!(irq_happened & PACA_IRQ_HARD_DIS)) { +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + WARN_ON(!(mfmsr() & MSR_EE)); +#endif __hard_irq_disable(); #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - else { + } else { /* * We should already be hard disabled here. We had bugs * where that wasn't the case so let's dbl check it and @@ -274,8 +295,8 @@ notrace void arch_local_irq_restore(unsigned long mask) */ if (WARN_ON(mfmsr() & MSR_EE)) __hard_irq_disable(); - } #endif + } irq_soft_mask_set(IRQS_ALL_DISABLED); trace_hardirqs_off(); diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c index 7a1f99f1b47f..e4a49c051325 100644 --- a/arch/powerpc/kernel/kprobes-ftrace.c +++ b/arch/powerpc/kernel/kprobes-ftrace.c @@ -25,50 +25,6 @@ #include <linux/preempt.h> #include <linux/ftrace.h> -/* - * This is called from ftrace code after invoking registered handlers to - * disambiguate regs->nip changes done by jprobes and livepatch. We check if - * there is an active jprobe at the provided address (mcount location). - */ -int __is_active_jprobe(unsigned long addr) -{ - if (!preemptible()) { - struct kprobe *p = raw_cpu_read(current_kprobe); - return (p && (unsigned long)p->addr == addr) ? 1 : 0; - } - - return 0; -} - -static nokprobe_inline -int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb, unsigned long orig_nip) -{ - /* - * Emulate singlestep (and also recover regs->nip) - * as if there is a nop - */ - regs->nip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); - if (orig_nip) - regs->nip = orig_nip; - return 1; -} - -int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - if (kprobe_ftrace(p)) - return __skip_singlestep(p, regs, kcb, 0); - else - return 0; -} -NOKPROBE_SYMBOL(skip_singlestep); - /* Ftrace callback handler for kprobes */ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct ftrace_ops *ops, struct pt_regs *regs) @@ -76,18 +32,14 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct kprobe *p; struct kprobe_ctlblk *kcb; - preempt_disable(); - p = get_kprobe((kprobe_opcode_t *)nip); if (unlikely(!p) || kprobe_disabled(p)) - goto end; + return; kcb = get_kprobe_ctlblk(); if (kprobe_running()) { kprobes_inc_nmissed_count(p); } else { - unsigned long orig_nip = regs->nip; - /* * On powerpc, NIP is *before* this instruction for the * pre handler @@ -96,19 +48,23 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) - __skip_singlestep(p, regs, kcb, orig_nip); - else { + if (!p->pre_handler || !p->pre_handler(p, regs)) { /* - * If pre_handler returns !0, it sets regs->nip and - * resets current kprobe. In this case, we should not - * re-enable preemption. + * Emulate singlestep (and also recover regs->nip) + * as if there is a nop */ - return; + regs->nip += MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } } + /* + * If pre_handler returns !0, it changes regs->nip. We have to + * skip emulating post_handler. + */ + __this_cpu_write(current_kprobe, NULL); } -end: - preempt_enable_no_resched(); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index e4c5bf33970b..5c60bb0f927f 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -317,25 +317,17 @@ int kprobe_handler(struct pt_regs *regs) } prepare_singlestep(p, regs); return 1; - } else { - if (*addr != BREAKPOINT_INSTRUCTION) { - /* If trap variant, then it belongs not to us */ - kprobe_opcode_t cur_insn = *addr; - if (is_trap(cur_insn)) - goto no_kprobe; - /* The breakpoint instruction was removed by - * another cpu right after we hit, no further - * handling of this interrupt is appropriate - */ - ret = 1; + } else if (*addr != BREAKPOINT_INSTRUCTION) { + /* If trap variant, then it belongs not to us */ + kprobe_opcode_t cur_insn = *addr; + + if (is_trap(cur_insn)) goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - if (!skip_singlestep(p, regs, kcb)) - goto ss_probe; - ret = 1; - } + /* The breakpoint instruction was removed by + * another cpu right after we hit, no further + * handling of this interrupt is appropriate + */ + ret = 1; } goto no_kprobe; } @@ -350,7 +342,7 @@ int kprobe_handler(struct pt_regs *regs) */ kprobe_opcode_t cur_insn = *addr; if (is_trap(cur_insn)) - goto no_kprobe; + goto no_kprobe; /* * The breakpoint instruction was removed right * after we hit it. Another cpu has removed @@ -366,11 +358,13 @@ int kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_HIT_ACTIVE; set_current_kprobe(p, regs, kcb); - if (p->pre_handler && p->pre_handler(p, regs)) - /* handler has already set things up, so skip ss setup */ + if (p->pre_handler && p->pre_handler(p, regs)) { + /* handler changed execution path, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: if (p->ainsn.boostable >= 0) { ret = try_to_emulate(p, regs); @@ -611,60 +605,6 @@ unsigned long arch_deref_entry_point(void *entry) } NOKPROBE_SYMBOL(arch_deref_entry_point); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); - - /* setup return addr to the jprobe handler routine */ - regs->nip = arch_deref_entry_point(jp->entry); -#ifdef PPC64_ELF_ABI_v2 - regs->gpr[12] = (unsigned long)jp->entry; -#elif defined(PPC64_ELF_ABI_v1) - regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); -#endif - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void __used jprobe_return(void) -{ - asm volatile("jprobe_return_trap:\n" - "trap\n" - ::: "memory"); -} -NOKPROBE_SYMBOL(jprobe_return); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (regs->nip != ppc_kallsyms_lookup_name("jprobe_return_trap")) { - pr_debug("longjmp_break_handler NIP (0x%lx) does not match jprobe_return_trap (0x%lx)\n", - regs->nip, ppc_kallsyms_lookup_name("jprobe_return_trap")); - return 0; - } - - memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - preempt_enable_no_resched(); - return 1; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - static struct kprobe trampoline_p = { .addr = (kprobe_opcode_t *) &kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S index e100ff324a85..c005088f6c9c 100644 --- a/arch/powerpc/kernel/kvm_emul.S +++ b/arch/powerpc/kernel/kvm_emul.S @@ -23,6 +23,7 @@ #include <asm/reg.h> #include <asm/page.h> #include <asm/asm-offsets.h> +#include <asm/asm-compat.h> #define KVM_MAGIC_PAGE (-4096) diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S index 6408f09dbbd9..6e7dbb7d527c 100644 --- a/arch/powerpc/kernel/l2cr_6xx.S +++ b/arch/powerpc/kernel/l2cr_6xx.S @@ -45,6 +45,7 @@ #include <asm/ppc_asm.h> #include <asm/cache.h> #include <asm/page.h> +#include <asm/feature-fixups.h> /* Usage: diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 936c7e2d421e..63f5a9311a29 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -17,6 +17,7 @@ #include <linux/irq.h> #include <linux/ftrace.h> +#include <asm/kdump.h> #include <asm/machdep.h> #include <asm/pgalloc.h> #include <asm/prom.h> @@ -188,7 +189,12 @@ void __init reserve_crashkernel(void) (unsigned long)(crashk_res.start >> 20), (unsigned long)(memblock_phys_mem_size() >> 20)); - memblock_reserve(crashk_res.start, crash_size); + if (!memblock_is_region_memory(crashk_res.start, crash_size) || + memblock_reserve(crashk_res.start, crash_size)) { + pr_err("Failed to reserve memory for crashkernel!\n"); + crashk_res.start = crashk_res.end = 0; + return; + } } int overlaps_crashkernel(unsigned long start, unsigned long size) diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c index 0bd23dc789a4..c77e95e9b384 100644 --- a/arch/powerpc/kernel/machine_kexec_file_64.c +++ b/arch/powerpc/kernel/machine_kexec_file_64.c @@ -269,18 +269,14 @@ int setup_new_fdt(const struct kimage *image, void *fdt, ret = fdt_setprop_u64(fdt, chosen_node, "linux,initrd-start", initrd_load_addr); - if (ret < 0) { - pr_err("Error setting up the new device tree.\n"); - return -EINVAL; - } + if (ret < 0) + goto err; /* initrd-end is the first address after the initrd image. */ ret = fdt_setprop_u64(fdt, chosen_node, "linux,initrd-end", initrd_load_addr + initrd_len); - if (ret < 0) { - pr_err("Error setting up the new device tree.\n"); - return -EINVAL; - } + if (ret < 0) + goto err; ret = fdt_add_mem_rsv(fdt, initrd_load_addr, initrd_len); if (ret) { @@ -292,10 +288,8 @@ int setup_new_fdt(const struct kimage *image, void *fdt, if (cmdline != NULL) { ret = fdt_setprop_string(fdt, chosen_node, "bootargs", cmdline); - if (ret < 0) { - pr_err("Error setting up the new device tree.\n"); - return -EINVAL; - } + if (ret < 0) + goto err; } else { ret = fdt_delprop(fdt, chosen_node, "bootargs"); if (ret && ret != -FDT_ERR_NOTFOUND) { @@ -311,10 +305,12 @@ int setup_new_fdt(const struct kimage *image, void *fdt, } ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0); - if (ret) { - pr_err("Error setting up the new device tree.\n"); - return -EINVAL; - } + if (ret) + goto err; return 0; + +err: + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; } diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 38c5b4764bfe..3497c8329c1d 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -62,11 +62,8 @@ static unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) #ifdef CONFIG_PPC_BOOK3S_64 static void flush_and_reload_slb(void) { - struct slb_shadow *slb; - unsigned long i, n; - /* Invalidate all SLBs */ - asm volatile("slbmte %0,%0; slbia" : : "r" (0)); + slb_flush_all_realmode(); #ifdef CONFIG_KVM_BOOK3S_HANDLER /* @@ -76,22 +73,17 @@ static void flush_and_reload_slb(void) if (get_paca()->kvm_hstate.in_guest) return; #endif - - /* For host kernel, reload the SLBs from shadow SLB buffer. */ - slb = get_slb_shadow(); - if (!slb) + if (early_radix_enabled()) return; - n = min_t(u32, be32_to_cpu(slb->persistent), SLB_MIN_SIZE); - - /* Load up the SLB entries from shadow SLB */ - for (i = 0; i < n; i++) { - unsigned long rb = be64_to_cpu(slb->save_area[i].esid); - unsigned long rs = be64_to_cpu(slb->save_area[i].vsid); + /* + * This probably shouldn't happen, but it may be possible it's + * called in early boot before SLB shadows are allocated. + */ + if (!get_slb_shadow()) + return; - rb = (rb & ~0xFFFul) | i; - asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb)); - } + slb_restore_bolted_realmode(); } #endif @@ -257,12 +249,12 @@ static const struct mce_derror_table mce_p7_derror_table[] = { { 0x00000400, true, MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, +{ 0x00000080, true, + MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */ + MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, { 0x00000100, true, MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, -{ 0x00000080, true, - MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, - MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, { 0x00000040, true, MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, @@ -290,12 +282,12 @@ static const struct mce_derror_table mce_p8_derror_table[] = { { 0x00000200, true, MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, /* SECONDARY ERAT */ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, +{ 0x00000080, true, + MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */ + MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, { 0x00000100, true, MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, -{ 0x00000080, true, - MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, - MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, { 0, false, 0, 0, 0, 0 } }; static const struct mce_derror_table mce_p9_derror_table[] = { @@ -320,12 +312,12 @@ static const struct mce_derror_table mce_p9_derror_table[] = { { 0x00000200, false, MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE, MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, +{ 0x00000080, true, + MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */ + MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, { 0x00000100, true, MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, -{ 0x00000080, true, - MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, - MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, { 0x00000040, true, MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD, MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, }, diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 3f7a9a2d2435..695b24a2d954 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -34,6 +34,7 @@ #include <asm/bug.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/feature-fixups.h> .text diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index fa267e94090a..262ba9481781 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -28,6 +28,7 @@ #include <asm/ptrace.h> #include <asm/mmu.h> #include <asm/export.h> +#include <asm/feature-fixups.h> .text diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 1b3c6835e730..77371c9ef3d8 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -72,13 +72,15 @@ int module_finalize(const Elf_Ehdr *hdr, do_feature_fixups(powerpc_firmware_features, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); +#endif /* CONFIG_PPC64 */ +#ifdef CONFIG_PPC_BARRIER_NOSPEC sect = find_section(hdr, sechdrs, "__spec_barrier_fixup"); if (sect != NULL) do_barrier_nospec_fixups_range(barrier_nospec_enabled, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); -#endif +#endif /* CONFIG_PPC_BARRIER_NOSPEC */ sect = find_section(hdr, sechdrs, "__lwsync_fixup"); if (sect != NULL) diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index fe9733ffffaa..88e4f69a09e5 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -42,6 +42,8 @@ #include <asm/ppc-pci.h> #include <asm/eeh.h> +#include "../../../drivers/pci/pci.h" + /* hose_spinlock protects accesses to the the phb_bitmap. */ static DEFINE_SPINLOCK(hose_spinlock); LIST_HEAD(hose_list); @@ -366,9 +368,6 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev)); -#ifdef DEBUG - memset(&oirq, 0xff, sizeof(oirq)); -#endif /* Try to get a mapping from the device-tree */ virq = of_irq_parse_and_map_pci(pci_dev, 0, 0); if (virq <= 0) { @@ -1014,7 +1013,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) /* Cardbus can call us to add new devices to a bus, so ignore * those who are already fully discovered */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pcibios_setup_device(dev); diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S index 8afbe213d729..6d1b42ee797c 100644 --- a/arch/powerpc/kernel/ppc_save_regs.S +++ b/arch/powerpc/kernel/ppc_save_regs.S @@ -12,6 +12,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> +#include <asm/asm-compat.h> /* * Grab the register values as they are now. diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 9ef4aea9fffe..913c5725cdb2 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -583,6 +583,7 @@ static void save_all(struct task_struct *tsk) __giveup_spe(tsk); msr_check_and_clear(msr_all_available); + thread_pkey_regs_save(&tsk->thread); } void flush_all_to_thread(struct task_struct *tsk) @@ -716,6 +717,13 @@ void switch_booke_debug_regs(struct debug_reg *new_debug) EXPORT_SYMBOL_GPL(switch_booke_debug_regs); #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ #ifndef CONFIG_HAVE_HW_BREAKPOINT +static void set_breakpoint(struct arch_hw_breakpoint *brk) +{ + preempt_disable(); + __set_breakpoint(brk); + preempt_enable(); +} + static void set_debug_reg_defaults(struct thread_struct *thread) { thread->hw_brk.address = 0; @@ -828,13 +836,6 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk) WARN_ON_ONCE(1); } -void set_breakpoint(struct arch_hw_breakpoint *brk) -{ - preempt_disable(); - __set_breakpoint(brk); - preempt_enable(); -} - /* Check if we have DAWR or DABR hardware */ bool ppc_breakpoint_available(void) { @@ -866,8 +867,7 @@ static inline bool tm_enabled(struct task_struct *tsk) return tsk && tsk->thread.regs && (tsk->thread.regs->msr & MSR_TM); } -static void tm_reclaim_thread(struct thread_struct *thr, - struct thread_info *ti, uint8_t cause) +static void tm_reclaim_thread(struct thread_struct *thr, uint8_t cause) { /* * Use the current MSR TM suspended bit to track if we have @@ -914,7 +914,7 @@ static void tm_reclaim_thread(struct thread_struct *thr, void tm_reclaim_current(uint8_t cause) { tm_enable(); - tm_reclaim_thread(¤t->thread, current_thread_info(), cause); + tm_reclaim_thread(¤t->thread, cause); } static inline void tm_reclaim_task(struct task_struct *tsk) @@ -945,7 +945,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk) thr->regs->ccr, thr->regs->msr, thr->regs->trap); - tm_reclaim_thread(thr, task_thread_info(tsk), TM_CAUSE_RESCHED); + tm_reclaim_thread(thr, TM_CAUSE_RESCHED); TM_DEBUG("--- tm_reclaim on pid %d complete\n", tsk->pid); @@ -1250,17 +1250,9 @@ struct task_struct *__switch_to(struct task_struct *prev, * mappings. If the new process has the foreign real address * mappings, we must issue a cp_abort to clear any state and * prevent snooping, corruption or a covert channel. - * - * DD1 allows paste into normal system memory so we do an - * unpaired copy, rather than cp_abort, to clear the buffer, - * since cp_abort is quite expensive. */ - if (current_thread_info()->task->thread.used_vas) { + if (current_thread_info()->task->thread.used_vas) asm volatile(PPC_CP_ABORT); - } else if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { - asm volatile(PPC_COPY(%0, %1) - : : "r"(dummy_copy_buffer), "r"(0)); - } } #endif /* CONFIG_PPC_BOOK3S_64 */ @@ -1307,6 +1299,38 @@ static void show_instructions(struct pt_regs *regs) pr_cont("\n"); } +void show_user_instructions(struct pt_regs *regs) +{ + unsigned long pc; + int i; + + pc = regs->nip - (instructions_to_print * 3 / 4 * sizeof(int)); + + pr_info("%s[%d]: code: ", current->comm, current->pid); + + for (i = 0; i < instructions_to_print; i++) { + int instr; + + if (!(i % 8) && (i > 0)) { + pr_cont("\n"); + pr_info("%s[%d]: code: ", current->comm, current->pid); + } + + if (probe_kernel_address((unsigned int __user *)pc, instr)) { + pr_cont("XXXXXXXX "); + } else { + if (regs->nip == pc) + pr_cont("<%08x> ", instr); + else + pr_cont("%08x ", instr); + } + + pc += sizeof(int); + } + + pr_cont("\n"); +} + struct regbit { unsigned long bit; const char *name; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 05e7fb47a7a4..c4d7078e5295 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -23,7 +23,6 @@ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/pci.h> -#include <linux/stringify.h> #include <linux/delay.h> #include <linux/initrd.h> #include <linux/bitops.h> @@ -440,6 +439,29 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node, return 1; } +/* + * Compare the range against max mem limit and update + * size if it cross the limit. + */ + +#ifdef CONFIG_SPARSEMEM +static bool validate_mem_limit(u64 base, u64 *size) +{ + u64 max_mem = 1UL << (MAX_PHYSMEM_BITS); + + if (base >= max_mem) + return false; + if ((base + *size) > max_mem) + *size = max_mem - base; + return true; +} +#else +static bool validate_mem_limit(u64 base, u64 *size) +{ + return true; +} +#endif + #ifdef CONFIG_PPC_PSERIES /* * Interpret the ibm dynamic reconfiguration memory LMBs. @@ -494,7 +516,8 @@ static void __init early_init_drmem_lmb(struct drmem_lmb *lmb, } DBG("Adding: %llx -> %llx\n", base, size); - memblock_add(base, size); + if (validate_mem_limit(base, &size)) + memblock_add(base, size); } while (--rngs); } #endif /* CONFIG_PPC_PSERIES */ @@ -548,8 +571,10 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) } /* Add the chunk to the MEMBLOCK list */ - if (add_mem_to_memblock) - memblock_add(base, size); + if (add_mem_to_memblock) { + if (validate_mem_limit(base, &size)) + memblock_add(base, size); + } } static void __init early_reserve_mem_dt(void) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 5425dd3d6a9f..9b38a2e5dd35 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -27,7 +27,6 @@ #include <linux/types.h> #include <linux/pci.h> #include <linux/proc_fs.h> -#include <linux/stringify.h> #include <linux/delay.h> #include <linux/initrd.h> #include <linux/bitops.h> @@ -629,7 +628,7 @@ static void __init early_cmdline_parse(void) const char *opt; char *p; - int l = 0; + int l __maybe_unused = 0; prom_cmd_line[0] = 0; p = prom_cmd_line; @@ -1422,7 +1421,10 @@ static void __init reserve_mem(u64 base, u64 size) static void __init prom_init_mem(void) { phandle node; - char *path, type[64]; +#ifdef DEBUG_PROM + char *path; +#endif + char type[64]; unsigned int plen; cell_t *p, *endp; __be32 val; @@ -1443,7 +1445,9 @@ static void __init prom_init_mem(void) prom_debug("root_size_cells: %x\n", rsc); prom_debug("scanning memory:\n"); +#ifdef DEBUG_PROM path = prom_scratch; +#endif for (node = 0; prom_next_node(&node); ) { type[0] = 0; @@ -2102,8 +2106,6 @@ static void __init prom_init_stdout(void) stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout); if (stdout_node != PROM_ERROR) { val = cpu_to_be32(stdout_node); - prom_setprop(prom.chosen, "/chosen", "linux,stdout-package", - &val, sizeof(val)); /* If it's a display, note it */ memset(type, 0, sizeof(type)); diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index a8b277362931..f6f469fc4073 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -8,6 +8,8 @@ #include <linux/device.h> #include <linux/seq_buf.h> +#include <asm/asm-prototypes.h> +#include <asm/code-patching.h> #include <asm/debugfs.h> #include <asm/security_features.h> #include <asm/setup.h> @@ -15,7 +17,15 @@ unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; +enum count_cache_flush_type { + COUNT_CACHE_FLUSH_NONE = 0x1, + COUNT_CACHE_FLUSH_SW = 0x2, + COUNT_CACHE_FLUSH_HW = 0x4, +}; +static enum count_cache_flush_type count_cache_flush_type; + bool barrier_nospec_enabled; +static bool no_nospec; static void enable_barrier_nospec(bool enable) { @@ -42,8 +52,17 @@ void setup_barrier_nospec(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR); - enable_barrier_nospec(enable); + if (!no_nospec) + enable_barrier_nospec(enable); +} + +static int __init handle_nospectre_v1(char *p) +{ + no_nospec = true; + + return 0; } +early_param("nospectre_v1", handle_nospectre_v1); #ifdef CONFIG_DEBUG_FS static int barrier_nospec_set(void *data, u64 val) @@ -82,6 +101,7 @@ static __init int barrier_nospec_debugfs_init(void) device_initcall(barrier_nospec_debugfs_init); #endif /* CONFIG_DEBUG_FS */ +#ifdef CONFIG_PPC_BOOK3S_64 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { bool thread_priv; @@ -114,51 +134,72 @@ ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, cha return sprintf(buf, "Vulnerable\n"); } +#endif ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { - if (!security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) - return sprintf(buf, "Not affected\n"); + struct seq_buf s; - if (barrier_nospec_enabled) - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + seq_buf_init(&s, buf, PAGE_SIZE - 1); - return sprintf(buf, "Vulnerable\n"); + if (security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) { + if (barrier_nospec_enabled) + seq_buf_printf(&s, "Mitigation: __user pointer sanitization"); + else + seq_buf_printf(&s, "Vulnerable"); + + if (security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31)) + seq_buf_printf(&s, ", ori31 speculation barrier enabled"); + + seq_buf_printf(&s, "\n"); + } else + seq_buf_printf(&s, "Not affected\n"); + + return s.len; } ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { - bool bcs, ccd, ori; struct seq_buf s; + bool bcs, ccd; seq_buf_init(&s, buf, PAGE_SIZE - 1); bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED); ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED); - ori = security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31); - if (bcs || ccd) { + if (bcs || ccd || count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { + bool comma = false; seq_buf_printf(&s, "Mitigation: "); - if (bcs) + if (bcs) { seq_buf_printf(&s, "Indirect branch serialisation (kernel only)"); + comma = true; + } + + if (ccd) { + if (comma) + seq_buf_printf(&s, ", "); + seq_buf_printf(&s, "Indirect branch cache disabled"); + comma = true; + } - if (bcs && ccd) + if (comma) seq_buf_printf(&s, ", "); - if (ccd) - seq_buf_printf(&s, "Indirect branch cache disabled"); + seq_buf_printf(&s, "Software count cache flush"); + + if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) + seq_buf_printf(&s, "(hardware accelerated)"); } else seq_buf_printf(&s, "Vulnerable"); - if (ori) - seq_buf_printf(&s, ", ori31 speculation barrier enabled"); - seq_buf_printf(&s, "\n"); return s.len; } +#ifdef CONFIG_PPC_BOOK3S_64 /* * Store-forwarding barrier support. */ @@ -306,3 +347,71 @@ static __init int stf_barrier_debugfs_init(void) } device_initcall(stf_barrier_debugfs_init); #endif /* CONFIG_DEBUG_FS */ + +static void toggle_count_cache_flush(bool enable) +{ + if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP); + count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; + pr_info("count-cache-flush: software flush disabled.\n"); + return; + } + + patch_branch_site(&patch__call_flush_count_cache, + (u64)&flush_count_cache, BRANCH_SET_LINK); + + if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) { + count_cache_flush_type = COUNT_CACHE_FLUSH_SW; + pr_info("count-cache-flush: full software flush sequence enabled.\n"); + return; + } + + patch_instruction_site(&patch__flush_count_cache_return, PPC_INST_BLR); + count_cache_flush_type = COUNT_CACHE_FLUSH_HW; + pr_info("count-cache-flush: hardware assisted flush sequence enabled\n"); +} + +void setup_count_cache_flush(void) +{ + toggle_count_cache_flush(true); +} + +#ifdef CONFIG_DEBUG_FS +static int count_cache_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + toggle_count_cache_flush(enable); + + return 0; +} + +static int count_cache_flush_get(void *data, u64 *val) +{ + if (count_cache_flush_type == COUNT_CACHE_FLUSH_NONE) + *val = 0; + else + *val = 1; + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get, + count_cache_flush_set, "%llu\n"); + +static __init int count_cache_flush_debugfs_init(void) +{ + debugfs_create_file("count_cache_flush", 0600, powerpc_debugfs_root, + NULL, &fops_count_cache_flush); + return 0; +} +device_initcall(count_cache_flush_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ +#endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 40b44bb53a4e..93fa0c99681e 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -972,6 +972,8 @@ void __init setup_arch(char **cmdline_p) if (ppc_md.setup_arch) ppc_md.setup_arch(); + setup_barrier_nospec(); + paging_init(); /* Initialize the MMU context management stuff. */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 74457485574b..8c507be12c3c 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -40,6 +40,10 @@ #include <asm/code-patching.h> #include <asm/cpu_has_feature.h> #include <asm/asm-prototypes.h> +#include <asm/kdump.h> +#include <asm/feature-fixups.h> + +#include "setup.h" #define DBG(fmt...) @@ -95,11 +99,10 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * We do the initial parsing of the flat device-tree and prepares * for the MMU to be fully initialized. */ -extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ - notrace void __init machine_init(u64 dt_ptr) { - unsigned int *addr = &memset_nocache_branch; + unsigned int *addr = (unsigned int *)((unsigned long)&patch__memset_nocache + + patch__memset_nocache); unsigned long insn; /* Configure static keys first, now that we're relocated. */ @@ -108,7 +111,7 @@ notrace void __init machine_init(u64 dt_ptr) /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); - patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP); + patch_instruction_site(&patch__memcpy_nocache, PPC_INST_NOP); insn = create_cond_branch(addr, branch_target(addr), 0x820000); patch_instruction(addr, insn); /* replace b by bne cr0 */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 225bc5f91049..6a501b25dd85 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -68,6 +68,7 @@ #include <asm/opal.h> #include <asm/cputhreads.h> #include <asm/hw_irq.h> +#include <asm/feature-fixups.h> #include "setup.h" diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 4794d6b4f4d2..b19d832ef386 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -423,7 +423,8 @@ int smp_handle_nmi_ipi(struct pt_regs *regs) fn(regs); nmi_ipi_lock(); - nmi_ipi_busy_count--; + if (nmi_ipi_busy_count > 1) /* Can race with caller time-out */ + nmi_ipi_busy_count--; out: nmi_ipi_unlock_end(&flags); @@ -448,29 +449,11 @@ static void do_smp_send_nmi_ipi(int cpu, bool safe) } } -void smp_flush_nmi_ipi(u64 delay_us) -{ - unsigned long flags; - - nmi_ipi_lock_start(&flags); - while (nmi_ipi_busy_count) { - nmi_ipi_unlock_end(&flags); - udelay(1); - if (delay_us) { - delay_us--; - if (!delay_us) - return; - } - nmi_ipi_lock_start(&flags); - } - nmi_ipi_unlock_end(&flags); -} - /* * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS. * - fn is the target callback function. * - delay_us > 0 is the delay before giving up waiting for targets to - * enter the handler, == 0 specifies indefinite delay. + * complete executing the handler, == 0 specifies indefinite delay. */ int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool safe) { @@ -507,8 +490,23 @@ int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool do_smp_send_nmi_ipi(cpu, safe); + nmi_ipi_lock(); + /* nmi_ipi_busy_count is held here, so unlock/lock is okay */ while (!cpumask_empty(&nmi_ipi_pending_mask)) { + nmi_ipi_unlock(); udelay(1); + nmi_ipi_lock(); + if (delay_us) { + delay_us--; + if (!delay_us) + break; + } + } + + while (nmi_ipi_busy_count > 1) { + nmi_ipi_unlock(); + udelay(1); + nmi_ipi_lock(); if (delay_us) { delay_us--; if (!delay_us) @@ -516,12 +514,17 @@ int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool } } - nmi_ipi_lock(); if (!cpumask_empty(&nmi_ipi_pending_mask)) { - /* Could not gather all CPUs */ + /* Timeout waiting for CPUs to call smp_handle_nmi_ipi */ ret = 0; cpumask_clear(&nmi_ipi_pending_mask); } + if (nmi_ipi_busy_count > 1) { + /* Timeout waiting for CPUs to execute fn */ + ret = 0; + nmi_ipi_busy_count = 1; + } + nmi_ipi_busy_count--; nmi_ipi_unlock_end(&flags); @@ -597,7 +600,8 @@ static void nmi_stop_this_cpu(struct pt_regs *regs) * IRQs are already hard disabled by the smp_handle_nmi_ipi. */ nmi_ipi_lock(); - nmi_ipi_busy_count--; + if (nmi_ipi_busy_count > 1) + nmi_ipi_busy_count--; nmi_ipi_unlock(); spin_begin(); diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index 34b73a262709..7a919e9a3400 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -7,6 +7,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/mmu.h> +#include <asm/feature-fixups.h> /* * Structure for storing CPU registers on the save area. diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S index 82d8aae81c6a..f83bf6f72cb0 100644 --- a/arch/powerpc/kernel/swsusp_asm64.S +++ b/arch/powerpc/kernel/swsusp_asm64.S @@ -13,6 +13,7 @@ #include <asm/thread_info.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> +#include <asm/feature-fixups.h> /* * Structure for storing CPU registers on the save area. diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index ff12f47a96b6..6bffbc5affe7 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -13,6 +13,7 @@ #include <asm/reg.h> #include <asm/bug.h> #include <asm/export.h> +#include <asm/feature-fixups.h> #ifdef CONFIG_VSX /* See fpu.S, this is borrowed from there */ @@ -312,8 +313,8 @@ _GLOBAL(tm_reclaim) blr - /* void __tm_recheckpoint(struct thread_struct *thread, - * unsigned long orig_msr) + /* + * void __tm_recheckpoint(struct thread_struct *thread) * - Restore the checkpointed register state saved by tm_reclaim * when we switch_to a process. * diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index 9a5b5a513604..32476a6e4e9c 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -104,39 +104,13 @@ ftrace_regs_call: bl ftrace_stub nop - /* Load the possibly modified NIP */ - ld r15, _NIP(r1) - + /* Load ctr with the possibly modified NIP */ + ld r3, _NIP(r1) + mtctr r3 #ifdef CONFIG_LIVEPATCH - cmpd r14, r15 /* has NIP been altered? */ + cmpd r14, r3 /* has NIP been altered? */ #endif -#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE) - /* NIP has not been altered, skip over further checks */ - beq 1f - - /* Check if there is an active jprobe on us */ - subi r3, r14, 4 - bl __is_active_jprobe - nop - - /* - * If r3 == 1, then this is a kprobe/jprobe. - * else, this is livepatched function. - * - * The conditional branch for livepatch_handler below will use the - * result of this comparison. For kprobe/jprobe, we just need to branch to - * the new NIP, not call livepatch_handler. The branch below is bne, so we - * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want - * CR0[EQ] = (r3 == 1). - */ - cmpdi r3, 1 -1: -#endif - - /* Load CTR with the possibly modified NIP */ - mtctr r15 - /* Restore gprs */ REST_GPR(0,r1) REST_10GPRS(2,r1) @@ -154,10 +128,7 @@ ftrace_regs_call: addi r1, r1, SWITCH_FRAME_SIZE #ifdef CONFIG_LIVEPATCH - /* - * Based on the cmpd or cmpdi above, if the NIP was altered and we're - * not on a kprobe/jprobe, then handle livepatch. - */ + /* Based on the cmpd above, if the NIP was altered handle livepatch */ bne- livepatch_handler #endif diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 0e17dcb48720..070e96f1773a 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -70,6 +70,7 @@ #include <asm/hmi.h> #include <sysdev/fsl_pci.h> #include <asm/kprobes.h> +#include <asm/stacktrace.h> #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) int (*__debugger)(struct pt_regs *regs) __read_mostly; @@ -96,6 +97,19 @@ EXPORT_SYMBOL(__debugger_fault_handler); #define TM_DEBUG(x...) do { } while(0) #endif +static const char *signame(int signr) +{ + switch (signr) { + case SIGBUS: return "bus error"; + case SIGFPE: return "floating point exception"; + case SIGILL: return "illegal instruction"; + case SIGSEGV: return "segfault"; + case SIGTRAP: return "unhandled trap"; + } + + return "unknown signal"; +} + /* * Trap & Exception support */ @@ -301,26 +315,44 @@ void user_single_step_siginfo(struct task_struct *tsk, info->si_addr = (void __user *)regs->nip; } +static bool show_unhandled_signals_ratelimited(void) +{ + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + return show_unhandled_signals && __ratelimit(&rs); +} + +static void show_signal_msg(int signr, struct pt_regs *regs, int code, + unsigned long addr) +{ + if (!show_unhandled_signals_ratelimited()) + return; + + if (!unhandled_signal(current, signr)) + return; + + pr_info("%s[%d]: %s (%d) at %lx nip %lx lr %lx code %x", + current->comm, current->pid, signame(signr), signr, + addr, regs->nip, regs->link, code); + + print_vma_addr(KERN_CONT " in ", regs->nip); + + pr_cont("\n"); + + show_user_instructions(regs); +} void _exception_pkey(int signr, struct pt_regs *regs, int code, - unsigned long addr, int key) + unsigned long addr, int key) { siginfo_t info; - const char fmt32[] = KERN_INFO "%s[%d]: unhandled signal %d " \ - "at %08lx nip %08lx lr %08lx code %x\n"; - const char fmt64[] = KERN_INFO "%s[%d]: unhandled signal %d " \ - "at %016lx nip %016lx lr %016lx code %x\n"; if (!user_mode(regs)) { die("Exception in kernel mode", regs, signr); return; } - if (show_unhandled_signals && unhandled_signal(current, signr)) { - printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, signr, - addr, regs->nip, regs->link, code); - } + show_signal_msg(signr, regs, code, addr); if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs)) local_irq_enable(); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index d2205b97628c..65b3bdb99f0b 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -22,7 +22,6 @@ #include <linux/security.h> #include <linux/memblock.h> -#include <asm/cpu_has_feature.h> #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/vdso32/note.S b/arch/powerpc/kernel/vdso32/note.S index d4b5be4f3d5f..227a7327399e 100644 --- a/arch/powerpc/kernel/vdso32/note.S +++ b/arch/powerpc/kernel/vdso32/note.S @@ -5,6 +5,7 @@ #include <linux/uts.h> #include <linux/version.h> +#include <linux/build-salt.h> #define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type) \ .section name, flags; \ @@ -23,3 +24,5 @@ ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0) .long LINUX_VERSION_CODE ASM_ELF_NOTE_END + +BUILD_SALT diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index f314fd475491..21165da0052d 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -8,6 +8,7 @@ #include <asm/page.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/asm-compat.h> /* * Load state from memory into VMX registers including VSCR. diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 5baac79df97e..07ae018e550e 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -153,14 +153,16 @@ SECTIONS *(__rfi_flush_fixup) __stop___rfi_flush_fixup = .; } +#endif /* CONFIG_PPC64 */ +#ifdef CONFIG_PPC_BARRIER_NOSPEC . = ALIGN(8); __spec_barrier_fixup : AT(ADDR(__spec_barrier_fixup) - LOAD_OFFSET) { __start___barrier_nospec_fixup = .; *(__barrier_nospec_fixup) __stop___barrier_nospec_fixup = .; } -#endif +#endif /* CONFIG_PPC_BARRIER_NOSPEC */ EXCEPTION_TABLE(0) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 1d82274f7e9f..3c6ab22a0c4e 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -174,7 +174,6 @@ static void watchdog_smp_panic(int cpu, u64 tb) continue; smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000); } - smp_flush_nmi_ipi(1000000); } /* Take the stuck CPUs out of the watch group */ diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index edaf4720d156..87348e498c89 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -28,7 +28,6 @@ #include <asm/reg.h> #include <asm/cputable.h> #include <asm/cacheflush.h> -#include <asm/tlbflush.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/kvm_ppc.h> diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 45c8ea4a0487..612169988a3d 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -23,7 +23,6 @@ #include <linux/kvm_host.h> #include <linux/highmem.h> -#include <asm/tlbflush.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index cf9d686e8162..c92dd25bed23 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -23,7 +23,6 @@ #include <linux/kvm_host.h> #include <linux/highmem.h> -#include <asm/tlbflush.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> #include <asm/book3s/64/mmu-hash.h> diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 7f3a8cf5d66f..3c0e8fb2b773 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -29,7 +29,6 @@ #include <linux/file.h> #include <linux/debugfs.h> -#include <asm/tlbflush.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> #include <asm/book3s/64/mmu-hash.h> diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 176f911ee983..0af1c0aea1fe 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -66,10 +66,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, bits = root & RPDS_MASK; root = root & RPDB_MASK; - /* P9 DD1 interprets RTS (radix tree size) differently */ offset = rts + 31; - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - offset -= 3; /* current implementations only support 52-bit space */ if (offset != 52) @@ -160,17 +157,7 @@ static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep, unsigned long clr, unsigned long set, unsigned long addr, unsigned int shift) { - unsigned long old = 0; - - if (!(clr & _PAGE_PRESENT) && cpu_has_feature(CPU_FTR_POWER9_DD1) && - pte_present(*ptep)) { - /* have to invalidate it first */ - old = __radix_pte_update(ptep, _PAGE_PRESENT, 0); - kvmppc_radix_tlbie_page(kvm, addr, shift); - set |= _PAGE_PRESENT; - old &= _PAGE_PRESENT; - } - return __radix_pte_update(ptep, clr, set) | old; + return __radix_pte_update(ptep, clr, set); } void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr, diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S index 688722acd692..066c665dc86f 100644 --- a/arch/powerpc/kvm/book3s_64_slb.S +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -17,6 +17,9 @@ * Authors: Alexander Graf <agraf@suse.de> */ +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> + #define SHADOW_SLB_ENTRY_LEN 0x10 #define OFFSET_ESID(x) (SHADOW_SLB_ENTRY_LEN * x) #define OFFSET_VSID(x) ((SHADOW_SLB_ENTRY_LEN * x) + 8) diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 8c456fa691a5..9a3f2646ecc7 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -31,7 +31,6 @@ #include <linux/iommu.h> #include <linux/file.h> -#include <asm/tlbflush.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> #include <asm/book3s/64/mmu-hash.h> @@ -180,7 +179,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, if ((tbltmp->it_page_shift <= stt->page_shift) && (tbltmp->it_offset << tbltmp->it_page_shift == stt->offset << stt->page_shift) && - (tbltmp->it_size << tbltmp->it_page_shift == + (tbltmp->it_size << tbltmp->it_page_shift >= stt->size << stt->page_shift)) { /* * Reference the table to avoid races with @@ -296,7 +295,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, { struct kvmppc_spapr_tce_table *stt = NULL; struct kvmppc_spapr_tce_table *siter; - unsigned long npages, size; + unsigned long npages, size = args->size; int ret = -ENOMEM; int i; @@ -304,7 +303,6 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, (args->offset + args->size > (ULLONG_MAX >> args->page_shift))) return -EINVAL; - size = _ALIGN_UP(args->size, PAGE_SIZE >> 3); npages = kvmppc_tce_pages(size); ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true); if (ret) @@ -378,19 +376,19 @@ static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, { struct mm_iommu_table_group_mem_t *mem = NULL; const unsigned long pgsize = 1ULL << tbl->it_page_shift; - unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); if (!pua) /* it_userspace allocation might be delayed */ return H_TOO_HARD; - mem = mm_iommu_lookup(kvm->mm, *pua, pgsize); + mem = mm_iommu_lookup(kvm->mm, be64_to_cpu(*pua), pgsize); if (!mem) return H_TOO_HARD; mm_iommu_mapped_dec(mem); - *pua = 0; + *pua = cpu_to_be64(0); return H_SUCCESS; } @@ -437,7 +435,8 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, enum dma_data_direction dir) { long ret; - unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + unsigned long hpa; + __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); struct mm_iommu_table_group_mem_t *mem; if (!pua) @@ -464,7 +463,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (dir != DMA_NONE) kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry); - *pua = ua; + *pua = cpu_to_be64(ua); return 0; } diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 5b298f5a1a14..506a4d400458 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -26,8 +26,8 @@ #include <linux/slab.h> #include <linux/hugetlb.h> #include <linux/list.h> +#include <linux/stringify.h> -#include <asm/tlbflush.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> #include <asm/book3s/64/mmu-hash.h> @@ -200,23 +200,19 @@ static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, { struct mm_iommu_table_group_mem_t *mem = NULL; const unsigned long pgsize = 1ULL << tbl->it_page_shift; - unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry); if (!pua) /* it_userspace allocation might be delayed */ return H_TOO_HARD; - pua = (void *) vmalloc_to_phys(pua); - if (WARN_ON_ONCE_RM(!pua)) - return H_HARDWARE; - - mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize); + mem = mm_iommu_lookup_rm(kvm->mm, be64_to_cpu(*pua), pgsize); if (!mem) return H_TOO_HARD; mm_iommu_mapped_dec(mem); - *pua = 0; + *pua = cpu_to_be64(0); return H_SUCCESS; } @@ -268,7 +264,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, { long ret; unsigned long hpa = 0; - unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry); struct mm_iommu_table_group_mem_t *mem; if (!pua) @@ -283,10 +279,6 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, &hpa))) return H_HARDWARE; - pua = (void *) vmalloc_to_phys(pua); - if (WARN_ON_ONCE_RM(!pua)) - return H_HARDWARE; - if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) return H_CLOSED; @@ -303,7 +295,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (dir != DMA_NONE) kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); - *pua = ua; + *pua = cpu_to_be64(ua); return 0; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index de686b340f4a..574fc1dcb2bf 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -53,7 +53,6 @@ #include <asm/disassemble.h> #include <asm/cputable.h> #include <asm/cacheflush.h> -#include <asm/tlbflush.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/kvm_ppc.h> @@ -128,14 +127,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); * and SPURR count and should be set according to the number of * online threads in the vcore being run. */ -#define RWMR_RPA_P8_1THREAD 0x164520C62609AECA -#define RWMR_RPA_P8_2THREAD 0x7FFF2908450D8DA9 -#define RWMR_RPA_P8_3THREAD 0x164520C62609AECA -#define RWMR_RPA_P8_4THREAD 0x199A421245058DA9 -#define RWMR_RPA_P8_5THREAD 0x164520C62609AECA -#define RWMR_RPA_P8_6THREAD 0x164520C62609AECA -#define RWMR_RPA_P8_7THREAD 0x164520C62609AECA -#define RWMR_RPA_P8_8THREAD 0x164520C62609AECA +#define RWMR_RPA_P8_1THREAD 0x164520C62609AECAUL +#define RWMR_RPA_P8_2THREAD 0x7FFF2908450D8DA9UL +#define RWMR_RPA_P8_3THREAD 0x164520C62609AECAUL +#define RWMR_RPA_P8_4THREAD 0x199A421245058DA9UL +#define RWMR_RPA_P8_5THREAD 0x164520C62609AECAUL +#define RWMR_RPA_P8_6THREAD 0x164520C62609AECAUL +#define RWMR_RPA_P8_7THREAD 0x164520C62609AECAUL +#define RWMR_RPA_P8_8THREAD 0x164520C62609AECAUL static unsigned long p8_rwmr_values[MAX_SMT_THREADS + 1] = { RWMR_RPA_P8_1THREAD, @@ -216,7 +215,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) wqp = kvm_arch_vcpu_wq(vcpu); if (swq_has_sleeper(wqp)) { - swake_up(wqp); + swake_up_one(wqp); ++vcpu->stat.halt_wakeup; } @@ -1693,14 +1692,6 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len); break; case KVM_REG_PPC_TB_OFFSET: - /* - * POWER9 DD1 has an erratum where writing TBU40 causes - * the timebase to lose ticks. So we don't let the - * timebase offset be changed on P9 DD1. (It is - * initialized to zero.) - */ - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - break; /* round up to multiple of 2^24 */ vcpu->arch.vcore->tb_offset = ALIGN(set_reg_val(id, *val), 1UL << 24); @@ -1816,7 +1807,7 @@ static int threads_per_vcore(struct kvm *kvm) return threads_per_subcore; } -static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) +static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id) { struct kvmppc_vcore *vcore; @@ -1830,7 +1821,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) init_swait_queue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; - vcore->first_vcpuid = core * kvm->arch.smt_mode; + vcore->first_vcpuid = id; vcore->kvm = kvm; INIT_LIST_HEAD(&vcore->preempt_list); @@ -2026,8 +2017,6 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, /* * Set the default HFSCR for the guest from the host value. * This value is only used on POWER9. - * On POWER9 DD1, TM doesn't work, so we make sure to - * prevent the guest from using it. * On POWER9, we want to virtualize the doorbell facility, so we * turn off the HFSCR bit, which causes those instructions to trap. */ @@ -2048,12 +2037,26 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, mutex_lock(&kvm->lock); vcore = NULL; err = -EINVAL; - core = id / kvm->arch.smt_mode; + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (id >= (KVM_MAX_VCPUS * kvm->arch.emul_smt_mode)) { + pr_devel("KVM: VCPU ID too high\n"); + core = KVM_MAX_VCORES; + } else { + BUG_ON(kvm->arch.smt_mode != 1); + core = kvmppc_pack_vcpu_id(kvm, id); + } + } else { + core = id / kvm->arch.smt_mode; + } if (core < KVM_MAX_VCORES) { vcore = kvm->arch.vcores[core]; - if (!vcore) { + if (vcore && cpu_has_feature(CPU_FTR_ARCH_300)) { + pr_devel("KVM: collision on id %u", id); + vcore = NULL; + } else if (!vcore) { err = -ENOMEM; - vcore = kvmppc_vcore_create(kvm, core); + vcore = kvmppc_vcore_create(kvm, + id & ~(kvm->arch.smt_mode - 1)); kvm->arch.vcores[core] = vcore; kvm->arch.online_vcores++; } @@ -3188,7 +3191,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } } - prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE); if (kvmppc_vcore_check_block(vc)) { finish_swait(&vc->wq, &wait); @@ -3311,7 +3314,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - swake_up(&vc->wq); + swake_up_one(&vc->wq); } } @@ -4561,6 +4564,8 @@ static int kvmppc_book3s_init_hv(void) pr_err("KVM-HV: Cannot determine method for accessing XICS\n"); return -ENODEV; } + /* presence of intc confirmed - node can be dropped again */ + of_node_put(np); } #endif diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index d4a3f4da409b..fc6bb9630a9c 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -77,7 +77,7 @@ struct page *kvm_alloc_hpt_cma(unsigned long nr_pages) VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES), - GFP_KERNEL); + false); } EXPORT_SYMBOL_GPL(kvm_alloc_hpt_cma); diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 82f2ff9410b6..666b91c79eb4 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -27,6 +27,8 @@ #include <asm/asm-offsets.h> #include <asm/exception-64s.h> #include <asm/ppc-opcode.h> +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> /***************************************************************************** * * diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 1f22d9e977d4..a67cf1cdeda4 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -14,7 +14,6 @@ #include <linux/module.h> #include <linux/log2.h> -#include <asm/tlbflush.h> #include <asm/trace.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 153988d878e8..1d14046124a0 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -32,6 +32,8 @@ #include <asm/opal.h> #include <asm/xive-regs.h> #include <asm/thread_info.h> +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> /* Sign-extend HDEC if not on POWER9 */ #define EXTEND_HDEC(reg) \ @@ -917,9 +919,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR) mtspr SPRN_PID, r7 mtspr SPRN_WORT, r8 BEGIN_FTR_SECTION - PPC_INVALIDATE_ERAT -END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1) -BEGIN_FTR_SECTION /* POWER8-only registers */ ld r5, VCPU_TCSCR(r4) ld r6, VCPU_ACOP(r4) @@ -1912,7 +1911,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) ld r5, VCPU_KVM(r9) lbz r0, KVM_RADIX(r5) cmpwi cr2, r0, 0 - beq cr2, 4f + beq cr2, 2f /* * Radix: do eieio; tlbsync; ptesync sequence in case we @@ -1952,11 +1951,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) bdnz 1b ptesync -2: /* Flush the ERAT on radix P9 DD1 guest exit */ -BEGIN_FTR_SECTION - PPC_INVALIDATE_ERAT -END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1) -4: +2: #endif /* CONFIG_PPC_RADIX_MMU */ /* @@ -3367,11 +3362,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) mtspr SPRN_CIABR, r0 mtspr SPRN_DAWRX, r0 - /* Flush the ERAT on radix P9 DD1 guest exit */ -BEGIN_FTR_SECTION - PPC_INVALIDATE_ERAT -END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1) - BEGIN_MMU_FTR_SECTION b 4f END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index c18e845019ec..d71dab16dc6f 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -23,6 +23,7 @@ #include <asm/page.h> #include <asm/asm-offsets.h> #include <asm/exception-64s.h> +#include <asm/asm-compat.h> #if defined(CONFIG_PPC_BOOK3S_64) #ifdef PPC64_ELF_ABI_v2 diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index c3b8006f0eac..47ee43bbd696 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -27,7 +27,6 @@ #include <asm/reg.h> #include <asm/cputable.h> #include <asm/cacheflush.h> -#include <asm/tlbflush.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/kvm_ppc.h> diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 34a5adeff084..b0089e04c8c8 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -23,6 +23,7 @@ #include <asm/mmu.h> #include <asm/page.h> #include <asm/asm-offsets.h> +#include <asm/asm-compat.h> #ifdef CONFIG_PPC_BOOK3S_64 #include <asm/exception-64s.h> diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index 98ccc7ec5d48..e5c542a7c5ac 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -19,6 +19,9 @@ /* Real mode helpers */ +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> + #if defined(CONFIG_PPC_BOOK3S_64) #define GET_SHADOW_VCPU(reg) \ diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index f9818d7d3381..126f02b3ffb8 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -317,6 +317,11 @@ static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio) return -EBUSY; } +static u32 xive_vp(struct kvmppc_xive *xive, u32 server) +{ + return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server); +} + static u8 xive_lock_and_mask(struct kvmppc_xive *xive, struct kvmppc_xive_src_block *sb, struct kvmppc_xive_irq_state *state) @@ -362,7 +367,7 @@ static u8 xive_lock_and_mask(struct kvmppc_xive *xive, */ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) { xive_native_configure_irq(hw_num, - xive->vp_base + state->act_server, + xive_vp(xive, state->act_server), MASKED, state->number); /* set old_p so we can track if an H_EOI was done */ state->old_p = true; @@ -418,7 +423,7 @@ static void xive_finish_unmask(struct kvmppc_xive *xive, */ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) { xive_native_configure_irq(hw_num, - xive->vp_base + state->act_server, + xive_vp(xive, state->act_server), state->act_priority, state->number); /* If an EOI is needed, do it here */ if (!state->old_p) @@ -495,7 +500,7 @@ static int xive_target_interrupt(struct kvm *kvm, kvmppc_xive_select_irq(state, &hw_num, NULL); return xive_native_configure_irq(hw_num, - xive->vp_base + server, + xive_vp(xive, server), prio, state->number); } @@ -883,7 +888,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq, * which is fine for a never started interrupt. */ xive_native_configure_irq(hw_irq, - xive->vp_base + state->act_server, + xive_vp(xive, state->act_server), state->act_priority, state->number); /* @@ -959,7 +964,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq, /* Reconfigure the IPI */ xive_native_configure_irq(state->ipi_number, - xive->vp_base + state->act_server, + xive_vp(xive, state->act_server), state->act_priority, state->number); /* @@ -1084,7 +1089,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, pr_devel("Duplicate !\n"); return -EEXIST; } - if (cpu >= KVM_MAX_VCPUS) { + if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) { pr_devel("Out of bounds !\n"); return -EINVAL; } @@ -1098,7 +1103,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, xc->xive = xive; xc->vcpu = vcpu; xc->server_num = cpu; - xc->vp_id = xive->vp_base + cpu; + xc->vp_id = xive_vp(xive, cpu); xc->mfrr = 0xff; xc->valid = true; diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c index 6e41ba7ec8f4..4171ede8722b 100644 --- a/arch/powerpc/kvm/book3s_xive_template.c +++ b/arch/powerpc/kvm/book3s_xive_template.c @@ -25,18 +25,6 @@ static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc) */ eieio(); - /* - * DD1 bug workaround: If PIPR is less favored than CPPR - * ignore the interrupt or we might incorrectly lose an IPB - * bit. - */ - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { - __be64 qw1 = __x_readq(__x_tima + TM_QW1_OS); - u8 pipr = be64_to_cpu(qw1) & 0xff; - if (pipr >= xc->hw_cppr) - return; - } - /* Perform the acknowledge OS to register cycle. */ ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG)); @@ -89,8 +77,15 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd) /* If the XIVE supports the new "store EOI facility, use it */ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI) __x_writeq(0, __x_eoi_page(xd) + XIVE_ESB_STORE_EOI); - else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) { + else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) opal_int_eoi(hw_irq); + else if (xd->flags & XIVE_IRQ_FLAG_LSI) { + /* + * For LSIs the HW EOI cycle is used rather than PQ bits, + * as they are automatically re-triggred in HW when still + * pending. + */ + __x_readq(__x_eoi_page(xd) + XIVE_ESB_LOAD_EOI); } else { uint64_t eoi_val; @@ -102,20 +97,12 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd) * * This allows us to then do a re-trigger if Q was set * rather than synthetizing an interrupt in software - * - * For LSIs, using the HW EOI cycle works around a problem - * on P9 DD1 PHBs where the other ESB accesses don't work - * properly. */ - if (xd->flags & XIVE_IRQ_FLAG_LSI) - __x_readq(__x_eoi_page(xd) + XIVE_ESB_LOAD_EOI); - else { - eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00); - - /* Re-trigger if needed */ - if ((eoi_val & 1) && __x_trig_page(xd)) - __x_writeq(0, __x_trig_page(xd)); - } + eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00); + + /* Re-trigger if needed */ + if ((eoi_val & 1) && __x_trig_page(xd)) + __x_writeq(0, __x_trig_page(xd)); } } diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index f9f6468f4171..afd3c255a427 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -21,7 +21,6 @@ #include <asm/reg.h> #include <asm/cputable.h> -#include <asm/tlbflush.h> #include <asm/kvm_ppc.h> #include "../mm/mmu_decl.h" diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index d0b6b5788afc..d31645491a93 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -21,7 +21,6 @@ #include <asm/reg.h> #include <asm/cputable.h> -#include <asm/tlbflush.h> #include <asm/kvm_ppc.h> #include <asm/dbell.h> diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index afde788be141..75dce1ef3bc8 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -106,7 +106,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) * if mmio_vsx_tx_sx_enabled == 1, copy data between * VSR[32..63] and memory */ - vcpu->arch.mmio_vsx_tx_sx_enabled = get_tx_or_sx(inst); vcpu->arch.mmio_vsx_copy_nums = 0; vcpu->arch.mmio_vsx_offset = 0; vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE; @@ -242,8 +241,8 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) } emulated = kvmppc_handle_vsx_load(run, vcpu, - KVM_MMIO_REG_VSX | (op.reg & 0x1f), - io_size_each, 1, op.type & SIGNEXT); + KVM_MMIO_REG_VSX|op.reg, io_size_each, + 1, op.type & SIGNEXT); break; } #endif @@ -363,7 +362,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) } emulated = kvmppc_handle_vsx_store(run, vcpu, - op.reg & 0x1f, io_size_each, 1); + op.reg, io_size_each, 1); break; } #endif diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 0e8c20c5eaac..eba5756d5b41 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -33,7 +33,6 @@ #include <asm/cputable.h> #include <linux/uaccess.h> #include <asm/kvm_ppc.h> -#include <asm/tlbflush.h> #include <asm/cputhreads.h> #include <asm/irqflags.h> #include <asm/iommu.h> @@ -880,10 +879,10 @@ static inline void kvmppc_set_vsr_dword(struct kvm_vcpu *vcpu, if (offset == -1) return; - if (vcpu->arch.mmio_vsx_tx_sx_enabled) { - val.vval = VCPU_VSX_VR(vcpu, index); + if (index >= 32) { + val.vval = VCPU_VSX_VR(vcpu, index - 32); val.vsxval[offset] = gpr; - VCPU_VSX_VR(vcpu, index) = val.vval; + VCPU_VSX_VR(vcpu, index - 32) = val.vval; } else { VCPU_VSX_FPR(vcpu, index, offset) = gpr; } @@ -895,11 +894,11 @@ static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu, union kvmppc_one_reg val; int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK; - if (vcpu->arch.mmio_vsx_tx_sx_enabled) { - val.vval = VCPU_VSX_VR(vcpu, index); + if (index >= 32) { + val.vval = VCPU_VSX_VR(vcpu, index - 32); val.vsxval[0] = gpr; val.vsxval[1] = gpr; - VCPU_VSX_VR(vcpu, index) = val.vval; + VCPU_VSX_VR(vcpu, index - 32) = val.vval; } else { VCPU_VSX_FPR(vcpu, index, 0) = gpr; VCPU_VSX_FPR(vcpu, index, 1) = gpr; @@ -912,12 +911,12 @@ static inline void kvmppc_set_vsr_word_dump(struct kvm_vcpu *vcpu, union kvmppc_one_reg val; int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK; - if (vcpu->arch.mmio_vsx_tx_sx_enabled) { + if (index >= 32) { val.vsx32val[0] = gpr; val.vsx32val[1] = gpr; val.vsx32val[2] = gpr; val.vsx32val[3] = gpr; - VCPU_VSX_VR(vcpu, index) = val.vval; + VCPU_VSX_VR(vcpu, index - 32) = val.vval; } else { val.vsx32val[0] = gpr; val.vsx32val[1] = gpr; @@ -937,10 +936,10 @@ static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu, if (offset == -1) return; - if (vcpu->arch.mmio_vsx_tx_sx_enabled) { - val.vval = VCPU_VSX_VR(vcpu, index); + if (index >= 32) { + val.vval = VCPU_VSX_VR(vcpu, index - 32); val.vsx32val[offset] = gpr32; - VCPU_VSX_VR(vcpu, index) = val.vval; + VCPU_VSX_VR(vcpu, index - 32) = val.vval; } else { dword_offset = offset / 2; word_offset = offset % 2; @@ -1361,10 +1360,10 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val) break; } - if (!vcpu->arch.mmio_vsx_tx_sx_enabled) { + if (rs < 32) { *val = VCPU_VSX_FPR(vcpu, rs, vsx_offset); } else { - reg.vval = VCPU_VSX_VR(vcpu, rs); + reg.vval = VCPU_VSX_VR(vcpu, rs - 32); *val = reg.vsxval[vsx_offset]; } break; @@ -1378,13 +1377,13 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val) break; } - if (!vcpu->arch.mmio_vsx_tx_sx_enabled) { + if (rs < 32) { dword_offset = vsx_offset / 2; word_offset = vsx_offset % 2; reg.vsxval[0] = VCPU_VSX_FPR(vcpu, rs, dword_offset); *val = reg.vsx32val[word_offset]; } else { - reg.vval = VCPU_VSX_VR(vcpu, rs); + reg.vval = VCPU_VSX_VR(vcpu, rs - 32); *val = reg.vsx32val[vsx_offset]; } break; diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index d0ca13ad8231..670286808928 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -12,7 +12,7 @@ CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE) obj-y += string.o alloc.o code-patching.o feature-fixups.o -obj-$(CONFIG_PPC32) += div64.o copy_32.o crtsavres.o +obj-$(CONFIG_PPC32) += div64.o copy_32.o crtsavres.o strlen_32.o # See corresponding test in arch/powerpc/Makefile # 64-bit linker creates .sfpr on demand for final link (vmlinux), diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index e0d881ab304e..850f3b8f4da5 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -195,6 +195,22 @@ int patch_branch(unsigned int *addr, unsigned long target, int flags) return patch_instruction(addr, create_branch(addr, target, flags)); } +int patch_branch_site(s32 *site, unsigned long target, int flags) +{ + unsigned int *addr; + + addr = (unsigned int *)((unsigned long)site + *site); + return patch_instruction(addr, create_branch(addr, target, flags)); +} + +int patch_instruction_site(s32 *site, unsigned int instr) +{ + unsigned int *addr; + + addr = (unsigned int *)((unsigned long)site + *site); + return patch_instruction(addr, instr); +} + bool is_offset_in_branch_range(long offset) { /* diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S index da425bb6b369..ba66846fe973 100644 --- a/arch/powerpc/lib/copy_32.S +++ b/arch/powerpc/lib/copy_32.S @@ -13,6 +13,7 @@ #include <asm/errno.h> #include <asm/ppc_asm.h> #include <asm/export.h> +#include <asm/code-patching-asm.h> #define COPY_16_BYTES \ lwz r7,4(r4); \ @@ -107,8 +108,8 @@ _GLOBAL(memset) * Skip optimised bloc until cache is enabled. Will be replaced * by 'bne' during boot to use normal procedure if r4 is not zero */ -_GLOBAL(memset_nocache_branch) - b 2f +5: b 2f + patch_site 5b, patch__memset_nocache clrlwi r7,r6,32-LG_CACHELINE_BYTES add r8,r7,r5 @@ -168,7 +169,9 @@ _GLOBAL(memmove) /* fall through */ _GLOBAL(memcpy) - b generic_memcpy +1: b generic_memcpy + patch_site 1b, patch__memcpy_nocache + add r7,r3,r5 /* test if the src & dst overlap */ add r8,r4,r5 cmplw 0,r4,r7 diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 8d5034f645f3..694390357667 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -11,6 +11,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/export.h> +#include <asm/feature-fixups.h> .section ".toc","aw" PPC64_CACHES: diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S index 8fa73b7ab20e..e38f956f7d9f 100644 --- a/arch/powerpc/lib/copypage_power7.S +++ b/arch/powerpc/lib/copypage_power7.S @@ -57,7 +57,7 @@ _GLOBAL(copypage_power7) std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl enter_vmx_copy + bl enter_vmx_ops cmpwi r3,0 ld r0,STACKFRAMESIZE+16(r1) ld r3,STK_REG(R31)(r1) @@ -100,7 +100,7 @@ _GLOBAL(copypage_power7) addi r3,r3,128 bdnz 1b - b exit_vmx_copy /* tail call optimise */ + b exit_vmx_ops /* tail call optimise */ #else li r0,(PAGE_SIZE/128) diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S index 506677395681..96c514bee66b 100644 --- a/arch/powerpc/lib/copyuser_64.S +++ b/arch/powerpc/lib/copyuser_64.S @@ -9,6 +9,13 @@ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/export.h> +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> + +#ifndef SELFTEST_CASE +/* 0 == most CPUs, 1 == POWER6, 2 == Cell */ +#define SELFTEST_CASE 0 +#endif #ifdef __BIG_ENDIAN__ #define sLd sld /* Shift towards low-numbered address. */ @@ -18,6 +25,28 @@ #define sHd sld /* Shift towards high-numbered address. */ #endif +/* + * These macros are used to generate exception table entries. + * The exception handlers below use the original arguments + * (stored on the stack) and the point where we're up to in + * the destination buffer, i.e. the address of the first + * unmodified byte. Generally r3 points into the destination + * buffer, but the first unmodified byte is at a variable + * offset from r3. In the code below, the symbol r3_offset + * is set to indicate the current offset at each point in + * the code. This offset is then used as a negative offset + * from the exception handler code, and those instructions + * before the exception handlers are addi instructions that + * adjust r3 to point to the correct place. + */ + .macro lex /* exception handler for load */ +100: EX_TABLE(100b, .Lld_exc - r3_offset) + .endm + + .macro stex /* exception handler for store */ +100: EX_TABLE(100b, .Lst_exc - r3_offset) + .endm + .align 7 _GLOBAL_TOC(__copy_tofrom_user) #ifdef CONFIG_PPC_BOOK3S_64 @@ -28,7 +57,7 @@ FTR_SECTION_ELSE ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) #endif _GLOBAL(__copy_tofrom_user_base) - /* first check for a whole page copy on a page boundary */ + /* first check for a 4kB copy on a 4kB boundary */ cmpldi cr1,r5,16 cmpdi cr6,r5,4096 or r0,r3,r4 @@ -49,6 +78,7 @@ _GLOBAL(__copy_tofrom_user_base) * At the time of writing the only CPU that has this combination of bits * set is Power6. */ +test_feature = (SELFTEST_CASE == 1) BEGIN_FTR_SECTION nop FTR_SECTION_ELSE @@ -57,6 +87,8 @@ ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \ CPU_FTR_UNALIGNED_LD_STD) .Ldst_aligned: addi r3,r3,-16 +r3_offset = 16 +test_feature = (SELFTEST_CASE == 0) BEGIN_FTR_SECTION andi. r0,r4,7 bne .Lsrc_unaligned @@ -64,57 +96,69 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) blt cr1,.Ldo_tail /* if < 16 bytes to copy */ srdi r0,r5,5 cmpdi cr1,r0,0 -20: ld r7,0(r4) -220: ld r6,8(r4) +lex; ld r7,0(r4) +lex; ld r6,8(r4) addi r4,r4,16 mtctr r0 andi. r0,r5,0x10 beq 22f addi r3,r3,16 +r3_offset = 0 addi r4,r4,-16 mr r9,r7 mr r8,r6 beq cr1,72f -21: ld r7,16(r4) -221: ld r6,24(r4) +21: +lex; ld r7,16(r4) +lex; ld r6,24(r4) addi r4,r4,32 -70: std r9,0(r3) -270: std r8,8(r3) -22: ld r9,0(r4) -222: ld r8,8(r4) -71: std r7,16(r3) -271: std r6,24(r3) +stex; std r9,0(r3) +r3_offset = 8 +stex; std r8,8(r3) +r3_offset = 16 +22: +lex; ld r9,0(r4) +lex; ld r8,8(r4) +stex; std r7,16(r3) +r3_offset = 24 +stex; std r6,24(r3) addi r3,r3,32 +r3_offset = 0 bdnz 21b -72: std r9,0(r3) -272: std r8,8(r3) +72: +stex; std r9,0(r3) +r3_offset = 8 +stex; std r8,8(r3) +r3_offset = 16 andi. r5,r5,0xf beq+ 3f addi r4,r4,16 .Ldo_tail: addi r3,r3,16 +r3_offset = 0 bf cr7*4+0,246f -244: ld r9,0(r4) +lex; ld r9,0(r4) addi r4,r4,8 -245: std r9,0(r3) +stex; std r9,0(r3) addi r3,r3,8 246: bf cr7*4+1,1f -23: lwz r9,0(r4) +lex; lwz r9,0(r4) addi r4,r4,4 -73: stw r9,0(r3) +stex; stw r9,0(r3) addi r3,r3,4 1: bf cr7*4+2,2f -44: lhz r9,0(r4) +lex; lhz r9,0(r4) addi r4,r4,2 -74: sth r9,0(r3) +stex; sth r9,0(r3) addi r3,r3,2 2: bf cr7*4+3,3f -45: lbz r9,0(r4) -75: stb r9,0(r3) +lex; lbz r9,0(r4) +stex; stb r9,0(r3) 3: li r3,0 blr .Lsrc_unaligned: +r3_offset = 16 srdi r6,r5,3 addi r5,r5,-16 subf r4,r0,r4 @@ -127,58 +171,69 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) add r5,r5,r0 bt cr7*4+0,28f -24: ld r9,0(r4) /* 3+2n loads, 2+2n stores */ -25: ld r0,8(r4) +lex; ld r9,0(r4) /* 3+2n loads, 2+2n stores */ +lex; ld r0,8(r4) sLd r6,r9,r10 -26: ldu r9,16(r4) +lex; ldu r9,16(r4) sHd r7,r0,r11 sLd r8,r0,r10 or r7,r7,r6 blt cr6,79f -27: ld r0,8(r4) +lex; ld r0,8(r4) b 2f -28: ld r0,0(r4) /* 4+2n loads, 3+2n stores */ -29: ldu r9,8(r4) +28: +lex; ld r0,0(r4) /* 4+2n loads, 3+2n stores */ +lex; ldu r9,8(r4) sLd r8,r0,r10 addi r3,r3,-8 +r3_offset = 24 blt cr6,5f -30: ld r0,8(r4) +lex; ld r0,8(r4) sHd r12,r9,r11 sLd r6,r9,r10 -31: ldu r9,16(r4) +lex; ldu r9,16(r4) or r12,r8,r12 sHd r7,r0,r11 sLd r8,r0,r10 addi r3,r3,16 +r3_offset = 8 beq cr6,78f 1: or r7,r7,r6 -32: ld r0,8(r4) -76: std r12,8(r3) +lex; ld r0,8(r4) +stex; std r12,8(r3) +r3_offset = 16 2: sHd r12,r9,r11 sLd r6,r9,r10 -33: ldu r9,16(r4) +lex; ldu r9,16(r4) or r12,r8,r12 -77: stdu r7,16(r3) +stex; stdu r7,16(r3) +r3_offset = 8 sHd r7,r0,r11 sLd r8,r0,r10 bdnz 1b -78: std r12,8(r3) +78: +stex; std r12,8(r3) +r3_offset = 16 or r7,r7,r6 -79: std r7,16(r3) +79: +stex; std r7,16(r3) +r3_offset = 24 5: sHd r12,r9,r11 or r12,r8,r12 -80: std r12,24(r3) +stex; std r12,24(r3) +r3_offset = 32 bne 6f li r3,0 blr 6: cmpwi cr1,r5,8 addi r3,r3,32 +r3_offset = 0 sLd r9,r9,r10 ble cr1,7f -34: ld r0,8(r4) +lex; ld r0,8(r4) sHd r7,r0,r11 or r9,r7,r9 7: @@ -186,7 +241,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) #ifdef __BIG_ENDIAN__ rotldi r9,r9,32 #endif -94: stw r9,0(r3) +stex; stw r9,0(r3) #ifdef __LITTLE_ENDIAN__ rotrdi r9,r9,32 #endif @@ -195,7 +250,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) #ifdef __BIG_ENDIAN__ rotldi r9,r9,16 #endif -95: sth r9,0(r3) +stex; sth r9,0(r3) #ifdef __LITTLE_ENDIAN__ rotrdi r9,r9,16 #endif @@ -204,7 +259,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) #ifdef __BIG_ENDIAN__ rotldi r9,r9,8 #endif -96: stb r9,0(r3) +stex; stb r9,0(r3) #ifdef __LITTLE_ENDIAN__ rotrdi r9,r9,8 #endif @@ -212,47 +267,55 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) blr .Ldst_unaligned: +r3_offset = 0 PPC_MTOCRF(0x01,r6) /* put #bytes to 8B bdry into cr7 */ subf r5,r6,r5 li r7,0 cmpldi cr1,r5,16 bf cr7*4+3,1f -35: lbz r0,0(r4) -81: stb r0,0(r3) +100: EX_TABLE(100b, .Lld_exc_r7) + lbz r0,0(r4) +100: EX_TABLE(100b, .Lst_exc_r7) + stb r0,0(r3) addi r7,r7,1 1: bf cr7*4+2,2f -36: lhzx r0,r7,r4 -82: sthx r0,r7,r3 +100: EX_TABLE(100b, .Lld_exc_r7) + lhzx r0,r7,r4 +100: EX_TABLE(100b, .Lst_exc_r7) + sthx r0,r7,r3 addi r7,r7,2 2: bf cr7*4+1,3f -37: lwzx r0,r7,r4 -83: stwx r0,r7,r3 +100: EX_TABLE(100b, .Lld_exc_r7) + lwzx r0,r7,r4 +100: EX_TABLE(100b, .Lst_exc_r7) + stwx r0,r7,r3 3: PPC_MTOCRF(0x01,r5) add r4,r6,r4 add r3,r6,r3 b .Ldst_aligned .Lshort_copy: +r3_offset = 0 bf cr7*4+0,1f -38: lwz r0,0(r4) -39: lwz r9,4(r4) +lex; lwz r0,0(r4) +lex; lwz r9,4(r4) addi r4,r4,8 -84: stw r0,0(r3) -85: stw r9,4(r3) +stex; stw r0,0(r3) +stex; stw r9,4(r3) addi r3,r3,8 1: bf cr7*4+1,2f -40: lwz r0,0(r4) +lex; lwz r0,0(r4) addi r4,r4,4 -86: stw r0,0(r3) +stex; stw r0,0(r3) addi r3,r3,4 2: bf cr7*4+2,3f -41: lhz r0,0(r4) +lex; lhz r0,0(r4) addi r4,r4,2 -87: sth r0,0(r3) +stex; sth r0,0(r3) addi r3,r3,2 3: bf cr7*4+3,4f -42: lbz r0,0(r4) -88: stb r0,0(r3) +lex; lbz r0,0(r4) +stex; stb r0,0(r3) 4: li r3,0 blr @@ -260,48 +323,34 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) * exception handlers follow * we have to return the number of bytes not copied * for an exception on a load, we set the rest of the destination to 0 + * Note that the number of bytes of instructions for adjusting r3 needs + * to equal the amount of the adjustment, due to the trick of using + * .Lld_exc - r3_offset as the handler address. */ -136: -137: +.Lld_exc_r7: add r3,r3,r7 - b 1f -130: -131: + b .Lld_exc + + /* adjust by 24 */ addi r3,r3,8 -120: -320: -122: -322: -124: -125: -126: -127: -128: -129: -133: + nop + /* adjust by 16 */ addi r3,r3,8 -132: + nop + /* adjust by 8 */ addi r3,r3,8 -121: -321: -344: -134: -135: -138: -139: -140: -141: -142: -123: -144: -145: + nop /* - * here we have had a fault on a load and r3 points to the first - * unmodified byte of the destination + * Here we have had a fault on a load and r3 points to the first + * unmodified byte of the destination. We use the original arguments + * and r3 to work out how much wasn't copied. Since we load some + * distance ahead of the stores, we continue copying byte-by-byte until + * we hit the load fault again in order to copy as much as possible. */ -1: ld r6,-24(r1) +.Lld_exc: + ld r6,-24(r1) ld r4,-16(r1) ld r5,-8(r1) subf r6,r6,r3 @@ -312,9 +361,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) * first see if we can copy any more bytes before hitting another exception */ mtctr r5 +r3_offset = 0 +100: EX_TABLE(100b, .Ldone) 43: lbz r0,0(r4) addi r4,r4,1 -89: stb r0,0(r3) +stex; stb r0,0(r3) addi r3,r3,1 bdnz 43b li r3,0 /* huh? all copied successfully this time? */ @@ -323,116 +374,63 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) /* * here we have trapped again, amount remaining is in ctr. */ -143: mfctr r3 +.Ldone: + mfctr r3 blr /* - * exception handlers for stores: we just need to work - * out how many bytes weren't copied + * exception handlers for stores: we need to work out how many bytes + * weren't copied, and we may need to copy some more. + * Note that the number of bytes of instructions for adjusting r3 needs + * to equal the amount of the adjustment, due to the trick of using + * .Lst_exc - r3_offset as the handler address. */ -182: -183: +.Lst_exc_r7: add r3,r3,r7 - b 1f -371: -180: + b .Lst_exc + + /* adjust by 24 */ addi r3,r3,8 -171: -177: -179: + nop + /* adjust by 16 */ addi r3,r3,8 -370: -372: -176: -178: + nop + /* adjust by 8 */ addi r3,r3,4 -185: + /* adjust by 4 */ addi r3,r3,4 -170: -172: -345: -173: -174: -175: -181: -184: -186: -187: -188: -189: -194: -195: -196: -1: - ld r6,-24(r1) - ld r5,-8(r1) - add r6,r6,r5 - subf r3,r3,r6 /* #bytes not copied */ +.Lst_exc: + ld r6,-24(r1) /* original destination pointer */ + ld r4,-16(r1) /* original source pointer */ + ld r5,-8(r1) /* original number of bytes */ + add r7,r6,r5 + /* + * If the destination pointer isn't 8-byte aligned, + * we may have got the exception as a result of a + * store that overlapped a page boundary, so we may be + * able to copy a few more bytes. + */ +17: andi. r0,r3,7 + beq 19f + subf r8,r6,r3 /* #bytes copied */ +100: EX_TABLE(100b,19f) + lbzx r0,r8,r4 +100: EX_TABLE(100b,19f) + stb r0,0(r3) + addi r3,r3,1 + cmpld r3,r7 + blt 17b +19: subf r3,r3,r7 /* #bytes not copied in r3 */ blr - EX_TABLE(20b,120b) - EX_TABLE(220b,320b) - EX_TABLE(21b,121b) - EX_TABLE(221b,321b) - EX_TABLE(70b,170b) - EX_TABLE(270b,370b) - EX_TABLE(22b,122b) - EX_TABLE(222b,322b) - EX_TABLE(71b,171b) - EX_TABLE(271b,371b) - EX_TABLE(72b,172b) - EX_TABLE(272b,372b) - EX_TABLE(244b,344b) - EX_TABLE(245b,345b) - EX_TABLE(23b,123b) - EX_TABLE(73b,173b) - EX_TABLE(44b,144b) - EX_TABLE(74b,174b) - EX_TABLE(45b,145b) - EX_TABLE(75b,175b) - EX_TABLE(24b,124b) - EX_TABLE(25b,125b) - EX_TABLE(26b,126b) - EX_TABLE(27b,127b) - EX_TABLE(28b,128b) - EX_TABLE(29b,129b) - EX_TABLE(30b,130b) - EX_TABLE(31b,131b) - EX_TABLE(32b,132b) - EX_TABLE(76b,176b) - EX_TABLE(33b,133b) - EX_TABLE(77b,177b) - EX_TABLE(78b,178b) - EX_TABLE(79b,179b) - EX_TABLE(80b,180b) - EX_TABLE(34b,134b) - EX_TABLE(94b,194b) - EX_TABLE(95b,195b) - EX_TABLE(96b,196b) - EX_TABLE(35b,135b) - EX_TABLE(81b,181b) - EX_TABLE(36b,136b) - EX_TABLE(82b,182b) - EX_TABLE(37b,137b) - EX_TABLE(83b,183b) - EX_TABLE(38b,138b) - EX_TABLE(39b,139b) - EX_TABLE(84b,184b) - EX_TABLE(85b,185b) - EX_TABLE(40b,140b) - EX_TABLE(86b,186b) - EX_TABLE(41b,141b) - EX_TABLE(87b,187b) - EX_TABLE(42b,142b) - EX_TABLE(88b,188b) - EX_TABLE(43b,143b) - EX_TABLE(89b,189b) - /* * Routine to copy a whole page of data, optimized for POWER4. * On POWER4 it is more than 50% faster than the simple loop * above (following the .Ldst_aligned label). */ + .macro exc +100: EX_TABLE(100b, .Labort) + .endm .Lcopy_page_4K: std r31,-32(1) std r30,-40(1) @@ -451,86 +449,86 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) li r0,5 0: addi r5,r5,-24 mtctr r0 -20: ld r22,640(4) -21: ld r21,512(4) -22: ld r20,384(4) -23: ld r11,256(4) -24: ld r9,128(4) -25: ld r7,0(4) -26: ld r25,648(4) -27: ld r24,520(4) -28: ld r23,392(4) -29: ld r10,264(4) -30: ld r8,136(4) -31: ldu r6,8(4) +exc; ld r22,640(4) +exc; ld r21,512(4) +exc; ld r20,384(4) +exc; ld r11,256(4) +exc; ld r9,128(4) +exc; ld r7,0(4) +exc; ld r25,648(4) +exc; ld r24,520(4) +exc; ld r23,392(4) +exc; ld r10,264(4) +exc; ld r8,136(4) +exc; ldu r6,8(4) cmpwi r5,24 1: -32: std r22,648(3) -33: std r21,520(3) -34: std r20,392(3) -35: std r11,264(3) -36: std r9,136(3) -37: std r7,8(3) -38: ld r28,648(4) -39: ld r27,520(4) -40: ld r26,392(4) -41: ld r31,264(4) -42: ld r30,136(4) -43: ld r29,8(4) -44: std r25,656(3) -45: std r24,528(3) -46: std r23,400(3) -47: std r10,272(3) -48: std r8,144(3) -49: std r6,16(3) -50: ld r22,656(4) -51: ld r21,528(4) -52: ld r20,400(4) -53: ld r11,272(4) -54: ld r9,144(4) -55: ld r7,16(4) -56: std r28,664(3) -57: std r27,536(3) -58: std r26,408(3) -59: std r31,280(3) -60: std r30,152(3) -61: stdu r29,24(3) -62: ld r25,664(4) -63: ld r24,536(4) -64: ld r23,408(4) -65: ld r10,280(4) -66: ld r8,152(4) -67: ldu r6,24(4) +exc; std r22,648(3) +exc; std r21,520(3) +exc; std r20,392(3) +exc; std r11,264(3) +exc; std r9,136(3) +exc; std r7,8(3) +exc; ld r28,648(4) +exc; ld r27,520(4) +exc; ld r26,392(4) +exc; ld r31,264(4) +exc; ld r30,136(4) +exc; ld r29,8(4) +exc; std r25,656(3) +exc; std r24,528(3) +exc; std r23,400(3) +exc; std r10,272(3) +exc; std r8,144(3) +exc; std r6,16(3) +exc; ld r22,656(4) +exc; ld r21,528(4) +exc; ld r20,400(4) +exc; ld r11,272(4) +exc; ld r9,144(4) +exc; ld r7,16(4) +exc; std r28,664(3) +exc; std r27,536(3) +exc; std r26,408(3) +exc; std r31,280(3) +exc; std r30,152(3) +exc; stdu r29,24(3) +exc; ld r25,664(4) +exc; ld r24,536(4) +exc; ld r23,408(4) +exc; ld r10,280(4) +exc; ld r8,152(4) +exc; ldu r6,24(4) bdnz 1b -68: std r22,648(3) -69: std r21,520(3) -70: std r20,392(3) -71: std r11,264(3) -72: std r9,136(3) -73: std r7,8(3) -74: addi r4,r4,640 -75: addi r3,r3,648 +exc; std r22,648(3) +exc; std r21,520(3) +exc; std r20,392(3) +exc; std r11,264(3) +exc; std r9,136(3) +exc; std r7,8(3) + addi r4,r4,640 + addi r3,r3,648 bge 0b mtctr r5 -76: ld r7,0(4) -77: ld r8,8(4) -78: ldu r9,16(4) +exc; ld r7,0(4) +exc; ld r8,8(4) +exc; ldu r9,16(4) 3: -79: ld r10,8(4) -80: std r7,8(3) -81: ld r7,16(4) -82: std r8,16(3) -83: ld r8,24(4) -84: std r9,24(3) -85: ldu r9,32(4) -86: stdu r10,32(3) +exc; ld r10,8(4) +exc; std r7,8(3) +exc; ld r7,16(4) +exc; std r8,16(3) +exc; ld r8,24(4) +exc; std r9,24(3) +exc; ldu r9,32(4) +exc; stdu r10,32(3) bdnz 3b 4: -87: ld r10,8(4) -88: std r7,8(3) -89: std r8,16(3) -90: std r9,24(3) -91: std r10,32(3) +exc; ld r10,8(4) +exc; std r7,8(3) +exc; std r8,16(3) +exc; std r9,24(3) +exc; std r10,32(3) 9: ld r20,-120(1) ld r21,-112(1) ld r22,-104(1) @@ -550,7 +548,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) * on an exception, reset to the beginning and jump back into the * standard __copy_tofrom_user */ -100: ld r20,-120(1) +.Labort: + ld r20,-120(1) ld r21,-112(1) ld r22,-104(1) ld r23,-96(1) @@ -566,78 +565,4 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) ld r4,-16(r1) li r5,4096 b .Ldst_aligned - - EX_TABLE(20b,100b) - EX_TABLE(21b,100b) - EX_TABLE(22b,100b) - EX_TABLE(23b,100b) - EX_TABLE(24b,100b) - EX_TABLE(25b,100b) - EX_TABLE(26b,100b) - EX_TABLE(27b,100b) - EX_TABLE(28b,100b) - EX_TABLE(29b,100b) - EX_TABLE(30b,100b) - EX_TABLE(31b,100b) - EX_TABLE(32b,100b) - EX_TABLE(33b,100b) - EX_TABLE(34b,100b) - EX_TABLE(35b,100b) - EX_TABLE(36b,100b) - EX_TABLE(37b,100b) - EX_TABLE(38b,100b) - EX_TABLE(39b,100b) - EX_TABLE(40b,100b) - EX_TABLE(41b,100b) - EX_TABLE(42b,100b) - EX_TABLE(43b,100b) - EX_TABLE(44b,100b) - EX_TABLE(45b,100b) - EX_TABLE(46b,100b) - EX_TABLE(47b,100b) - EX_TABLE(48b,100b) - EX_TABLE(49b,100b) - EX_TABLE(50b,100b) - EX_TABLE(51b,100b) - EX_TABLE(52b,100b) - EX_TABLE(53b,100b) - EX_TABLE(54b,100b) - EX_TABLE(55b,100b) - EX_TABLE(56b,100b) - EX_TABLE(57b,100b) - EX_TABLE(58b,100b) - EX_TABLE(59b,100b) - EX_TABLE(60b,100b) - EX_TABLE(61b,100b) - EX_TABLE(62b,100b) - EX_TABLE(63b,100b) - EX_TABLE(64b,100b) - EX_TABLE(65b,100b) - EX_TABLE(66b,100b) - EX_TABLE(67b,100b) - EX_TABLE(68b,100b) - EX_TABLE(69b,100b) - EX_TABLE(70b,100b) - EX_TABLE(71b,100b) - EX_TABLE(72b,100b) - EX_TABLE(73b,100b) - EX_TABLE(74b,100b) - EX_TABLE(75b,100b) - EX_TABLE(76b,100b) - EX_TABLE(77b,100b) - EX_TABLE(78b,100b) - EX_TABLE(79b,100b) - EX_TABLE(80b,100b) - EX_TABLE(81b,100b) - EX_TABLE(82b,100b) - EX_TABLE(83b,100b) - EX_TABLE(84b,100b) - EX_TABLE(85b,100b) - EX_TABLE(86b,100b) - EX_TABLE(87b,100b) - EX_TABLE(88b,100b) - EX_TABLE(89b,100b) - EX_TABLE(90b,100b) - EX_TABLE(91b,100b) - EXPORT_SYMBOL(__copy_tofrom_user) diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 215e4760c09f..1a1fe180af62 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -19,6 +19,11 @@ */ #include <asm/ppc_asm.h> +#ifndef SELFTEST_CASE +/* 0 == don't use VMX, 1 == use VMX */ +#define SELFTEST_CASE 0 +#endif + #ifdef __BIG_ENDIAN__ #define LVS(VRT,RA,RB) lvsl VRT,RA,RB #define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC @@ -80,7 +85,6 @@ _GLOBAL(__copy_tofrom_user_power7) -#ifdef CONFIG_ALTIVEC cmpldi r5,16 cmpldi cr1,r5,3328 @@ -89,15 +93,12 @@ _GLOBAL(__copy_tofrom_user_power7) std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) blt .Lshort_copy - bge cr1,.Lvmx_copy -#else - cmpldi r5,16 - std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) - std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) - std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) - - blt .Lshort_copy +#ifdef CONFIG_ALTIVEC +test_feature = SELFTEST_CASE +BEGIN_FTR_SECTION + bgt cr1,.Lvmx_copy +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif .Lnonvmx_copy: @@ -278,8 +279,8 @@ err1; stb r0,0(r3) addi r1,r1,STACKFRAMESIZE b .Lnonvmx_copy -#ifdef CONFIG_ALTIVEC .Lvmx_copy: +#ifdef CONFIG_ALTIVEC mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) diff --git a/arch/powerpc/lib/feature-fixups-test.S b/arch/powerpc/lib/feature-fixups-test.S index f16cec989506..ee7c5fd5fc64 100644 --- a/arch/powerpc/lib/feature-fixups-test.S +++ b/arch/powerpc/lib/feature-fixups-test.S @@ -11,6 +11,7 @@ #include <asm/feature-fixups.h> #include <asm/ppc_asm.h> #include <asm/synch.h> +#include <asm/asm-compat.h> .text diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 8b69f868298c..e613b02bb2f0 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -304,6 +304,9 @@ void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_ printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); } +#endif /* CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_BARRIER_NOSPEC void do_barrier_nospec_fixups(bool enable) { void *start, *end; @@ -313,8 +316,38 @@ void do_barrier_nospec_fixups(bool enable) do_barrier_nospec_fixups_range(enable, start, end); } +#endif /* CONFIG_PPC_BARRIER_NOSPEC */ -#endif /* CONFIG_PPC_BOOK3S_64 */ +#ifdef CONFIG_PPC_FSL_BOOK3E +void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end) +{ + unsigned int instr[2], *dest; + long *start, *end; + int i; + + start = fixup_start; + end = fixup_end; + + instr[0] = PPC_INST_NOP; + instr[1] = PPC_INST_NOP; + + if (enable) { + pr_info("barrier-nospec: using isync; sync as speculation barrier\n"); + instr[0] = PPC_INST_ISYNC; + instr[1] = PPC_INST_SYNC; + } + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + patch_instruction(dest, instr[0]); + patch_instruction(dest + 1, instr[1]); + } + + printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); +} +#endif /* CONFIG_PPC_FSL_BOOK3E */ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) { diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S index 3de7ac154f24..0526b2225260 100644 --- a/arch/powerpc/lib/hweight_64.S +++ b/arch/powerpc/lib/hweight_64.S @@ -20,6 +20,7 @@ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/export.h> +#include <asm/feature-fixups.h> /* Note: This code relies on -mminimal-toc */ diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S index ae15eba49c1f..32e91994b6b2 100644 --- a/arch/powerpc/lib/ldstfp.S +++ b/arch/powerpc/lib/ldstfp.S @@ -15,6 +15,7 @@ #include <asm/ppc-opcode.h> #include <asm/reg.h> #include <asm/asm-offsets.h> +#include <asm/asm-compat.h> #include <linux/errno.h> #ifdef CONFIG_PPC_FPU diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c index b7b1237d4aa6..35a0ef932e1a 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -15,7 +15,6 @@ #include <linux/kernel.h> #include <linux/spinlock.h> #include <linux/export.h> -#include <linux/stringify.h> #include <linux/smp.h> /* waiting for a spinlock... */ diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S index d75d18b7bd55..844d8e774492 100644 --- a/arch/powerpc/lib/memcmp_64.S +++ b/arch/powerpc/lib/memcmp_64.S @@ -9,6 +9,7 @@ */ #include <asm/ppc_asm.h> #include <asm/export.h> +#include <asm/ppc-opcode.h> #define off8 r6 #define off16 r7 @@ -24,28 +25,102 @@ #define rH r31 #ifdef __LITTLE_ENDIAN__ +#define LH lhbrx +#define LW lwbrx #define LD ldbrx +#define LVS lvsr +#define VPERM(_VRT,_VRA,_VRB,_VRC) \ + vperm _VRT,_VRB,_VRA,_VRC #else +#define LH lhzx +#define LW lwzx #define LD ldx +#define LVS lvsl +#define VPERM(_VRT,_VRA,_VRB,_VRC) \ + vperm _VRT,_VRA,_VRB,_VRC #endif -_GLOBAL(memcmp) +#define VMX_THRESH 4096 +#define ENTER_VMX_OPS \ + mflr r0; \ + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1); \ + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1); \ + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1); \ + std r0,16(r1); \ + stdu r1,-STACKFRAMESIZE(r1); \ + bl enter_vmx_ops; \ + cmpwi cr1,r3,0; \ + ld r0,STACKFRAMESIZE+16(r1); \ + ld r3,STK_REG(R31)(r1); \ + ld r4,STK_REG(R30)(r1); \ + ld r5,STK_REG(R29)(r1); \ + addi r1,r1,STACKFRAMESIZE; \ + mtlr r0 + +#define EXIT_VMX_OPS \ + mflr r0; \ + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1); \ + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1); \ + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1); \ + std r0,16(r1); \ + stdu r1,-STACKFRAMESIZE(r1); \ + bl exit_vmx_ops; \ + ld r0,STACKFRAMESIZE+16(r1); \ + ld r3,STK_REG(R31)(r1); \ + ld r4,STK_REG(R30)(r1); \ + ld r5,STK_REG(R29)(r1); \ + addi r1,r1,STACKFRAMESIZE; \ + mtlr r0 + +/* + * LD_VSR_CROSS16B load the 2nd 16 bytes for _vaddr which is unaligned with + * 16 bytes boundary and permute the result with the 1st 16 bytes. + + * | y y y y y y y y y y y y y 0 1 2 | 3 4 5 6 7 8 9 a b c d e f z z z | + * ^ ^ ^ + * 0xbbbb10 0xbbbb20 0xbbb30 + * ^ + * _vaddr + * + * + * _vmask is the mask generated by LVS + * _v1st_qw is the 1st aligned QW of current addr which is already loaded. + * for example: 0xyyyyyyyyyyyyy012 for big endian + * _v2nd_qw is the 2nd aligned QW of cur _vaddr to be loaded. + * for example: 0x3456789abcdefzzz for big endian + * The permute result is saved in _v_res. + * for example: 0x0123456789abcdef for big endian. + */ +#define LD_VSR_CROSS16B(_vaddr,_vmask,_v1st_qw,_v2nd_qw,_v_res) \ + lvx _v2nd_qw,_vaddr,off16; \ + VPERM(_v_res,_v1st_qw,_v2nd_qw,_vmask) + +/* + * There are 2 categories for memcmp: + * 1) src/dst has the same offset to the 8 bytes boundary. The handlers + * are named like .Lsameoffset_xxxx + * 2) src/dst has different offset to the 8 bytes boundary. The handlers + * are named like .Ldiffoffset_xxxx + */ +_GLOBAL_TOC(memcmp) cmpdi cr1,r5,0 - /* Use the short loop if both strings are not 8B aligned */ - or r6,r3,r4 + /* Use the short loop if the src/dst addresses are not + * with the same offset of 8 bytes align boundary. + */ + xor r6,r3,r4 andi. r6,r6,7 - /* Use the short loop if length is less than 32B */ - cmpdi cr6,r5,31 + /* Fall back to short loop if compare at aligned addrs + * with less than 8 bytes. + */ + cmpdi cr6,r5,7 beq cr1,.Lzero - bne .Lshort - bgt cr6,.Llong + bgt cr6,.Lno_short .Lshort: mtctr r5 - 1: lbz rA,0(r3) lbz rB,0(r4) subf. rC,rB,rA @@ -78,11 +153,98 @@ _GLOBAL(memcmp) li r3,0 blr +.Lno_short: + dcbt 0,r3 + dcbt 0,r4 + bne .Ldiffoffset_8bytes_make_align_start + + +.Lsameoffset_8bytes_make_align_start: + /* attempt to compare bytes not aligned with 8 bytes so that + * rest comparison can run based on 8 bytes alignment. + */ + andi. r6,r3,7 + + /* Try to compare the first double word which is not 8 bytes aligned: + * load the first double word at (src & ~7UL) and shift left appropriate + * bits before comparision. + */ + rlwinm r6,r3,3,26,28 + beq .Lsameoffset_8bytes_aligned + clrrdi r3,r3,3 + clrrdi r4,r4,3 + LD rA,0,r3 + LD rB,0,r4 + sld rA,rA,r6 + sld rB,rB,r6 + cmpld cr0,rA,rB + srwi r6,r6,3 + bne cr0,.LcmpAB_lightweight + subfic r6,r6,8 + subf. r5,r6,r5 + addi r3,r3,8 + addi r4,r4,8 + beq .Lzero + +.Lsameoffset_8bytes_aligned: + /* now we are aligned with 8 bytes. + * Use .Llong loop if left cmp bytes are equal or greater than 32B. + */ + cmpdi cr6,r5,31 + bgt cr6,.Llong + +.Lcmp_lt32bytes: + /* compare 1 ~ 31 bytes, at least r3 addr is 8 bytes aligned now */ + cmpdi cr5,r5,7 + srdi r0,r5,3 + ble cr5,.Lcmp_rest_lt8bytes + + /* handle 8 ~ 31 bytes */ + clrldi r5,r5,61 + mtctr r0 +2: + LD rA,0,r3 + LD rB,0,r4 + cmpld cr0,rA,rB + addi r3,r3,8 + addi r4,r4,8 + bne cr0,.LcmpAB_lightweight + bdnz 2b + + cmpwi r5,0 + beq .Lzero + +.Lcmp_rest_lt8bytes: + /* Here we have only less than 8 bytes to compare with. at least s1 + * Address is aligned with 8 bytes. + * The next double words are load and shift right with appropriate + * bits. + */ + subfic r6,r5,8 + slwi r6,r6,3 + LD rA,0,r3 + LD rB,0,r4 + srd rA,rA,r6 + srd rB,rB,r6 + cmpld cr0,rA,rB + bne cr0,.LcmpAB_lightweight + b .Lzero + .Lnon_zero: mr r3,rC blr .Llong: +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + /* Try to use vmx loop if length is equal or greater than 4K */ + cmpldi cr6,r5,VMX_THRESH + bge cr6,.Lsameoffset_vmx_cmp +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + +.Llong_novmx_cmp: +#endif + /* At least s1 addr is aligned with 8 bytes */ li off8,8 li off16,16 li off24,24 @@ -232,4 +394,240 @@ _GLOBAL(memcmp) ld r28,-32(r1) ld r27,-40(r1) blr + +.LcmpAB_lightweight: /* skip NV GPRS restore */ + li r3,1 + bgtlr + li r3,-1 + blr + +#ifdef CONFIG_ALTIVEC +.Lsameoffset_vmx_cmp: + /* Enter with src/dst addrs has the same offset with 8 bytes + * align boundary. + * + * There is an optimization based on following fact: memcmp() + * prones to fail early at the first 32 bytes. + * Before applying VMX instructions which will lead to 32x128bits + * VMX regs load/restore penalty, we compare the first 32 bytes + * so that we can catch the ~80% fail cases. + */ + + li r0,4 + mtctr r0 +.Lsameoffset_prechk_32B_loop: + LD rA,0,r3 + LD rB,0,r4 + cmpld cr0,rA,rB + addi r3,r3,8 + addi r4,r4,8 + bne cr0,.LcmpAB_lightweight + addi r5,r5,-8 + bdnz .Lsameoffset_prechk_32B_loop + + ENTER_VMX_OPS + beq cr1,.Llong_novmx_cmp + +3: + /* need to check whether r4 has the same offset with r3 + * for 16 bytes boundary. + */ + xor r0,r3,r4 + andi. r0,r0,0xf + bne .Ldiffoffset_vmx_cmp_start + + /* len is no less than 4KB. Need to align with 16 bytes further. + */ + andi. rA,r3,8 + LD rA,0,r3 + beq 4f + LD rB,0,r4 + cmpld cr0,rA,rB + addi r3,r3,8 + addi r4,r4,8 + addi r5,r5,-8 + + beq cr0,4f + /* save and restore cr0 */ + mfocrf r5,128 + EXIT_VMX_OPS + mtocrf 128,r5 + b .LcmpAB_lightweight + +4: + /* compare 32 bytes for each loop */ + srdi r0,r5,5 + mtctr r0 + clrldi r5,r5,59 + li off16,16 + +.balign 16 +5: + lvx v0,0,r3 + lvx v1,0,r4 + VCMPEQUD_RC(v0,v0,v1) + bnl cr6,7f + lvx v0,off16,r3 + lvx v1,off16,r4 + VCMPEQUD_RC(v0,v0,v1) + bnl cr6,6f + addi r3,r3,32 + addi r4,r4,32 + bdnz 5b + + EXIT_VMX_OPS + cmpdi r5,0 + beq .Lzero + b .Lcmp_lt32bytes + +6: + addi r3,r3,16 + addi r4,r4,16 + +7: + /* diff the last 16 bytes */ + EXIT_VMX_OPS + LD rA,0,r3 + LD rB,0,r4 + cmpld cr0,rA,rB + li off8,8 + bne cr0,.LcmpAB_lightweight + + LD rA,off8,r3 + LD rB,off8,r4 + cmpld cr0,rA,rB + bne cr0,.LcmpAB_lightweight + b .Lzero +#endif + +.Ldiffoffset_8bytes_make_align_start: + /* now try to align s1 with 8 bytes */ + rlwinm r6,r3,3,26,28 + beq .Ldiffoffset_align_s1_8bytes + + clrrdi r3,r3,3 + LD rA,0,r3 + LD rB,0,r4 /* unaligned load */ + sld rA,rA,r6 + srd rA,rA,r6 + srd rB,rB,r6 + cmpld cr0,rA,rB + srwi r6,r6,3 + bne cr0,.LcmpAB_lightweight + + subfic r6,r6,8 + subf. r5,r6,r5 + addi r3,r3,8 + add r4,r4,r6 + + beq .Lzero + +.Ldiffoffset_align_s1_8bytes: + /* now s1 is aligned with 8 bytes. */ +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + /* only do vmx ops when the size equal or greater than 4K bytes */ + cmpdi cr5,r5,VMX_THRESH + bge cr5,.Ldiffoffset_vmx_cmp +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + +.Ldiffoffset_novmx_cmp: +#endif + + + cmpdi cr5,r5,31 + ble cr5,.Lcmp_lt32bytes + +#ifdef CONFIG_ALTIVEC + b .Llong_novmx_cmp +#else + b .Llong +#endif + +#ifdef CONFIG_ALTIVEC +.Ldiffoffset_vmx_cmp: + /* perform a 32 bytes pre-checking before + * enable VMX operations. + */ + li r0,4 + mtctr r0 +.Ldiffoffset_prechk_32B_loop: + LD rA,0,r3 + LD rB,0,r4 + cmpld cr0,rA,rB + addi r3,r3,8 + addi r4,r4,8 + bne cr0,.LcmpAB_lightweight + addi r5,r5,-8 + bdnz .Ldiffoffset_prechk_32B_loop + + ENTER_VMX_OPS + beq cr1,.Ldiffoffset_novmx_cmp + +.Ldiffoffset_vmx_cmp_start: + /* Firstly try to align r3 with 16 bytes */ + andi. r6,r3,0xf + li off16,16 + beq .Ldiffoffset_vmx_s1_16bytes_align + + LVS v3,0,r3 + LVS v4,0,r4 + + lvx v5,0,r3 + lvx v6,0,r4 + LD_VSR_CROSS16B(r3,v3,v5,v7,v9) + LD_VSR_CROSS16B(r4,v4,v6,v8,v10) + + VCMPEQUB_RC(v7,v9,v10) + bnl cr6,.Ldiffoffset_vmx_diff_found + + subfic r6,r6,16 + subf r5,r6,r5 + add r3,r3,r6 + add r4,r4,r6 + +.Ldiffoffset_vmx_s1_16bytes_align: + /* now s1 is aligned with 16 bytes */ + lvx v6,0,r4 + LVS v4,0,r4 + srdi r6,r5,5 /* loop for 32 bytes each */ + clrldi r5,r5,59 + mtctr r6 + +.balign 16 +.Ldiffoffset_vmx_32bytesloop: + /* the first qw of r4 was saved in v6 */ + lvx v9,0,r3 + LD_VSR_CROSS16B(r4,v4,v6,v8,v10) + VCMPEQUB_RC(v7,v9,v10) + vor v6,v8,v8 + bnl cr6,.Ldiffoffset_vmx_diff_found + + addi r3,r3,16 + addi r4,r4,16 + + lvx v9,0,r3 + LD_VSR_CROSS16B(r4,v4,v6,v8,v10) + VCMPEQUB_RC(v7,v9,v10) + vor v6,v8,v8 + bnl cr6,.Ldiffoffset_vmx_diff_found + + addi r3,r3,16 + addi r4,r4,16 + + bdnz .Ldiffoffset_vmx_32bytesloop + + EXIT_VMX_OPS + + cmpdi r5,0 + beq .Lzero + b .Lcmp_lt32bytes + +.Ldiffoffset_vmx_diff_found: + EXIT_VMX_OPS + /* anyway, the diff will appear in next 16 bytes */ + li r5,16 + b .Lcmp_lt32bytes + +#endif EXPORT_SYMBOL(memcmp) diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S index 8d8265be1a59..273ea67e60a1 100644 --- a/arch/powerpc/lib/memcpy_64.S +++ b/arch/powerpc/lib/memcpy_64.S @@ -9,6 +9,13 @@ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/export.h> +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> + +#ifndef SELFTEST_CASE +/* For big-endian, 0 == most CPUs, 1 == POWER6, 2 == Cell */ +#define SELFTEST_CASE 0 +#endif .align 7 _GLOBAL_TOC(memcpy) @@ -20,10 +27,8 @@ BEGIN_FTR_SECTION #endif FTR_SECTION_ELSE #ifdef CONFIG_PPC_BOOK3S_64 -#ifndef SELFTEST b memcpy_power7 #endif -#endif ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) #ifdef __LITTLE_ENDIAN__ /* dumb little-endian memcpy that will get replaced at runtime */ @@ -47,6 +52,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) cleared. At the time of writing the only CPU that has this combination of bits set is Power6. */ +test_feature = (SELFTEST_CASE == 1) BEGIN_FTR_SECTION nop FTR_SECTION_ELSE @@ -55,6 +61,7 @@ ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \ CPU_FTR_UNALIGNED_LD_STD) .Ldst_aligned: addi r3,r3,-16 +test_feature = (SELFTEST_CASE == 0) BEGIN_FTR_SECTION andi. r0,r4,7 bne .Lsrc_unaligned diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S index df7de9d3da08..89bfefcf7fcc 100644 --- a/arch/powerpc/lib/memcpy_power7.S +++ b/arch/powerpc/lib/memcpy_power7.S @@ -19,7 +19,10 @@ */ #include <asm/ppc_asm.h> -_GLOBAL(memcpy_power7) +#ifndef SELFTEST_CASE +/* 0 == don't use VMX, 1 == use VMX */ +#define SELFTEST_CASE 0 +#endif #ifdef __BIG_ENDIAN__ #define LVS(VRT,RA,RB) lvsl VRT,RA,RB @@ -29,20 +32,17 @@ _GLOBAL(memcpy_power7) #define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRB,VRA,VRC #endif -#ifdef CONFIG_ALTIVEC +_GLOBAL(memcpy_power7) cmpldi r5,16 cmpldi cr1,r5,4096 - std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) - blt .Lshort_copy - bgt cr1,.Lvmx_copy -#else - cmpldi r5,16 - - std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) - blt .Lshort_copy +#ifdef CONFIG_ALTIVEC +test_feature = SELFTEST_CASE +BEGIN_FTR_SECTION + bgt cr1, .Lvmx_copy +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif .Lnonvmx_copy: @@ -223,14 +223,14 @@ _GLOBAL(memcpy_power7) addi r1,r1,STACKFRAMESIZE b .Lnonvmx_copy -#ifdef CONFIG_ALTIVEC .Lvmx_copy: +#ifdef CONFIG_ALTIVEC mflr r0 std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl enter_vmx_copy + bl enter_vmx_ops cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) ld r3,STK_REG(R31)(r1) @@ -445,7 +445,7 @@ _GLOBAL(memcpy_power7) 15: addi r1,r1,STACKFRAMESIZE ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) - b exit_vmx_copy /* tail call optimise */ + b exit_vmx_ops /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -649,5 +649,5 @@ _GLOBAL(memcpy_power7) 15: addi r1,r1,STACKFRAMESIZE ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) - b exit_vmx_copy /* tail call optimise */ + b exit_vmx_ops /* tail call optimise */ #endif /* CONFIG_ALTIVEC */ diff --git a/arch/powerpc/lib/strlen_32.S b/arch/powerpc/lib/strlen_32.S new file mode 100644 index 000000000000..0a8d3f64d493 --- /dev/null +++ b/arch/powerpc/lib/strlen_32.S @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * strlen() for PPC32 + * + * Copyright (C) 2018 Christophe Leroy CS Systemes d'Information. + * + * Inspired from glibc implementation + */ +#include <asm/ppc_asm.h> +#include <asm/export.h> +#include <asm/cache.h> + + .text + +/* + * Algorithm: + * + * 1) Given a word 'x', we can test to see if it contains any 0 bytes + * by subtracting 0x01010101, and seeing if any of the high bits of each + * byte changed from 0 to 1. This works because the least significant + * 0 byte must have had no incoming carry (otherwise it's not the least + * significant), so it is 0x00 - 0x01 == 0xff. For all other + * byte values, either they have the high bit set initially, or when + * 1 is subtracted you get a value in the range 0x00-0x7f, none of which + * have their high bit set. The expression here is + * (x - 0x01010101) & ~x & 0x80808080), which gives 0x00000000 when + * there were no 0x00 bytes in the word. You get 0x80 in bytes that + * match, but possibly false 0x80 matches in the next more significant + * byte to a true match due to carries. For little-endian this is + * of no consequence since the least significant match is the one + * we're interested in, but big-endian needs method 2 to find which + * byte matches. + * 2) Given a word 'x', we can test to see _which_ byte was zero by + * calculating ~(((x & ~0x80808080) - 0x80808080 - 1) | x | ~0x80808080). + * This produces 0x80 in each byte that was zero, and 0x00 in all + * the other bytes. The '| ~0x80808080' clears the low 7 bits in each + * byte, and the '| x' part ensures that bytes with the high bit set + * produce 0x00. The addition will carry into the high bit of each byte + * iff that byte had one of its low 7 bits set. We can then just see + * which was the most significant bit set and divide by 8 to find how + * many to add to the index. + * This is from the book 'The PowerPC Compiler Writer's Guide', + * by Steve Hoxey, Faraydon Karim, Bill Hay and Hank Warren. + */ + +_GLOBAL(strlen) + andi. r0, r3, 3 + lis r7, 0x0101 + addi r10, r3, -4 + addic r7, r7, 0x0101 /* r7 = 0x01010101 (lomagic) & clear XER[CA] */ + rotlwi r6, r7, 31 /* r6 = 0x80808080 (himagic) */ + bne- 3f + .balign IFETCH_ALIGN_BYTES +1: lwzu r9, 4(r10) +2: subf r8, r7, r9 + and. r8, r8, r6 + beq+ 1b + andc. r8, r8, r9 + beq+ 1b + andc r8, r9, r6 + orc r9, r9, r6 + subfe r8, r6, r8 + nor r8, r8, r9 + cntlzw r8, r8 + subf r3, r3, r10 + srwi r8, r8, 3 + add r3, r3, r8 + blr + + /* Missaligned string: make sure bytes before string are seen not 0 */ +3: xor r10, r10, r0 + orc r8, r8, r8 + lwzu r9, 4(r10) + slwi r0, r0, 3 + srw r8, r8, r0 + orc r9, r9, r8 + b 2b +EXPORT_SYMBOL(strlen) diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index bf925cdcaca9..9f340494a8ac 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -53,7 +53,7 @@ int exit_vmx_usercopy(void) return 0; } -int enter_vmx_copy(void) +int enter_vmx_ops(void) { if (in_interrupt()) return 0; @@ -70,7 +70,7 @@ int enter_vmx_copy(void) * passed a pointer to the destination which we return as required by a * memcpy implementation. */ -void *exit_vmx_copy(void *dest) +void *exit_vmx_ops(void *dest) { disable_kernel_altivec(); preempt_enable(); diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c index 82b1ff759e26..12d92518e898 100644 --- a/arch/powerpc/mm/44x_mmu.c +++ b/arch/powerpc/mm/44x_mmu.c @@ -229,7 +229,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, } #ifdef CONFIG_SMP -void mmu_init_secondary(int cpu) +void __init mmu_init_secondary(int cpu) { unsigned long addr; unsigned long memstart = memstart_addr & ~(PPC_PIN_SIZE - 1); diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index f06f3577d8d1..cdf6a9960046 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -19,7 +19,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb_low.o slb.o obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(BITS).o -ifeq ($(CONFIG_PPC_BOOK3S_64),y) +ifdef CONFIG_PPC_BOOK3S_64 obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o endif @@ -31,7 +31,7 @@ obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o obj-$(CONFIG_PPC_SPLPAR) += vphn.o obj-$(CONFIG_PPC_MM_SLICES) += slice.o obj-y += hugetlbpage.o -ifeq ($(CONFIG_HUGETLB_PAGE),y) +ifdef CONFIG_HUGETLB_PAGE obj-$(CONFIG_PPC_BOOK3S_64) += hugetlbpage-hash64.o obj-$(CONFIG_PPC_RADIX_MMU) += hugetlbpage-radix.o obj-$(CONFIG_PPC_BOOK3E_MMU) += hugetlbpage-book3e.o diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index 7d0945bd3a61..c8da352e8686 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -34,7 +34,7 @@ * to handle fortunately. */ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, - unsigned long dsisr, unsigned *flt) + unsigned long dsisr, vm_fault_t *flt) { struct vm_area_struct *vma; unsigned long is_write; diff --git a/arch/powerpc/mm/dump_hashpagetable.c b/arch/powerpc/mm/dump_hashpagetable.c index 14cfb11b09d0..869294695048 100644 --- a/arch/powerpc/mm/dump_hashpagetable.c +++ b/arch/powerpc/mm/dump_hashpagetable.c @@ -19,7 +19,6 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/seq_file.h> -#include <asm/fixmap.h> #include <asm/pgtable.h> #include <linux/const.h> #include <asm/page.h> @@ -260,7 +259,7 @@ static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 * /* to check in the secondary hash table, we invert the hash */ if (!primary) hash = ~hash; - hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; /* see if we can find an entry in the hpte with this hash */ for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) { lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index b1ca7a0974e3..d51cf5f4e45e 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -42,7 +42,6 @@ #include <asm/pgtable.h> #include <asm/mmu.h> #include <asm/mmu_context.h> -#include <asm/tlbflush.h> #include <asm/siginfo.h> #include <asm/debug.h> @@ -156,7 +155,7 @@ static noinline int bad_access(struct pt_regs *regs, unsigned long address) } static int do_sigbus(struct pt_regs *regs, unsigned long address, - unsigned int fault) + vm_fault_t fault) { siginfo_t info; unsigned int lsb = 0; @@ -187,7 +186,8 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address, return 0; } -static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) +static int mm_fault_error(struct pt_regs *regs, unsigned long addr, + vm_fault_t fault) { /* * Kernel page fault interrupted by SIGKILL. We have no reason to @@ -415,7 +415,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address, int is_exec = TRAP(regs) == 0x400; int is_user = user_mode(regs); int is_write = page_fault_is_write(error_code); - int fault, major = 0; + vm_fault_t fault, major = 0; bool must_retry = false; if (notify_page_fault(regs)) diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c index d573d7d07f25..6fa6765a10eb 100644 --- a/arch/powerpc/mm/hash64_4k.c +++ b/arch/powerpc/mm/hash64_4k.c @@ -80,7 +80,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, hash = hpt_hash(vpn, shift, ssize); repeat: - hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; /* Insert into the hash table, primary slot */ slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0, @@ -89,7 +89,7 @@ repeat: * Primary is full, try the secondary */ if (unlikely(slot == -1)) { - hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (~hash & htab_hash_mask) * HPTES_PER_GROUP; slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, HPTE_V_SECONDARY, @@ -97,8 +97,8 @@ repeat: MMU_PAGE_4K, ssize); if (slot == -1) { if (mftb() & 0x1) - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * + HPTES_PER_GROUP; mmu_hash_ops.hpte_remove(hpte_group); /* * FIXME!! Should be try the group from which we removed ? diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index e601d95c3b20..3afa253d7f52 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -154,7 +154,7 @@ htab_insert_hpte: } hash = hpt_hash(vpn, shift, ssize); repeat: - hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; /* Insert into the hash table, primary slot */ slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0, @@ -165,7 +165,7 @@ repeat: if (unlikely(slot == -1)) { bool soft_invalid; - hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (~hash & htab_hash_mask) * HPTES_PER_GROUP; slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, HPTE_V_SECONDARY, MMU_PAGE_4K, MMU_PAGE_4K, @@ -193,8 +193,7 @@ repeat: * that we do not get the same soft-invalid slot. */ if (soft_invalid || (mftb() & 0x1)) - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; mmu_hash_ops.hpte_remove(hpte_group); /* @@ -288,7 +287,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, hash = hpt_hash(vpn, shift, ssize); repeat: - hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; /* Insert into the hash table, primary slot */ slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0, @@ -298,7 +297,7 @@ repeat: * Primary is full, try the secondary */ if (unlikely(slot == -1)) { - hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (~hash & htab_hash_mask) * HPTES_PER_GROUP; slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, HPTE_V_SECONDARY, @@ -306,8 +305,8 @@ repeat: MMU_PAGE_64K, ssize); if (slot == -1) { if (mftb() & 0x1) - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * + HPTES_PER_GROUP; mmu_hash_ops.hpte_remove(hpte_group); /* * FIXME!! Should be try the group from which we removed ? diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S index ffbd7c0bda96..26acf6c8c20c 100644 --- a/arch/powerpc/mm/hash_low_32.S +++ b/arch/powerpc/mm/hash_low_32.S @@ -27,6 +27,7 @@ #include <asm/thread_info.h> #include <asm/asm-offsets.h> #include <asm/export.h> +#include <asm/feature-fixups.h> #ifdef CONFIG_SMP .section .bss diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 1d049c78c82a..729f02df8290 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -23,13 +23,13 @@ #include <asm/mmu.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> -#include <asm/tlbflush.h> #include <asm/trace.h> #include <asm/tlb.h> #include <asm/cputable.h> #include <asm/udbg.h> #include <asm/kexec.h> #include <asm/ppc-opcode.h> +#include <asm/feature-fixups.h> #include <misc/cxl-base.h> @@ -423,9 +423,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, DBG_LOW(" update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)", vpn, want_v & HPTE_V_AVPN, slot, newpp); - hpte_v = be64_to_cpu(hptep->v); - if (cpu_has_feature(CPU_FTR_ARCH_300)) - hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r)); + hpte_v = hpte_get_old_v(hptep); /* * We need to invalidate the TLB always because hpte_remove doesn't do * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less @@ -439,9 +437,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, } else { native_lock_hpte(hptep); /* recheck with locks held */ - hpte_v = be64_to_cpu(hptep->v); - if (cpu_has_feature(CPU_FTR_ARCH_300)) - hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r)); + hpte_v = hpte_get_old_v(hptep); if (unlikely(!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))) { ret = -1; @@ -481,11 +477,9 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize) /* Bolted mappings are only ever in the primary group */ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; for (i = 0; i < HPTES_PER_GROUP; i++) { - hptep = htab_address + slot; - hpte_v = be64_to_cpu(hptep->v); - if (cpu_has_feature(CPU_FTR_ARCH_300)) - hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r)); + hptep = htab_address + slot; + hpte_v = hpte_get_old_v(hptep); if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) /* HPTE matches */ return slot; @@ -574,11 +568,19 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, DBG_LOW(" invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot); want_v = hpte_encode_avpn(vpn, bpsize, ssize); - native_lock_hpte(hptep); - hpte_v = be64_to_cpu(hptep->v); - if (cpu_has_feature(CPU_FTR_ARCH_300)) - hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r)); + hpte_v = hpte_get_old_v(hptep); + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { + native_lock_hpte(hptep); + /* recheck with locks held */ + hpte_v = hpte_get_old_v(hptep); + + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) + /* Invalidate the hpte. NOTE: this also unlocks it */ + hptep->v = 0; + else + native_unlock_hpte(hptep); + } /* * We need to invalidate the TLB always because hpte_remove doesn't do * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less @@ -586,13 +588,6 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, * (hpte_remove) because we assume the old translation is still * technically "valid". */ - if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) - native_unlock_hpte(hptep); - else - /* Invalidate the hpte. NOTE: this also unlocks it */ - hptep->v = 0; - - /* Invalidate the TLB */ tlbie(vpn, bpsize, apsize, ssize, local); local_irq_restore(flags); @@ -634,17 +629,23 @@ static void native_hugepage_invalidate(unsigned long vsid, hptep = htab_address + slot; want_v = hpte_encode_avpn(vpn, psize, ssize); - native_lock_hpte(hptep); - hpte_v = be64_to_cpu(hptep->v); - if (cpu_has_feature(CPU_FTR_ARCH_300)) - hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r)); + hpte_v = hpte_get_old_v(hptep); /* Even if we miss, we need to invalidate the TLB */ - if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) - native_unlock_hpte(hptep); - else - /* Invalidate the hpte. NOTE: this also unlocks it */ - hptep->v = 0; + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { + /* recheck with locks held */ + native_lock_hpte(hptep); + hpte_v = hpte_get_old_v(hptep); + + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { + /* + * Invalidate the hpte. NOTE: this also unlocks it + */ + + hptep->v = 0; + } else + native_unlock_hpte(hptep); + } /* * We need to do tlb invalidate for all the address, tlbie * instruction compares entry_VA in tlb with the VA specified @@ -812,16 +813,19 @@ static void native_flush_hash_range(unsigned long number, int local) slot += hidx & _PTEIDX_GROUP_IX; hptep = htab_address + slot; want_v = hpte_encode_avpn(vpn, psize, ssize); + hpte_v = hpte_get_old_v(hptep); + + if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) + continue; + /* lock and try again */ native_lock_hpte(hptep); - hpte_v = be64_to_cpu(hptep->v); - if (cpu_has_feature(CPU_FTR_ARCH_300)) - hpte_v = hpte_new_to_old_v(hpte_v, - be64_to_cpu(hptep->r)); - if (!HPTE_V_COMPARE(hpte_v, want_v) || - !(hpte_v & HPTE_V_VALID)) + hpte_v = hpte_get_old_v(hptep); + + if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) native_unlock_hpte(hptep); else hptep->v = 0; + } pte_iterate_hashed_end(); } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 8318716e5075..f23a89d8e4ce 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -48,7 +48,6 @@ #include <linux/uaccess.h> #include <asm/machdep.h> #include <asm/prom.h> -#include <asm/tlbflush.h> #include <asm/io.h> #include <asm/eeh.h> #include <asm/tlb.h> @@ -808,31 +807,6 @@ int hash__remove_section_mapping(unsigned long start, unsigned long end) } #endif /* CONFIG_MEMORY_HOTPLUG */ -static void update_hid_for_hash(void) -{ - unsigned long hid0; - unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */ - - asm volatile("ptesync": : :"memory"); - /* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */ - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(0), "i"(0), "i"(2), "r"(0) : "memory"); - asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory"); - trace_tlbie(0, 0, rb, 0, 2, 0, 0); - - /* - * now switch the HID - */ - hid0 = mfspr(SPRN_HID0); - hid0 &= ~HID0_POWER9_RADIX; - mtspr(SPRN_HID0, hid0); - asm volatile("isync": : :"memory"); - - /* Wait for it to happen */ - while ((mfspr(SPRN_HID0) & HID0_POWER9_RADIX)) - cpu_relax(); -} - static void __init hash_init_partition_table(phys_addr_t hash_table, unsigned long htab_size) { @@ -845,8 +819,6 @@ static void __init hash_init_partition_table(phys_addr_t hash_table, htab_size = __ilog2(htab_size) - 18; mmu_partition_table_set_entry(0, hash_table | htab_size, 0); pr_info("Partition table %p\n", partition_tb); - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - update_hid_for_hash(); } static void __init htab_initialize(void) @@ -1077,9 +1049,6 @@ void hash__early_init_mmu_secondary(void) /* Initialize hash table for that CPU */ if (!firmware_has_feature(FW_FEATURE_LPAR)) { - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - update_hid_for_hash(); - if (!cpu_has_feature(CPU_FTR_ARCH_300)) mtspr(SPRN_SDR1, _SDR1); else @@ -1783,8 +1752,7 @@ long hpte_insert_repeating(unsigned long hash, unsigned long vpn, long slot; repeat: - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; /* Insert into the hash table, primary slot */ slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, vflags, @@ -1792,15 +1760,14 @@ repeat: /* Primary is full, try the secondary */ if (unlikely(slot == -1)) { - hpte_group = ((~hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (~hash & htab_hash_mask) * HPTES_PER_GROUP; slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, vflags | HPTE_V_SECONDARY, psize, psize, ssize); if (slot == -1) { if (mftb() & 0x1) - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP)&~0x7UL; + hpte_group = (hash & htab_hash_mask) * + HPTES_PER_GROUP; mmu_hash_ops.hpte_remove(hpte_group); goto repeat; diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c index 668e87d03f9e..82a0e37557a5 100644 --- a/arch/powerpc/mm/highmem.c +++ b/arch/powerpc/mm/highmem.c @@ -56,7 +56,7 @@ EXPORT_SYMBOL(kmap_atomic_prot); void __kunmap_atomic(void *kvaddr) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - int type; + int type __maybe_unused; if (vaddr < __fix_to_virt(FIX_KMAP_END)) { pagefault_enable(); diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index f20d16f849c5..01f213d2bcb9 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -128,7 +128,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, new_pmd |= H_PAGE_HASHPTE; repeat: - hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; /* Insert into the hash table, primary slot */ slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0, @@ -137,16 +137,15 @@ repeat: * Primary is full, try the secondary */ if (unlikely(slot == -1)) { - hpte_group = ((~hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (~hash & htab_hash_mask) * HPTES_PER_GROUP; slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, HPTE_V_SECONDARY, psize, lpsize, ssize); if (slot == -1) { if (mftb() & 0x1) - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; + hpte_group = (hash & htab_hash_mask) * + HPTES_PER_GROUP; mmu_hash_ops.hpte_remove(hpte_group); goto repeat; diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 8a9a49c13865..e87f9ef9115b 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -118,15 +118,6 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, } /* - * These macros define how to determine which level of the page table holds - * the hpdp. - */ -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) -#define HUGEPD_PGD_SHIFT PGDIR_SHIFT -#define HUGEPD_PUD_SHIFT PUD_SHIFT -#endif - -/* * At this point we do the placement change only for BOOK3S 64. This would * possibly work on other subarchs. */ @@ -174,13 +165,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz } } #else - if (pshift >= HUGEPD_PGD_SHIFT) { + if (pshift >= PGDIR_SHIFT) { ptl = &mm->page_table_lock; hpdp = (hugepd_t *)pg; } else { pdshift = PUD_SHIFT; pu = pud_alloc(mm, pg, addr); - if (pshift >= HUGEPD_PUD_SHIFT) { + if (pshift >= PUD_SHIFT) { ptl = pud_lockptr(mm, pu); hpdp = (hugepd_t *)pu; } else { @@ -621,15 +612,12 @@ static int __init add_huge_page_size(unsigned long long size) * firmware we only add hugetlb support for page sizes that can be * supported by linux page table layout. * For now we have - * Radix: 2M + * Radix: 2M and 1G * Hash: 16M and 16G */ if (radix_enabled()) { - if (mmu_psize != MMU_PAGE_2M) { - if (cpu_has_feature(CPU_FTR_POWER9_DD1) || - (mmu_psize != MMU_PAGE_1G)) - return -EINVAL; - } + if (mmu_psize != MMU_PAGE_2M && mmu_psize != MMU_PAGE_1G) + return -EINVAL; } else { if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G) return -EINVAL; @@ -695,9 +683,9 @@ static int __init hugetlbpage_init(void) else pdshift = PMD_SHIFT; #else - if (shift < HUGEPD_PUD_SHIFT) + if (shift < PUD_SHIFT) pdshift = PMD_SHIFT; - else if (shift < HUGEPD_PGD_SHIFT) + else if (shift < PGDIR_SHIFT) pdshift = PUD_SHIFT; else pdshift = PGDIR_SHIFT; diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index f3d4b4a0e561..4a892d894a0f 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -200,9 +200,9 @@ static void pte_frag_destroy(void *pte_frag) /* drop all the pending references */ count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) { + if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { pgtable_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -215,13 +215,13 @@ static void pmd_frag_destroy(void *pmd_frag) /* drop all the pending references */ count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (page_ref_sub_and_test(page, PMD_FRAG_NR - count)) { + if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); - free_unref_page(page); + __free_page(page); } } -static void destroy_pagetable_page(struct mm_struct *mm) +static void destroy_pagetable_cache(struct mm_struct *mm) { void *frag; @@ -244,13 +244,14 @@ void destroy_context(struct mm_struct *mm) WARN_ON(process_tb[mm->context.id].prtb0 != 0); else subpage_prot_free(mm); - destroy_pagetable_page(mm); destroy_contexts(&mm->context); mm->context.id = MMU_NO_CONTEXT; } void arch_exit_mmap(struct mm_struct *mm) { + destroy_pagetable_cache(mm); + if (radix_enabled()) { /* * Radix doesn't have a valid bit in the process table @@ -273,15 +274,7 @@ void arch_exit_mmap(struct mm_struct *mm) #ifdef CONFIG_PPC_RADIX_MMU void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) { - - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { - isync(); - mtspr(SPRN_PID, next->context.id); - isync(); - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); - } else { - mtspr(SPRN_PID, next->context.id); - isync(); - } + mtspr(SPRN_PID, next->context.id); + isync(); } #endif diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c index aa5a7fd89461..921c1e33e941 100644 --- a/arch/powerpc/mm/mmu_context_hash32.c +++ b/arch/powerpc/mm/mmu_context_hash32.c @@ -27,7 +27,6 @@ #include <linux/export.h> #include <asm/mmu_context.h> -#include <asm/tlbflush.h> /* * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index c4c0a09a7775..e5d779eed181 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -19,7 +19,6 @@ * */ #include <linux/mm.h> -#include <asm/tlbflush.h> #include <asm/mmu.h> #ifdef CONFIG_PPC_MMU_NOHASH diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 4afbfbb64bfd..01d7c0f7c4f0 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -270,6 +270,8 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) return NULL; } + atomic_set(&page->pt_frag_refcount, 1); + ret = page_address(page); /* * if we support only one fragment just return the @@ -285,7 +287,7 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) * count. */ if (likely(!mm->context.pmd_frag)) { - set_page_count(page, PMD_FRAG_NR); + atomic_set(&page->pt_frag_refcount, PMD_FRAG_NR); mm->context.pmd_frag = ret + PMD_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -308,9 +310,10 @@ void pmd_fragment_free(unsigned long *pmd) { struct page *page = virt_to_page(pmd); - if (put_page_testzero(page)) { + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -352,6 +355,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) return NULL; } + atomic_set(&page->pt_frag_refcount, 1); ret = page_address(page); /* @@ -367,7 +371,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) * count. */ if (likely(!mm->context.pte_frag)) { - set_page_count(page, PTE_FRAG_NR); + atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); mm->context.pte_frag = ret + PTE_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -390,10 +394,11 @@ void pte_fragment_free(unsigned long *table, int kernel) { struct page *page = virt_to_page(table); - if (put_page_testzero(page)) { + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { if (!kernel) pgtable_page_dtor(page); - free_unref_page(page); + __free_page(page); } } @@ -450,3 +455,25 @@ void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index) return pgtable_free(table, index); } #endif + +#ifdef CONFIG_PROC_FS +atomic_long_t direct_pages_count[MMU_PAGE_COUNT]; + +void arch_report_meminfo(struct seq_file *m) +{ + /* + * Hash maps the memory with one size mmu_linear_psize. + * So don't bother to print these on hash + */ + if (!radix_enabled()) + return; + seq_printf(m, "DirectMap4k: %8lu kB\n", + atomic_long_read(&direct_pages_count[MMU_PAGE_4K]) << 2); + seq_printf(m, "DirectMap64k: %8lu kB\n", + atomic_long_read(&direct_pages_count[MMU_PAGE_64K]) << 6); + seq_printf(m, "DirectMap2M: %8lu kB\n", + atomic_long_read(&direct_pages_count[MMU_PAGE_2M]) << 11); + seq_printf(m, "DirectMap1G: %8lu kB\n", + atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20); +} +#endif /* CONFIG_PROC_FS */ diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 96f68c5aa1f5..7be99fd9af15 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -226,16 +226,6 @@ void radix__mark_rodata_ro(void) { unsigned long start, end; - /* - * mark_rodata_ro() will mark itself as !writable at some point. - * Due to DD1 workaround in radix__pte_update(), we'll end up with - * an invalid pte and the system will crash quite severly. - */ - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { - pr_warn("Warning: Unable to mark rodata read only on P9 DD1\n"); - return; - } - start = (unsigned long)_stext; end = (unsigned long)__init_begin; @@ -277,6 +267,7 @@ static int __meminit create_physical_mapping(unsigned long start, #else int split_text_mapping = 0; #endif + int psize; start = _ALIGN_UP(start, PAGE_SIZE); for (addr = start; addr < end; addr += mapping_size) { @@ -290,13 +281,17 @@ static int __meminit create_physical_mapping(unsigned long start, retry: if (IS_ALIGNED(addr, PUD_SIZE) && gap >= PUD_SIZE && mmu_psize_defs[MMU_PAGE_1G].shift && - PUD_SIZE <= max_mapping_size) + PUD_SIZE <= max_mapping_size) { mapping_size = PUD_SIZE; - else if (IS_ALIGNED(addr, PMD_SIZE) && gap >= PMD_SIZE && - mmu_psize_defs[MMU_PAGE_2M].shift) + psize = MMU_PAGE_1G; + } else if (IS_ALIGNED(addr, PMD_SIZE) && gap >= PMD_SIZE && + mmu_psize_defs[MMU_PAGE_2M].shift) { mapping_size = PMD_SIZE; - else + psize = MMU_PAGE_2M; + } else { mapping_size = PAGE_SIZE; + psize = mmu_virtual_psize; + } if (split_text_mapping && (mapping_size == PUD_SIZE) && (addr <= __pa_symbol(__init_begin)) && @@ -307,8 +302,10 @@ retry: if (split_text_mapping && (mapping_size == PMD_SIZE) && (addr <= __pa_symbol(__init_begin)) && - (addr + mapping_size) >= __pa_symbol(_stext)) + (addr + mapping_size) >= __pa_symbol(_stext)) { mapping_size = PAGE_SIZE; + psize = mmu_virtual_psize; + } if (mapping_size != previous_size) { print_mapping(start, addr, previous_size); @@ -326,6 +323,8 @@ retry: rc = __map_kernel_page(vaddr, addr, prot, mapping_size, nid, start, end); if (rc) return rc; + + update_page_count(psize, 1); } print_mapping(start, addr, mapping_size); @@ -533,35 +532,6 @@ found: return; } -static void update_hid_for_radix(void) -{ - unsigned long hid0; - unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */ - - asm volatile("ptesync": : :"memory"); - /* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */ - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(1), "i"(0), "i"(2), "r"(0) : "memory"); - /* prs = 1, ric = 2, rs = 0, r = 1 is = 3 */ - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(1), "i"(1), "i"(2), "r"(0) : "memory"); - asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory"); - trace_tlbie(0, 0, rb, 0, 2, 0, 1); - trace_tlbie(0, 0, rb, 0, 2, 1, 1); - - /* - * now switch the HID - */ - hid0 = mfspr(SPRN_HID0); - hid0 |= HID0_POWER9_RADIX; - mtspr(SPRN_HID0, hid0); - asm volatile("isync": : :"memory"); - - /* Wait for it to happen */ - while (!(mfspr(SPRN_HID0) & HID0_POWER9_RADIX)) - cpu_relax(); -} - static void radix_init_amor(void) { /* @@ -576,22 +546,12 @@ static void radix_init_amor(void) static void radix_init_iamr(void) { - unsigned long iamr; - - /* - * The IAMR should set to 0 on DD1. - */ - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - iamr = 0; - else - iamr = (1ul << 62); - /* * Radix always uses key0 of the IAMR to determine if an access is * allowed. We set bit 0 (IBM bit 1) of key0, to prevent instruction * fetch. */ - mtspr(SPRN_IAMR, iamr); + mtspr(SPRN_IAMR, (1ul << 62)); } void __init radix__early_init_mmu(void) @@ -644,8 +604,6 @@ void __init radix__early_init_mmu(void) if (!firmware_has_feature(FW_FEATURE_LPAR)) { radix_init_native(); - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - update_hid_for_radix(); lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); @@ -671,10 +629,6 @@ void radix__early_init_mmu_secondary(void) * update partition table control register and UPRT */ if (!firmware_has_feature(FW_FEATURE_LPAR)) { - - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - update_hid_for_radix(); - lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); @@ -1095,8 +1049,7 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, * To avoid NMMU hang while relaxing access, we need mark * the pte invalid in between. */ - if (cpu_has_feature(CPU_FTR_POWER9_DD1) || - atomic_read(&mm->context.copros) > 0) { + if (atomic_read(&mm->context.copros) > 0) { unsigned long old_pte, new_pte; old_pte = __radix_pte_update(ptep, ~0, 0); diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c index e6f500fabf5e..333b1f80c435 100644 --- a/arch/powerpc/mm/pkeys.c +++ b/arch/powerpc/mm/pkeys.c @@ -14,9 +14,12 @@ DEFINE_STATIC_KEY_TRUE(pkey_disabled); bool pkey_execute_disable_supported; int pkeys_total; /* Total pkeys as per device tree */ bool pkeys_devtree_defined; /* pkey property exported by device tree */ -u32 initial_allocation_mask; /* Bits set for reserved keys */ -u64 pkey_amr_uamor_mask; /* Bits in AMR/UMOR not to be touched */ +u32 initial_allocation_mask; /* Bits set for the initially allocated keys */ +u32 reserved_allocation_mask; /* Bits set for reserved keys */ +u64 pkey_amr_mask; /* Bits in AMR not to be touched */ u64 pkey_iamr_mask; /* Bits in AMR not to be touched */ +u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */ +int execute_only_key = 2; #define AMR_BITS_PER_PKEY 2 #define AMR_RD_BIT 0x1UL @@ -91,7 +94,7 @@ int pkey_initialize(void) * arch-neutral code. */ pkeys_total = min_t(int, pkeys_total, - (ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT)); + ((ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT)+1)); if (!pkey_mmu_enabled() || radix_enabled() || !pkeys_total) static_branch_enable(&pkey_disabled); @@ -119,20 +122,39 @@ int pkey_initialize(void) #else os_reserved = 0; #endif - initial_allocation_mask = ~0x0; - pkey_amr_uamor_mask = ~0x0ul; + /* Bits are in LE format. */ + reserved_allocation_mask = (0x1 << 1) | (0x1 << execute_only_key); + + /* register mask is in BE format */ + pkey_amr_mask = ~0x0ul; + pkey_amr_mask &= ~(0x3ul << pkeyshift(0)); + pkey_iamr_mask = ~0x0ul; - /* - * key 0, 1 are reserved. - * key 0 is the default key, which allows read/write/execute. - * key 1 is recommended not to be used. PowerISA(3.0) page 1015, - * programming note. - */ - for (i = 2; i < (pkeys_total - os_reserved); i++) { - initial_allocation_mask &= ~(0x1 << i); - pkey_amr_uamor_mask &= ~(0x3ul << pkeyshift(i)); - pkey_iamr_mask &= ~(0x1ul << pkeyshift(i)); + pkey_iamr_mask &= ~(0x3ul << pkeyshift(0)); + pkey_iamr_mask &= ~(0x3ul << pkeyshift(execute_only_key)); + + pkey_uamor_mask = ~0x0ul; + pkey_uamor_mask &= ~(0x3ul << pkeyshift(0)); + pkey_uamor_mask &= ~(0x3ul << pkeyshift(execute_only_key)); + + /* mark the rest of the keys as reserved and hence unavailable */ + for (i = (pkeys_total - os_reserved); i < pkeys_total; i++) { + reserved_allocation_mask |= (0x1 << i); + pkey_uamor_mask &= ~(0x3ul << pkeyshift(i)); + } + initial_allocation_mask = reserved_allocation_mask | (0x1 << 0); + + if (unlikely((pkeys_total - os_reserved) <= execute_only_key)) { + /* + * Insufficient number of keys to support + * execute only key. Mark it unavailable. + * Any AMR, UAMOR, IAMR bit set for + * this key is irrelevant since this key + * can never be allocated. + */ + execute_only_key = -1; } + return 0; } @@ -143,8 +165,7 @@ void pkey_mm_init(struct mm_struct *mm) if (static_branch_likely(&pkey_disabled)) return; mm_pkey_allocation_map(mm) = initial_allocation_mask; - /* -1 means unallocated or invalid */ - mm->context.execute_only_pkey = -1; + mm->context.execute_only_pkey = execute_only_key; } static inline u64 read_amr(void) @@ -213,33 +234,6 @@ static inline void init_iamr(int pkey, u8 init_bits) write_iamr(old_iamr | new_iamr_bits); } -static void pkey_status_change(int pkey, bool enable) -{ - u64 old_uamor; - - /* Reset the AMR and IAMR bits for this key */ - init_amr(pkey, 0x0); - init_iamr(pkey, 0x0); - - /* Enable/disable key */ - old_uamor = read_uamor(); - if (enable) - old_uamor |= (0x3ul << pkeyshift(pkey)); - else - old_uamor &= ~(0x3ul << pkeyshift(pkey)); - write_uamor(old_uamor); -} - -void __arch_activate_pkey(int pkey) -{ - pkey_status_change(pkey, true); -} - -void __arch_deactivate_pkey(int pkey) -{ - pkey_status_change(pkey, false); -} - /* * Set the access rights in AMR IAMR and UAMOR registers for @pkey to that * specified in @init_val. @@ -289,9 +283,6 @@ void thread_pkey_regs_restore(struct thread_struct *new_thread, if (static_branch_likely(&pkey_disabled)) return; - /* - * TODO: Just set UAMOR to zero if @new_thread hasn't used any keys yet. - */ if (old_thread->amr != new_thread->amr) write_amr(new_thread->amr); if (old_thread->iamr != new_thread->iamr) @@ -305,9 +296,13 @@ void thread_pkey_regs_init(struct thread_struct *thread) if (static_branch_likely(&pkey_disabled)) return; - thread->amr = read_amr() & pkey_amr_uamor_mask; - thread->iamr = read_iamr() & pkey_iamr_mask; - thread->uamor = read_uamor() & pkey_amr_uamor_mask; + thread->amr = pkey_amr_mask; + thread->iamr = pkey_iamr_mask; + thread->uamor = pkey_uamor_mask; + + write_uamor(pkey_uamor_mask); + write_amr(pkey_amr_mask); + write_iamr(pkey_iamr_mask); } static inline bool pkey_allows_readwrite(int pkey) @@ -322,48 +317,7 @@ static inline bool pkey_allows_readwrite(int pkey) int __execute_only_pkey(struct mm_struct *mm) { - bool need_to_set_mm_pkey = false; - int execute_only_pkey = mm->context.execute_only_pkey; - int ret; - - /* Do we need to assign a pkey for mm's execute-only maps? */ - if (execute_only_pkey == -1) { - /* Go allocate one to use, which might fail */ - execute_only_pkey = mm_pkey_alloc(mm); - if (execute_only_pkey < 0) - return -1; - need_to_set_mm_pkey = true; - } - - /* - * We do not want to go through the relatively costly dance to set AMR - * if we do not need to. Check it first and assume that if the - * execute-only pkey is readwrite-disabled than we do not have to set it - * ourselves. - */ - if (!need_to_set_mm_pkey && !pkey_allows_readwrite(execute_only_pkey)) - return execute_only_pkey; - - /* - * Set up AMR so that it denies access for everything other than - * execution. - */ - ret = __arch_set_user_pkey_access(current, execute_only_pkey, - PKEY_DISABLE_ACCESS | - PKEY_DISABLE_WRITE); - /* - * If the AMR-set operation failed somehow, just return 0 and - * effectively disable execute-only support. - */ - if (ret) { - mm_pkey_free(mm, execute_only_pkey); - return -1; - } - - /* We got one, store it and use it from here on out */ - if (need_to_set_mm_pkey) - mm->context.execute_only_pkey = execute_only_pkey; - return execute_only_pkey; + return mm->context.execute_only_pkey; } static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma) @@ -407,9 +361,6 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute) int pkey_shift; u64 amr; - if (!pkey) - return true; - if (!is_pkey_enabled(pkey)) return true; diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index cb796724a6fc..0b095fa54049 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -90,6 +90,45 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize, : "memory" ); } +/* + * Insert bolted entries into SLB (which may not be empty, so don't clear + * slb_cache_ptr). + */ +void __slb_restore_bolted_realmode(void) +{ + struct slb_shadow *p = get_slb_shadow(); + enum slb_index index; + + /* No isync needed because realmode. */ + for (index = 0; index < SLB_NUM_BOLTED; index++) { + asm volatile("slbmte %0,%1" : + : "r" (be64_to_cpu(p->save_area[index].vsid)), + "r" (be64_to_cpu(p->save_area[index].esid))); + } +} + +/* + * Insert the bolted entries into an empty SLB. + * This is not the same as rebolt because the bolted segments are not + * changed, just loaded from the shadow area. + */ +void slb_restore_bolted_realmode(void) +{ + __slb_restore_bolted_realmode(); + get_paca()->slb_cache_ptr = 0; +} + +/* + * This flushes all SLB entries including 0, so it must be realmode. + */ +void slb_flush_all_realmode(void) +{ + /* + * This flushes all SLB entries including 0, so it must be realmode. + */ + asm volatile("slbmte %0,%0; slbia" : : "r" (0)); +} + static void __slb_flush_and_rebolt(void) { /* If you change this make sure you change SLB_NUM_BOLTED diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index a83fbd2a4a24..4ac5057ad439 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -22,6 +22,7 @@ #include <asm/mmu.h> #include <asm/pgtable.h> #include <asm/firmware.h> +#include <asm/feature-fixups.h> /* * This macro generates asm code to compute the VSID scramble diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index 9d16ee251fc0..3327551c8b47 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -17,7 +17,6 @@ #include <asm/pgtable.h> #include <linux/uaccess.h> -#include <asm/tlbflush.h> /* * Free all pages allocated for subpage protection maps and pointers. diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 1135b43a597c..fef3e1eb3a19 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -1048,24 +1048,6 @@ void radix__flush_tlb_all(void) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm, - unsigned long address) -{ - /* - * We track page size in pte only for DD1, So we can - * call this only on DD1. - */ - if (!cpu_has_feature(CPU_FTR_POWER9_DD1)) { - VM_WARN_ON(1); - return; - } - - if (old_pte & R_PAGE_LARGE) - radix__flush_tlb_page_psize(mm, address, MMU_PAGE_2M); - else - radix__flush_tlb_page_psize(mm, address, mmu_virtual_psize); -} - #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) { diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index eb82d787d99a..7fd20c52a8ec 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -22,6 +22,7 @@ #include <asm/ppc-opcode.h> #include <asm/kvm_asm.h> #include <asm/kvm_booke_hv_asm.h> +#include <asm/feature-fixups.h> #ifdef CONFIG_PPC_64K_PAGES #define VPTE_PMD_SHIFT (PTE_INDEX_SIZE+1) diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index 048b8e9f4492..e066a658acac 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -34,6 +34,8 @@ #include <asm/asm-offsets.h> #include <asm/processor.h> #include <asm/bug.h> +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> #if defined(CONFIG_40x) diff --git a/arch/powerpc/net/Makefile b/arch/powerpc/net/Makefile index 809f019d3cba..c2dec3a68d4c 100644 --- a/arch/powerpc/net/Makefile +++ b/arch/powerpc/net/Makefile @@ -2,7 +2,7 @@ # # Arch-specific network modules # -ifeq ($(CONFIG_PPC64),y) +ifdef CONFIG_PPC64 obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o else obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h index a8cd7e289ecd..6f4daacad296 100644 --- a/arch/powerpc/net/bpf_jit32.h +++ b/arch/powerpc/net/bpf_jit32.h @@ -13,6 +13,7 @@ #ifndef _BPF_JIT32_H #define _BPF_JIT32_H +#include <asm/asm-compat.h> #include "bpf_jit.h" #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/net/bpf_jit_asm.S b/arch/powerpc/net/bpf_jit_asm.S index 3dd9c43d40c9..c80280dc2e04 100644 --- a/arch/powerpc/net/bpf_jit_asm.S +++ b/arch/powerpc/net/bpf_jit_asm.S @@ -10,6 +10,7 @@ */ #include <asm/ppc_asm.h> +#include <asm/asm-compat.h> #include "bpf_jit32.h" /* diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 5b061fc81df3..d5bfe24bb3b5 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -12,6 +12,7 @@ */ #include <linux/moduleloader.h> #include <asm/cacheflush.h> +#include <asm/asm-compat.h> #include <linux/netdevice.h> #include <linux/filter.h> #include <linux/if_vlan.h> diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 380cbf9a40d9..50b129785aee 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -13,6 +13,7 @@ */ #include <linux/moduleloader.h> #include <asm/cacheflush.h> +#include <asm/asm-compat.h> #include <linux/netdevice.h> #include <linux/filter.h> #include <linux/if_vlan.h> @@ -286,6 +287,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u64 imm64; u8 *func; u32 true_cond; + u32 tmp_idx; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -637,11 +639,7 @@ emit_clear: case BPF_STX | BPF_XADD | BPF_W: /* Get EA into TMP_REG_1 */ PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not word-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); + tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); /* add value from src_reg into this */ @@ -649,32 +647,16 @@ emit_clear: /* store result back */ PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); /* we're done if this succeeded */ - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); - /* otherwise, let's try once more */ - PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - /* exit if the store was not successful */ - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not doubleword-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4)); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); - PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); + tmp_idx = ctx->idx * 4; PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 3f66fcf8ad99..81f8a0c838ae 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -128,10 +128,6 @@ static inline void power_pmu_bhrb_disable(struct perf_event *event) {} static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {} static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {} static void pmao_restore_workaround(bool ebb) { } -static bool use_ic(u64 event) -{ - return false; -} #endif /* CONFIG_PPC32 */ static bool regs_use_siar(struct pt_regs *regs) @@ -714,14 +710,6 @@ static void pmao_restore_workaround(bool ebb) mtspr(SPRN_PMC6, pmcs[5]); } -static bool use_ic(u64 event) -{ - if (cpu_has_feature(CPU_FTR_POWER9_DD1) && - (event == 0x200f2 || event == 0x300f2)) - return true; - - return false; -} #endif /* CONFIG_PPC64 */ static void perf_event_interrupt(struct pt_regs *regs); @@ -1046,7 +1034,6 @@ static u64 check_and_compute_delta(u64 prev, u64 val) static void power_pmu_read(struct perf_event *event) { s64 val, delta, prev; - struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); if (event->hw.state & PERF_HES_STOPPED) return; @@ -1056,13 +1043,6 @@ static void power_pmu_read(struct perf_event *event) if (is_ebb_event(event)) { val = read_pmc(event->hw.idx); - if (use_ic(event->attr.config)) { - val = mfspr(SPRN_IC); - if (val > cpuhw->ic_init) - val = val - cpuhw->ic_init; - else - val = val + (0 - cpuhw->ic_init); - } local64_set(&event->hw.prev_count, val); return; } @@ -1076,13 +1056,6 @@ static void power_pmu_read(struct perf_event *event) prev = local64_read(&event->hw.prev_count); barrier(); val = read_pmc(event->hw.idx); - if (use_ic(event->attr.config)) { - val = mfspr(SPRN_IC); - if (val > cpuhw->ic_init) - val = val - cpuhw->ic_init; - else - val = val + (0 - cpuhw->ic_init); - } delta = check_and_compute_delta(prev, val); if (!delta) return; @@ -1469,7 +1442,7 @@ static int collect_events(struct perf_event *group, int max_count, } /* - * Add a event to the PMU. + * Add an event to the PMU. * If all events are not already frozen, then we disable and * re-enable the PMU in order to get hw_perf_enable to do the * actual work of reconfiguring the PMU. @@ -1535,20 +1508,13 @@ nocheck: event->attr.branch_sample_type); } - /* - * Workaround for POWER9 DD1 to use the Instruction Counter - * register value for instruction counting - */ - if (use_ic(event->attr.config)) - cpuhw->ic_init = mfspr(SPRN_IC); - perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; } /* - * Remove a event from the PMU. + * Remove an event from the PMU. */ static void power_pmu_del(struct perf_event *event, int ef_flags) { @@ -1742,7 +1708,7 @@ static int power_pmu_commit_txn(struct pmu *pmu) /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. - * A event can only go on a limited PMC if it counts something + * An event can only go on a limited PMC if it counts something * that a limited PMC can count, doesn't require interrupts, and * doesn't exclude any processor mode. */ diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index d1977b61f827..1fafc32b12a0 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -867,59 +867,6 @@ static int thread_imc_cpu_init(void) ppc_thread_imc_cpu_offline); } -void thread_imc_pmu_sched_task(struct perf_event_context *ctx, - bool sched_in) -{ - int core_id; - struct imc_pmu_ref *ref; - - if (!is_core_imc_mem_inited(smp_processor_id())) - return; - - core_id = smp_processor_id() / threads_per_core; - /* - * imc pmus are enabled only when it is used. - * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the counters. - * If not, just increment the count in ref count struct. - */ - ref = &core_imc_refc[core_id]; - if (!ref) - return; - - if (sched_in) { - mutex_lock(&ref->lock); - if (ref->refc == 0) { - if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, - get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); - pr_err("thread-imc: Unable to start the counter\ - for core %d\n", core_id); - return; - } - } - ++ref->refc; - mutex_unlock(&ref->lock); - } else { - mutex_lock(&ref->lock); - ref->refc--; - if (ref->refc == 0) { - if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, - get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); - pr_err("thread-imc: Unable to stop the counters\ - for core %d\n", core_id); - return; - } - } else if (ref->refc < 0) { - ref->refc = 0; - } - mutex_unlock(&ref->lock); - } - - return; -} - static int thread_imc_event_init(struct perf_event *event) { u32 config = event->attr.config; @@ -1046,22 +993,70 @@ static int imc_event_add(struct perf_event *event, int flags) static int thread_imc_event_add(struct perf_event *event, int flags) { + int core_id; + struct imc_pmu_ref *ref; + if (flags & PERF_EF_START) imc_event_start(event, flags); - /* Enable the sched_task to start the engine */ - perf_sched_cb_inc(event->ctx->pmu); + if (!is_core_imc_mem_inited(smp_processor_id())) + return -EINVAL; + + core_id = smp_processor_id() / threads_per_core; + /* + * imc pmus are enabled only when it is used. + * See if this is triggered for the first time. + * If yes, take the mutex lock and enable the counters. + * If not, just increment the count in ref count struct. + */ + ref = &core_imc_refc[core_id]; + if (!ref) + return -EINVAL; + + mutex_lock(&ref->lock); + if (ref->refc == 0) { + if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, + get_hard_smp_processor_id(smp_processor_id()))) { + mutex_unlock(&ref->lock); + pr_err("thread-imc: Unable to start the counter\ + for core %d\n", core_id); + return -EINVAL; + } + } + ++ref->refc; + mutex_unlock(&ref->lock); return 0; } static void thread_imc_event_del(struct perf_event *event, int flags) { + + int core_id; + struct imc_pmu_ref *ref; + /* * Take a snapshot and calculate the delta and update * the event counter values. */ imc_event_update(event); - perf_sched_cb_dec(event->ctx->pmu); + + core_id = smp_processor_id() / threads_per_core; + ref = &core_imc_refc[core_id]; + + mutex_lock(&ref->lock); + ref->refc--; + if (ref->refc == 0) { + if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, + get_hard_smp_processor_id(smp_processor_id()))) { + mutex_unlock(&ref->lock); + pr_err("thread-imc: Unable to stop the counters\ + for core %d\n", core_id); + return; + } + } else if (ref->refc < 0) { + ref->refc = 0; + } + mutex_unlock(&ref->lock); } /* update_pmu_ops : Populate the appropriate operations for "pmu" */ @@ -1087,7 +1082,6 @@ static int update_pmu_ops(struct imc_pmu *pmu) break; case IMC_DOMAIN_THREAD: pmu->pmu.event_init = thread_imc_event_init; - pmu->pmu.sched_task = thread_imc_pmu_sched_task; pmu->pmu.add = thread_imc_event_add; pmu->pmu.del = thread_imc_event_del; pmu->pmu.start_txn = thread_imc_pmu_start_txn; diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 2efee3f196f5..177de814286f 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -59,7 +59,7 @@ static bool is_event_valid(u64 event) { u64 valid_mask = EVENT_VALID_MASK; - if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) valid_mask = p9_EVENT_VALID_MASK; return !(event & ~valid_mask); @@ -86,8 +86,6 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) * Incase of Power9: * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'), * or if group already have any marked events. - * Non-Marked events (for DD1): - * MMCRA[SDAR_MODE] will be set to 0b01 * For rest * MMCRA[SDAR_MODE] will be set from event code. * If sdar_mode from event is zero, default to 0b01. Hardware @@ -96,7 +94,7 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) if (cpu_has_feature(CPU_FTR_ARCH_300)) { if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE)) *mmcra &= MMCRA_SDAR_MODE_NO_UPDATES; - else if (!cpu_has_feature(CPU_FTR_POWER9_DD1) && p9_SDAR_MODE(event)) + else if (p9_SDAR_MODE(event)) *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT; else *mmcra |= MMCRA_SDAR_MODE_DCACHE; @@ -106,7 +104,7 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) static u64 thresh_cmp_val(u64 value) { - if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) return value << p9_MMCRA_THR_CMP_SHIFT; return value << MMCRA_THR_CMP_SHIFT; @@ -114,7 +112,7 @@ static u64 thresh_cmp_val(u64 value) static unsigned long combine_from_event(u64 event) { - if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) return p9_EVENT_COMBINE(event); return EVENT_COMBINE(event); @@ -122,7 +120,7 @@ static unsigned long combine_from_event(u64 event) static unsigned long combine_shift(unsigned long pmc) { - if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) return p9_MMCR1_COMBINE_SHIFT(pmc); return MMCR1_COMBINE_SHIFT(pmc); diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 6a0b586c935a..0028f4b9490d 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -158,11 +158,6 @@ CNST_PMC_VAL(1) | CNST_PMC_VAL(2) | CNST_PMC_VAL(3) | \ CNST_PMC_VAL(4) | CNST_PMC_VAL(5) | CNST_PMC_VAL(6) | CNST_NC_VAL -/* - * Lets restrict use of PMC5 for instruction counting. - */ -#define P9_DD1_TEST_ADDER (ISA207_TEST_ADDER | CNST_PMC_VAL(5)) - /* Bits in MMCR1 for PowerISA v2.07 */ #define MMCR1_UNIT_SHIFT(pmc) (60 - (4 * ((pmc) - 1))) #define MMCR1_COMBINE_SHIFT(pmc) (35 - ((pmc) - 1)) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 2ca0b33b4efb..e012b1030a5b 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -219,12 +219,6 @@ static struct attribute_group power9_pmu_events_group = { .attrs = power9_events_attr, }; -static const struct attribute_group *power9_isa207_pmu_attr_groups[] = { - &isa207_pmu_format_group, - &power9_pmu_events_group, - NULL, -}; - PMU_FORMAT_ATTR(event, "config:0-51"); PMU_FORMAT_ATTR(pmcxsel, "config:0-7"); PMU_FORMAT_ATTR(mark, "config:8"); @@ -267,17 +261,6 @@ static const struct attribute_group *power9_pmu_attr_groups[] = { NULL, }; -static int power9_generic_events_dd1[] = { - [PERF_COUNT_HW_CPU_CYCLES] = PM_CYC, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PM_ICT_NOSLOT_CYC, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = PM_CMPLU_STALL, - [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_DISP, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL_ALT, - [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, - [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, - [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1_FIN, -}; - static int power9_generic_events[] = { [PERF_COUNT_HW_CPU_CYCLES] = PM_CYC, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PM_ICT_NOSLOT_CYC, @@ -439,25 +422,6 @@ static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { #undef C -static struct power_pmu power9_isa207_pmu = { - .name = "POWER9", - .n_counter = MAX_PMU_COUNTERS, - .add_fields = ISA207_ADD_FIELDS, - .test_adder = P9_DD1_TEST_ADDER, - .compute_mmcr = isa207_compute_mmcr, - .config_bhrb = power9_config_bhrb, - .bhrb_filter_map = power9_bhrb_filter_map, - .get_constraint = isa207_get_constraint, - .get_alternatives = power9_get_alternatives, - .disable_pmc = isa207_disable_pmc, - .flags = PPMU_NO_SIAR | PPMU_ARCH_207S, - .n_generic = ARRAY_SIZE(power9_generic_events_dd1), - .generic_events = power9_generic_events_dd1, - .cache_events = &power9_cache_events, - .attr_groups = power9_isa207_pmu_attr_groups, - .bhrb_nr = 32, -}; - static struct power_pmu power9_pmu = { .name = "POWER9", .n_counter = MAX_PMU_COUNTERS, @@ -500,23 +464,7 @@ static int __init init_power9_pmu(void) } } - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { - /* - * Since PM_INST_CMPL may not provide right counts in all - * sampling scenarios in power9 DD1, instead use PM_INST_DISP. - */ - EVENT_VAR(PM_INST_CMPL, _g).id = PM_INST_DISP; - /* - * Power9 DD1 should use PM_BR_CMPL_ALT event code for - * "branches" to provide correct counter value. - */ - EVENT_VAR(PM_BR_CMPL, _g).id = PM_BR_CMPL_ALT; - EVENT_VAR(PM_BR_CMPL, _c).id = PM_BR_CMPL_ALT; - rc = register_power_pmu(&power9_isa207_pmu); - } else { - rc = register_power_pmu(&power9_pmu); - } - + rc = register_power_pmu(&power9_pmu); if (rc) return rc; diff --git a/arch/powerpc/perf/req-gen/_begin.h b/arch/powerpc/perf/req-gen/_begin.h index 549f8782c52d..a200b86eba3b 100644 --- a/arch/powerpc/perf/req-gen/_begin.h +++ b/arch/powerpc/perf/req-gen/_begin.h @@ -3,6 +3,8 @@ #ifndef POWERPC_PERF_REQ_GEN_H_ #define POWERPC_PERF_REQ_GEN_H_ +#include <linux/stringify.h> + #define CAT2_STR_(t, s) __stringify(t/s) #define CAT2_STR(t, s) CAT2_STR_(t, s) #define I(...) __VA_ARGS__ diff --git a/arch/powerpc/perf/req-gen/perf.h b/arch/powerpc/perf/req-gen/perf.h index 871a9a1766c2..fa9bc804e67a 100644 --- a/arch/powerpc/perf/req-gen/perf.h +++ b/arch/powerpc/perf/req-gen/perf.h @@ -3,6 +3,7 @@ #define LINUX_POWERPC_PERF_REQ_GEN_PERF_H_ #include <linux/perf_event.h> +#include <linux/stringify.h> #ifndef REQUEST_FILE #error "REQUEST_FILE must be defined before including" diff --git a/arch/powerpc/platforms/4xx/msi.c b/arch/powerpc/platforms/4xx/msi.c index 81b2cbce7df8..7c324eff2f22 100644 --- a/arch/powerpc/platforms/4xx/msi.c +++ b/arch/powerpc/platforms/4xx/msi.c @@ -146,13 +146,19 @@ static int ppc4xx_setup_pcieh_hw(struct platform_device *dev, const u32 *sdr_addr; dma_addr_t msi_phys; void *msi_virt; + int err; sdr_addr = of_get_property(dev->dev.of_node, "sdr-base", NULL); if (!sdr_addr) - return -1; + return -EINVAL; - mtdcri(SDR0, *sdr_addr, upper_32_bits(res.start)); /*HIGH addr */ - mtdcri(SDR0, *sdr_addr + 1, lower_32_bits(res.start)); /* Low addr */ + msi_data = of_get_property(dev->dev.of_node, "msi-data", NULL); + if (!msi_data) + return -EINVAL; + + msi_mask = of_get_property(dev->dev.of_node, "msi-mask", NULL); + if (!msi_mask) + return -EINVAL; msi->msi_dev = of_find_node_by_name(NULL, "ppc4xx-msi"); if (!msi->msi_dev) @@ -160,30 +166,30 @@ static int ppc4xx_setup_pcieh_hw(struct platform_device *dev, msi->msi_regs = of_iomap(msi->msi_dev, 0); if (!msi->msi_regs) { - dev_err(&dev->dev, "of_iomap problem failed\n"); - return -ENOMEM; + dev_err(&dev->dev, "of_iomap failed\n"); + err = -ENOMEM; + goto node_put; } dev_dbg(&dev->dev, "PCIE-MSI: msi register mapped 0x%x 0x%x\n", (u32) (msi->msi_regs + PEIH_TERMADH), (u32) (msi->msi_regs)); msi_virt = dma_alloc_coherent(&dev->dev, 64, &msi_phys, GFP_KERNEL); - if (!msi_virt) - return -ENOMEM; + if (!msi_virt) { + err = -ENOMEM; + goto iounmap; + } msi->msi_addr_hi = upper_32_bits(msi_phys); msi->msi_addr_lo = lower_32_bits(msi_phys & 0xffffffff); dev_dbg(&dev->dev, "PCIE-MSI: msi address high 0x%x, low 0x%x\n", msi->msi_addr_hi, msi->msi_addr_lo); + mtdcri(SDR0, *sdr_addr, upper_32_bits(res.start)); /*HIGH addr */ + mtdcri(SDR0, *sdr_addr + 1, lower_32_bits(res.start)); /* Low addr */ + /* Progam the Interrupt handler Termination addr registers */ out_be32(msi->msi_regs + PEIH_TERMADH, msi->msi_addr_hi); out_be32(msi->msi_regs + PEIH_TERMADL, msi->msi_addr_lo); - msi_data = of_get_property(dev->dev.of_node, "msi-data", NULL); - if (!msi_data) - return -1; - msi_mask = of_get_property(dev->dev.of_node, "msi-mask", NULL); - if (!msi_mask) - return -1; /* Program MSI Expected data and Mask bits */ out_be32(msi->msi_regs + PEIH_MSIED, *msi_data); out_be32(msi->msi_regs + PEIH_MSIMK, *msi_mask); @@ -191,6 +197,12 @@ static int ppc4xx_setup_pcieh_hw(struct platform_device *dev, dma_free_coherent(&dev->dev, 64, msi_virt, msi_phys); return 0; + +iounmap: + iounmap(msi->msi_regs); +node_put: + of_node_put(msi->msi_dev); + return err; } static int ppc4xx_of_msi_remove(struct platform_device *dev) @@ -209,7 +221,6 @@ static int ppc4xx_of_msi_remove(struct platform_device *dev) msi_bitmap_free(&msi->bitmap); iounmap(msi->msi_regs); of_node_put(msi->msi_dev); - kfree(msi); return 0; } @@ -223,18 +234,16 @@ static int ppc4xx_msi_probe(struct platform_device *dev) dev_dbg(&dev->dev, "PCIE-MSI: Setting up MSI support...\n"); - msi = kzalloc(sizeof(*msi), GFP_KERNEL); - if (!msi) { - dev_err(&dev->dev, "No memory for MSI structure\n"); + msi = devm_kzalloc(&dev->dev, sizeof(*msi), GFP_KERNEL); + if (!msi) return -ENOMEM; - } dev->dev.platform_data = msi; /* Get MSI ranges */ err = of_address_to_resource(dev->dev.of_node, 0, &res); if (err) { dev_err(&dev->dev, "%pOF resource error!\n", dev->dev.of_node); - goto error_out; + return err; } msi_irqs = of_irq_count(dev->dev.of_node); @@ -243,7 +252,7 @@ static int ppc4xx_msi_probe(struct platform_device *dev) err = ppc4xx_setup_pcieh_hw(dev, res, msi); if (err) - goto error_out; + return err; err = ppc4xx_msi_init_allocator(dev, msi); if (err) { @@ -256,7 +265,7 @@ static int ppc4xx_msi_probe(struct platform_device *dev) phb->controller_ops.setup_msi_irqs = ppc4xx_setup_msi_irqs; phb->controller_ops.teardown_msi_irqs = ppc4xx_teardown_msi_irqs; } - return err; + return 0; error_out: ppc4xx_of_msi_remove(dev); diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile index ff2f86fe5429..f40d48eab779 100644 --- a/arch/powerpc/platforms/52xx/Makefile +++ b/arch/powerpc/platforms/52xx/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_PPC_LITE5200) += lite5200.o obj-$(CONFIG_PPC_MEDIA5200) += media5200.o obj-$(CONFIG_PM) += mpc52xx_sleep.o mpc52xx_pm.o -ifeq ($(CONFIG_PPC_LITE5200),y) +ifdef CONFIG_PPC_LITE5200 obj-$(CONFIG_PM) += lite5200_sleep.o lite5200_pm.o endif diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pm.c b/arch/powerpc/platforms/52xx/mpc52xx_pm.c index 31d3515672f3..b1d208ded981 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_pm.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_pm.c @@ -117,7 +117,10 @@ int mpc52xx_pm_enter(suspend_state_t state) u32 intr_main_mask; void __iomem * irq_0x500 = (void __iomem *)CONFIG_KERNEL_START + 0x500; unsigned long irq_0x500_stop = (unsigned long)irq_0x500 + mpc52xx_ds_cached_size; - char saved_0x500[mpc52xx_ds_cached_size]; + char saved_0x500[0x600-0x500]; + + if (WARN_ON(mpc52xx_ds_cached_size > sizeof(saved_0x500))) + return -ENOMEM; /* disable all interrupts in PIC */ intr_main_mask = in_be32(&intr->main_mask); diff --git a/arch/powerpc/platforms/85xx/t1042rdb_diu.c b/arch/powerpc/platforms/85xx/t1042rdb_diu.c index 58fa3d319f1c..dac36ba82fea 100644 --- a/arch/powerpc/platforms/85xx/t1042rdb_diu.c +++ b/arch/powerpc/platforms/85xx/t1042rdb_diu.c @@ -9,8 +9,10 @@ * option) any later version. */ +#include <linux/init.h> #include <linux/io.h> #include <linux/kernel.h> +#include <linux/module.h> #include <linux/of.h> #include <linux/of_address.h> @@ -150,3 +152,5 @@ static int __init t1042rdb_diu_init(void) } early_initcall(t1042rdb_diu_init); + +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index e6a1de521319..6c6a7c72cae4 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -74,7 +74,6 @@ config PPC_BOOK3S_64 select HAVE_ARCH_TRANSPARENT_HUGEPAGE select ARCH_SUPPORTS_NUMA_BALANCING select IRQ_WORK - select HAVE_KERNEL_XZ config PPC_BOOK3E_64 bool "Embedded processors" @@ -86,7 +85,6 @@ endchoice choice prompt "CPU selection" - depends on PPC64 default GENERIC_CPU help This will create a kernel which is optimised for a particular CPU. @@ -96,13 +94,17 @@ choice config GENERIC_CPU bool "Generic (POWER4 and above)" - depends on !CPU_LITTLE_ENDIAN + depends on PPC64 && !CPU_LITTLE_ENDIAN config GENERIC_CPU bool "Generic (POWER8 and above)" - depends on CPU_LITTLE_ENDIAN + depends on PPC64 && CPU_LITTLE_ENDIAN select ARCH_HAS_FAST_MULTIPLIER +config GENERIC_CPU + bool "Generic 32 bits powerpc" + depends on PPC32 && !PPC_8xx + config CELL_CPU bool "Cell Broadband Engine" depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN @@ -138,8 +140,37 @@ config E6500_CPU bool "Freescale e6500" depends on E500 +config 860_CPU + bool "8xx family" + depends on PPC_8xx + +config E300C2_CPU + bool "e300c2 (832x)" + depends on PPC_BOOK3S_32 + +config E300C3_CPU + bool "e300c3 (831x)" + depends on PPC_BOOK3S_32 + endchoice +config TARGET_CPU_BOOL + bool + default !GENERIC_CPU + +config TARGET_CPU + string + depends on TARGET_CPU_BOOL + default "cell" if CELL_CPU + default "power5" if POWER5_CPU + default "power6" if POWER6_CPU + default "power7" if POWER7_CPU + default "power8" if POWER8_CPU + default "power9" if POWER9_CPU + default "860" if 860_CPU + default "e300c2" if E300C2_CPU + default "e300c3" if E300C3_CPU + config PPC_BOOK3S def_bool y depends on PPC_BOOK3S_32 || PPC_BOOK3S_64 diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index d5f808e8a5f3..10064a33ca96 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_CBE_CPUFREQ_SPU_GOVERNOR) += cpufreq_spudemand.o obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON) += cbe_powerbutton.o -ifeq ($(CONFIG_SMP),y) +ifdef CONFIG_SMP obj-$(CONFIG_PPC_CELL_NATIVE) += smp.o endif diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c index 2c15ff094483..55aac74e1cb9 100644 --- a/arch/powerpc/platforms/cell/cbe_thermal.c +++ b/arch/powerpc/platforms/cell/cbe_thermal.c @@ -49,6 +49,7 @@ #include <linux/device.h> #include <linux/kernel.h> #include <linux/cpu.h> +#include <linux/stringify.h> #include <asm/spu.h> #include <asm/io.h> #include <asm/prom.h> diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c index 1e002e94d0f6..83cf58daaa79 100644 --- a/arch/powerpc/platforms/cell/spufs/fault.c +++ b/arch/powerpc/platforms/cell/spufs/fault.c @@ -111,7 +111,7 @@ int spufs_handle_class1(struct spu_context *ctx) { u64 ea, dsisr, access; unsigned long flags; - unsigned flt = 0; + vm_fault_t flt = 0; int ret; /* diff --git a/arch/powerpc/platforms/cell/spufs/sputrace.h b/arch/powerpc/platforms/cell/spufs/sputrace.h index d557e999b662..1def11e911ac 100644 --- a/arch/powerpc/platforms/cell/spufs/sputrace.h +++ b/arch/powerpc/platforms/cell/spufs/sputrace.h @@ -3,6 +3,7 @@ #define _TRACE_SPUFS_H #include <linux/tracepoint.h> +#include <linux/stringify.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM spufs diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c index c3ede2c365c3..791b86398e1d 100644 --- a/arch/powerpc/platforms/chrp/nvram.c +++ b/arch/powerpc/platforms/chrp/nvram.c @@ -11,6 +11,7 @@ */ #include <linux/kernel.h> +#include <linux/module.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/uaccess.h> @@ -89,3 +90,5 @@ void __init chrp_nvram_init(void) return; } + +MODULE_LICENSE("GPL v2"); diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 8bb46dcbebd8..403523c061ba 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -67,16 +67,6 @@ void __init wii_memory_fixups(void) { struct memblock_region *p = memblock.memory.regions; - /* - * This is part of a workaround to allow the use of two - * discontinuous RAM ranges on the Wii, even if this is - * currently unsupported on 32-bit PowerPC Linux. - * - * We coalesce the two memory ranges of the Wii into a - * single range, then create a reservation for the "hole" - * between both ranges. - */ - BUG_ON(memblock.memory.cnt != 2); BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base)); diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c index 2c72263ad6ab..c80f72c370ae 100644 --- a/arch/powerpc/platforms/pasemi/dma_lib.c +++ b/arch/powerpc/platforms/pasemi/dma_lib.c @@ -531,7 +531,7 @@ int pasemi_dma_init(void) iob_pdev = pci_get_device(PCI_VENDOR_ID_PASEMI, 0xa001, NULL); if (!iob_pdev) { BUG(); - printk(KERN_WARNING "Can't find I/O Bridge\n"); + pr_warn("Can't find I/O Bridge\n"); err = -ENODEV; goto out; } @@ -540,7 +540,7 @@ int pasemi_dma_init(void) dma_pdev = pci_get_device(PCI_VENDOR_ID_PASEMI, 0xa007, NULL); if (!dma_pdev) { BUG(); - printk(KERN_WARNING "Can't find DMA controller\n"); + pr_warn("Can't find DMA controller\n"); err = -ENODEV; goto out; } @@ -623,7 +623,7 @@ int pasemi_dma_init(void) pasemi_write_dma_reg(PAS_DMA_TXF_CFLG0, 0xffffffff); pasemi_write_dma_reg(PAS_DMA_TXF_CFLG1, 0xffffffff); - printk(KERN_INFO "PA Semi PWRficient DMA library initialized " + pr_info("PA Semi PWRficient DMA library initialized " "(%d tx, %d rx channels)\n", num_txch, num_rxch); out: diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c index c23e60959aa8..6f35a2afe522 100644 --- a/arch/powerpc/platforms/pasemi/gpio_mdio.c +++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c @@ -256,7 +256,7 @@ static int gpio_mdio_probe(struct platform_device *ofdev) err = of_mdiobus_register(new_bus, np); if (err != 0) { - printk(KERN_ERR "%s: Cannot register as MDIO bus, err %d\n", + pr_err("%s: Cannot register as MDIO bus, err %d\n", new_bus->name, err); goto out_free_irq; } diff --git a/arch/powerpc/platforms/pasemi/idle.c b/arch/powerpc/platforms/pasemi/idle.c index 44e0d9226f0a..8bb4e8082441 100644 --- a/arch/powerpc/platforms/pasemi/idle.c +++ b/arch/powerpc/platforms/pasemi/idle.c @@ -78,13 +78,13 @@ static int pasemi_system_reset_exception(struct pt_regs *regs) static int __init pasemi_idle_init(void) { #ifndef CONFIG_PPC_PASEMI_CPUFREQ - printk(KERN_WARNING "No cpufreq driver, powersavings modes disabled\n"); + pr_warn("No cpufreq driver, powersavings modes disabled\n"); current_mode = 0; #endif ppc_md.system_reset_exception = pasemi_system_reset_exception; ppc_md.power_save = modes[current_mode].entry; - printk(KERN_INFO "Using PA6T idle loop (%s)\n", modes[current_mode].name); + pr_info("Using PA6T idle loop (%s)\n", modes[current_mode].name); return 0; } diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 78b80cbd9768..f06c83f321e6 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -210,7 +210,7 @@ static int __init iob_init(struct device_node *dn) /* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */ iob_l2_base = (u32 *)__va(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000)); - printk(KERN_INFO "IOBMAP L2 allocated at: %p\n", iob_l2_base); + pr_info("IOBMAP L2 allocated at: %p\n", iob_l2_base); /* Allocate a spare page to map all invalid IOTLB pages. */ tmp = memblock_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE); diff --git a/arch/powerpc/platforms/pasemi/misc.c b/arch/powerpc/platforms/pasemi/misc.c index 8571e7bf78b6..aa958a46957f 100644 --- a/arch/powerpc/platforms/pasemi/misc.c +++ b/arch/powerpc/platforms/pasemi/misc.c @@ -69,9 +69,7 @@ static int __init pasemi_register_i2c_devices(void) addr = of_get_property(node, "reg", &len); if (!addr || len < sizeof(int) || *addr > (1 << 10) - 1) { - printk(KERN_WARNING - "pasemi_register_i2c_devices: " - "invalid i2c device entry\n"); + pr_warn("pasemi_register_i2c_devices: invalid i2c device entry\n"); continue; } diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c index aea9ff2c8e6d..c3c64172482d 100644 --- a/arch/powerpc/platforms/pasemi/pci.c +++ b/arch/powerpc/platforms/pasemi/pci.c @@ -205,7 +205,7 @@ static int __init pas_add_bridge(struct device_node *dev) setup_pa_pxp(hose); - printk(KERN_INFO "Found PA-PXP PCI host bridge.\n"); + pr_info("Found PA-PXP PCI host bridge.\n"); /* Interpret the "ranges" property */ pci_process_bridge_OF_ranges(hose, dev, 1); @@ -216,21 +216,21 @@ static int __init pas_add_bridge(struct device_node *dev) void __init pas_pci_init(void) { struct device_node *np, *root; + int res; root = of_find_node_by_path("/"); if (!root) { - printk(KERN_CRIT "pas_pci_init: can't find root " - "of device tree\n"); + pr_crit("pas_pci_init: can't find root of device tree\n"); return; } pci_set_flags(PCI_SCAN_ALL_PCIE_DEVS); - for (np = NULL; (np = of_get_next_child(root, np)) != NULL;) - if (np->name && !strcmp(np->name, "pxp") && !pas_add_bridge(np)) - of_node_get(np); - - of_node_put(root); + np = of_find_compatible_node(root, NULL, "pasemi,rootbus"); + if (np) { + res = pas_add_bridge(np); + of_node_put(np); + } } void __iomem *pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset) diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c index d0b8ae53660d..9a6eb04cca83 100644 --- a/arch/powerpc/platforms/pasemi/setup.c +++ b/arch/powerpc/platforms/pasemi/setup.c @@ -207,8 +207,7 @@ static __init void pas_init_IRQ(void) break; } if (!mpic_node) { - printk(KERN_ERR - "Failed to locate the MPIC interrupt controller\n"); + pr_err("Failed to locate the MPIC interrupt controller\n"); return; } @@ -217,12 +216,12 @@ static __init void pas_init_IRQ(void) naddr = of_n_addr_cells(root); opprop = of_get_property(root, "platform-open-pic", &opplen); if (!opprop) { - printk(KERN_ERR "No platform-open-pic property.\n"); + pr_err("No platform-open-pic property.\n"); of_node_put(root); return; } openpic_addr = of_read_number(opprop, naddr); - printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr); + pr_debug("OpenPIC addr: %lx\n", openpic_addr); mpic_flags = MPIC_LARGE_VECTORS | MPIC_NO_BIAS | MPIC_NO_RESET; @@ -265,72 +264,72 @@ static int pas_machine_check_handler(struct pt_regs *regs) srr1 = regs->msr; if (nmi_virq && mpic_get_mcirq() == nmi_virq) { - printk(KERN_ERR "NMI delivered\n"); + pr_err("NMI delivered\n"); debugger(regs); mpic_end_irq(irq_get_irq_data(nmi_virq)); goto out; } dsisr = mfspr(SPRN_DSISR); - printk(KERN_ERR "Machine Check on CPU %d\n", cpu); - printk(KERN_ERR "SRR0 0x%016lx SRR1 0x%016lx\n", srr0, srr1); - printk(KERN_ERR "DSISR 0x%016lx DAR 0x%016lx\n", dsisr, regs->dar); - printk(KERN_ERR "BER 0x%016lx MER 0x%016lx\n", mfspr(SPRN_PA6T_BER), + pr_err("Machine Check on CPU %d\n", cpu); + pr_err("SRR0 0x%016lx SRR1 0x%016lx\n", srr0, srr1); + pr_err("DSISR 0x%016lx DAR 0x%016lx\n", dsisr, regs->dar); + pr_err("BER 0x%016lx MER 0x%016lx\n", mfspr(SPRN_PA6T_BER), mfspr(SPRN_PA6T_MER)); - printk(KERN_ERR "IER 0x%016lx DER 0x%016lx\n", mfspr(SPRN_PA6T_IER), + pr_err("IER 0x%016lx DER 0x%016lx\n", mfspr(SPRN_PA6T_IER), mfspr(SPRN_PA6T_DER)); - printk(KERN_ERR "Cause:\n"); + pr_err("Cause:\n"); if (srr1 & 0x200000) - printk(KERN_ERR "Signalled by SDC\n"); + pr_err("Signalled by SDC\n"); if (srr1 & 0x100000) { - printk(KERN_ERR "Load/Store detected error:\n"); + pr_err("Load/Store detected error:\n"); if (dsisr & 0x8000) - printk(KERN_ERR "D-cache ECC double-bit error or bus error\n"); + pr_err("D-cache ECC double-bit error or bus error\n"); if (dsisr & 0x4000) - printk(KERN_ERR "LSU snoop response error\n"); + pr_err("LSU snoop response error\n"); if (dsisr & 0x2000) { - printk(KERN_ERR "MMU SLB multi-hit or invalid B field\n"); + pr_err("MMU SLB multi-hit or invalid B field\n"); dump_slb = 1; } if (dsisr & 0x1000) - printk(KERN_ERR "Recoverable Duptags\n"); + pr_err("Recoverable Duptags\n"); if (dsisr & 0x800) - printk(KERN_ERR "Recoverable D-cache parity error count overflow\n"); + pr_err("Recoverable D-cache parity error count overflow\n"); if (dsisr & 0x400) - printk(KERN_ERR "TLB parity error count overflow\n"); + pr_err("TLB parity error count overflow\n"); } if (srr1 & 0x80000) - printk(KERN_ERR "Bus Error\n"); + pr_err("Bus Error\n"); if (srr1 & 0x40000) { - printk(KERN_ERR "I-side SLB multiple hit\n"); + pr_err("I-side SLB multiple hit\n"); dump_slb = 1; } if (srr1 & 0x20000) - printk(KERN_ERR "I-cache parity error hit\n"); + pr_err("I-cache parity error hit\n"); if (num_mce_regs == 0) - printk(KERN_ERR "No MCE registers mapped yet, can't dump\n"); + pr_err("No MCE registers mapped yet, can't dump\n"); else - printk(KERN_ERR "SoC debug registers:\n"); + pr_err("SoC debug registers:\n"); for (i = 0; i < num_mce_regs; i++) - printk(KERN_ERR "%s: 0x%08x\n", mce_regs[i].name, + pr_err("%s: 0x%08x\n", mce_regs[i].name, in_le32(mce_regs[i].addr)); if (dump_slb) { unsigned long e, v; int i; - printk(KERN_ERR "slb contents:\n"); + pr_err("slb contents:\n"); for (i = 0; i < mmu_slb_size; i++) { asm volatile("slbmfee %0,%1" : "=r" (e) : "r" (i)); asm volatile("slbmfev %0,%1" : "=r" (v) : "r" (i)); - printk(KERN_ERR "%02d %016lx %016lx\n", i, e, v); + pr_err("%02d %016lx %016lx\n", i, e, v); } } diff --git a/arch/powerpc/platforms/powermac/cache.S b/arch/powerpc/platforms/powermac/cache.S index cc5347eb1662..27862feee4a5 100644 --- a/arch/powerpc/platforms/powermac/cache.S +++ b/arch/powerpc/platforms/powermac/cache.S @@ -17,6 +17,7 @@ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/cputable.h> +#include <asm/feature-fixups.h> /* * Flush and disable all data caches (dL1, L2, L3). This is used diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 3f82cb24eb2b..4eb8cb38fc69 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -2889,10 +2889,8 @@ set_initial_features(void) /* On all machines, switch modem & serial ports off */ for_each_node_by_name(np, "ch-a") initial_serial_shutdown(np); - of_node_put(np); for_each_node_by_name(np, "ch-b") initial_serial_shutdown(np); - of_node_put(np); } void __init diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index df762bb3c735..04527d13d5a4 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -781,12 +781,12 @@ static int __init pmac_add_bridge(struct device_node *dev) struct resource rsrc; char *disp_name; const int *bus_range; - int primary = 1, has_address = 0; + int primary = 1; DBG("Adding PCI host bridge %pOF\n", dev); /* Fetch host bridge registers address */ - has_address = (of_address_to_resource(dev, 0, &rsrc) == 0); + of_address_to_resource(dev, 0, &rsrc); /* Get bus range if any */ bus_range = of_get_property(dev, "bus-range", &len); @@ -904,7 +904,7 @@ static int pmac_pci_root_bridge_prepare(struct pci_host_bridge *bridge) void __init pmac_pci_init(void) { struct device_node *np, *root; - struct device_node *ht = NULL; + struct device_node *ht __maybe_unused = NULL; pci_set_flags(PCI_CAN_SKIP_ISA_ALIGN); @@ -1019,7 +1019,7 @@ static bool pmac_pci_enable_device_hook(struct pci_dev *dev) return true; } -void pmac_pci_fixup_ohci(struct pci_dev *dev) +static void pmac_pci_fixup_ohci(struct pci_dev *dev) { struct device_node *node = pci_device_to_OF_node(dev); @@ -1054,7 +1054,7 @@ void __init pmac_pcibios_after_init(void) } } -void pmac_pci_fixup_cardbus(struct pci_dev* dev) +static void pmac_pci_fixup_cardbus(struct pci_dev *dev) { if (!machine_is(powermac)) return; @@ -1091,7 +1091,7 @@ void pmac_pci_fixup_cardbus(struct pci_dev* dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_TI, PCI_ANY_ID, pmac_pci_fixup_cardbus); -void pmac_pci_fixup_pciata(struct pci_dev* dev) +static void pmac_pci_fixup_pciata(struct pci_dev *dev) { u8 progif = 0; diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index 1c2802fabd57..f89808b9713d 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -18,6 +18,7 @@ #include <asm/thread_info.h> #include <asm/asm-offsets.h> #include <asm/mmu.h> +#include <asm/feature-fixups.h> #define MAGIC 0x4c617273 /* 'Lars' */ diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c index 12e6e4d30602..f92c1918fb56 100644 --- a/arch/powerpc/platforms/powermac/time.c +++ b/arch/powerpc/platforms/powermac/time.c @@ -34,6 +34,8 @@ #include <asm/nvram.h> #include <asm/smu.h> +#include "pmac.h" + #undef DEBUG #ifdef DEBUG @@ -249,7 +251,7 @@ int pmac_set_rtc_time(struct rtc_time *tm) * Calibrate the decrementer register using VIA timer 1. * This is used both on powermacs and CHRP machines. */ -int __init via_calibrate_decr(void) +static int __init via_calibrate_decr(void) { struct device_node *vias; volatile unsigned char __iomem *via; diff --git a/arch/powerpc/platforms/powermac/udbg_scc.c b/arch/powerpc/platforms/powermac/udbg_scc.c index d83135a9830e..8901973ed683 100644 --- a/arch/powerpc/platforms/powermac/udbg_scc.c +++ b/arch/powerpc/platforms/powermac/udbg_scc.c @@ -73,7 +73,7 @@ void udbg_scc_init(int force_scc) struct device_node *stdout = NULL, *escc = NULL, *macio = NULL; struct device_node *ch, *ch_def = NULL, *ch_a = NULL; const char *path; - int i, x; + int i; escc = of_find_node_by_name(NULL, "escc"); if (escc == NULL) @@ -120,7 +120,7 @@ void udbg_scc_init(int force_scc) mb(); for (i = 20000; i != 0; --i) - x = in_8(sccc); + in_8(sccc); out_8(sccc, 0x09); /* reset A or B side */ out_8(sccc, 0xc0); diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 703a350a7f4e..b540ce8eec55 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -6,7 +6,7 @@ obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o obj-y += opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o -obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o +obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o obj-$(CONFIG_CXL_BASE) += pci-cxl.o obj-$(CONFIG_EEH) += eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index ddfc3544d285..3c1beae29f2d 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -223,6 +223,14 @@ int pnv_eeh_post_init(void) eeh_probe_devices(); eeh_addr_cache_build(); + if (eeh_has_flag(EEH_POSTPONED_PROBE)) { + eeh_clear_flag(EEH_POSTPONED_PROBE); + if (eeh_enabled()) + pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); + else + pr_info("EEH: No capable adapters found\n"); + } + /* Register OPAL event notifier */ eeh_event_irq = opal_event_request(ilog2(OPAL_EVENT_PCI_ERROR)); if (eeh_event_irq < 0) { @@ -384,8 +392,10 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) return NULL; /* Skip if we haven't probed yet */ - if (phb->ioda.pe_rmap[config_addr] == IODA_INVALID_PE) + if (phb->ioda.pe_rmap[config_addr] == IODA_INVALID_PE) { + eeh_add_flag(EEH_POSTPONED_PROBE); return NULL; + } /* Initialize eeh device */ edev->class_code = pdn->class_code; diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 1c5d0675b43c..35f699ebb662 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -36,6 +36,8 @@ #define P9_STOP_SPR_PSSCR 855 static u32 supported_cpuidle_states; +struct pnv_idle_states_t *pnv_idle_states; +int nr_pnv_idle_states; /* * The default stop state that will be used by ppc_md.power_save @@ -177,11 +179,6 @@ static void pnv_alloc_idle_core_states(void) paca_ptrs[cpu]->core_idle_state_ptr = core_idle_state; paca_ptrs[cpu]->thread_idle_state = PNV_THREAD_RUNNING; paca_ptrs[cpu]->thread_mask = 1 << j; - if (!cpu_has_feature(CPU_FTR_POWER9_DD1)) - continue; - paca_ptrs[cpu]->thread_sibling_pacas = - kmalloc_node(paca_ptr_array_size, - GFP_KERNEL, node); } } @@ -622,48 +619,10 @@ int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags) * @dt_idle_states: Number of idle state entries * Returns 0 on success */ -static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags, - int dt_idle_states) +static int __init pnv_power9_idle_init(void) { - u64 *psscr_val = NULL; - u64 *psscr_mask = NULL; - u32 *residency_ns = NULL; u64 max_residency_ns = 0; - int rc = 0, i; - - psscr_val = kcalloc(dt_idle_states, sizeof(*psscr_val), GFP_KERNEL); - psscr_mask = kcalloc(dt_idle_states, sizeof(*psscr_mask), GFP_KERNEL); - residency_ns = kcalloc(dt_idle_states, sizeof(*residency_ns), - GFP_KERNEL); - - if (!psscr_val || !psscr_mask || !residency_ns) { - rc = -1; - goto out; - } - - if (of_property_read_u64_array(np, - "ibm,cpu-idle-state-psscr", - psscr_val, dt_idle_states)) { - pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n"); - rc = -1; - goto out; - } - - if (of_property_read_u64_array(np, - "ibm,cpu-idle-state-psscr-mask", - psscr_mask, dt_idle_states)) { - pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr-mask in DT\n"); - rc = -1; - goto out; - } - - if (of_property_read_u32_array(np, - "ibm,cpu-idle-state-residency-ns", - residency_ns, dt_idle_states)) { - pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-residency-ns in DT\n"); - rc = -1; - goto out; - } + int i; /* * Set pnv_first_deep_stop_state, pnv_deepest_stop_psscr_{val,mask}, @@ -679,33 +638,37 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags, * the shallowest (OPAL_PM_STOP_INST_FAST) loss-less stop state. */ pnv_first_deep_stop_state = MAX_STOP_STATE; - for (i = 0; i < dt_idle_states; i++) { + for (i = 0; i < nr_pnv_idle_states; i++) { int err; - u64 psscr_rl = psscr_val[i] & PSSCR_RL_MASK; + struct pnv_idle_states_t *state = &pnv_idle_states[i]; + u64 psscr_rl = state->psscr_val & PSSCR_RL_MASK; - if ((flags[i] & OPAL_PM_LOSE_FULL_CONTEXT) && - (pnv_first_deep_stop_state > psscr_rl)) + if ((state->flags & OPAL_PM_LOSE_FULL_CONTEXT) && + pnv_first_deep_stop_state > psscr_rl) pnv_first_deep_stop_state = psscr_rl; - err = validate_psscr_val_mask(&psscr_val[i], &psscr_mask[i], - flags[i]); + err = validate_psscr_val_mask(&state->psscr_val, + &state->psscr_mask, + state->flags); if (err) { - report_invalid_psscr_val(psscr_val[i], err); + report_invalid_psscr_val(state->psscr_val, err); continue; } - if (max_residency_ns < residency_ns[i]) { - max_residency_ns = residency_ns[i]; - pnv_deepest_stop_psscr_val = psscr_val[i]; - pnv_deepest_stop_psscr_mask = psscr_mask[i]; - pnv_deepest_stop_flag = flags[i]; + state->valid = true; + + if (max_residency_ns < state->residency_ns) { + max_residency_ns = state->residency_ns; + pnv_deepest_stop_psscr_val = state->psscr_val; + pnv_deepest_stop_psscr_mask = state->psscr_mask; + pnv_deepest_stop_flag = state->flags; deepest_stop_found = true; } if (!default_stop_found && - (flags[i] & OPAL_PM_STOP_INST_FAST)) { - pnv_default_stop_val = psscr_val[i]; - pnv_default_stop_mask = psscr_mask[i]; + (state->flags & OPAL_PM_STOP_INST_FAST)) { + pnv_default_stop_val = state->psscr_val; + pnv_default_stop_mask = state->psscr_mask; default_stop_found = true; } } @@ -728,11 +691,8 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags, pr_info("cpuidle-powernv: Requested Level (RL) value of first deep stop = 0x%llx\n", pnv_first_deep_stop_state); -out: - kfree(psscr_val); - kfree(psscr_mask); - kfree(residency_ns); - return rc; + + return 0; } /* @@ -740,50 +700,146 @@ out: */ static void __init pnv_probe_idle_states(void) { - struct device_node *np; - int dt_idle_states; - u32 *flags = NULL; int i; + if (nr_pnv_idle_states < 0) { + pr_warn("cpuidle-powernv: no idle states found in the DT\n"); + return; + } + + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (pnv_power9_idle_init()) + return; + } + + for (i = 0; i < nr_pnv_idle_states; i++) + supported_cpuidle_states |= pnv_idle_states[i].flags; +} + +/* + * This function parses device-tree and populates all the information + * into pnv_idle_states structure. It also sets up nr_pnv_idle_states + * which is the number of cpuidle states discovered through device-tree. + */ + +static int pnv_parse_cpuidle_dt(void) +{ + struct device_node *np; + int nr_idle_states, i; + int rc = 0; + u32 *temp_u32; + u64 *temp_u64; + const char **temp_string; + np = of_find_node_by_path("/ibm,opal/power-mgt"); if (!np) { pr_warn("opal: PowerMgmt Node not found\n"); - goto out; + return -ENODEV; } - dt_idle_states = of_property_count_u32_elems(np, - "ibm,cpu-idle-state-flags"); - if (dt_idle_states < 0) { - pr_warn("cpuidle-powernv: no idle states found in the DT\n"); + nr_idle_states = of_property_count_u32_elems(np, + "ibm,cpu-idle-state-flags"); + + pnv_idle_states = kcalloc(nr_idle_states, sizeof(*pnv_idle_states), + GFP_KERNEL); + temp_u32 = kcalloc(nr_idle_states, sizeof(u32), GFP_KERNEL); + temp_u64 = kcalloc(nr_idle_states, sizeof(u64), GFP_KERNEL); + temp_string = kcalloc(nr_idle_states, sizeof(char *), GFP_KERNEL); + + if (!(pnv_idle_states && temp_u32 && temp_u64 && temp_string)) { + pr_err("Could not allocate memory for dt parsing\n"); + rc = -ENOMEM; goto out; } - flags = kcalloc(dt_idle_states, sizeof(*flags), GFP_KERNEL); - - if (of_property_read_u32_array(np, - "ibm,cpu-idle-state-flags", flags, dt_idle_states)) { + /* Read flags */ + if (of_property_read_u32_array(np, "ibm,cpu-idle-state-flags", + temp_u32, nr_idle_states)) { pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n"); + rc = -EINVAL; + goto out; + } + for (i = 0; i < nr_idle_states; i++) + pnv_idle_states[i].flags = temp_u32[i]; + + /* Read latencies */ + if (of_property_read_u32_array(np, "ibm,cpu-idle-state-latencies-ns", + temp_u32, nr_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-latencies-ns in DT\n"); + rc = -EINVAL; + goto out; + } + for (i = 0; i < nr_idle_states; i++) + pnv_idle_states[i].latency_ns = temp_u32[i]; + + /* Read residencies */ + if (of_property_read_u32_array(np, "ibm,cpu-idle-state-residency-ns", + temp_u32, nr_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-latencies-ns in DT\n"); + rc = -EINVAL; goto out; } + for (i = 0; i < nr_idle_states; i++) + pnv_idle_states[i].residency_ns = temp_u32[i]; + /* For power9 */ if (cpu_has_feature(CPU_FTR_ARCH_300)) { - if (pnv_power9_idle_init(np, flags, dt_idle_states)) + /* Read pm_crtl_val */ + if (of_property_read_u64_array(np, "ibm,cpu-idle-state-psscr", + temp_u64, nr_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n"); + rc = -EINVAL; + goto out; + } + for (i = 0; i < nr_idle_states; i++) + pnv_idle_states[i].psscr_val = temp_u64[i]; + + /* Read pm_crtl_mask */ + if (of_property_read_u64_array(np, "ibm,cpu-idle-state-psscr-mask", + temp_u64, nr_idle_states)) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr-mask in DT\n"); + rc = -EINVAL; goto out; + } + for (i = 0; i < nr_idle_states; i++) + pnv_idle_states[i].psscr_mask = temp_u64[i]; } - for (i = 0; i < dt_idle_states; i++) - supported_cpuidle_states |= flags[i]; + /* + * power8 specific properties ibm,cpu-idle-state-pmicr-mask and + * ibm,cpu-idle-state-pmicr-val were never used and there is no + * plan to use it in near future. Hence, not parsing these properties + */ + if (of_property_read_string_array(np, "ibm,cpu-idle-state-names", + temp_string, nr_idle_states) < 0) { + pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-names in DT\n"); + rc = -EINVAL; + goto out; + } + for (i = 0; i < nr_idle_states; i++) + strlcpy(pnv_idle_states[i].name, temp_string[i], + PNV_IDLE_NAME_LEN); + nr_pnv_idle_states = nr_idle_states; + rc = 0; out: - kfree(flags); + kfree(temp_u32); + kfree(temp_u64); + kfree(temp_string); + return rc; } + static int __init pnv_init_idle_states(void) { - + int rc = 0; supported_cpuidle_states = 0; + /* In case we error out nr_pnv_idle_states will be zero */ + nr_pnv_idle_states = 0; if (cpuidle_disable != IDLE_NO_OVERRIDE) goto out; - + rc = pnv_parse_cpuidle_dt(); + if (rc) + return rc; pnv_probe_idle_states(); if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) { @@ -805,29 +861,6 @@ static int __init pnv_init_idle_states(void) pnv_alloc_idle_core_states(); - /* - * For each CPU, record its PACA address in each of it's - * sibling thread's PACA at the slot corresponding to this - * CPU's index in the core. - */ - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { - int cpu; - - pr_info("powernv: idle: Saving PACA pointers of all CPUs in their thread sibling PACA\n"); - for_each_present_cpu(cpu) { - int base_cpu = cpu_first_thread_sibling(cpu); - int idx = cpu_thread_in_core(cpu); - int i; - - for (i = 0; i < threads_per_core; i++) { - int j = base_cpu + i; - - paca_ptrs[j]->thread_sibling_pacas[idx] = - paca_ptrs[cpu]; - } - } - } - if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED) ppc_md.power_save = power7_idle; diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index b99283df8584..51dc398ae3f7 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -47,38 +47,9 @@ static ssize_t memtrace_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, count, ppos, ent->mem, ent->size); } -static bool valid_memtrace_range(struct memtrace_entry *dev, - unsigned long start, unsigned long size) -{ - if ((start >= dev->start) && - ((start + size) <= (dev->start + dev->size))) - return true; - - return false; -} - -static int memtrace_mmap(struct file *filp, struct vm_area_struct *vma) -{ - unsigned long size = vma->vm_end - vma->vm_start; - struct memtrace_entry *dev = filp->private_data; - - if (!valid_memtrace_range(dev, vma->vm_pgoff << PAGE_SHIFT, size)) - return -EINVAL; - - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - - if (remap_pfn_range(vma, vma->vm_start, - vma->vm_pgoff + (dev->start >> PAGE_SHIFT), - size, vma->vm_page_prot)) - return -EAGAIN; - - return 0; -} - static const struct file_operations memtrace_fops = { .llseek = default_llseek, .read = memtrace_read, - .mmap = memtrace_mmap, .open = simple_open, }; @@ -206,8 +177,11 @@ static int memtrace_init_debugfs(void) snprintf(ent->name, 16, "%08x", ent->nid); dir = debugfs_create_dir(ent->name, memtrace_debugfs_dir); - if (!dir) + if (!dir) { + pr_err("Failed to create debugfs directory for node %d\n", + ent->nid); return -1; + } ent->dir = dir; debugfs_create_file("trace", 0400, dir, ent, &memtrace_fops); @@ -218,18 +192,93 @@ static int memtrace_init_debugfs(void) return ret; } +static int online_mem_block(struct memory_block *mem, void *arg) +{ + return device_online(&mem->dev); +} + +/* + * Iterate through the chunks of memory we have removed from the kernel + * and attempt to add them back to the kernel. + */ +static int memtrace_online(void) +{ + int i, ret = 0; + struct memtrace_entry *ent; + + for (i = memtrace_array_nr - 1; i >= 0; i--) { + ent = &memtrace_array[i]; + + /* We have onlined this chunk previously */ + if (ent->nid == -1) + continue; + + /* Remove from io mappings */ + if (ent->mem) { + iounmap(ent->mem); + ent->mem = 0; + } + + if (add_memory(ent->nid, ent->start, ent->size)) { + pr_err("Failed to add trace memory to node %d\n", + ent->nid); + ret += 1; + continue; + } + + /* + * If kernel isn't compiled with the auto online option + * we need to online the memory ourselves. + */ + if (!memhp_auto_online) { + walk_memory_range(PFN_DOWN(ent->start), + PFN_UP(ent->start + ent->size - 1), + NULL, online_mem_block); + } + + /* + * Memory was added successfully so clean up references to it + * so on reentry we can tell that this chunk was added. + */ + debugfs_remove_recursive(ent->dir); + pr_info("Added trace memory back to node %d\n", ent->nid); + ent->size = ent->start = ent->nid = -1; + } + if (ret) + return ret; + + /* If all chunks of memory were added successfully, reset globals */ + kfree(memtrace_array); + memtrace_array = NULL; + memtrace_size = 0; + memtrace_array_nr = 0; + return 0; +} + static int memtrace_enable_set(void *data, u64 val) { - if (memtrace_size) + u64 bytes; + + /* + * Don't attempt to do anything if size isn't aligned to a memory + * block or equal to zero. + */ + bytes = memory_block_size_bytes(); + if (val & (bytes - 1)) { + pr_err("Value must be aligned with 0x%llx\n", bytes); return -EINVAL; + } - if (!val) - return -EINVAL; + /* Re-add/online previously removed/offlined memory */ + if (memtrace_size) { + if (memtrace_online()) + return -EAGAIN; + } - /* Make sure size is aligned to a memory block */ - if (val & (memory_block_size_bytes() - 1)) - return -EINVAL; + if (!val) + return 0; + /* Offline and remove memory */ if (memtrace_init_regions_runtime(val)) return -EINVAL; diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 8cdf91f5d3a4..8006c54a91e3 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -17,7 +17,9 @@ #include <linux/pci.h> #include <linux/memblock.h> #include <linux/iommu.h> +#include <linux/debugfs.h> +#include <asm/debugfs.h> #include <asm/tlb.h> #include <asm/powernv.h> #include <asm/reg.h> @@ -44,7 +46,8 @@ static DEFINE_SPINLOCK(npu_context_lock); * entire TLB on the GPU for the given PID rather than each specific address in * the range. */ -#define ATSD_THRESHOLD (2*1024*1024) +static uint64_t atsd_threshold = 2 * 1024 * 1024; +static struct dentry *atsd_threshold_dentry; /* * Other types of TCE cache invalidation are not functional in the @@ -437,8 +440,9 @@ static int get_mmio_atsd_reg(struct npu *npu) int i; for (i = 0; i < npu->mmio_atsd_count; i++) { - if (!test_and_set_bit_lock(i, &npu->mmio_atsd_usage)) - return i; + if (!test_bit(i, &npu->mmio_atsd_usage)) + if (!test_and_set_bit_lock(i, &npu->mmio_atsd_usage)) + return i; } return -ENOSPC; @@ -683,7 +687,7 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, struct npu_context *npu_context = mn_to_npu_context(mn); unsigned long address; - if (end - start > ATSD_THRESHOLD) { + if (end - start > atsd_threshold) { /* * Just invalidate the entire PID if the address range is too * large. @@ -958,6 +962,11 @@ int pnv_npu2_init(struct pnv_phb *phb) static int npu_index; uint64_t rc = 0; + if (!atsd_threshold_dentry) { + atsd_threshold_dentry = debugfs_create_x64("atsd_threshold", + 0600, powerpc_debugfs_root, &atsd_threshold); + } + phb->npu.nmmu_flush = of_property_read_bool(phb->hose->dn, "ibm,nmmu-flush"); for_each_child_of_node(phb->hose->dn, dn) { diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 0dc8fa4e0af2..198143833f00 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -225,13 +225,16 @@ static int64_t dump_read_info(uint32_t *dump_id, uint32_t *dump_size, uint32_t * if (rc == OPAL_PARAMETER) rc = opal_dump_info(&id, &size); + if (rc) { + pr_warn("%s: Failed to get dump info (%d)\n", + __func__, rc); + return rc; + } + *dump_id = be32_to_cpu(id); *dump_size = be32_to_cpu(size); *dump_type = be32_to_cpu(type); - if (rc) - pr_warn("%s: Failed to get dump info (%d)\n", - __func__, rc); return rc; } @@ -368,13 +371,12 @@ static irqreturn_t process_dump(int irq, void *data) { int rc; uint32_t dump_id, dump_size, dump_type; - struct dump_obj *dump; char name[22]; struct kobject *kobj; rc = dump_read_info(&dump_id, &dump_size, &dump_type); if (rc != OPAL_SUCCESS) - return rc; + return IRQ_HANDLED; sprintf(name, "0x%x-0x%x", dump_type, dump_id); @@ -386,12 +388,10 @@ static irqreturn_t process_dump(int irq, void *data) if (kobj) { /* Drop reference added by kset_find_obj() */ kobject_put(kobj); - return 0; + return IRQ_HANDLED; } - dump = create_dump_obj(dump_id, dump_size, dump_type); - if (!dump) - return -1; + create_dump_obj(dump_id, dump_size, dump_type); return IRQ_HANDLED; } diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index 605c7e5d52c2..bc97770a67db 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -22,6 +22,7 @@ #include <linux/kthread.h> #include <linux/delay.h> #include <linux/slab.h> +#include <linux/of_irq.h> #include <asm/machdep.h> #include <asm/opal.h> @@ -38,8 +39,8 @@ struct opal_event_irqchip { }; static struct opal_event_irqchip opal_event_irqchip; static u64 last_outstanding_events; -static unsigned int opal_irq_count; -static unsigned int *opal_irqs; +static int opal_irq_count; +static struct resource *opal_irqs; void opal_handle_events(void) { @@ -165,24 +166,23 @@ void opal_event_shutdown(void) /* First free interrupts, which will also mask them */ for (i = 0; i < opal_irq_count; i++) { - if (!opal_irqs[i]) + if (!opal_irqs || !opal_irqs[i].start) continue; if (in_interrupt() || irqs_disabled()) - disable_irq_nosync(opal_irqs[i]); + disable_irq_nosync(opal_irqs[i].start); else - free_irq(opal_irqs[i], NULL); + free_irq(opal_irqs[i].start, NULL); - opal_irqs[i] = 0; + opal_irqs[i].start = 0; } } int __init opal_event_init(void) { struct device_node *dn, *opal_node; - const char **names; - u32 *irqs; - int i, rc; + bool old_style = false; + int i, rc = 0; opal_node = of_find_node_by_path("/ibm,opal"); if (!opal_node) { @@ -207,67 +207,91 @@ int __init opal_event_init(void) goto out; } - /* Get opal-interrupts property and names if present */ - rc = of_property_count_u32_elems(opal_node, "opal-interrupts"); - if (rc < 0) - goto out; + /* Look for new-style (standard) "interrupts" property */ + opal_irq_count = of_irq_count(opal_node); - opal_irq_count = rc; - pr_debug("Found %d interrupts reserved for OPAL\n", opal_irq_count); + /* Absent ? Look for the old one */ + if (opal_irq_count < 1) { + /* Get opal-interrupts property and names if present */ + rc = of_property_count_u32_elems(opal_node, "opal-interrupts"); + if (rc > 0) + opal_irq_count = rc; + old_style = true; + } - irqs = kcalloc(opal_irq_count, sizeof(*irqs), GFP_KERNEL); - names = kcalloc(opal_irq_count, sizeof(*names), GFP_KERNEL); - opal_irqs = kcalloc(opal_irq_count, sizeof(*opal_irqs), GFP_KERNEL); + /* No interrupts ? Bail out */ + if (!opal_irq_count) + goto out; - if (WARN_ON(!irqs || !names || !opal_irqs)) - goto out_free; + pr_debug("OPAL: Found %d interrupts reserved for OPAL using %s scheme\n", + opal_irq_count, old_style ? "old" : "new"); - rc = of_property_read_u32_array(opal_node, "opal-interrupts", - irqs, opal_irq_count); - if (rc < 0) { - pr_err("Error %d reading opal-interrupts array\n", rc); - goto out_free; + /* Allocate an IRQ resources array */ + opal_irqs = kcalloc(opal_irq_count, sizeof(struct resource), GFP_KERNEL); + if (WARN_ON(!opal_irqs)) { + rc = -ENOMEM; + goto out; } - /* It's not an error for the names to be missing */ - of_property_read_string_array(opal_node, "opal-interrupts-names", - names, opal_irq_count); + /* Build the resources array */ + if (old_style) { + /* Old style "opal-interrupts" property */ + for (i = 0; i < opal_irq_count; i++) { + struct resource *r = &opal_irqs[i]; + const char *name = NULL; + u32 hw_irq; + int virq; + + rc = of_property_read_u32_index(opal_node, "opal-interrupts", + i, &hw_irq); + if (WARN_ON(rc < 0)) { + opal_irq_count = i; + break; + } + of_property_read_string_index(opal_node, "opal-interrupts-names", + i, &name); + virq = irq_create_mapping(NULL, hw_irq); + if (!virq) { + pr_warn("Failed to map OPAL irq 0x%x\n", hw_irq); + continue; + } + r->start = r->end = virq; + r->flags = IORESOURCE_IRQ | IRQ_TYPE_LEVEL_LOW; + r->name = name; + } + } else { + /* new style standard "interrupts" property */ + rc = of_irq_to_resource_table(opal_node, opal_irqs, opal_irq_count); + if (WARN_ON(rc < 0)) { + opal_irq_count = 0; + kfree(opal_irqs); + goto out; + } + if (WARN_ON(rc < opal_irq_count)) + opal_irq_count = rc; + } /* Install interrupt handlers */ for (i = 0; i < opal_irq_count; i++) { - unsigned int virq; - char *name; - - /* Get hardware and virtual IRQ */ - virq = irq_create_mapping(NULL, irqs[i]); - if (!virq) { - pr_warn("Failed to map irq 0x%x\n", irqs[i]); - continue; - } + struct resource *r = &opal_irqs[i]; + const char *name; - if (names[i] && strlen(names[i])) - name = kasprintf(GFP_KERNEL, "opal-%s", names[i]); + /* Prefix name */ + if (r->name && strlen(r->name)) + name = kasprintf(GFP_KERNEL, "opal-%s", r->name); else name = kasprintf(GFP_KERNEL, "opal"); /* Install interrupt handler */ - rc = request_irq(virq, opal_interrupt, IRQF_TRIGGER_LOW, + rc = request_irq(r->start, opal_interrupt, r->flags & IRQD_TRIGGER_MASK, name, NULL); if (rc) { - irq_dispose_mapping(virq); - pr_warn("Error %d requesting irq %d (0x%x)\n", - rc, virq, irqs[i]); + pr_warn("Error %d requesting OPAL irq %d\n", rc, (int)r->start); continue; } - - /* Cache IRQ */ - opal_irqs[i] = virq; } - -out_free: - kfree(irqs); - kfree(names); -out: + rc = 0; + out: of_node_put(opal_node); return rc; } diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c index 6f1214d4de92..55691950d981 100644 --- a/arch/powerpc/platforms/powernv/opal-kmsg.c +++ b/arch/powerpc/platforms/powernv/opal-kmsg.c @@ -23,12 +23,9 @@ * may not be completely printed. This function does not actually dump the * message, it just ensures that OPAL completely flushes the console buffer. */ -static void force_opal_console_flush(struct kmsg_dumper *dumper, +static void kmsg_dump_opal_console_flush(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason) { - int i; - int64_t ret; - /* * Outside of a panic context the pollers will continue to run, * so we don't need to do any special flushing. @@ -36,32 +33,11 @@ static void force_opal_console_flush(struct kmsg_dumper *dumper, if (reason != KMSG_DUMP_PANIC) return; - if (opal_check_token(OPAL_CONSOLE_FLUSH)) { - ret = opal_console_flush(0); - - if (ret == OPAL_UNSUPPORTED || ret == OPAL_PARAMETER) - return; - - /* Incrementally flush until there's nothing left */ - while (opal_console_flush(0) != OPAL_SUCCESS); - } else { - /* - * If OPAL_CONSOLE_FLUSH is not implemented in the firmware, - * the console can still be flushed by calling the polling - * function enough times to flush the buffer. We don't know - * how much output still needs to be flushed, but we can be - * generous since the kernel is in panic and doesn't need - * to do much else. - */ - printk(KERN_NOTICE "opal: OPAL_CONSOLE_FLUSH missing.\n"); - for (i = 0; i < 1024; i++) { - opal_poll_events(NULL); - } - } + opal_flush_console(0); } static struct kmsg_dumper opal_kmsg_dumper = { - .dump = force_opal_console_flush + .dump = kmsg_dump_opal_console_flush }; void __init opal_kmsg_init(void) diff --git a/arch/powerpc/platforms/powernv/opal-sensor-groups.c b/arch/powerpc/platforms/powernv/opal-sensor-groups.c index 541c9ea04a32..f7d04b6a2d7a 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor-groups.c +++ b/arch/powerpc/platforms/powernv/opal-sensor-groups.c @@ -32,6 +32,34 @@ static struct sensor_group { struct sg_attr *sgattrs; } *sgs; +int sensor_group_enable(u32 handle, bool enable) +{ + struct opal_msg msg; + int token, ret; + + token = opal_async_get_token_interruptible(); + if (token < 0) + return token; + + ret = opal_sensor_group_enable(handle, token, enable); + if (ret == OPAL_ASYNC_COMPLETION) { + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_devel("Failed to wait for the async response\n"); + ret = -EIO; + goto out; + } + ret = opal_error_code(opal_get_async_rc(msg)); + } else { + ret = opal_error_code(ret); + } + +out: + opal_async_release_token(token); + return ret; +} +EXPORT_SYMBOL_GPL(sensor_group_enable); + static ssize_t sg_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index a8d9b4089c31..251528231a9e 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -14,6 +14,8 @@ #include <asm/hvcall.h> #include <asm/asm-offsets.h> #include <asm/opal.h> +#include <asm/asm-compat.h> +#include <asm/feature-fixups.h> .section ".text" @@ -327,3 +329,5 @@ OPAL_CALL(opal_npu_tl_set, OPAL_NPU_TL_SET); OPAL_CALL(opal_pci_get_pbcq_tunnel_bar, OPAL_PCI_GET_PBCQ_TUNNEL_BAR); OPAL_CALL(opal_pci_set_pbcq_tunnel_bar, OPAL_PCI_SET_PBCQ_TUNNEL_BAR); OPAL_CALL(opal_sensor_read_u64, OPAL_SENSOR_READ_U64); +OPAL_CALL(opal_sensor_group_enable, OPAL_SENSOR_GROUP_ENABLE); +OPAL_CALL(opal_nx_coproc_init, OPAL_NX_COPROC_INIT); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 0d539c661748..404c379db168 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -344,70 +344,125 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count) return 0; } -int opal_put_chars(uint32_t vtermno, const char *data, int total_len) +static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, bool atomic) { - int written = 0; + unsigned long flags = 0 /* shut up gcc */; + int written; __be64 olen; - s64 len, rc; - unsigned long flags; - __be64 evt; + s64 rc; if (!opal.entry) return -ENODEV; - /* We want put_chars to be atomic to avoid mangling of hvsi - * packets. To do that, we first test for room and return - * -EAGAIN if there isn't enough. - * - * Unfortunately, opal_console_write_buffer_space() doesn't - * appear to work on opal v1, so we just assume there is - * enough room and be done with it - */ - spin_lock_irqsave(&opal_write_lock, flags); + if (atomic) + spin_lock_irqsave(&opal_write_lock, flags); rc = opal_console_write_buffer_space(vtermno, &olen); - len = be64_to_cpu(olen); - if (rc || len < total_len) { - spin_unlock_irqrestore(&opal_write_lock, flags); + if (rc || be64_to_cpu(olen) < total_len) { /* Closed -> drop characters */ if (rc) - return total_len; - opal_poll_events(NULL); - return -EAGAIN; + written = total_len; + else + written = -EAGAIN; + goto out; } - /* We still try to handle partial completions, though they - * should no longer happen. - */ - rc = OPAL_BUSY; - while(total_len > 0 && (rc == OPAL_BUSY || - rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) { - olen = cpu_to_be64(total_len); - rc = opal_console_write(vtermno, &olen, data); - len = be64_to_cpu(olen); - - /* Closed or other error drop */ - if (rc != OPAL_SUCCESS && rc != OPAL_BUSY && - rc != OPAL_BUSY_EVENT) { - written = total_len; - break; + /* Should not get a partial write here because space is available. */ + olen = cpu_to_be64(total_len); + rc = opal_console_write(vtermno, &olen, data); + if (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + if (rc == OPAL_BUSY_EVENT) { + mdelay(OPAL_BUSY_DELAY_MS); + opal_poll_events(NULL); + } else if (rc == OPAL_BUSY_EVENT) { + mdelay(OPAL_BUSY_DELAY_MS); } - if (rc == OPAL_SUCCESS) { - total_len -= len; - data += len; - written += len; + written = -EAGAIN; + goto out; + } + + /* Closed or other error drop */ + if (rc != OPAL_SUCCESS) { + written = opal_error_code(rc); + goto out; + } + + written = be64_to_cpu(olen); + if (written < total_len) { + if (atomic) { + /* Should not happen */ + pr_warn("atomic console write returned partial " + "len=%d written=%d\n", total_len, written); } - /* This is a bit nasty but we need that for the console to - * flush when there aren't any interrupts. We will clean - * things a bit later to limit that to synchronous path - * such as the kernel console and xmon/udbg + if (!written) + written = -EAGAIN; + } + +out: + if (atomic) + spin_unlock_irqrestore(&opal_write_lock, flags); + + /* In the -EAGAIN case, callers loop, so we have to flush the console + * here in case they have interrupts off (and we don't want to wait + * for async flushing if we can make immediate progress here). If + * necessary the API could be made entirely non-flushing if the + * callers had a ->flush API to use. + */ + if (written == -EAGAIN) + opal_flush_console(vtermno); + + return written; +} + +int opal_put_chars(uint32_t vtermno, const char *data, int total_len) +{ + return __opal_put_chars(vtermno, data, total_len, false); +} + +/* + * opal_put_chars_atomic will not perform partial-writes. Data will be + * atomically written to the terminal or not at all. This is not strictly + * true at the moment because console space can race with OPAL's console + * writes. + */ +int opal_put_chars_atomic(uint32_t vtermno, const char *data, int total_len) +{ + return __opal_put_chars(vtermno, data, total_len, true); +} + +int opal_flush_console(uint32_t vtermno) +{ + s64 rc; + + if (!opal_check_token(OPAL_CONSOLE_FLUSH)) { + __be64 evt; + + WARN_ONCE(1, "opal: OPAL_CONSOLE_FLUSH missing.\n"); + /* + * If OPAL_CONSOLE_FLUSH is not implemented in the firmware, + * the console can still be flushed by calling the polling + * function while it has OPAL_EVENT_CONSOLE_OUTPUT events. */ - do + do { opal_poll_events(&evt); - while(rc == OPAL_SUCCESS && - (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT)); + } while (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT); + + return OPAL_SUCCESS; } - spin_unlock_irqrestore(&opal_write_lock, flags); - return written; + + do { + rc = OPAL_BUSY; + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_console_flush(vtermno); + if (rc == OPAL_BUSY_EVENT) { + mdelay(OPAL_BUSY_DELAY_MS); + opal_poll_events(NULL); + } else if (rc == OPAL_BUSY) { + mdelay(OPAL_BUSY_DELAY_MS); + } + } + } while (rc == OPAL_PARTIAL); /* More to flush */ + + return opal_error_code(rc); } static int opal_recover_mce(struct pt_regs *regs, @@ -922,6 +977,7 @@ EXPORT_SYMBOL_GPL(opal_flash_read); EXPORT_SYMBOL_GPL(opal_flash_write); EXPORT_SYMBOL_GPL(opal_flash_erase); EXPORT_SYMBOL_GPL(opal_prd_msg); +EXPORT_SYMBOL_GPL(opal_check_token); /* Convert a region of vmalloc memory to an opal sg list */ struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, @@ -1034,3 +1090,5 @@ EXPORT_SYMBOL_GPL(opal_write_oppanel_async); EXPORT_SYMBOL_GPL(opal_int_set_mfrr); EXPORT_SYMBOL_GPL(opal_int_eoi); EXPORT_SYMBOL_GPL(opal_error_code); +/* Export the below symbol for NX compression */ +EXPORT_SYMBOL(opal_nx_coproc_init); diff --git a/arch/powerpc/platforms/powernv/pci-cxl.c b/arch/powerpc/platforms/powernv/pci-cxl.c index cee003de63af..1b18111453d7 100644 --- a/arch/powerpc/platforms/powernv/pci-cxl.c +++ b/arch/powerpc/platforms/powernv/pci-cxl.c @@ -8,11 +8,8 @@ */ #include <linux/module.h> -#include <linux/msi.h> -#include <asm/pci-bridge.h> #include <asm/pnv-pci.h> #include <asm/opal.h> -#include <misc/cxl.h> #include "pci.h" @@ -179,199 +176,3 @@ static inline int get_cxl_module(void) #else static inline int get_cxl_module(void) { return 0; } #endif - -/* - * Sets flags and switches the controller ops to enable the cxl kernel api. - * Originally the cxl kernel API operated on a virtual PHB, but certain cards - * such as the Mellanox CX4 use a peer model instead and for these cards the - * cxl kernel api will operate on the real PHB. - */ -int pnv_cxl_enable_phb_kernel_api(struct pci_controller *hose, bool enable) -{ - struct pnv_phb *phb = hose->private_data; - int rc; - - if (!enable) { - /* - * Once cxl mode is enabled on the PHB, there is currently no - * known safe method to disable it again, and trying risks a - * checkstop. If we can find a way to safely disable cxl mode - * in the future we can revisit this, but for now the only sane - * thing to do is to refuse to disable cxl mode: - */ - return -EPERM; - } - - /* - * Hold a reference to the cxl module since several PHB operations now - * depend on it, and it would be insane to allow it to be removed so - * long as we are in this mode (and since we can't safely disable this - * mode once enabled...). - */ - rc = get_cxl_module(); - if (rc) - return rc; - - phb->flags |= PNV_PHB_FLAG_CXL; - hose->controller_ops = pnv_cxl_cx4_ioda_controller_ops; - - return 0; -} -EXPORT_SYMBOL_GPL(pnv_cxl_enable_phb_kernel_api); - -bool pnv_pci_on_cxl_phb(struct pci_dev *dev) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - struct pnv_phb *phb = hose->private_data; - - return !!(phb->flags & PNV_PHB_FLAG_CXL); -} -EXPORT_SYMBOL_GPL(pnv_pci_on_cxl_phb); - -struct cxl_afu *pnv_cxl_phb_to_afu(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - - return (struct cxl_afu *)phb->cxl_afu; -} -EXPORT_SYMBOL_GPL(pnv_cxl_phb_to_afu); - -void pnv_cxl_phb_set_peer_afu(struct pci_dev *dev, struct cxl_afu *afu) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - struct pnv_phb *phb = hose->private_data; - - phb->cxl_afu = afu; -} -EXPORT_SYMBOL_GPL(pnv_cxl_phb_set_peer_afu); - -/* - * In the peer cxl model, the XSL/PSL is physical function 0, and will be used - * by other functions on the device for memory access and interrupts. When the - * other functions are enabled we explicitly take a reference on the cxl - * function since they will use it, and allocate a default context associated - * with that function just like the vPHB model of the cxl kernel API. - */ -bool pnv_cxl_enable_device_hook(struct pci_dev *dev) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - struct pnv_phb *phb = hose->private_data; - struct cxl_afu *afu = phb->cxl_afu; - - if (!pnv_pci_enable_device_hook(dev)) - return false; - - - /* No special handling for the cxl function, which is always PF 0 */ - if (PCI_FUNC(dev->devfn) == 0) - return true; - - if (!afu) { - dev_WARN(&dev->dev, "Attempted to enable function > 0 on CXL PHB without a peer AFU\n"); - return false; - } - - dev_info(&dev->dev, "Enabling function on CXL enabled PHB with peer AFU\n"); - - /* Make sure the peer AFU can't go away while this device is active */ - cxl_afu_get(afu); - - return cxl_pci_associate_default_context(dev, afu); -} - -void pnv_cxl_disable_device(struct pci_dev *dev) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - struct pnv_phb *phb = hose->private_data; - struct cxl_afu *afu = phb->cxl_afu; - - /* No special handling for cxl function: */ - if (PCI_FUNC(dev->devfn) == 0) - return; - - cxl_pci_disable_device(dev); - cxl_afu_put(afu); -} - -/* - * This is a special version of pnv_setup_msi_irqs for cards in cxl mode. This - * function handles setting up the IVTE entries for the XSL to use. - * - * We are currently not filling out the MSIX table, since the only currently - * supported adapter (CX4) uses a custom MSIX table format in cxl mode and it - * is up to their driver to fill that out. In the future we may fill out the - * MSIX table (and change the IVTE entries to be an index to the MSIX table) - * for adapters implementing the Full MSI-X mode described in the CAIA. - */ -int pnv_cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) -{ - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; - struct msi_desc *entry; - struct cxl_context *ctx = NULL; - unsigned int virq; - int hwirq; - int afu_irq = 0; - int rc; - - if (WARN_ON(!phb) || !phb->msi_bmp.bitmap) - return -ENODEV; - - if (pdev->no_64bit_msi && !phb->msi32_support) - return -ENODEV; - - rc = cxl_cx4_setup_msi_irqs(pdev, nvec, type); - if (rc) - return rc; - - for_each_pci_msi_entry(entry, pdev) { - if (!entry->msi_attrib.is_64 && !phb->msi32_support) { - pr_warn("%s: Supports only 64-bit MSIs\n", - pci_name(pdev)); - return -ENXIO; - } - - hwirq = cxl_next_msi_hwirq(pdev, &ctx, &afu_irq); - if (WARN_ON(hwirq <= 0)) - return (hwirq ? hwirq : -ENOMEM); - - virq = irq_create_mapping(NULL, hwirq); - if (!virq) { - pr_warn("%s: Failed to map cxl mode MSI to linux irq\n", - pci_name(pdev)); - return -ENOMEM; - } - - rc = pnv_cxl_ioda_msi_setup(pdev, hwirq, virq); - if (rc) { - pr_warn("%s: Failed to setup cxl mode MSI\n", pci_name(pdev)); - irq_dispose_mapping(virq); - return rc; - } - - irq_set_msi_desc(virq, entry); - } - - return 0; -} - -void pnv_cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev) -{ - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; - struct msi_desc *entry; - irq_hw_number_t hwirq; - - if (WARN_ON(!phb)) - return; - - for_each_pci_msi_entry(entry, pdev) { - if (!entry->irq) - continue; - hwirq = virq_to_hw(entry->irq); - irq_set_msi_desc(entry->irq, NULL); - irq_dispose_mapping(entry->irq); - } - - cxl_cx4_teardown_msi_irqs(pdev); -} diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c new file mode 100644 index 000000000000..6c5db1acbe8d --- /dev/null +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -0,0 +1,399 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * TCE helpers for IODA PCI/PCIe on PowerNV platforms + * + * Copyright 2018 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/iommu.h> + +#include <asm/iommu.h> +#include <asm/tce.h> +#include "pci.h" + +void pnv_pci_setup_iommu_table(struct iommu_table *tbl, + void *tce_mem, u64 tce_size, + u64 dma_offset, unsigned int page_shift) +{ + tbl->it_blocksize = 16; + tbl->it_base = (unsigned long)tce_mem; + tbl->it_page_shift = page_shift; + tbl->it_offset = dma_offset >> tbl->it_page_shift; + tbl->it_index = 0; + tbl->it_size = tce_size >> 3; + tbl->it_busno = 0; + tbl->it_type = TCE_PCI; +} + +static __be64 *pnv_alloc_tce_level(int nid, unsigned int shift) +{ + struct page *tce_mem = NULL; + __be64 *addr; + + tce_mem = alloc_pages_node(nid, GFP_KERNEL, shift - PAGE_SHIFT); + if (!tce_mem) { + pr_err("Failed to allocate a TCE memory, level shift=%d\n", + shift); + return NULL; + } + addr = page_address(tce_mem); + memset(addr, 0, 1UL << shift); + + return addr; +} + +static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc) +{ + __be64 *tmp = user ? tbl->it_userspace : (__be64 *) tbl->it_base; + int level = tbl->it_indirect_levels; + const long shift = ilog2(tbl->it_level_size); + unsigned long mask = (tbl->it_level_size - 1) << (level * shift); + + while (level) { + int n = (idx & mask) >> (level * shift); + unsigned long tce; + + if (tmp[n] == 0) { + __be64 *tmp2; + + if (!alloc) + return NULL; + + tmp2 = pnv_alloc_tce_level(tbl->it_nid, + ilog2(tbl->it_level_size) + 3); + if (!tmp2) + return NULL; + + tmp[n] = cpu_to_be64(__pa(tmp2) | + TCE_PCI_READ | TCE_PCI_WRITE); + } + tce = be64_to_cpu(tmp[n]); + + tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE)); + idx &= ~mask; + mask >>= shift; + --level; + } + + return tmp + idx; +} + +int pnv_tce_build(struct iommu_table *tbl, long index, long npages, + unsigned long uaddr, enum dma_data_direction direction, + unsigned long attrs) +{ + u64 proto_tce = iommu_direction_to_tce_perm(direction); + u64 rpn = __pa(uaddr) >> tbl->it_page_shift; + long i; + + if (proto_tce & TCE_PCI_WRITE) + proto_tce |= TCE_PCI_READ; + + for (i = 0; i < npages; i++) { + unsigned long newtce = proto_tce | + ((rpn + i) << tbl->it_page_shift); + unsigned long idx = index - tbl->it_offset + i; + + *(pnv_tce(tbl, false, idx, true)) = cpu_to_be64(newtce); + } + + return 0; +} + +#ifdef CONFIG_IOMMU_API +int pnv_tce_xchg(struct iommu_table *tbl, long index, + unsigned long *hpa, enum dma_data_direction *direction, + bool alloc) +{ + u64 proto_tce = iommu_direction_to_tce_perm(*direction); + unsigned long newtce = *hpa | proto_tce, oldtce; + unsigned long idx = index - tbl->it_offset; + __be64 *ptce = NULL; + + BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl)); + + if (*direction == DMA_NONE) { + ptce = pnv_tce(tbl, false, idx, false); + if (!ptce) { + *hpa = 0; + return 0; + } + } + + if (!ptce) { + ptce = pnv_tce(tbl, false, idx, alloc); + if (!ptce) + return alloc ? H_HARDWARE : H_TOO_HARD; + } + + if (newtce & TCE_PCI_WRITE) + newtce |= TCE_PCI_READ; + + oldtce = be64_to_cpu(xchg(ptce, cpu_to_be64(newtce))); + *hpa = oldtce & ~(TCE_PCI_READ | TCE_PCI_WRITE); + *direction = iommu_tce_direction(oldtce); + + return 0; +} + +__be64 *pnv_tce_useraddrptr(struct iommu_table *tbl, long index, bool alloc) +{ + if (WARN_ON_ONCE(!tbl->it_userspace)) + return NULL; + + return pnv_tce(tbl, true, index - tbl->it_offset, alloc); +} +#endif + +void pnv_tce_free(struct iommu_table *tbl, long index, long npages) +{ + long i; + + for (i = 0; i < npages; i++) { + unsigned long idx = index - tbl->it_offset + i; + __be64 *ptce = pnv_tce(tbl, false, idx, false); + + if (ptce) + *ptce = cpu_to_be64(0); + } +} + +unsigned long pnv_tce_get(struct iommu_table *tbl, long index) +{ + __be64 *ptce = pnv_tce(tbl, false, index - tbl->it_offset, false); + + if (!ptce) + return 0; + + return be64_to_cpu(*ptce); +} + +static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr, + unsigned long size, unsigned int levels) +{ + const unsigned long addr_ul = (unsigned long) addr & + ~(TCE_PCI_READ | TCE_PCI_WRITE); + + if (levels) { + long i; + u64 *tmp = (u64 *) addr_ul; + + for (i = 0; i < size; ++i) { + unsigned long hpa = be64_to_cpu(tmp[i]); + + if (!(hpa & (TCE_PCI_READ | TCE_PCI_WRITE))) + continue; + + pnv_pci_ioda2_table_do_free_pages(__va(hpa), size, + levels - 1); + } + } + + free_pages(addr_ul, get_order(size << 3)); +} + +void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl) +{ + const unsigned long size = tbl->it_indirect_levels ? + tbl->it_level_size : tbl->it_size; + + if (!tbl->it_size) + return; + + pnv_pci_ioda2_table_do_free_pages((__be64 *)tbl->it_base, size, + tbl->it_indirect_levels); + if (tbl->it_userspace) { + pnv_pci_ioda2_table_do_free_pages(tbl->it_userspace, size, + tbl->it_indirect_levels); + } +} + +static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned int shift, + unsigned int levels, unsigned long limit, + unsigned long *current_offset, unsigned long *total_allocated) +{ + __be64 *addr, *tmp; + unsigned long allocated = 1UL << shift; + unsigned int entries = 1UL << (shift - 3); + long i; + + addr = pnv_alloc_tce_level(nid, shift); + *total_allocated += allocated; + + --levels; + if (!levels) { + *current_offset += allocated; + return addr; + } + + for (i = 0; i < entries; ++i) { + tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift, + levels, limit, current_offset, total_allocated); + if (!tmp) + break; + + addr[i] = cpu_to_be64(__pa(tmp) | + TCE_PCI_READ | TCE_PCI_WRITE); + + if (*current_offset >= limit) + break; + } + + return addr; +} + +long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, + __u32 page_shift, __u64 window_size, __u32 levels, + bool alloc_userspace_copy, struct iommu_table *tbl) +{ + void *addr, *uas = NULL; + unsigned long offset = 0, level_shift, total_allocated = 0; + unsigned long total_allocated_uas = 0; + const unsigned int window_shift = ilog2(window_size); + unsigned int entries_shift = window_shift - page_shift; + unsigned int table_shift = max_t(unsigned int, entries_shift + 3, + PAGE_SHIFT); + const unsigned long tce_table_size = 1UL << table_shift; + unsigned int tmplevels = levels; + + if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS)) + return -EINVAL; + + if (!is_power_of_2(window_size)) + return -EINVAL; + + if (alloc_userspace_copy && (window_size > (1ULL << 32))) + tmplevels = 1; + + /* Adjust direct table size from window_size and levels */ + entries_shift = (entries_shift + levels - 1) / levels; + level_shift = entries_shift + 3; + level_shift = max_t(unsigned int, level_shift, PAGE_SHIFT); + + if ((level_shift - 3) * levels + page_shift >= 60) + return -EINVAL; + + /* Allocate TCE table */ + addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, + tmplevels, tce_table_size, &offset, &total_allocated); + + /* addr==NULL means that the first level allocation failed */ + if (!addr) + return -ENOMEM; + + /* + * First level was allocated but some lower level failed as + * we did not allocate as much as we wanted, + * release partially allocated table. + */ + if (tmplevels == levels && offset < tce_table_size) + goto free_tces_exit; + + /* Allocate userspace view of the TCE table */ + if (alloc_userspace_copy) { + offset = 0; + uas = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, + levels, tce_table_size, &offset, + &total_allocated_uas); + if (!uas) + goto free_tces_exit; + if (tmplevels == levels && (offset < tce_table_size || + total_allocated_uas != total_allocated)) + goto free_uas_exit; + } + + /* Setup linux iommu table */ + pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset, + page_shift); + tbl->it_level_size = 1ULL << (level_shift - 3); + tbl->it_indirect_levels = levels - 1; + tbl->it_allocated_size = total_allocated; + tbl->it_userspace = uas; + tbl->it_nid = nid; + + pr_debug("Created TCE table: ws=%08llx ts=%lx @%08llx base=%lx uas=%p levels=%d/%d\n", + window_size, tce_table_size, bus_offset, tbl->it_base, + tbl->it_userspace, tmplevels, levels); + + return 0; + +free_uas_exit: + pnv_pci_ioda2_table_do_free_pages(uas, + 1ULL << (level_shift - 3), levels - 1); +free_tces_exit: + pnv_pci_ioda2_table_do_free_pages(addr, + 1ULL << (level_shift - 3), levels - 1); + + return -ENOMEM; +} + +static void pnv_iommu_table_group_link_free(struct rcu_head *head) +{ + struct iommu_table_group_link *tgl = container_of(head, + struct iommu_table_group_link, rcu); + + kfree(tgl); +} + +void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, + struct iommu_table_group *table_group) +{ + long i; + bool found; + struct iommu_table_group_link *tgl; + + if (!tbl || !table_group) + return; + + /* Remove link to a group from table's list of attached groups */ + found = false; + list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) { + if (tgl->table_group == table_group) { + list_del_rcu(&tgl->next); + call_rcu(&tgl->rcu, pnv_iommu_table_group_link_free); + found = true; + break; + } + } + if (WARN_ON(!found)) + return; + + /* Clean a pointer to iommu_table in iommu_table_group::tables[] */ + found = false; + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + if (table_group->tables[i] == tbl) { + table_group->tables[i] = NULL; + found = true; + break; + } + } + WARN_ON(!found); +} + +long pnv_pci_link_table_and_group(int node, int num, + struct iommu_table *tbl, + struct iommu_table_group *table_group) +{ + struct iommu_table_group_link *tgl = NULL; + + if (WARN_ON(!tbl || !table_group)) + return -EINVAL; + + tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL, + node); + if (!tgl) + return -ENOMEM; + + tgl->table_group = table_group; + list_add_rcu(&tgl->next, &tbl->it_group_list); + + table_group->tables[num] = tbl; + + return 0; +} diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 5bd0eb6681bc..4e6302bf4073 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -46,17 +46,14 @@ #include "powernv.h" #include "pci.h" +#include "../../../../drivers/pci/pci.h" #define PNV_IODA1_M64_NUM 16 /* Number of M64 BARs */ #define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */ #define PNV_IODA1_DMA32_SEGSIZE 0x10000000 -#define POWERNV_IOMMU_DEFAULT_LEVELS 1 -#define POWERNV_IOMMU_MAX_LEVELS 5 - static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK", "NPU_OCAPI" }; -static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl); void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, const char *fmt, ...) @@ -2007,7 +2004,7 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index, static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index, unsigned long *hpa, enum dma_data_direction *direction) { - long ret = pnv_tce_xchg(tbl, index, hpa, direction); + long ret = pnv_tce_xchg(tbl, index, hpa, direction, true); if (!ret) pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, false); @@ -2018,7 +2015,7 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index, static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index, unsigned long *hpa, enum dma_data_direction *direction) { - long ret = pnv_tce_xchg(tbl, index, hpa, direction); + long ret = pnv_tce_xchg(tbl, index, hpa, direction, false); if (!ret) pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true); @@ -2040,6 +2037,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = { #ifdef CONFIG_IOMMU_API .exchange = pnv_ioda1_tce_xchg, .exchange_rm = pnv_ioda1_tce_xchg_rm, + .useraddrptr = pnv_tce_useraddrptr, #endif .clear = pnv_ioda1_tce_free, .get = pnv_tce_get, @@ -2171,7 +2169,7 @@ static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index, static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index, unsigned long *hpa, enum dma_data_direction *direction) { - long ret = pnv_tce_xchg(tbl, index, hpa, direction); + long ret = pnv_tce_xchg(tbl, index, hpa, direction, true); if (!ret) pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false); @@ -2182,7 +2180,7 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index, static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index, unsigned long *hpa, enum dma_data_direction *direction) { - long ret = pnv_tce_xchg(tbl, index, hpa, direction); + long ret = pnv_tce_xchg(tbl, index, hpa, direction, false); if (!ret) pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true); @@ -2199,20 +2197,16 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index, pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false); } -static void pnv_ioda2_table_free(struct iommu_table *tbl) -{ - pnv_pci_ioda2_table_free_pages(tbl); -} - static struct iommu_table_ops pnv_ioda2_iommu_ops = { .set = pnv_ioda2_tce_build, #ifdef CONFIG_IOMMU_API .exchange = pnv_ioda2_tce_xchg, .exchange_rm = pnv_ioda2_tce_xchg_rm, + .useraddrptr = pnv_tce_useraddrptr, #endif .clear = pnv_ioda2_tce_free, .get = pnv_tce_get, - .free = pnv_ioda2_table_free, + .free = pnv_pci_ioda2_table_free_pages, }; static int pnv_pci_ioda_dev_dma_weight(struct pci_dev *dev, void *data) @@ -2462,13 +2456,9 @@ void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable) pe->tce_bypass_enabled = enable; } -static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, - __u32 page_shift, __u64 window_size, __u32 levels, - struct iommu_table *tbl); - static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, int num, __u32 page_shift, __u64 window_size, __u32 levels, - struct iommu_table **ptbl) + bool alloc_userspace_copy, struct iommu_table **ptbl) { struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe, table_group); @@ -2485,7 +2475,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, ret = pnv_pci_ioda2_table_alloc_pages(nid, bus_offset, page_shift, window_size, - levels, tbl); + levels, alloc_userspace_copy, tbl); if (ret) { iommu_tce_table_put(tbl); return ret; @@ -2518,7 +2508,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) rc = pnv_pci_ioda2_create_table(&pe->table_group, 0, IOMMU_PAGE_SHIFT_4K, window_size, - POWERNV_IOMMU_DEFAULT_LEVELS, &tbl); + POWERNV_IOMMU_DEFAULT_LEVELS, false, &tbl); if (rc) { pe_err(pe, "Failed to create 32-bit TCE table, err %ld", rc); @@ -2605,7 +2595,16 @@ static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, tce_table_size, direct_table_size); } - return bytes; + return bytes + bytes; /* one for HW table, one for userspace copy */ +} + +static long pnv_pci_ioda2_create_table_userspace( + struct iommu_table_group *table_group, + int num, __u32 page_shift, __u64 window_size, __u32 levels, + struct iommu_table **ptbl) +{ + return pnv_pci_ioda2_create_table(table_group, + num, page_shift, window_size, levels, true, ptbl); } static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) @@ -2634,7 +2633,7 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) static struct iommu_table_group_ops pnv_pci_ioda2_ops = { .get_table_size = pnv_pci_ioda2_get_table_size, - .create_table = pnv_pci_ioda2_create_table, + .create_table = pnv_pci_ioda2_create_table_userspace, .set_window = pnv_pci_ioda2_set_window, .unset_window = pnv_pci_ioda2_unset_window, .take_ownership = pnv_ioda2_take_ownership, @@ -2739,7 +2738,7 @@ static void pnv_ioda2_npu_take_ownership(struct iommu_table_group *table_group) static struct iommu_table_group_ops pnv_pci_ioda2_npu_ops = { .get_table_size = pnv_pci_ioda2_get_table_size, - .create_table = pnv_pci_ioda2_create_table, + .create_table = pnv_pci_ioda2_create_table_userspace, .set_window = pnv_pci_ioda2_npu_set_window, .unset_window = pnv_pci_ioda2_npu_unset_window, .take_ownership = pnv_ioda2_npu_take_ownership, @@ -2773,144 +2772,6 @@ static void pnv_pci_ioda_setup_iommu_api(void) static void pnv_pci_ioda_setup_iommu_api(void) { }; #endif -static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift, - unsigned levels, unsigned long limit, - unsigned long *current_offset, unsigned long *total_allocated) -{ - struct page *tce_mem = NULL; - __be64 *addr, *tmp; - unsigned order = max_t(unsigned, shift, PAGE_SHIFT) - PAGE_SHIFT; - unsigned long allocated = 1UL << (order + PAGE_SHIFT); - unsigned entries = 1UL << (shift - 3); - long i; - - tce_mem = alloc_pages_node(nid, GFP_KERNEL, order); - if (!tce_mem) { - pr_err("Failed to allocate a TCE memory, order=%d\n", order); - return NULL; - } - addr = page_address(tce_mem); - memset(addr, 0, allocated); - *total_allocated += allocated; - - --levels; - if (!levels) { - *current_offset += allocated; - return addr; - } - - for (i = 0; i < entries; ++i) { - tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift, - levels, limit, current_offset, total_allocated); - if (!tmp) - break; - - addr[i] = cpu_to_be64(__pa(tmp) | - TCE_PCI_READ | TCE_PCI_WRITE); - - if (*current_offset >= limit) - break; - } - - return addr; -} - -static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr, - unsigned long size, unsigned level); - -static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, - __u32 page_shift, __u64 window_size, __u32 levels, - struct iommu_table *tbl) -{ - void *addr; - unsigned long offset = 0, level_shift, total_allocated = 0; - const unsigned window_shift = ilog2(window_size); - unsigned entries_shift = window_shift - page_shift; - unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT); - const unsigned long tce_table_size = 1UL << table_shift; - - if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS)) - return -EINVAL; - - if (!is_power_of_2(window_size)) - return -EINVAL; - - /* Adjust direct table size from window_size and levels */ - entries_shift = (entries_shift + levels - 1) / levels; - level_shift = entries_shift + 3; - level_shift = max_t(unsigned, level_shift, PAGE_SHIFT); - - if ((level_shift - 3) * levels + page_shift >= 60) - return -EINVAL; - - /* Allocate TCE table */ - addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, - levels, tce_table_size, &offset, &total_allocated); - - /* addr==NULL means that the first level allocation failed */ - if (!addr) - return -ENOMEM; - - /* - * First level was allocated but some lower level failed as - * we did not allocate as much as we wanted, - * release partially allocated table. - */ - if (offset < tce_table_size) { - pnv_pci_ioda2_table_do_free_pages(addr, - 1ULL << (level_shift - 3), levels - 1); - return -ENOMEM; - } - - /* Setup linux iommu table */ - pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset, - page_shift); - tbl->it_level_size = 1ULL << (level_shift - 3); - tbl->it_indirect_levels = levels - 1; - tbl->it_allocated_size = total_allocated; - - pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n", - window_size, tce_table_size, bus_offset); - - return 0; -} - -static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr, - unsigned long size, unsigned level) -{ - const unsigned long addr_ul = (unsigned long) addr & - ~(TCE_PCI_READ | TCE_PCI_WRITE); - - if (level) { - long i; - u64 *tmp = (u64 *) addr_ul; - - for (i = 0; i < size; ++i) { - unsigned long hpa = be64_to_cpu(tmp[i]); - - if (!(hpa & (TCE_PCI_READ | TCE_PCI_WRITE))) - continue; - - pnv_pci_ioda2_table_do_free_pages(__va(hpa), size, - level - 1); - } - } - - free_pages(addr_ul, get_order(size << 3)); -} - -static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl) -{ - const unsigned long size = tbl->it_indirect_levels ? - tbl->it_level_size : tbl->it_size; - - if (!tbl->it_size) - return; - - pnv_pci_ioda2_table_do_free_pages((__be64 *)tbl->it_base, size, - tbl->it_indirect_levels); -} - static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb) { struct pci_controller *hose = phb->hose; @@ -2925,7 +2786,7 @@ static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb) /* Add 16M for POWER8 by default */ if (cpu_has_feature(CPU_FTR_ARCH_207S) && !cpu_has_feature(CPU_FTR_ARCH_300)) - mask |= SZ_16M; + mask |= SZ_16M | SZ_256M; return mask; } @@ -3138,7 +2999,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) struct pci_dn *pdn; int mul, total_vfs; - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; pdn = pci_get_pdn(pdev); @@ -3575,7 +3436,7 @@ static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, /* Prevent enabling devices for which we couldn't properly * assign a PE */ -bool pnv_pci_enable_device_hook(struct pci_dev *dev) +static bool pnv_pci_enable_device_hook(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); struct pnv_phb *phb = hose->private_data; @@ -3843,26 +3704,6 @@ static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = { .shutdown = pnv_pci_ioda_shutdown, }; -#ifdef CONFIG_CXL_BASE -const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops = { - .dma_dev_setup = pnv_pci_dma_dev_setup, - .dma_bus_setup = pnv_pci_dma_bus_setup, -#ifdef CONFIG_PCI_MSI - .setup_msi_irqs = pnv_cxl_cx4_setup_msi_irqs, - .teardown_msi_irqs = pnv_cxl_cx4_teardown_msi_irqs, -#endif - .enable_device_hook = pnv_cxl_enable_device_hook, - .disable_device = pnv_cxl_disable_device, - .release_device = pnv_pci_release_device, - .window_alignment = pnv_pci_window_alignment, - .setup_bridge = pnv_pci_setup_bridge, - .reset_secondary_bus = pnv_pci_reset_secondary_bus, - .dma_set_mask = pnv_pci_ioda_dma_set_mask, - .dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask, - .shutdown = pnv_pci_ioda_shutdown, -}; -#endif - static void __init pnv_pci_init_ioda_phb(struct device_node *np, u64 hub_id, int ioda_type) { diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b265ecc0836a..13aef2323bbc 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -802,85 +802,6 @@ struct pci_ops pnv_pci_ops = { .write = pnv_pci_write_config, }; -static __be64 *pnv_tce(struct iommu_table *tbl, long idx) -{ - __be64 *tmp = ((__be64 *)tbl->it_base); - int level = tbl->it_indirect_levels; - const long shift = ilog2(tbl->it_level_size); - unsigned long mask = (tbl->it_level_size - 1) << (level * shift); - - while (level) { - int n = (idx & mask) >> (level * shift); - unsigned long tce = be64_to_cpu(tmp[n]); - - tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE)); - idx &= ~mask; - mask >>= shift; - --level; - } - - return tmp + idx; -} - -int pnv_tce_build(struct iommu_table *tbl, long index, long npages, - unsigned long uaddr, enum dma_data_direction direction, - unsigned long attrs) -{ - u64 proto_tce = iommu_direction_to_tce_perm(direction); - u64 rpn = __pa(uaddr) >> tbl->it_page_shift; - long i; - - if (proto_tce & TCE_PCI_WRITE) - proto_tce |= TCE_PCI_READ; - - for (i = 0; i < npages; i++) { - unsigned long newtce = proto_tce | - ((rpn + i) << tbl->it_page_shift); - unsigned long idx = index - tbl->it_offset + i; - - *(pnv_tce(tbl, idx)) = cpu_to_be64(newtce); - } - - return 0; -} - -#ifdef CONFIG_IOMMU_API -int pnv_tce_xchg(struct iommu_table *tbl, long index, - unsigned long *hpa, enum dma_data_direction *direction) -{ - u64 proto_tce = iommu_direction_to_tce_perm(*direction); - unsigned long newtce = *hpa | proto_tce, oldtce; - unsigned long idx = index - tbl->it_offset; - - BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl)); - - if (newtce & TCE_PCI_WRITE) - newtce |= TCE_PCI_READ; - - oldtce = be64_to_cpu(xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce))); - *hpa = oldtce & ~(TCE_PCI_READ | TCE_PCI_WRITE); - *direction = iommu_tce_direction(oldtce); - - return 0; -} -#endif - -void pnv_tce_free(struct iommu_table *tbl, long index, long npages) -{ - long i; - - for (i = 0; i < npages; i++) { - unsigned long idx = index - tbl->it_offset + i; - - *(pnv_tce(tbl, idx)) = cpu_to_be64(0); - } -} - -unsigned long pnv_tce_get(struct iommu_table *tbl, long index) -{ - return be64_to_cpu(*(pnv_tce(tbl, index - tbl->it_offset))); -} - struct iommu_table *pnv_pci_table_alloc(int nid) { struct iommu_table *tbl; @@ -895,85 +816,6 @@ struct iommu_table *pnv_pci_table_alloc(int nid) return tbl; } -long pnv_pci_link_table_and_group(int node, int num, - struct iommu_table *tbl, - struct iommu_table_group *table_group) -{ - struct iommu_table_group_link *tgl = NULL; - - if (WARN_ON(!tbl || !table_group)) - return -EINVAL; - - tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL, - node); - if (!tgl) - return -ENOMEM; - - tgl->table_group = table_group; - list_add_rcu(&tgl->next, &tbl->it_group_list); - - table_group->tables[num] = tbl; - - return 0; -} - -static void pnv_iommu_table_group_link_free(struct rcu_head *head) -{ - struct iommu_table_group_link *tgl = container_of(head, - struct iommu_table_group_link, rcu); - - kfree(tgl); -} - -void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, - struct iommu_table_group *table_group) -{ - long i; - bool found; - struct iommu_table_group_link *tgl; - - if (!tbl || !table_group) - return; - - /* Remove link to a group from table's list of attached groups */ - found = false; - list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) { - if (tgl->table_group == table_group) { - list_del_rcu(&tgl->next); - call_rcu(&tgl->rcu, pnv_iommu_table_group_link_free); - found = true; - break; - } - } - if (WARN_ON(!found)) - return; - - /* Clean a pointer to iommu_table in iommu_table_group::tables[] */ - found = false; - for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { - if (table_group->tables[i] == tbl) { - table_group->tables[i] = NULL; - found = true; - break; - } - } - WARN_ON(!found); -} - -void pnv_pci_setup_iommu_table(struct iommu_table *tbl, - void *tce_mem, u64 tce_size, - u64 dma_offset, unsigned page_shift) -{ - tbl->it_blocksize = 16; - tbl->it_base = (unsigned long)tce_mem; - tbl->it_page_shift = page_shift; - tbl->it_offset = dma_offset >> tbl->it_page_shift; - tbl->it_index = 0; - tbl->it_size = tce_size >> 3; - tbl->it_busno = 0; - tbl->it_type = TCE_PCI; -} - void pnv_pci_dma_dev_setup(struct pci_dev *pdev) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index eada4b6068cb..8b37b28e3831 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -88,7 +88,6 @@ struct pnv_ioda_pe { }; #define PNV_PHB_FLAG_EEH (1 << 0) -#define PNV_PHB_FLAG_CXL (1 << 1) /* Real PHB supporting the cxl kernel API */ struct pnv_phb { struct pci_controller *hose; @@ -194,20 +193,10 @@ struct pnv_phb { bool nmmu_flush; } npu; -#ifdef CONFIG_CXL_BASE - struct cxl_afu *cxl_afu; -#endif int p2p_target_count; }; extern struct pci_ops pnv_pci_ops; -extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages, - unsigned long uaddr, enum dma_data_direction direction, - unsigned long attrs); -extern void pnv_tce_free(struct iommu_table *tbl, long index, long npages); -extern int pnv_tce_xchg(struct iommu_table *tbl, long index, - unsigned long *hpa, enum dma_data_direction *direction); -extern unsigned long pnv_tce_get(struct iommu_table *tbl, long index); void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, unsigned char *log_buff); @@ -217,14 +206,6 @@ int pnv_pci_cfg_write(struct pci_dn *pdn, int where, int size, u32 val); extern struct iommu_table *pnv_pci_table_alloc(int nid); -extern long pnv_pci_link_table_and_group(int node, int num, - struct iommu_table *tbl, - struct iommu_table_group *table_group); -extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, - struct iommu_table_group *table_group); -extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, - void *tce_mem, u64 tce_size, - u64 dma_offset, unsigned page_shift); extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_init_npu_phb(struct device_node *np); @@ -238,7 +219,6 @@ extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev); extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq); -extern bool pnv_pci_enable_device_hook(struct pci_dev *dev); extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable); extern int pnv_eeh_post_init(void); @@ -262,14 +242,33 @@ extern void pnv_npu_take_ownership(struct pnv_ioda_pe *npe); extern void pnv_npu_release_ownership(struct pnv_ioda_pe *npe); extern int pnv_npu2_init(struct pnv_phb *phb); -/* cxl functions */ -extern bool pnv_cxl_enable_device_hook(struct pci_dev *dev); -extern void pnv_cxl_disable_device(struct pci_dev *dev); -extern int pnv_cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); -extern void pnv_cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev); +/* pci-ioda-tce.c */ +#define POWERNV_IOMMU_DEFAULT_LEVELS 1 +#define POWERNV_IOMMU_MAX_LEVELS 5 +extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages, + unsigned long uaddr, enum dma_data_direction direction, + unsigned long attrs); +extern void pnv_tce_free(struct iommu_table *tbl, long index, long npages); +extern int pnv_tce_xchg(struct iommu_table *tbl, long index, + unsigned long *hpa, enum dma_data_direction *direction, + bool alloc); +extern __be64 *pnv_tce_useraddrptr(struct iommu_table *tbl, long index, + bool alloc); +extern unsigned long pnv_tce_get(struct iommu_table *tbl, long index); + +extern long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, + __u32 page_shift, __u64 window_size, __u32 levels, + bool alloc_userspace_copy, struct iommu_table *tbl); +extern void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl); -/* phb ops (cxl switches these when enabling the kernel api on the phb) */ -extern const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops; +extern long pnv_pci_link_table_and_group(int node, int num, + struct iommu_table *tbl, + struct iommu_table_group *table_group); +extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, + struct iommu_table_group *table_group); +extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, + void *tce_mem, u64 tce_size, + u64 dma_offset, unsigned int page_shift); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index f96df0a25d05..adddde023622 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -78,6 +78,12 @@ static void init_fw_feat_flags(struct device_node *np) if (fw_feature_is("enabled", "fw-count-cache-disabled", np)) security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED); + if (fw_feature_is("enabled", "fw-count-cache-flush-bcctr2,0,0", np)) + security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST); + + if (fw_feature_is("enabled", "needs-count-cache-flush-on-context-switch", np)) + security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE); + /* * The features below are enabled by default, so we instead look to see * if firmware has *disabled* them, and clear them if so. @@ -124,7 +130,7 @@ static void pnv_setup_rfi_flush(void) security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV)); setup_rfi_flush(type, enable); - setup_barrier_nospec(); + setup_count_cache_flush(); } static void __init pnv_setup_arch(void) @@ -314,7 +320,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) u64 reinit_flags; if (xive_enabled()) - xive_kexec_teardown_cpu(secondary); + xive_teardown_cpu(); else xics_kexec_teardown_cpu(secondary); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index b80909957792..0d354e19ef92 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -283,23 +283,6 @@ static void pnv_cause_ipi(int cpu) ic_cause_ipi(cpu); } -static void pnv_p9_dd1_cause_ipi(int cpu) -{ - int this_cpu = get_cpu(); - - /* - * POWER9 DD1 has a global addressed msgsnd, but for now we restrict - * IPIs to same core, because it requires additional synchronization - * for inter-core doorbells which we do not implement. - */ - if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) - doorbell_global_ipi(cpu); - else - ic_cause_ipi(cpu); - - put_cpu(); -} - static void __init pnv_smp_probe(void) { if (xive_enabled()) @@ -311,14 +294,10 @@ static void __init pnv_smp_probe(void) ic_cause_ipi = smp_ops->cause_ipi; WARN_ON(!ic_cause_ipi); - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - smp_ops->cause_ipi = pnv_p9_dd1_cause_ipi; - else - smp_ops->cause_ipi = doorbell_global_ipi; - } else { + if (cpu_has_feature(CPU_FTR_ARCH_300)) + smp_ops->cause_ipi = doorbell_global_ipi; + else smp_ops->cause_ipi = pnv_cause_ipi; - } } } diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h index ae0100fd35bb..f5493dbdd7ff 100644 --- a/arch/powerpc/platforms/powernv/vas.h +++ b/arch/powerpc/platforms/powernv/vas.h @@ -15,6 +15,7 @@ #include <linux/io.h> #include <linux/dcache.h> #include <linux/mutex.h> +#include <linux/stringify.h> /* * Overview of Virtual Accelerator Switchboard (VAS). diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 13eede60c24d..7e89d5c47068 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -25,6 +25,6 @@ obj-$(CONFIG_LPARCFG) += lparcfg.o obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_IBMEBUS) += ibmebus.o -ifeq ($(CONFIG_PPC_PSERIES),y) +ifdef CONFIG_PPC_PSERIES obj-$(CONFIG_SUSPEND) += suspend.o endif diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index c511a1743a44..d91412c591ef 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -13,6 +13,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> +#include <asm/feature-fixups.h> .section ".text" diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 46fbaef69a59..23f54223ed56 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -58,7 +58,7 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary) } if (xive_enabled()) { - xive_kexec_teardown_cpu(secondary); + xive_teardown_cpu(); if (!secondary) xive_shutdown(); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 5a392e40f3d2..d3992ced0782 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -21,6 +21,7 @@ /* Enables debugging of low-level hash table routines - careful! */ #undef DEBUG +#define pr_fmt(fmt) "lpar: " fmt #include <linux/kernel.h> #include <linux/dma-mapping.h> @@ -36,7 +37,6 @@ #include <asm/machdep.h> #include <asm/mmu_context.h> #include <asm/iommu.h> -#include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/prom.h> #include <asm/cputable.h> @@ -165,8 +165,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, lpar_rc = plpar_pte_enter(flags, hpte_group, hpte_v, hpte_r, &slot); if (unlikely(lpar_rc == H_PTEG_FULL)) { - if (!(vflags & HPTE_V_BOLTED)) - pr_devel(" full\n"); + pr_devel("Hash table group is full\n"); return -1; } @@ -176,8 +175,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, * or we will loop forever, so return -2 in this case. */ if (unlikely(lpar_rc != H_SUCCESS)) { - if (!(vflags & HPTE_V_BOLTED)) - pr_devel(" lpar err %ld\n", lpar_rc); + pr_err("Failed hash pte insert with error %ld\n", lpar_rc); return -2; } if (!(vflags & HPTE_V_BOLTED)) @@ -240,8 +238,11 @@ static void manual_hpte_clear_all(void) */ for (i = 0; i < hpte_count; i += 4) { lpar_rc = plpar_pte_read_4_raw(0, i, (void *)ptes); - if (lpar_rc != H_SUCCESS) + if (lpar_rc != H_SUCCESS) { + pr_info("Failed to read hash page table at %ld err %ld\n", + i, lpar_rc); continue; + } for (j = 0; j < 4; j++){ if ((ptes[j].pteh & HPTE_V_VRMA_MASK) == HPTE_V_VRMA_MASK) @@ -340,8 +341,11 @@ static long __pSeries_lpar_hpte_find(unsigned long want_v, unsigned long hpte_gr for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) { lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes); - if (lpar_rc != H_SUCCESS) + if (lpar_rc != H_SUCCESS) { + pr_info("Failed to read hash page table at %ld err %ld\n", + hpte_group, lpar_rc); continue; + } for (j = 0; j < 4; j++) { if (HPTE_V_COMPARE(ptes[j].pteh, want_v) && @@ -612,8 +616,8 @@ static int __init disable_bulk_remove(char *str) { if (strcmp(str, "off") == 0 && firmware_has_feature(FW_FEATURE_BULK_REMOVE)) { - printk(KERN_INFO "Disabling BULK_REMOVE firmware feature"); - powerpc_firmware_features &= ~FW_FEATURE_BULK_REMOVE; + pr_info("Disabling BULK_REMOVE firmware feature"); + powerpc_firmware_features &= ~FW_FEATURE_BULK_REMOVE; } return 1; } @@ -659,8 +663,7 @@ static int pseries_lpar_resize_hpt(unsigned long shift) if (!firmware_has_feature(FW_FEATURE_HPT_RESIZE)) return -ENODEV; - printk(KERN_INFO "lpar: Attempting to resize HPT to shift %lu\n", - shift); + pr_info("Attempting to resize HPT to shift %lu\n", shift); t0 = ktime_get(); @@ -672,8 +675,7 @@ static int pseries_lpar_resize_hpt(unsigned long shift) /* prepare with shift==0 cancels an in-progress resize */ rc = plpar_resize_hpt_prepare(0, 0); if (rc != H_SUCCESS) - printk(KERN_WARNING - "lpar: Unexpected error %d cancelling timed out HPT resize\n", + pr_warn("Unexpected error %d cancelling timed out HPT resize\n", rc); return -ETIMEDOUT; } @@ -691,9 +693,7 @@ static int pseries_lpar_resize_hpt(unsigned long shift) case H_RESOURCE: return -EPERM; default: - printk(KERN_WARNING - "lpar: Unexpected error %d from H_RESIZE_HPT_PREPARE\n", - rc); + pr_warn("Unexpected error %d from H_RESIZE_HPT_PREPARE\n", rc); return -EIO; } @@ -706,22 +706,19 @@ static int pseries_lpar_resize_hpt(unsigned long shift) if (rc != 0) { switch (state.commit_rc) { case H_PTEG_FULL: - printk(KERN_WARNING - "lpar: Hash collision while resizing HPT\n"); + pr_warn("Hash collision while resizing HPT\n"); return -ENOSPC; default: - printk(KERN_WARNING - "lpar: Unexpected error %d from H_RESIZE_HPT_COMMIT\n", - state.commit_rc); + pr_warn("Unexpected error %d from H_RESIZE_HPT_COMMIT\n", + state.commit_rc); return -EIO; }; } - printk(KERN_INFO - "lpar: HPT resize to shift %lu complete (%lld ms / %lld ms)\n", - shift, (long long) ktime_ms_delta(t1, t0), - (long long) ktime_ms_delta(t2, t1)); + pr_info("HPT resize to shift %lu complete (%lld ms / %lld ms)\n", + shift, (long long) ktime_ms_delta(t1, t0), + (long long) ktime_ms_delta(t2, t1)); return 0; } @@ -785,13 +782,13 @@ static int __init cmo_free_hint(char *str) parm = strstrip(str); if (strcasecmp(parm, "no") == 0 || strcasecmp(parm, "off") == 0) { - printk(KERN_INFO "cmo_free_hint: CMO free page hinting is not active.\n"); + pr_info("%s: CMO free page hinting is not active.\n", __func__); cmo_free_hint_flag = 0; return 1; } cmo_free_hint_flag = 1; - printk(KERN_INFO "cmo_free_hint: CMO free page hinting is active.\n"); + pr_info("%s: CMO free page hinting is active.\n", __func__); if (strcasecmp(parm, "yes") == 0 || strcasecmp(parm, "on") == 0) return 1; diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 8a8033a249c7..f0e30dc94988 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -17,6 +17,7 @@ #include <linux/device.h> #include <linux/delay.h> #include <linux/slab.h> +#include <linux/stringify.h> #include <asm/machdep.h> #include <asm/rtas.h> diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 5e1ef9150182..851ce326874a 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -22,6 +22,7 @@ #include <linux/of.h> #include <linux/fs.h> #include <linux/reboot.h> +#include <linux/irq_work.h> #include <asm/machdep.h> #include <asm/rtas.h> @@ -32,11 +33,13 @@ static unsigned char ras_log_buf[RTAS_ERROR_LOG_MAX]; static DEFINE_SPINLOCK(ras_log_buf_lock); -static char global_mce_data_buf[RTAS_ERROR_LOG_MAX]; -static DEFINE_PER_CPU(__u64, mce_data_buf); - static int ras_check_exception_token; +static void mce_process_errlog_event(struct irq_work *work); +static struct irq_work mce_errlog_process_work = { + .func = mce_process_errlog_event, +}; + #define EPOW_SENSOR_TOKEN 9 #define EPOW_SENSOR_INDEX 0 @@ -330,16 +333,20 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) ((((A) >= 0x7000) && ((A) < 0x7ff0)) || \ (((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16)))) +static inline struct rtas_error_log *fwnmi_get_errlog(void) +{ + return (struct rtas_error_log *)local_paca->mce_data_buf; +} + /* * Get the error information for errors coming through the * FWNMI vectors. The pt_regs' r3 will be updated to reflect * the actual r3 if possible, and a ptr to the error log entry * will be returned if found. * - * If the RTAS error is not of the extended type, then we put it in a per - * cpu 64bit buffer. If it is the extended type we use global_mce_data_buf. + * Use one buffer mce_data_buf per cpu to store RTAS error. * - * The global_mce_data_buf does not have any locks or protection around it, + * The mce_data_buf does not have any locks or protection around it, * if a second machine check comes in, or a system reset is done * before we have logged the error, then we will get corruption in the * error log. This is preferable over holding off on calling @@ -349,7 +356,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) { unsigned long *savep; - struct rtas_error_log *h, *errhdr = NULL; + struct rtas_error_log *h; /* Mask top two bits */ regs->gpr[3] &= ~(0x3UL << 62); @@ -360,24 +367,22 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) } savep = __va(regs->gpr[3]); - regs->gpr[3] = savep[0]; /* restore original r3 */ + regs->gpr[3] = be64_to_cpu(savep[0]); /* restore original r3 */ - /* If it isn't an extended log we can use the per cpu 64bit buffer */ h = (struct rtas_error_log *)&savep[1]; + /* Use the per cpu buffer from paca to store rtas error log */ + memset(local_paca->mce_data_buf, 0, RTAS_ERROR_LOG_MAX); if (!rtas_error_extended(h)) { - memcpy(this_cpu_ptr(&mce_data_buf), h, sizeof(__u64)); - errhdr = (struct rtas_error_log *)this_cpu_ptr(&mce_data_buf); + memcpy(local_paca->mce_data_buf, h, sizeof(__u64)); } else { int len, error_log_length; error_log_length = 8 + rtas_error_extended_log_length(h); - len = max_t(int, error_log_length, RTAS_ERROR_LOG_MAX); - memset(global_mce_data_buf, 0, RTAS_ERROR_LOG_MAX); - memcpy(global_mce_data_buf, h, len); - errhdr = (struct rtas_error_log *)global_mce_data_buf; + len = min_t(int, error_log_length, RTAS_ERROR_LOG_MAX); + memcpy(local_paca->mce_data_buf, h, len); } - return errhdr; + return (struct rtas_error_log *)local_paca->mce_data_buf; } /* Call this when done with the data returned by FWNMI_get_errinfo. @@ -423,6 +428,17 @@ int pSeries_system_reset_exception(struct pt_regs *regs) } /* + * Process MCE rtas errlog event. + */ +static void mce_process_errlog_event(struct irq_work *work) +{ + struct rtas_error_log *err; + + err = fwnmi_get_errlog(); + log_error((char *)err, ERR_TYPE_RTAS_LOG, 0); +} + +/* * See if we can recover from a machine check exception. * This is only called on power4 (or above) and only via * the Firmware Non-Maskable Interrupts (fwnmi) handler @@ -466,7 +482,8 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) recovered = 1; } - log_error((char *)err, ERR_TYPE_RTAS_LOG, 0); + /* Queue irq work to log this rtas event later. */ + irq_work_queue(&mce_errlog_process_work); return recovered; } diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 139f0af6c3d9..ba1791fd3234 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -41,6 +41,7 @@ #include <linux/root_dev.h> #include <linux/of.h> #include <linux/of_pci.h> +#include <linux/memblock.h> #include <asm/mmu.h> #include <asm/processor.h> @@ -69,8 +70,10 @@ #include <asm/kexec.h> #include <asm/isa-bridge.h> #include <asm/security_features.h> +#include <asm/asm-const.h> #include "pseries.h" +#include "../../../../drivers/pci/pci.h" int CMO_PrPSP = -1; int CMO_SecPSP = -1; @@ -101,6 +104,9 @@ static void pSeries_show_cpuinfo(struct seq_file *m) static void __init fwnmi_init(void) { unsigned long system_reset_addr, machine_check_addr; + u8 *mce_data_buf; + unsigned int i; + int nr_cpus = num_possible_cpus(); int ibm_nmi_register = rtas_token("ibm,nmi-register"); if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE) @@ -114,6 +120,18 @@ static void __init fwnmi_init(void) if (0 == rtas_call(ibm_nmi_register, 2, 1, NULL, system_reset_addr, machine_check_addr)) fwnmi_active = 1; + + /* + * Allocate a chunk for per cpu buffer to hold rtas errorlog. + * It will be used in real mode mce handler, hence it needs to be + * below RMA. + */ + mce_data_buf = __va(memblock_alloc_base(RTAS_ERROR_LOG_MAX * nr_cpus, + RTAS_ERROR_LOG_MAX, ppc64_rma_size)); + for_each_possible_cpu(i) { + paca_ptrs[i]->mce_data_buf = mce_data_buf + + (RTAS_ERROR_LOG_MAX * i); + } } static void pseries_8259_cascade(struct irq_desc *desc) @@ -484,6 +502,12 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) if (result->character & H_CPU_CHAR_COUNT_CACHE_DISABLED) security_ftr_set(SEC_FTR_COUNT_CACHE_DISABLED); + if (result->character & H_CPU_CHAR_BCCTR_FLUSH_ASSIST) + security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST); + + if (result->behaviour & H_CPU_BEHAV_FLUSH_COUNT_CACHE) + security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE); + /* * The features below are enabled by default, so we instead look to see * if firmware has *disabled* them, and clear them if so. @@ -534,7 +558,7 @@ void pseries_setup_rfi_flush(void) security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR); setup_rfi_flush(types, enable); - setup_barrier_nospec(); + setup_count_cache_flush(); } #ifdef CONFIG_PCI_IOV @@ -646,6 +670,15 @@ void of_pci_parse_iov_addrs(struct pci_dev *dev, const int *indexes) } } +static void pseries_disable_sriov_resources(struct pci_dev *pdev) +{ + int i; + + pci_warn(pdev, "No hypervisor support for SR-IOV on this device, IOV BARs disabled.\n"); + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) + pdev->resource[i + PCI_IOV_RESOURCES].flags = 0; +} + static void pseries_pci_fixup_resources(struct pci_dev *pdev) { const int *indexes; @@ -653,10 +686,10 @@ static void pseries_pci_fixup_resources(struct pci_dev *pdev) /*Firmware must support open sriov otherwise dont configure*/ indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL); - if (!indexes) - return; - /* Assign the addresses from device tree*/ - of_pci_set_vf_bar_size(pdev, indexes); + if (indexes) + of_pci_set_vf_bar_size(pdev, indexes); + else + pseries_disable_sriov_resources(pdev); } static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev) @@ -664,14 +697,14 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev) const int *indexes; struct device_node *dn = pci_device_to_OF_node(pdev); - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; /*Firmware must support open sriov otherwise dont configure*/ indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL); - if (!indexes) - return; - /* Assign the addresses from device tree*/ - of_pci_parse_iov_addrs(pdev, indexes); + if (indexes) + of_pci_parse_iov_addrs(pdev, indexes); + else + pseries_disable_sriov_resources(pdev); } static resource_size_t pseries_pci_iov_resource_alignment(struct pci_dev *pdev, diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile index 30e05decbb4c..4314ba5baf43 100644 --- a/arch/powerpc/purgatory/Makefile +++ b/arch/powerpc/purgatory/Makefile @@ -6,9 +6,8 @@ LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined $(obj)/purgatory.ro: $(obj)/trampoline.o FORCE $(call if_changed,ld) -CMD_BIN2C = $(objtree)/scripts/basic/bin2c quiet_cmd_bin2c = BIN2C $@ - cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@ + cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@ $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE $(call if_changed,bin2c) diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S index 4aad9dd10ace..1e1129553fd7 100644 --- a/arch/powerpc/purgatory/trampoline.S +++ b/arch/powerpc/purgatory/trampoline.S @@ -12,15 +12,7 @@ * Software Foundation (version 2 of the License). */ -#if defined(__LITTLE_ENDIAN__) -#define STWX_BE stwbrx -#define LWZX_BE lwbrx -#elif defined(__BIG_ENDIAN__) -#define STWX_BE stwx -#define LWZX_BE lwzx -#else -#error no endianness defined! -#endif +#include <asm/asm-compat.h> .machine ppc64 .balign 256 diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index ea2f595b5133..f730539074c4 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -48,7 +48,7 @@ obj-$(CONFIG_UCODE_PATCH) += micropatch.o obj-$(CONFIG_PPC_MPC512x) += mpc5xxx_clocks.o obj-$(CONFIG_PPC_MPC52xx) += mpc5xxx_clocks.o -ifeq ($(CONFIG_SUSPEND),y) +ifdef CONFIG_SUSPEND obj-$(CONFIG_6xx) += 6xx-suspend.o endif diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index 5240d3a74a10..4f8dcf124828 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -38,7 +38,6 @@ #include <asm/8xx_immap.h> #include <asm/cpm1.h> #include <asm/io.h> -#include <asm/tlbflush.h> #include <asm/rheap.h> #include <asm/prom.h> #include <asm/cpm.h> diff --git a/arch/powerpc/sysdev/fsl_mpic_err.c b/arch/powerpc/sysdev/fsl_mpic_err.c index 488ec453038a..2a98837dc6ba 100644 --- a/arch/powerpc/sysdev/fsl_mpic_err.c +++ b/arch/powerpc/sysdev/fsl_mpic_err.c @@ -76,7 +76,7 @@ int mpic_setup_error_int(struct mpic *mpic, int intvec) mpic->flags |= MPIC_FSL_HAS_EIMR; /* allocate interrupt vectors for error interrupts */ for (i = MPIC_MAX_ERR - 1; i >= 0; i--) - mpic->err_int_vecs[i] = --intvec; + mpic->err_int_vecs[i] = intvec--; return 0; } diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 353b43972bbf..934a77324f6b 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1380,12 +1380,12 @@ struct mpic * __init mpic_alloc(struct device_node *node, * global vector number space, as in case of ipis * and timer interrupts. * - * Available vector space = intvec_top - 12, where 12 + * Available vector space = intvec_top - 13, where 13 * is the number of vectors which have been consumed by - * ipis and timer interrupts. + * ipis, timer interrupts and spurious. */ if (fsl_version >= 0x401) { - ret = mpic_setup_error_int(mpic, intvec_top - 12); + ret = mpic_setup_error_int(mpic, intvec_top - 13); if (ret) return NULL; } diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index eb69a5186243..280e964e1aa8 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -196,7 +196,7 @@ static int mpic_msgr_probe(struct platform_device *dev) /* IO map the message register block. */ of_address_to_resource(np, 0, &rsrc); - msgr_block_addr = ioremap(rsrc.start, rsrc.end - rsrc.start); + msgr_block_addr = ioremap(rsrc.start, resource_size(&rsrc)); if (!msgr_block_addr) { dev_err(&dev->dev, "Failed to iomap MPIC message registers"); return -EFAULT; diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 6243a7e537d0..e64a411d1a00 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -225,22 +225,23 @@ static void __init test_of_node(void) struct device_node of_node; struct property prop; struct msi_bitmap bmp; - int size = 256; - DECLARE_BITMAP(expected, size); +#define SIZE_EXPECTED 256 + DECLARE_BITMAP(expected, SIZE_EXPECTED); /* There should really be a struct device_node allocator */ memset(&of_node, 0, sizeof(of_node)); of_node_init(&of_node); of_node.full_name = node_name; - WARN_ON(msi_bitmap_alloc(&bmp, size, &of_node)); + WARN_ON(msi_bitmap_alloc(&bmp, SIZE_EXPECTED, &of_node)); /* No msi-available-ranges, so expect > 0 */ WARN_ON(msi_bitmap_reserve_dt_hwirqs(&bmp) <= 0); /* Should all still be free */ - WARN_ON(bitmap_find_free_region(bmp.bitmap, size, get_count_order(size))); - bitmap_release_region(bmp.bitmap, 0, get_count_order(size)); + WARN_ON(bitmap_find_free_region(bmp.bitmap, SIZE_EXPECTED, + get_count_order(SIZE_EXPECTED))); + bitmap_release_region(bmp.bitmap, 0, get_count_order(SIZE_EXPECTED)); /* Now create a fake msi-available-ranges property */ @@ -256,8 +257,8 @@ static void __init test_of_node(void) WARN_ON(msi_bitmap_reserve_dt_hwirqs(&bmp)); /* Check we got the expected result */ - WARN_ON(bitmap_parselist(expected_str, expected, size)); - WARN_ON(!bitmap_equal(expected, bmp.bitmap, size)); + WARN_ON(bitmap_parselist(expected_str, expected, SIZE_EXPECTED)); + WARN_ON(!bitmap_equal(expected, bmp.bitmap, SIZE_EXPECTED)); msi_bitmap_free(&bmp); kfree(bmp.bitmap); diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 3459015092fa..e8f5b0551095 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -319,7 +319,7 @@ void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) * The FW told us to call it. This happens for some * interrupt sources that need additional HW whacking * beyond the ESB manipulation. For example LPC interrupts - * on P9 DD1.0 need a latch to be clared in the LPC bridge + * on P9 DD1.0 needed a latch to be clared in the LPC bridge * itself. The Firmware will take care of it. */ if (WARN_ON_ONCE(!xive_ops->eoi)) @@ -337,9 +337,9 @@ void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) * This allows us to then do a re-trigger if Q was set * rather than synthesizing an interrupt in software * - * For LSIs, using the HW EOI cycle works around a problem - * on P9 DD1 PHBs where the other ESB accesses don't work - * properly. + * For LSIs the HW EOI cycle is used rather than PQ bits, + * as they are automatically re-triggred in HW when still + * pending. */ if (xd->flags & XIVE_IRQ_FLAG_LSI) xive_esb_read(xd, XIVE_ESB_LOAD_EOI); @@ -1408,28 +1408,6 @@ void xive_teardown_cpu(void) xive_cleanup_cpu_queues(cpu, xc); } -void xive_kexec_teardown_cpu(int secondary) -{ - struct xive_cpu *xc = __this_cpu_read(xive_cpu); - unsigned int cpu = smp_processor_id(); - - /* Set CPPR to 0 to disable flow of interrupts */ - xc->cppr = 0; - out_8(xive_tima + xive_tima_offset + TM_CPPR, 0); - - /* Backend cleanup if any */ - if (xive_ops->teardown_cpu) - xive_ops->teardown_cpu(cpu, xc); - -#ifdef CONFIG_SMP - /* Get rid of IPI */ - xive_cleanup_cpu_ipi(cpu, xc); -#endif - - /* Disable and free the queues */ - xive_cleanup_cpu_queues(cpu, xc); -} - void xive_shutdown(void) { xive_ops->shutdown(); diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 311185b9960a..5b20a678d755 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -109,7 +109,7 @@ int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq) rc = opal_xive_set_irq_config(hw_irq, target, prio, sw_irq); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } return rc == 0 ? 0 : -ENXIO; } @@ -163,7 +163,7 @@ int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio, rc = opal_xive_set_queue_info(vp_id, prio, qpage_phys, order, flags); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } if (rc) { pr_err("Error %lld setting queue for prio %d\n", rc, prio); @@ -190,7 +190,7 @@ static void __xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio) rc = opal_xive_set_queue_info(vp_id, prio, 0, 0, 0); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } if (rc) pr_err("Error %lld disabling queue for prio %d\n", rc, prio); @@ -253,7 +253,7 @@ static int xive_native_get_ipi(unsigned int cpu, struct xive_cpu *xc) for (;;) { irq = opal_xive_allocate_irq(chip_id); if (irq == OPAL_BUSY) { - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); continue; } if (irq < 0) { @@ -275,7 +275,7 @@ u32 xive_native_alloc_irq(void) rc = opal_xive_allocate_irq(OPAL_XIVE_ANY_CHIP); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } if (rc < 0) return 0; @@ -289,7 +289,7 @@ void xive_native_free_irq(u32 irq) s64 rc = opal_xive_free_irq(irq); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } } EXPORT_SYMBOL_GPL(xive_native_free_irq); @@ -305,7 +305,7 @@ static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc) for (;;) { rc = opal_xive_free_irq(xc->hw_ipi); if (rc == OPAL_BUSY) { - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); continue; } xc->hw_ipi = 0; @@ -395,12 +395,11 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc) /* Enable the pool VP */ vp = xive_pool_vps + cpu; - pr_debug("CPU %d setting up pool VP 0x%x\n", cpu, vp); for (;;) { rc = opal_xive_set_vp_info(vp, OPAL_XIVE_VP_ENABLED, 0); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } if (rc) { pr_err("Failed to enable pool VP on CPU %d\n", cpu); @@ -415,16 +414,9 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc) } vp_cam = be64_to_cpu(vp_cam_be); - pr_debug("VP CAM = %llx\n", vp_cam); - /* Push it on the CPU (set LSMFB to 0xff to skip backlog scan) */ - pr_debug("(Old HW value: %08x)\n", - in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2)); out_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD0, 0xff); - out_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2, - TM_QW2W2_VP | vp_cam); - pr_debug("(New HW value: %08x)\n", - in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2)); + out_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2, TM_QW2W2_VP | vp_cam); } static void xive_native_teardown_cpu(unsigned int cpu, struct xive_cpu *xc) @@ -444,7 +436,7 @@ static void xive_native_teardown_cpu(unsigned int cpu, struct xive_cpu *xc) rc = opal_xive_set_vp_info(vp, 0, 0); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } } @@ -645,7 +637,7 @@ u32 xive_native_alloc_vp_block(u32 max_vcpus) rc = opal_xive_alloc_vp_block(order); switch (rc) { case OPAL_BUSY: - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); break; case OPAL_XIVE_PROVISIONING: if (!xive_native_provision_pages()) @@ -687,7 +679,7 @@ int xive_native_enable_vp(u32 vp_id, bool single_escalation) rc = opal_xive_set_vp_info(vp_id, flags, 0); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } return rc ? -EIO : 0; } @@ -701,7 +693,7 @@ int xive_native_disable_vp(u32 vp_id) rc = opal_xive_set_vp_info(vp_id, 0, 0); if (rc != OPAL_BUSY) break; - msleep(1); + msleep(OPAL_BUSY_DELAY_MS); } return rc ? -EIO : 0; } diff --git a/arch/powerpc/tools/checkpatch.sh b/arch/powerpc/tools/checkpatch.sh new file mode 100755 index 000000000000..1fad3fb90e7c --- /dev/null +++ b/arch/powerpc/tools/checkpatch.sh @@ -0,0 +1,22 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# Copyright 2018, Michael Ellerman, IBM Corporation. +# +# Wrapper around checkpatch that uses our preferred settings + +script_base=$(realpath $(dirname $0)) + +exec $script_base/../../../scripts/checkpatch.pl \ + --subjective \ + --no-summary \ + --max-line-length=90 \ + --show-types \ + --ignore ARCH_INCLUDE_LINUX \ + --ignore BIT_MACRO \ + --ignore COMPARISON_TO_NULL \ + --ignore EMAIL_SUBJECT \ + --ignore FILE_PATH_CHANGES \ + --ignore GLOBAL_INITIALISERS \ + --ignore LINE_SPACING \ + --ignore MULTIPLE_ASSIGNMENTS \ + $@ diff --git a/arch/powerpc/xmon/spr_access.S b/arch/powerpc/xmon/spr_access.S index 4099cbcddaaa..720a52afdd58 100644 --- a/arch/powerpc/xmon/spr_access.S +++ b/arch/powerpc/xmon/spr_access.S @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <asm/ppc_asm.h> +#include <asm/asm-compat.h> /* unsigned long xmon_mfspr(sprn, default_value) */ _GLOBAL(xmon_mfspr) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 196978733e64..4264aedc7775 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -56,6 +56,7 @@ #include <asm/opal.h> #include <asm/firmware.h> #include <asm/code-patching.h> +#include <asm/sections.h> #ifdef CONFIG_PPC64 #include <asm/hvcall.h> @@ -244,6 +245,7 @@ Commands:\n\ f flush cache\n\ la lookup symbol+offset of specified address\n\ ls lookup address of specified symbol\n\ + lp s [#] lookup address of percpu symbol s for current cpu, or cpu #\n\ m examine/change memory\n\ mm move a block of memory\n\ ms set a block of memory\n\ @@ -918,13 +920,13 @@ static void remove_cpu_bpts(void) static void show_uptime(void) { - struct timespec uptime; + struct timespec64 uptime; if (setjmp(bus_error_jmp) == 0) { catch_memory_errors = 1; sync(); - get_monotonic_boottime(&uptime); + ktime_get_coarse_boottime_ts64(&uptime); printf("Uptime: %lu.%.2lu seconds\n", (unsigned long)uptime.tv_sec, ((unsigned long)uptime.tv_nsec / (NSEC_PER_SEC/100))); @@ -2429,7 +2431,6 @@ static void dump_one_paca(int cpu) DUMP(p, thread_idle_state, "%#-*x"); DUMP(p, thread_mask, "%#-*x"); DUMP(p, subcore_sibling_mask, "%#-*x"); - DUMP(p, thread_sibling_pacas, "%-*px"); DUMP(p, requested_psscr, "%#-*llx"); DUMP(p, stop_sprs.pid, "%#-*llx"); DUMP(p, stop_sprs.ldbar, "%#-*llx"); @@ -3353,7 +3354,8 @@ static void symbol_lookup(void) { int type = inchar(); - unsigned long addr; + unsigned long addr, cpu; + void __percpu *ptr = NULL; static char tmp[64]; switch (type) { @@ -3377,6 +3379,34 @@ symbol_lookup(void) catch_memory_errors = 0; termch = 0; break; + case 'p': + getstring(tmp, 64); + if (setjmp(bus_error_jmp) == 0) { + catch_memory_errors = 1; + sync(); + ptr = (void __percpu *)kallsyms_lookup_name(tmp); + sync(); + } + + if (ptr && + ptr >= (void __percpu *)__per_cpu_start && + ptr < (void __percpu *)__per_cpu_end) + { + if (scanhex(&cpu) && cpu < num_possible_cpus()) { + addr = (unsigned long)per_cpu_ptr(ptr, cpu); + } else { + cpu = raw_smp_processor_id(); + addr = (unsigned long)this_cpu_ptr(ptr); + } + + printf("%s for cpu 0x%lx: %lx\n", tmp, cpu, addr); + } else { + printf("Percpu symbol '%s' not found.\n", tmp); + } + + catch_memory_errors = 0; + termch = 0; + break; } } diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 4764fdeb4f1f..a344980287a5 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -212,10 +212,6 @@ endmenu menu "Kernel type" -source "mm/Kconfig" - -source "kernel/Kconfig.preempt" - source "kernel/Kconfig.hz" endmenu @@ -242,75 +238,8 @@ source "drivers/pci/Kconfig" endmenu -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - menu "Power management options" source kernel/power/Kconfig endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -menu "Kernel hacking" - -config CMDLINE_BOOL - bool "Built-in kernel command line" - help - For most platforms, it is firmware or second stage bootloader - that by default specifies the kernel command line options. - However, it might be necessary or advantageous to either override - the default kernel command line or add a few extra options to it. - For such cases, this option allows hardcoding command line options - directly into the kernel. - - For that, choose 'Y' here and fill in the extra boot parameters - in CONFIG_CMDLINE. - - The built-in options will be concatenated to the default command - line if CMDLINE_FORCE is set to 'N'. Otherwise, the default - command line will be ignored and replaced by the built-in string. - -config CMDLINE - string "Built-in kernel command string" - depends on CMDLINE_BOOL - default "" - help - Supply command-line options at build time by entering them here. - -config CMDLINE_FORCE - bool "Built-in command line overrides bootloader arguments" - depends on CMDLINE_BOOL - help - Set this option to 'Y' to have the kernel ignore the bootloader - or firmware command line. Instead, the built-in command line - will be used exclusively. - - If you don't know what to do here, say N. - -config EARLY_PRINTK - def_bool y - -source "lib/Kconfig.debug" - -config CMDLINE_BOOL - bool -endmenu - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/riscv/Kconfig.debug b/arch/riscv/Kconfig.debug new file mode 100644 index 000000000000..3224ff6ecf6e --- /dev/null +++ b/arch/riscv/Kconfig.debug @@ -0,0 +1,37 @@ + +config CMDLINE_BOOL + bool "Built-in kernel command line" + help + For most platforms, it is firmware or second stage bootloader + that by default specifies the kernel command line options. + However, it might be necessary or advantageous to either override + the default kernel command line or add a few extra options to it. + For such cases, this option allows hardcoding command line options + directly into the kernel. + + For that, choose 'Y' here and fill in the extra boot parameters + in CONFIG_CMDLINE. + + The built-in options will be concatenated to the default command + line if CMDLINE_FORCE is set to 'N'. Otherwise, the default + command line will be ignored and replaced by the built-in string. + +config CMDLINE + string "Built-in kernel command string" + depends on CMDLINE_BOOL + default "" + help + Supply command-line options at build time by entering them here. + +config CMDLINE_FORCE + bool "Built-in command line overrides bootloader arguments" + depends on CMDLINE_BOOL + help + Set this option to 'Y' to have the kernel ignore the bootloader + or firmware command line. Instead, the built-in command line + will be used exclusively. + + If you don't know what to do here, say N. + +config EARLY_PRINTK + def_bool y diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 6d4a5f6c3f4f..9ddd88bb30b7 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -8,7 +8,6 @@ # for more details. # -LDFLAGS := OBJCOPYFLAGS := -O binary LDFLAGS_vmlinux := ifeq ($(CONFIG_DYNAMIC_FTRACE),y) @@ -26,6 +25,9 @@ ifeq ($(CONFIG_ARCH_RV64I),y) KBUILD_CFLAGS += -mabi=lp64 KBUILD_AFLAGS += -mabi=lp64 + + KBUILD_CFLAGS += $(call cc-ifversion, -ge, 0500, -DCONFIG_ARCH_SUPPORTS_INT128) + KBUILD_MARCH = rv64im LDFLAGS += -melf64lriscv else diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 07326466871b..36473d7dbaac 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -76,3 +76,4 @@ CONFIG_ROOT_NFS=y CONFIG_CRYPTO_USER_API_HASH=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y +CONFIG_SIFIVE_PLIC=y diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 855115ace98c..c452359c9cb8 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -25,18 +25,11 @@ #define ATOMIC_INIT(i) { (i) } -#define __atomic_op_acquire(op, args...) \ -({ \ - typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ - __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory"); \ - __ret; \ -}) - -#define __atomic_op_release(op, args...) \ -({ \ - __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); \ - op##_relaxed(args); \ -}) +#define __atomic_acquire_fence() \ + __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); static __always_inline int atomic_read(const atomic_t *v) { @@ -209,130 +202,8 @@ ATOMIC_OPS(xor, xor, i) #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN -/* - * The extra atomic operations that are constructed from one of the core - * AMO-based operations above (aside from sub, which is easier to fit above). - * These are required to perform a full barrier, but they're OK this way - * because atomic_*_return is also required to perform a full barrier. - * - */ -#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \ -static __always_inline \ -bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_##func_op##_return(i, v) comp_op I; \ -} - -#ifdef CONFIG_GENERIC_ATOMIC64 -#define ATOMIC_OPS(op, func_op, comp_op, I) \ - ATOMIC_OP(op, func_op, comp_op, I, int, ) -#else -#define ATOMIC_OPS(op, func_op, comp_op, I) \ - ATOMIC_OP(op, func_op, comp_op, I, int, ) \ - ATOMIC_OP(op, func_op, comp_op, I, long, 64) -#endif - -ATOMIC_OPS(add_and_test, add, ==, 0) -ATOMIC_OPS(sub_and_test, sub, ==, 0) -ATOMIC_OPS(add_negative, add, <, 0) - -#undef ATOMIC_OP -#undef ATOMIC_OPS - -#define ATOMIC_OP(op, func_op, I, c_type, prefix) \ -static __always_inline \ -void atomic##prefix##_##op(atomic##prefix##_t *v) \ -{ \ - atomic##prefix##_##func_op(I, v); \ -} - -#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix) \ -static __always_inline \ -c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##func_op##_relaxed(I, v); \ -} \ -static __always_inline \ -c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##func_op(I, v); \ -} - -#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix) \ -static __always_inline \ -c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##op##_relaxed(v) c_op I; \ -} \ -static __always_inline \ -c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_fetch_##op(v) c_op I; \ -} - -#ifdef CONFIG_GENERIC_ATOMIC64 -#define ATOMIC_OPS(op, asm_op, c_op, I) \ - ATOMIC_OP( op, asm_op, I, int, ) \ - ATOMIC_FETCH_OP( op, asm_op, I, int, ) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) -#else -#define ATOMIC_OPS(op, asm_op, c_op, I) \ - ATOMIC_OP( op, asm_op, I, int, ) \ - ATOMIC_FETCH_OP( op, asm_op, I, int, ) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) \ - ATOMIC_OP( op, asm_op, I, long, 64) \ - ATOMIC_FETCH_OP( op, asm_op, I, long, 64) \ - ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64) -#endif - -ATOMIC_OPS(inc, add, +, 1) -ATOMIC_OPS(dec, add, +, -1) - -#define atomic_inc_return_relaxed atomic_inc_return_relaxed -#define atomic_dec_return_relaxed atomic_dec_return_relaxed -#define atomic_inc_return atomic_inc_return -#define atomic_dec_return atomic_dec_return - -#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed -#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed -#define atomic_fetch_inc atomic_fetch_inc -#define atomic_fetch_dec atomic_fetch_dec - -#ifndef CONFIG_GENERIC_ATOMIC64 -#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed -#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#define atomic64_inc_return atomic64_inc_return -#define atomic64_dec_return atomic64_dec_return - -#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed -#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed -#define atomic64_fetch_inc atomic64_fetch_inc -#define atomic64_fetch_dec atomic64_fetch_dec -#endif - -#undef ATOMIC_OPS -#undef ATOMIC_OP -#undef ATOMIC_FETCH_OP -#undef ATOMIC_OP_RETURN - -#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \ -static __always_inline \ -bool atomic##prefix##_##op(atomic##prefix##_t *v) \ -{ \ - return atomic##prefix##_##func_op##_return(v) comp_op I; \ -} - -ATOMIC_OP(inc_and_test, inc, ==, 0, ) -ATOMIC_OP(dec_and_test, dec, ==, 0, ) -#ifndef CONFIG_GENERIC_ATOMIC64 -ATOMIC_OP(inc_and_test, inc, ==, 0, 64) -ATOMIC_OP(dec_and_test, dec, ==, 0, 64) -#endif - -#undef ATOMIC_OP - /* This is required to provide a full barrier on success. */ -static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int prev, rc; @@ -349,9 +220,10 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) : "memory"); return prev; } +#define atomic_fetch_add_unless atomic_fetch_add_unless #ifndef CONFIG_GENERIC_ATOMIC64 -static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u) +static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u) { long prev, rc; @@ -368,27 +240,7 @@ static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u) : "memory"); return prev; } - -static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - return __atomic64_add_unless(v, a, u) != u; -} -#endif - -/* - * The extra atomic operations that are constructed from one of the core - * LR/SC-based operations above. - */ -static __always_inline int atomic_inc_not_zero(atomic_t *v) -{ - return __atomic_add_unless(v, 1, 0); -} - -#ifndef CONFIG_GENERIC_ATOMIC64 -static __always_inline long atomic64_inc_not_zero(atomic64_t *v) -{ - return atomic64_add_unless(v, 1, 0); -} +#define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif /* diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 421fa3585798..28a0d1cb374c 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -54,6 +54,7 @@ /* Interrupt Enable and Interrupt Pending flags */ #define SIE_SSIE _AC(0x00000002, UL) /* Software Interrupt Enable */ #define SIE_STIE _AC(0x00000020, UL) /* Timer Interrupt Enable */ +#define SIE_SEIE _AC(0x00000200, UL) /* External Interrupt Enable */ #define EXC_INST_MISALIGNED 0 #define EXC_INST_ACCESS 1 diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h index 4dee9d4c13c0..996b6fbe17a6 100644 --- a/arch/riscv/include/asm/irq.h +++ b/arch/riscv/include/asm/irq.h @@ -17,11 +17,8 @@ #define NR_IRQS 0 -#define INTERRUPT_CAUSE_SOFTWARE 1 -#define INTERRUPT_CAUSE_TIMER 5 -#define INTERRUPT_CAUSE_EXTERNAL 9 - void riscv_timer_interrupt(void); +void riscv_software_interrupt(void); #include <asm-generic/irq.h> diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h index 0e638a0c3feb..aefbfaa6a781 100644 --- a/arch/riscv/include/asm/perf_event.h +++ b/arch/riscv/include/asm/perf_event.h @@ -10,6 +10,7 @@ #include <linux/perf_event.h> #include <linux/ptrace.h> +#include <linux/interrupt.h> #define RISCV_BASE_COUNTERS 2 diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index 85e4220839b0..36016845461d 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -25,9 +25,6 @@ #ifdef CONFIG_SMP /* SMP initialization hook for setup_arch */ -void __init init_clockevent(void); - -/* SMP initialization hook for setup_arch */ void __init setup_smp(void); /* Hook for the generic smp_call_function_many() routine. */ @@ -44,9 +41,6 @@ void arch_send_call_function_single_ipi(int cpu); */ #define raw_smp_processor_id() (*((int*)((char*)get_current() + TASK_TI_CPU))) -/* Interprocessor interrupt handler */ -irqreturn_t handle_ipi(void); - #endif /* CONFIG_SMP */ #endif /* _ASM_RISCV_SMP_H */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 9aaf6c986771..fa2c08e3c05e 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -168,8 +168,8 @@ ENTRY(handle_exception) /* Handle interrupts */ move a0, sp /* pt_regs */ - REG_L a1, handle_arch_irq - jr a1 + move a1, s4 /* scause */ + tail do_IRQ 1: /* Exceptions run with interrupts enabled */ csrs sstatus, SR_SIE diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 6e07ed37bbff..c4d2c63f9a29 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -94,6 +94,7 @@ relocate: or a0, a0, a1 sfence.vma csrw sptbr, a0 +.align 2 1: /* Set trap vector to spin forever to help debug */ la a0, .Lsecondary_park @@ -143,6 +144,7 @@ relocate: tail smp_callin #endif +.align 2 .Lsecondary_park: /* We lack SMP support or have too many harts, so park this hart */ wfi diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index 7bcdaed15703..0cfac48a1272 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -1,21 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2012 Regents of the University of California * Copyright (C) 2017 SiFive - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation, version 2. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. + * Copyright (C) 2018 Christoph Hellwig */ #include <linux/interrupt.h> #include <linux/irqchip.h> #include <linux/irqdomain.h> +/* + * Possible interrupt causes: + */ +#define INTERRUPT_CAUSE_SOFTWARE 1 +#define INTERRUPT_CAUSE_TIMER 5 +#define INTERRUPT_CAUSE_EXTERNAL 9 + +/* + * The high order bit of the trap cause register is always set for + * interrupts, which allows us to differentiate them from exceptions + * quickly. The INTERRUPT_CAUSE_* macros don't contain that bit, so we + * need to mask it off. + */ +#define INTERRUPT_CAUSE_FLAG (1UL << (__riscv_xlen - 1)) + +asmlinkage void __irq_entry do_IRQ(struct pt_regs *regs, unsigned long cause) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + irq_enter(); + switch (cause & ~INTERRUPT_CAUSE_FLAG) { + case INTERRUPT_CAUSE_TIMER: + riscv_timer_interrupt(); + break; +#ifdef CONFIG_SMP + case INTERRUPT_CAUSE_SOFTWARE: + /* + * We only use software interrupts to pass IPIs, so if a non-SMP + * system gets one, then we don't know what to do. + */ + riscv_software_interrupt(); + break; +#endif + case INTERRUPT_CAUSE_EXTERNAL: + handle_arch_irq(regs); + break; + default: + panic("unexpected interrupt cause"); + } + irq_exit(); + + set_irq_regs(old_regs); +} + void __init init_IRQ(void) { irqchip_init(); diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c index b0e10c4e9f77..a243fae1c1db 100644 --- a/arch/riscv/kernel/perf_event.c +++ b/arch/riscv/kernel/perf_event.c @@ -27,7 +27,6 @@ #include <linux/mutex.h> #include <linux/bitmap.h> #include <linux/irq.h> -#include <linux/interrupt.h> #include <linux/perf_event.h> #include <linux/atomic.h> #include <linux/of.h> diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f0d2070866d4..db20dc630e7e 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -39,6 +39,27 @@ #include <asm/tlbflush.h> #include <asm/thread_info.h> +#ifdef CONFIG_EARLY_PRINTK +static void sbi_console_write(struct console *co, const char *buf, + unsigned int n) +{ + int i; + + for (i = 0; i < n; ++i) { + if (buf[i] == '\n') + sbi_console_putchar('\r'); + sbi_console_putchar(buf[i]); + } +} + +struct console riscv_sbi_early_console_dev __initdata = { + .name = "early", + .write = sbi_console_write, + .flags = CON_PRINTBUFFER | CON_BOOT | CON_ANYTIME, + .index = -1 +}; +#endif + #ifdef CONFIG_DUMMY_CONSOLE struct screen_info screen_info = { .orig_video_lines = 30, @@ -195,6 +216,12 @@ static void __init setup_bootmem(void) void __init setup_arch(char **cmdline_p) { +#if defined(CONFIG_EARLY_PRINTK) + if (likely(early_console == NULL)) { + early_console = &riscv_sbi_early_console_dev; + register_console(early_console); + } +#endif *cmdline_p = boot_command_line; parse_early_param(); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 6d3962435720..906fe21ea21b 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -45,7 +45,7 @@ int setup_profiling_timer(unsigned int multiplier) return -EINVAL; } -irqreturn_t handle_ipi(void) +void riscv_software_interrupt(void) { unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits; @@ -60,7 +60,7 @@ irqreturn_t handle_ipi(void) ops = xchg(pending_ipis, 0); if (ops == 0) - return IRQ_HANDLED; + return; if (ops & (1 << IPI_RESCHEDULE)) scheduler_ipi(); @@ -73,8 +73,6 @@ irqreturn_t handle_ipi(void) /* Order data access and bit testing. */ mb(); } - - return IRQ_HANDLED; } static void diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index f741458c5a3f..56abab6a9812 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -104,7 +104,6 @@ asmlinkage void __init smp_callin(void) current->active_mm = mm; trap_init(); - init_clockevent(); notify_cpu_starting(smp_processor_id()); set_cpu_online(smp_processor_id(), 1); local_flush_tlb_all(); diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 2463fcca719e..1911c8f6b8a6 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -13,38 +13,11 @@ */ #include <linux/clocksource.h> -#include <linux/clockchips.h> #include <linux/delay.h> - -#ifdef CONFIG_RISCV_TIMER -#include <linux/timer_riscv.h> -#endif - #include <asm/sbi.h> unsigned long riscv_timebase; -DECLARE_PER_CPU(struct clock_event_device, riscv_clock_event); - -void riscv_timer_interrupt(void) -{ -#ifdef CONFIG_RISCV_TIMER - /* - * FIXME: This needs to be cleaned up along with the rest of the IRQ - * handling cleanup. See irq.c for more details. - */ - struct clock_event_device *evdev = this_cpu_ptr(&riscv_clock_event); - - evdev->event_handler(evdev); -#endif -} - -void __init init_clockevent(void) -{ - timer_probe(); - csr_set(sie, SIE_STIE); -} - void __init time_init(void) { struct device_node *cpu; @@ -56,6 +29,5 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; - - init_clockevent(); + timer_probe(); } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 81a1952015a6..24a9333dda2c 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -138,7 +138,6 @@ asmlinkage void do_trap_break(struct pt_regs *regs) #endif /* CONFIG_GENERIC_BUG */ force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)(regs->sepc), current); - regs->sepc += 0x4; } #ifdef CONFIG_GENERIC_BUG diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index f6561b783b61..eed1c137f618 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -52,8 +52,8 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE # Add -lgcc so rv32 gets static muldi3 and lshrdi3 definitions. # Make sure only to export the intended __vdso_xxx symbol offsets. quiet_cmd_vdsold = VDSOLD $@ - cmd_vdsold = $(CC) $(KCFLAGS) $(call cc-option, -no-pie) -nostdlib $(SYSCFLAGS_$(@F)) \ - -Wl,-T,$(filter-out FORCE,$^) -o $@.tmp -lgcc && \ + cmd_vdsold = $(CC) $(KBUILD_CFLAGS) $(call cc-option, -no-pie) -nostdlib -nostartfiles $(SYSCFLAGS_$(@F)) \ + -Wl,-T,$(filter-out FORCE,$^) -o $@.tmp && \ $(CROSS_COMPILE)objcopy \ $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 596c2ca40d63..445ec84f9a47 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -2,5 +2,6 @@ lib-y += delay.o lib-y += memcpy.o lib-y += memset.o lib-y += uaccess.o +lib-y += tishift.o lib-$(CONFIG_32BIT) += udivdi3.o diff --git a/arch/riscv/lib/tishift.S b/arch/riscv/lib/tishift.S new file mode 100644 index 000000000000..69abb1277234 --- /dev/null +++ b/arch/riscv/lib/tishift.S @@ -0,0 +1,42 @@ +/* + * Copyright (C) 2018 Free Software Foundation, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + .globl __lshrti3 +__lshrti3: + beqz a2, .L1 + li a5,64 + sub a5,a5,a2 + addi sp,sp,-16 + sext.w a4,a5 + blez a5, .L2 + sext.w a2,a2 + sll a4,a1,a4 + srl a0,a0,a2 + srl a1,a1,a2 + or a0,a0,a4 + sd a1,8(sp) + sd a0,0(sp) + ld a0,0(sp) + ld a1,8(sp) + addi sp,sp,16 + ret +.L1: + ret +.L2: + negw a4,a4 + srl a1,a1,a4 + sd a1,0(sp) + sd zero,8(sp) + ld a0,0(sp) + ld a1,8(sp) + addi sp,sp,16 + ret diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 148c98ca9b45..88401d5125bc 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -41,7 +41,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs) struct mm_struct *mm; unsigned long addr, cause; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; - int fault, code = SEGV_MAPERR; + int code = SEGV_MAPERR; + vm_fault_t fault; cause = regs->scause; addr = regs->sbadaddr; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 4e914445553e..054b29c9a533 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -106,7 +106,6 @@ config S390 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANTS_DYNAMIC_TASK_STRUCT - select ARCH_WANTS_UBSAN_NO_NULL select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS2 @@ -141,12 +140,13 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if FUTEX - select HAVE_GCC_PLUGINS + select HAVE_GCC_PLUGINS if BROKEN select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 select HAVE_KERNEL_LZMA select HAVE_KERNEL_LZO + select HAVE_KERNEL_UNCOMPRESSED select HAVE_KERNEL_XZ select HAVE_KPROBES select HAVE_KRETPROBES @@ -186,10 +186,6 @@ config PGTABLE_LEVELS int default 5 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - source "kernel/livepatch/Kconfig" menu "Processor type and features" @@ -517,8 +513,6 @@ config SCHED_TOPOLOGY making when dealing with machines that have multi-threading, multiple cores or multiple books. -source kernel/Kconfig.preempt - source kernel/Kconfig.hz config KEXEC @@ -629,8 +623,6 @@ config FORCE_MAX_ZONEORDER int default "9" -source "mm/Kconfig" - config MAX_PHYSMEM_BITS int "Maximum size of supported physical memory in bits (42-53)" range 42 53 @@ -800,10 +792,6 @@ config CRASH_DUMP endmenu -menu "Executable file formats / Emulations" - -source "fs/Kconfig.binfmt" - config SECCOMP def_bool y prompt "Enable seccomp to safely compute untrusted bytecode" @@ -821,8 +809,6 @@ config SECCOMP If unsure, say Y. -endmenu - menu "Power Management" config ARCH_HIBERNATION_POSSIBLE @@ -832,30 +818,16 @@ source "kernel/power/Kconfig" endmenu -source "net/Kconfig" - config PCMCIA def_bool n config CCW def_bool y -source "drivers/Kconfig" - config HAVE_PNETID tristate default (SMC || CCWGROUP) -source "fs/Kconfig" - -source "arch/s390/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - menu "Virtualization" config PFAULT diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug index 2cfdfbf8d320..190527560b2c 100644 --- a/arch/s390/Kconfig.debug +++ b/arch/s390/Kconfig.debug @@ -1,11 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" config TRACE_IRQFLAGS_SUPPORT def_bool y -source "lib/Kconfig.debug" - config S390_PTDUMP bool "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL @@ -20,5 +17,3 @@ config S390_PTDUMP config EARLY_PRINTK def_bool y - -endmenu diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 8498babb5dad..ba6d122526fb 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -14,8 +14,18 @@ LD_BFD := elf64-s390 LDFLAGS := -m elf64_s390 KBUILD_AFLAGS_MODULE += -fPIC KBUILD_CFLAGS_MODULE += -fPIC -KBUILD_CFLAGS += -m64 KBUILD_AFLAGS += -m64 +KBUILD_CFLAGS += -m64 +aflags_dwarf := -Wa,-gdwarf-2 +KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__ +KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf)) +KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2 +KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY +KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float +KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables +KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding) +KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) +KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) UTS_MACHINE := s390x STACK_SIZE := 16384 CHECKFLAGS += -D__s390__ -D__s390x__ @@ -52,18 +62,14 @@ cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include # cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls -# old style option for packed stacks -ifeq ($(call cc-option-yn,-mkernel-backchain),y) -cflags-$(CONFIG_PACK_STACK) += -mkernel-backchain -D__PACK_STACK -aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK -endif - -# new style option for packed stacks ifeq ($(call cc-option-yn,-mpacked-stack),y) cflags-$(CONFIG_PACK_STACK) += -mpacked-stack -D__PACK_STACK aflags-$(CONFIG_PACK_STACK) += -D__PACK_STACK endif +KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y) +KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y) + ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y) cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE) ifneq ($(call cc-option-yn,-mstack-size=8192),y) @@ -71,8 +77,11 @@ cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD) endif endif -ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y) -cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack +ifdef CONFIG_WARN_DYNAMIC_STACK + ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y) + KBUILD_CFLAGS += -mwarn-dynamicstack + KBUILD_CFLAGS_DECOMPRESSOR += -mwarn-dynamicstack + endif endif ifdef CONFIG_EXPOLINE @@ -82,6 +91,7 @@ ifdef CONFIG_EXPOLINE CC_FLAGS_EXPOLINE += -mindirect-branch-table export CC_FLAGS_EXPOLINE cflags-y += $(CC_FLAGS_EXPOLINE) -DCC_USING_EXPOLINE + aflags-y += -DCC_USING_EXPOLINE endif endif @@ -104,11 +114,12 @@ KBUILD_CFLAGS += -mbackchain -msoft-float $(cflags-y) KBUILD_CFLAGS += -pipe -fno-strength-reduce -Wno-sign-compare KBUILD_CFLAGS += -fno-asynchronous-unwind-tables $(cfi) KBUILD_AFLAGS += $(aflags-y) $(cfi) +export KBUILD_AFLAGS_DECOMPRESSOR +export KBUILD_CFLAGS_DECOMPRESSOR OBJCOPYFLAGS := -O binary -head-y := arch/s390/kernel/head.o -head-y += arch/s390/kernel/head64.o +head-y := arch/s390/kernel/head64.o # See arch/s390/Kbuild for content of core part of the kernel core-y += arch/s390/ @@ -123,7 +134,7 @@ boot := arch/s390/boot syscalls := arch/s390/kernel/syscalls tools := arch/s390/tools -all: image bzImage +all: bzImage #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg... KBUILD_IMAGE := $(boot)/bzImage @@ -131,7 +142,7 @@ KBUILD_IMAGE := $(boot)/bzImage install: vmlinux $(Q)$(MAKE) $(build)=$(boot) $@ -image bzImage: vmlinux +bzImage: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ zfcpdump: @@ -154,8 +165,7 @@ archprepare: # Don't use tabs in echo arguments define archhelp - echo '* image - Kernel image for IPL ($(boot)/image)' - echo '* bzImage - Compressed kernel image for IPL ($(boot)/bzImage)' + echo '* bzImage - Kernel image for IPL ($(boot)/bzImage)' echo ' install - Install kernel using' echo ' (your) ~/bin/$(INSTALLKERNEL) or' echo ' (distribution) /sbin/$(INSTALLKERNEL) or' diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index ee6a9c387c87..9bf8489df6e6 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -206,35 +206,28 @@ static int appldata_timer_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - unsigned int len; - char buf[2]; + int timer_active = appldata_timer_active; + int zero = 0; + int one = 1; + int rc; + struct ctl_table ctl_entry = { + .procname = ctl->procname, + .data = &timer_active, + .maxlen = sizeof(int), + .extra1 = &zero, + .extra2 = &one, + }; + + rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos); + if (rc < 0 || !write) + return rc; - if (!*lenp || *ppos) { - *lenp = 0; - return 0; - } - if (!write) { - strncpy(buf, appldata_timer_active ? "1\n" : "0\n", - ARRAY_SIZE(buf)); - len = strnlen(buf, ARRAY_SIZE(buf)); - if (len > *lenp) - len = *lenp; - if (copy_to_user(buffer, buf, len)) - return -EFAULT; - goto out; - } - len = *lenp; - if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) - return -EFAULT; spin_lock(&appldata_timer_lock); - if (buf[0] == '1') + if (timer_active) __appldata_vtimer_setup(APPLDATA_ADD_TIMER); - else if (buf[0] == '0') + else __appldata_vtimer_setup(APPLDATA_DEL_TIMER); spin_unlock(&appldata_timer_lock); -out: - *lenp = len; - *ppos += len; return 0; } @@ -248,37 +241,24 @@ static int appldata_interval_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - unsigned int len; - int interval; - char buf[16]; + int interval = appldata_interval; + int one = 1; + int rc; + struct ctl_table ctl_entry = { + .procname = ctl->procname, + .data = &interval, + .maxlen = sizeof(int), + .extra1 = &one, + }; - if (!*lenp || *ppos) { - *lenp = 0; - return 0; - } - if (!write) { - len = sprintf(buf, "%i\n", appldata_interval); - if (len > *lenp) - len = *lenp; - if (copy_to_user(buffer, buf, len)) - return -EFAULT; - goto out; - } - len = *lenp; - if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) - return -EFAULT; - interval = 0; - sscanf(buf, "%i", &interval); - if (interval <= 0) - return -EINVAL; + rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos); + if (rc < 0 || !write) + return rc; spin_lock(&appldata_timer_lock); appldata_interval = interval; __appldata_vtimer_setup(APPLDATA_MOD_TIMER); spin_unlock(&appldata_timer_lock); -out: - *lenp = len; - *ppos += len; return 0; } @@ -293,10 +273,17 @@ appldata_generic_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct appldata_ops *ops = NULL, *tmp_ops; - unsigned int len; - int rc, found; - char buf[2]; struct list_head *lh; + int rc, found; + int active; + int zero = 0; + int one = 1; + struct ctl_table ctl_entry = { + .data = &active, + .maxlen = sizeof(int), + .extra1 = &zero, + .extra2 = &one, + }; found = 0; mutex_lock(&appldata_ops_mutex); @@ -317,31 +304,15 @@ appldata_generic_handler(struct ctl_table *ctl, int write, } mutex_unlock(&appldata_ops_mutex); - if (!*lenp || *ppos) { - *lenp = 0; + active = ops->active; + rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos); + if (rc < 0 || !write) { module_put(ops->owner); - return 0; - } - if (!write) { - strncpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf)); - len = strnlen(buf, ARRAY_SIZE(buf)); - if (len > *lenp) - len = *lenp; - if (copy_to_user(buffer, buf, len)) { - module_put(ops->owner); - return -EFAULT; - } - goto out; - } - len = *lenp; - if (copy_from_user(buf, buffer, - len > sizeof(buf) ? sizeof(buf) : len)) { - module_put(ops->owner); - return -EFAULT; + return rc; } mutex_lock(&appldata_ops_mutex); - if ((buf[0] == '1') && (ops->active == 0)) { + if (active && (ops->active == 0)) { // protect work queue callback if (!try_module_get(ops->owner)) { mutex_unlock(&appldata_ops_mutex); @@ -359,7 +330,7 @@ appldata_generic_handler(struct ctl_table *ctl, int write, module_put(ops->owner); } else ops->active = 1; - } else if ((buf[0] == '0') && (ops->active == 1)) { + } else if (!active && (ops->active == 1)) { ops->active = 0; rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC, (unsigned long) ops->data, ops->size, @@ -370,9 +341,6 @@ appldata_generic_handler(struct ctl_table *ctl, int write, module_put(ops->owner); } mutex_unlock(&appldata_ops_mutex); -out: - *lenp = len; - *ppos += len; module_put(ops->owner); return 0; } diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index d1fa37fcce83..9e6668ee93de 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -3,19 +3,52 @@ # Makefile for the linux s390-specific parts of the memory manager. # -targets := image -targets += bzImage -subdir- := compressed +KCOV_INSTRUMENT := n +GCOV_PROFILE := n +UBSAN_SANITIZE := n -$(obj)/image: vmlinux FORCE - $(call if_changed,objcopy) +KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR) +KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR) + +# +# Use -march=z900 for als.c to be able to print an error +# message if the kernel is started on a machine which is too old +# +ifneq ($(CC_FLAGS_MARCH),-march=z900) +AFLAGS_REMOVE_head.o += $(CC_FLAGS_MARCH) +AFLAGS_head.o += -march=z900 +AFLAGS_REMOVE_mem.o += $(CC_FLAGS_MARCH) +AFLAGS_mem.o += -march=z900 +CFLAGS_REMOVE_als.o += $(CC_FLAGS_MARCH) +CFLAGS_als.o += -march=z900 +CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_MARCH) +CFLAGS_sclp_early_core.o += -march=z900 +endif + +CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char + +obj-y := head.o als.o ebcdic.o sclp_early_core.o mem.o +targets := bzImage startup.a $(obj-y) +subdir- := compressed + +OBJECTS := $(addprefix $(obj)/,$(obj-y)) $(obj)/bzImage: $(obj)/compressed/vmlinux FORCE $(call if_changed,objcopy) -$(obj)/compressed/vmlinux: FORCE +$(obj)/compressed/vmlinux: $(obj)/startup.a FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed $@ +quiet_cmd_ar = AR $@ + cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter $(OBJECTS), $^) + +$(obj)/startup.a: $(OBJECTS) FORCE + $(call if_changed,ar) + install: $(CONFIGURE) $(obj)/bzImage sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ System.map "$(INSTALL_PATH)" + +chkbss := $(OBJECTS) +chkbss-target := $(obj)/startup.a +include $(srctree)/arch/s390/scripts/Makefile.chkbss diff --git a/arch/s390/kernel/als.c b/arch/s390/boot/als.c index d1892bf36cab..d592e0d90d9f 100644 --- a/arch/s390/kernel/als.c +++ b/arch/s390/boot/als.c @@ -3,12 +3,10 @@ * Copyright IBM Corp. 2016 */ #include <linux/kernel.h> -#include <linux/init.h> #include <asm/processor.h> #include <asm/facility.h> #include <asm/lowcore.h> #include <asm/sclp.h> -#include "entry.h" /* * The code within this file will be called very early. It may _not_ @@ -18,9 +16,9 @@ * For temporary objects the stack (16k) should be used. */ -static unsigned long als[] __initdata = { FACILITIES_ALS }; +static unsigned long als[] = { FACILITIES_ALS }; -static void __init u16_to_hex(char *str, u16 val) +static void u16_to_hex(char *str, u16 val) { int i, num; @@ -33,9 +31,9 @@ static void __init u16_to_hex(char *str, u16 val) *str = '\0'; } -static void __init print_machine_type(void) +static void print_machine_type(void) { - static char mach_str[80] __initdata = "Detected machine-type number: "; + static char mach_str[80] = "Detected machine-type number: "; char type_str[5]; struct cpuid id; @@ -46,7 +44,7 @@ static void __init print_machine_type(void) sclp_early_printk(mach_str); } -static void __init u16_to_decimal(char *str, u16 val) +static void u16_to_decimal(char *str, u16 val) { int div = 1; @@ -60,9 +58,9 @@ static void __init u16_to_decimal(char *str, u16 val) *str = '\0'; } -static void __init print_missing_facilities(void) +static void print_missing_facilities(void) { - static char als_str[80] __initdata = "Missing facilities: "; + static char als_str[80] = "Missing facilities: "; unsigned long val; char val_str[6]; int i, j, first; @@ -95,7 +93,7 @@ static void __init print_missing_facilities(void) sclp_early_printk("See Principles of Operations for facility bits\n"); } -static void __init facility_mismatch(void) +static void facility_mismatch(void) { sclp_early_printk("The Linux kernel requires more recent processor hardware\n"); print_machine_type(); @@ -103,7 +101,7 @@ static void __init facility_mismatch(void) disabled_wait(0x8badcccc); } -void __init verify_facilities(void) +void verify_facilities(void) { int i; diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore index 2088cc140629..45aeb4f08752 100644 --- a/arch/s390/boot/compressed/.gitignore +++ b/arch/s390/boot/compressed/.gitignore @@ -1,4 +1,5 @@ sizes.h vmlinux vmlinux.lds +vmlinux.scr.lds vmlinux.bin.full diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 5766f7b9b271..04609478d18b 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -6,39 +6,29 @@ # KCOV_INSTRUMENT := n +GCOV_PROFILE := n +UBSAN_SANITIZE := n +obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,head.o misc.o) piggy.o targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4 -targets += misc.o piggy.o sizes.h head.o - -KBUILD_CFLAGS := -m64 -D__KERNEL__ -O2 -KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY -KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float -KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -KBUILD_CFLAGS += $(call cc-option,-mpacked-stack) -KBUILD_CFLAGS += $(call cc-option,-ffreestanding) +targets += vmlinux.scr.lds $(obj-y) $(if $(CONFIG_KERNEL_UNCOMPRESSED),,sizes.h) -GCOV_PROFILE := n -UBSAN_SANITIZE := n +KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR) +KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR) -OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o ebcdic.o als.o) -OBJECTS += $(objtree)/drivers/s390/char/sclp_early_core.o -OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o +OBJECTS := $(addprefix $(obj)/,$(obj-y)) LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T -$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS) +$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) $(call if_changed,ld) -TRIM_HEAD_SIZE := 0x11000 - -sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - $(TRIM_HEAD_SIZE))/p' +# extract required uncompressed vmlinux symbols and adjust them to reflect offsets inside vmlinux.bin +sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - 0x100000)/p' quiet_cmd_sizes = GEN $@ cmd_sizes = $(NM) $< | sed -n $(sed-sizes) > $@ -quiet_cmd_trim_head = TRIM $@ - cmd_trim_head = tail -c +$$(($(TRIM_HEAD_SIZE) + 1)) $< > $@ - $(obj)/sizes.h: vmlinux $(call if_changed,sizes) @@ -48,21 +38,18 @@ $(obj)/head.o: $(obj)/sizes.h CFLAGS_misc.o += -I$(objtree)/$(obj) $(obj)/misc.o: $(obj)/sizes.h -OBJCOPYFLAGS_vmlinux.bin.full := -R .comment -S -$(obj)/vmlinux.bin.full: vmlinux +OBJCOPYFLAGS_vmlinux.bin := -R .comment -S +$(obj)/vmlinux.bin: vmlinux $(call if_changed,objcopy) -$(obj)/vmlinux.bin: $(obj)/vmlinux.bin.full - $(call if_changed,trim_head) - vmlinux.bin.all-y := $(obj)/vmlinux.bin -suffix-$(CONFIG_KERNEL_GZIP) := gz -suffix-$(CONFIG_KERNEL_BZIP2) := bz2 -suffix-$(CONFIG_KERNEL_LZ4) := lz4 -suffix-$(CONFIG_KERNEL_LZMA) := lzma -suffix-$(CONFIG_KERNEL_LZO) := lzo -suffix-$(CONFIG_KERNEL_XZ) := xz +suffix-$(CONFIG_KERNEL_GZIP) := .gz +suffix-$(CONFIG_KERNEL_BZIP2) := .bz2 +suffix-$(CONFIG_KERNEL_LZ4) := .lz4 +suffix-$(CONFIG_KERNEL_LZMA) := .lzma +suffix-$(CONFIG_KERNEL_LZO) := .lzo +suffix-$(CONFIG_KERNEL_XZ) := .xz $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) $(call if_changed,gzip) @@ -78,5 +65,9 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) $(call if_changed,xzkern) LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T -$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) +$(obj)/piggy.o: $(obj)/vmlinux.scr.lds $(obj)/vmlinux.bin$(suffix-y) $(call if_changed,ld) + +chkbss := $(filter-out $(obj)/misc.o $(obj)/piggy.o,$(OBJECTS)) +chkbss-target := $(obj)/vmlinux.bin +include $(srctree)/arch/s390/scripts/Makefile.chkbss diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S index 9f94eca0f467..df8dbbc17bcc 100644 --- a/arch/s390/boot/compressed/head.S +++ b/arch/s390/boot/compressed/head.S @@ -15,7 +15,7 @@ #include "sizes.h" __HEAD -ENTRY(startup_continue) +ENTRY(startup_decompressor) basr %r13,0 # get base .LPG1: # setup stack @@ -23,7 +23,7 @@ ENTRY(startup_continue) aghi %r15,-160 brasl %r14,decompress_kernel # Set up registers for memory mover. We move the decompressed image to - # 0x11000, where startup_continue of the decompressed image is supposed + # 0x100000, where startup_continue of the decompressed image is supposed # to be. lgr %r4,%r2 lg %r2,.Loffset-.LPG1(%r13) @@ -33,7 +33,7 @@ ENTRY(startup_continue) la %r1,0x200 mvc 0(mover_end-mover,%r1),mover-.LPG1(%r13) # When the memory mover is done we pass control to - # arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in + # arch/s390/kernel/head64.S:startup_continue which lives at 0x100000 in # the decompressed image. lgr %r6,%r2 br %r1 @@ -47,6 +47,6 @@ mover_end: .Lstack: .quad 0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)) .Loffset: - .quad 0x11000 + .quad 0x100000 .Lmvsize: .quad SZ__bss_start diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index 511b2cc9b91a..f66ad73c205b 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -71,43 +71,6 @@ static int puts(const char *s) return 0; } -void *memset(void *s, int c, size_t n) -{ - char *xs; - - xs = s; - while (n--) - *xs++ = c; - return s; -} - -void *memcpy(void *dest, const void *src, size_t n) -{ - const char *s = src; - char *d = dest; - - while (n--) - *d++ = *s++; - return dest; -} - -void *memmove(void *dest, const void *src, size_t n) -{ - const char *s = src; - char *d = dest; - - if (d <= s) { - while (n--) - *d++ = *s++; - } else { - d += n; - s += n; - while (n--) - *--d = *--s; - } - return dest; -} - static void error(char *x) { unsigned long long psw = 0x000a0000deadbeefULL; diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S index d43c2db12d30..b16ac8b3c439 100644 --- a/arch/s390/boot/compressed/vmlinux.lds.S +++ b/arch/s390/boot/compressed/vmlinux.lds.S @@ -23,13 +23,10 @@ SECTIONS *(.text.*) _etext = . ; } - .rodata.compressed : { - *(.rodata.compressed) - } .rodata : { _rodata = . ; *(.rodata) /* read-only data */ - *(.rodata.*) + *(EXCLUDE_FILE (*piggy.o) .rodata.compressed) _erodata = . ; } .data : { @@ -38,6 +35,15 @@ SECTIONS *(.data.*) _edata = . ; } + startup_continue = 0x100000; +#ifdef CONFIG_KERNEL_UNCOMPRESSED + . = 0x100000; +#else + . = ALIGN(8); +#endif + .rodata.compressed : { + *(.rodata.compressed) + } . = ALIGN(256); .bss : { _bss = . ; @@ -54,5 +60,6 @@ SECTIONS *(.eh_frame) *(__ex_table) *(*__ksymtab*) + *(___kcrctab*) } } diff --git a/arch/s390/boot/compressed/vmlinux.scr b/arch/s390/boot/compressed/vmlinux.scr.lds.S index 42a242597f34..ff01d18c9222 100644 --- a/arch/s390/boot/compressed/vmlinux.scr +++ b/arch/s390/boot/compressed/vmlinux.scr.lds.S @@ -2,10 +2,14 @@ SECTIONS { .rodata.compressed : { +#ifndef CONFIG_KERNEL_UNCOMPRESSED input_len = .; LONG(input_data_end - input_data) input_data = .; +#endif *(.data) +#ifndef CONFIG_KERNEL_UNCOMPRESSED output_len = . - 4; input_data_end = .; +#endif } } diff --git a/arch/s390/boot/ebcdic.c b/arch/s390/boot/ebcdic.c new file mode 100644 index 000000000000..7391e7d36086 --- /dev/null +++ b/arch/s390/boot/ebcdic.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "../kernel/ebcdic.c" diff --git a/arch/s390/kernel/head.S b/arch/s390/boot/head.S index 5c42f16a54c4..f721913b73f1 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/boot/head.S @@ -272,14 +272,14 @@ iplstart: .org 0x10000 ENTRY(startup) j .Lep_startup_normal - .org 0x10008 + .org EP_OFFSET # # This is a list of s390 kernel entry points. At address 0x1000f the number of # valid entry points is stored. # # IMPORTANT: Do not change this table, it is s390 kernel ABI! # - .ascii "S390EP" + .ascii EP_STRING .byte 0x00,0x01 # # kdump startup-code at 0x10010, running in 64 bit absolute addressing mode @@ -310,10 +310,11 @@ ENTRY(startup_kdump) l %r15,.Lstack-.LPG0(%r13) ahi %r15,-STACK_FRAME_OVERHEAD brasl %r14,verify_facilities -# For uncompressed images, continue in -# arch/s390/kernel/head64.S. For compressed images, continue in -# arch/s390/boot/compressed/head.S. +#ifdef CONFIG_KERNEL_UNCOMPRESSED jg startup_continue +#else + jg startup_decompressor +#endif .Lstack: .long 0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)) diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/boot/head_kdump.S index 174d6959bf5b..174d6959bf5b 100644 --- a/arch/s390/kernel/head_kdump.S +++ b/arch/s390/boot/head_kdump.S diff --git a/arch/s390/boot/mem.S b/arch/s390/boot/mem.S new file mode 100644 index 000000000000..b33463633f03 --- /dev/null +++ b/arch/s390/boot/mem.S @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include "../lib/mem.S" diff --git a/arch/s390/boot/sclp_early_core.c b/arch/s390/boot/sclp_early_core.c new file mode 100644 index 000000000000..5a19fd7020b5 --- /dev/null +++ b/arch/s390/boot/sclp_early_core.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "../../../drivers/s390/char/sclp_early_core.c" diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index ad47abd08630..c54cb26eb7f5 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -1035,7 +1035,6 @@ static struct aead_alg gcm_aes_aead = { .chunksize = AES_BLOCK_SIZE, .base = { - .cra_flags = CRYPTO_ALG_TYPE_AEAD, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct s390_aes_ctx), .cra_priority = 900, diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c index 3b7f96c9eead..86aed30fad3a 100644 --- a/arch/s390/crypto/ghash_s390.c +++ b/arch/s390/crypto/ghash_s390.c @@ -128,7 +128,6 @@ static struct shash_alg ghash_alg = { .cra_name = "ghash", .cra_driver_name = "ghash-s390", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = GHASH_BLOCK_SIZE, .cra_ctxsize = sizeof(struct ghash_ctx), .cra_module = THIS_MODULE, diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index a00c17f761c1..009572e8276d 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -78,7 +78,6 @@ static struct shash_alg alg = { .cra_name = "sha1", .cra_driver_name= "sha1-s390", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 944aa6b237cd..62833a1d8724 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -71,7 +71,6 @@ static struct shash_alg sha256_alg = { .cra_name = "sha256", .cra_driver_name= "sha256-s390", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -108,7 +107,6 @@ static struct shash_alg sha224_alg = { .cra_name = "sha224", .cra_driver_name= "sha224-s390", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c index b17eded532b1..be589c340d15 100644 --- a/arch/s390/crypto/sha512_s390.c +++ b/arch/s390/crypto/sha512_s390.c @@ -76,7 +76,6 @@ static struct shash_alg sha512_alg = { .cra_name = "sha512", .cra_driver_name= "sha512-s390", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -115,7 +114,6 @@ static struct shash_alg sha384_alg = { .cra_name = "sha384", .cra_driver_name= "sha384-s390", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_ctxsize = sizeof(struct s390_sha_ctx), .cra_module = THIS_MODULE, diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index a2945b289a29..3452e18bb1ca 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -497,7 +497,7 @@ static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info) } diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer); rc = hypfs_create_str(cpu_dir, "type", buffer); - return PTR_RET(rc); + return PTR_ERR_OR_ZERO(rc); } static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr) @@ -544,7 +544,7 @@ static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info) return PTR_ERR(rc); diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer); rc = hypfs_create_str(cpu_dir, "type", buffer); - return PTR_RET(rc); + return PTR_ERR_OR_ZERO(rc); } static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr) diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 06b513d192b9..c681329fdeec 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -36,7 +36,7 @@ struct hypfs_sb_info { kuid_t uid; /* uid used for files and dirs */ kgid_t gid; /* gid used for files and dirs */ struct dentry *update_file; /* file to trigger update */ - time_t last_update; /* last update time in secs since 1970 */ + time64_t last_update; /* last update, CLOCK_MONOTONIC time */ struct mutex lock; /* lock to protect update process */ }; @@ -52,7 +52,7 @@ static void hypfs_update_update(struct super_block *sb) struct hypfs_sb_info *sb_info = sb->s_fs_info; struct inode *inode = d_inode(sb_info->update_file); - sb_info->last_update = get_seconds(); + sb_info->last_update = ktime_get_seconds(); inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); } @@ -179,7 +179,7 @@ static ssize_t hypfs_write_iter(struct kiocb *iocb, struct iov_iter *from) * to restart data collection in this case. */ mutex_lock(&fs_info->lock); - if (fs_info->last_update == get_seconds()) { + if (fs_info->last_update == ktime_get_seconds()) { rc = -EBUSY; goto out; } diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index c1bedb4c8de0..046e044a48d0 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -47,6 +47,50 @@ struct ap_queue_status { }; /** + * ap_intructions_available() - Test if AP instructions are available. + * + * Returns 0 if the AP instructions are installed. + */ +static inline int ap_instructions_available(void) +{ + register unsigned long reg0 asm ("0") = AP_MKQID(0, 0); + register unsigned long reg1 asm ("1") = -ENODEV; + register unsigned long reg2 asm ("2"); + + asm volatile( + " .long 0xb2af0000\n" /* PQAP(TAPQ) */ + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b, 1b) + : "+d" (reg1), "=d" (reg2) + : "d" (reg0) + : "cc"); + return reg1; +} + +/** + * ap_tapq(): Test adjunct processor queue. + * @qid: The AP queue number + * @info: Pointer to queue descriptor + * + * Returns AP queue status structure. + */ +static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info) +{ + register unsigned long reg0 asm ("0") = qid; + register struct ap_queue_status reg1 asm ("1"); + register unsigned long reg2 asm ("2"); + + asm volatile(".long 0xb2af0000" /* PQAP(TAPQ) */ + : "=d" (reg1), "=d" (reg2) + : "d" (reg0) + : "cc"); + if (info) + *info = reg2; + return reg1; +} + +/** * ap_test_queue(): Test adjunct processor queue. * @qid: The AP queue number * @tbit: Test facilities bit @@ -54,10 +98,57 @@ struct ap_queue_status { * * Returns AP queue status structure. */ -struct ap_queue_status ap_test_queue(ap_qid_t qid, - int tbit, - unsigned long *info); +static inline struct ap_queue_status ap_test_queue(ap_qid_t qid, + int tbit, + unsigned long *info) +{ + if (tbit) + qid |= 1UL << 23; /* set T bit*/ + return ap_tapq(qid, info); +} +/** + * ap_pqap_rapq(): Reset adjunct processor queue. + * @qid: The AP queue number + * + * Returns AP queue status structure. + */ +static inline struct ap_queue_status ap_rapq(ap_qid_t qid) +{ + register unsigned long reg0 asm ("0") = qid | (1UL << 24); + register struct ap_queue_status reg1 asm ("1"); + + asm volatile( + ".long 0xb2af0000" /* PQAP(RAPQ) */ + : "=d" (reg1) + : "d" (reg0) + : "cc"); + return reg1; +} + +/** + * ap_pqap_zapq(): Reset and zeroize adjunct processor queue. + * @qid: The AP queue number + * + * Returns AP queue status structure. + */ +static inline struct ap_queue_status ap_zapq(ap_qid_t qid) +{ + register unsigned long reg0 asm ("0") = qid | (2UL << 24); + register struct ap_queue_status reg1 asm ("1"); + + asm volatile( + ".long 0xb2af0000" /* PQAP(ZAPQ) */ + : "=d" (reg1) + : "d" (reg0) + : "cc"); + return reg1; +} + +/** + * struct ap_config_info - convenience struct for AP crypto + * config info as returned by the ap_qci() function. + */ struct ap_config_info { unsigned int apsc : 1; /* S bit */ unsigned int apxa : 1; /* N bit */ @@ -74,50 +165,189 @@ struct ap_config_info { unsigned char _reserved4[16]; } __aligned(8); -/* - * ap_query_configuration(): Fetch cryptographic config info +/** + * ap_qci(): Get AP configuration data * - * Returns the ap configuration info fetched via PQAP(QCI). - * On success 0 is returned, on failure a negative errno - * is returned, e.g. if the PQAP(QCI) instruction is not - * available, the return value will be -EOPNOTSUPP. + * Returns 0 on success, or -EOPNOTSUPP. */ -int ap_query_configuration(struct ap_config_info *info); +static inline int ap_qci(struct ap_config_info *config) +{ + register unsigned long reg0 asm ("0") = 4UL << 24; + register unsigned long reg1 asm ("1") = -EOPNOTSUPP; + register struct ap_config_info *reg2 asm ("2") = config; + + asm volatile( + ".long 0xb2af0000\n" /* PQAP(QCI) */ + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b, 1b) + : "+d" (reg1) + : "d" (reg0), "d" (reg2) + : "cc", "memory"); + + return reg1; +} /* * struct ap_qirq_ctrl - convenient struct for easy invocation - * of the ap_queue_irq_ctrl() function. This struct is passed - * as GR1 parameter to the PQAP(AQIC) instruction. For details - * please see the AR documentation. + * of the ap_aqic() function. This struct is passed as GR1 + * parameter to the PQAP(AQIC) instruction. For details please + * see the AR documentation. */ struct ap_qirq_ctrl { unsigned int _res1 : 8; - unsigned int zone : 8; /* zone info */ - unsigned int ir : 1; /* ir flag: enable (1) or disable (0) irq */ + unsigned int zone : 8; /* zone info */ + unsigned int ir : 1; /* ir flag: enable (1) or disable (0) irq */ unsigned int _res2 : 4; - unsigned int gisc : 3; /* guest isc field */ + unsigned int gisc : 3; /* guest isc field */ unsigned int _res3 : 6; - unsigned int gf : 2; /* gisa format */ + unsigned int gf : 2; /* gisa format */ unsigned int _res4 : 1; - unsigned int gisa : 27; /* gisa origin */ + unsigned int gisa : 27; /* gisa origin */ unsigned int _res5 : 1; - unsigned int isc : 3; /* irq sub class */ + unsigned int isc : 3; /* irq sub class */ }; /** - * ap_queue_irq_ctrl(): Control interruption on a AP queue. + * ap_aqic(): Control interruption for a specific AP. * @qid: The AP queue number - * @qirqctrl: struct ap_qirq_ctrl, see above + * @qirqctrl: struct ap_qirq_ctrl (64 bit value) * @ind: The notification indicator byte * * Returns AP queue status. + */ +static inline struct ap_queue_status ap_aqic(ap_qid_t qid, + struct ap_qirq_ctrl qirqctrl, + void *ind) +{ + register unsigned long reg0 asm ("0") = qid | (3UL << 24); + register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl; + register struct ap_queue_status reg1_out asm ("1"); + register void *reg2 asm ("2") = ind; + + asm volatile( + ".long 0xb2af0000" /* PQAP(AQIC) */ + : "=d" (reg1_out) + : "d" (reg0), "d" (reg1_in), "d" (reg2) + : "cc"); + return reg1_out; +} + +/* + * union ap_qact_ap_info - used together with the + * ap_aqic() function to provide a convenient way + * to handle the ap info needed by the qact function. + */ +union ap_qact_ap_info { + unsigned long val; + struct { + unsigned int : 3; + unsigned int mode : 3; + unsigned int : 26; + unsigned int cat : 8; + unsigned int : 8; + unsigned char ver[2]; + }; +}; + +/** + * ap_qact(): Query AP combatibility type. + * @qid: The AP queue number + * @apinfo: On input the info about the AP queue. On output the + * alternate AP queue info provided by the qact function + * in GR2 is stored in. * - * Control interruption on the given AP queue. - * Just a simple wrapper function for the low level PQAP(AQIC) - * instruction available for other kernel modules. + * Returns AP queue status. Check response_code field for failures. */ -struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid, - struct ap_qirq_ctrl qirqctrl, - void *ind); +static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit, + union ap_qact_ap_info *apinfo) +{ + register unsigned long reg0 asm ("0") = qid | (5UL << 24) + | ((ifbit & 0x01) << 22); + register unsigned long reg1_in asm ("1") = apinfo->val; + register struct ap_queue_status reg1_out asm ("1"); + register unsigned long reg2 asm ("2"); + + asm volatile( + ".long 0xb2af0000" /* PQAP(QACT) */ + : "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2) + : "d" (reg0) + : "cc"); + apinfo->val = reg2; + return reg1_out; +} + +/** + * ap_nqap(): Send message to adjunct processor queue. + * @qid: The AP queue number + * @psmid: The program supplied message identifier + * @msg: The message text + * @length: The message length + * + * Returns AP queue status structure. + * Condition code 1 on NQAP can't happen because the L bit is 1. + * Condition code 2 on NQAP also means the send is incomplete, + * because a segment boundary was reached. The NQAP is repeated. + */ +static inline struct ap_queue_status ap_nqap(ap_qid_t qid, + unsigned long long psmid, + void *msg, size_t length) +{ + register unsigned long reg0 asm ("0") = qid | 0x40000000UL; + register struct ap_queue_status reg1 asm ("1"); + register unsigned long reg2 asm ("2") = (unsigned long) msg; + register unsigned long reg3 asm ("3") = (unsigned long) length; + register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32); + register unsigned long reg5 asm ("5") = psmid & 0xffffffff; + + asm volatile ( + "0: .long 0xb2ad0042\n" /* NQAP */ + " brc 2,0b" + : "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3) + : "d" (reg4), "d" (reg5) + : "cc", "memory"); + return reg1; +} + +/** + * ap_dqap(): Receive message from adjunct processor queue. + * @qid: The AP queue number + * @psmid: Pointer to program supplied message identifier + * @msg: The message text + * @length: The message length + * + * Returns AP queue status structure. + * Condition code 1 on DQAP means the receive has taken place + * but only partially. The response is incomplete, hence the + * DQAP is repeated. + * Condition code 2 on DQAP also means the receive is incomplete, + * this time because a segment boundary was reached. Again, the + * DQAP is repeated. + * Note that gpr2 is used by the DQAP instruction to keep track of + * any 'residual' length, in case the instruction gets interrupted. + * Hence it gets zeroed before the instruction. + */ +static inline struct ap_queue_status ap_dqap(ap_qid_t qid, + unsigned long long *psmid, + void *msg, size_t length) +{ + register unsigned long reg0 asm("0") = qid | 0x80000000UL; + register struct ap_queue_status reg1 asm ("1"); + register unsigned long reg2 asm("2") = 0UL; + register unsigned long reg4 asm("4") = (unsigned long) msg; + register unsigned long reg5 asm("5") = (unsigned long) length; + register unsigned long reg6 asm("6") = 0UL; + register unsigned long reg7 asm("7") = 0UL; + + + asm volatile( + "0: .long 0xb2ae0064\n" /* DQAP */ + " brc 6,0b\n" + : "+d" (reg0), "=d" (reg1), "+d" (reg2), + "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7) + : : "cc", "memory"); + *psmid = (((unsigned long long) reg6) << 32) + reg7; + return reg1; +} #endif /* _ASM_S390_AP_H_ */ diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 4b55532f15c4..fd20ab5d4cf7 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -55,17 +55,9 @@ static inline void atomic_add(int i, atomic_t *v) __atomic_add(i, &v->counter); } -#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0) -#define atomic_inc(_v) atomic_add(1, _v) -#define atomic_inc_return(_v) atomic_add_return(1, _v) -#define atomic_inc_and_test(_v) (atomic_add_return(1, _v) == 0) #define atomic_sub(_i, _v) atomic_add(-(int)(_i), _v) #define atomic_sub_return(_i, _v) atomic_add_return(-(int)(_i), _v) #define atomic_fetch_sub(_i, _v) atomic_fetch_add(-(int)(_i), _v) -#define atomic_sub_and_test(_i, _v) (atomic_sub_return(_i, _v) == 0) -#define atomic_dec(_v) atomic_sub(1, _v) -#define atomic_dec_return(_v) atomic_sub_return(1, _v) -#define atomic_dec_and_test(_v) (atomic_sub_return(1, _v) == 0) #define ATOMIC_OPS(op) \ static inline void atomic_##op(int i, atomic_t *v) \ @@ -90,21 +82,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new) return __atomic_cmpxchg(&v->counter, old, new); } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == u)) - break; - old = atomic_cmpxchg(v, c, c + a); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define ATOMIC64_INIT(i) { (i) } static inline long atomic64_read(const atomic64_t *v) @@ -168,50 +145,8 @@ ATOMIC64_OPS(xor) #undef ATOMIC64_OPS -static inline int atomic64_add_unless(atomic64_t *v, long i, long u) -{ - long c, old; - - c = atomic64_read(v); - for (;;) { - if (unlikely(c == u)) - break; - old = atomic64_cmpxchg(v, c, c + i); - if (likely(old == c)) - break; - c = old; - } - return c != u; -} - -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long c, old, dec; - - c = atomic64_read(v); - for (;;) { - dec = c - 1; - if (unlikely(dec < 0)) - break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } - return dec; -} - -#define atomic64_add_negative(_i, _v) (atomic64_add_return(_i, _v) < 0) -#define atomic64_inc(_v) atomic64_add(1, _v) -#define atomic64_inc_return(_v) atomic64_add_return(1, _v) -#define atomic64_inc_and_test(_v) (atomic64_add_return(1, _v) == 0) #define atomic64_sub_return(_i, _v) atomic64_add_return(-(long)(_i), _v) #define atomic64_fetch_sub(_i, _v) atomic64_fetch_add(-(long)(_i), _v) #define atomic64_sub(_i, _v) atomic64_add(-(long)(_i), _v) -#define atomic64_sub_and_test(_i, _v) (atomic64_sub_return(_i, _v) == 0) -#define atomic64_dec(_v) atomic64_sub(1, _v) -#define atomic64_dec_return(_v) atomic64_sub_return(1, _v) -#define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #endif /* __ARCH_S390_ATOMIC__ */ diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index de023a9a88ca..bf2cbff926ef 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -2,7 +2,7 @@ /* * CPU-measurement facilities * - * Copyright IBM Corp. 2012 + * Copyright IBM Corp. 2012, 2018 * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> * Jan Glauber <jang@linux.vnet.ibm.com> */ @@ -139,8 +139,14 @@ struct hws_trailer_entry { unsigned char timestamp[16]; /* 16 - 31 timestamp */ unsigned long long reserved1; /* 32 -Reserved */ unsigned long long reserved2; /* */ - unsigned long long progusage1; /* 48 - reserved for programming use */ - unsigned long long progusage2; /* */ + union { /* 48 - reserved for programming use */ + struct { + unsigned int clock_base:1; /* in progusage2 */ + unsigned long long progusage1:63; + unsigned long long progusage2; + }; + unsigned long long progusage[2]; + }; } __packed; /* Load program parameter */ diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index e07cce88dfb0..fcbd638fb9f4 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -9,6 +9,14 @@ #ifndef _ASM_S390_GMAP_H #define _ASM_S390_GMAP_H +/* Generic bits for GMAP notification on DAT table entry changes. */ +#define GMAP_NOTIFY_SHADOW 0x2 +#define GMAP_NOTIFY_MPROT 0x1 + +/* Status bits only for huge segment entries */ +#define _SEGMENT_ENTRY_GMAP_IN 0x8000 /* invalidation notify bit */ +#define _SEGMENT_ENTRY_GMAP_UC 0x4000 /* dirty (migration) */ + /** * struct gmap_struct - guest address space * @list: list head for the mm->context gmap list @@ -132,4 +140,6 @@ void gmap_pte_notify(struct mm_struct *, unsigned long addr, pte_t *, int gmap_mprotect_notify(struct gmap *, unsigned long start, unsigned long len, int prot); +void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], + unsigned long gaddr, unsigned long vmaddr); #endif /* _ASM_S390_GMAP_H */ diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 9c5fc50204dd..2d1afa58a4b6 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -37,7 +37,10 @@ static inline int prepare_hugepage_range(struct file *file, return 0; } -#define arch_clear_hugepage_flags(page) do { } while (0) +static inline void arch_clear_hugepage_flags(struct page *page) +{ + clear_bit(PG_arch_1, &page->flags); +} static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 13de80cf741c..b106aa29bf55 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -68,8 +68,6 @@ struct kprobe_ctlblk { unsigned long kprobe_saved_imask; unsigned long kprobe_saved_ctl[3]; struct prev_kprobe prev_kprobe; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *p); diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index a2188e309bd6..29c940bf8506 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -269,6 +269,7 @@ struct kvm_s390_sie_block { __u8 reserved1c0[8]; /* 0x01c0 */ #define ECD_HOSTREGMGMT 0x20000000 #define ECD_MEF 0x08000000 +#define ECD_ETOKENF 0x02000000 __u32 ecd; /* 0x01c8 */ __u8 reserved1cc[18]; /* 0x01cc */ __u64 pp; /* 0x01de */ @@ -655,6 +656,7 @@ struct kvm_vcpu_arch { seqcount_t cputm_seqcount; __u64 cputm_start; bool gs_enabled; + bool skey_enabled; }; struct kvm_vm_stat { @@ -793,12 +795,6 @@ struct kvm_s390_vsie { struct page *pages[KVM_MAX_VCPUS]; }; -struct kvm_s390_migration_state { - unsigned long bitmap_size; /* in bits (number of guest pages) */ - atomic64_t dirty_pages; /* number of dirty pages */ - unsigned long *pgste_bitmap; -}; - struct kvm_arch{ void *sca; int use_esca; @@ -828,7 +824,8 @@ struct kvm_arch{ struct kvm_s390_vsie vsie; u8 epdx; u64 epoch; - struct kvm_s390_migration_state *migration_state; + int migration_mode; + atomic64_t cmma_dirty_pages; /* subset of available cpu features enabled by user space */ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); struct kvm_s390_gisa *gisa; diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 5bc888841eaf..406d940173ab 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -185,7 +185,7 @@ struct lowcore { /* Transaction abort diagnostic block */ __u8 pgm_tdb[256]; /* 0x1800 */ __u8 pad_0x1900[0x2000-0x1900]; /* 0x1900 */ -} __packed; +} __packed __aligned(8192); #define S390_lowcore (*((struct lowcore *) 0)) diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index f5ff9dbad8ac..f31a15044c24 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -24,6 +24,8 @@ typedef struct { unsigned int uses_skeys:1; /* The mmu context uses CMM. */ unsigned int uses_cmm:1; + /* The gmaps associated with this context are allowed to use huge pages. */ + unsigned int allow_gmap_hpage_1m:1; } mm_context_t; #define INIT_MM_CONTEXT(name) \ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index d16bc79c30bb..0717ee76885d 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -32,6 +32,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.has_pgste = 0; mm->context.uses_skeys = 0; mm->context.uses_cmm = 0; + mm->context.allow_gmap_hpage_1m = 0; #endif switch (mm->context.asce_limit) { case _REGION2_SIZE: diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h index a01f81186e86..123dac3717b3 100644 --- a/arch/s390/include/asm/nospec-insn.h +++ b/arch/s390/include/asm/nospec-insn.h @@ -8,7 +8,7 @@ #ifdef __ASSEMBLY__ -#ifdef CONFIG_EXPOLINE +#ifdef CC_USING_EXPOLINE _LC_BR_R1 = __LC_BR_R1 @@ -189,7 +189,7 @@ _LC_BR_R1 = __LC_BR_R1 .macro BASR_EX rsave,rtarget,ruse=%r1 basr \rsave,\rtarget .endm -#endif +#endif /* CC_USING_EXPOLINE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 94f8db468c9b..10fe982f2b4b 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -51,6 +51,10 @@ struct zpci_fmb_fmt2 { u64 max_work_units; }; +struct zpci_fmb_fmt3 { + u64 tx_bytes; +}; + struct zpci_fmb { u32 format : 8; u32 fmt_ind : 24; @@ -66,6 +70,7 @@ struct zpci_fmb { struct zpci_fmb_fmt0 fmt0; struct zpci_fmb_fmt1 fmt1; struct zpci_fmb_fmt2 fmt2; + struct zpci_fmb_fmt3 fmt3; }; } __packed __aligned(128); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 5ab636089c60..0e7cb0dc9c33 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -268,8 +268,10 @@ static inline int is_module_addr(void *addr) #define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL /* Bits in the segment table entry */ -#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL -#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL +#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL +#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL +#define _SEGMENT_ENTRY_HARDWARE_BITS 0xfffffffffffffe30UL +#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE 0xfffffffffff00730UL #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ #define _SEGMENT_ENTRY_ORIGIN ~0x7ffUL/* page table origin */ #define _SEGMENT_ENTRY_PROTECT 0x200 /* segment protection bit */ @@ -1101,7 +1103,8 @@ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *sptep, pte_t *tptep, pte_t pte); void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep); -bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address); +bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long address, + pte_t *ptep); int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, unsigned char key, bool nq); int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr, @@ -1116,6 +1119,10 @@ int set_pgste_bits(struct mm_struct *mm, unsigned long addr, int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep); int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, unsigned long *oldpte, unsigned long *oldpgste); +void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr); +void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr); +void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr); +void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr); /* * Certain architectures need to do special things when PTEs diff --git a/arch/s390/include/asm/purgatory.h b/arch/s390/include/asm/purgatory.h index 6090670df51f..e297bcfc476f 100644 --- a/arch/s390/include/asm/purgatory.h +++ b/arch/s390/include/asm/purgatory.h @@ -13,11 +13,5 @@ int verify_sha256_digest(void); -extern u64 kernel_entry; -extern u64 kernel_type; - -extern u64 crash_start; -extern u64 crash_size; - #endif /* __ASSEMBLY__ */ #endif /* _S390_PURGATORY_H_ */ diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index de11ecc99c7c..9c9970a5dfb1 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -262,7 +262,6 @@ struct qdio_outbuf_state { void *user; }; -#define QDIO_OUTBUF_STATE_FLAG_NONE 0x00 #define QDIO_OUTBUF_STATE_FLAG_PENDING 0x01 #define CHSC_AC1_INITIATE_INPUTQ 0x80 diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h index 54f81f8ed662..724faede8ac5 100644 --- a/arch/s390/include/asm/sections.h +++ b/arch/s390/include/asm/sections.h @@ -4,6 +4,4 @@ #include <asm-generic/sections.h> -extern char _ehead[]; - #endif diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 9c30ebe046f3..1d66016f4170 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -9,8 +9,10 @@ #include <linux/const.h> #include <uapi/asm/setup.h> - +#define EP_OFFSET 0x10008 +#define EP_STRING "S390EP" #define PARMAREA 0x10400 +#define PARMAREA_END 0x11000 /* * Machine features detected in early.c diff --git a/arch/s390/include/uapi/asm/chsc.h b/arch/s390/include/uapi/asm/chsc.h index dc329aa03f76..83a574e95b3a 100644 --- a/arch/s390/include/uapi/asm/chsc.h +++ b/arch/s390/include/uapi/asm/chsc.h @@ -23,29 +23,29 @@ struct chsc_async_header { __u32 key : 4; __u32 : 28; struct subchannel_id sid; -} __attribute__ ((packed)); +}; struct chsc_async_area { struct chsc_async_header header; __u8 data[CHSC_SIZE - sizeof(struct chsc_async_header)]; -} __attribute__ ((packed)); +}; struct chsc_header { __u16 length; __u16 code; -} __attribute__ ((packed)); +}; struct chsc_sync_area { struct chsc_header header; __u8 data[CHSC_SIZE - sizeof(struct chsc_header)]; -} __attribute__ ((packed)); +}; struct chsc_response_struct { __u16 length; __u16 code; __u32 parms; __u8 data[CHSC_SIZE - 2 * sizeof(__u16) - sizeof(__u32)]; -} __attribute__ ((packed)); +}; struct chsc_chp_cd { struct chp_id chpid; diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 4cdaa55fabfe..9a50f02b9894 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -4,7 +4,7 @@ /* * KVM s390 specific structures and definitions * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008, 2018 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -225,6 +225,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_FPRS (1UL << 8) #define KVM_SYNC_GSCB (1UL << 9) #define KVM_SYNC_BPBC (1UL << 10) +#define KVM_SYNC_ETOKEN (1UL << 11) /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) @@ -258,6 +259,8 @@ struct kvm_sync_regs { struct { __u64 reserved1[2]; __u64 gscb[4]; + __u64 etoken; + __u64 etoken_extension; }; }; }; diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 3510c0fd06f4..39d901476ee5 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -111,4 +111,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 2fed39b26b42..dbfd1730e631 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -9,39 +9,21 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) # Do not trace early setup code -CFLAGS_REMOVE_als.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_early_nobss.o = $(CC_FLAGS_FTRACE) endif -GCOV_PROFILE_als.o := n GCOV_PROFILE_early.o := n GCOV_PROFILE_early_nobss.o := n -KCOV_INSTRUMENT_als.o := n KCOV_INSTRUMENT_early.o := n KCOV_INSTRUMENT_early_nobss.o := n -UBSAN_SANITIZE_als.o := n UBSAN_SANITIZE_early.o := n UBSAN_SANITIZE_early_nobss.o := n # -# Use -march=z900 for als.c to be able to print an error -# message if the kernel is started on a machine which is too old -# -ifneq ($(CC_FLAGS_MARCH),-march=z900) -CFLAGS_REMOVE_als.o += $(CC_FLAGS_MARCH) -CFLAGS_REMOVE_als.o += $(CC_FLAGS_EXPOLINE) -CFLAGS_als.o += -march=z900 -AFLAGS_REMOVE_head.o += $(CC_FLAGS_MARCH) -AFLAGS_head.o += -march=z900 -endif - -CFLAGS_als.o += -D__NO_FORTIFY - -# # Passing null pointers is ok for smp code, since we access the lowcore here. # CFLAGS_smp.o := -Wno-nonnull @@ -61,13 +43,13 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' obj-y := traps.o time.o process.o base.o early.o setup.o idle.o vtime.o obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o -obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o als.o early_nobss.o +obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o obj-y += nospec-branch.o -extra-y += head.o head64.o vmlinux.lds +extra-y += head64.o vmlinux.lds obj-$(CONFIG_SYSFS) += nospec-sysfs.o CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE) @@ -99,5 +81,5 @@ obj-$(CONFIG_TRACEPOINTS) += trace.o obj-y += vdso64/ obj-$(CONFIG_COMPAT) += vdso32/ -chkbss := head.o head64.o als.o early_nobss.o +chkbss := head64.o early_nobss.o include $(srctree)/arch/s390/scripts/Makefile.chkbss diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 9f5ea9d87069..c3620bafc374 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -306,6 +306,15 @@ static void *kzalloc_panic(int len) return rc; } +static const char *nt_name(Elf64_Word type) +{ + const char *name = "LINUX"; + + if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG) + name = KEXEC_CORE_NOTE_NAME; + return name; +} + /* * Initialize ELF note */ @@ -332,11 +341,26 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len, static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len) { - const char *note_name = "LINUX"; + return nt_init_name(buf, type, desc, d_len, nt_name(type)); +} + +/* + * Calculate the size of ELF note + */ +static size_t nt_size_name(int d_len, const char *name) +{ + size_t size; - if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG) - note_name = KEXEC_CORE_NOTE_NAME; - return nt_init_name(buf, type, desc, d_len, note_name); + size = sizeof(Elf64_Nhdr); + size += roundup(strlen(name) + 1, 4); + size += roundup(d_len, 4); + + return size; +} + +static inline size_t nt_size(Elf64_Word type, int d_len) +{ + return nt_size_name(d_len, nt_name(type)); } /* @@ -375,6 +399,29 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa) } /* + * Calculate size of ELF notes per cpu + */ +static size_t get_cpu_elf_notes_size(void) +{ + struct save_area *sa = NULL; + size_t size; + + size = nt_size(NT_PRSTATUS, sizeof(struct elf_prstatus)); + size += nt_size(NT_PRFPREG, sizeof(elf_fpregset_t)); + size += nt_size(NT_S390_TIMER, sizeof(sa->timer)); + size += nt_size(NT_S390_TODCMP, sizeof(sa->todcmp)); + size += nt_size(NT_S390_TODPREG, sizeof(sa->todpreg)); + size += nt_size(NT_S390_CTRS, sizeof(sa->ctrs)); + size += nt_size(NT_S390_PREFIX, sizeof(sa->prefix)); + if (MACHINE_HAS_VX) { + size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high)); + size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low)); + } + + return size; +} + +/* * Initialize prpsinfo note (new kernel) */ static void *nt_prpsinfo(void *ptr) @@ -429,6 +476,30 @@ static void *nt_vmcoreinfo(void *ptr) return nt_init_name(ptr, 0, vmcoreinfo, size, "VMCOREINFO"); } +static size_t nt_vmcoreinfo_size(void) +{ + const char *name = "VMCOREINFO"; + char nt_name[11]; + Elf64_Nhdr note; + void *addr; + + if (copy_oldmem_kernel(&addr, &S390_lowcore.vmcore_info, sizeof(addr))) + return 0; + + if (copy_oldmem_kernel(¬e, addr, sizeof(note))) + return 0; + + memset(nt_name, 0, sizeof(nt_name)); + if (copy_oldmem_kernel(nt_name, addr + sizeof(note), + sizeof(nt_name) - 1)) + return 0; + + if (strcmp(nt_name, name) != 0) + return 0; + + return nt_size_name(note.n_descsz, name); +} + /* * Initialize final note (needed for /proc/vmcore code) */ @@ -539,6 +610,27 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) return ptr; } +static size_t get_elfcorehdr_size(int mem_chunk_cnt) +{ + size_t size; + + size = sizeof(Elf64_Ehdr); + /* PT_NOTES */ + size += sizeof(Elf64_Phdr); + /* nt_prpsinfo */ + size += nt_size(NT_PRPSINFO, sizeof(struct elf_prpsinfo)); + /* regsets */ + size += get_cpu_cnt() * get_cpu_elf_notes_size(); + /* nt_vmcoreinfo */ + size += nt_vmcoreinfo_size(); + /* nt_final */ + size += sizeof(Elf64_Nhdr); + /* PT_LOADS */ + size += mem_chunk_cnt * sizeof(Elf64_Phdr); + + return size; +} + /* * Create ELF core header (new kernel) */ @@ -566,8 +658,8 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) mem_chunk_cnt = get_mem_chunk_cnt(); - alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 + - mem_chunk_cnt * sizeof(Elf64_Phdr); + alloc_size = get_elfcorehdr_size(mem_chunk_cnt); + hdr = kzalloc_panic(alloc_size); /* Init elf header */ ptr = ehdr_init(hdr, mem_chunk_cnt); diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 827699eb48fa..5b28b434f8a1 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -331,8 +331,20 @@ static void __init setup_boot_command_line(void) append_to_cmdline(append_ipl_scpdata); } +static void __init check_image_bootable(void) +{ + if (!memcmp(EP_STRING, (void *)EP_OFFSET, strlen(EP_STRING))) + return; + + sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n"); + sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n"); + sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n"); + disabled_wait(0xbadb007); +} + void __init startup_init(void) { + check_image_bootable(); time_early_init(); init_kernel_storage_key(); lockdep_off(); diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 961abfac2c5f..472fa2f1a4a5 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -83,7 +83,6 @@ long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user DECLARE_PER_CPU(u64, mt_cycles[8]); -void verify_facilities(void); void gs_load_bc_cb(struct pt_regs *regs); void set_fs_fixup(void); diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 791cb9000e86..6d14ad42ba88 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -48,11 +48,23 @@ ENTRY(startup_continue) # Early machine initialization and detection functions. # brasl %r14,startup_init - lpswe .Lentry-.LPG1(13) # jump to _stext in primary-space, - # virtual and never return ... + +# check control registers + stctg %c0,%c15,0(%r15) + oi 6(%r15),0x60 # enable sigp emergency & external call + oi 4(%r15),0x10 # switch on low address proctection + lctlg %c0,%c15,0(%r15) + + lam 0,15,.Laregs-.LPG1(%r13) # load acrs needed by uaccess + brasl %r14,start_kernel # go to C code +# +# We returned from start_kernel ?!? PANIK +# + basr %r13,0 + lpswe .Ldw-.(%r13) # load disabled wait psw + .align 16 .LPG1: -.Lentry:.quad 0x0000000180000000,_stext .Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space .quad 0 # cr1: primary space segment table .quad .Lduct # cr2: dispatchable unit control table @@ -85,30 +97,5 @@ ENTRY(startup_continue) .endr .Llinkage_stack: .long 0,0,0x89000000,0,0,0,0x8a000000,0 - -ENTRY(_ehead) - - .org 0x100000 - 0x11000 # head.o ends at 0x11000 -# -# startup-code, running in absolute addressing mode -# -ENTRY(_stext) - basr %r13,0 # get base -.LPG3: -# check control registers - stctg %c0,%c15,0(%r15) - oi 6(%r15),0x60 # enable sigp emergency & external call - oi 4(%r15),0x10 # switch on low address proctection - lctlg %c0,%c15,0(%r15) - - lam 0,15,.Laregs-.LPG3(%r13) # load acrs needed by uaccess - brasl %r14,start_kernel # go to C code -# -# We returned from start_kernel ?!? PANIK -# - basr %r13,0 - lpswe .Ldw-.(%r13) # load disabled wait psw - - .align 8 .Ldw: .quad 0x0002000180000000,0x0000000000000000 .Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 60f60afa645c..7c0a095e9c5f 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -321,38 +321,20 @@ static int kprobe_handler(struct pt_regs *regs) * If we have no pre-handler or it returned 0, we * continue with single stepping. If we have a * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry - * for jprobe processing, so get out doing nothing - * more here. + * for changing execution path, so get out doing + * nothing more here. */ push_kprobe(kcb, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { + pop_kprobe(kcb); + preempt_enable_no_resched(); return 1; + } kcb->kprobe_status = KPROBE_HIT_SS; } enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn); return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - /* - * Continuation after the jprobe completed and - * caused the jprobe_return trap. The jprobe - * break_handler "returns" to the original - * function that still has the kprobe breakpoint - * installed. We continue with single stepping. - */ - kcb->kprobe_status = KPROBE_HIT_SS; - enable_singlestep(kcb, regs, - (unsigned long) p->ainsn.insn); - return 1; - } /* else: - * No kprobe at this address and the current kprobe - * has no break handler (no jprobe!). The kernel just - * exploded, let the standard trap handler pick up the - * pieces. - */ } /* else: * No kprobe at this address and no active kprobe. The trap has * not been caused by a kprobe breakpoint. The race of breakpoint @@ -452,9 +434,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) regs->psw.addr = orig_ret_address; - pop_kprobe(get_kprobe_ctlblk()); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); @@ -661,60 +641,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, } NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack; - - memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); - - /* setup return addr to the jprobe handler routine */ - regs->psw.addr = (unsigned long) jp->entry; - regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); - - /* r15 is the stack pointer */ - stack = (unsigned long) regs->gprs[15]; - - memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack)); - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer to get messed up. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void jprobe_return(void) -{ - asm volatile(".word 0x0002"); -} -NOKPROBE_SYMBOL(jprobe_return); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack; - - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - - stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15]; - - /* Put the regs back */ - memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); - /* put the stack back */ - memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack)); - preempt_enable_no_resched(); - return 1; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - static struct kprobe trampoline = { .addr = (kprobe_opcode_t *) &kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index 18ae7b9c71d6..bdddaae96559 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -35,6 +35,8 @@ early_param("nospec", nospec_setup_early); static int __init nospec_report(void) { + if (test_facility(156)) + pr_info("Spectre V2 mitigation: etokens\n"); if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) pr_info("Spectre V2 mitigation: execute trampolines\n"); if (__test_facility(82, S390_lowcore.alt_stfle_fac_list)) @@ -56,7 +58,15 @@ early_param("nospectre_v2", nospectre_v2_setup_early); void __init nospec_auto_detect(void) { - if (IS_ENABLED(CC_USING_EXPOLINE)) { + if (test_facility(156)) { + /* + * The machine supports etokens. + * Disable expolines and disable nobp. + */ + if (IS_ENABLED(CC_USING_EXPOLINE)) + nospec_disable = 1; + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); + } else if (IS_ENABLED(CC_USING_EXPOLINE)) { /* * The kernel has been compiled with expolines. * Keep expolines enabled and disable nobp. diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c index 8affad5f18cb..e30e580ae362 100644 --- a/arch/s390/kernel/nospec-sysfs.c +++ b/arch/s390/kernel/nospec-sysfs.c @@ -13,6 +13,8 @@ ssize_t cpu_show_spectre_v1(struct device *dev, ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { + if (test_facility(156)) + return sprintf(buf, "Mitigation: etokens\n"); if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) return sprintf(buf, "Mitigation: execute trampolines\n"); if (__test_facility(82, S390_lowcore.alt_stfle_fac_list)) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 0292d68e7dde..cb198d4a6dca 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -2,7 +2,7 @@ /* * Performance event support for the System z CPU-measurement Sampling Facility * - * Copyright IBM Corp. 2013 + * Copyright IBM Corp. 2013, 2018 * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> */ #define KMSG_COMPONENT "cpum_sf" @@ -1587,6 +1587,17 @@ static void aux_buffer_free(void *data) "%lu SDBTs\n", num_sdbt); } +static void aux_sdb_init(unsigned long sdb) +{ + struct hws_trailer_entry *te; + + te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb); + + /* Save clock base */ + te->clock_base = 1; + memcpy(&te->progusage2, &tod_clock_base[1], 8); +} + /* * aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling * @cpu: On which to allocate, -1 means current @@ -1666,6 +1677,7 @@ static void *aux_buffer_setup(int cpu, void **pages, int nr_pages, /* Tail is the entry in a SDBT */ *tail = (unsigned long)pages[i]; aux->sdb_index[i] = (unsigned long)pages[i]; + aux_sdb_init((unsigned long)pages[i]); } sfb->num_sdb = nr_pages; diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c index 54e2d634b849..4352a504f235 100644 --- a/arch/s390/kernel/perf_regs.c +++ b/arch/s390/kernel/perf_regs.c @@ -12,9 +12,6 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) { freg_t fp; - if (WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX)) - return 0; - if (idx >= PERF_REG_S390_R0 && idx <= PERF_REG_S390_R15) return regs->gprs[idx]; @@ -33,7 +30,8 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) if (idx == PERF_REG_S390_PC) return regs->psw.addr; - return regs->gprs[idx]; + WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX); + return 0; } #define REG_RESERVED (~((1UL << PERF_REG_S390_MAX) - 1)) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index d82a9ec64ea9..c637c12f9e37 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -674,12 +674,12 @@ static void __init reserve_kernel(void) #ifdef CONFIG_DMA_API_DEBUG /* * DMA_API_DEBUG code stumbles over addresses from the - * range [_ehead, _stext]. Mark the memory as reserved + * range [PARMAREA_END, _stext]. Mark the memory as reserved * so it is not used for CONFIG_DMA_API_DEBUG=y. */ memblock_reserve(0, PFN_PHYS(start_pfn)); #else - memblock_reserve(0, (unsigned long)_ehead); + memblock_reserve(0, PARMAREA_END); memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn) - (unsigned long)_stext); #endif diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile index 8ff96c08955f..4d929edc80a6 100644 --- a/arch/s390/kernel/syscalls/Makefile +++ b/arch/s390/kernel/syscalls/Makefile @@ -25,15 +25,15 @@ _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') define filechk_syshdr - $(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2" + $(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2" < $< endef define filechk_sysnr - $(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget)) + $(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget)) < $< endef define filechk_syscalls - $(CONFIG_SHELL) '$(systbl)' -S + $(CONFIG_SHELL) '$(systbl)' -S < $< endef syshdr_abi_unistd_32 := common,32 diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 54f5496913fa..12f80d1f0415 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -59,6 +59,8 @@ int stsi(void *sysinfo, int fc, int sel1, int sel2) } EXPORT_SYMBOL(stsi); +#ifdef CONFIG_PROC_FS + static bool convert_ext_name(unsigned char encoding, char *name, size_t len) { switch (encoding) { @@ -301,6 +303,8 @@ static int __init sysinfo_create_proc(void) } device_initcall(sysinfo_create_proc); +#endif /* CONFIG_PROC_FS */ + /* * Service levels interface. */ diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index cf561160ea88..e8766beee5ad 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -221,17 +221,22 @@ void read_persistent_clock64(struct timespec64 *ts) ext_to_timespec64(clk, ts); } -void read_boot_clock64(struct timespec64 *ts) +void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, + struct timespec64 *boot_offset) { unsigned char clk[STORE_CLOCK_EXT_SIZE]; + struct timespec64 boot_time; __u64 delta; delta = initial_leap_seconds + TOD_UNIX_EPOCH; - memcpy(clk, tod_clock_base, 16); - *(__u64 *) &clk[1] -= delta; - if (*(__u64 *) &clk[1] > delta) + memcpy(clk, tod_clock_base, STORE_CLOCK_EXT_SIZE); + *(__u64 *)&clk[1] -= delta; + if (*(__u64 *)&clk[1] > delta) clk[0]--; - ext_to_timespec64(clk, ts); + ext_to_timespec64(clk, &boot_time); + + read_persistent_clock64(wall_time); + *boot_offset = timespec64_sub(*wall_time, boot_time); } static u64 read_tod_clock(struct clocksource *cs) diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 4b6e0397f66d..e8184a15578a 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -579,41 +579,33 @@ early_param("topology", topology_setup); static int topology_ctl_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - unsigned int len; + int enabled = topology_is_enabled(); int new_mode; - char buf[2]; + int zero = 0; + int one = 1; + int rc; + struct ctl_table ctl_entry = { + .procname = ctl->procname, + .data = &enabled, + .maxlen = sizeof(int), + .extra1 = &zero, + .extra2 = &one, + }; + + rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos); + if (rc < 0 || !write) + return rc; - if (!*lenp || *ppos) { - *lenp = 0; - return 0; - } - if (!write) { - strncpy(buf, topology_is_enabled() ? "1\n" : "0\n", - ARRAY_SIZE(buf)); - len = strnlen(buf, ARRAY_SIZE(buf)); - if (len > *lenp) - len = *lenp; - if (copy_to_user(buffer, buf, len)) - return -EFAULT; - goto out; - } - len = *lenp; - if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) - return -EFAULT; - if (buf[0] != '0' && buf[0] != '1') - return -EINVAL; mutex_lock(&smp_cpu_state_mutex); - new_mode = topology_get_mode(buf[0] == '1'); + new_mode = topology_get_mode(enabled); if (topology_mode != new_mode) { topology_mode = new_mode; topology_schedule_update(); } mutex_unlock(&smp_cpu_state_mutex); topology_flush_work(); -out: - *lenp = len; - *ppos += len; - return 0; + + return rc; } static struct ctl_table topology_ctl_table[] = { diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 09abae40f917..3031cc6dd0ab 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -47,7 +47,7 @@ static struct page **vdso64_pagelist; */ unsigned int __read_mostly vdso_enabled = 1; -static int vdso_fault(const struct vm_special_mapping *sm, +static vm_fault_t vdso_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf) { struct page **vdso_pagelist; diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index f0414f52817b..b43f8d33a369 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -19,7 +19,7 @@ OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390") OUTPUT_ARCH(s390:64-bit) -ENTRY(startup) +ENTRY(startup_continue) jiffies = jiffies_64; PHDRS { @@ -30,16 +30,12 @@ PHDRS { SECTIONS { - . = 0x00000000; + . = 0x100000; + _stext = .; /* Start of text section */ .text : { /* Text and read-only data */ + _text = .; HEAD_TEXT - /* - * E.g. perf doesn't like symbols starting at address zero, - * therefore skip the initial PSW and channel program located - * at address zero and let _text start at 0x200. - */ - _text = 0x200; TEXT_TEXT SCHED_TEXT CPUIDLE_TEXT @@ -47,6 +43,7 @@ SECTIONS KPROBES_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT + *(.text.*_indirect_*) *(.fixup) *(.gnu.warning) } :text = 0x0700 diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index daa09f89ca2d..fcb55b02990e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1145,7 +1145,7 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) * yield-candidate. */ vcpu->preempted = true; - swake_up(&vcpu->wq); + swake_up_one(&vcpu->wq); vcpu->stat.halt_wakeup++; } /* diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3b7a5151b6a5..91ad4a9425c0 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -172,6 +172,10 @@ static int nested; module_param(nested, int, S_IRUGO); MODULE_PARM_DESC(nested, "Nested virtualization support"); +/* allow 1m huge page guest backing, if !nested */ +static int hpage; +module_param(hpage, int, 0444); +MODULE_PARM_DESC(hpage, "1m huge page backing support"); /* * For now we handle at most 16 double words as this is what the s390 base @@ -475,6 +479,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_AIS_MIGRATION: r = 1; break; + case KVM_CAP_S390_HPAGE_1M: + r = 0; + if (hpage) + r = 1; + break; case KVM_CAP_S390_MEM_OP: r = MEM_OP_MAX_SIZE; break; @@ -511,19 +520,30 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) } static void kvm_s390_sync_dirty_log(struct kvm *kvm, - struct kvm_memory_slot *memslot) + struct kvm_memory_slot *memslot) { + int i; gfn_t cur_gfn, last_gfn; - unsigned long address; + unsigned long gaddr, vmaddr; struct gmap *gmap = kvm->arch.gmap; + DECLARE_BITMAP(bitmap, _PAGE_ENTRIES); - /* Loop over all guest pages */ + /* Loop over all guest segments */ + cur_gfn = memslot->base_gfn; last_gfn = memslot->base_gfn + memslot->npages; - for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) { - address = gfn_to_hva_memslot(memslot, cur_gfn); + for (; cur_gfn <= last_gfn; cur_gfn += _PAGE_ENTRIES) { + gaddr = gfn_to_gpa(cur_gfn); + vmaddr = gfn_to_hva_memslot(memslot, cur_gfn); + if (kvm_is_error_hva(vmaddr)) + continue; + + bitmap_zero(bitmap, _PAGE_ENTRIES); + gmap_sync_dirty_log_pmd(gmap, bitmap, gaddr, vmaddr); + for (i = 0; i < _PAGE_ENTRIES; i++) { + if (test_bit(i, bitmap)) + mark_page_dirty(kvm, cur_gfn + i); + } - if (test_and_clear_guest_dirty(gmap->mm, address)) - mark_page_dirty(kvm, cur_gfn); if (fatal_signal_pending(current)) return; cond_resched(); @@ -667,6 +687,27 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s", r ? "(not available)" : "(success)"); break; + case KVM_CAP_S390_HPAGE_1M: + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) + r = -EBUSY; + else if (!hpage || kvm->arch.use_cmma) + r = -EINVAL; + else { + r = 0; + kvm->mm->context.allow_gmap_hpage_1m = 1; + /* + * We might have to create fake 4k page + * tables. To avoid that the hardware works on + * stale PGSTEs, we emulate these instructions. + */ + kvm->arch.use_skf = 0; + kvm->arch.use_pfmfi = 0; + } + mutex_unlock(&kvm->lock); + VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s", + r ? "(not available)" : "(success)"); + break; case KVM_CAP_S390_USER_STSI: VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI"); kvm->arch.user_stsi = 1; @@ -714,10 +755,13 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att if (!sclp.has_cmma) break; - ret = -EBUSY; VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support"); mutex_lock(&kvm->lock); - if (!kvm->created_vcpus) { + if (kvm->created_vcpus) + ret = -EBUSY; + else if (kvm->mm->context.allow_gmap_hpage_1m) + ret = -EINVAL; + else { kvm->arch.use_cmma = 1; /* Not compatible with cmma. */ kvm->arch.use_pfmfi = 0; @@ -862,54 +906,37 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) */ static int kvm_s390_vm_start_migration(struct kvm *kvm) { - struct kvm_s390_migration_state *mgs; struct kvm_memory_slot *ms; - /* should be the only one */ struct kvm_memslots *slots; - unsigned long ram_pages; + unsigned long ram_pages = 0; int slotnr; /* migration mode already enabled */ - if (kvm->arch.migration_state) + if (kvm->arch.migration_mode) return 0; - slots = kvm_memslots(kvm); if (!slots || !slots->used_slots) return -EINVAL; - mgs = kzalloc(sizeof(*mgs), GFP_KERNEL); - if (!mgs) - return -ENOMEM; - kvm->arch.migration_state = mgs; - - if (kvm->arch.use_cmma) { + if (!kvm->arch.use_cmma) { + kvm->arch.migration_mode = 1; + return 0; + } + /* mark all the pages in active slots as dirty */ + for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { + ms = slots->memslots + slotnr; /* - * Get the first slot. They are reverse sorted by base_gfn, so - * the first slot is also the one at the end of the address - * space. We have verified above that at least one slot is - * present. + * The second half of the bitmap is only used on x86, + * and would be wasted otherwise, so we put it to good + * use here to keep track of the state of the storage + * attributes. */ - ms = slots->memslots; - /* round up so we only use full longs */ - ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG); - /* allocate enough bytes to store all the bits */ - mgs->pgste_bitmap = vmalloc(ram_pages / 8); - if (!mgs->pgste_bitmap) { - kfree(mgs); - kvm->arch.migration_state = NULL; - return -ENOMEM; - } - - mgs->bitmap_size = ram_pages; - atomic64_set(&mgs->dirty_pages, ram_pages); - /* mark all the pages in active slots as dirty */ - for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { - ms = slots->memslots + slotnr; - bitmap_set(mgs->pgste_bitmap, ms->base_gfn, ms->npages); - } - - kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION); + memset(kvm_second_dirty_bitmap(ms), 0xff, kvm_dirty_bitmap_bytes(ms)); + ram_pages += ms->npages; } + atomic64_set(&kvm->arch.cmma_dirty_pages, ram_pages); + kvm->arch.migration_mode = 1; + kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION); return 0; } @@ -919,21 +946,12 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) */ static int kvm_s390_vm_stop_migration(struct kvm *kvm) { - struct kvm_s390_migration_state *mgs; - /* migration mode already disabled */ - if (!kvm->arch.migration_state) + if (!kvm->arch.migration_mode) return 0; - mgs = kvm->arch.migration_state; - kvm->arch.migration_state = NULL; - - if (kvm->arch.use_cmma) { + kvm->arch.migration_mode = 0; + if (kvm->arch.use_cmma) kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION); - /* We have to wait for the essa emulation to finish */ - synchronize_srcu(&kvm->srcu); - vfree(mgs->pgste_bitmap); - } - kfree(mgs); return 0; } @@ -961,7 +979,7 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm, static int kvm_s390_vm_get_migration(struct kvm *kvm, struct kvm_device_attr *attr) { - u64 mig = (kvm->arch.migration_state != NULL); + u64 mig = kvm->arch.migration_mode; if (attr->attr != KVM_S390_VM_MIGRATION_STATUS) return -ENXIO; @@ -1540,6 +1558,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) uint8_t *keys; uint64_t hva; int srcu_idx, i, r = 0; + bool unlocked; if (args->flags != 0) return -EINVAL; @@ -1564,9 +1583,11 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) if (r) goto out; + i = 0; down_read(¤t->mm->mmap_sem); srcu_idx = srcu_read_lock(&kvm->srcu); - for (i = 0; i < args->count; i++) { + while (i < args->count) { + unlocked = false; hva = gfn_to_hva(kvm, args->start_gfn + i); if (kvm_is_error_hva(hva)) { r = -EFAULT; @@ -1580,8 +1601,14 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) } r = set_guest_storage_key(current->mm, hva, keys[i], 0); - if (r) - break; + if (r) { + r = fixup_user_fault(current, current->mm, hva, + FAULT_FLAG_WRITE, &unlocked); + if (r) + break; + } + if (!r) + i++; } srcu_read_unlock(&kvm->srcu, srcu_idx); up_read(¤t->mm->mmap_sem); @@ -1600,6 +1627,134 @@ out: #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX) /* + * Similar to gfn_to_memslot, but returns the index of a memslot also when the + * address falls in a hole. In that case the index of one of the memslots + * bordering the hole is returned. + */ +static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) +{ + int start = 0, end = slots->used_slots; + int slot = atomic_read(&slots->lru_slot); + struct kvm_memory_slot *memslots = slots->memslots; + + if (gfn >= memslots[slot].base_gfn && + gfn < memslots[slot].base_gfn + memslots[slot].npages) + return slot; + + while (start < end) { + slot = start + (end - start) / 2; + + if (gfn >= memslots[slot].base_gfn) + end = slot; + else + start = slot + 1; + } + + if (gfn >= memslots[start].base_gfn && + gfn < memslots[start].base_gfn + memslots[start].npages) { + atomic_set(&slots->lru_slot, start); + } + + return start; +} + +static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, + u8 *res, unsigned long bufsize) +{ + unsigned long pgstev, hva, cur_gfn = args->start_gfn; + + args->count = 0; + while (args->count < bufsize) { + hva = gfn_to_hva(kvm, cur_gfn); + /* + * We return an error if the first value was invalid, but we + * return successfully if at least one value was copied. + */ + if (kvm_is_error_hva(hva)) + return args->count ? 0 : -EFAULT; + if (get_pgste(kvm->mm, hva, &pgstev) < 0) + pgstev = 0; + res[args->count++] = (pgstev >> 24) & 0x43; + cur_gfn++; + } + + return 0; +} + +static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots, + unsigned long cur_gfn) +{ + int slotidx = gfn_to_memslot_approx(slots, cur_gfn); + struct kvm_memory_slot *ms = slots->memslots + slotidx; + unsigned long ofs = cur_gfn - ms->base_gfn; + + if (ms->base_gfn + ms->npages <= cur_gfn) { + slotidx--; + /* If we are above the highest slot, wrap around */ + if (slotidx < 0) + slotidx = slots->used_slots - 1; + + ms = slots->memslots + slotidx; + ofs = 0; + } + ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs); + while ((slotidx > 0) && (ofs >= ms->npages)) { + slotidx--; + ms = slots->memslots + slotidx; + ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0); + } + return ms->base_gfn + ofs; +} + +static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, + u8 *res, unsigned long bufsize) +{ + unsigned long mem_end, cur_gfn, next_gfn, hva, pgstev; + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *ms; + + cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); + ms = gfn_to_memslot(kvm, cur_gfn); + args->count = 0; + args->start_gfn = cur_gfn; + if (!ms) + return 0; + next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1); + mem_end = slots->memslots[0].base_gfn + slots->memslots[0].npages; + + while (args->count < bufsize) { + hva = gfn_to_hva(kvm, cur_gfn); + if (kvm_is_error_hva(hva)) + return 0; + /* Decrement only if we actually flipped the bit to 0 */ + if (test_and_clear_bit(cur_gfn - ms->base_gfn, kvm_second_dirty_bitmap(ms))) + atomic64_dec(&kvm->arch.cmma_dirty_pages); + if (get_pgste(kvm->mm, hva, &pgstev) < 0) + pgstev = 0; + /* Save the value */ + res[args->count++] = (pgstev >> 24) & 0x43; + /* If the next bit is too far away, stop. */ + if (next_gfn > cur_gfn + KVM_S390_MAX_BIT_DISTANCE) + return 0; + /* If we reached the previous "next", find the next one */ + if (cur_gfn == next_gfn) + next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1); + /* Reached the end of memory or of the buffer, stop */ + if ((next_gfn >= mem_end) || + (next_gfn - args->start_gfn >= bufsize)) + return 0; + cur_gfn++; + /* Reached the end of the current memslot, take the next one. */ + if (cur_gfn - ms->base_gfn >= ms->npages) { + ms = gfn_to_memslot(kvm, cur_gfn); + if (!ms) + return 0; + } + } + return 0; +} + +/* * This function searches for the next page with dirty CMMA attributes, and * saves the attributes in the buffer up to either the end of the buffer or * until a block of at least KVM_S390_MAX_BIT_DISTANCE clean bits is found; @@ -1610,22 +1765,18 @@ out: static int kvm_s390_get_cmma_bits(struct kvm *kvm, struct kvm_s390_cmma_log *args) { - struct kvm_s390_migration_state *s = kvm->arch.migration_state; - unsigned long bufsize, hva, pgstev, i, next, cur; - int srcu_idx, peek, r = 0, rr; - u8 *res; - - cur = args->start_gfn; - i = next = pgstev = 0; + unsigned long bufsize; + int srcu_idx, peek, ret; + u8 *values; - if (unlikely(!kvm->arch.use_cmma)) + if (!kvm->arch.use_cmma) return -ENXIO; /* Invalid/unsupported flags were specified */ if (args->flags & ~KVM_S390_CMMA_PEEK) return -EINVAL; /* Migration mode query, and we are not doing a migration */ peek = !!(args->flags & KVM_S390_CMMA_PEEK); - if (!peek && !s) + if (!peek && !kvm->arch.migration_mode) return -EINVAL; /* CMMA is disabled or was not used, or the buffer has length zero */ bufsize = min(args->count, KVM_S390_CMMA_SIZE_MAX); @@ -1633,74 +1784,35 @@ static int kvm_s390_get_cmma_bits(struct kvm *kvm, memset(args, 0, sizeof(*args)); return 0; } - - if (!peek) { - /* We are not peeking, and there are no dirty pages */ - if (!atomic64_read(&s->dirty_pages)) { - memset(args, 0, sizeof(*args)); - return 0; - } - cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, - args->start_gfn); - if (cur >= s->bitmap_size) /* nothing found, loop back */ - cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, 0); - if (cur >= s->bitmap_size) { /* again! (very unlikely) */ - memset(args, 0, sizeof(*args)); - return 0; - } - next = find_next_bit(s->pgste_bitmap, s->bitmap_size, cur + 1); + /* We are not peeking, and there are no dirty pages */ + if (!peek && !atomic64_read(&kvm->arch.cmma_dirty_pages)) { + memset(args, 0, sizeof(*args)); + return 0; } - res = vmalloc(bufsize); - if (!res) + values = vmalloc(bufsize); + if (!values) return -ENOMEM; - args->start_gfn = cur; - down_read(&kvm->mm->mmap_sem); srcu_idx = srcu_read_lock(&kvm->srcu); - while (i < bufsize) { - hva = gfn_to_hva(kvm, cur); - if (kvm_is_error_hva(hva)) { - r = -EFAULT; - break; - } - /* decrement only if we actually flipped the bit to 0 */ - if (!peek && test_and_clear_bit(cur, s->pgste_bitmap)) - atomic64_dec(&s->dirty_pages); - r = get_pgste(kvm->mm, hva, &pgstev); - if (r < 0) - pgstev = 0; - /* save the value */ - res[i++] = (pgstev >> 24) & 0x43; - /* - * if the next bit is too far away, stop. - * if we reached the previous "next", find the next one - */ - if (!peek) { - if (next > cur + KVM_S390_MAX_BIT_DISTANCE) - break; - if (cur == next) - next = find_next_bit(s->pgste_bitmap, - s->bitmap_size, cur + 1); - /* reached the end of the bitmap or of the buffer, stop */ - if ((next >= s->bitmap_size) || - (next >= args->start_gfn + bufsize)) - break; - } - cur++; - } + if (peek) + ret = kvm_s390_peek_cmma(kvm, args, values, bufsize); + else + ret = kvm_s390_get_cmma(kvm, args, values, bufsize); srcu_read_unlock(&kvm->srcu, srcu_idx); up_read(&kvm->mm->mmap_sem); - args->count = i; - args->remaining = s ? atomic64_read(&s->dirty_pages) : 0; - rr = copy_to_user((void __user *)args->values, res, args->count); - if (rr) - r = -EFAULT; + if (kvm->arch.migration_mode) + args->remaining = atomic64_read(&kvm->arch.cmma_dirty_pages); + else + args->remaining = 0; - vfree(res); - return r; + if (copy_to_user((void __user *)args->values, values, args->count)) + ret = -EFAULT; + + vfree(values); + return ret; } /* @@ -2139,10 +2251,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_s390_destroy_adapters(kvm); kvm_s390_clear_float_irqs(kvm); kvm_s390_vsie_destroy(kvm); - if (kvm->arch.migration_state) { - vfree(kvm->arch.migration_state->pgste_bitmap); - kfree(kvm->arch.migration_state); - } KVM_EVENT(3, "vm 0x%pK destroyed", kvm); } @@ -2300,6 +2408,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; if (test_kvm_facility(vcpu->kvm, 133)) vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; + if (test_kvm_facility(vcpu->kvm, 156)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN; /* fprs can be synchronized via vrs, even if the guest has no vx. With * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format. */ @@ -2549,7 +2659,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) } if (test_kvm_facility(vcpu->kvm, 139)) vcpu->arch.sie_block->ecd |= ECD_MEF; - + if (test_kvm_facility(vcpu->kvm, 156)) + vcpu->arch.sie_block->ecd |= ECD_ETOKENF; if (vcpu->arch.sie_block->gd) { vcpu->arch.sie_block->eca |= ECA_AIV; VCPU_EVENT(vcpu, 3, "AIV gisa format-%u enabled for cpu %03u", @@ -3467,6 +3578,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } preempt_enable(); } + /* SIE will load etoken directly from SDNX and therefore kvm_run */ kvm_run->kvm_dirty_regs = 0; } @@ -3506,7 +3618,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) __ctl_clear_bit(2, 4); vcpu->arch.host_gscb = NULL; } - + /* SIE will save etoken directly into SDNX and therefore kvm_run */ } int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -4082,6 +4194,11 @@ static int __init kvm_s390_init(void) return -ENODEV; } + if (nested && hpage) { + pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently"); + return -EINVAL; + } + for (i = 0; i < 16; i++) kvm_s390_fac_base[i] |= S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index eb0eb60c7be6..d68f10441a16 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -205,13 +205,10 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu) int kvm_s390_skey_check_enable(struct kvm_vcpu *vcpu) { int rc; - struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block; trace_kvm_s390_skey_related_inst(vcpu); /* Already enabled? */ - if (vcpu->kvm->arch.use_skf && - !(sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)) && - !kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS)) + if (vcpu->arch.skey_enabled) return 0; rc = s390_enable_skey(); @@ -222,9 +219,10 @@ int kvm_s390_skey_check_enable(struct kvm_vcpu *vcpu) if (kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS)) kvm_s390_clear_cpuflags(vcpu, CPUSTAT_KSS); if (!vcpu->kvm->arch.use_skf) - sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE; + vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE; else - sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE); + vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE); + vcpu->arch.skey_enabled = true; return 0; } @@ -246,9 +244,10 @@ static int try_handle_skey(struct kvm_vcpu *vcpu) static int handle_iske(struct kvm_vcpu *vcpu) { - unsigned long addr; + unsigned long gaddr, vmaddr; unsigned char key; int reg1, reg2; + bool unlocked; int rc; vcpu->stat.instruction_iske++; @@ -262,18 +261,28 @@ static int handle_iske(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, ®1, ®2); - addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; - addr = kvm_s390_logical_to_effective(vcpu, addr); - addr = kvm_s390_real_to_abs(vcpu, addr); - addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr)); - if (kvm_is_error_hva(addr)) + gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; + gaddr = kvm_s390_logical_to_effective(vcpu, gaddr); + gaddr = kvm_s390_real_to_abs(vcpu, gaddr); + vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr)); + if (kvm_is_error_hva(vmaddr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - +retry: + unlocked = false; down_read(¤t->mm->mmap_sem); - rc = get_guest_storage_key(current->mm, addr, &key); - up_read(¤t->mm->mmap_sem); + rc = get_guest_storage_key(current->mm, vmaddr, &key); + + if (rc) { + rc = fixup_user_fault(current, current->mm, vmaddr, + FAULT_FLAG_WRITE, &unlocked); + if (!rc) { + up_read(¤t->mm->mmap_sem); + goto retry; + } + } if (rc) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + up_read(¤t->mm->mmap_sem); vcpu->run->s.regs.gprs[reg1] &= ~0xff; vcpu->run->s.regs.gprs[reg1] |= key; return 0; @@ -281,8 +290,9 @@ static int handle_iske(struct kvm_vcpu *vcpu) static int handle_rrbe(struct kvm_vcpu *vcpu) { - unsigned long addr; + unsigned long vmaddr, gaddr; int reg1, reg2; + bool unlocked; int rc; vcpu->stat.instruction_rrbe++; @@ -296,19 +306,27 @@ static int handle_rrbe(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, ®1, ®2); - addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; - addr = kvm_s390_logical_to_effective(vcpu, addr); - addr = kvm_s390_real_to_abs(vcpu, addr); - addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr)); - if (kvm_is_error_hva(addr)) + gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; + gaddr = kvm_s390_logical_to_effective(vcpu, gaddr); + gaddr = kvm_s390_real_to_abs(vcpu, gaddr); + vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr)); + if (kvm_is_error_hva(vmaddr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - +retry: + unlocked = false; down_read(¤t->mm->mmap_sem); - rc = reset_guest_reference_bit(current->mm, addr); - up_read(¤t->mm->mmap_sem); + rc = reset_guest_reference_bit(current->mm, vmaddr); + if (rc < 0) { + rc = fixup_user_fault(current, current->mm, vmaddr, + FAULT_FLAG_WRITE, &unlocked); + if (!rc) { + up_read(¤t->mm->mmap_sem); + goto retry; + } + } if (rc < 0) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - + up_read(¤t->mm->mmap_sem); kvm_s390_set_psw_cc(vcpu, rc); return 0; } @@ -323,6 +341,7 @@ static int handle_sske(struct kvm_vcpu *vcpu) unsigned long start, end; unsigned char key, oldkey; int reg1, reg2; + bool unlocked; int rc; vcpu->stat.instruction_sske++; @@ -355,19 +374,28 @@ static int handle_sske(struct kvm_vcpu *vcpu) } while (start != end) { - unsigned long addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start)); + unsigned long vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start)); + unlocked = false; - if (kvm_is_error_hva(addr)) + if (kvm_is_error_hva(vmaddr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); down_read(¤t->mm->mmap_sem); - rc = cond_set_guest_storage_key(current->mm, addr, key, &oldkey, + rc = cond_set_guest_storage_key(current->mm, vmaddr, key, &oldkey, m3 & SSKE_NQ, m3 & SSKE_MR, m3 & SSKE_MC); - up_read(¤t->mm->mmap_sem); - if (rc < 0) + + if (rc < 0) { + rc = fixup_user_fault(current, current->mm, vmaddr, + FAULT_FLAG_WRITE, &unlocked); + rc = !rc ? -EAGAIN : rc; + } + if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - start += PAGE_SIZE; + + up_read(¤t->mm->mmap_sem); + if (rc >= 0) + start += PAGE_SIZE; } if (m3 & (SSKE_MC | SSKE_MR)) { @@ -948,15 +976,16 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) } while (start != end) { - unsigned long useraddr; + unsigned long vmaddr; + bool unlocked = false; /* Translate guest address to host address */ - useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start)); - if (kvm_is_error_hva(useraddr)) + vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start)); + if (kvm_is_error_hva(vmaddr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { - if (clear_user((void __user *)useraddr, PAGE_SIZE)) + if (kvm_clear_guest(vcpu->kvm, start, PAGE_SIZE)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); } @@ -966,14 +995,20 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) if (rc) return rc; down_read(¤t->mm->mmap_sem); - rc = cond_set_guest_storage_key(current->mm, useraddr, + rc = cond_set_guest_storage_key(current->mm, vmaddr, key, NULL, nq, mr, mc); - up_read(¤t->mm->mmap_sem); - if (rc < 0) + if (rc < 0) { + rc = fixup_user_fault(current, current->mm, vmaddr, + FAULT_FLAG_WRITE, &unlocked); + rc = !rc ? -EAGAIN : rc; + } + if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - } - start += PAGE_SIZE; + up_read(¤t->mm->mmap_sem); + if (rc >= 0) + start += PAGE_SIZE; + } } if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) { @@ -987,9 +1022,11 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) return 0; } -static inline int do_essa(struct kvm_vcpu *vcpu, const int orc) +/* + * Must be called with relevant read locks held (kvm->mm->mmap_sem, kvm->srcu) + */ +static inline int __do_essa(struct kvm_vcpu *vcpu, const int orc) { - struct kvm_s390_migration_state *ms = vcpu->kvm->arch.migration_state; int r1, r2, nappended, entries; unsigned long gfn, hva, res, pgstev, ptev; unsigned long *cbrlo; @@ -1039,10 +1076,12 @@ static inline int do_essa(struct kvm_vcpu *vcpu, const int orc) cbrlo[entries] = gfn << PAGE_SHIFT; } - if (orc && gfn < ms->bitmap_size) { - /* increment only if we are really flipping the bit to 1 */ - if (!test_and_set_bit(gfn, ms->pgste_bitmap)) - atomic64_inc(&ms->dirty_pages); + if (orc) { + struct kvm_memory_slot *ms = gfn_to_memslot(vcpu->kvm, gfn); + + /* Increment only if we are really flipping the bit */ + if (ms && !test_and_set_bit(gfn - ms->base_gfn, kvm_second_dirty_bitmap(ms))) + atomic64_inc(&vcpu->kvm->arch.cmma_dirty_pages); } return nappended; @@ -1071,7 +1110,7 @@ static int handle_essa(struct kvm_vcpu *vcpu) : ESSA_SET_STABLE_IF_RESIDENT)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - if (likely(!vcpu->kvm->arch.migration_state)) { + if (!vcpu->kvm->arch.migration_mode) { /* * CMMA is enabled in the KVM settings, but is disabled in * the SIE block and in the mm_context, and we are not doing @@ -1099,10 +1138,16 @@ static int handle_essa(struct kvm_vcpu *vcpu) /* Retry the ESSA instruction */ kvm_s390_retry_instr(vcpu); } else { - /* Account for the possible extra cbrl entry */ - i = do_essa(vcpu, orc); + int srcu_idx; + + down_read(&vcpu->kvm->mm->mmap_sem); + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + i = __do_essa(vcpu, orc); + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); + up_read(&vcpu->kvm->mm->mmap_sem); if (i < 0) return i; + /* Account for the possible extra cbrl entry */ entries += i; } vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */ diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 84c89cb9636f..63844b95c22c 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -2,7 +2,7 @@ /* * kvm nested virtualization support for s390x * - * Copyright IBM Corp. 2016 + * Copyright IBM Corp. 2016, 2018 * * Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com> */ @@ -378,6 +378,10 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (test_kvm_facility(vcpu->kvm, 139)) scb_s->ecd |= scb_o->ecd & ECD_MEF; + /* etoken */ + if (test_kvm_facility(vcpu->kvm, 156)) + scb_s->ecd |= scb_o->ecd & ECD_ETOKENF; + prepare_ibc(vcpu, vsie_page); rc = shadow_crycb(vcpu, vsie_page); out: @@ -627,7 +631,8 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) vsie_page->riccbd_gpa = gpa; scb_s->riccbd = hpa; } - if ((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) { + if (((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) || + (scb_s->ecd & ECD_ETOKENF)) { unsigned long sdnxc; gpa = READ_ONCE(scb_o->sdnxo) & ~0xfUL; @@ -818,6 +823,8 @@ static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) * - < 0 if an error occurred */ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) + __releases(vcpu->kvm->srcu) + __acquires(vcpu->kvm->srcu) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S index 2311f15be9cf..40c4d59c926e 100644 --- a/arch/s390/lib/mem.S +++ b/arch/s390/lib/mem.S @@ -17,7 +17,7 @@ ENTRY(memmove) ltgr %r4,%r4 lgr %r1,%r2 - bzr %r14 + jz .Lmemmove_exit aghi %r4,-1 clgr %r2,%r3 jnh .Lmemmove_forward @@ -36,6 +36,7 @@ ENTRY(memmove) .Lmemmove_forward_remainder: larl %r5,.Lmemmove_mvc ex %r4,0(%r5) +.Lmemmove_exit: BR_EX %r14 .Lmemmove_reverse: ic %r0,0(%r4,%r3) @@ -65,7 +66,7 @@ EXPORT_SYMBOL(memmove) */ ENTRY(memset) ltgr %r4,%r4 - bzr %r14 + jz .Lmemset_exit ltgr %r3,%r3 jnz .Lmemset_fill aghi %r4,-1 @@ -80,6 +81,7 @@ ENTRY(memset) .Lmemset_clear_remainder: larl %r3,.Lmemset_xc ex %r4,0(%r3) +.Lmemset_exit: BR_EX %r14 .Lmemset_fill: cghi %r4,1 @@ -115,7 +117,7 @@ EXPORT_SYMBOL(memset) */ ENTRY(memcpy) ltgr %r4,%r4 - bzr %r14 + jz .Lmemcpy_exit aghi %r4,-1 srlg %r5,%r4,8 ltgr %r5,%r5 @@ -124,6 +126,7 @@ ENTRY(memcpy) .Lmemcpy_remainder: larl %r5,.Lmemcpy_mvc ex %r4,0(%r5) +.Lmemcpy_exit: BR_EX %r14 .Lmemcpy_loop: mvc 0(256,%r1),0(%r3) @@ -145,9 +148,9 @@ EXPORT_SYMBOL(memcpy) .macro __MEMSET bits,bytes,insn ENTRY(__memset\bits) ltgr %r4,%r4 - bzr %r14 + jz .L__memset_exit\bits cghi %r4,\bytes - je .L__memset_exit\bits + je .L__memset_store\bits aghi %r4,-(\bytes+1) srlg %r5,%r4,8 ltgr %r5,%r5 @@ -163,8 +166,9 @@ ENTRY(__memset\bits) larl %r5,.L__memset_mvc\bits ex %r4,0(%r5) BR_EX %r14 -.L__memset_exit\bits: +.L__memset_store\bits: \insn %r3,0(%r2) +.L__memset_exit\bits: BR_EX %r14 .L__memset_mvc\bits: mvc \bytes(1,%r1),0(%r1) diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 6cf024eb2085..510a18299196 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -191,12 +191,7 @@ static void cmm_set_timer(void) del_timer(&cmm_timer); return; } - if (timer_pending(&cmm_timer)) { - if (mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds*HZ)) - return; - } - cmm_timer.expires = jiffies + cmm_timeout_seconds*HZ; - add_timer(&cmm_timer); + mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds * HZ); } static void cmm_timer_fn(struct timer_list *unused) @@ -251,45 +246,42 @@ static int cmm_skip_blanks(char *cp, char **endp) return str != cp; } -static struct ctl_table cmm_table[]; - static int cmm_pages_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - char buf[16], *p; - unsigned int len; - long nr; + long nr = cmm_get_pages(); + struct ctl_table ctl_entry = { + .procname = ctl->procname, + .data = &nr, + .maxlen = sizeof(long), + }; + int rc; - if (!*lenp || (*ppos && !write)) { - *lenp = 0; - return 0; - } + rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos); + if (rc < 0 || !write) + return rc; - if (write) { - len = *lenp; - if (copy_from_user(buf, buffer, - len > sizeof(buf) ? sizeof(buf) : len)) - return -EFAULT; - buf[sizeof(buf) - 1] = '\0'; - cmm_skip_blanks(buf, &p); - nr = simple_strtoul(p, &p, 0); - if (ctl == &cmm_table[0]) - cmm_set_pages(nr); - else - cmm_add_timed_pages(nr); - } else { - if (ctl == &cmm_table[0]) - nr = cmm_get_pages(); - else - nr = cmm_get_timed_pages(); - len = sprintf(buf, "%ld\n", nr); - if (len > *lenp) - len = *lenp; - if (copy_to_user(buffer, buf, len)) - return -EFAULT; - } - *lenp = len; - *ppos += len; + cmm_set_pages(nr); + return 0; +} + +static int cmm_timed_pages_handler(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + long nr = cmm_get_timed_pages(); + struct ctl_table ctl_entry = { + .procname = ctl->procname, + .data = &nr, + .maxlen = sizeof(long), + }; + int rc; + + rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos); + if (rc < 0 || !write) + return rc; + + cmm_add_timed_pages(nr); return 0; } @@ -338,7 +330,7 @@ static struct ctl_table cmm_table[] = { { .procname = "cmm_timed_pages", .mode = 0644, - .proc_handler = cmm_pages_handler, + .proc_handler = cmm_timed_pages_handler, }, { .procname = "cmm_timeout", diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 6ad15d3fab81..84111a43ea29 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -80,7 +80,7 @@ struct qin64 { struct dcss_segment { struct list_head list; char dcss_name[8]; - char res_name[15]; + char res_name[16]; unsigned long start_addr; unsigned long end; atomic_t ref_count; @@ -433,7 +433,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long memcpy(&seg->res_name, seg->dcss_name, 8); EBCASC(seg->res_name, 8); seg->res_name[8] = '\0'; - strncat(seg->res_name, " (DCSS)", 7); + strlcat(seg->res_name, " (DCSS)", sizeof(seg->res_name)); seg->res->name = seg->res_name; rc = seg->vm_segtype; if (rc == SEG_TYPE_SC || diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e074480d3598..72af23bacbb5 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -341,7 +341,8 @@ static noinline int signal_return(struct pt_regs *regs) return -EACCES; } -static noinline void do_fault_error(struct pt_regs *regs, int access, int fault) +static noinline void do_fault_error(struct pt_regs *regs, int access, + vm_fault_t fault) { int si_code; @@ -401,7 +402,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int access, int fault) * 11 Page translation -> Not present (nullification) * 3b Region third trans. -> Not present (nullification) */ -static inline int do_exception(struct pt_regs *regs, int access) +static inline vm_fault_t do_exception(struct pt_regs *regs, int access) { struct gmap *gmap; struct task_struct *tsk; @@ -411,7 +412,7 @@ static inline int do_exception(struct pt_regs *regs, int access) unsigned long trans_exc_code; unsigned long address; unsigned int flags; - int fault; + vm_fault_t fault; tsk = current; /* @@ -502,6 +503,8 @@ retry: /* No reason to continue if interrupted by SIGKILL. */ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { fault = VM_FAULT_SIGNAL; + if (flags & FAULT_FLAG_RETRY_NOWAIT) + goto out_up; goto out; } if (unlikely(fault & VM_FAULT_ERROR)) @@ -562,7 +565,8 @@ out: void do_protection_exception(struct pt_regs *regs) { unsigned long trans_exc_code; - int access, fault; + int access; + vm_fault_t fault; trans_exc_code = regs->int_parm_long; /* @@ -597,7 +601,8 @@ NOKPROBE_SYMBOL(do_protection_exception); void do_dat_exception(struct pt_regs *regs) { - int access, fault; + int access; + vm_fault_t fault; access = VM_READ | VM_EXEC | VM_WRITE; fault = do_exception(regs, access); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index bc56ec8abcf7..bb44990c8212 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2,8 +2,10 @@ /* * KVM guest address space mapping code * - * Copyright IBM Corp. 2007, 2016 + * Copyright IBM Corp. 2007, 2016, 2018 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + * David Hildenbrand <david@redhat.com> + * Janosch Frank <frankja@linux.vnet.ibm.com> */ #include <linux/kernel.h> @@ -521,6 +523,9 @@ void gmap_unlink(struct mm_struct *mm, unsigned long *table, rcu_read_unlock(); } +static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *old, pmd_t new, + unsigned long gaddr); + /** * gmap_link - set up shadow page tables to connect a host to a guest address * @gmap: pointer to guest mapping meta data structure @@ -541,6 +546,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) p4d_t *p4d; pud_t *pud; pmd_t *pmd; + u64 unprot; int rc; BUG_ON(gmap_is_shadow(gmap)); @@ -584,8 +590,8 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) return -EFAULT; pmd = pmd_offset(pud, vmaddr); VM_BUG_ON(pmd_none(*pmd)); - /* large pmds cannot yet be handled */ - if (pmd_large(*pmd)) + /* Are we allowed to use huge pages? */ + if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m) return -EFAULT; /* Link gmap segment table entry location to page table. */ rc = radix_tree_preload(GFP_KERNEL); @@ -596,10 +602,22 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) if (*table == _SEGMENT_ENTRY_EMPTY) { rc = radix_tree_insert(&gmap->host_to_guest, vmaddr >> PMD_SHIFT, table); - if (!rc) - *table = pmd_val(*pmd); - } else - rc = 0; + if (!rc) { + if (pmd_large(*pmd)) { + *table = (pmd_val(*pmd) & + _SEGMENT_ENTRY_HARDWARE_BITS_LARGE) + | _SEGMENT_ENTRY_GMAP_UC; + } else + *table = pmd_val(*pmd) & + _SEGMENT_ENTRY_HARDWARE_BITS; + } + } else if (*table & _SEGMENT_ENTRY_PROTECT && + !(pmd_val(*pmd) & _SEGMENT_ENTRY_PROTECT)) { + unprot = (u64)*table; + unprot &= ~_SEGMENT_ENTRY_PROTECT; + unprot |= _SEGMENT_ENTRY_GMAP_UC; + gmap_pmdp_xchg(gmap, (pmd_t *)table, __pmd(unprot), gaddr); + } spin_unlock(&gmap->guest_table_lock); spin_unlock(ptl); radix_tree_preload_end(); @@ -690,6 +708,12 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to) vmaddr |= gaddr & ~PMD_MASK; /* Find vma in the parent mm */ vma = find_vma(gmap->mm, vmaddr); + /* + * We do not discard pages that are backed by + * hugetlbfs, so we don't have to refault them. + */ + if (vma && is_vm_hugetlb_page(vma)) + continue; size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK)); zap_page_range(vma, vmaddr, size); } @@ -864,7 +888,128 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr, */ static void gmap_pte_op_end(spinlock_t *ptl) { - spin_unlock(ptl); + if (ptl) + spin_unlock(ptl); +} + +/** + * gmap_pmd_op_walk - walk the gmap tables, get the guest table lock + * and return the pmd pointer + * @gmap: pointer to guest mapping meta data structure + * @gaddr: virtual address in the guest address space + * + * Returns a pointer to the pmd for a guest address, or NULL + */ +static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr) +{ + pmd_t *pmdp; + + BUG_ON(gmap_is_shadow(gmap)); + spin_lock(&gmap->guest_table_lock); + pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1); + + if (!pmdp || pmd_none(*pmdp)) { + spin_unlock(&gmap->guest_table_lock); + return NULL; + } + + /* 4k page table entries are locked via the pte (pte_alloc_map_lock). */ + if (!pmd_large(*pmdp)) + spin_unlock(&gmap->guest_table_lock); + return pmdp; +} + +/** + * gmap_pmd_op_end - release the guest_table_lock if needed + * @gmap: pointer to the guest mapping meta data structure + * @pmdp: pointer to the pmd + */ +static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp) +{ + if (pmd_large(*pmdp)) + spin_unlock(&gmap->guest_table_lock); +} + +/* + * gmap_protect_pmd - remove access rights to memory and set pmd notification bits + * @pmdp: pointer to the pmd to be protected + * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE + * @bits: notification bits to set + * + * Returns: + * 0 if successfully protected + * -EAGAIN if a fixup is needed + * -EINVAL if unsupported notifier bits have been specified + * + * Expected to be called with sg->mm->mmap_sem in read and + * guest_table_lock held. + */ +static int gmap_protect_pmd(struct gmap *gmap, unsigned long gaddr, + pmd_t *pmdp, int prot, unsigned long bits) +{ + int pmd_i = pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID; + int pmd_p = pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT; + pmd_t new = *pmdp; + + /* Fixup needed */ + if ((pmd_i && (prot != PROT_NONE)) || (pmd_p && (prot == PROT_WRITE))) + return -EAGAIN; + + if (prot == PROT_NONE && !pmd_i) { + pmd_val(new) |= _SEGMENT_ENTRY_INVALID; + gmap_pmdp_xchg(gmap, pmdp, new, gaddr); + } + + if (prot == PROT_READ && !pmd_p) { + pmd_val(new) &= ~_SEGMENT_ENTRY_INVALID; + pmd_val(new) |= _SEGMENT_ENTRY_PROTECT; + gmap_pmdp_xchg(gmap, pmdp, new, gaddr); + } + + if (bits & GMAP_NOTIFY_MPROT) + pmd_val(*pmdp) |= _SEGMENT_ENTRY_GMAP_IN; + + /* Shadow GMAP protection needs split PMDs */ + if (bits & GMAP_NOTIFY_SHADOW) + return -EINVAL; + + return 0; +} + +/* + * gmap_protect_pte - remove access rights to memory and set pgste bits + * @gmap: pointer to guest mapping meta data structure + * @gaddr: virtual address in the guest address space + * @pmdp: pointer to the pmd associated with the pte + * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE + * @bits: notification bits to set + * + * Returns 0 if successfully protected, -ENOMEM if out of memory and + * -EAGAIN if a fixup is needed. + * + * Expected to be called with sg->mm->mmap_sem in read + */ +static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr, + pmd_t *pmdp, int prot, unsigned long bits) +{ + int rc; + pte_t *ptep; + spinlock_t *ptl = NULL; + unsigned long pbits = 0; + + if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID) + return -EAGAIN; + + ptep = pte_alloc_map_lock(gmap->mm, pmdp, gaddr, &ptl); + if (!ptep) + return -ENOMEM; + + pbits |= (bits & GMAP_NOTIFY_MPROT) ? PGSTE_IN_BIT : 0; + pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0; + /* Protect and unlock. */ + rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits); + gmap_pte_op_end(ptl); + return rc; } /* @@ -883,30 +1028,45 @@ static void gmap_pte_op_end(spinlock_t *ptl) static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr, unsigned long len, int prot, unsigned long bits) { - unsigned long vmaddr; - spinlock_t *ptl; - pte_t *ptep; + unsigned long vmaddr, dist; + pmd_t *pmdp; int rc; BUG_ON(gmap_is_shadow(gmap)); while (len) { rc = -EAGAIN; - ptep = gmap_pte_op_walk(gmap, gaddr, &ptl); - if (ptep) { - rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits); - gmap_pte_op_end(ptl); + pmdp = gmap_pmd_op_walk(gmap, gaddr); + if (pmdp) { + if (!pmd_large(*pmdp)) { + rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, + bits); + if (!rc) { + len -= PAGE_SIZE; + gaddr += PAGE_SIZE; + } + } else { + rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, + bits); + if (!rc) { + dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK); + len = len < dist ? 0 : len - dist; + gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE; + } + } + gmap_pmd_op_end(gmap, pmdp); } if (rc) { + if (rc == -EINVAL) + return rc; + + /* -EAGAIN, fixup of userspace mm and gmap */ vmaddr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(vmaddr)) return vmaddr; rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot); if (rc) return rc; - continue; } - gaddr += PAGE_SIZE; - len -= PAGE_SIZE; } return 0; } @@ -935,7 +1095,7 @@ int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr, if (!MACHINE_HAS_ESOP && prot == PROT_READ) return -EINVAL; down_read(&gmap->mm->mmap_sem); - rc = gmap_protect_range(gmap, gaddr, len, prot, PGSTE_IN_BIT); + rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT); up_read(&gmap->mm->mmap_sem); return rc; } @@ -1474,6 +1634,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, unsigned long limit; int rc; + BUG_ON(parent->mm->context.allow_gmap_hpage_1m); BUG_ON(gmap_is_shadow(parent)); spin_lock(&parent->shadow_lock); sg = gmap_find_shadow(parent, asce, edat_level); @@ -1526,7 +1687,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, down_read(&parent->mm->mmap_sem); rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN, ((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE, - PROT_READ, PGSTE_VSIE_BIT); + PROT_READ, GMAP_NOTIFY_SHADOW); up_read(&parent->mm->mmap_sem); spin_lock(&parent->shadow_lock); new->initialized = true; @@ -2092,6 +2253,225 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, } EXPORT_SYMBOL_GPL(ptep_notify); +static void pmdp_notify_gmap(struct gmap *gmap, pmd_t *pmdp, + unsigned long gaddr) +{ + pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_IN; + gmap_call_notifier(gmap, gaddr, gaddr + HPAGE_SIZE - 1); +} + +/** + * gmap_pmdp_xchg - exchange a gmap pmd with another + * @gmap: pointer to the guest address space structure + * @pmdp: pointer to the pmd entry + * @new: replacement entry + * @gaddr: the affected guest address + * + * This function is assumed to be called with the guest_table_lock + * held. + */ +static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new, + unsigned long gaddr) +{ + gaddr &= HPAGE_MASK; + pmdp_notify_gmap(gmap, pmdp, gaddr); + pmd_val(new) &= ~_SEGMENT_ENTRY_GMAP_IN; + if (MACHINE_HAS_TLB_GUEST) + __pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce, + IDTE_GLOBAL); + else if (MACHINE_HAS_IDTE) + __pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL); + else + __pmdp_csp(pmdp); + *pmdp = new; +} + +static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr, + int purge) +{ + pmd_t *pmdp; + struct gmap *gmap; + unsigned long gaddr; + + rcu_read_lock(); + list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { + spin_lock(&gmap->guest_table_lock); + pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest, + vmaddr >> PMD_SHIFT); + if (pmdp) { + gaddr = __gmap_segment_gaddr((unsigned long *)pmdp); + pmdp_notify_gmap(gmap, pmdp, gaddr); + WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC)); + if (purge) + __pmdp_csp(pmdp); + pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY; + } + spin_unlock(&gmap->guest_table_lock); + } + rcu_read_unlock(); +} + +/** + * gmap_pmdp_invalidate - invalidate all affected guest pmd entries without + * flushing + * @mm: pointer to the process mm_struct + * @vmaddr: virtual address in the process address space + */ +void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr) +{ + gmap_pmdp_clear(mm, vmaddr, 0); +} +EXPORT_SYMBOL_GPL(gmap_pmdp_invalidate); + +/** + * gmap_pmdp_csp - csp all affected guest pmd entries + * @mm: pointer to the process mm_struct + * @vmaddr: virtual address in the process address space + */ +void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr) +{ + gmap_pmdp_clear(mm, vmaddr, 1); +} +EXPORT_SYMBOL_GPL(gmap_pmdp_csp); + +/** + * gmap_pmdp_idte_local - invalidate and clear a guest pmd entry + * @mm: pointer to the process mm_struct + * @vmaddr: virtual address in the process address space + */ +void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr) +{ + unsigned long *entry, gaddr; + struct gmap *gmap; + pmd_t *pmdp; + + rcu_read_lock(); + list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { + spin_lock(&gmap->guest_table_lock); + entry = radix_tree_delete(&gmap->host_to_guest, + vmaddr >> PMD_SHIFT); + if (entry) { + pmdp = (pmd_t *)entry; + gaddr = __gmap_segment_gaddr(entry); + pmdp_notify_gmap(gmap, pmdp, gaddr); + WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC)); + if (MACHINE_HAS_TLB_GUEST) + __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, + gmap->asce, IDTE_LOCAL); + else if (MACHINE_HAS_IDTE) + __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL); + *entry = _SEGMENT_ENTRY_EMPTY; + } + spin_unlock(&gmap->guest_table_lock); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local); + +/** + * gmap_pmdp_idte_global - invalidate and clear a guest pmd entry + * @mm: pointer to the process mm_struct + * @vmaddr: virtual address in the process address space + */ +void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr) +{ + unsigned long *entry, gaddr; + struct gmap *gmap; + pmd_t *pmdp; + + rcu_read_lock(); + list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { + spin_lock(&gmap->guest_table_lock); + entry = radix_tree_delete(&gmap->host_to_guest, + vmaddr >> PMD_SHIFT); + if (entry) { + pmdp = (pmd_t *)entry; + gaddr = __gmap_segment_gaddr(entry); + pmdp_notify_gmap(gmap, pmdp, gaddr); + WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC)); + if (MACHINE_HAS_TLB_GUEST) + __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, + gmap->asce, IDTE_GLOBAL); + else if (MACHINE_HAS_IDTE) + __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL); + else + __pmdp_csp(pmdp); + *entry = _SEGMENT_ENTRY_EMPTY; + } + spin_unlock(&gmap->guest_table_lock); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global); + +/** + * gmap_test_and_clear_dirty_pmd - test and reset segment dirty status + * @gmap: pointer to guest address space + * @pmdp: pointer to the pmd to be tested + * @gaddr: virtual address in the guest address space + * + * This function is assumed to be called with the guest_table_lock + * held. + */ +bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp, + unsigned long gaddr) +{ + if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID) + return false; + + /* Already protected memory, which did not change is clean */ + if (pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT && + !(pmd_val(*pmdp) & _SEGMENT_ENTRY_GMAP_UC)) + return false; + + /* Clear UC indication and reset protection */ + pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_UC; + gmap_protect_pmd(gmap, gaddr, pmdp, PROT_READ, 0); + return true; +} + +/** + * gmap_sync_dirty_log_pmd - set bitmap based on dirty status of segment + * @gmap: pointer to guest address space + * @bitmap: dirty bitmap for this pmd + * @gaddr: virtual address in the guest address space + * @vmaddr: virtual address in the host address space + * + * This function is assumed to be called with the guest_table_lock + * held. + */ +void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4], + unsigned long gaddr, unsigned long vmaddr) +{ + int i; + pmd_t *pmdp; + pte_t *ptep; + spinlock_t *ptl; + + pmdp = gmap_pmd_op_walk(gmap, gaddr); + if (!pmdp) + return; + + if (pmd_large(*pmdp)) { + if (gmap_test_and_clear_dirty_pmd(gmap, pmdp, gaddr)) + bitmap_fill(bitmap, _PAGE_ENTRIES); + } else { + for (i = 0; i < _PAGE_ENTRIES; i++, vmaddr += PAGE_SIZE) { + ptep = pte_alloc_map_lock(gmap->mm, pmdp, vmaddr, &ptl); + if (!ptep) + continue; + if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep)) + set_bit(i, bitmap); + spin_unlock(ptl); + } + } + gmap_pmd_op_end(gmap, pmdp); +} +EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd); + static inline void thp_split_mm(struct mm_struct *mm) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -2168,17 +2548,45 @@ EXPORT_SYMBOL_GPL(s390_enable_sie); * Enable storage key handling from now on and initialize the storage * keys with the default key. */ -static int __s390_enable_skey(pte_t *pte, unsigned long addr, - unsigned long next, struct mm_walk *walk) +static int __s390_enable_skey_pte(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) { /* Clear storage key */ ptep_zap_key(walk->mm, addr, pte); return 0; } +static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, + unsigned long hmask, unsigned long next, + struct mm_walk *walk) +{ + pmd_t *pmd = (pmd_t *)pte; + unsigned long start, end; + struct page *page = pmd_page(*pmd); + + /* + * The write check makes sure we do not set a key on shared + * memory. This is needed as the walker does not differentiate + * between actual guest memory and the process executable or + * shared libraries. + */ + if (pmd_val(*pmd) & _SEGMENT_ENTRY_INVALID || + !(pmd_val(*pmd) & _SEGMENT_ENTRY_WRITE)) + return 0; + + start = pmd_val(*pmd) & HPAGE_MASK; + end = start + HPAGE_SIZE - 1; + __storage_key_init_range(start, end); + set_bit(PG_arch_1, &page->flags); + return 0; +} + int s390_enable_skey(void) { - struct mm_walk walk = { .pte_entry = __s390_enable_skey }; + struct mm_walk walk = { + .hugetlb_entry = __s390_enable_skey_hugetlb, + .pte_entry = __s390_enable_skey_pte, + }; struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int rc = 0; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index e804090f4470..b0246c705a19 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -123,6 +123,29 @@ static inline pte_t __rste_to_pte(unsigned long rste) return pte; } +static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) +{ + struct page *page; + unsigned long size, paddr; + + if (!mm_uses_skeys(mm) || + rste & _SEGMENT_ENTRY_INVALID) + return; + + if ((rste & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) { + page = pud_page(__pud(rste)); + size = PUD_SIZE; + paddr = rste & PUD_MASK; + } else { + page = pmd_page(__pmd(rste)); + size = PMD_SIZE; + paddr = rste & PMD_MASK; + } + + if (!test_and_set_bit(PG_arch_1, &page->flags)) + __storage_key_init_range(paddr, paddr + size - 1); +} + void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { @@ -137,6 +160,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE; else rste |= _SEGMENT_ENTRY_LARGE; + clear_huge_pte_skeys(mm, rste); pte_val(*ptep) = rste; } diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index 382153ff17e3..dc3cede7f2ec 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -271,7 +271,7 @@ void arch_set_page_states(int make_stable) list_for_each(l, &zone->free_area[order].free_list[t]) { page = list_entry(l, struct page, lru); if (make_stable) - set_page_stable_dat(page, 0); + set_page_stable_dat(page, order); else set_page_unused(page, order); } diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index c44171588d08..f8c6faab41f4 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -14,7 +14,7 @@ static inline unsigned long sske_frame(unsigned long addr, unsigned char skey) { - asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0" + asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],1,0" : [addr] "+a" (addr) : [skey] "d" (skey)); return addr; } @@ -23,8 +23,6 @@ void __storage_key_init_range(unsigned long start, unsigned long end) { unsigned long boundary, size; - if (!PAGE_DEFAULT_KEY) - return; while (start < end) { if (MACHINE_HAS_EDAT1) { /* set storage keys for a 1MB frame */ @@ -37,7 +35,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end) continue; } } - page_set_storage_key(start, PAGE_DEFAULT_KEY, 0); + page_set_storage_key(start, PAGE_DEFAULT_KEY, 1); start += PAGE_SIZE; } } diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index e3bd5627afef..76d89ee8b428 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -28,7 +28,7 @@ static struct ctl_table page_table_sysctl[] = { .data = &page_table_allocate_pgste, .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &page_table_allocate_pgste_min, .extra2 = &page_table_allocate_pgste_max, }, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 301e466e4263..f2cc7da473e4 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -347,18 +347,27 @@ static inline void pmdp_idte_local(struct mm_struct *mm, mm->context.asce, IDTE_LOCAL); else __pmdp_idte(addr, pmdp, 0, 0, IDTE_LOCAL); + if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m) + gmap_pmdp_idte_local(mm, addr); } static inline void pmdp_idte_global(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - if (MACHINE_HAS_TLB_GUEST) + if (MACHINE_HAS_TLB_GUEST) { __pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE, mm->context.asce, IDTE_GLOBAL); - else if (MACHINE_HAS_IDTE) + if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m) + gmap_pmdp_idte_global(mm, addr); + } else if (MACHINE_HAS_IDTE) { __pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL); - else + if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m) + gmap_pmdp_idte_global(mm, addr); + } else { __pmdp_csp(pmdp); + if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m) + gmap_pmdp_csp(mm, addr); + } } static inline pmd_t pmdp_flush_direct(struct mm_struct *mm, @@ -392,6 +401,8 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm, cpumask_of(smp_processor_id()))) { pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID; mm->context.flush_mm = 1; + if (mm_has_pgste(mm)) + gmap_pmdp_invalidate(mm, addr); } else { pmdp_idte_global(mm, addr, pmdp); } @@ -399,6 +410,24 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm, return old; } +static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + pmd = pmd_alloc(mm, pud, addr); + return pmd; +} + pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t new) { @@ -693,40 +722,14 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep) /* * Test and reset if a guest page is dirty */ -bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr) +bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { - spinlock_t *ptl; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; pgste_t pgste; - pte_t *ptep; pte_t pte; bool dirty; int nodat; - pgd = pgd_offset(mm, addr); - p4d = p4d_alloc(mm, pgd, addr); - if (!p4d) - return false; - pud = pud_alloc(mm, p4d, addr); - if (!pud) - return false; - pmd = pmd_alloc(mm, pud, addr); - if (!pmd) - return false; - /* We can't run guests backed by huge pages, but userspace can - * still set them up and then try to migrate them without any - * migration support. - */ - if (pmd_large(*pmd)) - return true; - - ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl); - if (unlikely(!ptep)) - return false; - pgste = pgste_get_lock(ptep); dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT); pgste_val(pgste) &= ~PGSTE_UC_BIT; @@ -742,21 +745,43 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr) *ptep = pte; } pgste_set_unlock(ptep, pgste); - - spin_unlock(ptl); return dirty; } -EXPORT_SYMBOL_GPL(test_and_clear_guest_dirty); +EXPORT_SYMBOL_GPL(ptep_test_and_clear_uc); int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, unsigned char key, bool nq) { - unsigned long keyul; + unsigned long keyul, paddr; spinlock_t *ptl; pgste_t old, new; + pmd_t *pmdp; pte_t *ptep; - ptep = get_locked_pte(mm, addr, &ptl); + pmdp = pmd_alloc_map(mm, addr); + if (unlikely(!pmdp)) + return -EFAULT; + + ptl = pmd_lock(mm, pmdp); + if (!pmd_present(*pmdp)) { + spin_unlock(ptl); + return -EFAULT; + } + + if (pmd_large(*pmdp)) { + paddr = pmd_val(*pmdp) & HPAGE_MASK; + paddr |= addr & ~HPAGE_MASK; + /* + * Huge pmds need quiescing operations, they are + * always mapped. + */ + page_set_storage_key(paddr, key, 1); + spin_unlock(ptl); + return 0; + } + spin_unlock(ptl); + + ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -767,14 +792,14 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48; pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; if (!(pte_val(*ptep) & _PAGE_INVALID)) { - unsigned long address, bits, skey; + unsigned long bits, skey; - address = pte_val(*ptep) & PAGE_MASK; - skey = (unsigned long) page_get_storage_key(address); + paddr = pte_val(*ptep) & PAGE_MASK; + skey = (unsigned long) page_get_storage_key(paddr); bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT); /* Set storage key ACC and FP */ - page_set_storage_key(address, skey, !nq); + page_set_storage_key(paddr, skey, !nq); /* Merge host changed & referenced into pgste */ pgste_val(new) |= bits << 52; } @@ -830,11 +855,32 @@ EXPORT_SYMBOL(cond_set_guest_storage_key); int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr) { spinlock_t *ptl; + unsigned long paddr; pgste_t old, new; + pmd_t *pmdp; pte_t *ptep; int cc = 0; - ptep = get_locked_pte(mm, addr, &ptl); + pmdp = pmd_alloc_map(mm, addr); + if (unlikely(!pmdp)) + return -EFAULT; + + ptl = pmd_lock(mm, pmdp); + if (!pmd_present(*pmdp)) { + spin_unlock(ptl); + return -EFAULT; + } + + if (pmd_large(*pmdp)) { + paddr = pmd_val(*pmdp) & HPAGE_MASK; + paddr |= addr & ~HPAGE_MASK; + cc = page_reset_referenced(paddr); + spin_unlock(ptl); + return cc; + } + spin_unlock(ptl); + + ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -843,7 +889,8 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr) pgste_val(new) &= ~PGSTE_GR_BIT; if (!(pte_val(*ptep) & _PAGE_INVALID)) { - cc = page_reset_referenced(pte_val(*ptep) & PAGE_MASK); + paddr = pte_val(*ptep) & PAGE_MASK; + cc = page_reset_referenced(paddr); /* Merge real referenced bit into host-set */ pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT; } @@ -862,18 +909,42 @@ EXPORT_SYMBOL(reset_guest_reference_bit); int get_guest_storage_key(struct mm_struct *mm, unsigned long addr, unsigned char *key) { + unsigned long paddr; spinlock_t *ptl; pgste_t pgste; + pmd_t *pmdp; pte_t *ptep; - ptep = get_locked_pte(mm, addr, &ptl); + pmdp = pmd_alloc_map(mm, addr); + if (unlikely(!pmdp)) + return -EFAULT; + + ptl = pmd_lock(mm, pmdp); + if (!pmd_present(*pmdp)) { + /* Not yet mapped memory has a zero key */ + spin_unlock(ptl); + *key = 0; + return 0; + } + + if (pmd_large(*pmdp)) { + paddr = pmd_val(*pmdp) & HPAGE_MASK; + paddr |= addr & ~HPAGE_MASK; + *key = page_get_storage_key(paddr); + spin_unlock(ptl); + return 0; + } + spin_unlock(ptl); + + ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); if (unlikely(!ptep)) return -EFAULT; pgste = pgste_get_lock(ptep); *key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56; + paddr = pte_val(*ptep) & PAGE_MASK; if (!(pte_val(*ptep) & _PAGE_INVALID)) - *key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK); + *key = page_get_storage_key(paddr); /* Reflect guest's logical view, not physical */ *key |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48; pgste_set_unlock(ptep, pgste); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 5f0234ec8038..d7052cbe984f 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -485,8 +485,6 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) /* br %r1 */ _EMIT2(0x07f1); } else { - /* larl %r1,.+14 */ - EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14); /* ex 0,S390_lowcore.br_r1_tampoline */ EMIT4_DISP(0x44000000, REG_0, REG_0, offsetof(struct lowcore, br_r1_trampoline)); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 06a80434cfe6..5bd374491f94 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -134,6 +134,8 @@ void __init numa_setup(void) { pr_info("NUMA mode: %s\n", mode->name); nodes_clear(node_possible_map); + /* Initially attach all possible CPUs to node 0. */ + cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask); if (mode->setup) mode->setup(); numa_setup_memory(); @@ -141,20 +143,6 @@ void __init numa_setup(void) } /* - * numa_init_early() - Initialization initcall - * - * This runs when only one CPU is online and before the first - * topology update is called for by the scheduler. - */ -static int __init numa_init_early(void) -{ - /* Attach all possible CPUs to node 0 for now. */ - cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask); - return 0; -} -early_initcall(numa_init_early); - -/* * numa_init_late() - Initialization initcall * * Register NUMA nodes. diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index b482e95b6249..57f7cdac70a3 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -48,6 +48,10 @@ static char *pci_fmt2_names[] = { "Maximum work units", }; +static char *pci_fmt3_names[] = { + "Transmitted bytes", +}; + static char *pci_sw_names[] = { "Allocated pages", "Mapped pages", @@ -112,6 +116,10 @@ static int pci_perf_show(struct seq_file *m, void *v) pci_fmb_show(m, pci_fmt2_names, ARRAY_SIZE(pci_fmt2_names), &zdev->fmb->fmt2.consumed_work_units); break; + case 3: + pci_fmb_show(m, pci_fmt3_names, ARRAY_SIZE(pci_fmt3_names), + &zdev->fmb->fmt3.tx_bytes); + break; default: seq_puts(m, "Unknown format\n"); } diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index 1ace023cbdce..ce6a3f75065b 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -7,13 +7,13 @@ purgatory-y := head.o purgatory.o string.o sha256.o mem.o targets += $(purgatory-y) purgatory.ro kexec-purgatory.c PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) -$(obj)/sha256.o: $(srctree)/lib/sha256.c +$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE $(call if_changed_rule,cc_o_c) -$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S +$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE $(call if_changed_rule,as_o_S) -$(obj)/string.o: $(srctree)/arch/s390/lib/string.c +$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE $(call if_changed_rule,cc_o_c) LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib @@ -21,15 +21,15 @@ LDFLAGS_purgatory.ro += -z nodefaultlib KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float +KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common KBUILD_CFLAGS += $(call cc-option,-fno-PIE) +KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS)) $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) -CMD_BIN2C = $(objtree)/scripts/basic/bin2c quiet_cmd_bin2c = BIN2C $@ - cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@ + cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@ $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE $(call if_changed,bin2c) diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S index 660c96a05a9b..2e3707b12edd 100644 --- a/arch/s390/purgatory/head.S +++ b/arch/s390/purgatory/head.S @@ -243,33 +243,26 @@ gprregs: .quad 0 .endr -purgatory_sha256_digest: - .global purgatory_sha256_digest - .rept 32 /* SHA256_DIGEST_SIZE */ - .byte 0 - .endr - -purgatory_sha_regions: - .global purgatory_sha_regions - .rept 16 * __KEXEC_SHA_REGION_SIZE /* KEXEC_SEGMENTS_MAX */ - .byte 0 - .endr - -kernel_entry: - .global kernel_entry - .quad 0 - -kernel_type: - .global kernel_type - .quad 0 - -crash_start: - .global crash_start - .quad 0 +/* Macro to define a global variable with name and size (in bytes) to be + * shared with C code. + * + * Add the .size and .type attribute to satisfy checks on the Elf_Sym during + * purgatory load. + */ +.macro GLOBAL_VARIABLE name,size +\name: + .global \name + .size \name,\size + .type \name,object + .skip \size,0 +.endm -crash_size: - .global crash_size - .quad 0 +GLOBAL_VARIABLE purgatory_sha256_digest,32 +GLOBAL_VARIABLE purgatory_sha_regions,16*__KEXEC_SHA_REGION_SIZE +GLOBAL_VARIABLE kernel_entry,8 +GLOBAL_VARIABLE kernel_type,8 +GLOBAL_VARIABLE crash_start,8 +GLOBAL_VARIABLE crash_size,8 .align PAGE_SIZE stack: diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c index 4e2beb3c29b7..3528e6da4e87 100644 --- a/arch/s390/purgatory/purgatory.c +++ b/arch/s390/purgatory/purgatory.c @@ -12,15 +12,6 @@ #include <linux/string.h> #include <asm/purgatory.h> -struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX]; -u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE]; - -u64 kernel_entry; -u64 kernel_type; - -u64 crash_start; -u64 crash_size; - int verify_sha256_digest(void) { struct kexec_sha_region *ptr, *end; diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss index d92f2d94a5d9..9bba2c14e0ca 100644 --- a/arch/s390/scripts/Makefile.chkbss +++ b/arch/s390/scripts/Makefile.chkbss @@ -2,13 +2,22 @@ quiet_cmd_chkbss = CHKBSS $< define cmd_chkbss + rm -f $@; \ if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \ echo "error: $< .bss section is not empty" >&2; exit 1; \ fi; \ touch $@; endef -$(obj)/built-in.a: $(patsubst %, $(obj)/%.chkbss, $(chkbss)) +chkbss-target ?= $(obj)/built-in.a +ifneq (,$(findstring /,$(chkbss))) +chkbss-files := $(patsubst %, %.chkbss, $(chkbss)) +else +chkbss-files := $(patsubst %, $(obj)/%.chkbss, $(chkbss)) +endif + +$(chkbss-target): $(chkbss-files) +targets += $(notdir $(chkbss-files)) %.o.chkbss: %.o $(call cmd,chkbss) diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c index 90a8c9e84ca6..0c85aedcf9b3 100644 --- a/arch/s390/tools/gen_facilities.c +++ b/arch/s390/tools/gen_facilities.c @@ -4,7 +4,7 @@ * numbering scheme from the Princples of Operations: most significant bit * has bit number 0. * - * Copyright IBM Corp. 2015 + * Copyright IBM Corp. 2015, 2018 * */ @@ -106,6 +106,7 @@ static struct facility_def facility_defs[] = { .name = "FACILITIES_KVM_CPUMODEL", .bits = (int[]){ + 156, /* etoken facility */ -1 /* END */ } }, diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c index 259aa0680d1a..a1bc02b29c81 100644 --- a/arch/s390/tools/gen_opcode_table.c +++ b/arch/s390/tools/gen_opcode_table.c @@ -257,7 +257,7 @@ static void add_to_group(struct gen_opcode *desc, struct insn *insn, int offset) if (!desc->group) exit(EXIT_FAILURE); group = &desc->group[desc->nr_groups - 1]; - strncpy(group->opcode, insn->opcode, 2); + memcpy(group->opcode, insn->opcode, 2); group->type = insn->type; group->offset = offset; group->count = 1; @@ -283,7 +283,7 @@ static void print_opcode_table(struct gen_opcode *desc) continue; add_to_group(desc, insn, offset); if (strncmp(opcode, insn->opcode, 2)) { - strncpy(opcode, insn->opcode, 2); + memcpy(opcode, insn->opcode, 2); printf("\t/* %.2s */ \\\n", opcode); } print_opcode(insn, offset); diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index dd4f3d3e644f..1fb7b6d72baf 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -51,7 +51,6 @@ config SUPERH select HAVE_ARCH_AUDITSYSCALL select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_NMI - select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH help @@ -159,19 +158,18 @@ config SWAP_IO_SPACE bool config DMA_COHERENT + select DMA_DIRECT_OPS bool config DMA_NONCOHERENT def_bool !DMA_COHERENT + select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select DMA_NONCOHERENT_OPS config PGTABLE_LEVELS default 3 if X2TLB default 2 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - menu "System type" # @@ -713,8 +711,6 @@ config HOTPLUG_CPU Say Y here to experiment with turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. -source "kernel/Kconfig.preempt" - config GUSA def_bool y depends on !SMP && SUPERH32 @@ -882,12 +878,6 @@ source "drivers/pcmcia/Kconfig" endmenu -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - menu "Power management options (EXPERIMENTAL)" source "kernel/power/Kconfig" @@ -895,17 +885,3 @@ source "kernel/power/Kconfig" source "drivers/cpuidle/Kconfig" endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "arch/sh/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug index d0767672640d..010b6c33bbba 100644 --- a/arch/sh/Kconfig.debug +++ b/arch/sh/Kconfig.debug @@ -1,11 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" config TRACE_IRQFLAGS_SUPPORT def_bool y -source "lib/Kconfig.debug" - config SH_STANDARD_BIOS bool "Use LinuxSH standard BIOS" depends on SUPERH32 @@ -88,5 +85,3 @@ config MCOUNT def_bool y depends on SUPERH32 depends on STACK_DEBUG || FUNCTION_TRACER - -endmenu diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c index de8393cb7313..8f234d0435aa 100644 --- a/arch/sh/boards/mach-ap325rxa/setup.c +++ b/arch/sh/boards/mach-ap325rxa/setup.c @@ -1,40 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Renesas - AP-325RXA * (Compatible with Algo System ., LTD. - AP-320A) * * Copyright (C) 2008 Renesas Solutions Corp. * Author : Yusuke Goda <goda.yuske@renesas.com> - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ -#include <linux/init.h> +#include <asm/clock.h> +#include <asm/io.h> +#include <asm/suspend.h> + +#include <cpu/sh7723.h> + +#include <linux/clkdev.h> +#include <linux/delay.h> #include <linux/device.h> +#include <linux/gpio.h> +#include <linux/gpio/machine.h> +#include <linux/i2c.h> +#include <linux/init.h> #include <linux/interrupt.h> -#include <linux/platform_device.h> +#include <linux/memblock.h> +#include <linux/mfd/tmio.h> #include <linux/mmc/host.h> #include <linux/mtd/physmap.h> #include <linux/mtd/sh_flctl.h> -#include <linux/mfd/tmio.h> -#include <linux/delay.h> -#include <linux/i2c.h> +#include <linux/platform_device.h> #include <linux/regulator/fixed.h> #include <linux/regulator/machine.h> +#include <linux/sh_intc.h> #include <linux/smsc911x.h> -#include <linux/gpio.h> #include <linux/videodev2.h> -#include <linux/sh_intc.h> + +#include <media/drv-intf/renesas-ceu.h> #include <media/i2c/ov772x.h> -#include <media/soc_camera.h> -#include <linux/platform_data/media/soc_camera_platform.h> -#include <media/drv-intf/sh_mobile_ceu.h> + #include <video/sh_mobile_lcdc.h> -#include <asm/io.h> -#include <asm/clock.h> -#include <asm/suspend.h> -#include <cpu/sh7723.h> + +#define CEU_BUFFER_MEMORY_SIZE (4 << 20) +static phys_addr_t ceu_dma_membase; /* Dummy supplies, where voltage doesn't matter */ static struct regulator_consumer_supply dummy_supplies[] = { @@ -253,150 +258,25 @@ static struct platform_device lcdc_device = { }, }; -static void camera_power(int val) -{ - gpio_set_value(GPIO_PTZ5, val); /* RST_CAM/RSTB */ - mdelay(10); -} - -#ifdef CONFIG_I2C -/* support for the old ncm03j camera */ -static unsigned char camera_ncm03j_magic[] = -{ - 0x87, 0x00, 0x88, 0x08, 0x89, 0x01, 0x8A, 0xE8, - 0x1D, 0x00, 0x1E, 0x8A, 0x21, 0x00, 0x33, 0x36, - 0x36, 0x60, 0x37, 0x08, 0x3B, 0x31, 0x44, 0x0F, - 0x46, 0xF0, 0x4B, 0x28, 0x4C, 0x21, 0x4D, 0x55, - 0x4E, 0x1B, 0x4F, 0xC7, 0x50, 0xFC, 0x51, 0x12, - 0x58, 0x02, 0x66, 0xC0, 0x67, 0x46, 0x6B, 0xA0, - 0x6C, 0x34, 0x7E, 0x25, 0x7F, 0x25, 0x8D, 0x0F, - 0x92, 0x40, 0x93, 0x04, 0x94, 0x26, 0x95, 0x0A, - 0x99, 0x03, 0x9A, 0xF0, 0x9B, 0x14, 0x9D, 0x7A, - 0xC5, 0x02, 0xD6, 0x07, 0x59, 0x00, 0x5A, 0x1A, - 0x5B, 0x2A, 0x5C, 0x37, 0x5D, 0x42, 0x5E, 0x56, - 0xC8, 0x00, 0xC9, 0x1A, 0xCA, 0x2A, 0xCB, 0x37, - 0xCC, 0x42, 0xCD, 0x56, 0xCE, 0x00, 0xCF, 0x1A, - 0xD0, 0x2A, 0xD1, 0x37, 0xD2, 0x42, 0xD3, 0x56, - 0x5F, 0x68, 0x60, 0x87, 0x61, 0xA3, 0x62, 0xBC, - 0x63, 0xD4, 0x64, 0xEA, 0xD6, 0x0F, -}; - -static int camera_probe(void) -{ - struct i2c_adapter *a = i2c_get_adapter(0); - struct i2c_msg msg; - int ret; - - if (!a) - return -ENODEV; - - camera_power(1); - msg.addr = 0x6e; - msg.buf = camera_ncm03j_magic; - msg.len = 2; - msg.flags = 0; - ret = i2c_transfer(a, &msg, 1); - camera_power(0); - - return ret; -} - -static int camera_set_capture(struct soc_camera_platform_info *info, - int enable) -{ - struct i2c_adapter *a = i2c_get_adapter(0); - struct i2c_msg msg; - int ret = 0; - int i; - - camera_power(0); - if (!enable) - return 0; /* no disable for now */ - - camera_power(1); - for (i = 0; i < ARRAY_SIZE(camera_ncm03j_magic); i += 2) { - u_int8_t buf[8]; - - msg.addr = 0x6e; - msg.buf = buf; - msg.len = 2; - msg.flags = 0; - - buf[0] = camera_ncm03j_magic[i]; - buf[1] = camera_ncm03j_magic[i + 1]; - - ret = (ret < 0) ? ret : i2c_transfer(a, &msg, 1); - } - - return ret; -} - -static int ap325rxa_camera_add(struct soc_camera_device *icd); -static void ap325rxa_camera_del(struct soc_camera_device *icd); - -static struct soc_camera_platform_info camera_info = { - .format_name = "UYVY", - .format_depth = 16, - .format = { - .code = MEDIA_BUS_FMT_UYVY8_2X8, - .colorspace = V4L2_COLORSPACE_SMPTE170M, - .field = V4L2_FIELD_NONE, - .width = 640, - .height = 480, +/* Powerdown/reset gpios for CEU image sensors */ +static struct gpiod_lookup_table ov7725_gpios = { + .dev_id = "0-0021", + .table = { + GPIO_LOOKUP("sh7723_pfc", GPIO_PTZ5, "reset", GPIO_ACTIVE_LOW), }, - .mbus_param = V4L2_MBUS_PCLK_SAMPLE_RISING | V4L2_MBUS_MASTER | - V4L2_MBUS_VSYNC_ACTIVE_HIGH | V4L2_MBUS_HSYNC_ACTIVE_HIGH | - V4L2_MBUS_DATA_ACTIVE_HIGH, - .mbus_type = V4L2_MBUS_PARALLEL, - .set_capture = camera_set_capture, -}; - -static struct soc_camera_link camera_link = { - .bus_id = 0, - .add_device = ap325rxa_camera_add, - .del_device = ap325rxa_camera_del, - .module_name = "soc_camera_platform", - .priv = &camera_info, }; -static struct platform_device *camera_device; - -static void ap325rxa_camera_release(struct device *dev) -{ - soc_camera_platform_release(&camera_device); -} - -static int ap325rxa_camera_add(struct soc_camera_device *icd) -{ - int ret = soc_camera_platform_add(icd, &camera_device, &camera_link, - ap325rxa_camera_release, 0); - if (ret < 0) - return ret; - - ret = camera_probe(); - if (ret < 0) - soc_camera_platform_del(icd, camera_device, &camera_link); - - return ret; -} - -static void ap325rxa_camera_del(struct soc_camera_device *icd) -{ - soc_camera_platform_del(icd, camera_device, &camera_link); -} -#endif /* CONFIG_I2C */ - -static int ov7725_power(struct device *dev, int mode) -{ - camera_power(0); - if (mode) - camera_power(1); - - return 0; -} - -static struct sh_mobile_ceu_info sh_mobile_ceu_info = { - .flags = SH_CEU_FLAG_USE_8BIT_BUS, +static struct ceu_platform_data ceu0_pdata = { + .num_subdevs = 1, + .subdevs = { + { /* [0] = ov7725 */ + .flags = 0, + .bus_width = 8, + .bus_shift = 0, + .i2c_adapter_id = 0, + .i2c_address = 0x21, + }, + }, }; static struct resource ceu_resources[] = { @@ -410,18 +290,15 @@ static struct resource ceu_resources[] = { .start = evt2irq(0x880), .flags = IORESOURCE_IRQ, }, - [2] = { - /* place holder for contiguous memory */ - }, }; -static struct platform_device ceu_device = { - .name = "sh_mobile_ceu", - .id = 0, /* "ceu0" clock */ +static struct platform_device ap325rxa_ceu_device = { + .name = "renesas-ceu", + .id = 0, /* "ceu.0" clock */ .num_resources = ARRAY_SIZE(ceu_resources), .resource = ceu_resources, .dev = { - .platform_data = &sh_mobile_ceu_info, + .platform_data = &ceu0_pdata, }, }; @@ -488,44 +365,18 @@ static struct platform_device sdhi1_cn7_device = { }, }; -static struct i2c_board_info __initdata ap325rxa_i2c_devices[] = { - { - I2C_BOARD_INFO("pcf8563", 0x51), - }, -}; - -static struct i2c_board_info ap325rxa_i2c_camera[] = { - { - I2C_BOARD_INFO("ov772x", 0x21), - }, -}; - static struct ov772x_camera_info ov7725_info = { .flags = OV772X_FLAG_VFLIP | OV772X_FLAG_HFLIP, .edgectrl = OV772X_AUTO_EDGECTRL(0xf, 0), }; -static struct soc_camera_link ov7725_link = { - .bus_id = 0, - .power = ov7725_power, - .board_info = &ap325rxa_i2c_camera[0], - .i2c_adapter_id = 0, - .priv = &ov7725_info, -}; - -static struct platform_device ap325rxa_camera[] = { +static struct i2c_board_info ap325rxa_i2c_devices[] __initdata = { { - .name = "soc-camera-pdrv", - .id = 0, - .dev = { - .platform_data = &ov7725_link, - }, - }, { - .name = "soc-camera-pdrv", - .id = 1, - .dev = { - .platform_data = &camera_link, - }, + I2C_BOARD_INFO("pcf8563", 0x51), + }, + { + I2C_BOARD_INFO("ov772x", 0x21), + .platform_data = &ov7725_info, }, }; @@ -533,12 +384,9 @@ static struct platform_device *ap325rxa_devices[] __initdata = { &smsc9118_device, &ap325rxa_nor_flash_device, &lcdc_device, - &ceu_device, &nand_flash_device, &sdhi0_cn3_device, &sdhi1_cn7_device, - &ap325rxa_camera[0], - &ap325rxa_camera[1], }; extern char ap325rxa_sdram_enter_start; @@ -649,8 +497,6 @@ static int __init ap325rxa_devices_setup(void) __raw_writew(0xFFFF, PORT_DRVCRA); __raw_writew(0xFFFF, PORT_DRVCRB); - platform_resource_setup_memory(&ceu_device, "ceu", 4 << 20); - /* SDHI0 - CN3 - SD CARD */ gpio_request(GPIO_FN_SDHI0CD_PTD, NULL); gpio_request(GPIO_FN_SDHI0WP_PTD, NULL); @@ -670,9 +516,25 @@ static int __init ap325rxa_devices_setup(void) gpio_request(GPIO_FN_SDHI1CMD, NULL); gpio_request(GPIO_FN_SDHI1CLK, NULL); + /* Add a clock alias for ov7725 xclk source. */ + clk_add_alias(NULL, "0-0021", "video_clk", NULL); + + /* Register RSTB gpio for ov7725 camera sensor. */ + gpiod_add_lookup_table(&ov7725_gpios); + i2c_register_board_info(0, ap325rxa_i2c_devices, ARRAY_SIZE(ap325rxa_i2c_devices)); + /* Initialize CEU platform device separately to map memory first */ + device_initialize(&ap325rxa_ceu_device.dev); + arch_setup_pdev_archdata(&ap325rxa_ceu_device); + dma_declare_coherent_memory(&ap325rxa_ceu_device.dev, + ceu_dma_membase, ceu_dma_membase, + ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1, + DMA_MEMORY_EXCLUSIVE); + + platform_device_add(&ap325rxa_ceu_device); + return platform_add_devices(ap325rxa_devices, ARRAY_SIZE(ap325rxa_devices)); } @@ -689,7 +551,21 @@ static int ap325rxa_mode_pins(void) return MODE_PIN5 | MODE_PIN8; } +/* Reserve a portion of memory for CEU buffers */ +static void __init ap325rxa_mv_mem_reserve(void) +{ + phys_addr_t phys; + phys_addr_t size = CEU_BUFFER_MEMORY_SIZE; + + phys = memblock_alloc_base(size, PAGE_SIZE, MEMBLOCK_ALLOC_ANYWHERE); + memblock_free(phys, size); + memblock_remove(phys, size); + + ceu_dma_membase = phys; +} + static struct sh_machine_vector mv_ap325rxa __initmv = { .mv_name = "AP-325RXA", .mv_mode_pins = ap325rxa_mode_pins, + .mv_mem_reserve = ap325rxa_mv_mem_reserve, }; diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c index 6af7777332fc..e59c577ed871 100644 --- a/arch/sh/boards/mach-kfr2r09/setup.c +++ b/arch/sh/boards/mach-kfr2r09/setup.c @@ -1,41 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 /* * KFR2R09 board support code * * Copyright (C) 2009 Magnus Damm - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/interrupt.h> -#include <linux/mmc/host.h> -#include <linux/mfd/tmio.h> -#include <linux/mtd/physmap.h> -#include <linux/mtd/onenand.h> + +#include <asm/clock.h> +#include <asm/io.h> +#include <asm/machvec.h> +#include <asm/suspend.h> + +#include <cpu/sh7724.h> + +#include <linux/clkdev.h> #include <linux/delay.h> -#include <linux/clk.h> +#include <linux/dma-mapping.h> #include <linux/gpio.h> +#include <linux/gpio/machine.h> +#include <linux/i2c.h> +#include <linux/init.h> #include <linux/input.h> #include <linux/input/sh_keysc.h> -#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/memblock.h> +#include <linux/mfd/tmio.h> +#include <linux/mmc/host.h> +#include <linux/mtd/onenand.h> +#include <linux/mtd/physmap.h> #include <linux/platform_data/lv5207lp.h> +#include <linux/platform_device.h> #include <linux/regulator/fixed.h> #include <linux/regulator/machine.h> +#include <linux/sh_intc.h> #include <linux/usb/r8a66597.h> #include <linux/videodev2.h> -#include <linux/sh_intc.h> + +#include <mach/kfr2r09.h> + +#include <media/drv-intf/renesas-ceu.h> #include <media/i2c/rj54n1cb0c.h> -#include <media/soc_camera.h> -#include <media/drv-intf/sh_mobile_ceu.h> + #include <video/sh_mobile_lcdc.h> -#include <asm/suspend.h> -#include <asm/clock.h> -#include <asm/machvec.h> -#include <asm/io.h> -#include <cpu/sh7724.h> -#include <mach/kfr2r09.h> + +#define CEU_BUFFER_MEMORY_SIZE (4 << 20) +static phys_addr_t ceu_dma_membase; + +/* set VIO_CKO clock to 25MHz */ +#define CEU_MCLK_FREQ 25000000 +#define DRVCRB 0xA405018C static struct mtd_partition kfr2r09_nor_flash_partitions[] = { @@ -230,8 +242,17 @@ static struct platform_device kfr2r09_usb0_gadget_device = { .resource = kfr2r09_usb0_gadget_resources, }; -static struct sh_mobile_ceu_info sh_mobile_ceu_info = { - .flags = SH_CEU_FLAG_USE_8BIT_BUS, +static struct ceu_platform_data ceu_pdata = { + .num_subdevs = 1, + .subdevs = { + { /* [0] = rj54n1cb0c */ + .flags = 0, + .bus_width = 8, + .bus_shift = 0, + .i2c_adapter_id = 1, + .i2c_address = 0x50, + }, + }, }; static struct resource kfr2r09_ceu_resources[] = { @@ -246,109 +267,35 @@ static struct resource kfr2r09_ceu_resources[] = { .end = evt2irq(0x880), .flags = IORESOURCE_IRQ, }, - [2] = { - /* place holder for contiguous memory */ - }, }; static struct platform_device kfr2r09_ceu_device = { - .name = "sh_mobile_ceu", + .name = "renesas-ceu", .id = 0, /* "ceu0" clock */ .num_resources = ARRAY_SIZE(kfr2r09_ceu_resources), .resource = kfr2r09_ceu_resources, .dev = { - .platform_data = &sh_mobile_ceu_info, + .platform_data = &ceu_pdata, }, }; -static struct i2c_board_info kfr2r09_i2c_camera = { - I2C_BOARD_INFO("rj54n1cb0c", 0x50), -}; - -static struct clk *camera_clk; - -/* set VIO_CKO clock to 25MHz */ -#define CEU_MCLK_FREQ 25000000 - -#define DRVCRB 0xA405018C -static int camera_power(struct device *dev, int mode) -{ - int ret; - - if (mode) { - long rate; - - camera_clk = clk_get(NULL, "video_clk"); - if (IS_ERR(camera_clk)) - return PTR_ERR(camera_clk); - - rate = clk_round_rate(camera_clk, CEU_MCLK_FREQ); - ret = clk_set_rate(camera_clk, rate); - if (ret < 0) - goto eclkrate; - - /* set DRVCRB - * - * use 1.8 V for VccQ_VIO - * use 2.85V for VccQ_SR - */ - __raw_writew((__raw_readw(DRVCRB) & ~0x0003) | 0x0001, DRVCRB); - - /* reset clear */ - ret = gpio_request(GPIO_PTB4, NULL); - if (ret < 0) - goto eptb4; - ret = gpio_request(GPIO_PTB7, NULL); - if (ret < 0) - goto eptb7; - - ret = gpio_direction_output(GPIO_PTB4, 1); - if (!ret) - ret = gpio_direction_output(GPIO_PTB7, 1); - if (ret < 0) - goto egpioout; - msleep(1); - - ret = clk_enable(camera_clk); /* start VIO_CKO */ - if (ret < 0) - goto eclkon; - - return 0; - } - - ret = 0; - - clk_disable(camera_clk); -eclkon: - gpio_set_value(GPIO_PTB7, 0); -egpioout: - gpio_set_value(GPIO_PTB4, 0); - gpio_free(GPIO_PTB7); -eptb7: - gpio_free(GPIO_PTB4); -eptb4: -eclkrate: - clk_put(camera_clk); - return ret; -} - static struct rj54n1_pdata rj54n1_priv = { .mclk_freq = CEU_MCLK_FREQ, .ioctl_high = false, }; -static struct soc_camera_link rj54n1_link = { - .power = camera_power, - .board_info = &kfr2r09_i2c_camera, - .i2c_adapter_id = 1, - .priv = &rj54n1_priv, +static struct i2c_board_info kfr2r09_i2c_camera = { + I2C_BOARD_INFO("rj54n1cb0c", 0x50), + .platform_data = &rj54n1_priv, }; -static struct platform_device kfr2r09_camera = { - .name = "soc-camera-pdrv", - .id = 0, - .dev = { - .platform_data = &rj54n1_link, +static struct gpiod_lookup_table rj54n1_gpios = { + .dev_id = "1-0050", + .table = { + GPIO_LOOKUP("sh7724_pfc", GPIO_PTB4, "poweron", + GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sh7724_pfc", GPIO_PTB7, "enable", + GPIO_ACTIVE_HIGH), }, }; @@ -393,8 +340,6 @@ static struct platform_device *kfr2r09_devices[] __initdata = { &kfr2r09_nand_flash_device, &kfr2r09_sh_keysc_device, &kfr2r09_sh_lcdc_device, - &kfr2r09_ceu_device, - &kfr2r09_camera, &kfr2r09_sh_sdhi0_device, }; @@ -533,6 +478,8 @@ extern char kfr2r09_sdram_leave_end; static int __init kfr2r09_devices_setup(void) { + static struct clk *camera_clk; + /* register board specific self-refresh code */ sh_mobile_register_self_refresh(SUSP_SH_STANDBY | SUSP_SH_SF | SUSP_SH_RSTANDBY, @@ -622,8 +569,6 @@ static int __init kfr2r09_devices_setup(void) gpio_request(GPIO_FN_VIO0_D1, NULL); gpio_request(GPIO_FN_VIO0_D0, NULL); - platform_resource_setup_memory(&kfr2r09_ceu_device, "ceu", 4 << 20); - /* SDHI0 connected to yc304 */ gpio_request(GPIO_FN_SDHI0CD, NULL); gpio_request(GPIO_FN_SDHI0D3, NULL); @@ -635,6 +580,36 @@ static int __init kfr2r09_devices_setup(void) i2c_register_board_info(0, &kfr2r09_backlight_board_info, 1); + /* Set camera clock frequency and register and alias for rj54n1. */ + camera_clk = clk_get(NULL, "video_clk"); + if (!IS_ERR(camera_clk)) { + clk_set_rate(camera_clk, + clk_round_rate(camera_clk, CEU_MCLK_FREQ)); + clk_put(camera_clk); + } + clk_add_alias(NULL, "1-0050", "video_clk", NULL); + + /* set DRVCRB + * + * use 1.8 V for VccQ_VIO + * use 2.85V for VccQ_SR + */ + __raw_writew((__raw_readw(DRVCRB) & ~0x0003) | 0x0001, DRVCRB); + + gpiod_add_lookup_table(&rj54n1_gpios); + + i2c_register_board_info(1, &kfr2r09_i2c_camera, 1); + + /* Initialize CEU platform device separately to map memory first */ + device_initialize(&kfr2r09_ceu_device.dev); + arch_setup_pdev_archdata(&kfr2r09_ceu_device); + dma_declare_coherent_memory(&kfr2r09_ceu_device.dev, + ceu_dma_membase, ceu_dma_membase, + ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1, + DMA_MEMORY_EXCLUSIVE); + + platform_device_add(&kfr2r09_ceu_device); + return platform_add_devices(kfr2r09_devices, ARRAY_SIZE(kfr2r09_devices)); } @@ -651,10 +626,24 @@ static int kfr2r09_mode_pins(void) return MODE_PIN0 | MODE_PIN1 | MODE_PIN5 | MODE_PIN8; } +/* Reserve a portion of memory for CEU buffers */ +static void __init kfr2r09_mv_mem_reserve(void) +{ + phys_addr_t phys; + phys_addr_t size = CEU_BUFFER_MEMORY_SIZE; + + phys = memblock_alloc_base(size, PAGE_SIZE, MEMBLOCK_ALLOC_ANYWHERE); + memblock_free(phys, size); + memblock_remove(phys, size); + + ceu_dma_membase = phys; +} + /* * The Machine Vector */ static struct sh_machine_vector mv_kfr2r09 __initmv = { .mv_name = "kfr2r09", .mv_mode_pins = kfr2r09_mode_pins, + .mv_mem_reserve = kfr2r09_mv_mem_reserve, }; diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c index 3d7d0046cf49..254f2c662703 100644 --- a/arch/sh/boards/mach-migor/setup.c +++ b/arch/sh/boards/mach-migor/setup.c @@ -28,7 +28,6 @@ #include <video/sh_mobile_lcdc.h> #include <media/drv-intf/renesas-ceu.h> #include <media/i2c/ov772x.h> -#include <media/soc_camera.h> #include <media/i2c/tw9910.h> #include <asm/clock.h> #include <asm/machvec.h> @@ -351,8 +350,9 @@ static struct platform_device migor_ceu_device = { static struct gpiod_lookup_table ov7725_gpios = { .dev_id = "0-0021", .table = { - GPIO_LOOKUP("sh7722_pfc", GPIO_PTT0, "pwdn", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sh7722_pfc", GPIO_PTT3, "rstb", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("sh7722_pfc", GPIO_PTT0, "powerdown", + GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sh7722_pfc", GPIO_PTT3, "reset", GPIO_ACTIVE_LOW), }, }; @@ -592,7 +592,7 @@ static int __init migor_devices_setup(void) } /* Add a clock alias for ov7725 xclk source. */ - clk_add_alias("xclk", "0-0021", "video_clk", NULL); + clk_add_alias(NULL, "0-0021", "video_clk", NULL); /* Register GPIOs for video sources. */ gpiod_add_lookup_table(&ov7725_gpios); diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c index 255952555656..fdbec22ae687 100644 --- a/arch/sh/boards/mach-se/7724/setup.c +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -1,43 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/arch/sh/boards/se/7724/setup.c * * Copyright (C) 2009 Renesas Solutions Corp. * * Kuninori Morimoto <morimoto.kuninori@renesas.com> - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. */ +#include <asm/clock.h> +#include <asm/heartbeat.h> +#include <asm/io.h> +#include <asm/suspend.h> -#include <linux/init.h> +#include <cpu/sh7724.h> + +#include <linux/delay.h> #include <linux/device.h> +#include <linux/gpio.h> +#include <linux/init.h> +#include <linux/input.h> +#include <linux/input/sh_keysc.h> #include <linux/interrupt.h> -#include <linux/platform_device.h> -#include <linux/mmc/host.h> +#include <linux/memblock.h> #include <linux/mfd/tmio.h> +#include <linux/mmc/host.h> #include <linux/mtd/physmap.h> -#include <linux/delay.h> +#include <linux/platform_device.h> #include <linux/regulator/fixed.h> #include <linux/regulator/machine.h> -#include <linux/smc91x.h> -#include <linux/gpio.h> -#include <linux/input.h> -#include <linux/input/sh_keysc.h> -#include <linux/usb/r8a66597.h> #include <linux/sh_eth.h> #include <linux/sh_intc.h> +#include <linux/smc91x.h> +#include <linux/usb/r8a66597.h> #include <linux/videodev2.h> -#include <video/sh_mobile_lcdc.h> -#include <media/drv-intf/sh_mobile_ceu.h> + +#include <mach-se/mach/se7724.h> +#include <media/drv-intf/renesas-ceu.h> + #include <sound/sh_fsi.h> #include <sound/simple_card.h> -#include <asm/io.h> -#include <asm/heartbeat.h> -#include <asm/clock.h> -#include <asm/suspend.h> -#include <cpu/sh7724.h> -#include <mach-se/mach/se7724.h> + +#include <video/sh_mobile_lcdc.h> + +#define CEU_BUFFER_MEMORY_SIZE (4 << 20) +static phys_addr_t ceu0_dma_membase; +static phys_addr_t ceu1_dma_membase; /* * SWx 1234 5678 @@ -216,8 +222,8 @@ static struct platform_device lcdc_device = { }; /* CEU0 */ -static struct sh_mobile_ceu_info sh_mobile_ceu0_info = { - .flags = SH_CEU_FLAG_USE_8BIT_BUS, +static struct ceu_platform_data ceu0_pdata = { + .num_subdevs = 0, }; static struct resource ceu0_resources[] = { @@ -231,24 +237,21 @@ static struct resource ceu0_resources[] = { .start = evt2irq(0x880), .flags = IORESOURCE_IRQ, }, - [2] = { - /* place holder for contiguous memory */ - }, }; static struct platform_device ceu0_device = { - .name = "sh_mobile_ceu", - .id = 0, /* "ceu0" clock */ + .name = "renesas-ceu", + .id = 0, /* "ceu.0" clock */ .num_resources = ARRAY_SIZE(ceu0_resources), .resource = ceu0_resources, .dev = { - .platform_data = &sh_mobile_ceu0_info, + .platform_data = &ceu0_pdata, }, }; /* CEU1 */ -static struct sh_mobile_ceu_info sh_mobile_ceu1_info = { - .flags = SH_CEU_FLAG_USE_8BIT_BUS, +static struct ceu_platform_data ceu1_pdata = { + .num_subdevs = 0, }; static struct resource ceu1_resources[] = { @@ -262,18 +265,15 @@ static struct resource ceu1_resources[] = { .start = evt2irq(0x9e0), .flags = IORESOURCE_IRQ, }, - [2] = { - /* place holder for contiguous memory */ - }, }; static struct platform_device ceu1_device = { - .name = "sh_mobile_ceu", - .id = 1, /* "ceu1" clock */ + .name = "renesas-ceu", + .id = 1, /* "ceu.1" clock */ .num_resources = ARRAY_SIZE(ceu1_resources), .resource = ceu1_resources, .dev = { - .platform_data = &sh_mobile_ceu1_info, + .platform_data = &ceu1_pdata, }, }; @@ -574,13 +574,16 @@ static struct platform_device vou_device = { }, }; +static struct platform_device *ms7724se_ceu_devices[] __initdata = { + &ceu0_device, + &ceu1_device, +}; + static struct platform_device *ms7724se_devices[] __initdata = { &heartbeat_device, &smc91x_eth_device, &lcdc_device, &nor_flash_device, - &ceu0_device, - &ceu1_device, &keysc_device, &sh_eth_device, &sh7724_usb0_host_device, @@ -797,7 +800,6 @@ static int __init devices_setup(void) gpio_request(GPIO_FN_VIO0_CLK, NULL); gpio_request(GPIO_FN_VIO0_FLD, NULL); gpio_request(GPIO_FN_VIO0_HD, NULL); - platform_resource_setup_memory(&ceu0_device, "ceu0", 4 << 20); /* enable CEU1 */ gpio_request(GPIO_FN_VIO1_D7, NULL); @@ -812,7 +814,6 @@ static int __init devices_setup(void) gpio_request(GPIO_FN_VIO1_HD, NULL); gpio_request(GPIO_FN_VIO1_VD, NULL); gpio_request(GPIO_FN_VIO1_CLK, NULL); - platform_resource_setup_memory(&ceu1_device, "ceu1", 4 << 20); /* KEYSC */ gpio_request(GPIO_FN_KEYOUT5_IN5, NULL); @@ -934,12 +935,49 @@ static int __init devices_setup(void) gpio_request(GPIO_FN_DV_VSYNC, NULL); gpio_request(GPIO_FN_DV_HSYNC, NULL); + /* Initialize CEU platform devices separately to map memory first */ + device_initialize(&ms7724se_ceu_devices[0]->dev); + arch_setup_pdev_archdata(ms7724se_ceu_devices[0]); + dma_declare_coherent_memory(&ms7724se_ceu_devices[0]->dev, + ceu0_dma_membase, ceu0_dma_membase, + ceu0_dma_membase + + CEU_BUFFER_MEMORY_SIZE - 1, + DMA_MEMORY_EXCLUSIVE); + platform_device_add(ms7724se_ceu_devices[0]); + + device_initialize(&ms7724se_ceu_devices[1]->dev); + arch_setup_pdev_archdata(ms7724se_ceu_devices[1]); + dma_declare_coherent_memory(&ms7724se_ceu_devices[1]->dev, + ceu1_dma_membase, ceu1_dma_membase, + ceu1_dma_membase + + CEU_BUFFER_MEMORY_SIZE - 1, + DMA_MEMORY_EXCLUSIVE); + platform_device_add(ms7724se_ceu_devices[1]); + return platform_add_devices(ms7724se_devices, ARRAY_SIZE(ms7724se_devices)); } device_initcall(devices_setup); +/* Reserve a portion of memory for CEU 0 and CEU 1 buffers */ +static void __init ms7724se_mv_mem_reserve(void) +{ + phys_addr_t phys; + phys_addr_t size = CEU_BUFFER_MEMORY_SIZE; + + phys = memblock_alloc_base(size, PAGE_SIZE, MEMBLOCK_ALLOC_ANYWHERE); + memblock_free(phys, size); + memblock_remove(phys, size); + ceu0_dma_membase = phys; + + phys = memblock_alloc_base(size, PAGE_SIZE, MEMBLOCK_ALLOC_ANYWHERE); + memblock_free(phys, size); + memblock_remove(phys, size); + ceu1_dma_membase = phys; +} + static struct sh_machine_vector mv_ms7724se __initmv = { .mv_name = "ms7724se", .mv_init_irq = init_se7724_IRQ, + .mv_mem_reserve = ms7724se_mv_mem_reserve, }; diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c index 46b2481eec90..26789ad28193 100644 --- a/arch/sh/boards/of-generic.c +++ b/arch/sh/boards/of-generic.c @@ -56,15 +56,15 @@ const struct of_cpu_method __cpu_method_of_table_sentinel static void sh_of_smp_probe(void) { - struct device_node *np = 0; - const char *method = 0; + struct device_node *np; + const char *method = NULL; const struct of_cpu_method *m = __cpu_method_of_table; pr_info("SH generic board support: scanning for cpus\n"); init_cpu_possible(cpumask_of(0)); - while ((np = of_find_node_by_type(np, "cpu"))) { + for_each_node_by_type(np, "cpu") { const __be32 *cell = of_get_property(np, "reg", NULL); u64 id = -1; if (cell) id = of_read_number(cell, of_n_addr_cells(np)); @@ -80,6 +80,7 @@ static void sh_of_smp_probe(void) if (!method) { np = of_find_node_by_name(NULL, "cpus"); of_property_read_string(np, "enable-method", &method); + of_node_put(np); } pr_info("CPU enable method: %s\n", method); diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index e5b7437ab4af..8256626bc53c 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -160,8 +160,6 @@ static int __init pcibios_init(void) for (hose = hose_head; hose; hose = hose->next) pcibios_scanbus(hose); - dma_debug_add_bus(&pci_bus_type); - pci_initialized = 1; return 0; diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 46dd82ab2c29..6a5609a55965 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -2,6 +2,7 @@ generic-y += compat.h generic-y += current.h generic-y += delay.h generic-y += div64.h +generic-y += dma-mapping.h generic-y += emergency-restart.h generic-y += exec.h generic-y += irq_regs.h diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index 0fd0099f43cc..f37b95a80232 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -32,44 +32,9 @@ #include <asm/atomic-irq.h> #endif -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic_dec_return(v) atomic_sub_return(1, (v)) -#define atomic_inc_return(v) atomic_add_return(1, (v)) -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) - -#define atomic_inc(v) atomic_add(1, (v)) -#define atomic_dec(v) atomic_sub(1, (v)) - #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - - return c; -} - #endif /* CONFIG_CPU_J2 */ #endif /* __ASM_SH_ATOMIC_H */ diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index d103ab5a4e4b..b932e42ef028 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -101,5 +101,12 @@ void kunmap_coherent(void *kvaddr); void cpu_cache_init(void); +static inline void *sh_cacheop_vaddr(void *vaddr) +{ + if (__in_29bit_mode()) + vaddr = (void *)CAC_ADDR((unsigned long)vaddr); + return vaddr; +} + #endif /* __KERNEL__ */ #endif /* __ASM_SH_CACHEFLUSH_H */ diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h index 1e881f5db659..593a9704782b 100644 --- a/arch/sh/include/asm/cmpxchg-xchg.h +++ b/arch/sh/include/asm/cmpxchg-xchg.h @@ -8,7 +8,8 @@ * This work is licensed under the terms of the GNU GPL, version 2. See the * file "COPYING" in the main directory of this archive for more details. */ -#include <linux/bitops.h> +#include <linux/bits.h> +#include <linux/compiler.h> #include <asm/byteorder.h> /* diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h deleted file mode 100644 index 41167931e5d9..000000000000 --- a/arch/sh/include/asm/dma-mapping.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_SH_DMA_MAPPING_H -#define __ASM_SH_DMA_MAPPING_H - -extern const struct dma_map_ops *dma_ops; -extern void no_iommu_init(void); - -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return dma_ops; -} - -extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_addr, gfp_t flag, - unsigned long attrs); -extern void dma_generic_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs); - -void sh_sync_dma_for_device(void *vaddr, size_t size, - enum dma_data_direction dir); - -#endif /* __ASM_SH_DMA_MAPPING_H */ diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h index 7431c172c0cb..199d17b765f2 100644 --- a/arch/sh/include/asm/hw_breakpoint.h +++ b/arch/sh/include/asm/hw_breakpoint.h @@ -10,7 +10,6 @@ #include <linux/types.h> struct arch_hw_breakpoint { - char *name; /* Contains name of the symbol to set bkpt */ unsigned long address; u16 len; u16 type; @@ -41,6 +40,7 @@ struct sh_ubc { struct clk *clk; /* optional interface clock / MSTP bit */ }; +struct perf_event_attr; struct perf_event; struct task_struct; struct pmu; @@ -54,8 +54,10 @@ static inline int hw_breakpoint_slots(int type) } /* arch/sh/kernel/hw_breakpoint.c */ -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/sh/include/asm/kexec.h b/arch/sh/include/asm/kexec.h index fd5f331a3912..927d80ba2332 100644 --- a/arch/sh/include/asm/kexec.h +++ b/arch/sh/include/asm/kexec.h @@ -4,6 +4,7 @@ #include <asm/ptrace.h> #include <asm/string.h> +#include <linux/kernel.h> /* * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return. @@ -61,7 +62,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, __asm__ __volatile__ ("stc gbr, %0" : "=r" (newregs->gbr)); __asm__ __volatile__ ("stc sr, %0" : "=r" (newregs->sr)); - newregs->pc = (unsigned long)current_text_addr(); + newregs->pc = _THIS_IP_; } } #else diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h index 85d8bcaa8493..6171682f7798 100644 --- a/arch/sh/include/asm/kprobes.h +++ b/arch/sh/include/asm/kprobes.h @@ -27,7 +27,6 @@ struct kprobe; void arch_remove_kprobe(struct kprobe *); void kretprobe_trampoline(void); -void jprobe_return_end(void); /* Architecture specific copy of original instruction*/ struct arch_specific_insn { @@ -43,9 +42,6 @@ struct prev_kprobe { /* per-cpu kprobe control block */ struct kprobe_ctlblk { unsigned long kprobe_status; - unsigned long jprobe_saved_r15; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile index dc80041f7363..59673f8a3379 100644 --- a/arch/sh/kernel/Makefile +++ b/arch/sh/kernel/Makefile @@ -12,7 +12,7 @@ endif CFLAGS_REMOVE_return_address.o = -pg -obj-y := debugtraps.o dma-nommu.o dumpstack.o \ +obj-y := debugtraps.o dumpstack.o \ idle.o io.o irq.o irq_$(BITS).o kdebugfs.o \ machvec.o nmi_debug.o process.o \ process_$(BITS).o ptrace.o ptrace_$(BITS).o \ @@ -45,7 +45,7 @@ obj-$(CONFIG_DUMP_CODE) += disassemble.o obj-$(CONFIG_HIBERNATION) += swsusp.o obj-$(CONFIG_DWARF_UNWINDER) += dwarf.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_callchain.o - +obj-$(CONFIG_DMA_NONCOHERENT) += dma-coherent.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o ccflags-y := -Werror diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c index fe844222f3f6..af01664f7b4c 100644 --- a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c +++ b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c @@ -260,7 +260,7 @@ static struct clk_lookup lookups[] = { CLKDEV_CON_ID("veu1", &mstp_clks[HWBLK_VEU2H1]), CLKDEV_DEV_ID("sh-vou.0", &mstp_clks[HWBLK_VOU]), CLKDEV_CON_ID("beu0", &mstp_clks[HWBLK_BEU]), - CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[HWBLK_CEU]), + CLKDEV_DEV_ID("ceu.0", &mstp_clks[HWBLK_CEU]), CLKDEV_CON_ID("veu0", &mstp_clks[HWBLK_VEU2H0]), CLKDEV_CON_ID("vpu0", &mstp_clks[HWBLK_VPU]), diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c new file mode 100644 index 000000000000..a0021eef956b --- /dev/null +++ b/arch/sh/kernel/dma-coherent.c @@ -0,0 +1,83 @@ +/* + * Copyright (C) 2004 - 2007 Paul Mundt + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#include <linux/mm.h> +#include <linux/init.h> +#include <linux/dma-noncoherent.h> +#include <linux/module.h> +#include <asm/cacheflush.h> +#include <asm/addrspace.h> + +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + void *ret, *ret_nocache; + int order = get_order(size); + + gfp |= __GFP_ZERO; + + ret = (void *)__get_free_pages(gfp, order); + if (!ret) + return NULL; + + /* + * Pages from the page allocator may have data present in + * cache. So flush the cache before using uncached memory. + */ + arch_sync_dma_for_device(dev, virt_to_phys(ret), size, + DMA_BIDIRECTIONAL); + + ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size); + if (!ret_nocache) { + free_pages((unsigned long)ret, order); + return NULL; + } + + split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order); + + *dma_handle = virt_to_phys(ret); + if (!WARN_ON(!dev)) + *dma_handle -= PFN_PHYS(dev->dma_pfn_offset); + + return ret_nocache; +} + +void arch_dma_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, unsigned long attrs) +{ + int order = get_order(size); + unsigned long pfn = (dma_handle >> PAGE_SHIFT); + int k; + + if (!WARN_ON(!dev)) + pfn += dev->dma_pfn_offset; + + for (k = 0; k < (1 << order); k++) + __free_pages(pfn_to_page(pfn + k), 0); + + iounmap(vaddr); +} + +void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) +{ + void *addr = sh_cacheop_vaddr(phys_to_virt(paddr)); + + switch (dir) { + case DMA_FROM_DEVICE: /* invalidate only */ + __flush_invalidate_region(addr, size); + break; + case DMA_TO_DEVICE: /* writeback only */ + __flush_wback_region(addr, size); + break; + case DMA_BIDIRECTIONAL: /* writeback and invalidate */ + __flush_purge_region(addr, size); + break; + default: + BUG(); + } +} diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c deleted file mode 100644 index 3e3a32fc676e..000000000000 --- a/arch/sh/kernel/dma-nommu.c +++ /dev/null @@ -1,88 +0,0 @@ -/* - * DMA mapping support for platforms lacking IOMMUs. - * - * Copyright (C) 2009 Paul Mundt - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ -#include <linux/dma-mapping.h> -#include <linux/io.h> -#include <asm/cacheflush.h> - -static dma_addr_t nommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t addr = page_to_phys(page) + offset - - PFN_PHYS(dev->dma_pfn_offset); - - WARN_ON(size == 0); - - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - sh_sync_dma_for_device(page_address(page) + offset, size, dir); - - return addr; -} - -static int nommu_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s; - int i; - - WARN_ON(nents == 0 || sg[0].length == 0); - - for_each_sg(sg, s, nents, i) { - dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset); - - BUG_ON(!sg_page(s)); - - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - sh_sync_dma_for_device(sg_virt(s), s->length, dir); - - s->dma_address = sg_phys(s) - offset; - s->dma_length = s->length; - } - - return nents; -} - -#ifdef CONFIG_DMA_NONCOHERENT -static void nommu_sync_single_for_device(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) -{ - sh_sync_dma_for_device(phys_to_virt(addr), size, dir); -} - -static void nommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir) -{ - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nelems, i) - sh_sync_dma_for_device(sg_virt(s), s->length, dir); -} -#endif - -const struct dma_map_ops nommu_dma_ops = { - .alloc = dma_generic_alloc_coherent, - .free = dma_generic_free_coherent, - .map_page = nommu_map_page, - .map_sg = nommu_map_sg, -#ifdef CONFIG_DMA_NONCOHERENT - .sync_single_for_device = nommu_sync_single_for_device, - .sync_sg_for_device = nommu_sync_sg_for_device, -#endif -}; - -void __init no_iommu_init(void) -{ - if (dma_ops) - return; - dma_ops = &nommu_dma_ops; -} diff --git a/arch/sh/kernel/dwarf.c b/arch/sh/kernel/dwarf.c index 1a2526676a87..bb511e2d9d68 100644 --- a/arch/sh/kernel/dwarf.c +++ b/arch/sh/kernel/dwarf.c @@ -599,7 +599,7 @@ struct dwarf_frame *dwarf_unwind_stack(unsigned long pc, * time this function makes its first function call. */ if (!pc || !prev) - pc = (unsigned long)current_text_addr(); + pc = _THIS_IP_; #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c index 8648ed05ccf0..d9ff3b42da7c 100644 --- a/arch/sh/kernel/hw_breakpoint.c +++ b/arch/sh/kernel/hw_breakpoint.c @@ -124,14 +124,13 @@ static int get_hbp_len(u16 hbp_len) /* * Check for virtual address in kernel space. */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = get_hbp_len(info->len); + va = hw->address; + len = get_hbp_len(hw->len); return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -174,40 +173,40 @@ int arch_bp_generic_fields(int sh_len, int sh_type, return 0; } -static int arch_build_bp_info(struct perf_event *bp) +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - info->address = bp->attr.bp_addr; + hw->address = attr->bp_addr; /* Len */ - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->len = SH_BREAKPOINT_LEN_1; + hw->len = SH_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->len = SH_BREAKPOINT_LEN_2; + hw->len = SH_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->len = SH_BREAKPOINT_LEN_4; + hw->len = SH_BREAKPOINT_LEN_4; break; case HW_BREAKPOINT_LEN_8: - info->len = SH_BREAKPOINT_LEN_8; + hw->len = SH_BREAKPOINT_LEN_8; break; default: return -EINVAL; } /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_R: - info->type = SH_BREAKPOINT_READ; + hw->type = SH_BREAKPOINT_READ; break; case HW_BREAKPOINT_W: - info->type = SH_BREAKPOINT_WRITE; + hw->type = SH_BREAKPOINT_WRITE; break; case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = SH_BREAKPOINT_RW; + hw->type = SH_BREAKPOINT_RW; break; default: return -EINVAL; @@ -219,19 +218,20 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned int align; int ret; - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; ret = -EINVAL; - switch (info->len) { + switch (hw->len) { case SH_BREAKPOINT_LEN_1: align = 0; break; @@ -249,17 +249,10 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) } /* - * For kernel-addresses, either the address or symbol name can be - * specified. - */ - if (info->name) - info->address = (unsigned long)kallsyms_lookup_name(info->name); - - /* * Check that the low-order bits of the address are appropriate * for the alignment implied by len. */ - if (info->address & align) + if (hw->address & align) return -EINVAL; return 0; @@ -346,7 +339,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) perf_bp_event(bp, args->regs); /* Deliver the signal to userspace */ - if (!arch_check_bp_in_kernelspace(bp)) { + if (!arch_check_bp_in_kernelspace(&bp->hw.info)) { force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)NULL, current); } diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 52a5e11247d1..241e903dd3ee 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -248,11 +248,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_REENTER; return 1; - } else { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - goto ss_probe; - } } goto no_kprobe; } @@ -277,11 +272,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) set_current_kprobe(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { /* handler has already set things up, so skip ss setup */ + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; return 1; @@ -358,8 +355,6 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) regs->pc = orig_ret_address; kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); @@ -508,14 +503,8 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, if (post_kprobe_handler(args->regs)) ret = NOTIFY_STOP; } else { - if (kprobe_handler(args->regs)) { + if (kprobe_handler(args->regs)) ret = NOTIFY_STOP; - } else { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && - p->break_handler(p, args->regs)) - ret = NOTIFY_STOP; - } } } } @@ -523,57 +512,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_r15 = regs->regs[15]; - addr = kcb->jprobe_saved_r15; - - /* - * TBD: As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. - */ - memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr, - MIN_STACK_SIZE(addr)); - - regs->pc = (unsigned long)(jp->entry); - - return 1; -} - -void __kprobes jprobe_return(void) -{ - asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t"); -} - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long stack_addr = kcb->jprobe_saved_r15; - u8 *addr = (u8 *)regs->pc; - - if ((addr >= (u8 *)jprobe_return) && - (addr <= (u8 *)jprobe_return_end)) { - *regs = kcb->jprobe_saved_regs; - - memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack, - MIN_STACK_SIZE(stack_addr)); - - kcb->kprobe_status = KPROBE_HIT_SS; - preempt_enable_no_resched(); - return 1; - } - - return 0; -} - static struct kprobe trampoline_p = { .addr = (kprobe_opcode_t *)&kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 50cdd1349015..02ed2df25a54 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -225,8 +225,6 @@ config HUGETLB_PAGE_SIZE_512MB endchoice -source "mm/Kconfig" - config SCHED_MC bool "Multi-core scheduler support" depends on SMP diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c index fceb2adfcac7..792f36129062 100644 --- a/arch/sh/mm/consistent.c +++ b/arch/sh/mm/consistent.c @@ -1,10 +1,6 @@ /* - * arch/sh/mm/consistent.c - * * Copyright (C) 2004 - 2007 Paul Mundt * - * Declared coherent memory functions based on arch/x86/kernel/pci-dma_32.c - * * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. @@ -13,90 +9,7 @@ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/dma-mapping.h> -#include <linux/dma-debug.h> #include <linux/io.h> -#include <linux/module.h> -#include <linux/gfp.h> -#include <asm/cacheflush.h> -#include <asm/addrspace.h> - -const struct dma_map_ops *dma_ops; -EXPORT_SYMBOL(dma_ops); - -void *dma_generic_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, - unsigned long attrs) -{ - void *ret, *ret_nocache; - int order = get_order(size); - - gfp |= __GFP_ZERO; - - ret = (void *)__get_free_pages(gfp, order); - if (!ret) - return NULL; - - /* - * Pages from the page allocator may have data present in - * cache. So flush the cache before using uncached memory. - */ - sh_sync_dma_for_device(ret, size, DMA_BIDIRECTIONAL); - - ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size); - if (!ret_nocache) { - free_pages((unsigned long)ret, order); - return NULL; - } - - split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order); - - *dma_handle = virt_to_phys(ret); - if (!WARN_ON(!dev)) - *dma_handle -= PFN_PHYS(dev->dma_pfn_offset); - - return ret_nocache; -} - -void dma_generic_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ - int order = get_order(size); - unsigned long pfn = dma_handle >> PAGE_SHIFT; - int k; - - if (!WARN_ON(!dev)) - pfn += dev->dma_pfn_offset; - - for (k = 0; k < (1 << order); k++) - __free_pages(pfn_to_page(pfn + k), 0); - - iounmap(vaddr); -} - -void sh_sync_dma_for_device(void *vaddr, size_t size, - enum dma_data_direction direction) -{ - void *addr; - - addr = __in_29bit_mode() ? - (void *)CAC_ADDR((unsigned long)vaddr) : vaddr; - - switch (direction) { - case DMA_FROM_DEVICE: /* invalidate only */ - __flush_invalidate_region(addr, size); - break; - case DMA_TO_DEVICE: /* writeback only */ - __flush_wback_region(addr, size); - break; - case DMA_BIDIRECTIONAL: /* writeback and invalidate */ - __flush_purge_region(addr, size); - break; - default: - BUG(); - } -} -EXPORT_SYMBOL(sh_sync_dma_for_device); static int __init memchunk_setup(char *str) { diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index b8e7bb84b6b1..6defd2c6d9b1 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -313,7 +313,7 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address) static noinline int mm_fault_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, unsigned int fault) + unsigned long address, vm_fault_t fault) { /* * Pagefault was interrupted by SIGKILL. We have no reason to @@ -396,7 +396,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, struct task_struct *tsk; struct mm_struct *mm; struct vm_area_struct * vma; - int fault; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; tsk = current; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 4034035fbede..7713c084d040 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -339,22 +339,12 @@ void __init paging_init(void) free_area_init_nodes(max_zone_pfns); } -/* - * Early initialization for any I/O MMUs we might have. - */ -static void __init iommu_init(void) -{ - no_iommu_init(); -} - unsigned int mem_init_done = 0; void __init mem_init(void) { pg_data_t *pgdat; - iommu_init(); - high_memory = NULL; for_each_online_pgdat(pgdat) high_memory = max_t(void *, high_memory, diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 0f535debf802..2d58c26bff9a 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -155,10 +155,6 @@ config PGTABLE_LEVELS config ARCH_SUPPORTS_UPROBES def_bool y if SPARC64 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - menu "Processor type and features" config SMP @@ -331,8 +327,6 @@ config FORCE_MAX_ZONEORDER This config option is actually maximum order plus one. For example, a value of 13 means that the largest free memory block is 2^12 pages. -source "mm/Kconfig" - if SPARC64 source "kernel/power/Kconfig" endif @@ -355,8 +349,6 @@ config SCHED_MC making when dealing with multi-core CPU chips at a cost of slightly increased overhead in some places. If unsure say N here. -source "kernel/Kconfig.preempt" - config CMDLINE_BOOL bool "Default bootloader kernel arguments" depends on SPARC64 @@ -556,10 +548,6 @@ config SPARC64_PCI_MSI endmenu -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - config COMPAT bool depends on SPARC64 @@ -574,20 +562,4 @@ config SYSVIPC_COMPAT depends on COMPAT && SYSVIPC default y -endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - source "drivers/sbus/char/Kconfig" - -source "fs/Kconfig" - -source "arch/sparc/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug index 4aef29a11925..50a918d496c8 100644 --- a/arch/sparc/Kconfig.debug +++ b/arch/sparc/Kconfig.debug @@ -1,12 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" config TRACE_IRQFLAGS_SUPPORT bool default y -source "lib/Kconfig.debug" - config DEBUG_DCFLUSH bool "D-cache flush debugging" depends on SPARC64 && DEBUG_KERNEL @@ -21,5 +18,3 @@ config FRAME_POINTER bool depends on MCOUNT default y - -endmenu diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c index c9d2b922734b..bc9cc26efa3d 100644 --- a/arch/sparc/crypto/md5_glue.c +++ b/arch/sparc/crypto/md5_glue.c @@ -144,7 +144,6 @@ static struct shash_alg alg = { .cra_name = "md5", .cra_driver_name= "md5-sparc64", .cra_priority = SPARC_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = MD5_HMAC_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c index 1b3e47accc74..4d6d7faf728e 100644 --- a/arch/sparc/crypto/sha1_glue.c +++ b/arch/sparc/crypto/sha1_glue.c @@ -139,7 +139,6 @@ static struct shash_alg alg = { .cra_name = "sha1", .cra_driver_name= "sha1-sparc64", .cra_priority = SPARC_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c index 285268ca9279..54c4de2db188 100644 --- a/arch/sparc/crypto/sha256_glue.c +++ b/arch/sparc/crypto/sha256_glue.c @@ -169,7 +169,6 @@ static struct shash_alg sha256 = { .cra_name = "sha256", .cra_driver_name= "sha256-sparc64", .cra_priority = SPARC_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -185,7 +184,6 @@ static struct shash_alg sha224 = { .cra_name = "sha224", .cra_driver_name= "sha224-sparc64", .cra_priority = SPARC_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c index 11eb36c3fc8c..4c55e97a4408 100644 --- a/arch/sparc/crypto/sha512_glue.c +++ b/arch/sparc/crypto/sha512_glue.c @@ -154,7 +154,6 @@ static struct shash_alg sha512 = { .cra_name = "sha512", .cra_driver_name= "sha512-sparc64", .cra_priority = SPARC_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -170,7 +169,6 @@ static struct shash_alg sha384 = { .cra_name = "sha384", .cra_driver_name= "sha384-sparc64", .cra_priority = SPARC_CR_OPCODE_PRIORITY, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index ac67828da201..410b263ef5c8 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -13,6 +13,7 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h +generic-y += msi.h generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index d13ce517f4b9..94c930f0bc62 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -27,17 +27,17 @@ int atomic_fetch_or(int, atomic_t *); int atomic_fetch_xor(int, atomic_t *); int atomic_cmpxchg(atomic_t *, int, int); int atomic_xchg(atomic_t *, int); -int __atomic_add_unless(atomic_t *, int, int); +int atomic_fetch_add_unless(atomic_t *, int, int); void atomic_set(atomic_t *, int); +#define atomic_fetch_add_unless atomic_fetch_add_unless + #define atomic_set_release(v, i) atomic_set((v), (i)) #define atomic_read(v) READ_ONCE((v)->counter) #define atomic_add(i, v) ((void)atomic_add_return( (int)(i), (v))) #define atomic_sub(i, v) ((void)atomic_add_return(-(int)(i), (v))) -#define atomic_inc(v) ((void)atomic_add_return( 1, (v))) -#define atomic_dec(v) ((void)atomic_add_return( -1, (v))) #define atomic_and(i, v) ((void)atomic_fetch_and((i), (v))) #define atomic_or(i, v) ((void)atomic_fetch_or((i), (v))) @@ -46,22 +46,4 @@ void atomic_set(atomic_t *, int); #define atomic_sub_return(i, v) (atomic_add_return(-(int)(i), (v))) #define atomic_fetch_sub(i, v) (atomic_fetch_add (-(int)(i), (v))) -#define atomic_inc_return(v) (atomic_add_return( 1, (v))) -#define atomic_dec_return(v) (atomic_add_return( -1, (v))) - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) - #endif /* !(__ARCH_SPARC_ATOMIC__) */ diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index 28db058d471b..6963482c81d8 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -50,38 +50,6 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define atomic_dec_return(v) atomic_sub_return(1, v) -#define atomic64_dec_return(v) atomic64_sub_return(1, v) - -#define atomic_inc_return(v) atomic_add_return(1, v) -#define atomic64_inc_return(v) atomic64_add_return(1, v) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) -#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) - -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) -#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0) - -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0) - -#define atomic_inc(v) atomic_add(1, v) -#define atomic64_inc(v) atomic64_add(1, v) - -#define atomic_dec(v) atomic_sub(1, v) -#define atomic64_dec(v) atomic64_sub(1, v) - -#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0) -#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0) - #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) static inline int atomic_xchg(atomic_t *v, int new) @@ -89,42 +57,11 @@ static inline int atomic_xchg(atomic_t *v, int new) return xchg(&v->counter, new); } -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) #define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) -static inline long atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); -} - -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) - long atomic64_dec_if_positive(atomic64_t *v); +#define atomic64_dec_if_positive atomic64_dec_if_positive #endif /* !(__ARCH_SPARC64_ATOMIC__) */ diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h index 9a1e9cbc7e6d..b162c23ae8c2 100644 --- a/arch/sparc/include/asm/io_64.h +++ b/arch/sparc/include/asm/io_64.h @@ -243,35 +243,42 @@ void insb(unsigned long, void *, unsigned long); void insw(unsigned long, void *, unsigned long); void insl(unsigned long, void *, unsigned long); -static inline void ioread8_rep(void __iomem *port, void *buf, unsigned long count) +static inline void readsb(void __iomem *port, void *buf, unsigned long count) { insb((unsigned long __force)port, buf, count); } -static inline void ioread16_rep(void __iomem *port, void *buf, unsigned long count) +static inline void readsw(void __iomem *port, void *buf, unsigned long count) { insw((unsigned long __force)port, buf, count); } -static inline void ioread32_rep(void __iomem *port, void *buf, unsigned long count) +static inline void readsl(void __iomem *port, void *buf, unsigned long count) { insl((unsigned long __force)port, buf, count); } -static inline void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count) +static inline void writesb(void __iomem *port, const void *buf, unsigned long count) { outsb((unsigned long __force)port, buf, count); } -static inline void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count) +static inline void writesw(void __iomem *port, const void *buf, unsigned long count) { outsw((unsigned long __force)port, buf, count); } -static inline void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count) +static inline void writesl(void __iomem *port, const void *buf, unsigned long count) { outsl((unsigned long __force)port, buf, count); } +#define ioread8_rep(p,d,l) readsb(p,d,l) +#define ioread16_rep(p,d,l) readsw(p,d,l) +#define ioread32_rep(p,d,l) readsl(p,d,l) +#define iowrite8_rep(p,d,l) writesb(p,d,l) +#define iowrite16_rep(p,d,l) writesw(p,d,l) +#define iowrite32_rep(p,d,l) writesl(p,d,l) + /* Valid I/O Space regions are anywhere, because each PCI bus supported * can live in an arbitrary area of the physical address range. */ diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h index 3704490b4488..bfcaa6326c20 100644 --- a/arch/sparc/include/asm/kprobes.h +++ b/arch/sparc/include/asm/kprobes.h @@ -44,7 +44,6 @@ struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_orig_tnpc; unsigned long kprobe_orig_tstate_pil; - struct pt_regs jprobe_saved_regs; struct prev_kprobe prev_kprobe; }; diff --git a/arch/sparc/include/asm/msi.h b/arch/sparc/include/asm/msi.h deleted file mode 100644 index 3c17c1074431..000000000000 --- a/arch/sparc/include/asm/msi.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * msi.h: Defines specific to the MBus - Sbus - Interface. - * - * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) - * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be) - */ - -#ifndef _SPARC_MSI_H -#define _SPARC_MSI_H - -/* - * Locations of MSI Registers. - */ -#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */ - -/* - * Useful bits in the MSI Registers. - */ -#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */ - - -static inline void msi_set_sync(void) -{ - __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t" - "andn %%g3, %2, %%g3\n\t" - "sta %%g3, [%0] %1\n\t" : : - "r" (MSI_MBUS_ARBEN), - "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3"); -} - -#endif /* !(_SPARC_MSI_H) */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index d58520c2e6ff..7ea35e5601b6 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -101,6 +101,9 @@ #define SO_ZEROCOPY 0x003e +#define SO_TXTIME 0x003f +#define SCM_TXTIME SO_TXTIME + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index ab4ba4347941..dfbca2470536 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -147,18 +147,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) kcb->kprobe_status = KPROBE_REENTER; prepare_singlestep(p, regs, kcb); return 1; - } else { - if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) { + } else if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) { /* The breakpoint instruction was removed by * another cpu right after we hit, no further * handling of this interrupt is appropriate */ - ret = 1; - goto no_kprobe; - } - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) - goto ss_probe; + ret = 1; } goto no_kprobe; } @@ -181,10 +175,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) set_current_kprobe(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (p->pre_handler && p->pre_handler(p, regs)) + if (p->pre_handler && p->pre_handler(p, regs)) { + reset_current_kprobe(); + preempt_enable_no_resched(); return 1; + } -ss_probe: prepare_singlestep(p, regs, kcb); kcb->kprobe_status = KPROBE_HIT_SS; return 1; @@ -441,53 +437,6 @@ out: exception_exit(prev_state); } -/* Jprobes support. */ -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs)); - - regs->tpc = (unsigned long) jp->entry; - regs->tnpc = ((unsigned long) jp->entry) + 0x4UL; - regs->tstate |= TSTATE_PIL; - - return 1; -} - -void __kprobes jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - register unsigned long orig_fp asm("g1"); - - orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP]; - __asm__ __volatile__("\n" -"1: cmp %%sp, %0\n\t" - "blu,a,pt %%xcc, 1b\n\t" - " restore\n\t" - ".globl jprobe_return_trap_instruction\n" -"jprobe_return_trap_instruction:\n\t" - "ta 0x70" - : /* no outputs */ - : "r" (orig_fp)); -} - -extern void jprobe_return_trap_instruction(void); - -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - u32 *addr = (u32 *) regs->tpc; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - if (addr == (u32 *) jprobe_return_trap_instruction) { - memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - /* The value stored in the return address register is actually 2 * instructions before where the callee will return to. * Sequences usually look something like this @@ -562,9 +511,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, regs->tpc = orig_ret_address; regs->tnpc = orig_ret_address + 4; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 2ef8cfa9677e..f0eba72aa1ad 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -814,7 +814,7 @@ static void __init get_tick_patch(void) } } -static void init_tick_ops(struct sparc64_tick_ops *ops) +static void __init init_tick_ops(struct sparc64_tick_ops *ops) { unsigned long freq, quotient, tick; diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index 465a901a0ada..281fa634bb1a 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -95,7 +95,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new) } EXPORT_SYMBOL(atomic_cmpxchg); -int __atomic_add_unless(atomic_t *v, int a, int u) +int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int ret; unsigned long flags; @@ -107,7 +107,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u) spin_unlock_irqrestore(ATOMIC_HASH(v), flags); return ret; } -EXPORT_SYMBOL(__atomic_add_unless); +EXPORT_SYMBOL(atomic_fetch_add_unless); /* Atomic operations are already serializing */ void atomic_set(atomic_t *v, int i) diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 9f75b6444bf1..b0440b0edd97 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -166,7 +166,8 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, unsigned int fixup; unsigned long g2; int from_user = !(regs->psr & PSR_PS); - int fault, code; + int code; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (text_fault) diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 63166fcf9e25..8f8a604c1300 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -278,7 +278,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned int insn = 0; - int si_code, fault_code, fault; + int si_code, fault_code; + vm_fault_t fault; unsigned long address, mm_rss; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 1d70c3f6d986..be9cb0065179 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -37,7 +37,6 @@ #include <asm/mbus.h> #include <asm/page.h> #include <asm/asi.h> -#include <asm/msi.h> #include <asm/smp.h> #include <asm/io.h> @@ -116,6 +115,25 @@ static inline void srmmu_ctxd_set(ctxd_t *ctxp, pgd_t *pgdp) set_pte((pte_t *)ctxp, pte); } +/* + * Locations of MSI Registers. + */ +#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */ + +/* + * Useful bits in the MSI Registers. + */ +#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */ + +static void msi_set_sync(void) +{ + __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t" + "andn %%g3, %2, %%g3\n\t" + "sta %%g3, [%0] %1\n\t" : : + "r" (MSI_MBUS_ARBEN), + "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3"); +} + void pmd_set(pmd_t *pmdp, pte_t *ptep) { unsigned long ptp; /* Physical address, shifted right by 4 */ diff --git a/arch/um/Kconfig.um b/arch/um/Kconfig index 20da5a8ca949..6b9938919f0b 100644 --- a/arch/um/Kconfig.um +++ b/arch/um/Kconfig @@ -1,4 +1,70 @@ # SPDX-License-Identifier: GPL-2.0 + +menu "UML-specific options" + +config UML + bool + default y + select ARCH_HAS_KCOV + select ARCH_NO_PREEMPT + select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_SECCOMP_FILTER + select HAVE_UID16 + select HAVE_FUTEX_CMPXCHG if FUTEX + select HAVE_DEBUG_KMEMLEAK + select GENERIC_IRQ_SHOW + select GENERIC_CPU_DEVICES + select GENERIC_CLOCKEVENTS + select HAVE_GCC_PLUGINS + select TTY # Needed for line.c + +config MMU + bool + default y + +config NO_IOMEM + def_bool y + +config ISA + bool + +config SBUS + bool + +config PCI + bool + +config PCMCIA + bool + +config TRACE_IRQFLAGS_SUPPORT + bool + default y + +config LOCKDEP_SUPPORT + bool + default y + +config STACKTRACE_SUPPORT + bool + default y + select STACKTRACE + +config GENERIC_CALIBRATE_DELAY + bool + default y + +config HZ + int + default 100 + +config NR_CPUS + int + range 1 1 + default 1 + +source "arch/$(HEADER_ARCH)/um/Kconfig" + config STATIC_LINK bool "Force a static link" default n @@ -10,8 +76,6 @@ config STATIC_LINK Additionally, this option enables using higher memory spaces (up to 2.75G) for UML. -source "mm/Kconfig" - config LD_SCRIPT_STATIC bool default y @@ -23,8 +87,6 @@ config LD_SCRIPT_DYN depends on !LD_SCRIPT_STATIC select MODULE_REL_CRCS if MODVERSIONS -source "fs/Kconfig.binfmt" - config HOSTFS tristate "Host filesystem" help @@ -122,3 +184,7 @@ config SECCOMP defined by each seccomp mode. If unsure, say Y. + +endmenu + +source "arch/um/drivers/Kconfig" diff --git a/arch/um/Kconfig.char b/arch/um/Kconfig.char deleted file mode 100644 index f184bde7030e..000000000000 --- a/arch/um/Kconfig.char +++ /dev/null @@ -1,124 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -menu "UML Character Devices" - -config STDERR_CONSOLE - bool "stderr console" - default y - help - console driver which dumps all printk messages to stderr. - -config SSL - bool "Virtual serial line" - help - The User-Mode Linux environment allows you to create virtual serial - lines on the UML that are usually made to show up on the host as - ttys or ptys. - - See <http://user-mode-linux.sourceforge.net/old/input.html> for more - information and command line examples of how to use this facility. - - Unless you have a specific reason for disabling this, say Y. - -config NULL_CHAN - bool "null channel support" - help - This option enables support for attaching UML consoles and serial - lines to a device similar to /dev/null. Data written to it disappears - and there is never any data to be read. - -config PORT_CHAN - bool "port channel support" - help - This option enables support for attaching UML consoles and serial - lines to host portals. They may be accessed with 'telnet <host> - <port number>'. Any number of consoles and serial lines may be - attached to a single portal, although what UML device you get when - you telnet to that portal will be unpredictable. - It is safe to say 'Y' here. - -config PTY_CHAN - bool "pty channel support" - help - This option enables support for attaching UML consoles and serial - lines to host pseudo-terminals. Access to both traditional - pseudo-terminals (/dev/pty*) and pts pseudo-terminals are controlled - with this option. The assignment of UML devices to host devices - will be announced in the kernel message log. - It is safe to say 'Y' here. - -config TTY_CHAN - bool "tty channel support" - help - This option enables support for attaching UML consoles and serial - lines to host terminals. Access to both virtual consoles - (/dev/tty*) and the slave side of pseudo-terminals (/dev/ttyp* and - /dev/pts/*) are controlled by this option. - It is safe to say 'Y' here. - -config XTERM_CHAN - bool "xterm channel support" - help - This option enables support for attaching UML consoles and serial - lines to xterms. Each UML device so assigned will be brought up in - its own xterm. - It is safe to say 'Y' here. - -config NOCONFIG_CHAN - bool - default !(XTERM_CHAN && TTY_CHAN && PTY_CHAN && PORT_CHAN && NULL_CHAN) - -config CON_ZERO_CHAN - string "Default main console channel initialization" - default "fd:0,fd:1" - help - This is the string describing the channel to which the main console - will be attached by default. This value can be overridden from the - command line. The default value is "fd:0,fd:1", which attaches the - main console to stdin and stdout. - It is safe to leave this unchanged. - -config CON_CHAN - string "Default console channel initialization" - default "xterm" - help - This is the string describing the channel to which all consoles - except the main console will be attached by default. This value can - be overridden from the command line. The default value is "xterm", - which brings them up in xterms. - It is safe to leave this unchanged, although you may wish to change - this if you expect the UML that you build to be run in environments - which don't have X or xterm available. - -config SSL_CHAN - string "Default serial line channel initialization" - default "pty" - help - This is the string describing the channel to which the serial lines - will be attached by default. This value can be overridden from the - command line. The default value is "pty", which attaches them to - traditional pseudo-terminals. - It is safe to leave this unchanged, although you may wish to change - this if you expect the UML that you build to be run in environments - which don't have a set of /dev/pty* devices. - -config UML_SOUND - tristate "Sound support" - help - This option enables UML sound support. If enabled, it will pull in - soundcore and the UML hostaudio relay, which acts as a intermediary - between the host's dsp and mixer devices and the UML sound system. - It is safe to say 'Y' here. - -config SOUND - tristate - default UML_SOUND - -config SOUND_OSS_CORE - bool - default UML_SOUND - -config HOSTAUDIO - tristate - default UML_SOUND - -endmenu diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common deleted file mode 100644 index 07f84c842cc3..000000000000 --- a/arch/um/Kconfig.common +++ /dev/null @@ -1,60 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -config UML - bool - default y - select ARCH_HAS_KCOV - select HAVE_ARCH_AUDITSYSCALL - select HAVE_ARCH_SECCOMP_FILTER - select HAVE_UID16 - select HAVE_FUTEX_CMPXCHG if FUTEX - select HAVE_DEBUG_KMEMLEAK - select GENERIC_IRQ_SHOW - select GENERIC_CPU_DEVICES - select GENERIC_CLOCKEVENTS - select HAVE_GCC_PLUGINS - select TTY # Needed for line.c - -config MMU - bool - default y - -config NO_IOMEM - def_bool y - -config ISA - bool - -config SBUS - bool - -config PCI - bool - -config PCMCIA - bool - -config TRACE_IRQFLAGS_SUPPORT - bool - default y - -config LOCKDEP_SUPPORT - bool - default y - -config STACKTRACE_SUPPORT - bool - default y - select STACKTRACE - -config GENERIC_CALIBRATE_DELAY - bool - default y - -config HZ - int - default 100 - -config NR_CPUS - int - range 1 1 - default 1 diff --git a/arch/um/Kconfig.debug b/arch/um/Kconfig.debug index 967d3109689f..2014597605ea 100644 --- a/arch/um/Kconfig.debug +++ b/arch/um/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config GPROF bool "Enable gprof support" @@ -37,5 +34,3 @@ config EARLY_PRINTK This is useful for kernel debugging when your machine crashes very early before the console code is initialized. - -endmenu diff --git a/arch/um/Kconfig.rest b/arch/um/Kconfig.rest deleted file mode 100644 index 08327b9c0cbe..000000000000 --- a/arch/um/Kconfig.rest +++ /dev/null @@ -1,22 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - -source "arch/um/Kconfig.char" - -source "drivers/Kconfig" - -source "net/Kconfig" - -source "arch/um/Kconfig.net" - -source "fs/Kconfig" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - -source "arch/um/Kconfig.debug" diff --git a/arch/um/Makefile b/arch/um/Makefile index e54dda8a0363..44ddc3e8fa66 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -113,17 +113,8 @@ define archhelp echo ' find in the kernel root.' endef -KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig - archheaders: - $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \ - kbuild-file=$(HOST_DIR)/include/asm/Kbuild \ - obj=$(HOST_DIR)/include/generated/asm - $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \ - kbuild-file=$(HOST_DIR)/include/uapi/asm/Kbuild \ - obj=$(HOST_DIR)/include/generated/uapi/asm - $(Q)$(MAKE) KBUILD_SRC= ARCH=$(HEADER_ARCH) archheaders - + $(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) asm-generic archheaders archprepare: include/generated/user_constants.h @@ -169,11 +160,11 @@ define filechk_gen-asm-offsets echo " *"; \ echo " */"; \ echo ""; \ - sed -ne "/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"; \ + sed -ne "/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}" < $<; \ echo ""; ) endef include/generated/user_constants.h: $(HOST_DIR)/um/user-offsets.s $(call filechk,gen-asm-offsets) -export SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS DEV_NULL_PATH +export HEADER_ARCH SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS DEV_NULL_PATH diff --git a/arch/um/Kconfig.net b/arch/um/drivers/Kconfig index c390f3deb0dc..2b1aaf7755aa 100644 --- a/arch/um/Kconfig.net +++ b/arch/um/drivers/Kconfig @@ -1,5 +1,129 @@ # SPDX-License-Identifier: GPL-2.0 +menu "UML Character Devices" + +config STDERR_CONSOLE + bool "stderr console" + default y + help + console driver which dumps all printk messages to stderr. + +config SSL + bool "Virtual serial line" + help + The User-Mode Linux environment allows you to create virtual serial + lines on the UML that are usually made to show up on the host as + ttys or ptys. + + See <http://user-mode-linux.sourceforge.net/old/input.html> for more + information and command line examples of how to use this facility. + + Unless you have a specific reason for disabling this, say Y. + +config NULL_CHAN + bool "null channel support" + help + This option enables support for attaching UML consoles and serial + lines to a device similar to /dev/null. Data written to it disappears + and there is never any data to be read. + +config PORT_CHAN + bool "port channel support" + help + This option enables support for attaching UML consoles and serial + lines to host portals. They may be accessed with 'telnet <host> + <port number>'. Any number of consoles and serial lines may be + attached to a single portal, although what UML device you get when + you telnet to that portal will be unpredictable. + It is safe to say 'Y' here. + +config PTY_CHAN + bool "pty channel support" + help + This option enables support for attaching UML consoles and serial + lines to host pseudo-terminals. Access to both traditional + pseudo-terminals (/dev/pty*) and pts pseudo-terminals are controlled + with this option. The assignment of UML devices to host devices + will be announced in the kernel message log. + It is safe to say 'Y' here. + +config TTY_CHAN + bool "tty channel support" + help + This option enables support for attaching UML consoles and serial + lines to host terminals. Access to both virtual consoles + (/dev/tty*) and the slave side of pseudo-terminals (/dev/ttyp* and + /dev/pts/*) are controlled by this option. + It is safe to say 'Y' here. + +config XTERM_CHAN + bool "xterm channel support" + help + This option enables support for attaching UML consoles and serial + lines to xterms. Each UML device so assigned will be brought up in + its own xterm. + It is safe to say 'Y' here. + +config NOCONFIG_CHAN + bool + default !(XTERM_CHAN && TTY_CHAN && PTY_CHAN && PORT_CHAN && NULL_CHAN) + +config CON_ZERO_CHAN + string "Default main console channel initialization" + default "fd:0,fd:1" + help + This is the string describing the channel to which the main console + will be attached by default. This value can be overridden from the + command line. The default value is "fd:0,fd:1", which attaches the + main console to stdin and stdout. + It is safe to leave this unchanged. + +config CON_CHAN + string "Default console channel initialization" + default "xterm" + help + This is the string describing the channel to which all consoles + except the main console will be attached by default. This value can + be overridden from the command line. The default value is "xterm", + which brings them up in xterms. + It is safe to leave this unchanged, although you may wish to change + this if you expect the UML that you build to be run in environments + which don't have X or xterm available. + +config SSL_CHAN + string "Default serial line channel initialization" + default "pty" + help + This is the string describing the channel to which the serial lines + will be attached by default. This value can be overridden from the + command line. The default value is "pty", which attaches them to + traditional pseudo-terminals. + It is safe to leave this unchanged, although you may wish to change + this if you expect the UML that you build to be run in environments + which don't have a set of /dev/pty* devices. + +config UML_SOUND + tristate "Sound support" + help + This option enables UML sound support. If enabled, it will pull in + soundcore and the UML hostaudio relay, which acts as a intermediary + between the host's dsp and mixer devices and the UML sound system. + It is safe to say 'Y' here. + +config SOUND + tristate + default UML_SOUND + +config SOUND_OSS_CORE + bool + default UML_SOUND + +config HOSTAUDIO + tristate + default UML_SOUND + +endmenu + menu "UML Network Devices" depends on NET @@ -211,4 +335,3 @@ config UML_NET_SLIRP Startup example: "eth0=slirp,FE:FD:01:02:03:04,/usr/local/bin/slirp" endmenu - diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index 16b3cebddafb..693319839f69 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -25,10 +25,10 @@ LDFLAGS_vde.o := -r $(shell $(CC) $(CFLAGS) -print-file-name=libvdeplug.a) targets := pcap_kern.o pcap_user.o vde_kern.o vde_user.o $(obj)/pcap.o: $(obj)/pcap_kern.o $(obj)/pcap_user.o - $(LD) -r -dp -o $@ $^ $(LDFLAGS) $(LDFLAGS_pcap.o) + $(LD) -r -dp -o $@ $^ $(ld_flags) $(obj)/vde.o: $(obj)/vde_kern.o $(obj)/vde_user.o - $(LD) -r -dp -o $@ $^ $(LDFLAGS) $(LDFLAGS_vde.o) + $(LD) -r -dp -o $@ $^ $(ld_flags) #XXX: The call below does not work because the flags are added before the # object name, so nothing from the library gets linked. diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index ec9a42c14c56..cced82946042 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -72,7 +72,7 @@ good_area: } do { - int fault; + vm_fault_t fault; fault = handle_mm_fault(vma, address, flags); diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 03f991e44288..60eae744d8fd 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -63,10 +63,6 @@ config ARCH_MAY_HAVE_PC_FDC config ZONE_DMA def_bool y -source "init/Kconfig" - -source "kernel/Kconfig.freezer" - menu "System Type" config MMU @@ -139,12 +135,8 @@ endmenu menu "Kernel Features" -source "kernel/Kconfig.preempt" - source "kernel/Kconfig.hz" -source "mm/Kconfig" - config LEDS def_bool y depends on GPIOLIB @@ -181,12 +173,6 @@ config CMDLINE_FORCE endmenu -menu "Userspace binary formats" - -source "fs/Kconfig.binfmt" - -endmenu - menu "Power management options" source "kernel/power/Kconfig" @@ -201,8 +187,6 @@ config ARCH_HIBERNATION_POSSIBLE endmenu -source "net/Kconfig" - if ARCH_PUV3 config PUV3_GPIO @@ -236,15 +220,3 @@ endmenu endif endif - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "arch/unicore32/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" diff --git a/arch/unicore32/Kconfig.debug b/arch/unicore32/Kconfig.debug index de8dae3abc0a..ca0ff97657ef 100644 --- a/arch/unicore32/Kconfig.debug +++ b/arch/unicore32/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config EARLY_PRINTK def_bool DEBUG_OCD @@ -30,5 +27,3 @@ config DEBUG_OCD help Say Y here if you want the debug print routines to direct their output to the UniCore On-Chip-Debugger channel using CP #1. - -endmenu diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c index 381473412937..8f12a5b50a42 100644 --- a/arch/unicore32/mm/fault.c +++ b/arch/unicore32/mm/fault.c @@ -168,11 +168,11 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) return vma->vm_flags & mask ? false : true; } -static int __do_pf(struct mm_struct *mm, unsigned long addr, unsigned int fsr, - unsigned int flags, struct task_struct *tsk) +static vm_fault_t __do_pf(struct mm_struct *mm, unsigned long addr, + unsigned int fsr, unsigned int flags, struct task_struct *tsk) { struct vm_area_struct *vma; - int fault; + vm_fault_t fault; vma = find_vma(mm, addr); fault = VM_FAULT_BADMAP; @@ -209,7 +209,8 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { struct task_struct *tsk; struct mm_struct *mm; - int fault, sig, code; + int sig, code; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; tsk = current; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 887d3a7bb646..b0312f8947ce 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -75,6 +75,7 @@ config X86 select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO + select ARCH_SUPPORTS_ACPI select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_USE_BUILTIN_BSWAP @@ -180,13 +181,14 @@ config X86 select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR select HAVE_STACK_VALIDATION if X86_64 select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER + select HOTPLUG_SMT if SMP select IRQ_FORCED_THREADING select NEED_SG_DMA_LENGTH select PCI_LOCKLESS_CONFIG @@ -345,8 +347,6 @@ config PGTABLE_LEVELS default 3 if X86_PAE default 2 -source "init/Kconfig" - config CC_HAS_SANE_STACKPROTECTOR bool default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC)) if 64BIT @@ -355,8 +355,6 @@ config CC_HAS_SANE_STACKPROTECTOR We have to make sure stack protector is unconditionally disabled if the compiler produces broken code. -source "kernel/Kconfig.freezer" - menu "Processor type and features" config ZONE_DMA @@ -1043,8 +1041,6 @@ config SCHED_MC_PRIO If unsure say Y here. -source "kernel/Kconfig.preempt" - config UP_LATE_INIT def_bool y depends on !SMP && X86_LOCAL_APIC @@ -1638,8 +1634,6 @@ config ILLEGAL_POINTER_VALUE default 0 if X86_32 default 0xdead000000000000 if X86_64 -source "mm/Kconfig" - config X86_PMEM_LEGACY_DEVICE bool @@ -2865,9 +2859,7 @@ config X86_SYSFB endmenu -menu "Executable file formats / Emulations" - -source "fs/Kconfig.binfmt" +menu "Binary Emulations" config IA32_EMULATION bool "IA32 Emulation" @@ -2937,20 +2929,6 @@ config X86_DMA_REMAP config HAVE_GENERIC_GUP def_bool y -source "net/Kconfig" - -source "drivers/Kconfig" - source "drivers/firmware/Kconfig" -source "fs/Kconfig" - -source "arch/x86/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - source "arch/x86/kvm/Kconfig" - -source "lib/Kconfig" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c6dd1d980081..7d68f0c7cfb1 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -1,11 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" config TRACE_IRQFLAGS_SUPPORT def_bool y -source "lib/Kconfig.debug" - config EARLY_PRINTK_USB bool @@ -410,5 +407,3 @@ endchoice config FRAME_POINTER depends on !UNWINDER_ORC && !UNWINDER_GUESS bool - -endmenu diff --git a/arch/x86/Makefile b/arch/x86/Makefile index a08e82856563..7e3c07d6ad42 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -80,11 +80,6 @@ ifeq ($(CONFIG_X86_32),y) # alignment instructions. KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4)) - # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use - # a lot more stack due to the lack of sharing of stacklots: - KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \ - $(call cc-option,-fno-unit-at-a-time)) - # CPU-specific tuning. Anything which can be shared with UML should go here. include arch/x86/Makefile_32.cpu KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 45af19921ebd..5296f8c9e7f0 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -13,8 +13,6 @@ KBUILD_CFLAGS += $(call cc-option,-m32) KBUILD_AFLAGS += $(call cc-option,-m32) LINK-y += $(call cc-option,-m32) -export LDFLAGS - LDS_EXTRA := -Ui386 export LDS_EXTRA diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h index 0d41d68131cc..2e1382486e91 100644 --- a/arch/x86/boot/bitops.h +++ b/arch/x86/boot/bitops.h @@ -17,6 +17,7 @@ #define _LINUX_BITOPS_H /* Inhibit inclusion of <linux/bitops.h> */ #include <linux/types.h> +#include <asm/asm.h> static inline bool constant_test_bit(int nr, const void *addr) { @@ -28,7 +29,7 @@ static inline bool variable_test_bit(int nr, const void *addr) bool v; const u32 *p = (const u32 *)addr; - asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr)); + asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr)); return v; } diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fa42f895fdde..169c2feda14a 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -106,9 +106,13 @@ define cmd_check_data_rel done endef +# We need to run two commands under "if_changed", so merge them into a +# single invocation. +quiet_cmd_check-and-link-vmlinux = LD $@ + cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld) + $(obj)/vmlinux: $(vmlinux-objs-y) FORCE - $(call if_changed,check_data_rel) - $(call if_changed,ld) + $(call if_changed,check-and-link-vmlinux) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index e98522ea6f09..1458b1700fc7 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -34,74 +34,13 @@ static void setup_boot_services##bits(struct efi_config *c) \ \ table = (typeof(table))sys_table; \ \ - c->runtime_services = table->runtime; \ - c->boot_services = table->boottime; \ - c->text_output = table->con_out; \ + c->runtime_services = table->runtime; \ + c->boot_services = table->boottime; \ + c->text_output = table->con_out; \ } BOOT_SERVICES(32); BOOT_SERVICES(64); -static inline efi_status_t __open_volume32(void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_32_t *image = __image; - efi_file_handle_32_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - unsigned long func; - - status = efi_call_early(handle_protocol, handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to handle fs_proto\n"); - return status; - } - - func = (unsigned long)io->open_volume; - status = efi_early->call(func, io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - -static inline efi_status_t __open_volume64(void *__image, void **__fh) -{ - efi_file_io_interface_t *io; - efi_loaded_image_64_t *image = __image; - efi_file_handle_64_t *fh; - efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; - efi_status_t status; - void *handle = (void *)(unsigned long)image->device_handle; - unsigned long func; - - status = efi_call_early(handle_protocol, handle, - &fs_proto, (void **)&io); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to handle fs_proto\n"); - return status; - } - - func = (unsigned long)io->open_volume; - status = efi_early->call(func, io, &fh); - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to open volume\n"); - - *__fh = fh; - return status; -} - -efi_status_t -efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) -{ - if (efi_early->is64) - return __open_volume64(__image, __fh); - - return __open_volume32(__image, __fh); -} - void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) { efi_call_proto(efi_simple_text_output_protocol, output_string, @@ -109,7 +48,7 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) } static efi_status_t -__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) +preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) { struct pci_setup_rom *rom = NULL; efi_status_t status; @@ -134,16 +73,16 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for rom\n"); + efi_printk(sys_table, "Failed to allocate memory for 'rom'\n"); return status; } memset(rom, 0, sizeof(*rom)); - rom->data.type = SETUP_PCI; - rom->data.len = size - sizeof(struct setup_data); - rom->data.next = 0; - rom->pcilen = pci->romsize; + rom->data.type = SETUP_PCI; + rom->data.len = size - sizeof(struct setup_data); + rom->data.next = 0; + rom->pcilen = pci->romsize; *__rom = rom; status = efi_call_proto(efi_pci_io_protocol, pci.read, pci, @@ -179,96 +118,6 @@ free_struct: return status; } -static void -setup_efi_pci32(struct boot_params *params, void **pci_handle, - unsigned long size) -{ - efi_pci_io_protocol_t *pci = NULL; - efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - u32 *handles = (u32 *)(unsigned long)pci_handle; - efi_status_t status; - unsigned long nr_pci; - struct setup_data *data; - int i; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - nr_pci = size / sizeof(u32); - for (i = 0; i < nr_pci; i++) { - struct pci_setup_rom *rom = NULL; - u32 h = handles[i]; - - status = efi_call_early(handle_protocol, h, - &pci_proto, (void **)&pci); - - if (status != EFI_SUCCESS) - continue; - - if (!pci) - continue; - - status = __setup_efi_pci(pci, &rom); - if (status != EFI_SUCCESS) - continue; - - if (data) - data->next = (unsigned long)rom; - else - params->hdr.setup_data = (unsigned long)rom; - - data = (struct setup_data *)rom; - - } -} - -static void -setup_efi_pci64(struct boot_params *params, void **pci_handle, - unsigned long size) -{ - efi_pci_io_protocol_t *pci = NULL; - efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; - u64 *handles = (u64 *)(unsigned long)pci_handle; - efi_status_t status; - unsigned long nr_pci; - struct setup_data *data; - int i; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - nr_pci = size / sizeof(u64); - for (i = 0; i < nr_pci; i++) { - struct pci_setup_rom *rom = NULL; - u64 h = handles[i]; - - status = efi_call_early(handle_protocol, h, - &pci_proto, (void **)&pci); - - if (status != EFI_SUCCESS) - continue; - - if (!pci) - continue; - - status = __setup_efi_pci(pci, &rom); - if (status != EFI_SUCCESS) - continue; - - if (data) - data->next = (unsigned long)rom; - else - params->hdr.setup_data = (unsigned long)rom; - - data = (struct setup_data *)rom; - - } -} - /* * There's no way to return an informative status from this function, * because any analysis (and printing of error messages) needs to be @@ -284,6 +133,9 @@ static void setup_efi_pci(struct boot_params *params) void **pci_handle = NULL; efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; unsigned long size = 0; + unsigned long nr_pci; + struct setup_data *data; + int i; status = efi_call_early(locate_handle, EFI_LOCATE_BY_PROTOCOL, @@ -295,7 +147,7 @@ static void setup_efi_pci(struct boot_params *params) size, (void **)&pci_handle); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for pci_handle\n"); + efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n"); return; } @@ -307,10 +159,34 @@ static void setup_efi_pci(struct boot_params *params) if (status != EFI_SUCCESS) goto free_handle; - if (efi_early->is64) - setup_efi_pci64(params, pci_handle, size); - else - setup_efi_pci32(params, pci_handle, size); + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); + for (i = 0; i < nr_pci; i++) { + efi_pci_io_protocol_t *pci = NULL; + struct pci_setup_rom *rom; + + status = efi_call_early(handle_protocol, + efi_is_64bit() ? ((u64 *)pci_handle)[i] + : ((u32 *)pci_handle)[i], + &pci_proto, (void **)&pci); + if (status != EFI_SUCCESS || !pci) + continue; + + status = preserve_pci_rom_image(pci, &rom); + if (status != EFI_SUCCESS) + continue; + + if (data) + data->next = (unsigned long)rom; + else + params->hdr.setup_data = (unsigned long)rom; + + data = (struct setup_data *)rom; + } free_handle: efi_call_early(free_pool, pci_handle); @@ -341,8 +217,7 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size + sizeof(struct setup_data), &new); if (status != EFI_SUCCESS) { - efi_printk(sys_table, - "Failed to alloc mem for properties\n"); + efi_printk(sys_table, "Failed to allocate memory for 'properties'\n"); return; } @@ -358,9 +233,9 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) new->next = 0; data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; - if (!data) + if (!data) { boot_params->hdr.setup_data = (unsigned long)new; - else { + } else { while (data->next) data = (struct setup_data *)(unsigned long)data->next; data->next = (unsigned long)new; @@ -380,81 +255,55 @@ static void setup_quirks(struct boot_params *boot_params) } } +/* + * See if we have Universal Graphics Adapter (UGA) protocol + */ static efi_status_t -setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) +setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) { - struct efi_uga_draw_protocol *uga = NULL, *first_uga; - efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; + efi_status_t status; + u32 width, height; + void **uga_handle = NULL; + efi_uga_draw_protocol_t *uga = NULL, *first_uga; unsigned long nr_ugas; - u32 *handles = (u32 *)uga_handle; - efi_status_t status = EFI_INVALID_PARAMETER; int i; - first_uga = NULL; - nr_ugas = size / sizeof(u32); - for (i = 0; i < nr_ugas; i++) { - efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; - u32 w, h, depth, refresh; - void *pciio; - u32 handle = handles[i]; - - status = efi_call_early(handle_protocol, handle, - &uga_proto, (void **)&uga); - if (status != EFI_SUCCESS) - continue; - - efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); - - status = efi_early->call((unsigned long)uga->get_mode, uga, - &w, &h, &depth, &refresh); - if (status == EFI_SUCCESS && (!first_uga || pciio)) { - *width = w; - *height = h; - - /* - * Once we've found a UGA supporting PCIIO, - * don't bother looking any further. - */ - if (pciio) - break; - - first_uga = uga; - } - } + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)&uga_handle); + if (status != EFI_SUCCESS) + return status; - return status; -} + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + uga_proto, NULL, &size, uga_handle); + if (status != EFI_SUCCESS) + goto free_handle; -static efi_status_t -setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) -{ - struct efi_uga_draw_protocol *uga = NULL, *first_uga; - efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; - unsigned long nr_ugas; - u64 *handles = (u64 *)uga_handle; - efi_status_t status = EFI_INVALID_PARAMETER; - int i; + height = 0; + width = 0; first_uga = NULL; - nr_ugas = size / sizeof(u64); + nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); for (i = 0; i < nr_ugas; i++) { efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; u32 w, h, depth, refresh; void *pciio; - u64 handle = handles[i]; + unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i] + : ((u32 *)uga_handle)[i]; status = efi_call_early(handle_protocol, handle, - &uga_proto, (void **)&uga); + uga_proto, (void **)&uga); if (status != EFI_SUCCESS) continue; + pciio = NULL; efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); - status = efi_early->call((unsigned long)uga->get_mode, uga, - &w, &h, &depth, &refresh); + status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga, + &w, &h, &depth, &refresh); if (status == EFI_SUCCESS && (!first_uga || pciio)) { - *width = w; - *height = h; + width = w; + height = h; /* * Once we've found a UGA supporting PCIIO, @@ -467,59 +316,28 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) } } - return status; -} - -/* - * See if we have Universal Graphics Adapter (UGA) protocol - */ -static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto, - unsigned long size) -{ - efi_status_t status; - u32 width, height; - void **uga_handle = NULL; - - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)&uga_handle); - if (status != EFI_SUCCESS) - return status; - - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - uga_proto, NULL, &size, uga_handle); - if (status != EFI_SUCCESS) - goto free_handle; - - height = 0; - width = 0; - - if (efi_early->is64) - status = setup_uga64(uga_handle, size, &width, &height); - else - status = setup_uga32(uga_handle, size, &width, &height); - if (!width && !height) goto free_handle; /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; + si->orig_video_isVGA = VIDEO_TYPE_EFI; - si->lfb_depth = 32; - si->lfb_width = width; - si->lfb_height = height; + si->lfb_depth = 32; + si->lfb_width = width; + si->lfb_height = height; - si->red_size = 8; - si->red_pos = 16; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 0; - si->rsvd_size = 8; - si->rsvd_pos = 24; + si->red_size = 8; + si->red_pos = 16; + si->green_size = 8; + si->green_pos = 8; + si->blue_size = 8; + si->blue_pos = 0; + si->rsvd_size = 8; + si->rsvd_pos = 24; free_handle: efi_call_early(free_pool, uga_handle); + return status; } @@ -586,7 +404,7 @@ struct boot_params *make_boot_params(struct efi_config *c) if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) return NULL; - if (efi_early->is64) + if (efi_is_64bit()) setup_boot_services64(efi_early); else setup_boot_services32(efi_early); @@ -601,7 +419,7 @@ struct boot_params *make_boot_params(struct efi_config *c) status = efi_low_alloc(sys_table, 0x4000, 1, (unsigned long *)&boot_params); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc lowmem for boot params\n"); + efi_printk(sys_table, "Failed to allocate lowmem for boot params\n"); return NULL; } @@ -617,9 +435,9 @@ struct boot_params *make_boot_params(struct efi_config *c) * Fill out some of the header fields ourselves because the * EFI firmware loader doesn't load the first sector. */ - hdr->root_flags = 1; - hdr->vid_mode = 0xffff; - hdr->boot_flag = 0xAA55; + hdr->root_flags = 1; + hdr->vid_mode = 0xffff; + hdr->boot_flag = 0xAA55; hdr->type_of_loader = 0x21; @@ -627,6 +445,7 @@ struct boot_params *make_boot_params(struct efi_config *c) cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); if (!cmdline_ptr) goto fail; + hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; /* Fill in upper bits of command line address, NOP on 32 bit */ boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32; @@ -663,10 +482,12 @@ struct boot_params *make_boot_params(struct efi_config *c) boot_params->ext_ramdisk_size = (u64)ramdisk_size >> 32; return boot_params; + fail2: efi_free(sys_table, options_size, hdr->cmd_line_ptr); fail: efi_free(sys_table, 0x4000, (unsigned long)boot_params); + return NULL; } @@ -678,7 +499,7 @@ static void add_e820ext(struct boot_params *params, unsigned long size; e820ext->type = SETUP_E820_EXT; - e820ext->len = nr_entries * sizeof(struct boot_e820_entry); + e820ext->len = nr_entries * sizeof(struct boot_e820_entry); e820ext->next = 0; data = (struct setup_data *)(unsigned long)params->hdr.setup_data; @@ -692,8 +513,8 @@ static void add_e820ext(struct boot_params *params, params->hdr.setup_data = (unsigned long)e820ext; } -static efi_status_t setup_e820(struct boot_params *params, - struct setup_data *e820ext, u32 e820ext_size) +static efi_status_t +setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size) { struct boot_e820_entry *entry = params->e820_table; struct efi_info *efi = ¶ms->efi_info; @@ -814,11 +635,10 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, } struct exit_boot_struct { - struct boot_params *boot_params; - struct efi_info *efi; - struct setup_data *e820ext; - __u32 e820ext_size; - bool is64; + struct boot_params *boot_params; + struct efi_info *efi; + struct setup_data *e820ext; + __u32 e820ext_size; }; static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, @@ -845,25 +665,25 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, first = false; } - signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE; + signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE + : EFI32_LOADER_SIGNATURE; memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32)); - p->efi->efi_systab = (unsigned long)sys_table_arg; - p->efi->efi_memdesc_size = *map->desc_size; - p->efi->efi_memdesc_version = *map->desc_ver; - p->efi->efi_memmap = (unsigned long)*map->map; - p->efi->efi_memmap_size = *map->map_size; + p->efi->efi_systab = (unsigned long)sys_table_arg; + p->efi->efi_memdesc_size = *map->desc_size; + p->efi->efi_memdesc_version = *map->desc_ver; + p->efi->efi_memmap = (unsigned long)*map->map; + p->efi->efi_memmap_size = *map->map_size; #ifdef CONFIG_X86_64 - p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; - p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; + p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; + p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; #endif return EFI_SUCCESS; } -static efi_status_t exit_boot(struct boot_params *boot_params, - void *handle, bool is64) +static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) { unsigned long map_sz, key, desc_size, buff_size; efi_memory_desc_t *mem_map; @@ -874,17 +694,16 @@ static efi_status_t exit_boot(struct boot_params *boot_params, struct efi_boot_memmap map; struct exit_boot_struct priv; - map.map = &mem_map; - map.map_size = &map_sz; - map.desc_size = &desc_size; - map.desc_ver = &desc_version; - map.key_ptr = &key; - map.buff_size = &buff_size; - priv.boot_params = boot_params; - priv.efi = &boot_params->efi_info; - priv.e820ext = NULL; - priv.e820ext_size = 0; - priv.is64 = is64; + map.map = &mem_map; + map.map_size = &map_sz; + map.desc_size = &desc_size; + map.desc_ver = &desc_version; + map.key_ptr = &key; + map.buff_size = &buff_size; + priv.boot_params = boot_params; + priv.efi = &boot_params->efi_info; + priv.e820ext = NULL; + priv.e820ext_size = 0; /* Might as well exit boot services now */ status = efi_exit_boot_services(sys_table, handle, &map, &priv, @@ -892,10 +711,11 @@ static efi_status_t exit_boot(struct boot_params *boot_params, if (status != EFI_SUCCESS) return status; - e820ext = priv.e820ext; - e820ext_size = priv.e820ext_size; + e820ext = priv.e820ext; + e820ext_size = priv.e820ext_size; + /* Historic? */ - boot_params->alt_mem_k = 32 * 1024; + boot_params->alt_mem_k = 32 * 1024; status = setup_e820(boot_params, e820ext, e820ext_size); if (status != EFI_SUCCESS) @@ -908,8 +728,8 @@ static efi_status_t exit_boot(struct boot_params *boot_params, * On success we return a pointer to a boot_params structure, and NULL * on failure. */ -struct boot_params *efi_main(struct efi_config *c, - struct boot_params *boot_params) +struct boot_params * +efi_main(struct efi_config *c, struct boot_params *boot_params) { struct desc_ptr *gdt = NULL; efi_loaded_image_t *image; @@ -918,13 +738,11 @@ struct boot_params *efi_main(struct efi_config *c, struct desc_struct *desc; void *handle; efi_system_table_t *_table; - bool is64; efi_early = c; _table = (efi_system_table_t *)(unsigned long)efi_early->table; handle = (void *)(unsigned long)efi_early->image_handle; - is64 = efi_early->is64; sys_table = _table; @@ -932,7 +750,7 @@ struct boot_params *efi_main(struct efi_config *c, if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) goto fail; - if (is64) + if (efi_is_64bit()) setup_boot_services64(efi_early); else setup_boot_services32(efi_early); @@ -957,7 +775,7 @@ struct boot_params *efi_main(struct efi_config *c, status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*gdt), (void **)&gdt); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for gdt structure\n"); + efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n"); goto fail; } @@ -965,7 +783,7 @@ struct boot_params *efi_main(struct efi_config *c, status = efi_low_alloc(sys_table, gdt->size, 8, (unsigned long *)&gdt->address); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for gdt\n"); + efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n"); goto fail; } @@ -988,7 +806,7 @@ struct boot_params *efi_main(struct efi_config *c, hdr->code32_start = bzimage_addr; } - status = exit_boot(boot_params, handle, is64); + status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { efi_printk(sys_table, "exit_boot() failed!\n"); goto fail; @@ -1002,19 +820,20 @@ struct boot_params *efi_main(struct efi_config *c, if (IS_ENABLED(CONFIG_X86_64)) { /* __KERNEL32_CS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; } else { /* Second entry is unused on 32-bit */ @@ -1022,15 +841,16 @@ struct boot_params *efi_main(struct efi_config *c, } /* __KERNEL_CS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + if (IS_ENABLED(CONFIG_X86_64)) { desc->l = 1; desc->d = 0; @@ -1038,41 +858,41 @@ struct boot_params *efi_main(struct efi_config *c, desc->l = 0; desc->d = SEG_OP_SIZE_32BIT; } - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; /* __KERNEL_DS */ - desc->limit0 = 0xffff; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE; - desc->s = DESC_TYPE_CODE_DATA; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0xf; - desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; if (IS_ENABLED(CONFIG_X86_64)) { /* Task segment value */ - desc->limit0 = 0x0000; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_TSS; - desc->s = 0; - desc->dpl = 0; - desc->p = 1; - desc->limit1 = 0x0; - desc->avl = 0; - desc->l = 0; - desc->d = 0; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; + desc->limit0 = 0x0000; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_TSS; + desc->s = 0; + desc->dpl = 0; + desc->p = 1; + desc->limit1 = 0x0; + desc->avl = 0; + desc->l = 0; + desc->d = 0; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; desc++; } @@ -1082,5 +902,6 @@ struct boot_params *efi_main(struct efi_config *c, return boot_params; fail: efi_printk(sys_table, "efi_main() failed!\n"); + return NULL; } diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index e799dc5c6448..8297387c4676 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -12,22 +12,22 @@ #define DESC_TYPE_CODE_DATA (1 << 0) -struct efi_uga_draw_protocol_32 { +typedef struct { u32 get_mode; u32 set_mode; u32 blt; -}; +} efi_uga_draw_protocol_32_t; -struct efi_uga_draw_protocol_64 { +typedef struct { u64 get_mode; u64 set_mode; u64 blt; -}; +} efi_uga_draw_protocol_64_t; -struct efi_uga_draw_protocol { +typedef struct { void *get_mode; void *set_mode; void *blt; -}; +} efi_uga_draw_protocol_t; #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index b87a7582853d..302517929932 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -102,7 +102,7 @@ static bool memmap_too_large; /* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ -unsigned long long mem_limit = ULLONG_MAX; +static unsigned long long mem_limit = ULLONG_MAX; enum mem_avoid_index { @@ -215,7 +215,36 @@ static void mem_avoid_memmap(char *str) memmap_too_large = true; } -static int handle_mem_memmap(void) +/* Store the number of 1GB huge pages which users specified: */ +static unsigned long max_gb_huge_pages; + +static void parse_gb_huge_pages(char *param, char *val) +{ + static bool gbpage_sz; + char *p; + + if (!strcmp(param, "hugepagesz")) { + p = val; + if (memparse(p, &p) != PUD_SIZE) { + gbpage_sz = false; + return; + } + + if (gbpage_sz) + warn("Repeatedly set hugeTLB page size of 1G!\n"); + gbpage_sz = true; + return; + } + + if (!strcmp(param, "hugepages") && gbpage_sz) { + p = val; + max_gb_huge_pages = simple_strtoull(p, &p, 0); + return; + } +} + + +static int handle_mem_options(void) { char *args = (char *)get_cmd_line_ptr(); size_t len = strlen((char *)args); @@ -223,7 +252,8 @@ static int handle_mem_memmap(void) char *param, *val; u64 mem_size; - if (!strstr(args, "memmap=") && !strstr(args, "mem=")) + if (!strstr(args, "memmap=") && !strstr(args, "mem=") && + !strstr(args, "hugepages")) return 0; tmp_cmdline = malloc(len + 1); @@ -248,6 +278,8 @@ static int handle_mem_memmap(void) if (!strcmp(param, "memmap")) { mem_avoid_memmap(val); + } else if (strstr(param, "hugepages")) { + parse_gb_huge_pages(param, val); } else if (!strcmp(param, "mem")) { char *p = val; @@ -387,7 +419,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* We don't need to set a mapping for setup_data. */ /* Mark the memmap regions we need to avoid */ - handle_mem_memmap(); + handle_mem_options(); #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ @@ -466,6 +498,60 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size) } } +/* + * Skip as many 1GB huge pages as possible in the passed region + * according to the number which users specified: + */ +static void +process_gb_huge_pages(struct mem_vector *region, unsigned long image_size) +{ + unsigned long addr, size = 0; + struct mem_vector tmp; + int i = 0; + + if (!max_gb_huge_pages) { + store_slot_info(region, image_size); + return; + } + + addr = ALIGN(region->start, PUD_SIZE); + /* Did we raise the address above the passed in memory entry? */ + if (addr < region->start + region->size) + size = region->size - (addr - region->start); + + /* Check how many 1GB huge pages can be filtered out: */ + while (size > PUD_SIZE && max_gb_huge_pages) { + size -= PUD_SIZE; + max_gb_huge_pages--; + i++; + } + + /* No good 1GB huge pages found: */ + if (!i) { + store_slot_info(region, image_size); + return; + } + + /* + * Skip those 'i'*1GB good huge pages, and continue checking and + * processing the remaining head or tail part of the passed region + * if available. + */ + + if (addr >= region->start + image_size) { + tmp.start = region->start; + tmp.size = addr - region->start; + store_slot_info(&tmp, image_size); + } + + size = region->size - (addr - region->start) - i * PUD_SIZE; + if (size >= image_size) { + tmp.start = addr + i * PUD_SIZE; + tmp.size = size; + store_slot_info(&tmp, image_size); + } +} + static unsigned long slots_fetch_random(void) { unsigned long slot; @@ -546,7 +632,7 @@ static void process_mem_region(struct mem_vector *entry, /* If nothing overlaps, store the region and return. */ if (!mem_avoid_overlap(®ion, &overlap)) { - store_slot_info(®ion, image_size); + process_gb_huge_pages(®ion, image_size); return; } @@ -556,7 +642,7 @@ static void process_mem_region(struct mem_vector *entry, beginning.start = region.start; beginning.size = overlap.start - region.start; - store_slot_info(&beginning, image_size); + process_gb_huge_pages(&beginning, image_size); } /* Return if overlap extends to or past end of region. */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 8c5107545251..9e2157371491 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,3 +1,4 @@ +#include <asm/e820/types.h> #include <asm/processor.h> #include "pgtable.h" #include "../string.h" @@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data); extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); +static unsigned long find_trampoline_placement(void) +{ + unsigned long bios_start, ebda_start; + unsigned long trampoline_start; + struct boot_e820_entry *entry; + int i; + + /* + * Find a suitable spot for the trampoline. + * This code is based on reserve_bios_regions(). + */ + + ebda_start = *(unsigned short *)0x40e << 4; + bios_start = *(unsigned short *)0x413 << 10; + + if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) + bios_start = BIOS_START_MAX; + + if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) + bios_start = ebda_start; + + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Find the first usable memory region under bios_start. */ + for (i = boot_params->e820_entries - 1; i >= 0; i--) { + entry = &boot_params->e820_table[i]; + + /* Skip all entries above bios_start. */ + if (bios_start <= entry->addr) + continue; + + /* Skip non-RAM entries. */ + if (entry->type != E820_TYPE_RAM) + continue; + + /* Adjust bios_start to the end of the entry if needed. */ + if (bios_start > entry->addr + entry->size) + bios_start = entry->addr + entry->size; + + /* Keep bios_start page-aligned. */ + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Skip the entry if it's too small. */ + if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr) + continue; + + break; + } + + /* Place the trampoline just below the end of low memory */ + return bios_start - TRAMPOLINE_32BIT_SIZE; +} + struct paging_config paging_prepare(void *rmode) { struct paging_config paging_config = {}; - unsigned long bios_start, ebda_start; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ boot_params = rmode; @@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode) paging_config.l5_required = 1; } - /* - * Find a suitable spot for the trampoline. - * This code is based on reserve_bios_regions(). - */ - - ebda_start = *(unsigned short *)0x40e << 4; - bios_start = *(unsigned short *)0x413 << 10; - - if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) - bios_start = BIOS_START_MAX; - - if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) - bios_start = ebda_start; - - /* Place the trampoline just below the end of low memory, aligned to 4k */ - paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE; - paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE); + paging_config.trampoline_start = find_trampoline_placement(); trampoline_32bit = (unsigned long *)paging_config.trampoline_start; diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 16f49123d747..c4428a176973 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -13,6 +13,7 @@ */ #include <linux/types.h> +#include <asm/asm.h> #include "ctype.h" #include "string.h" @@ -28,8 +29,8 @@ int memcmp(const void *s1, const void *s2, size_t len) { bool diff; - asm("repe; cmpsb; setnz %0" - : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len)); + asm("repe; cmpsb" CC_SET(nz) + : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; } diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index 717bf0776421..5f7e43d4f64a 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -75,7 +75,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov LEN, %r8 diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index 5de7c0d46edf..acd11b3bf639 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis128_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis128_aesni_alg, diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S index 4eda2b8db9e1..491dd61c845c 100644 --- a/arch/x86/crypto/aegis128l-aesni-asm.S +++ b/arch/x86/crypto/aegis128l-aesni-asm.S @@ -66,7 +66,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG0, MSG0 pxor MSG1, MSG1 diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c index 876e4866e633..2071c3d1ae07 100644 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ b/arch/x86/crypto/aegis128l-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128l_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis128l_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis128l_aesni_alg, diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S index 32aae8397268..8870c7c5d9a4 100644 --- a/arch/x86/crypto/aegis256-aesni-asm.S +++ b/arch/x86/crypto/aegis256-aesni-asm.S @@ -59,7 +59,7 @@ * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov LEN, %r8 diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c index 2b5dd3af8f4d..b5f2a8fd5a71 100644 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ b/arch/x86/crypto/aegis256-aesni-glue.c @@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis256_aesni_alg[] = { } }; -static const struct x86_cpu_id aesni_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AES), - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); - static int __init crypto_aegis256_aesni_module_init(void) { - if (!x86_match_cpu(aesni_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_aegis256_aesni_alg, diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index e762ef417562..9bd139569b41 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -258,7 +258,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff .macro GCM_INIT Iv SUBKEY AAD AADLEN mov \AADLEN, %r11 mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length - xor %r11, %r11 + xor %r11d, %r11d mov %r11, InLen(%arg2) # ctx_data.in_length = 0 mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0 mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0 @@ -286,7 +286,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff movdqu HashKey(%arg2), %xmm13 add %arg5, InLen(%arg2) - xor %r11, %r11 # initialise the data pointer offset as zero + xor %r11d, %r11d # initialise the data pointer offset as zero PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation sub %r11, %arg5 # sub partial block data used @@ -702,7 +702,7 @@ _no_extra_mask_1_\@: # GHASH computation for the last <16 Byte block GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 - xor %rax,%rax + xor %eax, %eax mov %rax, PBlockLen(%arg2) jmp _dec_done_\@ @@ -737,7 +737,7 @@ _no_extra_mask_2_\@: # GHASH computation for the last <16 Byte block GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 - xor %rax,%rax + xor %eax, %eax mov %rax, PBlockLen(%arg2) jmp _encode_done_\@ diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index faecb1518bf8..1985ea0b551b 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -463,7 +463,7 @@ _get_AAD_rest_final\@: _get_AAD_done\@: # initialize the data pointer offset as zero - xor %r11, %r11 + xor %r11d, %r11d # start AES for num_initial_blocks blocks mov arg5, %rax # rax = *Y0 @@ -1770,7 +1770,7 @@ _get_AAD_rest_final\@: _get_AAD_done\@: # initialize the data pointer offset as zero - xor %r11, %r11 + xor %r11d, %r11d # start AES for num_initial_blocks blocks mov arg5, %rax # rax = *Y0 diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 2ddbe3a1868b..3582ae885ee1 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -154,8 +154,7 @@ static struct shash_alg ghash_alg = { .cra_name = "__ghash", .cra_driver_name = "__ghash-pclmulqdqni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_SHASH | - CRYPTO_ALG_INTERNAL, + .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = GHASH_BLOCK_SIZE, .cra_ctxsize = sizeof(struct ghash_ctx), .cra_module = THIS_MODULE, @@ -315,9 +314,8 @@ static struct ahash_alg ghash_async_alg = { .cra_driver_name = "ghash-clmulni", .cra_priority = 400, .cra_ctxsize = sizeof(struct ghash_async_ctx), - .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = GHASH_BLOCK_SIZE, - .cra_type = &crypto_ahash_type, .cra_module = THIS_MODULE, .cra_init = ghash_async_init_tfm, .cra_exit = ghash_async_exit_tfm, diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S index 07653d4582a6..de182c460f82 100644 --- a/arch/x86/crypto/morus1280-avx2-asm.S +++ b/arch/x86/crypto/morus1280-avx2-asm.S @@ -113,7 +113,7 @@ ENDPROC(__morus1280_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d vpxor MSG, MSG, MSG mov %rcx, %r8 diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c index f111f36d26dc..6634907d6ccd 100644 --- a/arch/x86/crypto/morus1280-avx2-glue.c +++ b/arch/x86/crypto/morus1280-avx2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor, MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400); -static const struct x86_cpu_id avx2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_AVX2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, avx2_cpu_id); - static int __init crypto_morus1280_avx2_module_init(void) { - if (!x86_match_cpu(avx2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus1280_avx2_algs, diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S index bd1aa1b60869..da5d2905db60 100644 --- a/arch/x86/crypto/morus1280-sse2-asm.S +++ b/arch/x86/crypto/morus1280-sse2-asm.S @@ -235,7 +235,7 @@ ENDPROC(__morus1280_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG_LO, MSG_LO pxor MSG_HI, MSG_HI diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c index 839270aa713c..95cf857d2cbb 100644 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ b/arch/x86/crypto/morus1280-sse2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor, MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350); -static const struct x86_cpu_id sse2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id); - static int __init crypto_morus1280_sse2_module_init(void) { - if (!x86_match_cpu(sse2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus1280_sse2_algs, diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S index efa02816d921..414db480250e 100644 --- a/arch/x86/crypto/morus640-sse2-asm.S +++ b/arch/x86/crypto/morus640-sse2-asm.S @@ -113,7 +113,7 @@ ENDPROC(__morus640_update_zero) * %r9 */ __load_partial: - xor %r9, %r9 + xor %r9d, %r9d pxor MSG, MSG mov %rcx, %r8 diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c index 26b47e2db8d2..615fb7bc9a32 100644 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ b/arch/x86/crypto/morus640-sse2-glue.c @@ -37,15 +37,11 @@ asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor, MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400); -static const struct x86_cpu_id sse2_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_XMM2), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id); - static int __init crypto_morus640_sse2_module_init(void) { - if (!x86_match_cpu(sse2_cpu_id)) + if (!boot_cpu_has(X86_FEATURE_XMM2) || + !boot_cpu_has(X86_FEATURE_OSXSAVE) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; return crypto_register_aeads(crypto_morus640_sse2_algs, diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 790377797544..f012b7e28ad1 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -169,7 +169,6 @@ static struct shash_alg alg = { .cra_name = "poly1305", .cra_driver_name = "poly1305-simd", .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = POLY1305_BLOCK_SIZE, .cra_module = THIS_MODULE, }, diff --git a/arch/x86/crypto/sha1-mb/sha1_mb.c b/arch/x86/crypto/sha1-mb/sha1_mb.c index e17655ffde79..b93805664c1d 100644 --- a/arch/x86/crypto/sha1-mb/sha1_mb.c +++ b/arch/x86/crypto/sha1-mb/sha1_mb.c @@ -746,9 +746,8 @@ static struct ahash_alg sha1_mb_areq_alg = { * algo may not have completed before hashing thread * sleep */ - .cra_flags = CRYPTO_ALG_TYPE_AHASH | - CRYPTO_ALG_ASYNC | - CRYPTO_ALG_INTERNAL, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT @@ -871,10 +870,16 @@ static struct ahash_alg sha1_mb_async_alg = { .base = { .cra_name = "sha1", .cra_driver_name = "sha1_mb", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC, + /* + * Low priority, since with few concurrent hash requests + * this is extremely slow due to the flush delay. Users + * whose workloads would benefit from this can request + * it explicitly by driver name, or can increase its + * priority at runtime using NETLINK_CRYPTO. + */ + .cra_priority = 50, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA1_BLOCK_SIZE, - .cra_type = &crypto_ahash_type, .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT(sha1_mb_async_alg.halg.base.cra_list), .cra_init = sha1_mb_async_init_tfm, diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index 6204bd53528c..613d0bfc3d84 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -96,7 +96,7 @@ # cleanup workspace mov $8, %ecx mov %rsp, %rdi - xor %rax, %rax + xor %eax, %eax rep stosq mov %rbp, %rsp # deallocate workspace diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index fc61739150e7..7391c7de72c7 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -104,7 +104,6 @@ static struct shash_alg sha1_ssse3_alg = { .cra_name = "sha1", .cra_driver_name = "sha1-ssse3", .cra_priority = 150, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -157,7 +156,6 @@ static struct shash_alg sha1_avx_alg = { .cra_name = "sha1", .cra_driver_name = "sha1-avx", .cra_priority = 160, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -249,7 +247,6 @@ static struct shash_alg sha1_avx2_alg = { .cra_name = "sha1", .cra_driver_name = "sha1-avx2", .cra_priority = 170, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -307,7 +304,6 @@ static struct shash_alg sha1_ni_alg = { .cra_name = "sha1", .cra_driver_name = "sha1-ni", .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c index 4c46ac1b6653..97c5fc43e115 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb.c +++ b/arch/x86/crypto/sha256-mb/sha256_mb.c @@ -745,9 +745,8 @@ static struct ahash_alg sha256_mb_areq_alg = { * algo may not have completed before hashing thread * sleep */ - .cra_flags = CRYPTO_ALG_TYPE_AHASH | - CRYPTO_ALG_ASYNC | - CRYPTO_ALG_INTERNAL, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT @@ -870,11 +869,16 @@ static struct ahash_alg sha256_mb_async_alg = { .base = { .cra_name = "sha256", .cra_driver_name = "sha256_mb", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_AHASH | - CRYPTO_ALG_ASYNC, + /* + * Low priority, since with few concurrent hash requests + * this is extremely slow due to the flush delay. Users + * whose workloads would benefit from this can request + * it explicitly by driver name, or can increase its + * priority at runtime using NETLINK_CRYPTO. + */ + .cra_priority = 50, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA256_BLOCK_SIZE, - .cra_type = &crypto_ahash_type, .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT (sha256_mb_async_alg.halg.base.cra_list), diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S index 16c4ccb1f154..d2364c55bbde 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S @@ -265,7 +265,7 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2) vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0 - vmovd _args_digest(state , idx, 4) , %xmm0 + vmovd _args_digest+4*32(state, idx, 4), %xmm1 vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1 diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 9e79baf03a4b..773a873d2b28 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -109,7 +109,6 @@ static struct shash_alg sha256_ssse3_algs[] = { { .cra_name = "sha256", .cra_driver_name = "sha256-ssse3", .cra_priority = 150, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -124,7 +123,6 @@ static struct shash_alg sha256_ssse3_algs[] = { { .cra_name = "sha224", .cra_driver_name = "sha224-ssse3", .cra_priority = 150, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -177,7 +175,6 @@ static struct shash_alg sha256_avx_algs[] = { { .cra_name = "sha256", .cra_driver_name = "sha256-avx", .cra_priority = 160, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -192,7 +189,6 @@ static struct shash_alg sha256_avx_algs[] = { { .cra_name = "sha224", .cra_driver_name = "sha224-avx", .cra_priority = 160, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -261,7 +257,6 @@ static struct shash_alg sha256_avx2_algs[] = { { .cra_name = "sha256", .cra_driver_name = "sha256-avx2", .cra_priority = 170, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -276,7 +271,6 @@ static struct shash_alg sha256_avx2_algs[] = { { .cra_name = "sha224", .cra_driver_name = "sha224-avx2", .cra_priority = 170, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -343,7 +337,6 @@ static struct shash_alg sha256_ni_algs[] = { { .cra_name = "sha256", .cra_driver_name = "sha256-ni", .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -358,7 +351,6 @@ static struct shash_alg sha256_ni_algs[] = { { .cra_name = "sha224", .cra_driver_name = "sha224-ni", .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c index 39e2bbdc1836..26b85678012d 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb.c @@ -778,9 +778,8 @@ static struct ahash_alg sha512_mb_areq_alg = { * algo may not have completed before hashing thread * sleep */ - .cra_flags = CRYPTO_ALG_TYPE_AHASH | - CRYPTO_ALG_ASYNC | - CRYPTO_ALG_INTERNAL, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT @@ -904,11 +903,16 @@ static struct ahash_alg sha512_mb_async_alg = { .base = { .cra_name = "sha512", .cra_driver_name = "sha512_mb", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_AHASH | - CRYPTO_ALG_ASYNC, + /* + * Low priority, since with few concurrent hash requests + * this is extremely slow due to the flush delay. Users + * whose workloads would benefit from this can request + * it explicitly by driver name, or can increase its + * priority at runtime using NETLINK_CRYPTO. + */ + .cra_priority = 50, + .cra_flags = CRYPTO_ALG_ASYNC, .cra_blocksize = SHA512_BLOCK_SIZE, - .cra_type = &crypto_ahash_type, .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT (sha512_mb_async_alg.halg.base.cra_list), diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 2b0e2a6825f3..f1b811b60ba6 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -109,7 +109,6 @@ static struct shash_alg sha512_ssse3_algs[] = { { .cra_name = "sha512", .cra_driver_name = "sha512-ssse3", .cra_priority = 150, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -124,7 +123,6 @@ static struct shash_alg sha512_ssse3_algs[] = { { .cra_name = "sha384", .cra_driver_name = "sha384-ssse3", .cra_priority = 150, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -188,7 +186,6 @@ static struct shash_alg sha512_avx_algs[] = { { .cra_name = "sha512", .cra_driver_name = "sha512-avx", .cra_priority = 160, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -203,7 +200,6 @@ static struct shash_alg sha512_avx_algs[] = { { .cra_name = "sha384", .cra_driver_name = "sha384-avx", .cra_priority = 160, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -261,7 +257,6 @@ static struct shash_alg sha512_avx2_algs[] = { { .cra_name = "sha512", .cra_driver_name = "sha512-avx2", .cra_priority = 170, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA512_BLOCK_SIZE, .cra_module = THIS_MODULE, } @@ -276,7 +271,6 @@ static struct shash_alg sha512_avx2_algs[] = { { .cra_name = "sha384", .cra_driver_name = "sha384-avx2", .cra_priority = 170, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA384_BLOCK_SIZE, .cra_module = THIS_MODULE, } diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index c371bfee137a..2767c625a52c 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -65,7 +65,7 @@ # define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF #else # define preempt_stop(clobbers) -# define resume_kernel restore_all +# define resume_kernel restore_all_kernel #endif .macro TRACE_IRQS_IRET @@ -77,6 +77,8 @@ #endif .endm +#define PTI_SWITCH_MASK (1 << PAGE_SHIFT) + /* * User gs save/restore * @@ -154,7 +156,52 @@ #endif /* CONFIG_X86_32_LAZY_GS */ -.macro SAVE_ALL pt_regs_ax=%eax +/* Unconditionally switch to user cr3 */ +.macro SWITCH_TO_USER_CR3 scratch_reg:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + + movl %cr3, \scratch_reg + orl $PTI_SWITCH_MASK, \scratch_reg + movl \scratch_reg, %cr3 +.Lend_\@: +.endm + +.macro BUG_IF_WRONG_CR3 no_user_check=0 +#ifdef CONFIG_DEBUG_ENTRY + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + .if \no_user_check == 0 + /* coming from usermode? */ + testl $SEGMENT_RPL_MASK, PT_CS(%esp) + jz .Lend_\@ + .endif + /* On user-cr3? */ + movl %cr3, %eax + testl $PTI_SWITCH_MASK, %eax + jnz .Lend_\@ + /* From userspace with kernel cr3 - BUG */ + ud2 +.Lend_\@: +#endif +.endm + +/* + * Switch to kernel cr3 if not already loaded and return current cr3 in + * \scratch_reg + */ +.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + movl %cr3, \scratch_reg + /* Test if we are already on kernel CR3 */ + testl $PTI_SWITCH_MASK, \scratch_reg + jz .Lend_\@ + andl $(~PTI_SWITCH_MASK), \scratch_reg + movl \scratch_reg, %cr3 + /* Return original CR3 in \scratch_reg */ + orl $PTI_SWITCH_MASK, \scratch_reg +.Lend_\@: +.endm + +.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 cld PUSH_GS pushl %fs @@ -173,6 +220,29 @@ movl $(__KERNEL_PERCPU), %edx movl %edx, %fs SET_KERNEL_GS %edx + + /* Switch to kernel stack if necessary */ +.if \switch_stacks > 0 + SWITCH_TO_KERNEL_STACK +.endif + +.endm + +.macro SAVE_ALL_NMI cr3_reg:req + SAVE_ALL + + BUG_IF_WRONG_CR3 + + /* + * Now switch the CR3 when PTI is enabled. + * + * We can enter with either user or kernel cr3, the code will + * store the old cr3 in \cr3_reg and switches to the kernel cr3 + * if necessary. + */ + SWITCH_TO_KERNEL_CR3 scratch_reg=\cr3_reg + +.Lend_\@: .endm /* @@ -221,6 +291,349 @@ POP_GS_EX .endm +.macro RESTORE_ALL_NMI cr3_reg:req pop=0 + /* + * Now switch the CR3 when PTI is enabled. + * + * We enter with kernel cr3 and switch the cr3 to the value + * stored on \cr3_reg, which is either a user or a kernel cr3. + */ + ALTERNATIVE "jmp .Lswitched_\@", "", X86_FEATURE_PTI + + testl $PTI_SWITCH_MASK, \cr3_reg + jz .Lswitched_\@ + + /* User cr3 in \cr3_reg - write it to hardware cr3 */ + movl \cr3_reg, %cr3 + +.Lswitched_\@: + + BUG_IF_WRONG_CR3 + + RESTORE_REGS pop=\pop +.endm + +.macro CHECK_AND_APPLY_ESPFIX +#ifdef CONFIG_X86_ESPFIX32 +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) + + ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX + + movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS + /* + * Warning: PT_OLDSS(%esp) contains the wrong/random values if we + * are returning to the kernel. + * See comments in process.c:copy_thread() for details. + */ + movb PT_OLDSS(%esp), %ah + movb PT_CS(%esp), %al + andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax + cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax + jne .Lend_\@ # returning to user-space with LDT SS + + /* + * Setup and switch to ESPFIX stack + * + * We're returning to userspace with a 16 bit stack. The CPU will not + * restore the high word of ESP for us on executing iret... This is an + * "official" bug of all the x86-compatible CPUs, which we can work + * around to make dosemu and wine happy. We do this by preloading the + * high word of ESP with the high word of the userspace ESP while + * compensating for the offset by changing to the ESPFIX segment with + * a base address that matches for the difference. + */ + mov %esp, %edx /* load kernel esp */ + mov PT_OLDESP(%esp), %eax /* load userspace esp */ + mov %dx, %ax /* eax: new kernel esp */ + sub %eax, %edx /* offset (low word is 0) */ + shr $16, %edx + mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ + mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ + pushl $__ESPFIX_SS + pushl %eax /* new kernel esp */ + /* + * Disable interrupts, but do not irqtrace this section: we + * will soon execute iret and the tracer was already set to + * the irqstate after the IRET: + */ + DISABLE_INTERRUPTS(CLBR_ANY) + lss (%esp), %esp /* switch to espfix segment */ +.Lend_\@: +#endif /* CONFIG_X86_ESPFIX32 */ +.endm + +/* + * Called with pt_regs fully populated and kernel segments loaded, + * so we can access PER_CPU and use the integer registers. + * + * We need to be very careful here with the %esp switch, because an NMI + * can happen everywhere. If the NMI handler finds itself on the + * entry-stack, it will overwrite the task-stack and everything we + * copied there. So allocate the stack-frame on the task-stack and + * switch to it before we do any copying. + */ + +#define CS_FROM_ENTRY_STACK (1 << 31) +#define CS_FROM_USER_CR3 (1 << 30) + +.macro SWITCH_TO_KERNEL_STACK + + ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV + + BUG_IF_WRONG_CR3 + + SWITCH_TO_KERNEL_CR3 scratch_reg=%eax + + /* + * %eax now contains the entry cr3 and we carry it forward in + * that register for the time this macro runs + */ + + /* Are we on the entry stack? Bail out if not! */ + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx + subl %esp, %ecx /* ecx = (end of entry_stack) - esp */ + cmpl $SIZEOF_entry_stack, %ecx + jae .Lend_\@ + + /* Load stack pointer into %esi and %edi */ + movl %esp, %esi + movl %esi, %edi + + /* Move %edi to the top of the entry stack */ + andl $(MASK_entry_stack), %edi + addl $(SIZEOF_entry_stack), %edi + + /* Load top of task-stack into %edi */ + movl TSS_entry2task_stack(%edi), %edi + + /* + * Clear unused upper bits of the dword containing the word-sized CS + * slot in pt_regs in case hardware didn't clear it for us. + */ + andl $(0x0000ffff), PT_CS(%esp) + + /* Special case - entry from kernel mode via entry stack */ +#ifdef CONFIG_VM86 + movl PT_EFLAGS(%esp), %ecx # mix EFLAGS and CS + movb PT_CS(%esp), %cl + andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %ecx +#else + movl PT_CS(%esp), %ecx + andl $SEGMENT_RPL_MASK, %ecx +#endif + cmpl $USER_RPL, %ecx + jb .Lentry_from_kernel_\@ + + /* Bytes to copy */ + movl $PTREGS_SIZE, %ecx + +#ifdef CONFIG_VM86 + testl $X86_EFLAGS_VM, PT_EFLAGS(%esi) + jz .Lcopy_pt_regs_\@ + + /* + * Stack-frame contains 4 additional segment registers when + * coming from VM86 mode + */ + addl $(4 * 4), %ecx + +#endif +.Lcopy_pt_regs_\@: + + /* Allocate frame on task-stack */ + subl %ecx, %edi + + /* Switch to task-stack */ + movl %edi, %esp + + /* + * We are now on the task-stack and can safely copy over the + * stack-frame + */ + shrl $2, %ecx + cld + rep movsl + + jmp .Lend_\@ + +.Lentry_from_kernel_\@: + + /* + * This handles the case when we enter the kernel from + * kernel-mode and %esp points to the entry-stack. When this + * happens we need to switch to the task-stack to run C code, + * but switch back to the entry-stack again when we approach + * iret and return to the interrupted code-path. This usually + * happens when we hit an exception while restoring user-space + * segment registers on the way back to user-space or when the + * sysenter handler runs with eflags.tf set. + * + * When we switch to the task-stack here, we can't trust the + * contents of the entry-stack anymore, as the exception handler + * might be scheduled out or moved to another CPU. Therefore we + * copy the complete entry-stack to the task-stack and set a + * marker in the iret-frame (bit 31 of the CS dword) to detect + * what we've done on the iret path. + * + * On the iret path we copy everything back and switch to the + * entry-stack, so that the interrupted kernel code-path + * continues on the same stack it was interrupted with. + * + * Be aware that an NMI can happen anytime in this code. + * + * %esi: Entry-Stack pointer (same as %esp) + * %edi: Top of the task stack + * %eax: CR3 on kernel entry + */ + + /* Calculate number of bytes on the entry stack in %ecx */ + movl %esi, %ecx + + /* %ecx to the top of entry-stack */ + andl $(MASK_entry_stack), %ecx + addl $(SIZEOF_entry_stack), %ecx + + /* Number of bytes on the entry stack to %ecx */ + sub %esi, %ecx + + /* Mark stackframe as coming from entry stack */ + orl $CS_FROM_ENTRY_STACK, PT_CS(%esp) + + /* + * Test the cr3 used to enter the kernel and add a marker + * so that we can switch back to it before iret. + */ + testl $PTI_SWITCH_MASK, %eax + jz .Lcopy_pt_regs_\@ + orl $CS_FROM_USER_CR3, PT_CS(%esp) + + /* + * %esi and %edi are unchanged, %ecx contains the number of + * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate + * the stack-frame on task-stack and copy everything over + */ + jmp .Lcopy_pt_regs_\@ + +.Lend_\@: +.endm + +/* + * Switch back from the kernel stack to the entry stack. + * + * The %esp register must point to pt_regs on the task stack. It will + * first calculate the size of the stack-frame to copy, depending on + * whether we return to VM86 mode or not. With that it uses 'rep movsl' + * to copy the contents of the stack over to the entry stack. + * + * We must be very careful here, as we can't trust the contents of the + * task-stack once we switched to the entry-stack. When an NMI happens + * while on the entry-stack, the NMI handler will switch back to the top + * of the task stack, overwriting our stack-frame we are about to copy. + * Therefore we switch the stack only after everything is copied over. + */ +.macro SWITCH_TO_ENTRY_STACK + + ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV + + /* Bytes to copy */ + movl $PTREGS_SIZE, %ecx + +#ifdef CONFIG_VM86 + testl $(X86_EFLAGS_VM), PT_EFLAGS(%esp) + jz .Lcopy_pt_regs_\@ + + /* Additional 4 registers to copy when returning to VM86 mode */ + addl $(4 * 4), %ecx + +.Lcopy_pt_regs_\@: +#endif + + /* Initialize source and destination for movsl */ + movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi + subl %ecx, %edi + movl %esp, %esi + + /* Save future stack pointer in %ebx */ + movl %edi, %ebx + + /* Copy over the stack-frame */ + shrl $2, %ecx + cld + rep movsl + + /* + * Switch to entry-stack - needs to happen after everything is + * copied because the NMI handler will overwrite the task-stack + * when on entry-stack + */ + movl %ebx, %esp + +.Lend_\@: +.endm + +/* + * This macro handles the case when we return to kernel-mode on the iret + * path and have to switch back to the entry stack and/or user-cr3 + * + * See the comments below the .Lentry_from_kernel_\@ label in the + * SWITCH_TO_KERNEL_STACK macro for more details. + */ +.macro PARANOID_EXIT_TO_KERNEL_MODE + + /* + * Test if we entered the kernel with the entry-stack. Most + * likely we did not, because this code only runs on the + * return-to-kernel path. + */ + testl $CS_FROM_ENTRY_STACK, PT_CS(%esp) + jz .Lend_\@ + + /* Unlikely slow-path */ + + /* Clear marker from stack-frame */ + andl $(~CS_FROM_ENTRY_STACK), PT_CS(%esp) + + /* Copy the remaining task-stack contents to entry-stack */ + movl %esp, %esi + movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi + + /* Bytes on the task-stack to ecx */ + movl PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx + subl %esi, %ecx + + /* Allocate stack-frame on entry-stack */ + subl %ecx, %edi + + /* + * Save future stack-pointer, we must not switch until the + * copy is done, otherwise the NMI handler could destroy the + * contents of the task-stack we are about to copy. + */ + movl %edi, %ebx + + /* Do the copy */ + shrl $2, %ecx + cld + rep movsl + + /* Safe to switch to entry-stack now */ + movl %ebx, %esp + + /* + * We came from entry-stack and need to check if we also need to + * switch back to user cr3. + */ + testl $CS_FROM_USER_CR3, PT_CS(%esp) + jz .Lend_\@ + + /* Clear marker from stack-frame */ + andl $(~CS_FROM_USER_CR3), PT_CS(%esp) + + SWITCH_TO_USER_CR3 scratch_reg=%eax + +.Lend_\@: +.endm /* * %eax: prev task * %edx: next task @@ -351,9 +764,9 @@ ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) .Lneed_resched: cmpl $0, PER_CPU_VAR(__preempt_count) - jnz restore_all + jnz restore_all_kernel testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? - jz restore_all + jz restore_all_kernel call preempt_schedule_irq jmp .Lneed_resched END(resume_kernel) @@ -412,7 +825,21 @@ ENTRY(xen_sysenter_target) * 0(%ebp) arg6 */ ENTRY(entry_SYSENTER_32) - movl TSS_sysenter_sp0(%esp), %esp + /* + * On entry-stack with all userspace-regs live - save and + * restore eflags and %eax to use it as scratch-reg for the cr3 + * switch. + */ + pushfl + pushl %eax + BUG_IF_WRONG_CR3 no_user_check=1 + SWITCH_TO_KERNEL_CR3 scratch_reg=%eax + popl %eax + popfl + + /* Stack empty again, switch to task stack */ + movl TSS_entry2task_stack(%esp), %esp + .Lsysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ pushl %ebp /* pt_regs->sp (stashed in bp) */ @@ -421,7 +848,7 @@ ENTRY(entry_SYSENTER_32) pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ pushl %eax /* pt_regs->orig_ax */ - SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ + SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest, stack already switched */ /* * SYSENTER doesn't filter flags, so we need to clear NT, AC @@ -460,25 +887,49 @@ ENTRY(entry_SYSENTER_32) /* Opportunistic SYSEXIT */ TRACE_IRQS_ON /* User mode traces as IRQs on. */ + + /* + * Setup entry stack - we keep the pointer in %eax and do the + * switch after almost all user-state is restored. + */ + + /* Load entry stack pointer and allocate frame for eflags/eax */ + movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %eax + subl $(2*4), %eax + + /* Copy eflags and eax to entry stack */ + movl PT_EFLAGS(%esp), %edi + movl PT_EAX(%esp), %esi + movl %edi, (%eax) + movl %esi, 4(%eax) + + /* Restore user registers and segments */ movl PT_EIP(%esp), %edx /* pt_regs->ip */ movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */ 1: mov PT_FS(%esp), %fs PTGS_TO_GS + popl %ebx /* pt_regs->bx */ addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */ popl %esi /* pt_regs->si */ popl %edi /* pt_regs->di */ popl %ebp /* pt_regs->bp */ - popl %eax /* pt_regs->ax */ + + /* Switch to entry stack */ + movl %eax, %esp + + /* Now ready to switch the cr3 */ + SWITCH_TO_USER_CR3 scratch_reg=%eax /* * Restore all flags except IF. (We restore IF separately because * STI gives a one-instruction window in which we won't be interrupted, * whereas POPF does not.) */ - addl $PT_EFLAGS-PT_DS, %esp /* point esp at pt_regs->flags */ btrl $X86_EFLAGS_IF_BIT, (%esp) + BUG_IF_WRONG_CR3 no_user_check=1 popfl + popl %eax /* * Return back to the vDSO, which will pop ecx and edx. @@ -532,7 +983,8 @@ ENDPROC(entry_SYSENTER_32) ENTRY(entry_INT80_32) ASM_CLAC pushl %eax /* pt_regs->orig_ax */ - SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ + + SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1 /* save rest */ /* * User mode is traced as though IRQs are on, and the interrupt gate @@ -546,24 +998,17 @@ ENTRY(entry_INT80_32) restore_all: TRACE_IRQS_IRET + SWITCH_TO_ENTRY_STACK .Lrestore_all_notrace: -#ifdef CONFIG_X86_ESPFIX32 - ALTERNATIVE "jmp .Lrestore_nocheck", "", X86_BUG_ESPFIX - - movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS - /* - * Warning: PT_OLDSS(%esp) contains the wrong/random values if we - * are returning to the kernel. - * See comments in process.c:copy_thread() for details. - */ - movb PT_OLDSS(%esp), %ah - movb PT_CS(%esp), %al - andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax - cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax - je .Lldt_ss # returning to user-space with LDT SS -#endif + CHECK_AND_APPLY_ESPFIX .Lrestore_nocheck: - RESTORE_REGS 4 # skip orig_eax/error_code + /* Switch back to user CR3 */ + SWITCH_TO_USER_CR3 scratch_reg=%eax + + BUG_IF_WRONG_CR3 + + /* Restore user state */ + RESTORE_REGS pop=4 # skip orig_eax/error_code .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -572,46 +1017,33 @@ restore_all: */ INTERRUPT_RETURN +restore_all_kernel: + TRACE_IRQS_IRET + PARANOID_EXIT_TO_KERNEL_MODE + BUG_IF_WRONG_CR3 + RESTORE_REGS 4 + jmp .Lirq_return + .section .fixup, "ax" ENTRY(iret_exc ) pushl $0 # no error code pushl $do_iret_error - jmp common_exception -.previous - _ASM_EXTABLE(.Lirq_return, iret_exc) -#ifdef CONFIG_X86_ESPFIX32 -.Lldt_ss: -/* - * Setup and switch to ESPFIX stack - * - * We're returning to userspace with a 16 bit stack. The CPU will not - * restore the high word of ESP for us on executing iret... This is an - * "official" bug of all the x86-compatible CPUs, which we can work - * around to make dosemu and wine happy. We do this by preloading the - * high word of ESP with the high word of the userspace ESP while - * compensating for the offset by changing to the ESPFIX segment with - * a base address that matches for the difference. - */ -#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) - mov %esp, %edx /* load kernel esp */ - mov PT_OLDESP(%esp), %eax /* load userspace esp */ - mov %dx, %ax /* eax: new kernel esp */ - sub %eax, %edx /* offset (low word is 0) */ - shr $16, %edx - mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ - mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ - pushl $__ESPFIX_SS - pushl %eax /* new kernel esp */ +#ifdef CONFIG_DEBUG_ENTRY /* - * Disable interrupts, but do not irqtrace this section: we - * will soon execute iret and the tracer was already set to - * the irqstate after the IRET: + * The stack-frame here is the one that iret faulted on, so its a + * return-to-user frame. We are on kernel-cr3 because we come here from + * the fixup code. This confuses the CR3 checker, so switch to user-cr3 + * as the checker expects it. */ - DISABLE_INTERRUPTS(CLBR_ANY) - lss (%esp), %esp /* switch to espfix segment */ - jmp .Lrestore_nocheck + pushl %eax + SWITCH_TO_USER_CR3 scratch_reg=%eax + popl %eax #endif + + jmp common_exception +.previous + _ASM_EXTABLE(.Lirq_return, iret_exc) ENDPROC(entry_INT80_32) .macro FIXUP_ESPFIX_STACK @@ -671,7 +1103,8 @@ END(irq_entries_start) common_interrupt: ASM_CLAC addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */ - SAVE_ALL + + SAVE_ALL switch_stacks=1 ENCODE_FRAME_POINTER TRACE_IRQS_OFF movl %esp, %eax @@ -679,16 +1112,16 @@ common_interrupt: jmp ret_from_intr ENDPROC(common_interrupt) -#define BUILD_INTERRUPT3(name, nr, fn) \ -ENTRY(name) \ - ASM_CLAC; \ - pushl $~(nr); \ - SAVE_ALL; \ - ENCODE_FRAME_POINTER; \ - TRACE_IRQS_OFF \ - movl %esp, %eax; \ - call fn; \ - jmp ret_from_intr; \ +#define BUILD_INTERRUPT3(name, nr, fn) \ +ENTRY(name) \ + ASM_CLAC; \ + pushl $~(nr); \ + SAVE_ALL switch_stacks=1; \ + ENCODE_FRAME_POINTER; \ + TRACE_IRQS_OFF \ + movl %esp, %eax; \ + call fn; \ + jmp ret_from_intr; \ ENDPROC(name) #define BUILD_INTERRUPT(name, nr) \ @@ -920,16 +1353,20 @@ common_exception: pushl %es pushl %ds pushl %eax + movl $(__USER_DS), %eax + movl %eax, %ds + movl %eax, %es + movl $(__KERNEL_PERCPU), %eax + movl %eax, %fs pushl %ebp pushl %edi pushl %esi pushl %edx pushl %ecx pushl %ebx + SWITCH_TO_KERNEL_STACK ENCODE_FRAME_POINTER cld - movl $(__KERNEL_PERCPU), %ecx - movl %ecx, %fs UNWIND_ESPFIX_STACK GS_TO_REG %ecx movl PT_GS(%esp), %edi # get the function address @@ -937,9 +1374,6 @@ common_exception: movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart REG_TO_PTGS %ecx SET_KERNEL_GS %ecx - movl $(__USER_DS), %ecx - movl %ecx, %ds - movl %ecx, %es TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer CALL_NOSPEC %edi @@ -948,40 +1382,12 @@ END(common_exception) ENTRY(debug) /* - * #DB can happen at the first instruction of - * entry_SYSENTER_32 or in Xen's SYSENTER prologue. If this - * happens, then we will be running on a very small stack. We - * need to detect this condition and switch to the thread - * stack before calling any C code at all. - * - * If you edit this code, keep in mind that NMIs can happen in here. + * Entry from sysenter is now handled in common_exception */ ASM_CLAC pushl $-1 # mark this as an int - SAVE_ALL - ENCODE_FRAME_POINTER - xorl %edx, %edx # error code 0 - movl %esp, %eax # pt_regs pointer - - /* Are we currently on the SYSENTER stack? */ - movl PER_CPU_VAR(cpu_entry_area), %ecx - addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx - subl %eax, %ecx /* ecx = (end of entry_stack) - esp */ - cmpl $SIZEOF_entry_stack, %ecx - jb .Ldebug_from_sysenter_stack - - TRACE_IRQS_OFF - call do_debug - jmp ret_from_exception - -.Ldebug_from_sysenter_stack: - /* We're on the SYSENTER stack. Switch off. */ - movl %esp, %ebx - movl PER_CPU_VAR(cpu_current_top_of_stack), %esp - TRACE_IRQS_OFF - call do_debug - movl %ebx, %esp - jmp ret_from_exception + pushl $do_debug + jmp common_exception END(debug) /* @@ -993,6 +1399,7 @@ END(debug) */ ENTRY(nmi) ASM_CLAC + #ifdef CONFIG_X86_ESPFIX32 pushl %eax movl %ss, %eax @@ -1002,7 +1409,7 @@ ENTRY(nmi) #endif pushl %eax # pt_regs->orig_ax - SAVE_ALL + SAVE_ALL_NMI cr3_reg=%edi ENCODE_FRAME_POINTER xorl %edx, %edx # zero error code movl %esp, %eax # pt_regs pointer @@ -1016,7 +1423,7 @@ ENTRY(nmi) /* Not on SYSENTER stack. */ call do_nmi - jmp .Lrestore_all_notrace + jmp .Lnmi_return .Lnmi_from_sysenter_stack: /* @@ -1027,7 +1434,11 @@ ENTRY(nmi) movl PER_CPU_VAR(cpu_current_top_of_stack), %esp call do_nmi movl %ebx, %esp - jmp .Lrestore_all_notrace + +.Lnmi_return: + CHECK_AND_APPLY_ESPFIX + RESTORE_ALL_NMI cr3_reg=%edi pop=4 + jmp .Lirq_return #ifdef CONFIG_X86_ESPFIX32 .Lnmi_espfix_stack: @@ -1042,12 +1453,12 @@ ENTRY(nmi) pushl 16(%esp) .endr pushl %eax - SAVE_ALL + SAVE_ALL_NMI cr3_reg=%edi ENCODE_FRAME_POINTER FIXUP_ESPFIX_STACK # %eax == %esp xorl %edx, %edx # zero error code call do_nmi - RESTORE_REGS + RESTORE_ALL_NMI cr3_reg=%edi lss 12+4(%esp), %esp # back to espfix stack jmp .Lirq_return #endif @@ -1056,7 +1467,8 @@ END(nmi) ENTRY(int3) ASM_CLAC pushl $-1 # mark this as an int - SAVE_ALL + + SAVE_ALL switch_stacks=1 ENCODE_FRAME_POINTER TRACE_IRQS_OFF xorl %edx, %edx # zero error code diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 73a522d53b53..957dfb693ecc 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -92,7 +92,7 @@ END(native_usergs_sysret64) .endm .macro TRACE_IRQS_IRETQ_DEBUG - bt $9, EFLAGS(%rsp) /* interrupts off? */ + btl $9, EFLAGS(%rsp) /* interrupts off? */ jnc 1f TRACE_IRQS_ON_DEBUG 1: @@ -408,6 +408,7 @@ ENTRY(ret_from_fork) 1: /* kernel thread */ + UNWIND_HINT_EMPTY movq %r12, %rdi CALL_NOSPEC %rbx /* @@ -701,7 +702,7 @@ retint_kernel: #ifdef CONFIG_PREEMPT /* Interrupts are off */ /* Check if we need preemption */ - bt $9, EFLAGS(%rsp) /* were interrupts off? */ + btl $9, EFLAGS(%rsp) /* were interrupts off? */ jnc 1f 0: cmpl $0, PER_CPU_VAR(__preempt_count) jnz 1f @@ -981,7 +982,7 @@ ENTRY(\sym) call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ + jmp error_exit .endif END(\sym) .endm @@ -1222,7 +1223,6 @@ END(paranoid_exit) /* * Save all registers in pt_regs, and switch GS if needed. - * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) UNWIND_HINT_FUNC @@ -1269,7 +1269,6 @@ ENTRY(error_entry) * for these here too. */ .Lerror_kernelspace: - incl %ebx leaq native_irq_return_iret(%rip), %rcx cmpq %rcx, RIP+8(%rsp) je .Lerror_bad_iret @@ -1303,28 +1302,20 @@ ENTRY(error_entry) /* * Pretend that the exception came from user mode: set up pt_regs - * as if we faulted immediately after IRET and clear EBX so that - * error_exit knows that we will be returning to user mode. + * as if we faulted immediately after IRET. */ mov %rsp, %rdi call fixup_bad_iret mov %rax, %rsp - decl %ebx jmp .Lerror_entry_from_usermode_after_swapgs END(error_entry) - -/* - * On entry, EBX is a "return to kernel mode" flag: - * 1: already in kernel mode, don't need SWAPGS - * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode - */ ENTRY(error_exit) UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - testl %ebx, %ebx - jnz retint_kernel + testb $3, CS(%rsp) + jz retint_kernel jmp retint_user END(error_exit) diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 261802b1cc50..9f695f517747 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -46,10 +46,8 @@ targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so) CPPFLAGS_vdso.lds += -P -C -VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ - -Wl,--no-undefined \ - -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \ - $(DISABLE_LTO) +VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \ + -z max-page-size=4096 -z common-page-size=4096 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) @@ -58,9 +56,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(src hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ -define cmd_vdso2c - $(obj)/vdso2c $< $(<:%.dbg=%) $@ -endef + cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE $(call if_changed,vdso2c) @@ -95,10 +91,8 @@ CFLAGS_REMOVE_vvar.o = -pg # CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds) -VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \ - -Wl,-soname=linux-vdso.so.1 \ - -Wl,-z,max-page-size=4096 \ - -Wl,-z,common-page-size=4096 +VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \ + -z max-page-size=4096 -z common-page-size=4096 # x32-rebranded versions vobjx32s-y := $(vobjs-y:.o=-x32.o) @@ -123,7 +117,7 @@ $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE $(call if_changed,vdso) CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) -VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 +VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1 targets += vdso32/vdso32.lds targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o @@ -157,13 +151,13 @@ $(obj)/vdso32.so.dbg: FORCE \ # The DSO images are built using a special linker script. # quiet_cmd_vdso = VDSO $@ - cmd_vdso = $(CC) -nostdlib -o $@ \ + cmd_vdso = $(LD) -nostdlib -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ - -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ + -T $(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \ - $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS) +VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \ + $(call ld-option, --build-id) -Bsymbolic GCOV_PROFILE := n # diff --git a/arch/x86/entry/vdso/vdso-note.S b/arch/x86/entry/vdso/vdso-note.S index 79a071e4357e..79423170118f 100644 --- a/arch/x86/entry/vdso/vdso-note.S +++ b/arch/x86/entry/vdso/vdso-note.S @@ -3,6 +3,7 @@ * Here we can supply some information useful to userland. */ +#include <linux/build-salt.h> #include <linux/uts.h> #include <linux/version.h> #include <linux/elfnote.h> @@ -10,3 +11,5 @@ ELFNOTE_START(Linux, 0, "a") .long LINUX_VERSION_CODE ELFNOTE_END + +BUILD_SALT diff --git a/arch/x86/entry/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S index 9fd51f206314..e78047d119f6 100644 --- a/arch/x86/entry/vdso/vdso32/note.S +++ b/arch/x86/entry/vdso/vdso32/note.S @@ -4,6 +4,7 @@ * Here we can supply some information useful to userland. */ +#include <linux/build-salt.h> #include <linux/version.h> #include <linux/elfnote.h> @@ -14,6 +15,8 @@ ELFNOTE_START(Linux, 0, "a") .long LINUX_VERSION_CODE ELFNOTE_END +BUILD_SALT + #ifdef CONFIG_XEN /* * Add a special note telling glibc's dynamic linker a fake hardware diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 4b98101209a1..d50bb4dc0650 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) { struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); struct perf_event *event = pcpu->event; - struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event *hwc; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; @@ -602,6 +602,10 @@ fail: return 0; } + if (WARN_ON_ONCE(!event)) + goto fail; + + hwc = &event->hw; msr = hwc->config_base; buf = ibs_data.regs; rdmsrl(msr, *buf); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 707b2a96e516..035c37481f57 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2041,15 +2041,15 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); cpuc->intel_cp_status &= ~(1ull << hwc->idx); + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_disable(event); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; } x86_pmu_disable_event(event); - - if (unlikely(event->attr.precise_ip)) - intel_pmu_pebs_disable(event); } static void intel_pmu_del_event(struct perf_event *event) @@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event) x86_perf_event_update(event); } -static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) +static void intel_pmu_enable_fixed(struct perf_event *event) { + struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx - INTEL_PMC_IDX_FIXED; - u64 ctrl_val, bits, mask; + u64 ctrl_val, mask, bits = 0; /* - * Enable IRQ generation (0x8), + * Enable IRQ generation (0x8), if not PEBS, * and enable ring-3 counting (0x2) and ring-0 counting (0x1) * if requested: */ - bits = 0x8ULL; + if (!event->attr.precise_ip) + bits |= 0x8; if (hwc->config & ARCH_PERFMON_EVENTSEL_USR) bits |= 0x2; if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) @@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event) if (unlikely(event_is_checkpointed(event))) cpuc->intel_cp_status |= (1ull << hwc->idx); + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_enable(event); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { - intel_pmu_enable_fixed(hwc); + intel_pmu_enable_fixed(event); return; } - if (unlikely(event->attr.precise_ip)) - intel_pmu_pebs_enable(event); - __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } @@ -2280,7 +2282,10 @@ again: * counters from the GLOBAL_STATUS mask and we always process PEBS * events via drain_pebs(). */ - status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK); + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + status &= ~cpuc->pebs_enabled; + else + status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK); /* * PEBS overflow sets bit 62 in the global status register @@ -2997,6 +3002,9 @@ static int intel_pmu_hw_config(struct perf_event *event) } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); + + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; } if (needs_branch_stack(event)) { @@ -4069,7 +4077,6 @@ __init int intel_pmu_init(void) intel_pmu_lbr_init_skl(); x86_pmu.event_constraints = intel_slm_event_constraints; - x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints; x86_pmu.extra_regs = intel_glm_extra_regs; /* * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS @@ -4079,6 +4086,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_prec_dist = true; x86_pmu.lbr_pt_coexist = true; x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_PEBS_ALL; x86_pmu.get_event_constraints = glp_get_event_constraints; x86_pmu.cpu_events = glm_events_attrs; /* Goldmont Plus has 4-wide pipeline */ diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8cf03f101938..b7b01d762d32 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -713,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -struct event_constraint intel_glp_pebs_event_constraints[] = { - /* Allow all events as PEBS with no flags */ - INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), - EVENT_CONSTRAINT_END -}; - struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ @@ -871,6 +865,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) } } + /* + * Extended PEBS support + * Makes the PEBS code search the normal constraints. + */ + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + return NULL; + return &emptyconstraint; } @@ -896,10 +897,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) { struct debug_store *ds = cpuc->ds; u64 threshold; + int reserved; + + if (x86_pmu.flags & PMU_FL_PEBS_ALL) + reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed; + else + reserved = x86_pmu.max_pebs_events; if (cpuc->n_pebs == cpuc->n_large_pebs) { threshold = ds->pebs_absolute_maximum - - x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + reserved * x86_pmu.pebs_record_size; } else { threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; } @@ -963,7 +970,11 @@ void intel_pmu_pebs_enable(struct perf_event *event) * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD. */ if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { - ds->pebs_event_reset[hwc->idx] = + unsigned int idx = hwc->idx; + + if (idx >= INTEL_PMC_IDX_FIXED) + idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED); + ds->pebs_event_reset[idx] = (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; } else { ds->pebs_event_reset[hwc->idx] = 0; @@ -1186,16 +1197,20 @@ static void setup_pebs_sample_data(struct perf_event *event, } /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happend between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + + /* * We use the interrupt regs as a base because the PEBS record does not * contain a full regs set, specifically it seems to lack segment * descriptors, which get used by things like user_mode(). * * In the simple case fix up only the IP for PERF_SAMPLE_IP. - * - * We must however always use BP,SP from iregs for the unwinder to stay - * sane; the record BP,SP can point into thin air when the record is - * from a previous PMI context or an (I)RET happend between the record - * and PMI. */ *regs = *iregs; @@ -1214,15 +1229,8 @@ static void setup_pebs_sample_data(struct perf_event *event, regs->si = pebs->si; regs->di = pebs->di; - /* - * Per the above; only set BP,SP if we don't need callchains. - * - * XXX: does this make sense? - */ - if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) { - regs->bp = pebs->bp; - regs->sp = pebs->sp; - } + regs->bp = pebs->bp; + regs->sp = pebs->sp; #ifndef CONFIG_X86_32 regs->r8 = pebs->r8; @@ -1484,9 +1492,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) struct debug_store *ds = cpuc->ds; struct perf_event *event; void *base, *at, *top; - short counts[MAX_PEBS_EVENTS] = {}; - short error[MAX_PEBS_EVENTS] = {}; - int bit, i; + short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + int bit, i, size; + u64 mask; if (!x86_pmu.pebs_active) return; @@ -1496,6 +1505,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) ds->pebs_index = ds->pebs_buffer_base; + mask = (1ULL << x86_pmu.max_pebs_events) - 1; + size = x86_pmu.max_pebs_events; + if (x86_pmu.flags & PMU_FL_PEBS_ALL) { + mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED; + size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed; + } + if (unlikely(base >= top)) { /* * The drain_pebs() could be called twice in a short period @@ -1505,7 +1521,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * update the event->count for this case. */ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, - x86_pmu.max_pebs_events) { + size) { event = cpuc->events[bit]; if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) intel_pmu_save_and_restart_reload(event, 0); @@ -1518,12 +1534,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) u64 pebs_status; pebs_status = p->status & cpuc->pebs_enabled; - pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + pebs_status &= mask; /* PEBS v3 has more accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) { for_each_set_bit(bit, (unsigned long *)&pebs_status, - x86_pmu.max_pebs_events) + size) counts[bit]++; continue; @@ -1571,7 +1587,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) counts[bit]++; } - for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { + for (bit = 0; bit < size; bit++) { if ((counts[bit] == 0) && (error[bit] == 0)) continue; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index cf372b90557e..f3e006bed9a7 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void) void intel_pmu_lbr_reset(void) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + if (!x86_pmu.lbr_nr) return; @@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void) intel_pmu_lbr_reset_32(); else intel_pmu_lbr_reset_64(); + + cpuc->last_task_ctx = NULL; + cpuc->last_log_id = 0; } /* @@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx) static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; unsigned lbr_idx, mask; u64 tos; @@ -344,9 +350,21 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) return; } - mask = x86_pmu.lbr_nr - 1; tos = task_ctx->tos; - for (i = 0; i < tos; i++) { + /* + * Does not restore the LBR registers, if + * - No one else touched them, and + * - Did not enter C6 + */ + if ((task_ctx == cpuc->last_task_ctx) && + (task_ctx->log_id == cpuc->last_log_id) && + rdlbr_from(tos)) { + task_ctx->lbr_stack_state = LBR_NONE; + return; + } + + mask = x86_pmu.lbr_nr - 1; + for (i = 0; i < task_ctx->valid_lbrs; i++) { lbr_idx = (tos - i) & mask; wrlbr_from(lbr_idx, task_ctx->lbr_from[i]); wrlbr_to (lbr_idx, task_ctx->lbr_to[i]); @@ -354,14 +372,24 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + + for (; i < x86_pmu.lbr_nr; i++) { + lbr_idx = (tos - i) & mask; + wrlbr_from(lbr_idx, 0); + wrlbr_to(lbr_idx, 0); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0); + } + wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; } static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); unsigned lbr_idx, mask; - u64 tos; + u64 tos, from; int i; if (task_ctx->lbr_callstack_users == 0) { @@ -371,15 +399,22 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) mask = x86_pmu.lbr_nr - 1; tos = intel_pmu_lbr_tos(); - for (i = 0; i < tos; i++) { + for (i = 0; i < x86_pmu.lbr_nr; i++) { lbr_idx = (tos - i) & mask; - task_ctx->lbr_from[i] = rdlbr_from(lbr_idx); + from = rdlbr_from(lbr_idx); + if (!from) + break; + task_ctx->lbr_from[i] = from; task_ctx->lbr_to[i] = rdlbr_to(lbr_idx); if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + task_ctx->valid_lbrs = i; task_ctx->tos = tos; task_ctx->lbr_stack_state = LBR_VALID; + + cpuc->last_task_ctx = task_ctx; + cpuc->last_log_id = ++task_ctx->log_id; } void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) @@ -531,7 +566,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) */ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { - bool need_info = false; + bool need_info = false, call_stack = false; unsigned long mask = x86_pmu.lbr_nr - 1; int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); @@ -542,7 +577,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) if (cpuc->lbr_sel) { need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO); if (cpuc->lbr_sel->config & LBR_CALL_STACK) - num = tos; + call_stack = true; } for (i = 0; i < num; i++) { @@ -555,6 +590,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) from = rdlbr_from(lbr_idx); to = rdlbr_to(lbr_idx); + /* + * Read LBR call stack entries + * until invalid entry (0s) is detected. + */ + if (call_stack && !from) + break; + if (lbr_format == LBR_FORMAT_INFO && need_info) { u64 info; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index c9e1e0bef3c3..e17ab885b1e9 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -28,7 +28,7 @@ #define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) #define UNCORE_PCI_DEV_IDX(data) (data & 0xff) #define UNCORE_EXTRA_PCI_DEV 0xff -#define UNCORE_EXTRA_PCI_DEV_MAX 3 +#define UNCORE_EXTRA_PCI_DEV_MAX 4 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 87dc0263a2e1..51d7c117e3c7 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void) enum { SNBEP_PCI_QPI_PORT0_FILTER, SNBEP_PCI_QPI_PORT1_FILTER, + BDX_PCI_QPI_PORT2_FILTER, HSWEP_PCI_PCU_3, }; @@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { }, { /* QPI Port 0 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), }, { /* QPI Port 1 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), }, { /* QPI Port 2 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + BDX_PCI_QPI_PORT2_FILTER), }, { /* PCU.3 (for Capability registers) */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 9f3711470ec1..156286335351 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -163,6 +163,7 @@ struct intel_excl_cntrs { unsigned core_id; /* per-core: core id */ }; +struct x86_perf_task_context; #define MAX_LBR_ENTRIES 32 enum { @@ -214,6 +215,8 @@ struct cpu_hw_events { struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; u64 br_sel; + struct x86_perf_task_context *last_task_ctx; + int last_log_id; /* * Intel host/guest exclude bits @@ -648,8 +651,10 @@ struct x86_perf_task_context { u64 lbr_to[MAX_LBR_ENTRIES]; u64 lbr_info[MAX_LBR_ENTRIES]; int tos; + int valid_lbrs; int lbr_callstack_users; int lbr_stack_state; + int log_id; }; #define x86_add_quirk(func_) \ @@ -668,6 +673,7 @@ do { \ #define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */ #define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ +#define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index b173d404e3df..b21ee65c4101 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1,2 +1,2 @@ -obj-y := hv_init.o mmu.o +obj-y := hv_init.o mmu.o nested.o obj-$(CONFIG_X86_64) += hv_apic.o diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 402338365651..5b0f613428c2 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -31,6 +31,8 @@ #include <asm/mshyperv.h> #include <asm/apic.h> +#include <asm/trace/hyperv.h> + static struct apic orig_apic; static u64 hv_apic_icr_read(void) @@ -99,6 +101,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) int nr_bank = 0; int ret = 1; + if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return false; + local_irq_save(flags); arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); @@ -130,10 +135,10 @@ ipi_mask_ex_done: static bool __send_ipi_mask(const struct cpumask *mask, int vector) { int cur_cpu, vcpu; - struct ipi_arg_non_ex **arg; - struct ipi_arg_non_ex *ipi_arg; + struct ipi_arg_non_ex ipi_arg; int ret = 1; - unsigned long flags; + + trace_hyperv_send_ipi_mask(mask, vector); if (cpumask_empty(mask)) return true; @@ -144,40 +149,43 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return false; - if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - return __send_ipi_mask_ex(mask, vector); - - local_irq_save(flags); - arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); - - ipi_arg = *arg; - if (unlikely(!ipi_arg)) - goto ipi_mask_done; - - ipi_arg->vector = vector; - ipi_arg->reserved = 0; - ipi_arg->cpu_mask = 0; + /* + * From the supplied CPU set we need to figure out if we can get away + * with cheaper HVCALL_SEND_IPI hypercall. This is possible when the + * highest VP number in the set is < 64. As VP numbers are usually in + * ascending order and match Linux CPU ids, here is an optimization: + * we check the VP number for the highest bit in the supplied set first + * so we can quickly find out if using HVCALL_SEND_IPI_EX hypercall is + * a must. We will also check all VP numbers when walking the supplied + * CPU set to remain correct in all cases. + */ + if (hv_cpu_number_to_vp_number(cpumask_last(mask)) >= 64) + goto do_ex_hypercall; + + ipi_arg.vector = vector; + ipi_arg.cpu_mask = 0; for_each_cpu(cur_cpu, mask) { vcpu = hv_cpu_number_to_vp_number(cur_cpu); if (vcpu == VP_INVAL) - goto ipi_mask_done; + return false; /* * This particular version of the IPI hypercall can * only target upto 64 CPUs. */ if (vcpu >= 64) - goto ipi_mask_done; + goto do_ex_hypercall; - __set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask); + __set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask); } - ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL); - -ipi_mask_done: - local_irq_restore(flags); + ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector, + ipi_arg.cpu_mask); return ((ret == 0) ? true : false); + +do_ex_hypercall: + return __send_ipi_mask_ex(mask, vector); } static bool __send_ipi_one(int cpu, int vector) @@ -233,10 +241,7 @@ static void hv_send_ipi_self(int vector) void __init hv_apic_init(void) { if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) { - if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pr_info("Hyper-V: Using ext hypercalls for IPI\n"); - else - pr_info("Hyper-V: Using IPI hypercalls\n"); + pr_info("Hyper-V: Using IPI hypercalls\n"); /* * Set the IPI entry points. */ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 1ff420217298..20c876c7c5bf 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -333,7 +333,7 @@ void __init hyperv_init(void) * Register Hyper-V specific clocksource. */ #ifdef CONFIG_HYPERV_TSCPAGE - if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) { + if (ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE) { union hv_x64_msr_hypercall_contents tsc_msr; tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL); @@ -362,7 +362,7 @@ register_msr_cs: */ hyperv_cs = &hyperv_cs_msr; - if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) + if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); return; @@ -426,6 +426,33 @@ void hyperv_report_panic(struct pt_regs *regs, long err) } EXPORT_SYMBOL_GPL(hyperv_report_panic); +/** + * hyperv_report_panic_msg - report panic message to Hyper-V + * @pa: physical address of the panic page containing the message + * @size: size of the message in the page + */ +void hyperv_report_panic_msg(phys_addr_t pa, size_t size) +{ + /* + * P3 to contain the physical address of the panic page & P4 to + * contain the size of the panic data in that page. Rest of the + * registers are no-op when the NOTIFY_MSG flag is set. + */ + wrmsrl(HV_X64_MSR_CRASH_P0, 0); + wrmsrl(HV_X64_MSR_CRASH_P1, 0); + wrmsrl(HV_X64_MSR_CRASH_P2, 0); + wrmsrl(HV_X64_MSR_CRASH_P3, pa); + wrmsrl(HV_X64_MSR_CRASH_P4, size); + + /* + * Let Hyper-V know there is crash data available along with + * the panic message. + */ + wrmsrl(HV_X64_MSR_CRASH_CTL, + (HV_CRASH_CTL_CRASH_NOTIFY | HV_CRASH_CTL_CRASH_NOTIFY_MSG)); +} +EXPORT_SYMBOL_GPL(hyperv_report_panic_msg); + bool hv_is_hyperv_initialized(void) { union hv_x64_msr_hypercall_contents hypercall_msr; diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index de27615c51ea..1147e1fed7ff 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -16,6 +16,8 @@ /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) +static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, + const struct flush_tlb_info *info); /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -93,10 +95,29 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (cpumask_equal(cpus, cpu_present_mask)) { flush->flags |= HV_FLUSH_ALL_PROCESSORS; } else { + /* + * From the supplied CPU set we need to figure out if we can get + * away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} + * hypercalls. This is possible when the highest VP number in + * the set is < 64. As VP numbers are usually in ascending order + * and match Linux CPU ids, here is an optimization: we check + * the VP number for the highest bit in the supplied set first + * so we can quickly find out if using *_EX hypercalls is a + * must. We will also check all VP numbers when walking the + * supplied CPU set to remain correct in all cases. + */ + if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64) + goto do_ex_hypercall; + for_each_cpu(cpu, cpus) { vcpu = hv_cpu_number_to_vp_number(cpu); - if (vcpu >= 64) + if (vcpu == VP_INVAL) { + local_irq_restore(flags); goto do_native; + } + + if (vcpu >= 64) + goto do_ex_hypercall; __set_bit(vcpu, (unsigned long *) &flush->processor_mask); @@ -123,7 +144,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST, gva_n, 0, flush, NULL); } + goto check_status; + +do_ex_hypercall: + status = hyperv_flush_tlb_others_ex(cpus, info); +check_status: local_irq_restore(flags); if (!(status & HV_HYPERCALL_RESULT_MASK)) @@ -132,35 +158,22 @@ do_native: native_flush_tlb_others(cpus, info); } -static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, - const struct flush_tlb_info *info) +static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, + const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; struct hv_tlb_flush_ex **flush_pcpu; struct hv_tlb_flush_ex *flush; - u64 status = U64_MAX; - unsigned long flags; + u64 status; - trace_hyperv_mmu_flush_tlb_others(cpus, info); - - if (!hv_hypercall_pg) - goto do_native; - - if (cpumask_empty(cpus)) - return; - - local_irq_save(flags); + if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return U64_MAX; flush_pcpu = (struct hv_tlb_flush_ex **) this_cpu_ptr(hyperv_pcpu_input_arg); flush = *flush_pcpu; - if (unlikely(!flush)) { - local_irq_restore(flags); - goto do_native; - } - if (info->mm) { /* * AddressSpace argument must match the CR3 with PCID bits @@ -176,15 +189,10 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->hv_vp_set.valid_bank_mask = 0; - if (!cpumask_equal(cpus, cpu_present_mask)) { - flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); - } - - if (!nr_bank) { - flush->hv_vp_set.format = HV_GENERIC_SET_ALL; - flush->flags |= HV_FLUSH_ALL_PROCESSORS; - } + flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); + if (nr_bank < 0) + return U64_MAX; /* * We can flush not more than max_gvas with one hypercall. Flush the @@ -213,12 +221,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, gva_n, nr_bank, flush, NULL); } - local_irq_restore(flags); - - if (!(status & HV_HYPERCALL_RESULT_MASK)) - return; -do_native: - native_flush_tlb_others(cpus, info); + return status; } void hyperv_setup_mmu_ops(void) @@ -226,11 +229,6 @@ void hyperv_setup_mmu_ops(void) if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)) return; - if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) { - pr_info("Using hypercall for remote TLB flush\n"); - pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others; - } else { - pr_info("Using ext hypercall for remote TLB flush\n"); - pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex; - } + pr_info("Using hypercall for remote TLB flush\n"); + pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others; } diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c new file mode 100644 index 000000000000..b8e60cc50461 --- /dev/null +++ b/arch/x86/hyperv/nested.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Hyper-V nested virtualization code. + * + * Copyright (C) 2018, Microsoft, Inc. + * + * Author : Lan Tianyu <Tianyu.Lan@microsoft.com> + */ + + +#include <linux/types.h> +#include <asm/hyperv-tlfs.h> +#include <asm/mshyperv.h> +#include <asm/tlbflush.h> + +#include <asm/trace/hyperv.h> + +int hyperv_flush_guest_mapping(u64 as) +{ + struct hv_guest_mapping_flush **flush_pcpu; + struct hv_guest_mapping_flush *flush; + u64 status; + unsigned long flags; + int ret = -ENOTSUPP; + + if (!hv_hypercall_pg) + goto fault; + + local_irq_save(flags); + + flush_pcpu = (struct hv_guest_mapping_flush **) + this_cpu_ptr(hyperv_pcpu_input_arg); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto fault; + } + + flush->address_space = as; + flush->flags = 0; + + status = hv_do_hypercall(HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE, + flush, NULL); + local_irq_restore(flags); + + if (!(status & HV_HYPERCALL_RESULT_MASK)) + ret = 0; + +fault: + trace_hyperv_nested_flush_guest_mapping(as, ret); + return ret; +} +EXPORT_SYMBOL_GPL(hyperv_flush_guest_mapping); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 74a9e06b6cfd..130e81e10fc7 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -10,6 +10,7 @@ #include <asm/fixmap.h> #include <asm/mpspec.h> #include <asm/msr.h> +#include <asm/hardirq.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -502,12 +503,19 @@ extern int default_check_phys_apicid_present(int phys_apicid); #endif /* CONFIG_X86_LOCAL_APIC */ +#ifdef CONFIG_SMP +bool apic_id_is_primary_thread(unsigned int id); +#else +static inline bool apic_id_is_primary_thread(unsigned int id) { return false; } +#endif + extern void irq_enter(void); extern void irq_exit(void); static inline void entering_irq(void) { irq_enter(); + kvm_set_cpu_l1tf_flush_l1d(); } static inline void entering_ack_irq(void) @@ -520,6 +528,7 @@ static inline void ipi_entering_ack_irq(void) { irq_enter(); ack_APIC_irq(); + kvm_set_cpu_l1tf_flush_l1d(); } static inline void exiting_irq(void) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 0db6bec95489..b143717b92b3 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); @@ -91,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" @@ -103,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" @@ -117,6 +120,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); @@ -130,6 +134,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); @@ -144,6 +149,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); @@ -173,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) return arch_atomic_add_return(-i, v); } -#define arch_atomic_inc_return(v) (arch_atomic_add_return(1, v)) -#define arch_atomic_dec_return(v) (arch_atomic_sub_return(1, v)) - static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); @@ -199,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n static inline int arch_atomic_xchg(atomic_t *v, int new) { - return xchg(&v->counter, new); + return arch_xchg(&v->counter, new); } static inline void arch_atomic_and(int i, atomic_t *v) @@ -253,27 +256,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v) return val; } -/** - * __arch_atomic_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns the old value of @v. - */ -static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 92212bf0484f..ef959f02d070 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_inc_return arch_atomic64_inc_return static inline long long arch_atomic64_dec_return(atomic64_t *v) { @@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_dec_return arch_atomic64_dec_return /** * arch_atomic64_add - add integer to atomic64 variable @@ -198,25 +200,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) } /** - * arch_atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer to type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v) -{ - return arch_atomic64_sub_return(i, v) == 0; -} - -/** * arch_atomic64_inc - increment atomic64 variable * @v: pointer to type atomic64_t * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, @@ -229,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, @@ -236,46 +226,6 @@ static inline void arch_atomic64_dec(atomic64_t *v) } /** - * arch_atomic64_dec_and_test - decrement and test - * @v: pointer to type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static inline int arch_atomic64_dec_and_test(atomic64_t *v) -{ - return arch_atomic64_dec_return(v) == 0; -} - -/** - * atomic64_inc_and_test - increment and test - * @v: pointer to type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_inc_and_test(atomic64_t *v) -{ - return arch_atomic64_inc_return(v) == 0; -} - -/** - * arch_atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer to type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static inline int arch_atomic64_add_negative(long long i, atomic64_t *v) -{ - return arch_atomic64_add_return(i, v) < 0; -} - -/** * arch_atomic64_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... @@ -295,7 +245,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } - +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -304,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 6106b59d3260..4343d9b4f30e 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); @@ -82,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" @@ -95,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" @@ -110,6 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); @@ -123,6 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); @@ -137,6 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); @@ -169,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v) return xadd(&v->counter, -i); } -#define arch_atomic64_inc_return(v) (arch_atomic64_add_return(1, (v))) -#define arch_atomic64_dec_return(v) (arch_atomic64_sub_return(1, (v))) - static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new) { return arch_cmpxchg(&v->counter, old, new); @@ -185,46 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l static inline long arch_atomic64_xchg(atomic64_t *v, long new) { - return xchg(&v->counter, new); -} - -/** - * arch_atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u) -{ - s64 c = arch_atomic64_read(v); - do { - if (unlikely(c == u)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); - return true; -} - -#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0) - -/* - * arch_atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) -{ - s64 dec, c = arch_atomic64_read(v); - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); - return dec; + return arch_xchg(&v->counter, new); } static inline void arch_atomic64_and(long i, atomic64_t *v) diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index e3efd8a06066..a55d79b233d3 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -75,7 +75,7 @@ extern void __add_wrong_size(void) * use "asm volatile" and "memory" clobbers to prevent gcc from moving * information around. */ -#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") +#define arch_xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") /* * Atomic compare and exchange. Compare OLD with MEM, if identical, diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index bfca3b346c74..072e5459fe2f 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -10,13 +10,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) #define arch_cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg((ptr), (o), (n)); \ + arch_cmpxchg((ptr), (o), (n)); \ }) #define arch_cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg_local((ptr), (o), (n)); \ + arch_cmpxchg_local((ptr), (o), (n)); \ }) #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 5701f5cecd31..89a048c2faec 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -219,6 +219,8 @@ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ +#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -229,7 +231,7 @@ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ - +#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -341,6 +343,7 @@ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ @@ -373,5 +376,6 @@ #define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index 0ab2ab27ad1f..b825cb201251 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -4,8 +4,8 @@ #include <linux/compiler.h> #include <linux/init.h> +#include <linux/io.h> -#include <asm/io.h> #include <asm/setup.h> static __always_inline __init void *dmi_alloc(unsigned len) diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 740a428acf1e..d9069bb26c7f 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -3,10 +3,12 @@ #define _ASM_X86_HARDIRQ_H #include <linux/threads.h> -#include <linux/irq.h> typedef struct { - unsigned int __softirq_pending; + u16 __softirq_pending; +#if IS_ENABLED(CONFIG_KVM_INTEL) + u8 kvm_cpu_l1tf_flush_l1d; +#endif unsigned int __nmi_count; /* arch dependent */ #ifdef CONFIG_X86_LOCAL_APIC unsigned int apic_timer_irqs; /* arch dependent */ @@ -58,4 +60,24 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu); extern u64 arch_irq_stat(void); #define arch_irq_stat arch_irq_stat + +#if IS_ENABLED(CONFIG_KVM_INTEL) +static inline void kvm_set_cpu_l1tf_flush_l1d(void) +{ + __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1); +} + +static inline void kvm_clear_cpu_l1tf_flush_l1d(void) +{ + __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 0); +} + +static inline bool kvm_get_cpu_l1tf_flush_l1d(void) +{ + return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d); +} +#else /* !IS_ENABLED(CONFIG_KVM_INTEL) */ +static inline void kvm_set_cpu_l1tf_flush_l1d(void) { } +#endif /* IS_ENABLED(CONFIG_KVM_INTEL) */ + #endif /* _ASM_X86_HARDIRQ_H */ diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index f59c39835a5a..a1f0e90d0818 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -49,11 +49,14 @@ static inline int hw_breakpoint_slots(int type) return HBP_NUM; } +struct perf_event_attr; struct perf_event; struct pmu; -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index b8c89265baf0..e977b6b3a538 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -35,9 +35,9 @@ /* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */ #define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0) /* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/ -#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1) +#define HV_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1) /* Partition reference TSC MSR is available */ -#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE (1 << 9) +#define HV_MSR_REFERENCE_TSC_AVAILABLE (1 << 9) /* A partition's reference time stamp counter (TSC) page */ #define HV_X64_MSR_REFERENCE_TSC 0x40000021 @@ -60,7 +60,7 @@ * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through * HV_X64_MSR_STIMER3_COUNT) available */ -#define HV_X64_MSR_SYNTIMER_AVAILABLE (1 << 3) +#define HV_MSR_SYNTIMER_AVAILABLE (1 << 3) /* * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR) * are available @@ -86,7 +86,7 @@ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10) /* stimer Direct Mode is available */ -#define HV_X64_STIMER_DIRECT_MODE_AVAILABLE (1 << 19) +#define HV_STIMER_DIRECT_MODE_AVAILABLE (1 << 19) /* * Feature identification: EBX indicates which flags were specified at @@ -160,9 +160,9 @@ #define HV_X64_RELAXED_TIMING_RECOMMENDED (1 << 5) /* - * Virtual APIC support + * Recommend not using Auto End-Of-Interrupt feature */ -#define HV_X64_DEPRECATING_AEOI_RECOMMENDED (1 << 9) +#define HV_DEPRECATING_AEOI_RECOMMENDED (1 << 9) /* * Recommend using cluster IPI hypercalls. @@ -176,9 +176,10 @@ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED (1 << 14) /* - * Crash notification flag. + * Crash notification flags. */ -#define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63) +#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62) +#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63) /* MSR used to identify the guest OS. */ #define HV_X64_MSR_GUEST_OS_ID 0x40000000 @@ -309,6 +310,7 @@ struct ms_hyperv_tsc_page { #define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 /* Nested features (CPUID 0x4000000A) EAX */ +#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) struct hv_reenlightenment_control { @@ -350,6 +352,7 @@ struct hv_tsc_emulation_status { #define HVCALL_SEND_IPI_EX 0x0015 #define HVCALL_POST_MESSAGE 0x005c #define HVCALL_SIGNAL_EVENT 0x005d +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 @@ -741,6 +744,12 @@ struct ipi_arg_ex { struct hv_vpset vp_set; }; +/* HvFlushGuestPhysicalAddressSpace hypercalls */ +struct hv_guest_mapping_flush { + u64 address_space; + u64 flags; +}; + /* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ struct hv_tlb_flush { u64 address_space; diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h index 5cdcdbd4d892..89789e8c80f6 100644 --- a/arch/x86/include/asm/i8259.h +++ b/arch/x86/include/asm/i8259.h @@ -3,6 +3,7 @@ #define _ASM_X86_I8259_H #include <linux/delay.h> +#include <asm/io.h> extern unsigned int cached_irq_mask; diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index cf090e584202..7ed08a7c3398 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -76,4 +76,17 @@ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ #define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */ +/* Useful macros */ +#define INTEL_CPU_FAM_ANY(_family, _model, _driver_data) \ +{ \ + .vendor = X86_VENDOR_INTEL, \ + .family = _family, \ + .model = _model, \ + .feature = X86_FEATURE_ANY, \ + .driver_data = (kernel_ulong_t)&_driver_data \ +} + +#define INTEL_CPU_FAM6(_model, _driver_data) \ + INTEL_CPU_FAM_ANY(6, INTEL_FAM6_##_model, _driver_data) + #endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index fe04491130ae..52f815a80539 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -80,35 +80,6 @@ enum intel_mid_cpu_type { extern enum intel_mid_cpu_type __intel_mid_cpu_chip; -/** - * struct intel_mid_ops - Interface between intel-mid & sub archs - * @arch_setup: arch_setup function to re-initialize platform - * structures (x86_init, x86_platform_init) - * - * This structure can be extended if any new interface is required - * between intel-mid & its sub arch files. - */ -struct intel_mid_ops { - void (*arch_setup)(void); -}; - -/* Helper API's for INTEL_MID_OPS_INIT */ -#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid) \ - [cpuid] = get_##cpuname##_ops - -/* Maximum number of CPU ops */ -#define MAX_CPU_OPS(a) (sizeof(a)/sizeof(void *)) - -/* - * For every new cpu addition, a weak get_<cpuname>_ops() function needs be - * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h. - */ -#define INTEL_MID_OPS_INIT { \ - DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL), \ - DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW), \ - DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER) \ -}; - #ifdef CONFIG_X86_INTEL_MID static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void) @@ -136,20 +107,6 @@ enum intel_mid_timer_options { extern enum intel_mid_timer_options intel_mid_timer_options; -/* - * Penwell uses spread spectrum clock, so the freq number is not exactly - * the same as reported by MSR based on SDM. - */ -#define FSB_FREQ_83SKU 83200 -#define FSB_FREQ_100SKU 99840 -#define FSB_FREQ_133SKU 133000 - -#define FSB_FREQ_167SKU 167000 -#define FSB_FREQ_200SKU 200000 -#define FSB_FREQ_267SKU 267000 -#define FSB_FREQ_333SKU 333000 -#define FSB_FREQ_400SKU 400000 - /* Bus Select SoC Fuse value */ #define BSEL_SOC_FUSE_MASK 0x7 /* FSB 133MHz */ diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h index 62a9f4966b42..ae26df1c2789 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -8,6 +8,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS 8 +#define MAX_FIXED_PEBS_EVENTS 3 /* * A debug store configuration. @@ -23,7 +24,7 @@ struct debug_store { u64 pebs_index; u64 pebs_absolute_maximum; u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; + u64 pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS]; } __aligned(PAGE_SIZE); DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c4fc17220df9..c14f2a74b2be 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -13,6 +13,8 @@ * Interrupt control: */ +/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ +extern inline unsigned long native_save_fl(void); extern inline unsigned long native_save_fl(void) { unsigned long flags; diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 367d99cff426..c8cec1b39b88 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -78,7 +78,7 @@ struct arch_specific_insn { * boostable = true: This instruction has been boosted: we have * added a relative jump after the instruction copy in insn, * so no single-step and fixup are needed (unless there's - * a post_handler or break_handler). + * a post_handler). */ bool boostable; bool if_modifier; @@ -111,9 +111,6 @@ struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_old_flags; unsigned long kprobe_saved_flags; - unsigned long *jprobe_saved_sp; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h deleted file mode 100644 index 46185263d9c2..000000000000 --- a/arch/x86/include/asm/kvm_guest.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_KVM_GUEST_H -#define _ASM_X86_KVM_GUEST_H - -int kvm_setup_vsyscall_timeinfo(void); - -#endif /* _ASM_X86_KVM_GUEST_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c13cd28d9d1b..00ddb0c9e612 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -17,6 +17,7 @@ #include <linux/tracepoint.h> #include <linux/cpumask.h> #include <linux/irq_work.h> +#include <linux/irq.h> #include <linux/kvm.h> #include <linux/kvm_para.h> @@ -54,6 +55,7 @@ #define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) #define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) #define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) +#define KVM_REQ_LOAD_CR3 KVM_ARCH_REQ(5) #define KVM_REQ_EVENT KVM_ARCH_REQ(6) #define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) @@ -75,13 +77,13 @@ #define KVM_REQ_HV_EXIT KVM_ARCH_REQ(21) #define KVM_REQ_HV_STIMER KVM_ARCH_REQ(22) #define KVM_REQ_LOAD_EOI_EXITMAP KVM_ARCH_REQ(23) +#define KVM_REQ_GET_VMCS12_PAGES KVM_ARCH_REQ(24) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) -#define CR3_PCID_INVD BIT_64(63) #define CR4_RESERVED_BITS \ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ @@ -325,6 +327,16 @@ struct rsvd_bits_validate { u64 bad_mt_xwr; }; +struct kvm_mmu_root_info { + gpa_t cr3; + hpa_t hpa; +}; + +#define KVM_MMU_ROOT_INFO_INVALID \ + ((struct kvm_mmu_root_info) { .cr3 = INVALID_PAGE, .hpa = INVALID_PAGE }) + +#define KVM_MMU_NUM_PREV_ROOTS 3 + /* * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit, * and 2-level 32-bit). The kvm_mmu structure abstracts the details of the @@ -344,7 +356,7 @@ struct kvm_mmu { struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); - void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva); + void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *pte); hpa_t root_hpa; @@ -353,6 +365,7 @@ struct kvm_mmu { u8 shadow_root_level; u8 ept_ad; bool direct_map; + struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS]; /* * Bitmap; bit set = permission fault @@ -713,6 +726,9 @@ struct kvm_vcpu_arch { /* be preempted when it's in kernel-mode(cpl=0) */ bool preempted_in_kernel; + + /* Flush the L1 Data cache for L1TF mitigation on VMENTER */ + bool l1tf_flush_l1d; }; struct kvm_lpage_info { @@ -881,6 +897,7 @@ struct kvm_vcpu_stat { u64 signal_exits; u64 irq_window_exits; u64 nmi_window_exits; + u64 l1d_flush; u64 halt_exits; u64 halt_successful_poll; u64 halt_attempted_poll; @@ -973,6 +990,15 @@ struct kvm_x86_ops { void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); + int (*tlb_remote_flush)(struct kvm *kvm); + + /* + * Flush any TLB entries associated with the given GVA. + * Does not need to flush GPA->HPA mappings. + * Can potentially get non-canonical addresses through INVLPGs, which + * the implementation may choose to ignore if appropriate. + */ + void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr); void (*run)(struct kvm_vcpu *vcpu); int (*handle_exit)(struct kvm_vcpu *vcpu); @@ -1085,6 +1111,14 @@ struct kvm_x86_ops { void (*setup_mce)(struct kvm_vcpu *vcpu); + int (*get_nested_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + unsigned user_data_size); + int (*set_nested_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + struct kvm_nested_state *kvm_state); + void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); + int (*smi_allowed)(struct kvm_vcpu *vcpu); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); @@ -1117,6 +1151,16 @@ static inline void kvm_arch_free_vm(struct kvm *kvm) return kvm_x86_ops->vm_free(kvm); } +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB +static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) +{ + if (kvm_x86_ops->tlb_remote_flush && + !kvm_x86_ops->tlb_remote_flush(kvm)) + return 0; + else + return -ENOTSUPP; +} + int kvm_mmu_module_init(void); void kvm_mmu_module_exit(void); @@ -1268,6 +1312,10 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state, return !!(*irq_state); } +#define KVM_MMU_ROOT_CURRENT BIT(0) +#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) +#define KVM_MMU_ROOTS_ALL (~0UL) + int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level); void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); @@ -1279,7 +1327,7 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); -void kvm_mmu_free_roots(struct kvm_vcpu *vcpu); +void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free); gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, @@ -1298,7 +1346,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); -void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu); +void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); +void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush); void kvm_enable_tdp(void); void kvm_disable_tdp(void); @@ -1413,6 +1462,11 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); +int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, + unsigned long ipi_bitmap_high, int min, + unsigned long icr, int op_64_bit); + +u64 kvm_get_arch_capabilities(void); void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 3aea2658323a..4c723632c036 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,7 +7,6 @@ #include <uapi/asm/kvm_para.h> extern void kvmclock_init(void); -extern int kvm_register_clock(char *txt); #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index bbc796eb0a3b..eeeb9289c764 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -71,12 +71,7 @@ struct ldt_struct { static inline void *ldt_slot_va(int slot) { -#ifdef CONFIG_X86_64 return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); -#else - BUG(); - return (void *)fix_to_virt(FIX_HOLE); -#endif } /* diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5a7375ed5f7c..f37704497d8f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -76,8 +76,10 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) } } -#define hv_init_timer(timer, tick) wrmsrl(timer, tick) -#define hv_init_timer_config(config, val) wrmsrl(config, val) +#define hv_init_timer(timer, tick) \ + wrmsrl(HV_X64_MSR_STIMER0_COUNT + (2*timer), tick) +#define hv_init_timer_config(timer, val) \ + wrmsrl(HV_X64_MSR_STIMER0_CONFIG + (2*timer), val) #define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val) #define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val) @@ -90,8 +92,13 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) #define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index) -#define hv_get_synint_state(int_num, val) rdmsrl(int_num, val) -#define hv_set_synint_state(int_num, val) wrmsrl(int_num, val) +#define hv_get_synint_state(int_num, val) \ + rdmsrl(HV_X64_MSR_SINT0 + int_num, val) +#define hv_set_synint_state(int_num, val) \ + wrmsrl(HV_X64_MSR_SINT0 + int_num, val) + +#define hv_get_crash_ctl(val) \ + rdmsrl(HV_X64_MSR_CRASH_CTL, val) void hyperv_callback_vector(void); void hyperv_reenlightenment_vector(void); @@ -194,6 +201,40 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) return hv_status; } +/* Fast hypercall with 16 bytes of input */ +static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) +{ + u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; + +#ifdef CONFIG_X86_64 + { + __asm__ __volatile__("mov %4, %%r8\n" + CALL_NOSPEC + : "=a" (hv_status), ASM_CALL_CONSTRAINT, + "+c" (control), "+d" (input1) + : "r" (input2), + THUNK_TARGET(hv_hypercall_pg) + : "cc", "r8", "r9", "r10", "r11"); + } +#else + { + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + u32 input2_hi = upper_32_bits(input2); + u32 input2_lo = lower_32_bits(input2); + + __asm__ __volatile__ (CALL_NOSPEC + : "=A"(hv_status), + "+c"(input1_lo), ASM_CALL_CONSTRAINT + : "A" (control), "b" (input1_hi), + "D"(input2_hi), "S"(input2_lo), + THUNK_TARGET(hv_hypercall_pg) + : "cc"); + } +#endif + return hv_status; +} + /* * Rep hypercalls. Callers of this functions are supposed to ensure that * rep_count and varhead_size comply with Hyper-V hypercall definition. @@ -298,6 +339,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, void __init hyperv_init(void); void hyperv_setup_mmu_ops(void); void hyperv_report_panic(struct pt_regs *regs, long err); +void hyperv_report_panic_msg(phys_addr_t pa, size_t size); bool hv_is_hyperv_initialized(void); void hyperv_cleanup(void); @@ -305,6 +347,7 @@ void hyperv_reenlightenment_intr(struct pt_regs *regs); void set_hv_tscchange_cb(void (*cb)(void)); void clear_hv_tscchange_cb(void); void hyperv_stop_tsc_emulation(void); +int hyperv_flush_guest_mapping(u64 as); #ifdef CONFIG_X86_64 void hv_apic_init(void); @@ -324,6 +367,7 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) { return NULL; } +static inline int hyperv_flush_guest_mapping(u64 as) { return -1; } #endif /* CONFIG_HYPERV */ #ifdef CONFIG_HYPERV_TSCPAGE diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 68b2c3150de1..4731f0cf97c5 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -70,12 +70,19 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ +#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH (1 << 3) /* Skip L1D flush on vmentry */ #define ARCH_CAP_SSB_NO (1 << 4) /* * Not susceptible to Speculative Store Bypass * attack, so no Speculative Store Bypass * control required. */ +#define MSR_IA32_FLUSH_CMD 0x0000010b +#define L1D_FLUSH (1 << 0) /* + * Writeback and invalidate the + * L1 data cache. + */ + #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f6f6c63da62f..fd2a8c1b88bc 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -214,7 +214,7 @@ enum spectre_v2_mitigation { SPECTRE_V2_RETPOLINE_MINIMAL_AMD, SPECTRE_V2_RETPOLINE_GENERIC, SPECTRE_V2_RETPOLINE_AMD, - SPECTRE_V2_IBRS, + SPECTRE_V2_IBRS_ENHANCED, }; /* The Speculative Store Bypass disable variants */ diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index 9c9dc579bd7d..46f516dd80ce 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -88,6 +88,7 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned end:1; } __packed; /* @@ -101,6 +102,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 end; }; #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index aa30c3241ea7..0d5c739eebd7 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -29,8 +29,13 @@ #define N_EXCEPTION_STACKS 1 #ifdef CONFIG_X86_PAE -/* 44=32+12, the limit we can fit into an unsigned long pfn */ -#define __PHYSICAL_MASK_SHIFT 44 +/* + * This is beyond the 44 bit limit imposed by the 32bit long pfns, + * but we need the full mask to make sure inverted PROT_NONE + * entries have all the host bits set in a guest. + * The real limit is still 44 bits. + */ +#define __PHYSICAL_MASK_SHIFT 52 #define __VIRTUAL_MASK_SHIFT 32 #else /* !CONFIG_X86_PAE */ diff --git a/arch/x86/include/asm/pci-direct.h b/arch/x86/include/asm/pci-direct.h index e1084f71a295..94597a3cf3d0 100644 --- a/arch/x86/include/asm/pci-direct.h +++ b/arch/x86/include/asm/pci-direct.h @@ -15,8 +15,4 @@ extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val); extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val); extern int early_pci_allowed(void); - -extern unsigned int pci_early_dump_regs; -extern void early_dump_pci_device(u8 bus, u8 slot, u8 func); -extern void early_dump_pci_devices(void); #endif /* _ASM_X86_PCI_DIRECT_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a06b07399d17..e9202a0de8f0 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -450,9 +450,10 @@ do { \ bool __ret; \ typeof(pcp1) __o1 = (o1), __n1 = (n1); \ typeof(pcp2) __o2 = (o2), __n2 = (n2); \ - asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \ - : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \ - : "b" (__n1), "c" (__n2), "a" (__o1)); \ + asm volatile("cmpxchg8b "__percpu_arg(1) \ + CC_SET(z) \ + : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \ + : "b" (__n1), "c" (__n2)); \ __ret; \ }) diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 685ffe8a0eaf..24c6cf5f16b7 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -19,6 +19,9 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd); +#endif *pmdp = pmd; } @@ -58,6 +61,9 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp) #ifdef CONFIG_SMP static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0)); +#endif return __pmd(xchg((pmdval_t *)xp, 0)); } #else @@ -67,6 +73,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #ifdef CONFIG_SMP static inline pud_t native_pudp_get_and_clear(pud_t *xp) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0)); +#endif return __pud(xchg((pudval_t *)xp, 0)); } #else @@ -95,4 +104,21 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi #define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low }) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) +/* No inverted PFNs on 2 level page tables */ + +static inline u64 protnone_mask(u64 val) +{ + return 0; +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) +{ + return val; +} + +static inline bool __pte_needs_invert(u64 val) +{ + return false; +} + #endif /* _ASM_X86_PGTABLE_2LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h index f982ef808e7e..6deb6cd236e3 100644 --- a/arch/x86/include/asm/pgtable-2level_types.h +++ b/arch/x86/include/asm/pgtable-2level_types.h @@ -35,4 +35,7 @@ typedef union { #define PTRS_PER_PTE 1024 +/* This covers all VMSPLIT_* and VMSPLIT_*_OPT variants */ +#define PGD_KERNEL_START (CONFIG_PAGE_OFFSET >> PGDIR_SHIFT) + #endif /* _ASM_X86_PGTABLE_2LEVEL_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index f24df59c40b2..a564084c6141 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -98,6 +98,9 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) static inline void native_set_pud(pud_t *pudp, pud_t pud) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd); +#endif set_64bit((unsigned long long *)(pudp), native_pud_val(pud)); } @@ -229,6 +232,10 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) { union split_pud res, *orig = (union split_pud *)pudp; +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pti_set_user_pgtbl(&pudp->p4d.pgd, __pgd(0)); +#endif + /* xchg acts as a barrier before setting of the high bits */ res.pud_low = xchg(&orig->pud_low, 0); res.pud_high = orig->pud_high; @@ -241,12 +248,43 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) #endif /* Encode and de-code a swap entry */ +#define SWP_TYPE_BITS 5 + +#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) + +/* We always extract/encode the offset by shifting it all the way up, and then down again */ +#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS) + #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) #define __swp_type(x) (((x).val) & 0x1f) #define __swp_offset(x) ((x).val >> 5) #define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5}) -#define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) -#define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } }) + +/* + * Normally, __swp_entry() converts from arch-independent swp_entry_t to + * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result + * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the + * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to + * __swp_entry_to_pte() through the following helper macro based on 64bit + * __swp_entry(). + */ +#define __swp_pteval_entry(type, offset) ((pteval_t) { \ + (~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ + | ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) }) + +#define __swp_entry_to_pte(x) ((pte_t){ .pte = \ + __swp_pteval_entry(__swp_type(x), __swp_offset(x)) }) +/* + * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent + * swp_entry_t, but also has to convert it from 64bit to the 32bit + * intermediate representation, using the following macros based on 64bit + * __swp_type() and __swp_offset(). + */ +#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS))) +#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)) + +#define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \ + __pteval_swp_offset(pte))) #define gup_get_pte gup_get_pte /* @@ -295,4 +333,6 @@ static inline pte_t gup_get_pte(pte_t *ptep) return pte; } +#include <asm/pgtable-invert.h> + #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index 6a59a6d0cc50..858358a82b14 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -21,9 +21,10 @@ typedef union { #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_PARAVIRT -#define SHARED_KERNEL_PMD (pv_info.shared_kernel_pmd) +#define SHARED_KERNEL_PMD ((!static_cpu_has(X86_FEATURE_PTI) && \ + (pv_info.shared_kernel_pmd))) #else -#define SHARED_KERNEL_PMD 1 +#define SHARED_KERNEL_PMD (!static_cpu_has(X86_FEATURE_PTI)) #endif /* @@ -45,5 +46,6 @@ typedef union { #define PTRS_PER_PTE 512 #define MAX_POSSIBLE_PHYSMEM_BITS 36 +#define PGD_KERNEL_START (CONFIG_PAGE_OFFSET >> PGDIR_SHIFT) #endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h new file mode 100644 index 000000000000..a0c1525f1b6f --- /dev/null +++ b/arch/x86/include/asm/pgtable-invert.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_PGTABLE_INVERT_H +#define _ASM_PGTABLE_INVERT_H 1 + +#ifndef __ASSEMBLY__ + +/* + * A clear pte value is special, and doesn't get inverted. + * + * Note that even users that only pass a pgprot_t (rather + * than a full pte) won't trigger the special zero case, + * because even PAGE_NONE has _PAGE_PROTNONE | _PAGE_ACCESSED + * set. So the all zero case really is limited to just the + * cleared page table entry case. + */ +static inline bool __pte_needs_invert(u64 val) +{ + return val && !(val & _PAGE_PRESENT); +} + +/* Get a mask to xor with the page table entry to get the correct pfn. */ +static inline u64 protnone_mask(u64 val) +{ + return __pte_needs_invert(val) ? ~0ull : 0; +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) +{ + /* + * When a PTE transitions from NONE to !NONE or vice-versa + * invert the PFN part to stop speculation. + * pte_pfn undoes this when needed. + */ + if (__pte_needs_invert(oldval) != __pte_needs_invert(val)) + val = (val & ~mask) | (~val & mask); + return val; +} + +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5715647fc4fe..e4ffa565a69f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -30,11 +30,14 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user); void ptdump_walk_pgd_level_checkwx(void); +void ptdump_walk_user_pgd_level_checkwx(void); #ifdef CONFIG_DEBUG_WX -#define debug_checkwx() ptdump_walk_pgd_level_checkwx() +#define debug_checkwx() ptdump_walk_pgd_level_checkwx() +#define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else -#define debug_checkwx() do { } while (0) +#define debug_checkwx() do { } while (0) +#define debug_checkwx_user() do { } while (0) #endif /* @@ -185,19 +188,29 @@ static inline int pte_special(pte_t pte) return pte_flags(pte) & _PAGE_SPECIAL; } +/* Entries that were set to PROT_NONE are inverted */ + +static inline u64 protnone_mask(u64 val); + static inline unsigned long pte_pfn(pte_t pte) { - return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT; + phys_addr_t pfn = pte_val(pte); + pfn ^= protnone_mask(pfn); + return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { - return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; + phys_addr_t pfn = pmd_val(pmd); + pfn ^= protnone_mask(pfn); + return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } static inline unsigned long pud_pfn(pud_t pud) { - return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT; + phys_addr_t pfn = pud_val(pud); + pfn ^= protnone_mask(pfn); + return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) @@ -400,11 +413,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_RW); } -static inline pmd_t pmd_mknotpresent(pmd_t pmd) -{ - return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE); -} - static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); @@ -459,11 +467,6 @@ static inline pud_t pud_mkwrite(pud_t pud) return pud_set_flags(pud, _PAGE_RW); } -static inline pud_t pud_mknotpresent(pud_t pud) -{ - return pud_clear_flags(pud, _PAGE_PRESENT | _PAGE_PROTNONE); -} - #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { @@ -545,25 +548,45 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot) static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { - return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PTE_PFN_MASK; + return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PMD_PAGE_MASK; + return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { - return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PUD_PAGE_MASK; + return __pud(pfn | check_pgprot(pgprot)); +} + +static inline pmd_t pmd_mknotpresent(pmd_t pmd) +{ + return pfn_pmd(pmd_pfn(pmd), + __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); +} + +static inline pud_t pud_mknotpresent(pud_t pud) +{ + return pfn_pud(pud_pfn(pud), + __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - pteval_t val = pte_val(pte); + pteval_t val = pte_val(pte), oldval = val; /* * Chop off the NX bit (if present), and add the NX portion of @@ -571,17 +594,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; - + val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); return __pte(val); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmdval_t val = pmd_val(pmd); + pmdval_t val = pmd_val(pmd), oldval = val; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; - + val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); return __pmd(val); } @@ -640,8 +663,31 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); + +/* + * Take a PGD location (pgdp) and a pgd value that needs to be set there. + * Populates the user and returns the resulting PGD that must be set in + * the kernel copy of the page tables. + */ +static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) +{ + if (!static_cpu_has(X86_FEATURE_PTI)) + return pgd; + return __pti_set_user_pgtbl(pgdp, pgd); +} +#else /* CONFIG_PAGE_TABLE_ISOLATION */ +static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) +{ + return pgd; +} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ + #endif /* __ASSEMBLY__ */ + #ifdef CONFIG_X86_32 # include <asm/pgtable_32.h> #else @@ -1154,6 +1200,70 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, } } #endif +/* + * Page table pages are page-aligned. The lower half of the top + * level is used for userspace and the top half for the kernel. + * + * Returns true for parts of the PGD that map userspace and + * false for the parts that map the kernel. + */ +static inline bool pgdp_maps_userspace(void *__ptr) +{ + unsigned long ptr = (unsigned long)__ptr; + + return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); +} + +static inline int pgd_large(pgd_t pgd) { return 0; } + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages + * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and + * the user one is in the last 4k. To switch between them, you + * just need to flip the 12th bit in their addresses. + */ +#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT + +/* + * This generates better code than the inline assembly in + * __set_bit(). + */ +static inline void *ptr_set_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr |= BIT(bit); + return (void *)__ptr; +} +static inline void *ptr_clear_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr &= ~BIT(bit); + return (void *)__ptr; +} + +static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) +{ + return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) +{ + return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) +{ + return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) +{ + return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); @@ -1320,6 +1430,14 @@ static inline bool pud_access_permitted(pud_t pud, bool write) return __pte_access_permitted(pud_val(pud), write); } +#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 +extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); + +static inline bool arch_has_pfn_modify_check(void) +{ + return boot_cpu_has_bug(X86_BUG_L1TF); +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 88a056b01db4..b3ec519e3982 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -34,8 +34,6 @@ static inline void check_pgt_cache(void) { } void paging_init(void); void sync_initial_page_table(void); -static inline int pgd_large(pgd_t pgd) { return 0; } - /* * Define this if things work differently on an i386 and an i486: * it will (on an i486) warn about kernel memory accesses that are diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index d9a001a4a872..b0bc0fff5f1f 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -50,13 +50,18 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ & PMD_MASK) -#define PKMAP_BASE \ +#define LDT_BASE_ADDR \ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) +#define LDT_END_ADDR (LDT_BASE_ADDR + PMD_SIZE) + +#define PKMAP_BASE \ + ((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK) + #ifdef CONFIG_HIGHMEM # define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) #else -# define VMALLOC_END (CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE) +# define VMALLOC_END (LDT_BASE_ADDR - 2 * PAGE_SIZE) #endif #define MODULES_VADDR VMALLOC_START diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 3c5385f9a88f..f773d5e6c8cc 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -132,90 +132,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp) #endif } -#ifdef CONFIG_PAGE_TABLE_ISOLATION -/* - * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages - * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and - * the user one is in the last 4k. To switch between them, you - * just need to flip the 12th bit in their addresses. - */ -#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT - -/* - * This generates better code than the inline assembly in - * __set_bit(). - */ -static inline void *ptr_set_bit(void *ptr, int bit) -{ - unsigned long __ptr = (unsigned long)ptr; - - __ptr |= BIT(bit); - return (void *)__ptr; -} -static inline void *ptr_clear_bit(void *ptr, int bit) -{ - unsigned long __ptr = (unsigned long)ptr; - - __ptr &= ~BIT(bit); - return (void *)__ptr; -} - -static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) -{ - return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); -} - -static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) -{ - return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); -} - -static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) -{ - return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); -} - -static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) -{ - return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); -} -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ - -/* - * Page table pages are page-aligned. The lower half of the top - * level is used for userspace and the top half for the kernel. - * - * Returns true for parts of the PGD that map userspace and - * false for the parts that map the kernel. - */ -static inline bool pgdp_maps_userspace(void *__ptr) -{ - unsigned long ptr = (unsigned long)__ptr; - - return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2); -} - -#ifdef CONFIG_PAGE_TABLE_ISOLATION -pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd); - -/* - * Take a PGD location (pgdp) and a pgd value that needs to be set there. - * Populates the user and returns the resulting PGD that must be set in - * the kernel copy of the page tables. - */ -static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) -{ - if (!static_cpu_has(X86_FEATURE_PTI)) - return pgd; - return __pti_set_user_pgd(pgdp, pgd); -} -#else -static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) -{ - return pgd; -} -#endif - static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; @@ -226,7 +142,7 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) } pgd = native_make_pgd(native_p4d_val(p4d)); - pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd); + pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); *p4dp = native_make_p4d(native_pgd_val(pgd)); } @@ -237,7 +153,7 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pti_set_user_pgd(pgdp, pgd); + *pgdp = pti_set_user_pgtbl(pgdp, pgd); } static inline void native_pgd_clear(pgd_t *pgd) @@ -255,7 +171,6 @@ extern void sync_global_pgds(unsigned long start, unsigned long end); /* * Level 4 access. */ -static inline int pgd_large(pgd_t pgd) { return 0; } #define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE) /* PUD - Level3 access */ @@ -273,7 +188,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names - * | OFFSET (14->63) | TYPE (9-13) |0|0|X|X| X| X|X|SD|0| <- swp entry + * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|X|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above @@ -286,20 +201,34 @@ static inline int pgd_large(pgd_t pgd) { return 0; } * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. + * + * The offset is inverted by a binary not operation to make the high + * physical bits set. */ -#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) -#define SWP_TYPE_BITS 5 -/* Place the offset above the type: */ -#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS) +#define SWP_TYPE_BITS 5 + +#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) + +/* We always extract/encode the offset by shifting it all the way up, and then down again */ +#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) -#define __swp_type(x) (((x).val >> (SWP_TYPE_FIRST_BIT)) \ - & ((1U << SWP_TYPE_BITS) - 1)) -#define __swp_offset(x) ((x).val >> SWP_OFFSET_FIRST_BIT) -#define __swp_entry(type, offset) ((swp_entry_t) { \ - ((type) << (SWP_TYPE_FIRST_BIT)) \ - | ((offset) << SWP_OFFSET_FIRST_BIT) }) +/* Extract the high bits for type */ +#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) + +/* Shift up (to get rid of type), then down to get value */ +#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) + +/* + * Shift the offset up "too far" by TYPE bits, then down again + * The offset is inverted by a binary not operation to make the high + * physical bits set. + */ +#define __swp_entry(type, offset) ((swp_entry_t) { \ + (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ + | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) + #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) @@ -343,5 +272,7 @@ static inline bool gup_fast_permitted(unsigned long start, int nr_pages, return true; } +#include <asm/pgtable-invert.h> + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 054765ab2da2..04edd2d58211 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -115,6 +115,7 @@ extern unsigned int ptrs_per_p4d; #define LDT_PGD_ENTRY_L5 -112UL #define LDT_PGD_ENTRY (pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) +#define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) #define __VMALLOC_BASE_L4 0xffffc90000000000UL #define __VMALLOC_BASE_L5 0xffa0000000000000UL @@ -153,4 +154,6 @@ extern unsigned int ptrs_per_p4d; #define EARLY_DYNAMIC_PAGE_TABLES 64 +#define PGD_KERNEL_START ((PAGE_SIZE / 2) / sizeof(pgd_t)) + #endif /* _ASM_X86_PGTABLE_64_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 99fff853c944..b64acb08a62b 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -50,6 +50,7 @@ #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) #define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) #define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2) +#define _PAGE_SOFTW3 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW3) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) @@ -266,14 +267,37 @@ typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; typedef struct { pgdval_t pgd; } pgd_t; +#ifdef CONFIG_X86_PAE + +/* + * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't + * use it here. + */ + +#define PGD_PAE_PAGE_MASK ((signed long)PAGE_MASK) +#define PGD_PAE_PHYS_MASK (((1ULL << __PHYSICAL_MASK_SHIFT)-1) & PGD_PAE_PAGE_MASK) + +/* + * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries. + * All other bits are Reserved MBZ + */ +#define PGD_ALLOWED_BITS (PGD_PAE_PHYS_MASK | _PAGE_PRESENT | \ + _PAGE_PWT | _PAGE_PCD | \ + _PAGE_SOFTW1 | _PAGE_SOFTW2 | _PAGE_SOFTW3) + +#else +/* No need to mask any bits for !PAE */ +#define PGD_ALLOWED_BITS (~0ULL) +#endif + static inline pgd_t native_make_pgd(pgdval_t val) { - return (pgd_t) { val }; + return (pgd_t) { val & PGD_ALLOWED_BITS }; } static inline pgdval_t native_pgd_val(pgd_t pgd) { - return pgd.pgd; + return pgd.pgd & PGD_ALLOWED_BITS; } static inline pgdval_t pgd_flags(pgd_t pgd) diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 625a52a5594f..02c2cbda4a74 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -39,10 +39,6 @@ #define CR3_PCID_MASK 0xFFFull #define CR3_NOFLUSH BIT_ULL(63) -#ifdef CONFIG_PAGE_TABLE_ISOLATION -# define X86_CR3_PTI_PCID_USER_BIT 11 -#endif - #else /* * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save @@ -53,4 +49,8 @@ #define CR3_NOFLUSH 0 #endif +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define X86_CR3_PTI_PCID_USER_BIT 11 +#endif + #endif /* _ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index cfd29ee8c3da..682286aca881 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -181,6 +181,11 @@ extern const struct seq_operations cpuinfo_op; extern void cpu_detect(struct cpuinfo_x86 *c); +static inline unsigned long l1tf_pfn_limit(void) +{ + return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1; +} + extern void early_cpu_init(void); extern void identify_boot_cpu(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); @@ -966,6 +971,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) extern unsigned long arch_align_stack(unsigned long sp); extern void free_init_pages(char *what, unsigned long begin, unsigned long end); +extern void free_kernel_image_pages(void *begin, void *end); void default_idle(void); #ifdef CONFIG_XEN @@ -977,4 +983,16 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); void microcode_check(void); + +enum l1tf_mitigations { + L1TF_MITIGATION_OFF, + L1TF_MITIGATION_FLUSH_NOWARN, + L1TF_MITIGATION_FLUSH, + L1TF_MITIGATION_FLUSH_NOSMT, + L1TF_MITIGATION_FULL, + L1TF_MITIGATION_FULL_FORCE +}; + +extern enum l1tf_mitigations l1tf_mitigation; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h index 38a17f1d5c9d..5df09a0b80b8 100644 --- a/arch/x86/include/asm/pti.h +++ b/arch/x86/include/asm/pti.h @@ -6,10 +6,9 @@ #ifdef CONFIG_PAGE_TABLE_ISOLATION extern void pti_init(void); extern void pti_check_boottime_disable(void); -extern void pti_clone_kernel_text(void); +extern void pti_finalize(void); #else static inline void pti_check_boottime_disable(void) { } -static inline void pti_clone_kernel_text(void) { } #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 9ef5ee03d2d7..159622ee0674 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -43,7 +43,7 @@ asm (".pushsection .text;" "push %rdx;" "mov $0x1,%eax;" "xor %edx,%edx;" - "lock cmpxchg %dl,(%rdi);" + LOCK_PREFIX "cmpxchg %dl,(%rdi);" "cmp $0x1,%al;" "jne .slowpath;" "pop %rdx;" diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4cf11d88d3b3..19b90521954c 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -5,6 +5,7 @@ * PaX/grsecurity. */ #include <linux/refcount.h> +#include <asm/bug.h> /* * This is the first portion of the refcount error handling, which lives in diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 5c019d23d06b..4a911a382ade 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -7,6 +7,7 @@ extern char __brk_base[], __brk_limit[]; extern struct exception_table_entry __stop___ex_table[]; +extern char __end_rodata_aligned[]; #if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index bd090367236c..34cffcef7375 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -46,6 +46,7 @@ int set_memory_np(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); +int set_memory_np_noalias(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); int set_memory_array_wc(unsigned long *addr, int addrinarray); diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index eb5f7999a893..36bd243843d6 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -87,15 +87,25 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread) #endif /* This is used when switching tasks or entering/exiting vm86 mode. */ -static inline void update_sp0(struct task_struct *task) +static inline void update_task_stack(struct task_struct *task) { - /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */ + /* sp0 always points to the entry trampoline stack, which is constant: */ #ifdef CONFIG_X86_32 - load_sp0(task->thread.sp0); + if (static_cpu_has(X86_FEATURE_XENPV)) + load_sp0(task->thread.sp0); + else + this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); #else + /* + * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That + * doesn't work on x86-32 because sp1 and + * cpu_current_top_of_stack have different values (because of + * the non-zero stack-padding on 32bit). + */ if (static_cpu_has(X86_FEATURE_XENPV)) load_sp0(task_top_of_stack(task)); #endif + } #endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 2ecd34e2d46c..e85ff65c43c3 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -37,5 +37,6 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len); extern void *text_poke(void *addr, const void *opcode, size_t len); extern int poke_int3_handler(struct pt_regs *regs); extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); +extern int after_bootmem; #endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6690cd3fc8b1..511bf5fae8b8 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -148,22 +148,6 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) #define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif -static inline bool tlb_defer_switch_to_init_mm(void) -{ - /* - * If we have PCID, then switching to init_mm is reasonably - * fast. If we don't have PCID, then switching to init_mm is - * quite slow, so we try to defer it in the hopes that we can - * avoid it entirely. The latter approach runs the risk of - * receiving otherwise unnecessary IPIs. - * - * This choice is just a heuristic. The tlb code can handle this - * function returning true or false regardless of whether we have - * PCID. - */ - return !static_cpu_has(X86_FEATURE_PCID); -} - struct tlb_context { u64 ctx_id; u64 tlb_gen; @@ -554,4 +538,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); native_flush_tlb_others(mask, info) #endif +extern void tlb_flush_remove_tables(struct mm_struct *mm); +extern void tlb_flush_remove_tables_local(void *arg); + +#define HAVE_TLB_FLUSH_REMOVE_TABLES + #endif /* _ASM_X86_TLBFLUSH_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index c1d2a9892352..453cf38a1c33 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -123,13 +123,17 @@ static inline int topology_max_smt_threads(void) } int topology_update_package_map(unsigned int apicid, unsigned int cpu); -extern int topology_phys_to_logical_pkg(unsigned int pkg); +int topology_phys_to_logical_pkg(unsigned int pkg); +bool topology_is_primary_thread(unsigned int cpu); +bool topology_smt_supported(void); #else #define topology_max_packages() (1) static inline int topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; } static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } static inline int topology_max_smt_threads(void) { return 1; } +static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } +static inline bool topology_smt_supported(void) { return false; } #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h index 4253bca99989..2e6245a023ef 100644 --- a/arch/x86/include/asm/trace/hyperv.h +++ b/arch/x86/include/asm/trace/hyperv.h @@ -28,6 +28,35 @@ TRACE_EVENT(hyperv_mmu_flush_tlb_others, __entry->addr, __entry->end) ); +TRACE_EVENT(hyperv_nested_flush_guest_mapping, + TP_PROTO(u64 as, int ret), + TP_ARGS(as, ret), + + TP_STRUCT__entry( + __field(u64, as) + __field(int, ret) + ), + TP_fast_assign(__entry->as = as; + __entry->ret = ret; + ), + TP_printk("address space %llx ret %d", __entry->as, __entry->ret) + ); + +TRACE_EVENT(hyperv_send_ipi_mask, + TP_PROTO(const struct cpumask *cpus, + int vector), + TP_ARGS(cpus, vector), + TP_STRUCT__entry( + __field(unsigned int, ncpus) + __field(int, vector) + ), + TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); + __entry->vector = vector; + ), + TP_printk("ncpus %d vector %x", + __entry->ncpus, __entry->vector) + ); + #endif /* CONFIG_HYPERV */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 2701d221583a..eb5bbfeccb66 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -33,13 +33,13 @@ static inline cycles_t get_cycles(void) extern struct system_counterval_t convert_art_to_tsc(u64 art); extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns); -extern void tsc_early_delay_calibrate(void); +extern void tsc_early_init(void); extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); extern void mark_tsc_async_resets(char *reason); -extern unsigned long native_calibrate_cpu(void); +extern unsigned long native_calibrate_cpu_early(void); extern unsigned long native_calibrate_tsc(void); extern unsigned long long native_sched_clock_from_tsc(u64 tsc); diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index bae46fc6b9de..0bcdb1279361 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -26,7 +26,7 @@ * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL +.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0 #ifdef CONFIG_STACK_VALIDATION .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints @@ -35,12 +35,14 @@ .short \sp_offset .byte \sp_reg .byte \type + .byte \end + .balign 4 .popsection #endif .endm .macro UNWIND_HINT_EMPTY - UNWIND_HINT sp_reg=ORC_REG_UNDEFINED + UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1 .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0 @@ -86,19 +88,21 @@ #else /* !__ASSEMBLY__ */ -#define UNWIND_HINT(sp_reg, sp_offset, type) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ ".long 987b - .\n\t" \ - ".short " __stringify(sp_offset) "\n\t" \ + ".short " __stringify(sp_offset) "\n\t" \ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ + ".byte " __stringify(end) "\n\t" \ + ".balign 4 \n\t" \ ".popsection\n\t" -#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE) +#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0) -#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE) +#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 6aa8499e1f62..95f9107449bf 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -576,4 +576,15 @@ enum vm_instruction_error_number { VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID = 28, }; +enum vmx_l1d_flush_state { + VMENTER_L1D_FLUSH_AUTO, + VMENTER_L1D_FLUSH_NEVER, + VMENTER_L1D_FLUSH_COND, + VMENTER_L1D_FLUSH_ALWAYS, + VMENTER_L1D_FLUSH_EPT_DISABLED, + VMENTER_L1D_FLUSH_NOT_REQUIRED, +}; + +extern enum vmx_l1d_flush_state l1tf_vmx_mitigation; + #endif diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index bfd882617613..6b2f90a0b149 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -209,24 +209,37 @@ extern struct { char _entry[32]; } hypercall_page[]; }) static inline long -privcmd_call(unsigned call, - unsigned long a1, unsigned long a2, - unsigned long a3, unsigned long a4, - unsigned long a5) +xen_single_call(unsigned int call, + unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, + unsigned long a5) { __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - stac(); asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM : [thunk_target] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); - clac(); return (long)__res; } +static inline long +privcmd_call(unsigned int call, + unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, + unsigned long a5) +{ + long res; + + stac(); + res = xen_single_call(call, a1, a2, a3, a4, a5); + clac(); + + return res; +} + static inline int HYPERVISOR_set_trap_table(struct trap_info *table) { diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index c535c2fdea13..86299efa804a 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -378,4 +378,41 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_STATE_NESTED_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_RUN_PENDING 0x00000002 + +#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_SMM_VMXON 0x00000002 + +struct kvm_vmx_nested_state { + __u64 vmxon_pa; + __u64 vmcs_pa; + + struct { + __u16 flags; + } smm; +}; + +/* for KVM_CAP_NESTED_STATE */ +struct kvm_nested_state { + /* KVM_STATE_* flags */ + __u16 flags; + + /* 0 for VMX, 1 for SVM. */ + __u16 format; + + /* 128 for SVM, 128 + VMCS size for VMX. */ + __u32 size; + + union { + /* VMXON, VMCS */ + struct kvm_vmx_nested_state vmx; + + /* Pad the header to 128 bytes. */ + __u8 pad[120]; + }; + + __u8 data[0]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 0ede697c3961..19980ec1a316 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -28,6 +28,7 @@ #define KVM_FEATURE_PV_UNHALT 7 #define KVM_FEATURE_PV_TLB_FLUSH 9 #define KVM_FEATURE_ASYNC_PF_VMEXIT 10 +#define KVM_FEATURE_PV_SEND_IPI 11 #define KVM_HINTS_REALTIME 0 diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a481763a3776..014f214da581 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -668,6 +668,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode, local_irq_save(flags); memcpy(addr, opcode, len); local_irq_restore(flags); + sync_core(); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ return addr; @@ -693,6 +694,12 @@ void *text_poke(void *addr, const void *opcode, size_t len) struct page *pages[2]; int i; + /* + * While boot memory allocator is runnig we cannot use struct + * pages as they are not yet initialized. + */ + BUG_ON(!after_bootmem); + if (!core_kernel_text((unsigned long)addr)) { pages[0] = vmalloc_to_page(addr); pages[1] = vmalloc_to_page(addr + PAGE_SIZE); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2aabd4cb0e3f..84132eddb5a8 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -56,6 +56,7 @@ #include <asm/hypervisor.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> +#include <asm/irq_regs.h> unsigned int num_processors; @@ -573,6 +574,9 @@ static u32 skx_deadline_rev(void) case 0x04: return 0x02000014; } + if (boot_cpu_data.x86_stepping > 4) + return 0; + return ~0U; } @@ -937,7 +941,7 @@ static int __init calibrate_APIC_clock(void) if (levt->features & CLOCK_EVT_FEAT_DUMMY) { pr_warning("APIC timer disabled due to verification failure\n"); - return -1; + return -1; } return 0; @@ -2189,6 +2193,23 @@ static int cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = -1, }; +#ifdef CONFIG_SMP +/** + * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread + * @id: APIC ID to check + */ +bool apic_id_is_primary_thread(unsigned int apicid) +{ + u32 mask; + + if (smp_num_siblings == 1) + return true; + /* Isolate the SMT bit(s) in the APICID and check for 0 */ + mask = (1U << (fls(smp_num_siblings) - 1)) - 1; + return !(apicid & mask); +} +#endif + /* * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids * and cpuid_to_apicid[] synchronized. diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 3982f79d2377..ff0d14cd9e82 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -33,6 +33,7 @@ #include <linux/mm.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/init.h> #include <linux/delay.h> #include <linux/sched.h> diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index ce503c99f5c4..72a94401f9e0 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -12,6 +12,7 @@ */ #include <linux/mm.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/pci.h> #include <linux/dmar.h> #include <linux/hpet.h> diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 35aaee4fc028..9f148e3d45b4 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -11,6 +11,7 @@ * published by the Free Software Foundation. */ #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/compiler.h> @@ -218,7 +219,8 @@ static int reserve_irq_vector(struct irq_data *irqd) return 0; } -static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest) +static int +assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest) { struct apic_chip_data *apicd = apic_chip_data(irqd); bool resvd = apicd->has_reserved; @@ -245,22 +247,12 @@ static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest) return -EBUSY; vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu); - if (vector > 0) - apic_update_vector(irqd, vector, cpu); trace_vector_alloc(irqd->irq, vector, resvd, vector); - return vector; -} - -static int assign_vector_locked(struct irq_data *irqd, - const struct cpumask *dest) -{ - struct apic_chip_data *apicd = apic_chip_data(irqd); - int vector = allocate_vector(irqd, dest); - if (vector < 0) return vector; + apic_update_vector(irqd, vector, cpu); + apic_update_irq_cfg(irqd, vector, cpu); - apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu); return 0; } @@ -433,7 +425,7 @@ static int activate_managed(struct irq_data *irqd) pr_err("Managed startup irq %u, no vector available\n", irqd->irq); } - return ret; + return ret; } static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d492752f79e1..391f358ebb4c 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -394,10 +394,10 @@ extern int uv_hub_info_version(void) EXPORT_SYMBOL(uv_hub_info_version); /* Default UV memory block size is 2GB */ -static unsigned long mem_block_size = (2UL << 30); +static unsigned long mem_block_size __initdata = (2UL << 30); /* Kernel parameter to specify UV mem block size */ -static int parse_mem_block_size(char *ptr) +static int __init parse_mem_block_size(char *ptr) { unsigned long size = memparse(ptr, NULL); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index dcb008c320fe..01de31db300d 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -103,4 +103,9 @@ void common(void) { OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page); DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack)); + DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1))); + + /* Offset for sp0 and sp1 into the tss_struct */ + OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); + OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index a4a3be399f4b..82826f2275cc 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -46,8 +46,14 @@ void foo(void) OFFSET(saved_context_gdt_desc, saved_context, gdt_desc); BLANK(); - /* Offset from the sysenter stack to tss.sp0 */ - DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) - + /* + * Offset from the entry stack to task stack stored in TSS. Kernel entry + * happens on the per-cpu entry-stack, and the asm code switches to the + * task-stack pointer stored in x86_tss.sp1, which is a copy of + * task->thread.sp0 where entry code can find it. + */ + DEFINE(TSS_entry2task_stack, + offsetof(struct cpu_entry_area, tss.x86_tss.sp1) - offsetofend(struct cpu_entry_area, entry_stack_page.stack)); #ifdef CONFIG_STACKPROTECTOR diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index b2dcd161f514..3b9405e7ba2b 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -65,8 +65,6 @@ int main(void) #undef ENTRY OFFSET(TSS_ist, tss_struct, x86_tss.ist); - OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); - OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); BLANK(); #ifdef CONFIG_STACKPROTECTOR diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 7a40196967cb..347137e80bf5 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -35,7 +35,9 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o +CFLAGS_intel_rdt_pseudo_lock.o = -I$(src) obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 38915fbfae73..22ab408177b2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -232,8 +232,6 @@ static void init_amd_k7(struct cpuinfo_x86 *c) } } - set_cpu_cap(c, X86_FEATURE_K7); - /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -315,6 +313,13 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c) c->cpu_core_id %= cus_per_node; } + +static void amd_get_topology_early(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_TOPOEXT)) + smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; +} + /* * Fixup core topology information for * (1) AMD multi-node processors @@ -334,7 +339,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); node_id = ecx & 0xff; - smp_num_siblings = ((ebx >> 8) & 0xff) + 1; if (c->x86 == 0x15) c->cu_id = ebx & 0xff; @@ -613,10 +617,19 @@ clear_sev: static void early_init_amd(struct cpuinfo_x86 *c) { + u64 value; u32 dummy; early_init_amd_mc(c); +#ifdef CONFIG_X86_32 + if (c->x86 == 6) + set_cpu_cap(c, X86_FEATURE_K7); +#endif + + if (c->x86 >= 0xf) + set_cpu_cap(c, X86_FEATURE_K8); + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); /* @@ -683,6 +696,22 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_AMD_E400); early_detect_mem_encrypt(c); + + /* Re-enable TopologyExtensions if switched off by BIOS */ + if (c->x86 == 0x15 && + (c->x86_model >= 0x10 && c->x86_model <= 0x6f) && + !cpu_has(c, X86_FEATURE_TOPOEXT)) { + + if (msr_set_bit(0xc0011005, 54) > 0) { + rdmsrl(0xc0011005, value); + if (value & BIT_64(54)) { + set_cpu_cap(c, X86_FEATURE_TOPOEXT); + pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); + } + } + } + + amd_get_topology_early(c); } static void init_amd_k8(struct cpuinfo_x86 *c) @@ -774,19 +803,6 @@ static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; - /* re-enable TopologyExtensions if switched off by BIOS */ - if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) && - !cpu_has(c, X86_FEATURE_TOPOEXT)) { - - if (msr_set_bit(0xc0011005, 54) > 0) { - rdmsrl(0xc0011005, value); - if (value & BIT_64(54)) { - set_cpu_cap(c, X86_FEATURE_TOPOEXT); - pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); - } - } - } - /* * The way access filter has a performance penalty on some workloads. * Disable it on the affected CPUs. @@ -850,22 +866,12 @@ static void init_amd(struct cpuinfo_x86 *c) cpu_detect_cache_sizes(c); - /* Multi core CPU? */ - if (c->extended_cpuid_level >= 0x80000008) { - amd_detect_cmp(c); - amd_get_topology(c); - srat_detect_node(c); - } - -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif + amd_detect_cmp(c); + amd_get_topology(c); + srat_detect_node(c); init_amd_cacheinfo(c); - if (c->x86 >= 0xf) - set_cpu_cap(c, X86_FEATURE_K8); - if (cpu_has(c, X86_FEATURE_XMM2)) { unsigned long long val; int ret; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 5c0ea39311fe..cb4a16292aa7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -22,15 +22,18 @@ #include <asm/processor-flags.h> #include <asm/fpu/internal.h> #include <asm/msr.h> +#include <asm/vmx.h> #include <asm/paravirt.h> #include <asm/alternative.h> #include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/intel-family.h> +#include <asm/e820/api.h> #include <asm/hypervisor.h> static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); +static void __init l1tf_select_mitigation(void); /* * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any @@ -56,6 +59,12 @@ void __init check_bugs(void) { identify_boot_cpu(); + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology_early(); + if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); print_cpu_info(&boot_cpu_data); @@ -82,6 +91,8 @@ void __init check_bugs(void) */ ssb_select_mitigation(); + l1tf_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -130,6 +141,7 @@ static const char *spectre_v2_strings[] = { [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", + [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", }; #undef pr_fmt @@ -313,23 +325,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return cmd; } -/* Check for Skylake-like CPUs (for RSB handling) */ -static bool __init is_skylake_era(void) -{ - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && - boot_cpu_data.x86 == 6) { - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_SKYLAKE_MOBILE: - case INTEL_FAM6_SKYLAKE_DESKTOP: - case INTEL_FAM6_SKYLAKE_X: - case INTEL_FAM6_KABYLAKE_MOBILE: - case INTEL_FAM6_KABYLAKE_DESKTOP: - return true; - } - } - return false; -} - static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -349,6 +344,13 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_CMD_FORCE: case SPECTRE_V2_CMD_AUTO: + if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { + mode = SPECTRE_V2_IBRS_ENHANCED; + /* Force it so VMEXIT will restore correctly */ + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + goto specv2_set_mode; + } if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_auto; break; @@ -386,26 +388,20 @@ retpoline_auto: setup_force_cpu_cap(X86_FEATURE_RETPOLINE); } +specv2_set_mode: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); /* - * If neither SMEP nor PTI are available, there is a risk of - * hitting userspace addresses in the RSB after a context switch - * from a shallow call stack to a deeper one. To prevent this fill - * the entire RSB, even when using IBRS. + * If spectre v2 protection has been enabled, unconditionally fill + * RSB during a context switch; this protects against two independent + * issues: * - * Skylake era CPUs have a separate issue with *underflow* of the - * RSB, when they will predict 'ret' targets from the generic BTB. - * The proper mitigation for this is IBRS. If IBRS is not supported - * or deactivated in favour of retpolines the RSB fill on context - * switch is required. + * - RSB underflow (and switch to BTB) on Skylake+ + * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs */ - if ((!boot_cpu_has(X86_FEATURE_PTI) && - !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { - setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); - pr_info("Spectre v2 mitigation: Filling RSB on context switch\n"); - } + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); /* Initialize Indirect Branch Prediction Barrier if supported */ if (boot_cpu_has(X86_FEATURE_IBPB)) { @@ -415,9 +411,16 @@ retpoline_auto: /* * Retpoline means the kernel is safe because it has no indirect - * branches. But firmware isn't, so use IBRS to protect that. + * branches. Enhanced IBRS protects firmware too, so, enable restricted + * speculation around firmware calls only when Enhanced IBRS isn't + * supported. + * + * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because + * the user might select retpoline on the kernel command line and if + * the CPU supports Enhanced IBRS, kernel might un-intentionally not + * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS)) { + if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } @@ -654,8 +657,120 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +#undef pr_fmt +#define pr_fmt(fmt) "L1TF: " fmt + +/* Default mitigation for L1TF-affected CPUs */ +enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH; +#if IS_ENABLED(CONFIG_KVM_INTEL) +EXPORT_SYMBOL_GPL(l1tf_mitigation); +#endif +enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; +EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation); + +static void __init l1tf_select_mitigation(void) +{ + u64 half_pa; + + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return; + + switch (l1tf_mitigation) { + case L1TF_MITIGATION_OFF: + case L1TF_MITIGATION_FLUSH_NOWARN: + case L1TF_MITIGATION_FLUSH: + break; + case L1TF_MITIGATION_FLUSH_NOSMT: + case L1TF_MITIGATION_FULL: + cpu_smt_disable(false); + break; + case L1TF_MITIGATION_FULL_FORCE: + cpu_smt_disable(true); + break; + } + +#if CONFIG_PGTABLE_LEVELS == 2 + pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n"); + return; +#endif + + /* + * This is extremely unlikely to happen because almost all + * systems have far more MAX_PA/2 than RAM can be fit into + * DIMM slots. + */ + half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT; + if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) { + pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n"); + return; + } + + setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV); +} + +static int __init l1tf_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + l1tf_mitigation = L1TF_MITIGATION_OFF; + else if (!strcmp(str, "flush,nowarn")) + l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOWARN; + else if (!strcmp(str, "flush")) + l1tf_mitigation = L1TF_MITIGATION_FLUSH; + else if (!strcmp(str, "flush,nosmt")) + l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT; + else if (!strcmp(str, "full")) + l1tf_mitigation = L1TF_MITIGATION_FULL; + else if (!strcmp(str, "full,force")) + l1tf_mitigation = L1TF_MITIGATION_FULL_FORCE; + + return 0; +} +early_param("l1tf", l1tf_cmdline); + +#undef pr_fmt + #ifdef CONFIG_SYSFS +#define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion" + +#if IS_ENABLED(CONFIG_KVM_INTEL) +static const char *l1tf_vmx_states[] = { + [VMENTER_L1D_FLUSH_AUTO] = "auto", + [VMENTER_L1D_FLUSH_NEVER] = "vulnerable", + [VMENTER_L1D_FLUSH_COND] = "conditional cache flushes", + [VMENTER_L1D_FLUSH_ALWAYS] = "cache flushes", + [VMENTER_L1D_FLUSH_EPT_DISABLED] = "EPT disabled", + [VMENTER_L1D_FLUSH_NOT_REQUIRED] = "flush not necessary" +}; + +static ssize_t l1tf_show_state(char *buf) +{ + if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) + return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + + if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || + (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && + cpu_smt_control == CPU_SMT_ENABLED)) + return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation]); + + return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation], + cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled"); +} +#else +static ssize_t l1tf_show_state(char *buf) +{ + return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); +} +#endif + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -684,6 +799,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_SPEC_STORE_BYPASS: return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + case X86_BUG_L1TF: + if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) + return l1tf_show_state(buf); + break; default: break; } @@ -710,4 +829,9 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute * { return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); } + +ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_L1TF); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index eb4cb3efd20e..84dee5ab745a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -661,33 +661,36 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -void detect_ht(struct cpuinfo_x86 *c) +int detect_ht_early(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP u32 eax, ebx, ecx, edx; - int index_msb, core_bits; - static bool printed; if (!cpu_has(c, X86_FEATURE_HT)) - return; + return -1; if (cpu_has(c, X86_FEATURE_CMP_LEGACY)) - goto out; + return -1; if (cpu_has(c, X86_FEATURE_XTOPOLOGY)) - return; + return -1; cpuid(1, &eax, &ebx, &ecx, &edx); smp_num_siblings = (ebx & 0xff0000) >> 16; - - if (smp_num_siblings == 1) { + if (smp_num_siblings == 1) pr_info_once("CPU0: Hyper-Threading is disabled\n"); - goto out; - } +#endif + return 0; +} - if (smp_num_siblings <= 1) - goto out; +void detect_ht(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + int index_msb, core_bits; + + if (detect_ht_early(c) < 0) + return; index_msb = get_count_order(smp_num_siblings); c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb); @@ -700,15 +703,6 @@ void detect_ht(struct cpuinfo_x86 *c) c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) & ((1 << core_bits) - 1); - -out: - if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) { - pr_info("CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - pr_info("CPU: Processor Core ID: %d\n", - c->cpu_core_id); - printed = 1; - } #endif } @@ -911,7 +905,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) apply_forced_caps(c); } -static void get_cpu_address_sizes(struct cpuinfo_x86 *c) +void get_cpu_address_sizes(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -987,6 +981,21 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { {} }; +static const __initconst struct x86_cpu_id cpu_no_l1tf[] = { + /* in addition to cpu_no_speculation */ + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + {} +}; + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; @@ -1005,6 +1014,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); + if (ia32_cap & ARCH_CAP_IBRS_ALL) + setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); + if (x86_match_cpu(cpu_no_meltdown)) return; @@ -1013,6 +1025,29 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) return; setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + + if (x86_match_cpu(cpu_no_l1tf)) + return; + + setup_force_cpu_bug(X86_BUG_L1TF); +} + +/* + * The NOPL instruction is supposed to exist on all CPUs of family >= 6; + * unfortunately, that's not true in practice because of early VIA + * chips and (more importantly) broken virtualizers that are not easy + * to detect. In the latter case it doesn't even *fail* reliably, so + * probing for it doesn't even work. Disable it completely on 32-bit + * unless we can find a reliable way to detect all the broken cases. + * Enable it explicitly on 64-bit for non-constant inputs of cpu_has(). + */ +static void detect_nopl(void) +{ +#ifdef CONFIG_X86_32 + setup_clear_cpu_cap(X86_FEATURE_NOPL); +#else + setup_force_cpu_cap(X86_FEATURE_NOPL); +#endif } /* @@ -1089,6 +1124,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) */ if (!pgtable_l5_enabled()) setup_clear_cpu_cap(X86_FEATURE_LA57); + + detect_nopl(); } void __init early_cpu_init(void) @@ -1124,24 +1161,6 @@ void __init early_cpu_init(void) early_identify_cpu(&boot_cpu_data); } -/* - * The NOPL instruction is supposed to exist on all CPUs of family >= 6; - * unfortunately, that's not true in practice because of early VIA - * chips and (more importantly) broken virtualizers that are not easy - * to detect. In the latter case it doesn't even *fail* reliably, so - * probing for it doesn't even work. Disable it completely on 32-bit - * unless we can find a reliable way to detect all the broken cases. - * Enable it explicitly on 64-bit for non-constant inputs of cpu_has(). - */ -static void detect_nopl(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_X86_32 - clear_cpu_cap(c, X86_FEATURE_NOPL); -#else - set_cpu_cap(c, X86_FEATURE_NOPL); -#endif -} - static void detect_null_seg_behavior(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 @@ -1204,8 +1223,6 @@ static void generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - detect_nopl(c); - detect_null_seg_behavior(c); /* @@ -1804,11 +1821,12 @@ void cpu_init(void) enter_lazy_tlb(&init_mm, curr); /* - * Initialize the TSS. Don't bother initializing sp0, as the initial - * task never enters user mode. + * Initialize the TSS. sp0 points to the entry trampoline stack + * regardless of what task is running. */ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); + load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1)); load_mm_ldt(&init_mm); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 38216f678fc3..7b229afa0a37 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -46,6 +46,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; extern void get_cpu_cap(struct cpuinfo_x86 *c); +extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c); extern u32 get_scattered_cpuid_leaf(unsigned int level, @@ -55,7 +56,9 @@ extern void init_intel_cacheinfo(struct cpuinfo_x86 *c); extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); extern void detect_num_cpu_cores(struct cpuinfo_x86 *c); +extern int detect_extended_topology_early(struct cpuinfo_x86 *c); extern int detect_extended_topology(struct cpuinfo_x86 *c); +extern int detect_ht_early(struct cpuinfo_x86 *c); extern void detect_ht(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index eb75564f2d25..401e8c133108 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -301,6 +301,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) } check_mpx_erratum(c); + + /* + * Get the number of SMT siblings early from the extended topology + * leaf, if available. Otherwise try the legacy SMT detection. + */ + if (detect_extended_topology_early(c) < 0) + detect_ht_early(c); } #ifdef CONFIG_X86_32 @@ -465,14 +472,17 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) #define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 #define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 #define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 +#define x86_VMX_FEATURE_EPT_CAP_AD 0x00200000 u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; + u32 msr_vpid_cap, msr_ept_cap; clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW); clear_cpu_cap(c, X86_FEATURE_VNMI); clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); clear_cpu_cap(c, X86_FEATURE_EPT); clear_cpu_cap(c, X86_FEATURE_VPID); + clear_cpu_cap(c, X86_FEATURE_EPT_AD); rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); msr_ctl = vmx_msr_high | vmx_msr_low; @@ -487,8 +497,13 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) + if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) { set_cpu_cap(c, X86_FEATURE_EPT); + rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, + msr_ept_cap, msr_vpid_cap); + if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD) + set_cpu_cap(c, X86_FEATURE_EPT_AD); + } if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) set_cpu_cap(c, X86_FEATURE_VPID); } diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index ec4754f81cbd..abb71ac70443 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -859,6 +859,8 @@ static __init bool get_rdt_resources(void) return (rdt_mon_capable || rdt_alloc_capable); } +static enum cpuhp_state rdt_online; + static int __init intel_rdt_late_init(void) { struct rdt_resource *r; @@ -880,6 +882,7 @@ static int __init intel_rdt_late_init(void) cpuhp_remove_state(state); return ret; } + rdt_online = state; for_each_alloc_capable_rdt_resource(r) pr_info("Intel RDT %s allocation detected\n", r->name); @@ -891,3 +894,11 @@ static int __init intel_rdt_late_init(void) } late_initcall(intel_rdt_late_init); + +static void __exit intel_rdt_exit(void) +{ + cpuhp_remove_state(rdt_online); + rdtgroup_exit(); +} + +__exitcall(intel_rdt_exit); diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 39752825e376..4e588f36228f 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -81,6 +81,34 @@ enum rdt_group_type { }; /** + * enum rdtgrp_mode - Mode of a RDT resource group + * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations + * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed + * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking + * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations + * allowed AND the allocations are Cache Pseudo-Locked + * + * The mode of a resource group enables control over the allowed overlap + * between allocations associated with different resource groups (classes + * of service). User is able to modify the mode of a resource group by + * writing to the "mode" resctrl file associated with the resource group. + * + * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by + * writing the appropriate text to the "mode" file. A resource group enters + * "pseudo-locked" mode after the schemata is written while the resource + * group is in "pseudo-locksetup" mode. + */ +enum rdtgrp_mode { + RDT_MODE_SHAREABLE = 0, + RDT_MODE_EXCLUSIVE, + RDT_MODE_PSEUDO_LOCKSETUP, + RDT_MODE_PSEUDO_LOCKED, + + /* Must be last */ + RDT_NUM_MODES, +}; + +/** * struct mongroup - store mon group's data in resctrl fs. * @mon_data_kn kernlfs node for the mon_data directory * @parent: parent rdtgrp @@ -95,6 +123,43 @@ struct mongroup { }; /** + * struct pseudo_lock_region - pseudo-lock region information + * @r: RDT resource to which this pseudo-locked region + * belongs + * @d: RDT domain to which this pseudo-locked region + * belongs + * @cbm: bitmask of the pseudo-locked region + * @lock_thread_wq: waitqueue used to wait on the pseudo-locking thread + * completion + * @thread_done: variable used by waitqueue to test if pseudo-locking + * thread completed + * @cpu: core associated with the cache on which the setup code + * will be run + * @line_size: size of the cache lines + * @size: size of pseudo-locked region in bytes + * @kmem: the kernel memory associated with pseudo-locked region + * @minor: minor number of character device associated with this + * region + * @debugfs_dir: pointer to this region's directory in the debugfs + * filesystem + * @pm_reqs: Power management QoS requests related to this region + */ +struct pseudo_lock_region { + struct rdt_resource *r; + struct rdt_domain *d; + u32 cbm; + wait_queue_head_t lock_thread_wq; + int thread_done; + int cpu; + unsigned int line_size; + unsigned int size; + void *kmem; + unsigned int minor; + struct dentry *debugfs_dir; + struct list_head pm_reqs; +}; + +/** * struct rdtgroup - store rdtgroup's data in resctrl file system. * @kn: kernfs node * @rdtgroup_list: linked list for all rdtgroups @@ -106,16 +171,20 @@ struct mongroup { * @type: indicates type of this rdtgroup - either * monitor only or ctrl_mon group * @mon: mongroup related data + * @mode: mode of resource group + * @plr: pseudo-locked region */ struct rdtgroup { - struct kernfs_node *kn; - struct list_head rdtgroup_list; - u32 closid; - struct cpumask cpu_mask; - int flags; - atomic_t waitcount; - enum rdt_group_type type; - struct mongroup mon; + struct kernfs_node *kn; + struct list_head rdtgroup_list; + u32 closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; + enum rdt_group_type type; + struct mongroup mon; + enum rdtgrp_mode mode; + struct pseudo_lock_region *plr; }; /* rdtgroup.flags */ @@ -148,6 +217,7 @@ extern struct list_head rdt_all_groups; extern int max_name_width, max_data_width; int __init rdtgroup_init(void); +void __exit rdtgroup_exit(void); /** * struct rftype - describe each file in the resctrl file system @@ -216,22 +286,24 @@ struct mbm_state { * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps * @new_ctrl: new ctrl value to be loaded * @have_new_ctrl: did user provide new_ctrl for this domain + * @plr: pseudo-locked region (if any) associated with domain */ struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; - unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; - struct delayed_work mbm_over; - struct delayed_work cqm_limbo; - int mbm_work_cpu; - int cqm_work_cpu; - u32 *ctrl_val; - u32 *mbps_val; - u32 new_ctrl; - bool have_new_ctrl; + struct list_head list; + int id; + struct cpumask cpu_mask; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + u32 *ctrl_val; + u32 *mbps_val; + u32 new_ctrl; + bool have_new_ctrl; + struct pseudo_lock_region *plr; }; /** @@ -351,7 +423,7 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (char *buf, struct rdt_resource *r, + int (*parse_ctrlval) (void *data, struct rdt_resource *r, struct rdt_domain *d); struct list_head evt_list; int num_rmid; @@ -359,8 +431,8 @@ struct rdt_resource { unsigned long fflags; }; -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d); +int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -368,7 +440,7 @@ extern struct rdt_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); -int __init rdtgroup_init(void); +extern struct dentry *debugfs_resctrl; enum { RDT_RESOURCE_L3, @@ -439,13 +511,32 @@ void rdt_last_cmd_printf(const char *fmt, ...); void rdt_ctrl_update(void *arg); struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); void rdtgroup_kn_unlock(struct kernfs_node *kn); +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name); +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask); struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, struct list_head **pos); ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + u32 _cbm, int closid, bool exclusive); +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, + u32 cbm); +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); +int rdtgroup_tasks_assigned(struct rdtgroup *r); +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm); +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); +int rdt_pseudo_lock_init(void); +void rdt_pseudo_lock_release(void); +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +int update_domains(struct rdt_resource *r, int closid); +void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 116d57b248d3..af358ca05160 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -64,9 +64,10 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d) { unsigned long data; + char *buf = _buf; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); @@ -87,7 +88,7 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). * Additionally Haswell requires at least two bits set. */ -static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) +static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) { unsigned long first_bit, zero_bit, val; unsigned int cbm_len = r->cache.cbm_len; @@ -122,22 +123,64 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } +struct rdt_cbm_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) { - unsigned long data; + struct rdt_cbm_parse_data *data = _data; + struct rdtgroup *rdtgrp = data->rdtgrp; + u32 cbm_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if(!cbm_validate(buf, &data, r)) + /* + * Cannot set up more than one pseudo-locked region in a cache + * hierarchy. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + rdtgroup_pseudo_locked_in_hierarchy(d)) { + rdt_last_cmd_printf("pseudo-locked region in hierarchy\n"); return -EINVAL; - d->new_ctrl = data; + } + + if (!cbm_validate(data->buf, &cbm_val, r)) + return -EINVAL; + + if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_SHAREABLE) && + rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) { + rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n"); + return -EINVAL; + } + + /* + * The CBM may not overlap with the CBM of another closid if + * either is exclusive. + */ + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) { + rdt_last_cmd_printf("overlaps with exclusive group\n"); + return -EINVAL; + } + + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) { + if (rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + rdt_last_cmd_printf("overlaps with other group\n"); + return -EINVAL; + } + } + + d->new_ctrl = cbm_val; d->have_new_ctrl = true; return 0; @@ -149,8 +192,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) * separated by ";". The "id" is in decimal, and must match one of * the "id"s for this resource. */ -static int parse_line(char *line, struct rdt_resource *r) +static int parse_line(char *line, struct rdt_resource *r, + struct rdtgroup *rdtgrp) { + struct rdt_cbm_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; @@ -167,15 +212,32 @@ next: dom = strim(dom); list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { - if (r->parse_ctrlval(dom, r, d)) + data.buf = dom; + data.rdtgrp = rdtgrp; + if (r->parse_ctrlval(&data, r, d)) return -EINVAL; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * In pseudo-locking setup mode and just + * parsed a valid CBM that should be + * pseudo-locked. Only one locked region per + * resource group and domain so just do + * the required initialization for single + * region and return. + */ + rdtgrp->plr->r = r; + rdtgrp->plr->d = d; + rdtgrp->plr->cbm = d->new_ctrl; + d->plr = rdtgrp->plr; + return 0; + } goto next; } } return -EINVAL; } -static int update_domains(struct rdt_resource *r, int closid) +int update_domains(struct rdt_resource *r, int closid) { struct msr_param msr_param; cpumask_var_t cpu_mask; @@ -220,13 +282,14 @@ done: return 0; } -static int rdtgroup_parse_resource(char *resname, char *tok, int closid) +static int rdtgroup_parse_resource(char *resname, char *tok, + struct rdtgroup *rdtgrp) { struct rdt_resource *r; for_each_alloc_enabled_rdt_resource(r) { - if (!strcmp(resname, r->name) && closid < r->num_closid) - return parse_line(tok, r); + if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid) + return parse_line(tok, r, rdtgrp); } rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname); return -EINVAL; @@ -239,7 +302,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, struct rdt_domain *dom; struct rdt_resource *r; char *tok, *resname; - int closid, ret = 0; + int ret = 0; /* Valid input requires a trailing newline */ if (nbytes == 0 || buf[nbytes - 1] != '\n') @@ -253,7 +316,15 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, } rdt_last_cmd_clear(); - closid = rdtgrp->closid; + /* + * No changes to pseudo-locked region allowed. It has to be removed + * and re-created instead. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = -EINVAL; + rdt_last_cmd_puts("resource group is pseudo-locked\n"); + goto out; + } for_each_alloc_enabled_rdt_resource(r) { list_for_each_entry(dom, &r->domains, list) @@ -272,17 +343,27 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, ret = -EINVAL; goto out; } - ret = rdtgroup_parse_resource(resname, tok, closid); + ret = rdtgroup_parse_resource(resname, tok, rdtgrp); if (ret) goto out; } for_each_alloc_enabled_rdt_resource(r) { - ret = update_domains(r, closid); + ret = update_domains(r, rdtgrp->closid); if (ret) goto out; } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * If pseudo-locking fails we keep the resource group in + * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service + * active and updated for just the domain the pseudo-locked + * region was requested for. + */ + ret = rdtgroup_pseudo_lock_create(rdtgrp); + } + out: rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -318,10 +399,18 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - closid = rdtgrp->closid; - for_each_alloc_enabled_rdt_resource(r) { - if (closid < r->num_closid) - show_doms(s, r, closid); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + for_each_alloc_enabled_rdt_resource(r) + seq_printf(s, "%s:uninitialized\n", r->name); + } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name, + rdtgrp->plr->d->id, rdtgrp->plr->cbm); + } else { + closid = rdtgrp->closid; + for_each_alloc_enabled_rdt_resource(r) { + if (closid < r->num_closid) + show_doms(s, r, closid); + } } } else { ret = -ENOENT; diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c new file mode 100644 index 000000000000..40f3903ae5d9 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -0,0 +1,1522 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Resource Director Technology (RDT) + * + * Pseudo-locking support built on top of Cache Allocation Technology (CAT) + * + * Copyright (C) 2018 Intel Corporation + * + * Author: Reinette Chatre <reinette.chatre@intel.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cacheinfo.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/debugfs.h> +#include <linux/kthread.h> +#include <linux/mman.h> +#include <linux/pm_qos.h> +#include <linux/slab.h> +#include <linux/uaccess.h> + +#include <asm/cacheflush.h> +#include <asm/intel-family.h> +#include <asm/intel_rdt_sched.h> +#include <asm/perf_event.h> + +#include "intel_rdt.h" + +#define CREATE_TRACE_POINTS +#include "intel_rdt_pseudo_lock_event.h" + +/* + * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware + * prefetcher state. Details about this register can be found in the MSR + * tables for specific platforms found in Intel's SDM. + */ +#define MSR_MISC_FEATURE_CONTROL 0x000001a4 + +/* + * The bits needed to disable hardware prefetching varies based on the + * platform. During initialization we will discover which bits to use. + */ +static u64 prefetch_disable_bits; + +/* + * Major number assigned to and shared by all devices exposing + * pseudo-locked regions. + */ +static unsigned int pseudo_lock_major; +static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0); +static struct class *pseudo_lock_class; + +/** + * get_prefetch_disable_bits - prefetch disable bits of supported platforms + * + * Capture the list of platforms that have been validated to support + * pseudo-locking. This includes testing to ensure pseudo-locked regions + * with low cache miss rates can be created under variety of load conditions + * as well as that these pseudo-locked regions can maintain their low cache + * miss rates under variety of load conditions for significant lengths of time. + * + * After a platform has been validated to support pseudo-locking its + * hardware prefetch disable bits are included here as they are documented + * in the SDM. + * + * When adding a platform here also add support for its cache events to + * measure_cycles_perf_fn() + * + * Return: + * If platform is supported, the bits to disable hardware prefetchers, 0 + * if platform is not supported. + */ +static u64 get_prefetch_disable_bits(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return 0; + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_X: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 L2 Adjacent Cache Line Prefetcher Disable (R/W) + * 2 DCU Hardware Prefetcher Disable (R/W) + * 3 DCU IP Prefetcher Disable (R/W) + * 63:4 Reserved + */ + return 0xF; + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GEMINI_LAKE: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 Reserved + * 2 DCU Hardware Prefetcher Disable (R/W) + * 63:3 Reserved + */ + return 0x5; + } + + return 0; +} + +/* + * Helper to write 64bit value to MSR without tracing. Used when + * use of the cache should be restricted and use of registers used + * for local variables avoided. + */ +static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val) +{ + __wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); +} + +/** + * pseudo_lock_minor_get - Obtain available minor number + * @minor: Pointer to where new minor number will be stored + * + * A bitmask is used to track available minor numbers. Here the next free + * minor number is marked as unavailable and returned. + * + * Return: 0 on success, <0 on failure. + */ +static int pseudo_lock_minor_get(unsigned int *minor) +{ + unsigned long first_bit; + + first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS); + + if (first_bit == MINORBITS) + return -ENOSPC; + + __clear_bit(first_bit, &pseudo_lock_minor_avail); + *minor = first_bit; + + return 0; +} + +/** + * pseudo_lock_minor_release - Return minor number to available + * @minor: The minor number made available + */ +static void pseudo_lock_minor_release(unsigned int minor) +{ + __set_bit(minor, &pseudo_lock_minor_avail); +} + +/** + * region_find_by_minor - Locate a pseudo-lock region by inode minor number + * @minor: The minor number of the device representing pseudo-locked region + * + * When the character device is accessed we need to determine which + * pseudo-locked region it belongs to. This is done by matching the minor + * number of the device to the pseudo-locked region it belongs. + * + * Minor numbers are assigned at the time a pseudo-locked region is associated + * with a cache instance. + * + * Return: On success return pointer to resource group owning the pseudo-locked + * region, NULL on failure. + */ +static struct rdtgroup *region_find_by_minor(unsigned int minor) +{ + struct rdtgroup *rdtgrp, *rdtgrp_match = NULL; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->plr && rdtgrp->plr->minor == minor) { + rdtgrp_match = rdtgrp; + break; + } + } + return rdtgrp_match; +} + +/** + * pseudo_lock_pm_req - A power management QoS request list entry + * @list: Entry within the @pm_reqs list for a pseudo-locked region + * @req: PM QoS request + */ +struct pseudo_lock_pm_req { + struct list_head list; + struct dev_pm_qos_request req; +}; + +static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req, *next; + + list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) { + dev_pm_qos_remove_request(&pm_req->req); + list_del(&pm_req->list); + kfree(pm_req); + } +} + +/** + * pseudo_lock_cstates_constrain - Restrict cores from entering C6 + * + * To prevent the cache from being affected by power management entering + * C6 has to be avoided. This is accomplished by requesting a latency + * requirement lower than lowest C6 exit latency of all supported + * platforms as found in the cpuidle state tables in the intel_idle driver. + * At this time it is possible to do so with a single latency requirement + * for all supported platforms. + * + * Since Goldmont is supported, which is affected by X86_BUG_MONITOR, + * the ACPI latencies need to be considered while keeping in mind that C2 + * may be set to map to deeper sleep states. In this case the latency + * requirement needs to prevent entering C2 also. + */ +static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req; + int cpu; + int ret; + + for_each_cpu(cpu, &plr->d->cpu_mask) { + pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL); + if (!pm_req) { + rdt_last_cmd_puts("fail allocating mem for PM QoS\n"); + ret = -ENOMEM; + goto out_err; + } + ret = dev_pm_qos_add_request(get_cpu_device(cpu), + &pm_req->req, + DEV_PM_QOS_RESUME_LATENCY, + 30); + if (ret < 0) { + rdt_last_cmd_printf("fail to add latency req cpu%d\n", + cpu); + kfree(pm_req); + ret = -1; + goto out_err; + } + list_add(&pm_req->list, &plr->pm_reqs); + } + + return 0; + +out_err: + pseudo_lock_cstates_relax(plr); + return ret; +} + +/** + * pseudo_lock_region_clear - Reset pseudo-lock region data + * @plr: pseudo-lock region + * + * All content of the pseudo-locked region is reset - any memory allocated + * freed. + * + * Return: void + */ +static void pseudo_lock_region_clear(struct pseudo_lock_region *plr) +{ + plr->size = 0; + plr->line_size = 0; + kfree(plr->kmem); + plr->kmem = NULL; + plr->r = NULL; + if (plr->d) + plr->d->plr = NULL; + plr->d = NULL; + plr->cbm = 0; + plr->debugfs_dir = NULL; +} + +/** + * pseudo_lock_region_init - Initialize pseudo-lock region information + * @plr: pseudo-lock region + * + * Called after user provided a schemata to be pseudo-locked. From the + * schemata the &struct pseudo_lock_region is on entry already initialized + * with the resource, domain, and capacity bitmask. Here the information + * required for pseudo-locking is deduced from this data and &struct + * pseudo_lock_region initialized further. This information includes: + * - size in bytes of the region to be pseudo-locked + * - cache line size to know the stride with which data needs to be accessed + * to be pseudo-locked + * - a cpu associated with the cache instance on which the pseudo-locking + * flow can be executed + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_init(struct pseudo_lock_region *plr) +{ + struct cpu_cacheinfo *ci; + int ret; + int i; + + /* Pick the first cpu we find that is associated with the cache. */ + plr->cpu = cpumask_first(&plr->d->cpu_mask); + + if (!cpu_online(plr->cpu)) { + rdt_last_cmd_printf("cpu %u associated with cache not online\n", + plr->cpu); + ret = -ENODEV; + goto out_region; + } + + ci = get_cpu_cacheinfo(plr->cpu); + + plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm); + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == plr->r->cache_level) { + plr->line_size = ci->info_list[i].coherency_line_size; + return 0; + } + } + + ret = -1; + rdt_last_cmd_puts("unable to determine cache line size\n"); +out_region: + pseudo_lock_region_clear(plr); + return ret; +} + +/** + * pseudo_lock_init - Initialize a pseudo-lock region + * @rdtgrp: resource group to which new pseudo-locked region will belong + * + * A pseudo-locked region is associated with a resource group. When this + * association is created the pseudo-locked region is initialized. The + * details of the pseudo-locked region are not known at this time so only + * allocation is done and association established. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_init(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr; + + plr = kzalloc(sizeof(*plr), GFP_KERNEL); + if (!plr) + return -ENOMEM; + + init_waitqueue_head(&plr->lock_thread_wq); + INIT_LIST_HEAD(&plr->pm_reqs); + rdtgrp->plr = plr; + return 0; +} + +/** + * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked + * @plr: pseudo-lock region + * + * Initialize the details required to set up the pseudo-locked region and + * allocate the contiguous memory that will be pseudo-locked to the cache. + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr) +{ + int ret; + + ret = pseudo_lock_region_init(plr); + if (ret < 0) + return ret; + + /* + * We do not yet support contiguous regions larger than + * KMALLOC_MAX_SIZE. + */ + if (plr->size > KMALLOC_MAX_SIZE) { + rdt_last_cmd_puts("requested region exceeds maximum size\n"); + ret = -E2BIG; + goto out_region; + } + + plr->kmem = kzalloc(plr->size, GFP_KERNEL); + if (!plr->kmem) { + rdt_last_cmd_puts("unable to allocate memory\n"); + ret = -ENOMEM; + goto out_region; + } + + ret = 0; + goto out; +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * pseudo_lock_free - Free a pseudo-locked region + * @rdtgrp: resource group to which pseudo-locked region belonged + * + * The pseudo-locked region's resources have already been released, or not + * yet created at this point. Now it can be freed and disassociated from the + * resource group. + * + * Return: void + */ +static void pseudo_lock_free(struct rdtgroup *rdtgrp) +{ + pseudo_lock_region_clear(rdtgrp->plr); + kfree(rdtgrp->plr); + rdtgrp->plr = NULL; +} + +/** + * pseudo_lock_fn - Load kernel memory into cache + * @_rdtgrp: resource group to which pseudo-lock region belongs + * + * This is the core pseudo-locking flow. + * + * First we ensure that the kernel memory cannot be found in the cache. + * Then, while taking care that there will be as little interference as + * possible, the memory to be loaded is accessed while core is running + * with class of service set to the bitmask of the pseudo-locked region. + * After this is complete no future CAT allocations will be allowed to + * overlap with this bitmask. + * + * Local register variables are utilized to ensure that the memory region + * to be locked is the only memory access made during the critical locking + * loop. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int pseudo_lock_fn(void *_rdtgrp) +{ + struct rdtgroup *rdtgrp = _rdtgrp; + struct pseudo_lock_region *plr = rdtgrp->plr; + u32 rmid_p, closid_p; + unsigned long i; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use a regular + * variable to ensure we always use a valid pointer, but the cost + * is that this variable will enter the cache through evicting the + * memory we are trying to lock into the cache. Thus expect lower + * pseudo-locking success rate when KASAN is active. + */ + unsigned int line_size; + unsigned int size; + void *mem_r; +#else + register unsigned int line_size asm("esi"); + register unsigned int size asm("edi"); +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + /* + * Make sure none of the allocated memory is cached. If it is we + * will get a cache hit in below loop from outside of pseudo-locked + * region. + * wbinvd (as opposed to clflush/clflushopt) is required to + * increase likelihood that allocated cache portion will be filled + * with associated memory. + */ + native_wbinvd(); + + /* + * Always called with interrupts enabled. By disabling interrupts + * ensure that we will not be preempted during this critical section. + */ + local_irq_disable(); + + /* + * Call wrmsr and rdmsr as directly as possible to avoid tracing + * clobbering local register variables or affecting cache accesses. + * + * Disable the hardware prefetcher so that when the end of the memory + * being pseudo-locked is reached the hardware will not read beyond + * the buffer and evict pseudo-locked memory read earlier from the + * cache. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + closid_p = this_cpu_read(pqr_state.cur_closid); + rmid_p = this_cpu_read(pqr_state.cur_rmid); + mem_r = plr->kmem; + size = plr->size; + line_size = plr->line_size; + /* + * Critical section begin: start by writing the closid associated + * with the capacity bitmask of the cache region being + * pseudo-locked followed by reading of kernel memory to load it + * into the cache. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); + /* + * Cache was flushed earlier. Now access kernel memory to read it + * into cache region associated with just activated plr->closid. + * Loop over data twice: + * - In first loop the cache region is shared with the page walker + * as it populates the paging structure caches (including TLB). + * - In the second loop the paging structure caches are used and + * cache region is populated with the memory being referenced. + */ + for (i = 0; i < size; i += PAGE_SIZE) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + for (i = 0; i < size; i += line_size) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Critical section end: restore closid with capacity bitmask that + * does not overlap with pseudo-locked region. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p); + + /* Re-enable the hardware prefetcher(s) */ + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * rdtgroup_monitor_in_progress - Test if monitoring in progress + * @r: resource group being queried + * + * Return: 1 if monitor groups have been created for this resource + * group, 0 otherwise. + */ +static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp) +{ + return !list_empty(&rdtgrp->mon.crdtgrp_list); +} + +/** + * rdtgroup_locksetup_user_restrict - Restrict user access to group + * @rdtgrp: resource group needing access restricted + * + * A resource group used for cache pseudo-locking cannot have cpus or tasks + * assigned to it. This is communicated to the user by restricting access + * to all the files that can be used to make such changes. + * + * Permissions restored with rdtgroup_locksetup_user_restore() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restriction of access an attempt will be made to restore permissions but + * the state of the mode of these files will be uncertain when a failure + * occurs. + */ +static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups"); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); +err_cpus: + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); +err_tasks: + rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); +out: + return ret; +} + +/** + * rdtgroup_locksetup_user_restore - Restore user access to group + * @rdtgrp: resource group needing access restored + * + * Restore all file access previously removed using + * rdtgroup_locksetup_user_restrict() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restoration of access an attempt will be made to restrict permissions + * again but the state of the mode of these files will be uncertain when + * a failure occurs. + */ +static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); +err_cpus: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); +err_tasks: + rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); +out: + return ret; +} + +/** + * rdtgroup_locksetup_enter - Resource group enters locksetup mode + * @rdtgrp: resource group requested to enter locksetup mode + * + * A resource group enters locksetup mode to reflect that it would be used + * to represent a pseudo-locked region and is in the process of being set + * up to do so. A resource group used for a pseudo-locked region would + * lose the closid associated with it so we cannot allow it to have any + * tasks or cpus assigned nor permit tasks or cpus to be assigned in the + * future. Monitoring of a pseudo-locked region is not allowed either. + * + * The above and more restrictions on a pseudo-locked region are checked + * for and enforced before the resource group enters the locksetup mode. + * + * Returns: 0 if the resource group successfully entered locksetup mode, <0 + * on failure. On failure the last_cmd_status buffer is updated with text to + * communicate details of failure to the user. + */ +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) +{ + int ret; + + /* + * The default resource group can neither be removed nor lose the + * default closid associated with it. + */ + if (rdtgrp == &rdtgroup_default) { + rdt_last_cmd_puts("cannot pseudo-lock default group\n"); + return -EINVAL; + } + + /* + * Cache Pseudo-locking not supported when CDP is enabled. + * + * Some things to consider if you would like to enable this + * support (using L3 CDP as example): + * - When CDP is enabled two separate resources are exposed, + * L3DATA and L3CODE, but they are actually on the same cache. + * The implication for pseudo-locking is that if a + * pseudo-locked region is created on a domain of one + * resource (eg. L3CODE), then a pseudo-locked region cannot + * be created on that same domain of the other resource + * (eg. L3DATA). This is because the creation of a + * pseudo-locked region involves a call to wbinvd that will + * affect all cache allocations on particular domain. + * - Considering the previous, it may be possible to only + * expose one of the CDP resources to pseudo-locking and + * hide the other. For example, we could consider to only + * expose L3DATA and since the L3 cache is unified it is + * still possible to place instructions there are execute it. + * - If only one region is exposed to pseudo-locking we should + * still keep in mind that availability of a portion of cache + * for pseudo-locking should take into account both resources. + * Similarly, if a pseudo-locked region is created in one + * resource, the portion of cache used by it should be made + * unavailable to all future allocations from both resources. + */ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled || + rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) { + rdt_last_cmd_puts("CDP enabled\n"); + return -EINVAL; + } + + /* + * Not knowing the bits to disable prefetching implies that this + * platform does not support Cache Pseudo-Locking. + */ + prefetch_disable_bits = get_prefetch_disable_bits(); + if (prefetch_disable_bits == 0) { + rdt_last_cmd_puts("pseudo-locking not supported\n"); + return -EINVAL; + } + + if (rdtgroup_monitor_in_progress(rdtgrp)) { + rdt_last_cmd_puts("monitoring in progress\n"); + return -EINVAL; + } + + if (rdtgroup_tasks_assigned(rdtgrp)) { + rdt_last_cmd_puts("tasks assigned to resource group\n"); + return -EINVAL; + } + + if (!cpumask_empty(&rdtgrp->cpu_mask)) { + rdt_last_cmd_puts("CPUs assigned to resource group\n"); + return -EINVAL; + } + + if (rdtgroup_locksetup_user_restrict(rdtgrp)) { + rdt_last_cmd_puts("unable to modify resctrl permissions\n"); + return -EIO; + } + + ret = pseudo_lock_init(rdtgrp); + if (ret) { + rdt_last_cmd_puts("unable to init pseudo-lock region\n"); + goto out_release; + } + + /* + * If this system is capable of monitoring a rmid would have been + * allocated when the control group was created. This is not needed + * anymore when this group would be used for pseudo-locking. This + * is safe to call on platforms not capable of monitoring. + */ + free_rmid(rdtgrp->mon.rmid); + + ret = 0; + goto out; + +out_release: + rdtgroup_locksetup_user_restore(rdtgrp); +out: + return ret; +} + +/** + * rdtgroup_locksetup_exit - resource group exist locksetup mode + * @rdtgrp: resource group + * + * When a resource group exits locksetup mode the earlier restrictions are + * lifted. + * + * Return: 0 on success, <0 on failure + */ +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) +{ + int ret; + + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) { + rdt_last_cmd_puts("out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + } + + ret = rdtgroup_locksetup_user_restore(rdtgrp); + if (ret) { + free_rmid(rdtgrp->mon.rmid); + return ret; + } + + pseudo_lock_free(rdtgrp); + return 0; +} + +/** + * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked + * @d: RDT domain + * @_cbm: CBM to test + * + * @d represents a cache instance and @_cbm a capacity bitmask that is + * considered for it. Determine if @_cbm overlaps with any existing + * pseudo-locked region on @d. + * + * Return: true if @_cbm overlaps with pseudo-locked region on @d, false + * otherwise. + */ +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm) +{ + unsigned long *cbm = (unsigned long *)&_cbm; + unsigned long *cbm_b; + unsigned int cbm_len; + + if (d->plr) { + cbm_len = d->plr->r->cache.cbm_len; + cbm_b = (unsigned long *)&d->plr->cbm; + if (bitmap_intersects(cbm, cbm_b, cbm_len)) + return true; + } + return false; +} + +/** + * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy + * @d: RDT domain under test + * + * The setup of a pseudo-locked region affects all cache instances within + * the hierarchy of the region. It is thus essential to know if any + * pseudo-locked regions exist within a cache hierarchy to prevent any + * attempts to create new pseudo-locked regions in the same hierarchy. + * + * Return: true if a pseudo-locked region exists in the hierarchy of @d or + * if it is not possible to test due to memory allocation issue, + * false otherwise. + */ +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) +{ + cpumask_var_t cpu_with_psl; + struct rdt_resource *r; + struct rdt_domain *d_i; + bool ret = false; + + if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL)) + return true; + + /* + * First determine which cpus have pseudo-locked regions + * associated with them. + */ + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d_i, &r->domains, list) { + if (d_i->plr) + cpumask_or(cpu_with_psl, cpu_with_psl, + &d_i->cpu_mask); + } + } + + /* + * Next test if new pseudo-locked region would intersect with + * existing region. + */ + if (cpumask_intersects(&d->cpu_mask, cpu_with_psl)) + ret = true; + + free_cpumask_var(cpu_with_psl); + return ret; +} + +/** + * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory + * @_plr: pseudo-lock region to measure + * + * There is no deterministic way to test if a memory region is cached. One + * way is to measure how long it takes to read the memory, the speed of + * access is a good way to learn how close to the cpu the data was. Even + * more, if the prefetcher is disabled and the memory is read at a stride + * of half the cache line, then a cache miss will be easy to spot since the + * read of the first half would be significantly slower than the read of + * the second half. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int measure_cycles_lat_fn(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + unsigned long i; + u64 start, end; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use a regular + * variable to ensure we always use a valid pointer to access memory. + * The cost is that accessing this pointer, which could be in + * cache, will be included in the measurement of memory read latency. + */ + void *mem_r; +#else +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + local_irq_disable(); + /* + * The wrmsr call may be reordered with the assignment below it. + * Call wrmsr as directly as possible to avoid tracing clobbering + * local register variable used for memory pointer. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + mem_r = plr->kmem; + /* + * Dummy execute of the time measurement to load the needed + * instructions into the L1 instruction cache. + */ + start = rdtsc_ordered(); + for (i = 0; i < plr->size; i += 32) { + start = rdtsc_ordered(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + end = rdtsc_ordered(); + trace_pseudo_lock_mem_latency((u32)(end - start)); + } + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +static int measure_cycles_perf_fn(void *_plr) +{ + unsigned long long l3_hits = 0, l3_miss = 0; + u64 l3_hit_bits = 0, l3_miss_bits = 0; + struct pseudo_lock_region *plr = _plr; + unsigned long long l2_hits, l2_miss; + u64 l2_hit_bits, l2_miss_bits; + unsigned long i; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use regular variables + * at the cost of including cache access latency to these variables + * in the measurements. + */ + unsigned int line_size; + unsigned int size; + void *mem_r; +#else + register unsigned int line_size asm("esi"); + register unsigned int size asm("edi"); +#ifdef CONFIG_X86_64 + register void *mem_r asm("rbx"); +#else + register void *mem_r asm("ebx"); +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_KASAN */ + + /* + * Non-architectural event for the Goldmont Microarchitecture + * from Intel x86 Architecture Software Developer Manual (SDM): + * MEM_LOAD_UOPS_RETIRED D1H (event number) + * Umask values: + * L1_HIT 01H + * L2_HIT 02H + * L1_MISS 08H + * L2_MISS 10H + * + * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event + * has two "no fix" errata associated with it: BDM35 and BDM100. On + * this platform we use the following events instead: + * L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/) + * REFERENCES FFH + * MISS 3FH + * LONGEST_LAT_CACHE 2EH (Documented in SDM) + * REFERENCE 4FH + * MISS 41H + */ + + /* + * Start by setting flags for IA32_PERFEVTSELx: + * OS (Operating system mode) 0x2 + * INT (APIC interrupt enable) 0x10 + * EN (Enable counter) 0x40 + * + * Then add the Umask value and event number to select performance + * event. + */ + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GEMINI_LAKE: + l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1; + l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1; + break; + case INTEL_FAM6_BROADWELL_X: + /* On BDW the l2_hit_bits count references, not hits */ + l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24; + l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24; + /* On BDW the l3_hit_bits count references, not hits */ + l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e; + l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e; + break; + default: + goto out; + } + + local_irq_disable(); + /* + * Call wrmsr direcly to avoid the local register variables from + * being overwritten due to reordering of their assignment with + * the wrmsr calls. + */ + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + /* Disable events and reset counters */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0); + } + /* Set and enable the L2 counters */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, + l3_hit_bits); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, + l3_miss_bits); + } + mem_r = plr->kmem; + size = plr->size; + line_size = plr->line_size; + for (i = 0; i < size; i += line_size) { + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Call wrmsr directly (no tracing) to not influence + * the cache access counters as they are disabled. + */ + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, + l2_hit_bits & ~(0x40ULL << 16)); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, + l2_miss_bits & ~(0x40ULL << 16)); + if (l3_hit_bits > 0) { + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, + l3_hit_bits & ~(0x40ULL << 16)); + pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, + l3_miss_bits & ~(0x40ULL << 16)); + } + l2_hits = native_read_pmc(0); + l2_miss = native_read_pmc(1); + if (l3_hit_bits > 0) { + l3_hits = native_read_pmc(2); + l3_miss = native_read_pmc(3); + } + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); + /* + * On BDW we count references and misses, need to adjust. Sometimes + * the "hits" counter is a bit more than the references, for + * example, x references but x + 1 hits. To not report invalid + * hit values in this case we treat that as misses eaqual to + * references. + */ + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) + l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss); + trace_pseudo_lock_l2(l2_hits, l2_miss); + if (l3_hit_bits > 0) { + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) + l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss); + trace_pseudo_lock_l3(l3_hits, l3_miss); + } + +out: + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region + * + * The measurement of latency to access a pseudo-locked region should be + * done from a cpu that is associated with that pseudo-locked region. + * Determine which cpu is associated with this region and start a thread on + * that cpu to perform the measurement, wait for that thread to complete. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int cpu; + int ret = -1; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out; + } + + plr->thread_done = 0; + cpu = cpumask_first(&plr->d->cpu_mask); + if (!cpu_online(cpu)) { + ret = -ENODEV; + goto out; + } + + if (sel == 1) + thread = kthread_create_on_node(measure_cycles_lat_fn, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else if (sel == 2) + thread = kthread_create_on_node(measure_cycles_perf_fn, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else + goto out; + + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + goto out; + } + kthread_bind(thread, cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) + goto out; + + ret = 0; + +out: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + return ret; +} + +static ssize_t pseudo_lock_measure_trigger(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct rdtgroup *rdtgrp = file->private_data; + size_t buf_size; + char buf[32]; + int ret; + int sel; + + buf_size = min(count, (sizeof(buf) - 1)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + ret = kstrtoint(buf, 10, &sel); + if (ret == 0) { + if (sel != 1) + return -EINVAL; + ret = debugfs_file_get(file->f_path.dentry); + if (ret) + return ret; + ret = pseudo_lock_measure_cycles(rdtgrp, sel); + if (ret == 0) + ret = count; + debugfs_file_put(file->f_path.dentry); + } + + return ret; +} + +static const struct file_operations pseudo_measure_fops = { + .write = pseudo_lock_measure_trigger, + .open = simple_open, + .llseek = default_llseek, +}; + +/** + * rdtgroup_pseudo_lock_create - Create a pseudo-locked region + * @rdtgrp: resource group to which pseudo-lock region belongs + * + * Called when a resource group in the pseudo-locksetup mode receives a + * valid schemata that should be pseudo-locked. Since the resource group is + * in pseudo-locksetup mode the &struct pseudo_lock_region has already been + * allocated and initialized with the essential information. If a failure + * occurs the resource group remains in the pseudo-locksetup mode with the + * &struct pseudo_lock_region associated with it, but cleared from all + * information and ready for the user to re-attempt pseudo-locking by + * writing the schemata again. + * + * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0 + * on failure. Descriptive error will be written to last_cmd_status buffer. + */ +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int new_minor; + struct device *dev; + int ret; + + ret = pseudo_lock_region_alloc(plr); + if (ret < 0) + return ret; + + ret = pseudo_lock_cstates_constrain(plr); + if (ret < 0) { + ret = -EINVAL; + goto out_region; + } + + plr->thread_done = 0; + + thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp, + cpu_to_node(plr->cpu), + "pseudo_lock/%u", plr->cpu); + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + rdt_last_cmd_printf("locking thread returned error %d\n", ret); + goto out_cstates; + } + + kthread_bind(thread, plr->cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) { + /* + * If the thread does not get on the CPU for whatever + * reason and the process which sets up the region is + * interrupted then this will leave the thread in runnable + * state and once it gets on the CPU it will derefence + * the cleared, but not freed, plr struct resulting in an + * empty pseudo-locking loop. + */ + rdt_last_cmd_puts("locking thread interrupted\n"); + goto out_cstates; + } + + ret = pseudo_lock_minor_get(&new_minor); + if (ret < 0) { + rdt_last_cmd_puts("unable to obtain a new minor number\n"); + goto out_cstates; + } + + /* + * Unlock access but do not release the reference. The + * pseudo-locked region will still be here on return. + * + * The mutex has to be released temporarily to avoid a potential + * deadlock with the mm->mmap_sem semaphore which is obtained in + * the device_create() and debugfs_create_dir() callpath below + * as well as before the mmap() callback is called. + */ + mutex_unlock(&rdtgroup_mutex); + + if (!IS_ERR_OR_NULL(debugfs_resctrl)) { + plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name, + debugfs_resctrl); + if (!IS_ERR_OR_NULL(plr->debugfs_dir)) + debugfs_create_file("pseudo_lock_measure", 0200, + plr->debugfs_dir, rdtgrp, + &pseudo_measure_fops); + } + + dev = device_create(pseudo_lock_class, NULL, + MKDEV(pseudo_lock_major, new_minor), + rdtgrp, "%s", rdtgrp->kn->name); + + mutex_lock(&rdtgroup_mutex); + + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + rdt_last_cmd_printf("failed to create character device: %d\n", + ret); + goto out_debugfs; + } + + /* We released the mutex - check if group was removed while we did so */ + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out_device; + } + + plr->minor = new_minor; + + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED; + closid_free(rdtgrp->closid); + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444); + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444); + + ret = 0; + goto out; + +out_device: + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor)); +out_debugfs: + debugfs_remove_recursive(plr->debugfs_dir); + pseudo_lock_minor_release(new_minor); +out_cstates: + pseudo_lock_cstates_relax(plr); +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region + * @rdtgrp: resource group to which the pseudo-locked region belongs + * + * The removal of a pseudo-locked region can be initiated when the resource + * group is removed from user space via a "rmdir" from userspace or the + * unmount of the resctrl filesystem. On removal the resource group does + * not go back to pseudo-locksetup mode before it is removed, instead it is + * removed directly. There is thus assymmetry with the creation where the + * &struct pseudo_lock_region is removed here while it was not created in + * rdtgroup_pseudo_lock_create(). + * + * Return: void + */ +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * Default group cannot be a pseudo-locked region so we can + * free closid here. + */ + closid_free(rdtgrp->closid); + goto free; + } + + pseudo_lock_cstates_relax(plr); + debugfs_remove_recursive(rdtgrp->plr->debugfs_dir); + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor)); + pseudo_lock_minor_release(plr->minor); + +free: + pseudo_lock_free(rdtgrp); +} + +static int pseudo_lock_dev_open(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = region_find_by_minor(iminor(inode)); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + filp->private_data = rdtgrp; + atomic_inc(&rdtgrp->waitcount); + /* Perform a non-seekable open - llseek is not supported */ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); + + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int pseudo_lock_dev_release(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + filp->private_data = NULL; + atomic_dec(&rdtgrp->waitcount); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static int pseudo_lock_dev_mremap(struct vm_area_struct *area) +{ + /* Not supported */ + return -EINVAL; +} + +static const struct vm_operations_struct pseudo_mmap_ops = { + .mremap = pseudo_lock_dev_mremap, +}; + +static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) +{ + unsigned long vsize = vma->vm_end - vma->vm_start; + unsigned long off = vma->vm_pgoff << PAGE_SHIFT; + struct pseudo_lock_region *plr; + struct rdtgroup *rdtgrp; + unsigned long physical; + unsigned long psize; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + plr = rdtgrp->plr; + + /* + * Task is required to run with affinity to the cpus associated + * with the pseudo-locked region. If this is not the case the task + * may be scheduled elsewhere and invalidate entries in the + * pseudo-locked region. + */ + if (!cpumask_subset(¤t->cpus_allowed, &plr->d->cpu_mask)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + physical = __pa(plr->kmem) >> PAGE_SHIFT; + psize = plr->size - off; + + if (off > plr->size) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + /* + * Ensure changes are carried directly to the memory being mapped, + * do not allow copy-on-write mapping. + */ + if (!(vma->vm_flags & VM_SHARED)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + if (vsize > psize) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + memset(plr->kmem + off, 0, vsize); + + if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff, + vsize, vma->vm_page_prot)) { + mutex_unlock(&rdtgroup_mutex); + return -EAGAIN; + } + vma->vm_ops = &pseudo_mmap_ops; + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static const struct file_operations pseudo_lock_dev_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = NULL, + .write = NULL, + .open = pseudo_lock_dev_open, + .release = pseudo_lock_dev_release, + .mmap = pseudo_lock_dev_mmap, +}; + +static char *pseudo_lock_devnode(struct device *dev, umode_t *mode) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = dev_get_drvdata(dev); + if (mode) + *mode = 0600; + return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name); +} + +int rdt_pseudo_lock_init(void) +{ + int ret; + + ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops); + if (ret < 0) + return ret; + + pseudo_lock_major = ret; + + pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock"); + if (IS_ERR(pseudo_lock_class)) { + ret = PTR_ERR(pseudo_lock_class); + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + return ret; + } + + pseudo_lock_class->devnode = pseudo_lock_devnode; + return 0; +} + +void rdt_pseudo_lock_release(void) +{ + class_destroy(pseudo_lock_class); + pseudo_lock_class = NULL; + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + pseudo_lock_major = 0; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h new file mode 100644 index 000000000000..2c041e6d9f05 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM resctrl + +#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PSEUDO_LOCK_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(pseudo_lock_mem_latency, + TP_PROTO(u32 latency), + TP_ARGS(latency), + TP_STRUCT__entry(__field(u32, latency)), + TP_fast_assign(__entry->latency = latency), + TP_printk("latency=%u", __entry->latency) + ); + +TRACE_EVENT(pseudo_lock_l2, + TP_PROTO(u64 l2_hits, u64 l2_miss), + TP_ARGS(l2_hits, l2_miss), + TP_STRUCT__entry(__field(u64, l2_hits) + __field(u64, l2_miss)), + TP_fast_assign(__entry->l2_hits = l2_hits; + __entry->l2_miss = l2_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l2_hits, __entry->l2_miss)); + +TRACE_EVENT(pseudo_lock_l3, + TP_PROTO(u64 l3_hits, u64 l3_miss), + TP_ARGS(l3_hits, l3_miss), + TP_STRUCT__entry(__field(u64, l3_hits) + __field(u64, l3_miss)), + TP_fast_assign(__entry->l3_hits = l3_hits; + __entry->l3_miss = l3_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l3_hits, __entry->l3_miss)); + +#endif /* _TRACE_PSEUDO_LOCK_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event +#include <trace/define_trace.h> diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 749856a2e736..b799c00bef09 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -20,7 +20,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/cacheinfo.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernfs.h> @@ -55,6 +57,8 @@ static struct kernfs_node *kn_mondata; static struct seq_buf last_cmd_status; static char last_cmd_status_buf[512]; +struct dentry *debugfs_resctrl; + void rdt_last_cmd_clear(void) { lockdep_assert_held(&rdtgroup_mutex); @@ -121,11 +125,65 @@ static int closid_alloc(void) return closid; } -static void closid_free(int closid) +void closid_free(int closid) { closid_free_map |= 1 << closid; } +/** + * closid_allocated - test if provided closid is in use + * @closid: closid to be tested + * + * Return: true if @closid is currently associated with a resource group, + * false if @closid is free + */ +static bool closid_allocated(unsigned int closid) +{ + return (closid_free_map & (1 << closid)) == 0; +} + +/** + * rdtgroup_mode_by_closid - Return mode of resource group with closid + * @closid: closid if the resource group + * + * Each resource group is associated with a @closid. Here the mode + * of a resource group can be queried by searching for it using its closid. + * + * Return: mode as &enum rdtgrp_mode of resource group with closid @closid + */ +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid) +{ + struct rdtgroup *rdtgrp; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->closid == closid) + return rdtgrp->mode; + } + + return RDT_NUM_MODES; +} + +static const char * const rdt_mode_str[] = { + [RDT_MODE_SHAREABLE] = "shareable", + [RDT_MODE_EXCLUSIVE] = "exclusive", + [RDT_MODE_PSEUDO_LOCKSETUP] = "pseudo-locksetup", + [RDT_MODE_PSEUDO_LOCKED] = "pseudo-locked", +}; + +/** + * rdtgroup_mode_str - Return the string representation of mode + * @mode: the resource group mode as &enum rdtgroup_mode + * + * Return: string representation of valid mode, "unknown" otherwise + */ +static const char *rdtgroup_mode_str(enum rdtgrp_mode mode) +{ + if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES) + return "unknown"; + + return rdt_mode_str[mode]; +} + /* set uid and gid of rdtgroup dirs and files to that of the creator */ static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) { @@ -146,6 +204,7 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) int ret; kn = __kernfs_create_file(parent_kn, rft->name, rft->mode, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, rft->kf_ops, rft, NULL, NULL); if (IS_ERR(kn)) return PTR_ERR(kn); @@ -207,8 +266,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", - cpumask_pr_args(&rdtgrp->cpu_mask)); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->plr->d->cpu_mask)); + else + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->cpu_mask)); } else { ret = -ENOENT; } @@ -394,6 +457,13 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, goto unlock; } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto unlock; + } + if (is_cpu_list(of)) ret = cpulist_parse(buf, newmask); else @@ -509,6 +579,32 @@ static int __rdtgroup_move_task(struct task_struct *tsk, return ret; } +/** + * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group + * @r: Resource group + * + * Return: 1 if tasks have been assigned to @r, 0 otherwise + */ +int rdtgroup_tasks_assigned(struct rdtgroup *r) +{ + struct task_struct *p, *t; + int ret = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + rcu_read_lock(); + for_each_process_thread(p, t) { + if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || + (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) { + ret = 1; + break; + } + } + rcu_read_unlock(); + + return ret; +} + static int rdtgroup_task_write_permission(struct task_struct *task, struct kernfs_open_file *of) { @@ -570,13 +666,22 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } rdt_last_cmd_clear(); - if (rdtgrp) - ret = rdtgroup_move_task(pid, rdtgrp, of); - else - ret = -ENOENT; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto unlock; + } + ret = rdtgroup_move_task(pid, rdtgrp, of); + +unlock: rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; @@ -662,6 +767,94 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, return 0; } +/** + * rdt_bit_usage_show - Display current usage of resources + * + * A domain is a shared resource that can now be allocated differently. Here + * we display the current regions of the domain as an annotated bitmask. + * For each domain of this resource its allocation bitmask + * is annotated as below to indicate the current usage of the corresponding bit: + * 0 - currently unused + * X - currently available for sharing and used by software and hardware + * H - currently used by hardware only but available for software use + * S - currently used and shareable by software only + * E - currently used exclusively by one resource group + * P - currently pseudo-locked by one resource group + */ +static int rdt_bit_usage_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + u32 sw_shareable = 0, hw_shareable = 0; + u32 exclusive = 0, pseudo_locked = 0; + struct rdt_domain *dom; + int i, hwb, swb, excl, psl; + enum rdtgrp_mode mode; + bool sep = false; + u32 *ctrl; + + mutex_lock(&rdtgroup_mutex); + hw_shareable = r->cache.shareable_bits; + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_putc(seq, ';'); + ctrl = dom->ctrl_val; + sw_shareable = 0; + exclusive = 0; + seq_printf(seq, "%d=", dom->id); + for (i = 0; i < r->num_closid; i++, ctrl++) { + if (!closid_allocated(i)) + continue; + mode = rdtgroup_mode_by_closid(i); + switch (mode) { + case RDT_MODE_SHAREABLE: + sw_shareable |= *ctrl; + break; + case RDT_MODE_EXCLUSIVE: + exclusive |= *ctrl; + break; + case RDT_MODE_PSEUDO_LOCKSETUP: + /* + * RDT_MODE_PSEUDO_LOCKSETUP is possible + * here but not included since the CBM + * associated with this CLOSID in this mode + * is not initialized and no task or cpu can be + * assigned this CLOSID. + */ + break; + case RDT_MODE_PSEUDO_LOCKED: + case RDT_NUM_MODES: + WARN(1, + "invalid mode for closid %d\n", i); + break; + } + } + for (i = r->cache.cbm_len - 1; i >= 0; i--) { + pseudo_locked = dom->plr ? dom->plr->cbm : 0; + hwb = test_bit(i, (unsigned long *)&hw_shareable); + swb = test_bit(i, (unsigned long *)&sw_shareable); + excl = test_bit(i, (unsigned long *)&exclusive); + psl = test_bit(i, (unsigned long *)&pseudo_locked); + if (hwb && swb) + seq_putc(seq, 'X'); + else if (hwb && !swb) + seq_putc(seq, 'H'); + else if (!hwb && swb) + seq_putc(seq, 'S'); + else if (excl) + seq_putc(seq, 'E'); + else if (psl) + seq_putc(seq, 'P'); + else /* Unused bits remain */ + seq_putc(seq, '0'); + } + sep = true; + } + seq_putc(seq, '\n'); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -740,6 +933,269 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, return nbytes; } +/* + * rdtgroup_mode_show - Display mode of this resource group + */ +static int rdtgroup_mode_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode)); + + rdtgroup_kn_unlock(of->kn); + return 0; +} + +/** + * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Checks if provided @cbm intended to be used for @closid on domain + * @d overlaps with any other closids or other hardware usage associated + * with this domain. If @exclusive is true then only overlaps with + * resource groups in exclusive mode will be considered. If @exclusive + * is false then overlaps with any resource group or hardware entities + * will be considered. + * + * Return: false if CBM does not overlap, true if it does. + */ +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + u32 _cbm, int closid, bool exclusive) +{ + unsigned long *cbm = (unsigned long *)&_cbm; + unsigned long *ctrl_b; + enum rdtgrp_mode mode; + u32 *ctrl; + int i; + + /* Check for any overlap with regions used by hardware directly */ + if (!exclusive) { + if (bitmap_intersects(cbm, + (unsigned long *)&r->cache.shareable_bits, + r->cache.cbm_len)) + return true; + } + + /* Check for overlap with other resource groups */ + ctrl = d->ctrl_val; + for (i = 0; i < r->num_closid; i++, ctrl++) { + ctrl_b = (unsigned long *)ctrl; + mode = rdtgroup_mode_by_closid(i); + if (closid_allocated(i) && i != closid && + mode != RDT_MODE_PSEUDO_LOCKSETUP) { + if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) { + if (exclusive) { + if (mode == RDT_MODE_EXCLUSIVE) + return true; + continue; + } + return true; + } + } + } + + return false; +} + +/** + * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive + * + * An exclusive resource group implies that there should be no sharing of + * its allocated resources. At the time this group is considered to be + * exclusive this test can determine if its current schemata supports this + * setting by testing for overlap with all other resource groups. + * + * Return: true if resource group can be exclusive, false if there is overlap + * with allocations of other resource groups and thus this resource group + * cannot be exclusive. + */ +static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) +{ + int closid = rdtgrp->closid; + struct rdt_resource *r; + struct rdt_domain *d; + + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d, &r->domains, list) { + if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], + rdtgrp->closid, false)) + return false; + } + } + + return true; +} + +/** + * rdtgroup_mode_write - Modify the resource group's mode + * + */ +static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + enum rdtgrp_mode mode; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + rdt_last_cmd_clear(); + + mode = rdtgrp->mode; + + if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) || + (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) || + (!strcmp(buf, "pseudo-locksetup") && + mode == RDT_MODE_PSEUDO_LOCKSETUP) || + (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED)) + goto out; + + if (mode == RDT_MODE_PSEUDO_LOCKED) { + rdt_last_cmd_printf("cannot change pseudo-locked group\n"); + ret = -EINVAL; + goto out; + } + + if (!strcmp(buf, "shareable")) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } else if (!strcmp(buf, "exclusive")) { + if (!rdtgroup_mode_test_exclusive(rdtgrp)) { + rdt_last_cmd_printf("schemata overlaps\n"); + ret = -EINVAL; + goto out; + } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_EXCLUSIVE; + } else if (!strcmp(buf, "pseudo-locksetup")) { + ret = rdtgroup_locksetup_enter(rdtgrp); + if (ret) + goto out; + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP; + } else { + rdt_last_cmd_printf("unknown/unsupported mode\n"); + ret = -EINVAL; + } + +out: + rdtgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +/** + * rdtgroup_cbm_to_size - Translate CBM to size in bytes + * @r: RDT resource to which @d belongs. + * @d: RDT domain instance. + * @cbm: bitmask for which the size should be computed. + * + * The bitmask provided associated with the RDT domain instance @d will be + * translated into how many bytes it represents. The size in bytes is + * computed by first dividing the total cache size by the CBM length to + * determine how many bytes each bit in the bitmask represents. The result + * is multiplied with the number of bits set in the bitmask. + */ +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, + struct rdt_domain *d, u32 cbm) +{ + struct cpu_cacheinfo *ci; + unsigned int size = 0; + int num_b, i; + + num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len); + ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == r->cache_level) { + size = ci->info_list[i].size / r->cache.cbm_len * num_b; + break; + } + } + + return size; +} + +/** + * rdtgroup_size_show - Display size in bytes of allocated regions + * + * The "size" file mirrors the layout of the "schemata" file, printing the + * size in bytes of each region instead of the capacity bitmask. + * + */ +static int rdtgroup_size_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + struct rdt_domain *d; + unsigned int size; + bool sep = false; + u32 cbm; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + goto out; + } + + for_each_alloc_enabled_rdt_resource(r) { + seq_printf(s, "%*s:", max_name_width, r->name); + list_for_each_entry(d, &r->domains, list) { + if (sep) + seq_putc(s, ';'); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + size = 0; + } else { + cbm = d->ctrl_val[rdtgrp->closid]; + size = rdtgroup_cbm_to_size(r, d, cbm); + } + seq_printf(s, "%d=%u", d->id, size); + sep = true; + } + seq_putc(s, '\n'); + } + +out: + rdtgroup_kn_unlock(of->kn); + + return 0; +} + /* rdtgroup information files for one cache resource. */ static struct rftype res_common_files[] = { { @@ -792,6 +1248,13 @@ static struct rftype res_common_files[] = { .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { + .name = "bit_usage", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bit_usage_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, @@ -853,6 +1316,22 @@ static struct rftype res_common_files[] = { .seq_show = rdtgroup_schemata_show, .fflags = RF_CTRL_BASE, }, + { + .name = "mode", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mode_write, + .seq_show = rdtgroup_mode_show, + .fflags = RF_CTRL_BASE, + }, + { + .name = "size", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_size_show, + .fflags = RF_CTRL_BASE, + }, + }; static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) @@ -883,6 +1362,103 @@ error: return ret; } +/** + * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * + * The permissions of named resctrl file, directory, or link are modified + * to not allow read, write, or execute by any user. + * + * WARNING: This function is intended to communicate to the user that the + * resctrl file has been locked down - that it is not relevant to the + * particular state the system finds itself in. It should not be relied + * on to protect from user access because after the file's permissions + * are restricted the user can still change the permissions using chmod + * from the command line. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn; + int ret = 0; + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + iattr.ia_mode = S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode = S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode = S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + +/** + * rdtgroup_kn_mode_restore - Restore user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * @mask: Mask of permissions that should be restored + * + * Restore the permissions of the named file. If @name is a directory the + * permissions of its parent will be used. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn, *parent; + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + for (rft = rfts; rft < rfts + len; rft++) { + if (!strcmp(rft->name, name)) + iattr.ia_mode = rft->mode & mask; + } + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + parent = kernfs_get_parent(kn); + if (parent) { + iattr.ia_mode |= parent->mode; + kernfs_put(parent); + } + iattr.ia_mode |= S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode |= S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode |= S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, unsigned long fflags) { @@ -1224,6 +1800,9 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); kernfs_put(rdtgrp->kn); kfree(rdtgrp); @@ -1289,10 +1868,16 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, rdtgroup_default.mon.mon_data_kn = kn_mondata; } + ret = rdt_pseudo_lock_init(); + if (ret) { + dentry = ERR_PTR(ret); + goto out_mondata; + } + dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_mondata; + goto out_psl; if (rdt_alloc_capable) static_branch_enable_cpuslocked(&rdt_alloc_enable_key); @@ -1310,6 +1895,8 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, goto out; +out_psl: + rdt_pseudo_lock_release(); out_mondata: if (rdt_mon_capable) kernfs_remove(kn_mondata); @@ -1447,6 +2034,10 @@ static void rmdir_all_sub(void) if (rdtgrp == &rdtgroup_default) continue; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); + /* * Give any CPUs back to the default group. We cannot copy * cpu_online_mask because a CPU might have executed the @@ -1483,6 +2074,8 @@ static void rdt_kill_sb(struct super_block *sb) reset_all_ctrls(r); cdp_disable_all(); rmdir_all_sub(); + rdt_pseudo_lock_release(); + rdtgroup_default.mode = RDT_MODE_SHAREABLE; static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); static_branch_disable_cpuslocked(&rdt_enable_key); @@ -1503,7 +2096,8 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name, struct kernfs_node *kn; int ret = 0; - kn = __kernfs_create_file(parent_kn, name, 0444, 0, + kn = __kernfs_create_file(parent_kn, name, 0444, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, &kf_mondata_ops, priv, NULL, NULL); if (IS_ERR(kn)) return PTR_ERR(kn); @@ -1682,6 +2276,114 @@ out_destroy: return ret; } +/** + * cbm_ensure_valid - Enforce validity on provided CBM + * @_val: Candidate CBM + * @r: RDT resource to which the CBM belongs + * + * The provided CBM represents all cache portions available for use. This + * may be represented by a bitmap that does not consist of contiguous ones + * and thus be an invalid CBM. + * Here the provided CBM is forced to be a valid CBM by only considering + * the first set of contiguous bits as valid and clearing all bits. + * The intention here is to provide a valid default CBM with which a new + * resource group is initialized. The user can follow this with a + * modification to the CBM if the default does not satisfy the + * requirements. + */ +static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r) +{ + /* + * Convert the u32 _val to an unsigned long required by all the bit + * operations within this function. No more than 32 bits of this + * converted value can be accessed because all bit operations are + * additionally provided with cbm_len that is initialized during + * hardware enumeration using five bits from the EAX register and + * thus never can exceed 32 bits. + */ + unsigned long *val = (unsigned long *)_val; + unsigned int cbm_len = r->cache.cbm_len; + unsigned long first_bit, zero_bit; + + if (*val == 0) + return; + + first_bit = find_first_bit(val, cbm_len); + zero_bit = find_next_zero_bit(val, cbm_len, first_bit); + + /* Clear any remaining bits to ensure contiguous region */ + bitmap_clear(val, zero_bit, cbm_len - zero_bit); +} + +/** + * rdtgroup_init_alloc - Initialize the new RDT group's allocations + * + * A new RDT group is being created on an allocation capable (CAT) + * supporting system. Set this group up to start off with all usable + * allocations. That is, all shareable and unused bits. + * + * All-zero CBM is invalid. If there are no more shareable bits available + * on any domain then the entire allocation will fail. + */ +static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) +{ + u32 used_b = 0, unused_b = 0; + u32 closid = rdtgrp->closid; + struct rdt_resource *r; + enum rdtgrp_mode mode; + struct rdt_domain *d; + int i, ret; + u32 *ctrl; + + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d, &r->domains, list) { + d->have_new_ctrl = false; + d->new_ctrl = r->cache.shareable_bits; + used_b = r->cache.shareable_bits; + ctrl = d->ctrl_val; + for (i = 0; i < r->num_closid; i++, ctrl++) { + if (closid_allocated(i) && i != closid) { + mode = rdtgroup_mode_by_closid(i); + if (mode == RDT_MODE_PSEUDO_LOCKSETUP) + break; + used_b |= *ctrl; + if (mode == RDT_MODE_SHAREABLE) + d->new_ctrl |= *ctrl; + } + } + if (d->plr && d->plr->cbm > 0) + used_b |= d->plr->cbm; + unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1); + unused_b &= BIT_MASK(r->cache.cbm_len) - 1; + d->new_ctrl |= unused_b; + /* + * Force the initial CBM to be valid, user can + * modify the CBM based on system availability. + */ + cbm_ensure_valid(&d->new_ctrl, r); + if (bitmap_weight((unsigned long *) &d->new_ctrl, + r->cache.cbm_len) < + r->cache.min_cbm_bits) { + rdt_last_cmd_printf("no space on %s:%d\n", + r->name, d->id); + return -ENOSPC; + } + d->have_new_ctrl = true; + } + } + + for_each_alloc_enabled_rdt_resource(r) { + ret = update_domains(r, rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("failed to initialize allocations\n"); + return ret; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } + + return 0; +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, struct kernfs_node *prgrp_kn, const char *name, umode_t mode, @@ -1700,6 +2402,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_unlock; } + if (rtype == RDTMON_GROUP && + (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) { + ret = -EINVAL; + rdt_last_cmd_puts("pseudo-locking in progress\n"); + goto out_unlock; + } + /* allocate the rdtgroup. */ rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); if (!rdtgrp) { @@ -1840,6 +2550,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = 0; rdtgrp->closid = closid; + ret = rdtgroup_init_alloc(rdtgrp); + if (ret < 0) + goto out_id_free; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); if (rdt_mon_capable) { @@ -1850,15 +2564,16 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); - goto out_id_free; + goto out_del_list; } } goto out_unlock; +out_del_list: + list_del(&rdtgrp->rdtgroup_list); out_id_free: closid_free(closid); - list_del(&rdtgrp->rdtgroup_list); out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); out_unlock: @@ -1945,6 +2660,21 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, return 0; } +static int rdtgroup_ctrl_remove(struct kernfs_node *kn, + struct rdtgroup *rdtgrp) +{ + rdtgrp->flags = RDT_DELETED; + list_del(&rdtgrp->rdtgroup_list); + + /* + * one extra hold on this, will drop when we kfree(rdtgrp) + * in rdtgroup_kn_unlock() + */ + kernfs_get(kn); + kernfs_remove(rdtgrp->kn); + return 0; +} + static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) { @@ -1970,7 +2700,6 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); update_closid_rmid(tmpmask, NULL); - rdtgrp->flags = RDT_DELETED; closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); @@ -1979,14 +2708,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, */ free_all_child_rdtgrp(rdtgrp); - list_del(&rdtgrp->rdtgroup_list); - - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); - kernfs_remove(rdtgrp->kn); + rdtgroup_ctrl_remove(kn, rdtgrp); return 0; } @@ -2014,13 +2736,19 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) - ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); - else if (rdtgrp->type == RDTMON_GROUP && - is_mon_groups(parent_kn, kn->name)) + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = rdtgroup_ctrl_remove(kn, rdtgrp); + } else { + ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + } + } else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, kn->name)) { ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); - else + } else { ret = -EPERM; + } out: rdtgroup_kn_unlock(kn); @@ -2046,7 +2774,8 @@ static int __init rdtgroup_setup_root(void) int ret; rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, - KERNFS_ROOT_CREATE_DEACTIVATED, + KERNFS_ROOT_CREATE_DEACTIVATED | + KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, &rdtgroup_default); if (IS_ERR(rdt_root)) return PTR_ERR(rdt_root); @@ -2102,6 +2831,29 @@ int __init rdtgroup_init(void) if (ret) goto cleanup_mountpoint; + /* + * Adding the resctrl debugfs directory here may not be ideal since + * it would let the resctrl debugfs directory appear on the debugfs + * filesystem before the resctrl filesystem is mounted. + * It may also be ok since that would enable debugging of RDT before + * resctrl is mounted. + * The reason why the debugfs directory is created here and not in + * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and + * during the debugfs directory creation also &sb->s_type->i_mutex_key + * (the lockdep class of inode->i_rwsem). Other filesystem + * interactions (eg. SyS_getdents) have the lock ordering: + * &sb->s_type->i_mutex_key --> &mm->mmap_sem + * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex + * is taken, thus creating dependency: + * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause + * issues considering the other two lock dependencies. + * By creating the debugfs directory here we avoid a dependency + * that may cause deadlock (even though file operations cannot + * occur until the filesystem is mounted, but I do not know how to + * tell lockdep that). + */ + debugfs_resctrl = debugfs_create_dir("resctrl", NULL); + return 0; cleanup_mountpoint: @@ -2111,3 +2863,11 @@ cleanup_root: return ret; } + +void __exit rdtgroup_exit(void) +{ + debugfs_remove_recursive(debugfs_resctrl); + unregister_filesystem(&rdt_fs_type); + sysfs_remove_mount_point(fs_kobj, "resctrl"); + kernfs_destroy_root(rdt_root); +} diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8c50754c09c1..4b767284b7f5 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -123,8 +123,8 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - /* We hope get_seconds stays lockless */ - m->time = get_seconds(); + /* need the internal __ version to avoid deadlocks */ + m->time = __ktime_get_real_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; m->cpuid = cpuid_eax(1); m->socketid = cpu_data(m->extcpu).phys_proc_id; @@ -1104,6 +1104,101 @@ static void mce_unmap_kpfn(unsigned long pfn) } #endif + +/* + * Cases where we avoid rendezvous handler timeout: + * 1) If this CPU is offline. + * + * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to + * skip those CPUs which remain looping in the 1st kernel - see + * crash_nmi_callback(). + * + * Note: there still is a small window between kexec-ing and the new, + * kdump kernel establishing a new #MC handler where a broadcasted MCE + * might not get handled properly. + */ +static bool __mc_check_crashing_cpu(int cpu) +{ + if (cpu_is_offline(cpu) || + (crashing_cpu != -1 && crashing_cpu != cpu)) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return true; + } + } + return false; +} + +static void __mc_scan_banks(struct mce *m, struct mce *final, + unsigned long *toclear, unsigned long *valid_banks, + int no_way_out, int *worst) +{ + struct mca_config *cfg = &mca_cfg; + int severity, i; + + for (i = 0; i < cfg->banks; i++) { + __clear_bit(i, toclear); + if (!test_bit(i, valid_banks)) + continue; + + if (!mce_banks[i].ctl) + continue; + + m->misc = 0; + m->addr = 0; + m->bank = i; + + m->status = mce_rdmsrl(msr_ops.status(i)); + if (!(m->status & MCI_STATUS_VAL)) + continue; + + /* + * Corrected or non-signaled errors are handled by + * machine_check_poll(). Leave them alone, unless this panics. + */ + if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && + !no_way_out) + continue; + + /* Set taint even when machine check was not enabled. */ + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + + severity = mce_severity(m, cfg->tolerant, NULL, true); + + /* + * When machine check was for corrected/deferred handler don't + * touch, unless we're panicking. + */ + if ((severity == MCE_KEEP_SEVERITY || + severity == MCE_UCNA_SEVERITY) && !no_way_out) + continue; + + __set_bit(i, toclear); + + /* Machine check event was not enabled. Clear, but ignore. */ + if (severity == MCE_NO_SEVERITY) + continue; + + mce_read_aux(m, i); + + /* assuming valid severity level != 0 */ + m->severity = severity; + + mce_log(m); + + if (severity > *worst) { + *final = *m; + *worst = severity; + } + } + + /* mce_clear_state will clear *final, save locally for use later */ + *m = *final; +} + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -1118,68 +1213,45 @@ static void mce_unmap_kpfn(unsigned long pfn) */ void do_machine_check(struct pt_regs *regs, long error_code) { + DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); + DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; + int cpu = smp_processor_id(); + char *msg = "Unknown"; struct mce m, *final; - int i; int worst = 0; - int severity; /* * Establish sequential order between the CPUs entering the machine * check handler. */ int order = -1; + /* * If no_way_out gets set, there is no safe way to recover from this * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. */ int no_way_out = 0; + /* * If kill_it gets set, there might be a way to recover from this * error. */ int kill_it = 0; - DECLARE_BITMAP(toclear, MAX_NR_BANKS); - DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); - char *msg = "Unknown"; /* * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES * on Intel. */ int lmce = 1; - int cpu = smp_processor_id(); - /* - * Cases where we avoid rendezvous handler timeout: - * 1) If this CPU is offline. - * - * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to - * skip those CPUs which remain looping in the 1st kernel - see - * crash_nmi_callback(). - * - * Note: there still is a small window between kexec-ing and the new, - * kdump kernel establishing a new #MC handler where a broadcasted MCE - * might not get handled properly. - */ - if (cpu_is_offline(cpu) || - (crashing_cpu != -1 && crashing_cpu != cpu)) { - u64 mcgstatus; - - mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); - if (mcgstatus & MCG_STATUS_RIPV) { - mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); - return; - } - } + if (__mc_check_crashing_cpu(cpu)) + return; ist_enter(regs); this_cpu_inc(mce_exception_count); - if (!cfg->banks) - goto out; - mce_gather_info(&m, regs); m.tsc = rdtsc(); @@ -1220,67 +1292,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) order = mce_start(&no_way_out); } - for (i = 0; i < cfg->banks; i++) { - __clear_bit(i, toclear); - if (!test_bit(i, valid_banks)) - continue; - if (!mce_banks[i].ctl) - continue; - - m.misc = 0; - m.addr = 0; - m.bank = i; - - m.status = mce_rdmsrl(msr_ops.status(i)); - if ((m.status & MCI_STATUS_VAL) == 0) - continue; - - /* - * Non uncorrected or non signaled errors are handled by - * machine_check_poll. Leave them alone, unless this panics. - */ - if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && - !no_way_out) - continue; - - /* - * Set taint even when machine check was not enabled. - */ - add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - - severity = mce_severity(&m, cfg->tolerant, NULL, true); - - /* - * When machine check was for corrected/deferred handler don't - * touch, unless we're panicing. - */ - if ((severity == MCE_KEEP_SEVERITY || - severity == MCE_UCNA_SEVERITY) && !no_way_out) - continue; - __set_bit(i, toclear); - if (severity == MCE_NO_SEVERITY) { - /* - * Machine check event was not enabled. Clear, but - * ignore. - */ - continue; - } - - mce_read_aux(&m, i); - - /* assuming valid severity level != 0 */ - m.severity = severity; - - mce_log(&m); - - if (severity > worst) { - *final = m; - worst = severity; - } - } - - /* mce_clear_state will clear *final, save locally for use later */ - m = *final; + __mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst); if (!no_way_out) mce_clear_state(toclear); @@ -1319,7 +1331,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (worst > 0) mce_report_event(regs); mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); -out: + sync_core(); if (worst != MCE_AR_SEVERITY && !kill_it) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 08286269fd24..b9bc8a1a584e 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -509,12 +509,20 @@ static struct platform_device *microcode_pdev; static int check_online_cpus(void) { - if (num_online_cpus() == num_present_cpus()) - return 0; + unsigned int cpu; - pr_err("Not all CPUs online, aborting microcode update.\n"); + /* + * Make sure all CPUs are online. It's fine for SMT to be disabled if + * all the primary threads are still online. + */ + for_each_present_cpu(cpu) { + if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) { + pr_err("Not all CPUs online, aborting microcode update.\n"); + return -EINVAL; + } + } - return -EINVAL; + return 0; } static atomic_t late_cpus_in; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 031082c96db8..ad12733f6058 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -41,7 +41,7 @@ static void (*hv_stimer0_handler)(void); static void (*hv_kexec_handler)(void); static void (*hv_crash_handler)(struct pt_regs *regs); -void hyperv_vector_handler(struct pt_regs *regs) +__visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -50,7 +50,7 @@ void hyperv_vector_handler(struct pt_regs *regs) if (vmbus_handler) vmbus_handler(); - if (ms_hyperv.hints & HV_X64_DEPRECATING_AEOI_RECOMMENDED) + if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED) ack_APIC_irq(); exiting_irq(); @@ -300,7 +300,7 @@ static void __init ms_hyperv_init_platform(void) hyperv_reenlightenment_vector); /* Setup the IDT for stimer0 */ - if (ms_hyperv.misc_features & HV_X64_STIMER_DIRECT_MODE_AVAILABLE) + if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) alloc_intr_gate(HYPERV_STIMER0_VECTOR, hv_stimer0_callback_vector); #endif diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 81c0afb39d0a..71ca064e3794 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -22,18 +22,10 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -/* - * Check for extended topology enumeration cpuid leaf 0xb and if it - * exists, use it for populating initial_apicid and cpu topology - * detection. - */ -int detect_extended_topology(struct cpuinfo_x86 *c) +int detect_extended_topology_early(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - unsigned int eax, ebx, ecx, edx, sub_index; - unsigned int ht_mask_width, core_plus_mask_width; - unsigned int core_select_mask, core_level_siblings; - static bool printed; + unsigned int eax, ebx, ecx, edx; if (c->cpuid_level < 0xb) return -1; @@ -52,10 +44,30 @@ int detect_extended_topology(struct cpuinfo_x86 *c) * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; + smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); +#endif + return 0; +} + +/* + * Check for extended topology enumeration cpuid leaf 0xb and if it + * exists, use it for populating initial_apicid and cpu topology + * detection. + */ +int detect_extended_topology(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned int eax, ebx, ecx, edx, sub_index; + unsigned int ht_mask_width, core_plus_mask_width; + unsigned int core_select_mask, core_level_siblings; + + if (detect_extended_topology_early(c) < 0) + return -1; /* * Populate HT related information from sub-leaf level 0. */ + cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx); core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); @@ -86,15 +98,6 @@ int detect_extended_topology(struct cpuinfo_x86 *c) c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); c->x86_max_cores = (core_level_siblings / smp_num_siblings); - - if (!printed) { - pr_info("CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - if (c->x86_max_cores > 1) - pr_info("CPU: Processor Core ID: %d\n", - c->cpu_core_id); - printed = 1; - } #endif return 0; } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 666a284116ac..9c8652974f8e 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -22,8 +22,6 @@ #include <asm/stacktrace.h> #include <asm/unwind.h> -#define OPCODE_BUFSIZE 64 - int panic_on_unrecovered_nmi; int panic_on_io_nmi; static int die_counter; @@ -93,26 +91,18 @@ static void printk_stack_address(unsigned long address, int reliable, */ void show_opcodes(u8 *rip, const char *loglvl) { - unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3; +#define PROLOGUE_SIZE 42 +#define EPILOGUE_SIZE 21 +#define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE) u8 opcodes[OPCODE_BUFSIZE]; - u8 *ip; - int i; - - printk("%sCode: ", loglvl); - - ip = (u8 *)rip - code_prologue; - if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) { - pr_cont("Bad RIP value.\n"); - return; - } - for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) { - if (ip == rip) - pr_cont("<%02x> ", opcodes[i]); - else - pr_cont("%02x ", opcodes[i]); + if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) { + printk("%sCode: Bad RIP value.\n", loglvl); + } else { + printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" + __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, + opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1); } - pr_cont("\n"); } void show_ip(struct pt_regs *regs, const char *loglvl) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index da5d8ac60062..50d5848bf22e 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -338,6 +338,18 @@ static resource_size_t __init gen3_stolen_base(int num, int slot, int func, return bsm & INTEL_BSM_MASK; } +static resource_size_t __init gen11_stolen_base(int num, int slot, int func, + resource_size_t stolen_size) +{ + u64 bsm; + + bsm = read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW0); + bsm &= INTEL_BSM_MASK; + bsm |= (u64)read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW1) << 32; + + return bsm; +} + static resource_size_t __init i830_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; @@ -498,6 +510,11 @@ static const struct intel_early_ops chv_early_ops __initconst = { .stolen_size = chv_stolen_size, }; +static const struct intel_early_ops gen11_early_ops __initconst = { + .stolen_base = gen11_stolen_base, + .stolen_size = gen9_stolen_size, +}; + static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_I830_IDS(&i830_early_ops), INTEL_I845G_IDS(&i845_early_ops), @@ -529,6 +546,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_CFL_IDS(&gen9_early_ops), INTEL_GLK_IDS(&gen9_early_ops), INTEL_CNL_IDS(&gen9_early_ops), + INTEL_ICL_11_IDS(&gen11_early_ops), }; struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index f92a6593de1e..2ea85b32421a 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -10,6 +10,7 @@ #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/traps.h> +#include <asm/irq_regs.h> #include <linux/hardirq.h> #include <linux/pkeys.h> diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index abe6df15a8fb..30f9cb2c0b55 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -512,11 +512,18 @@ ENTRY(initial_code) ENTRY(setup_once_ref) .long setup_once +#ifdef CONFIG_PAGE_TABLE_ISOLATION +#define PGD_ALIGN (2 * PAGE_SIZE) +#define PTI_USER_PGD_FILL 1024 +#else +#define PGD_ALIGN (PAGE_SIZE) +#define PTI_USER_PGD_FILL 0 +#endif /* * BSS section */ __PAGE_ALIGNED_BSS - .align PAGE_SIZE + .align PGD_ALIGN #ifdef CONFIG_X86_PAE .globl initial_pg_pmd initial_pg_pmd: @@ -526,14 +533,17 @@ initial_pg_pmd: initial_page_table: .fill 1024,4,0 #endif + .align PGD_ALIGN initial_pg_fixmap: .fill 1024,4,0 -.globl empty_zero_page -empty_zero_page: - .fill 4096,1,0 .globl swapper_pg_dir + .align PGD_ALIGN swapper_pg_dir: .fill 1024,4,0 + .fill PTI_USER_PGD_FILL,4,0 +.globl empty_zero_page +empty_zero_page: + .fill 4096,1,0 EXPORT_SYMBOL(empty_zero_page) /* @@ -542,7 +552,7 @@ EXPORT_SYMBOL(empty_zero_page) #ifdef CONFIG_X86_PAE __PAGE_ALIGNED_DATA /* Page-aligned for the benefit of paravirt? */ - .align PAGE_SIZE + .align PGD_ALIGN ENTRY(initial_page_table) .long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 /* low identity map */ # if KPMDS == 3 diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 8344dd2f310a..15ebc2fc166e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -235,7 +235,7 @@ ENTRY(secondary_startup_64) * address given in m16:64. */ pushq $.Lafter_lret # put return address on stack for unwinder - xorq %rbp, %rbp # clear frame pointer + xorl %ebp, %ebp # clear frame pointer movq initial_code(%rip), %rax pushq $__KERNEL_CS # set correct cs pushq %rax # target address in negative space diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 346b24883911..b0acb22e5a46 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1,6 +1,7 @@ #include <linux/clocksource.h> #include <linux/clockchips.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/export.h> #include <linux/delay.h> #include <linux/errno.h> diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 8771766d46b6..34a5c1715148 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -169,28 +169,29 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) set_dr_addr_mask(0, i); } -/* - * Check for virtual address in kernel space. - */ -int arch_check_bp_in_kernelspace(struct perf_event *bp) +static int arch_bp_generic_len(int x86_len) { - unsigned int len; - unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - - va = info->address; - len = bp->attr.bp_len; - - /* - * We don't need to worry about va + len - 1 overflowing: - * we already require that va is aligned to a multiple of len. - */ - return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); + switch (x86_len) { + case X86_BREAKPOINT_LEN_1: + return HW_BREAKPOINT_LEN_1; + case X86_BREAKPOINT_LEN_2: + return HW_BREAKPOINT_LEN_2; + case X86_BREAKPOINT_LEN_4: + return HW_BREAKPOINT_LEN_4; +#ifdef CONFIG_X86_64 + case X86_BREAKPOINT_LEN_8: + return HW_BREAKPOINT_LEN_8; +#endif + default: + return -EINVAL; + } } int arch_bp_generic_fields(int x86_len, int x86_type, int *gen_len, int *gen_type) { + int len; + /* Type */ switch (x86_type) { case X86_BREAKPOINT_EXECUTE: @@ -211,42 +212,47 @@ int arch_bp_generic_fields(int x86_len, int x86_type, } /* Len */ - switch (x86_len) { - case X86_BREAKPOINT_LEN_1: - *gen_len = HW_BREAKPOINT_LEN_1; - break; - case X86_BREAKPOINT_LEN_2: - *gen_len = HW_BREAKPOINT_LEN_2; - break; - case X86_BREAKPOINT_LEN_4: - *gen_len = HW_BREAKPOINT_LEN_4; - break; -#ifdef CONFIG_X86_64 - case X86_BREAKPOINT_LEN_8: - *gen_len = HW_BREAKPOINT_LEN_8; - break; -#endif - default: + len = arch_bp_generic_len(x86_len); + if (len < 0) return -EINVAL; - } + *gen_len = len; return 0; } - -static int arch_build_bp_info(struct perf_event *bp) +/* + * Check for virtual address in kernel space. + */ +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); + unsigned long va; + int len; - info->address = bp->attr.bp_addr; + va = hw->address; + len = arch_bp_generic_len(hw->len); + WARN_ON_ONCE(len < 0); + + /* + * We don't need to worry about va + len - 1 overflowing: + * we already require that va is aligned to a multiple of len. + */ + return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); +} + +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + hw->address = attr->bp_addr; + hw->mask = 0; /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_W: - info->type = X86_BREAKPOINT_WRITE; + hw->type = X86_BREAKPOINT_WRITE; break; case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = X86_BREAKPOINT_RW; + hw->type = X86_BREAKPOINT_RW; break; case HW_BREAKPOINT_X: /* @@ -254,23 +260,23 @@ static int arch_build_bp_info(struct perf_event *bp) * acceptable for kprobes. On non-kprobes kernels, we don't * allow kernel breakpoints at all. */ - if (bp->attr.bp_addr >= TASK_SIZE_MAX) { + if (attr->bp_addr >= TASK_SIZE_MAX) { #ifdef CONFIG_KPROBES - if (within_kprobe_blacklist(bp->attr.bp_addr)) + if (within_kprobe_blacklist(attr->bp_addr)) return -EINVAL; #else return -EINVAL; #endif } - info->type = X86_BREAKPOINT_EXECUTE; + hw->type = X86_BREAKPOINT_EXECUTE; /* * x86 inst breakpoints need to have a specific undefined len. * But we still need to check userspace is not trying to setup * an unsupported length, to get a range breakpoint for example. */ - if (bp->attr.bp_len == sizeof(long)) { - info->len = X86_BREAKPOINT_LEN_X; + if (attr->bp_len == sizeof(long)) { + hw->len = X86_BREAKPOINT_LEN_X; return 0; } default: @@ -278,28 +284,26 @@ static int arch_build_bp_info(struct perf_event *bp) } /* Len */ - info->mask = 0; - - switch (bp->attr.bp_len) { + switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: - info->len = X86_BREAKPOINT_LEN_1; + hw->len = X86_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: - info->len = X86_BREAKPOINT_LEN_2; + hw->len = X86_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: - info->len = X86_BREAKPOINT_LEN_4; + hw->len = X86_BREAKPOINT_LEN_4; break; #ifdef CONFIG_X86_64 case HW_BREAKPOINT_LEN_8: - info->len = X86_BREAKPOINT_LEN_8; + hw->len = X86_BREAKPOINT_LEN_8; break; #endif default: /* AMD range breakpoint */ - if (!is_power_of_2(bp->attr.bp_len)) + if (!is_power_of_2(attr->bp_len)) return -EINVAL; - if (bp->attr.bp_addr & (bp->attr.bp_len - 1)) + if (attr->bp_addr & (attr->bp_len - 1)) return -EINVAL; if (!boot_cpu_has(X86_FEATURE_BPEXT)) @@ -312,8 +316,8 @@ static int arch_build_bp_info(struct perf_event *bp) * breakpoints, then we'll have to check for kprobe-blacklisted * addresses anywhere in the range. */ - info->mask = bp->attr.bp_len - 1; - info->len = X86_BREAKPOINT_LEN_1; + hw->mask = attr->bp_len - 1; + hw->len = X86_BREAKPOINT_LEN_1; } return 0; @@ -322,22 +326,23 @@ static int arch_build_bp_info(struct perf_event *bp) /* * Validate the arch-specific HW Breakpoint register settings */ -int arch_validate_hwbkpt_settings(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned int align; int ret; - ret = arch_build_bp_info(bp); + ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; - switch (info->len) { + switch (hw->len) { case X86_BREAKPOINT_LEN_1: align = 0; - if (info->mask) - align = info->mask; + if (hw->mask) + align = hw->mask; break; case X86_BREAKPOINT_LEN_2: align = 1; @@ -358,7 +363,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * Check that the low-order bits of the address are appropriate * for the alignment implied by len. */ - if (info->address & align) + if (hw->address & align) return -EINVAL; return 0; diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 86c4439f9d74..519649ddf100 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -5,6 +5,7 @@ #include <linux/sched.h> #include <linux/ioport.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/timex.h> #include <linux/random.h> #include <linux/init.h> diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 74383a3780dc..01adea278a71 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -8,6 +8,7 @@ #include <asm/traps.h> #include <asm/proto.h> #include <asm/desc.h> +#include <asm/hw_irq.h> struct idt_data { unsigned int vector; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 328d027d829d..59b5f2ea7c2f 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -10,6 +10,7 @@ #include <linux/ftrace.h> #include <linux/delay.h> #include <linux/export.h> +#include <linux/irq.h> #include <asm/apic.h> #include <asm/io_apic.h> diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index c1bdbd3d3232..95600a99ae93 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -11,6 +11,7 @@ #include <linux/seq_file.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/kernel_stat.h> #include <linux/notifier.h> #include <linux/cpu.h> diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index d86e344f5b3d..0469cd078db1 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -11,6 +11,7 @@ #include <linux/kernel_stat.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/seq_file.h> #include <linux/delay.h> #include <linux/ftrace.h> diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 772196c1b8c4..a0693b71cfc1 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -5,6 +5,7 @@ #include <linux/sched.h> #include <linux/ioport.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/timex.h> #include <linux/random.h> #include <linux/kprobes.h> diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index e56c95be2808..eeea935e9bb5 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -37,15 +37,18 @@ static void bug_at(unsigned char *ip, int line) BUG(); } -static void __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - void *(*poker)(void *, const void *, size_t), - int init) +static void __ref __jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + void *(*poker)(void *, const void *, size_t), + int init) { union jump_code_union code; const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; + if (early_boot_irqs_disabled) + poker = text_poke_early; + if (type == JUMP_LABEL_JMP) { if (init) { /* diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 7326078eaa7a..278cd07228dd 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -532,7 +532,7 @@ static int bzImage64_cleanup(void *loader_data) static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { return verify_pefile_signature(kernel, kernel_len, - NULL, + VERIFY_USE_SECONDARY_KEYRING, VERIFYING_KEXEC_PE_SIGNATURE); } #endif diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index ae38dccf0c8f..2b949f4fd4d8 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -105,14 +105,4 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig } #endif -#ifdef CONFIG_KPROBES_ON_FTRACE -extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb); -#else -static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - return 0; -} -#endif #endif diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6f4d42377fe5..b0d1e81c96bb 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -66,8 +66,6 @@ #include "common.h" -void jprobe_return_end(void); - DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -395,8 +393,6 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) - (u8 *) real; if ((s64) (s32) newdisp != newdisp) { pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); - pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", - src, real, insn->displacement.value); return 0; } disp = (u8 *) dest + insn_offset_displacement(insn); @@ -596,7 +592,6 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, * stepping. */ regs->ip = (unsigned long)p->ainsn.insn; - preempt_enable_no_resched(); return; } #endif @@ -640,8 +635,7 @@ static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs, * Raise a BUG or we'll continue in an endless reentering loop * and eventually a stack overflow. */ - printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n", - p->addr); + pr_err("Unrecoverable kprobe detected.\n"); dump_kprobe(p); BUG(); default: @@ -669,12 +663,10 @@ int kprobe_int3_handler(struct pt_regs *regs) addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t)); /* - * We don't want to be preempted for the entire - * duration of kprobe processing. We conditionally - * re-enable preemption at the end of this function, - * and also in reenter_kprobe() and setup_singlestep(). + * We don't want to be preempted for the entire duration of kprobe + * processing. Since int3 and debug trap disables irqs and we clear + * IF while singlestepping, it must be no preemptible. */ - preempt_disable(); kcb = get_kprobe_ctlblk(); p = get_kprobe(addr); @@ -690,13 +682,14 @@ int kprobe_int3_handler(struct pt_regs *regs) /* * If we have no pre-handler or it returned 0, we * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it prepped - * for calling the break_handler below on re-entry - * for jprobe processing, so get out doing nothing - * more here. + * pre-handler and it returned non-zero, that means + * user handler setup registers to exit to another + * instruction, we must skip the single stepping. */ if (!p->pre_handler || !p->pre_handler(p, regs)) setup_singlestep(p, regs, kcb, 0); + else + reset_current_kprobe(); return 1; } } else if (*addr != BREAKPOINT_INSTRUCTION) { @@ -710,18 +703,9 @@ int kprobe_int3_handler(struct pt_regs *regs) * the original instruction. */ regs->ip = (unsigned long)addr; - preempt_enable_no_resched(); return 1; - } else if (kprobe_running()) { - p = __this_cpu_read(current_kprobe); - if (p->break_handler && p->break_handler(p, regs)) { - if (!skip_singlestep(p, regs, kcb)) - setup_singlestep(p, regs, kcb, 0); - return 1; - } } /* else: not a kprobe fault; let the kernel handle it */ - preempt_enable_no_resched(); return 0; } NOKPROBE_SYMBOL(kprobe_int3_handler); @@ -972,8 +956,6 @@ int kprobe_debug_handler(struct pt_regs *regs) } reset_current_kprobe(); out: - preempt_enable_no_resched(); - /* * if somebody else is singlestepping across a probe point, flags * will have TF set, in which case, continue the remaining processing @@ -1020,7 +1002,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) restore_previous_kprobe(kcb); else reset_current_kprobe(); - preempt_enable_no_resched(); } else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE || kcb->kprobe_status == KPROBE_HIT_SSDONE) { /* @@ -1083,93 +1064,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, } NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct jprobe *jp = container_of(p, struct jprobe, kp); - unsigned long addr; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - kcb->jprobe_saved_regs = *regs; - kcb->jprobe_saved_sp = stack_addr(regs); - addr = (unsigned long)(kcb->jprobe_saved_sp); - - /* - * As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. - * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy - * raw stack chunk with redzones: - */ - __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->ip = (unsigned long)(jp->entry); - - /* - * jprobes use jprobe_return() which skips the normal return - * path of the function, and this messes up the accounting of the - * function graph tracer to get messed up. - * - * Pause function graph tracing while performing the jprobe function. - */ - pause_graph_tracing(); - return 1; -} -NOKPROBE_SYMBOL(setjmp_pre_handler); - -void jprobe_return(void) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - - /* Unpoison stack redzones in the frames we are going to jump over. */ - kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp); - - asm volatile ( -#ifdef CONFIG_X86_64 - " xchg %%rbx,%%rsp \n" -#else - " xchgl %%ebx,%%esp \n" -#endif - " int3 \n" - " .globl jprobe_return_end\n" - " jprobe_return_end: \n" - " nop \n"::"b" - (kcb->jprobe_saved_sp):"memory"); -} -NOKPROBE_SYMBOL(jprobe_return); -NOKPROBE_SYMBOL(jprobe_return_end); - -int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - u8 *addr = (u8 *) (regs->ip - 1); - struct jprobe *jp = container_of(p, struct jprobe, kp); - void *saved_sp = kcb->jprobe_saved_sp; - - if ((addr > (u8 *) jprobe_return) && - (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != saved_sp) { - struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; - printk(KERN_ERR - "current sp %p does not match saved sp %p\n", - stack_addr(regs), saved_sp); - printk(KERN_ERR "Saved registers for jprobe %p\n", jp); - show_regs(saved_regs); - printk(KERN_ERR "Current registers\n"); - show_regs(regs); - BUG(); - } - /* It's OK to start function graph tracing again */ - unpause_graph_tracing(); - *regs = kcb->jprobe_saved_regs; - __memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); - preempt_enable_no_resched(); - return 1; - } - return 0; -} -NOKPROBE_SYMBOL(longjmp_break_handler); - bool arch_within_kprobe_blacklist(unsigned long addr) { bool is_in_entry_trampoline_section = false; diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 8dc0161cec8f..ef819e19650b 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -25,36 +25,6 @@ #include "common.h" -static nokprobe_inline -void __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb, unsigned long orig_ip) -{ - /* - * Emulate singlestep (and also recover regs->ip) - * as if there is a 5byte nop - */ - regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); - if (orig_ip) - regs->ip = orig_ip; -} - -int skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - if (kprobe_ftrace(p)) { - __skip_singlestep(p, regs, kcb, 0); - preempt_enable_no_resched(); - return 1; - } - return 0; -} -NOKPROBE_SYMBOL(skip_singlestep); - /* Ftrace callback handler for kprobes -- called under preepmt disabed */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs) @@ -75,18 +45,25 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ regs->ip = ip + sizeof(kprobe_opcode_t); - /* To emulate trap based kprobes, preempt_disable here */ - preempt_disable(); __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; if (!p->pre_handler || !p->pre_handler(p, regs)) { - __skip_singlestep(p, regs, kcb, orig_ip); - preempt_enable_no_resched(); + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + regs->ip = orig_ip; } /* - * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe, and keep preempt count +1. + * If pre_handler returns !0, it changes regs->ip. We have to + * skip emulating post_handler. */ + __this_cpu_write(current_kprobe, NULL); } } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 203d398802a3..eaf02f2e7300 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -491,7 +491,6 @@ int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; if (!reenter) reset_current_kprobe(); - preempt_enable_no_resched(); return 1; } return 0; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 5b2300b818af..0f471bd93417 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -45,7 +45,6 @@ #include <asm/apic.h> #include <asm/apicdef.h> #include <asm/hypervisor.h> -#include <asm/kvm_guest.h> static int kvmapf = 1; @@ -66,15 +65,6 @@ static int __init parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); -static int kvmclock_vsyscall = 1; -static int __init parse_no_kvmclock_vsyscall(char *arg) -{ - kvmclock_vsyscall = 0; - return 0; -} - -early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); - static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64); static int has_steal_clock = 0; @@ -154,7 +144,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) for (;;) { if (!n.halted) - prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; @@ -188,7 +178,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n) if (n->halted) smp_send_reschedule(n->cpu); else if (swq_has_sleeper(&n->wq)) - swake_up(&n->wq); + swake_up_one(&n->wq); } static void apf_task_wake_all(void) @@ -454,6 +444,98 @@ static void __init sev_map_percpu_data(void) } #ifdef CONFIG_SMP +#define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) + +static void __send_ipi_mask(const struct cpumask *mask, int vector) +{ + unsigned long flags; + int cpu, apic_id, icr; + int min = 0, max = 0; +#ifdef CONFIG_X86_64 + __uint128_t ipi_bitmap = 0; +#else + u64 ipi_bitmap = 0; +#endif + + if (cpumask_empty(mask)) + return; + + local_irq_save(flags); + + switch (vector) { + default: + icr = APIC_DM_FIXED | vector; + break; + case NMI_VECTOR: + icr = APIC_DM_NMI; + break; + } + + for_each_cpu(cpu, mask) { + apic_id = per_cpu(x86_cpu_to_apicid, cpu); + if (!ipi_bitmap) { + min = max = apic_id; + } else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) { + ipi_bitmap <<= min - apic_id; + min = apic_id; + } else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) { + max = apic_id < max ? max : apic_id; + } else { + kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, + (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr); + min = max = apic_id; + ipi_bitmap = 0; + } + __set_bit(apic_id - min, (unsigned long *)&ipi_bitmap); + } + + if (ipi_bitmap) { + kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, + (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr); + } + + local_irq_restore(flags); +} + +static void kvm_send_ipi_mask(const struct cpumask *mask, int vector) +{ + __send_ipi_mask(mask, vector); +} + +static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) +{ + unsigned int this_cpu = smp_processor_id(); + struct cpumask new_mask; + const struct cpumask *local_mask; + + cpumask_copy(&new_mask, mask); + cpumask_clear_cpu(this_cpu, &new_mask); + local_mask = &new_mask; + __send_ipi_mask(local_mask, vector); +} + +static void kvm_send_ipi_allbutself(int vector) +{ + kvm_send_ipi_mask_allbutself(cpu_online_mask, vector); +} + +static void kvm_send_ipi_all(int vector) +{ + __send_ipi_mask(cpu_online_mask, vector); +} + +/* + * Set the IPI entry points + */ +static void kvm_setup_pv_ipi(void) +{ + apic->send_IPI_mask = kvm_send_ipi_mask; + apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself; + apic->send_IPI_allbutself = kvm_send_ipi_allbutself; + apic->send_IPI_all = kvm_send_ipi_all; + pr_info("KVM setup pv IPIs\n"); +} + static void __init kvm_smp_prepare_cpus(unsigned int max_cpus) { native_smp_prepare_cpus(max_cpus); @@ -560,9 +642,6 @@ static void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); - if (kvmclock_vsyscall) - kvm_setup_vsyscall_timeinfo(); - #ifdef CONFIG_SMP smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; @@ -624,12 +703,27 @@ static uint32_t __init kvm_detect(void) return kvm_cpuid_base(); } +static void __init kvm_apic_init(void) +{ +#if defined(CONFIG_SMP) + if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI)) + kvm_setup_pv_ipi(); +#endif +} + +static void __init kvm_init_platform(void) +{ + kvmclock_init(); + x86_platform.apic_post_init = kvm_apic_init; +} + const __initconst struct hypervisor_x86 x86_hyper_kvm = { .name = "KVM", .detect = kvm_detect, .type = X86_HYPER_KVM, .init.guest_late_init = kvm_guest_init, .init.x2apic_available = kvm_para_available, + .init.init_platform = kvm_init_platform, }; static __init int activate_jump_labels(void) @@ -748,6 +842,10 @@ void __init kvm_spinlock_init(void) if (kvm_para_has_hint(KVM_HINTS_REALTIME)) return; + /* Don't use the pvqspinlock code if there is only 1 vCPU. */ + if (num_possible_cpus() == 1) + return; + __pv_init_lock_hash(); pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 3b8e7c13c614..1e6764648af3 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -23,30 +23,57 @@ #include <asm/apic.h> #include <linux/percpu.h> #include <linux/hardirq.h> -#include <linux/memblock.h> +#include <linux/cpuhotplug.h> #include <linux/sched.h> #include <linux/sched/clock.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <asm/hypervisor.h> #include <asm/mem_encrypt.h> #include <asm/x86_init.h> #include <asm/reboot.h> #include <asm/kvmclock.h> -static int kvmclock __ro_after_init = 1; -static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; -static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; -static u64 kvm_sched_clock_offset; +static int kvmclock __initdata = 1; +static int kvmclock_vsyscall __initdata = 1; +static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME; +static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK; +static u64 kvm_sched_clock_offset __ro_after_init; -static int parse_no_kvmclock(char *arg) +static int __init parse_no_kvmclock(char *arg) { kvmclock = 0; return 0; } early_param("no-kvmclock", parse_no_kvmclock); -/* The hypervisor will put information about time periodically here */ -static struct pvclock_vsyscall_time_info *hv_clock; -static struct pvclock_wall_clock *wall_clock; +static int __init parse_no_kvmclock_vsyscall(char *arg) +{ + kvmclock_vsyscall = 0; + return 0; +} +early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); + +/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */ +#define HV_CLOCK_SIZE (sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS) +#define HVC_BOOT_ARRAY_SIZE \ + (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) + +static struct pvclock_vsyscall_time_info + hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE); +static struct pvclock_wall_clock wall_clock; +static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); + +static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +{ + return &this_cpu_read(hv_clock_per_cpu)->pvti; +} + +static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) +{ + return this_cpu_read(hv_clock_per_cpu); +} /* * The wallclock is the time of day when we booted. Since then, some time may @@ -55,21 +82,10 @@ static struct pvclock_wall_clock *wall_clock; */ static void kvm_get_wallclock(struct timespec64 *now) { - struct pvclock_vcpu_time_info *vcpu_time; - int low, high; - int cpu; - - low = (int)slow_virt_to_phys(wall_clock); - high = ((u64)slow_virt_to_phys(wall_clock) >> 32); - - native_write_msr(msr_kvm_wall_clock, low, high); - - cpu = get_cpu(); - - vcpu_time = &hv_clock[cpu].pvti; - pvclock_read_wallclock(wall_clock, vcpu_time, now); - - put_cpu(); + wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock)); + preempt_disable(); + pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now); + preempt_enable(); } static int kvm_set_wallclock(const struct timespec64 *now) @@ -79,14 +95,10 @@ static int kvm_set_wallclock(const struct timespec64 *now) static u64 kvm_clock_read(void) { - struct pvclock_vcpu_time_info *src; u64 ret; - int cpu; preempt_disable_notrace(); - cpu = smp_processor_id(); - src = &hv_clock[cpu].pvti; - ret = pvclock_clocksource_read(src); + ret = pvclock_clocksource_read(this_cpu_pvti()); preempt_enable_notrace(); return ret; } @@ -112,11 +124,11 @@ static inline void kvm_sched_clock_init(bool stable) kvm_sched_clock_offset = kvm_clock_read(); pv_time_ops.sched_clock = kvm_sched_clock_read; - printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", - kvm_sched_clock_offset); + pr_info("kvm-clock: using sched offset of %llu cycles", + kvm_sched_clock_offset); BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) > - sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time)); + sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time)); } /* @@ -130,19 +142,11 @@ static inline void kvm_sched_clock_init(bool stable) */ static unsigned long kvm_get_tsc_khz(void) { - struct pvclock_vcpu_time_info *src; - int cpu; - unsigned long tsc_khz; - - cpu = get_cpu(); - src = &hv_clock[cpu].pvti; - tsc_khz = pvclock_tsc_khz(src); - put_cpu(); setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); - return tsc_khz; + return pvclock_tsc_khz(this_cpu_pvti()); } -static void kvm_get_preset_lpj(void) +static void __init kvm_get_preset_lpj(void) { unsigned long khz; u64 lpj; @@ -156,49 +160,40 @@ static void kvm_get_preset_lpj(void) bool kvm_check_and_clear_guest_paused(void) { + struct pvclock_vsyscall_time_info *src = this_cpu_hvclock(); bool ret = false; - struct pvclock_vcpu_time_info *src; - int cpu = smp_processor_id(); - if (!hv_clock) + if (!src) return ret; - src = &hv_clock[cpu].pvti; - if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { - src->flags &= ~PVCLOCK_GUEST_STOPPED; + if ((src->pvti.flags & PVCLOCK_GUEST_STOPPED) != 0) { + src->pvti.flags &= ~PVCLOCK_GUEST_STOPPED; pvclock_touch_watchdogs(); ret = true; } - return ret; } struct clocksource kvm_clock = { - .name = "kvm-clock", - .read = kvm_clock_get_cycles, - .rating = 400, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .name = "kvm-clock", + .read = kvm_clock_get_cycles, + .rating = 400, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; EXPORT_SYMBOL_GPL(kvm_clock); -int kvm_register_clock(char *txt) +static void kvm_register_clock(char *txt) { - int cpu = smp_processor_id(); - int low, high, ret; - struct pvclock_vcpu_time_info *src; - - if (!hv_clock) - return 0; + struct pvclock_vsyscall_time_info *src = this_cpu_hvclock(); + u64 pa; - src = &hv_clock[cpu].pvti; - low = (int)slow_virt_to_phys(src) | 1; - high = ((u64)slow_virt_to_phys(src) >> 32); - ret = native_write_msr_safe(msr_kvm_system_time, low, high); - printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n", - cpu, high, low, txt); + if (!src) + return; - return ret; + pa = slow_virt_to_phys(&src->pvti) | 0x01ULL; + wrmsrl(msr_kvm_system_time, pa); + pr_info("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt); } static void kvm_save_sched_clock_state(void) @@ -213,11 +208,7 @@ static void kvm_restore_sched_clock_state(void) #ifdef CONFIG_X86_LOCAL_APIC static void kvm_setup_secondary_clock(void) { - /* - * Now that the first cpu already had this clocksource initialized, - * we shouldn't fail. - */ - WARN_ON(kvm_register_clock("secondary cpu clock")); + kvm_register_clock("secondary cpu clock"); } #endif @@ -245,100 +236,84 @@ static void kvm_shutdown(void) native_machine_shutdown(); } -static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size, - phys_addr_t align) +static int __init kvm_setup_vsyscall_timeinfo(void) { - phys_addr_t mem; +#ifdef CONFIG_X86_64 + u8 flags; - mem = memblock_alloc(size, align); - if (!mem) + if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall) return 0; - if (sev_active()) { - if (early_set_memory_decrypted((unsigned long)__va(mem), size)) - goto e_free; - } + flags = pvclock_read_flags(&hv_clock_boot[0].pvti); + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) + return 0; - return mem; -e_free: - memblock_free(mem, size); + kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; +#endif return 0; } +early_initcall(kvm_setup_vsyscall_timeinfo); -static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size) +static int kvmclock_setup_percpu(unsigned int cpu) { - if (sev_active()) - early_set_memory_encrypted((unsigned long)__va(addr), size); + struct pvclock_vsyscall_time_info *p = per_cpu(hv_clock_per_cpu, cpu); - memblock_free(addr, size); + /* + * The per cpu area setup replicates CPU0 data to all cpu + * pointers. So carefully check. CPU0 has been set up in init + * already. + */ + if (!cpu || (p && p != per_cpu(hv_clock_per_cpu, 0))) + return 0; + + /* Use the static page for the first CPUs, allocate otherwise */ + if (cpu < HVC_BOOT_ARRAY_SIZE) + p = &hv_clock_boot[cpu]; + else + p = kzalloc(sizeof(*p), GFP_KERNEL); + + per_cpu(hv_clock_per_cpu, cpu) = p; + return p ? 0 : -ENOMEM; } void __init kvmclock_init(void) { - struct pvclock_vcpu_time_info *vcpu_time; - unsigned long mem, mem_wall_clock; - int size, cpu, wall_clock_size; u8 flags; - size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); - - if (!kvm_para_available()) + if (!kvm_para_available() || !kvmclock) return; - if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) { + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) { msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW; msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW; - } else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE))) - return; - - wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock)); - mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE); - if (!mem_wall_clock) - return; - - wall_clock = __va(mem_wall_clock); - memset(wall_clock, 0, wall_clock_size); - - mem = kvm_memblock_alloc(size, PAGE_SIZE); - if (!mem) { - kvm_memblock_free(mem_wall_clock, wall_clock_size); - wall_clock = NULL; + } else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { return; } - hv_clock = __va(mem); - memset(hv_clock, 0, size); - - if (kvm_register_clock("primary cpu clock")) { - hv_clock = NULL; - kvm_memblock_free(mem, size); - kvm_memblock_free(mem_wall_clock, wall_clock_size); - wall_clock = NULL; + if (cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "kvmclock:setup_percpu", + kvmclock_setup_percpu, NULL) < 0) { return; } - printk(KERN_INFO "kvm-clock: Using msrs %x and %x", + pr_info("kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); - pvclock_set_pvti_cpu0_va(hv_clock); + this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]); + kvm_register_clock("primary cpu clock"); + pvclock_set_pvti_cpu0_va(hv_clock_boot); if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); - cpu = get_cpu(); - vcpu_time = &hv_clock[cpu].pvti; - flags = pvclock_read_flags(vcpu_time); - + flags = pvclock_read_flags(&hv_clock_boot[0].pvti); kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT); - put_cpu(); x86_platform.calibrate_tsc = kvm_get_tsc_khz; x86_platform.calibrate_cpu = kvm_get_tsc_khz; x86_platform.get_wallclock = kvm_get_wallclock; x86_platform.set_wallclock = kvm_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC - x86_cpuinit.early_percpu_clock_init = - kvm_setup_secondary_clock; + x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock; #endif x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; @@ -350,31 +325,3 @@ void __init kvmclock_init(void) clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); pv_info.name = "KVM"; } - -int __init kvm_setup_vsyscall_timeinfo(void) -{ -#ifdef CONFIG_X86_64 - int cpu; - u8 flags; - struct pvclock_vcpu_time_info *vcpu_time; - unsigned int size; - - if (!hv_clock) - return 0; - - size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); - - cpu = get_cpu(); - - vcpu_time = &hv_clock[cpu].pvti; - flags = pvclock_read_flags(vcpu_time); - - put_cpu(); - - if (!(flags & PVCLOCK_TSC_STABLE_BIT)) - return 1; - - kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; -#endif - return 0; -} diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index c9b14020f4dd..733e6ace0fa4 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -100,6 +100,102 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) return new_ldt; } +#ifdef CONFIG_PAGE_TABLE_ISOLATION + +static void do_sanity_check(struct mm_struct *mm, + bool had_kernel_mapping, + bool had_user_mapping) +{ + if (mm->context.ldt) { + /* + * We already had an LDT. The top-level entry should already + * have been allocated and synchronized with the usermode + * tables. + */ + WARN_ON(!had_kernel_mapping); + if (static_cpu_has(X86_FEATURE_PTI)) + WARN_ON(!had_user_mapping); + } else { + /* + * This is the first time we're mapping an LDT for this process. + * Sync the pgd to the usermode tables. + */ + WARN_ON(had_kernel_mapping); + if (static_cpu_has(X86_FEATURE_PTI)) + WARN_ON(had_user_mapping); + } +} + +#ifdef CONFIG_X86_PAE + +static pmd_t *pgd_to_pmd_walk(pgd_t *pgd, unsigned long va) +{ + p4d_t *p4d; + pud_t *pud; + + if (pgd->pgd == 0) + return NULL; + + p4d = p4d_offset(pgd, va); + if (p4d_none(*p4d)) + return NULL; + + pud = pud_offset(p4d, va); + if (pud_none(*pud)) + return NULL; + + return pmd_offset(pud, va); +} + +static void map_ldt_struct_to_user(struct mm_struct *mm) +{ + pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR); + pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); + pmd_t *k_pmd, *u_pmd; + + k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR); + u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR); + + if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt) + set_pmd(u_pmd, *k_pmd); +} + +static void sanity_check_ldt_mapping(struct mm_struct *mm) +{ + pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR); + pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); + bool had_kernel, had_user; + pmd_t *k_pmd, *u_pmd; + + k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR); + u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR); + had_kernel = (k_pmd->pmd != 0); + had_user = (u_pmd->pmd != 0); + + do_sanity_check(mm, had_kernel, had_user); +} + +#else /* !CONFIG_X86_PAE */ + +static void map_ldt_struct_to_user(struct mm_struct *mm) +{ + pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR); + + if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt) + set_pgd(kernel_to_user_pgdp(pgd), *pgd); +} + +static void sanity_check_ldt_mapping(struct mm_struct *mm) +{ + pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR); + bool had_kernel = (pgd->pgd != 0); + bool had_user = (kernel_to_user_pgdp(pgd)->pgd != 0); + + do_sanity_check(mm, had_kernel, had_user); +} + +#endif /* CONFIG_X86_PAE */ + /* * If PTI is enabled, this maps the LDT into the kernelmode and * usermode tables for the given mm. @@ -115,9 +211,8 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - bool is_vmalloc, had_top_level_entry; unsigned long va; + bool is_vmalloc; spinlock_t *ptl; pgd_t *pgd; int i; @@ -131,13 +226,15 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) */ WARN_ON(ldt->slot != -1); + /* Check if the current mappings are sane */ + sanity_check_ldt_mapping(mm); + /* * Did we already have the top level entry allocated? We can't * use pgd_none() for this because it doens't do anything on * 4-level page table kernels. */ pgd = pgd_offset(mm, LDT_BASE_ADDR); - had_top_level_entry = (pgd->pgd != 0); is_vmalloc = is_vmalloc_addr(ldt->entries); @@ -172,41 +269,31 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) pte_unmap_unlock(ptep, ptl); } - if (mm->context.ldt) { - /* - * We already had an LDT. The top-level entry should already - * have been allocated and synchronized with the usermode - * tables. - */ - WARN_ON(!had_top_level_entry); - if (static_cpu_has(X86_FEATURE_PTI)) - WARN_ON(!kernel_to_user_pgdp(pgd)->pgd); - } else { - /* - * This is the first time we're mapping an LDT for this process. - * Sync the pgd to the usermode tables. - */ - WARN_ON(had_top_level_entry); - if (static_cpu_has(X86_FEATURE_PTI)) { - WARN_ON(kernel_to_user_pgdp(pgd)->pgd); - set_pgd(kernel_to_user_pgdp(pgd), *pgd); - } - } + /* Propagate LDT mapping to the user page-table */ + map_ldt_struct_to_user(mm); va = (unsigned long)ldt_slot_va(slot); flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0); ldt->slot = slot; -#endif return 0; } +#else /* !CONFIG_PAGE_TABLE_ISOLATION */ + +static int +map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) +{ + return 0; +} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ + static void free_ldt_pgtables(struct mm_struct *mm) { #ifdef CONFIG_PAGE_TABLE_ISOLATION struct mmu_gather tlb; unsigned long start = LDT_BASE_ADDR; - unsigned long end = start + (1UL << PGDIR_SHIFT); + unsigned long end = LDT_END_ADDR; if (!static_cpu_has(X86_FEATURE_PTI)) return; diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index d1ab07ec8c9a..5409c2800ab5 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -56,7 +56,7 @@ static void load_segments(void) static void machine_kexec_free_page_tables(struct kimage *image) { - free_page((unsigned long)image->arch.pgd); + free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER); image->arch.pgd = NULL; #ifdef CONFIG_X86_PAE free_page((unsigned long)image->arch.pmd0); @@ -72,7 +72,8 @@ static void machine_kexec_free_page_tables(struct kimage *image) static int machine_kexec_alloc_page_tables(struct kimage *image) { - image->arch.pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL); + image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + PGD_ALLOCATION_ORDER); #ifdef CONFIG_X86_PAE image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL); image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 99dc79e76bdc..930c88341e4e 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -88,10 +88,12 @@ unsigned paravirt_patch_call(void *insnbuf, struct branch *b = insnbuf; unsigned long delta = (unsigned long)target - (addr+5); - if (tgt_clobbers & ~site_clobbers) - return len; /* target would clobber too much for this site */ - if (len < 5) + if (len < 5) { +#ifdef CONFIG_RETPOLINE + WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr); +#endif return len; /* call too long for patch site */ + } b->opcode = 0xe8; /* call */ b->delta = delta; @@ -106,8 +108,12 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, struct branch *b = insnbuf; unsigned long delta = (unsigned long)target - (addr+5); - if (len < 5) + if (len < 5) { +#ifdef CONFIG_RETPOLINE + WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr); +#endif return len; /* call too long for patch site */ + } b->opcode = 0xe9; /* jmp */ b->delta = delta; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 9edadabf04f6..9cb98f7b07c9 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -20,7 +20,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax"); #if defined(CONFIG_PARAVIRT_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); -DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax"); +DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax"); #endif unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index ab5d9dd668d2..acfd04121da3 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -155,9 +155,6 @@ static int __init pci_iommu_init(void) { struct iommu_table_entry *p; -#ifdef CONFIG_PCI - dma_debug_add_bus(&pci_bus_type); -#endif x86_init.iommu.iommu_init(); for (p = __iommu_table; p < __iommu_table_end; p++) { @@ -175,7 +172,7 @@ rootfs_initcall(pci_iommu_init); static int via_no_dac_cb(struct pci_dev *pdev, void *data) { - pdev->dev.dma_32bit_limit = true; + pdev->dev.bus_dma_mask = DMA_BIT_MASK(32); return 0; } diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index 4dfd90a75e63..2e9006c1e240 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -60,7 +60,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start, printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n", p->detect, q->detect); /* Heavy handed way..*/ - x->depend = 0; + x->depend = NULL; } } diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c index da5190a1ea16..4a710ffffd9a 100644 --- a/arch/x86/kernel/pcspeaker.c +++ b/arch/x86/kernel/pcspeaker.c @@ -9,6 +9,6 @@ static __init int add_pcspkr(void) pd = platform_device_register_simple("pcspkr", -1, NULL, 0); - return IS_ERR(pd) ? PTR_ERR(pd) : 0; + return PTR_ERR_OR_ZERO(pd); } device_initcall(add_pcspkr); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 30ca2d1a9231..c93fcfdf1673 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -57,14 +57,12 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = { */ .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, -#ifdef CONFIG_X86_64 /* * .sp1 is cpu_current_top_of_stack. The init task never * runs user code, but cpu_current_top_of_stack should still * be well defined before the first context switch. */ .sp1 = TOP_OF_INIT_STACK, -#endif #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 0ae659de21eb..2924fd447e61 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -285,7 +285,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * current_thread_info(). Refresh the SYSENTER configuration in * case prev or next is vm86. */ - update_sp0(next_p); + update_task_stack(next_p); refresh_sysenter_cs(next); this_cpu_write(cpu_current_top_of_stack, (unsigned long)task_stack_page(next_p) + diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 12bb445fb98d..476e3ddf8890 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -478,7 +478,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); /* Reload sp0. */ - update_sp0(next_p); + update_task_stack(next_p); /* * Now maybe reload the debug registers and handle I/O bitmaps diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 2f86d883dd95..b4866badb235 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -823,6 +823,12 @@ void __init setup_arch(char **cmdline_p) memblock_reserve(__pa_symbol(_text), (unsigned long)__bss_stop - (unsigned long)_text); + /* + * Make sure page 0 is always reserved because on systems with + * L1TF its contents can be leaked to user processes. + */ + memblock_reserve(0, PAGE_SIZE); + early_reserve_initrd(); /* @@ -866,6 +872,8 @@ void __init setup_arch(char **cmdline_p) idt_setup_early_traps(); early_cpu_init(); + arch_init_ideal_nops(); + jump_label_init(); early_ioremap_init(); setup_olpc_ofw_pgd(); @@ -991,11 +999,6 @@ void __init setup_arch(char **cmdline_p) setup_clear_cpu_cap(X86_FEATURE_APIC); } -#ifdef CONFIG_PCI - if (pci_early_dump_regs) - early_dump_pci_devices(); -#endif - e820__reserve_setup_data(); e820__finish_early_params(); @@ -1012,6 +1015,7 @@ void __init setup_arch(char **cmdline_p) */ init_hypervisor_platform(); + tsc_early_init(); x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ @@ -1197,11 +1201,6 @@ void __init setup_arch(char **cmdline_p) memblock_find_dma_reserve(); -#ifdef CONFIG_KVM_GUEST - kvmclock_init(); -#endif - - tsc_early_delay_calibrate(); if (!early_xdbc_setup_hardware()) early_xdbc_register_console(); @@ -1272,8 +1271,6 @@ void __init setup_arch(char **cmdline_p) mcheck_init(); - arch_init_ideal_nops(); - register_refined_jiffies(CLOCK_TICK_RATE); #ifdef CONFIG_EFI diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 5c574dff4c1a..04adc8d60aed 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -261,6 +261,7 @@ __visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); + kvm_set_cpu_l1tf_flush_l1d(); if (trace_resched_ipi_enabled()) { /* diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index db9656e13ea0..f02ecaf97904 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -80,6 +80,7 @@ #include <asm/intel-family.h> #include <asm/cpu_device_id.h> #include <asm/spec-ctrl.h> +#include <asm/hw_irq.h> /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); @@ -271,6 +272,23 @@ static void notrace start_secondary(void *unused) } /** + * topology_is_primary_thread - Check whether CPU is the primary SMT thread + * @cpu: CPU to check + */ +bool topology_is_primary_thread(unsigned int cpu) +{ + return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu)); +} + +/** + * topology_smt_supported - Check whether SMT is supported by the CPUs + */ +bool topology_smt_supported(void) +{ + return smp_num_siblings > 1; +} + +/** * topology_phys_to_logical_pkg - Map a physical package id to a logical * * Returns logical package id or -1 if not found diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 093f2ea5dd56..7627455047c2 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -81,16 +81,6 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE -#define STACKTRACE_DUMP_ONCE(task) ({ \ - static bool __section(.data.unlikely) __dumped; \ - \ - if (!__dumped) { \ - __dumped = true; \ - WARN_ON(1); \ - show_stack(task, NULL); \ - } \ -}) - static int __always_inline __save_stack_trace_reliable(struct stack_trace *trace, struct task_struct *task) @@ -99,30 +89,25 @@ __save_stack_trace_reliable(struct stack_trace *trace, struct pt_regs *regs; unsigned long addr; - for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state); + for (unwind_start(&state, task, NULL, NULL); + !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { regs = unwind_get_entry_regs(&state, NULL); if (regs) { + /* Success path for user tasks */ + if (user_mode(regs)) + goto success; + /* * Kernel mode registers on the stack indicate an * in-kernel interrupt or exception (e.g., preemption * or a page fault), which can make frame pointers * unreliable. */ - if (!user_mode(regs)) - return -EINVAL; - /* - * The last frame contains the user mode syscall - * pt_regs. Skip it and finish the unwind. - */ - unwind_next_frame(&state); - if (!unwind_done(&state)) { - STACKTRACE_DUMP_ONCE(task); + if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; - } - break; } addr = unwind_get_return_address(&state); @@ -132,21 +117,22 @@ __save_stack_trace_reliable(struct stack_trace *trace, * generated code which __kernel_text_address() doesn't know * about. */ - if (!addr) { - STACKTRACE_DUMP_ONCE(task); + if (!addr) return -EINVAL; - } if (save_stack_address(trace, addr, false)) return -EINVAL; } /* Check for stack corruption */ - if (unwind_error(&state)) { - STACKTRACE_DUMP_ONCE(task); + if (unwind_error(&state)) + return -EINVAL; + + /* Success path for non-user tasks, i.e. kthreads and idle tasks */ + if (!(task->flags & (PF_KTHREAD | PF_IDLE))) return -EINVAL; - } +success: if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 774ebafa97c4..be01328eb755 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -12,6 +12,7 @@ #include <linux/clockchips.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/i8253.h> #include <linux/time.h> #include <linux/export.h> diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 74392d9d51e0..1463468ba9a0 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -33,16 +33,13 @@ EXPORT_SYMBOL(cpu_khz); unsigned int __read_mostly tsc_khz; EXPORT_SYMBOL(tsc_khz); +#define KHZ 1000 + /* * TSC can be unstable due to cpufreq or due to unsynced TSCs */ static int __read_mostly tsc_unstable; -/* native_sched_clock() is called before tsc_init(), so - we must start with the TSC soft disabled to prevent - erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */ -static int __read_mostly tsc_disabled = -1; - static DEFINE_STATIC_KEY_FALSE(__use_tsc); int tsc_clocksource_reliable; @@ -106,23 +103,6 @@ void cyc2ns_read_end(void) * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ -static void cyc2ns_data_init(struct cyc2ns_data *data) -{ - data->cyc2ns_mul = 0; - data->cyc2ns_shift = 0; - data->cyc2ns_offset = 0; -} - -static void __init cyc2ns_init(int cpu) -{ - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - - cyc2ns_data_init(&c2n->data[0]); - cyc2ns_data_init(&c2n->data[1]); - - seqcount_init(&c2n->seq); -} - static inline unsigned long long cycles_2_ns(unsigned long long cyc) { struct cyc2ns_data data; @@ -138,18 +118,11 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) return ns; } -static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) +static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { unsigned long long ns_now; struct cyc2ns_data data; struct cyc2ns *c2n; - unsigned long flags; - - local_irq_save(flags); - sched_clock_idle_sleep_event(); - - if (!khz) - goto done; ns_now = cycles_2_ns(tsc_now); @@ -181,13 +154,56 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_ c2n->data[0] = data; raw_write_seqcount_latch(&c2n->seq); c2n->data[1] = data; +} + +static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) +{ + unsigned long flags; + + local_irq_save(flags); + sched_clock_idle_sleep_event(); + + if (khz) + __set_cyc2ns_scale(khz, cpu, tsc_now); -done: sched_clock_idle_wakeup_event(); local_irq_restore(flags); } /* + * Initialize cyc2ns for boot cpu + */ +static void __init cyc2ns_init_boot_cpu(void) +{ + struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); + + seqcount_init(&c2n->seq); + __set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc()); +} + +/* + * Secondary CPUs do not run through tsc_init(), so set up + * all the scale factors for all CPUs, assuming the same + * speed as the bootup CPU. (cpufreq notifiers will fix this + * up if their speed diverges) + */ +static void __init cyc2ns_init_secondary_cpus(void) +{ + unsigned int cpu, this_cpu = smp_processor_id(); + struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); + struct cyc2ns_data *data = c2n->data; + + for_each_possible_cpu(cpu) { + if (cpu != this_cpu) { + seqcount_init(&c2n->seq); + c2n = per_cpu_ptr(&cyc2ns, cpu); + c2n->data[0] = data[0]; + c2n->data[1] = data[1]; + } + } +} + +/* * Scheduler clock - returns current time in nanosec units. */ u64 native_sched_clock(void) @@ -248,8 +264,7 @@ EXPORT_SYMBOL_GPL(check_tsc_unstable); #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { - pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n"); - tsc_disabled = 1; + mark_tsc_unstable("boot parameter notsc"); return 1; } #else @@ -665,30 +680,17 @@ static unsigned long cpu_khz_from_cpuid(void) return eax_base_mhz * 1000; } -/** - * native_calibrate_cpu - calibrate the cpu on boot +/* + * calibrate cpu using pit, hpet, and ptimer methods. They are available + * later in boot after acpi is initialized. */ -unsigned long native_calibrate_cpu(void) +static unsigned long pit_hpet_ptimer_calibrate_cpu(void) { u64 tsc1, tsc2, delta, ref1, ref2; unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX; - unsigned long flags, latch, ms, fast_calibrate; + unsigned long flags, latch, ms; int hpet = is_hpet_enabled(), i, loopmin; - fast_calibrate = cpu_khz_from_cpuid(); - if (fast_calibrate) - return fast_calibrate; - - fast_calibrate = cpu_khz_from_msr(); - if (fast_calibrate) - return fast_calibrate; - - local_irq_save(flags); - fast_calibrate = quick_pit_calibrate(); - local_irq_restore(flags); - if (fast_calibrate) - return fast_calibrate; - /* * Run 5 calibration loops to get the lowest frequency value * (the best estimate). We use two different calibration modes @@ -831,6 +833,37 @@ unsigned long native_calibrate_cpu(void) return tsc_pit_min; } +/** + * native_calibrate_cpu_early - can calibrate the cpu early in boot + */ +unsigned long native_calibrate_cpu_early(void) +{ + unsigned long flags, fast_calibrate = cpu_khz_from_cpuid(); + + if (!fast_calibrate) + fast_calibrate = cpu_khz_from_msr(); + if (!fast_calibrate) { + local_irq_save(flags); + fast_calibrate = quick_pit_calibrate(); + local_irq_restore(flags); + } + return fast_calibrate; +} + + +/** + * native_calibrate_cpu - calibrate the cpu + */ +static unsigned long native_calibrate_cpu(void) +{ + unsigned long tsc_freq = native_calibrate_cpu_early(); + + if (!tsc_freq) + tsc_freq = pit_hpet_ptimer_calibrate_cpu(); + + return tsc_freq; +} + void recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP @@ -1307,7 +1340,7 @@ unreg: static int __init init_tsc_clocksource(void) { - if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz) + if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz) return 0; if (tsc_unstable) @@ -1341,40 +1374,22 @@ unreg: */ device_initcall(init_tsc_clocksource); -void __init tsc_early_delay_calibrate(void) +static bool __init determine_cpu_tsc_frequencies(bool early) { - unsigned long lpj; - - if (!boot_cpu_has(X86_FEATURE_TSC)) - return; - - cpu_khz = x86_platform.calibrate_cpu(); - tsc_khz = x86_platform.calibrate_tsc(); - - tsc_khz = tsc_khz ? : cpu_khz; - if (!tsc_khz) - return; - - lpj = tsc_khz * 1000; - do_div(lpj, HZ); - loops_per_jiffy = lpj; -} - -void __init tsc_init(void) -{ - u64 lpj, cyc; - int cpu; - - if (!boot_cpu_has(X86_FEATURE_TSC)) { - setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); - return; + /* Make sure that cpu and tsc are not already calibrated */ + WARN_ON(cpu_khz || tsc_khz); + + if (early) { + cpu_khz = x86_platform.calibrate_cpu(); + tsc_khz = x86_platform.calibrate_tsc(); + } else { + /* We should not be here with non-native cpu calibration */ + WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu); + cpu_khz = pit_hpet_ptimer_calibrate_cpu(); } - cpu_khz = x86_platform.calibrate_cpu(); - tsc_khz = x86_platform.calibrate_tsc(); - /* - * Trust non-zero tsc_khz as authorative, + * Trust non-zero tsc_khz as authoritative, * and use it to sanity check cpu_khz, * which will be off if system timer is off. */ @@ -1383,52 +1398,78 @@ void __init tsc_init(void) else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz) cpu_khz = tsc_khz; - if (!tsc_khz) { - mark_tsc_unstable("could not calculate TSC khz"); - setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); - return; - } + if (tsc_khz == 0) + return false; pr_info("Detected %lu.%03lu MHz processor\n", - (unsigned long)cpu_khz / 1000, - (unsigned long)cpu_khz % 1000); + (unsigned long)cpu_khz / KHZ, + (unsigned long)cpu_khz % KHZ); if (cpu_khz != tsc_khz) { pr_info("Detected %lu.%03lu MHz TSC", - (unsigned long)tsc_khz / 1000, - (unsigned long)tsc_khz % 1000); + (unsigned long)tsc_khz / KHZ, + (unsigned long)tsc_khz % KHZ); } + return true; +} + +static unsigned long __init get_loops_per_jiffy(void) +{ + unsigned long lpj = tsc_khz * KHZ; + do_div(lpj, HZ); + return lpj; +} + +static void __init tsc_enable_sched_clock(void) +{ /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); + cyc2ns_init_boot_cpu(); + static_branch_enable(&__use_tsc); +} + +void __init tsc_early_init(void) +{ + if (!boot_cpu_has(X86_FEATURE_TSC)) + return; + if (!determine_cpu_tsc_frequencies(true)) + return; + loops_per_jiffy = get_loops_per_jiffy(); + tsc_enable_sched_clock(); +} + +void __init tsc_init(void) +{ /* - * Secondary CPUs do not run through tsc_init(), so set up - * all the scale factors for all CPUs, assuming the same - * speed as the bootup CPU. (cpufreq notifiers will fix this - * up if their speed diverges) + * native_calibrate_cpu_early can only calibrate using methods that are + * available early in boot. */ - cyc = rdtsc(); - for_each_possible_cpu(cpu) { - cyc2ns_init(cpu); - set_cyc2ns_scale(tsc_khz, cpu, cyc); - } + if (x86_platform.calibrate_cpu == native_calibrate_cpu_early) + x86_platform.calibrate_cpu = native_calibrate_cpu; - if (tsc_disabled > 0) + if (!boot_cpu_has(X86_FEATURE_TSC)) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; + } - /* now allow native_sched_clock() to use rdtsc */ + if (!tsc_khz) { + /* We failed to determine frequencies earlier, try again */ + if (!determine_cpu_tsc_frequencies(false)) { + mark_tsc_unstable("could not calculate TSC khz"); + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); + return; + } + tsc_enable_sched_clock(); + } - tsc_disabled = 0; - static_branch_enable(&__use_tsc); + cyc2ns_init_secondary_cpus(); if (!no_sched_irq_time) enable_sched_clock_irqtime(); - lpj = ((u64)tsc_khz * 1000); - do_div(lpj, HZ); - lpj_fine = lpj; - + lpj_fine = get_loops_per_jiffy(); use_tsc_delay(); check_system_tsc_reliable(); @@ -1455,7 +1496,7 @@ unsigned long calibrate_delay_is_known(void) int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC); const struct cpumask *mask = topology_core_cpumask(cpu); - if (tsc_disabled || !constant_tsc || !mask) + if (!constant_tsc || !mask) return 0; sibling = cpumask_any_but(mask, cpu); diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 19afdbd7d0a7..27ef714d886c 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -1,17 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * tsc_msr.c - TSC frequency enumeration via MSR + * TSC frequency enumeration via MSR * - * Copyright (C) 2013 Intel Corporation + * Copyright (C) 2013, 2018 Intel Corporation * Author: Bin Gao <bin.gao@intel.com> - * - * This file is released under the GPLv2. */ #include <linux/kernel.h> -#include <asm/processor.h> -#include <asm/setup.h> + #include <asm/apic.h> +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> +#include <asm/msr.h> #include <asm/param.h> +#include <asm/tsc.h> #define MAX_NUM_FREQS 9 @@ -23,44 +25,48 @@ * field msr_plat does. */ struct freq_desc { - u8 x86_family; /* CPU family */ - u8 x86_model; /* model */ u8 msr_plat; /* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */ u32 freqs[MAX_NUM_FREQS]; }; -static struct freq_desc freq_desc_tables[] = { - /* PNW */ - { 6, 0x27, 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } }, - /* CLV+ */ - { 6, 0x35, 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } }, - /* TNG - Intel Atom processor Z3400 series */ - { 6, 0x4a, 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } }, - /* VLV2 - Intel Atom processor E3000, Z3600, Z3700 series */ - { 6, 0x37, 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } }, - /* ANN - Intel Atom processor Z3500 series */ - { 6, 0x5a, 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } }, - /* AMT - Intel Atom processor X7-Z8000 and X5-Z8000 series */ - { 6, 0x4c, 1, { 83300, 100000, 133300, 116700, - 80000, 93300, 90000, 88900, 87500 } }, +/* + * Penwell and Clovertrail use spread spectrum clock, + * so the freq number is not exactly the same as reported + * by MSR based on SDM. + */ +static const struct freq_desc freq_desc_pnw = { + 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } }; -static int match_cpu(u8 family, u8 model) -{ - int i; +static const struct freq_desc freq_desc_clv = { + 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } +}; - for (i = 0; i < ARRAY_SIZE(freq_desc_tables); i++) { - if ((family == freq_desc_tables[i].x86_family) && - (model == freq_desc_tables[i].x86_model)) - return i; - } +static const struct freq_desc freq_desc_byt = { + 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } +}; - return -1; -} +static const struct freq_desc freq_desc_cht = { + 1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 } +}; -/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */ -#define id_to_freq(cpu_index, freq_id) \ - (freq_desc_tables[cpu_index].freqs[freq_id]) +static const struct freq_desc freq_desc_tng = { + 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } +}; + +static const struct freq_desc freq_desc_ann = { + 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } +}; + +static const struct x86_cpu_id tsc_msr_cpu_ids[] = { + INTEL_CPU_FAM6(ATOM_PENWELL, freq_desc_pnw), + INTEL_CPU_FAM6(ATOM_CLOVERVIEW, freq_desc_clv), + INTEL_CPU_FAM6(ATOM_SILVERMONT1, freq_desc_byt), + INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht), + INTEL_CPU_FAM6(ATOM_MERRIFIELD, freq_desc_tng), + INTEL_CPU_FAM6(ATOM_MOOREFIELD, freq_desc_ann), + {} +}; /* * MSR-based CPU/TSC frequency discovery for certain CPUs. @@ -70,18 +76,17 @@ static int match_cpu(u8 family, u8 model) */ unsigned long cpu_khz_from_msr(void) { - u32 lo, hi, ratio, freq_id, freq; + u32 lo, hi, ratio, freq; + const struct freq_desc *freq_desc; + const struct x86_cpu_id *id; unsigned long res; - int cpu_index; - - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) - return 0; - cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model); - if (cpu_index < 0) + id = x86_match_cpu(tsc_msr_cpu_ids); + if (!id) return 0; - if (freq_desc_tables[cpu_index].msr_plat) { + freq_desc = (struct freq_desc *)id->driver_data; + if (freq_desc->msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); ratio = (lo >> 8) & 0xff; } else { @@ -91,8 +96,9 @@ unsigned long cpu_khz_from_msr(void) /* Get FSB FREQ ID */ rdmsr(MSR_FSB_FREQ, lo, hi); - freq_id = lo & 0x7; - freq = id_to_freq(cpu_index, freq_id); + + /* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */ + freq = freq_desc->freqs[lo & 0x7]; /* TSC frequency = maximum resolved freq * maximum resolved bus ratio */ res = freq * ratio; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index feb28fee6cea..26038eacf74a 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -198,7 +198,7 @@ static int orc_sort_cmp(const void *_a, const void *_b) * whitelisted .o files which didn't get objtool generation. */ orc_a = cur_orc_table + (a - cur_orc_ip_table); - return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1; + return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; } #ifdef CONFIG_MODULES @@ -352,7 +352,7 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip, prev_sp = state->sp; + unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -363,9 +363,9 @@ bool unwind_next_frame(struct unwind_state *state) /* Don't let modules unload while we're reading their ORC data. */ preempt_disable(); - /* Have we reached the end? */ + /* End-of-stack check for user tasks: */ if (state->regs && user_mode(state->regs)) - goto done; + goto the_end; /* * Find the orc_entry associated with the text address. @@ -374,9 +374,16 @@ bool unwind_next_frame(struct unwind_state *state) * calls and calls to noreturn functions. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); - if (!orc || orc->sp_reg == ORC_REG_UNDEFINED) - goto done; - orig_ip = state->ip; + if (!orc) + goto err; + + /* End-of-stack check for kernel threads: */ + if (orc->sp_reg == ORC_REG_UNDEFINED) { + if (!orc->end) + goto err; + + goto the_end; + } /* Find the previous frame's stack: */ switch (orc->sp_reg) { @@ -402,7 +409,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->r10; break; @@ -411,7 +418,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->r13; break; @@ -420,7 +427,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->di; break; @@ -429,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!state->regs || !state->full_regs) { orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); - goto done; + goto err; } sp = state->regs->dx; break; @@ -437,12 +444,12 @@ bool unwind_next_frame(struct unwind_state *state) default: orc_warn("unknown SP base reg %d for ip %pB\n", orc->sp_reg, (void *)state->ip); - goto done; + goto err; } if (indirect) { if (!deref_stack_reg(state, sp, &sp)) - goto done; + goto err; } /* Find IP, SP and possibly regs: */ @@ -451,7 +458,7 @@ bool unwind_next_frame(struct unwind_state *state) ip_p = sp - sizeof(long); if (!deref_stack_reg(state, ip_p, &state->ip)) - goto done; + goto err; state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, state->ip, (void *)ip_p); @@ -465,7 +472,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); - goto done; + goto err; } state->regs = (struct pt_regs *)sp; @@ -477,7 +484,7 @@ bool unwind_next_frame(struct unwind_state *state) if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); - goto done; + goto err; } state->regs = (void *)sp - IRET_FRAME_OFFSET; @@ -500,18 +507,18 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_PREV_SP: if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp)) - goto done; + goto err; break; case ORC_REG_BP: if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp)) - goto done; + goto err; break; default: orc_warn("unknown BP base reg %d for ip %pB\n", orc->bp_reg, (void *)orig_ip); - goto done; + goto err; } /* Prevent a recursive loop due to bad ORC data: */ @@ -520,13 +527,16 @@ bool unwind_next_frame(struct unwind_state *state) state->sp <= prev_sp) { orc_warn("stack going in the wrong direction? ip=%pB\n", (void *)orig_ip); - goto done; + goto err; } preempt_enable(); return true; -done: +err: + state->error = true; + +the_end: preempt_enable(); state->stack_info.type = STACK_TYPE_UNKNOWN; return false; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 9d0b5af7db91..1c03e4aa6474 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -149,7 +149,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) preempt_disable(); tsk->thread.sp0 = vm86->saved_sp0; tsk->thread.sysenter_cs = __KERNEL_CS; - update_sp0(tsk); + update_task_stack(tsk); refresh_sysenter_cs(&tsk->thread); vm86->saved_sp0 = 0; preempt_enable(); @@ -374,7 +374,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) refresh_sysenter_cs(&tsk->thread); } - update_sp0(tsk); + update_task_stack(tsk); preempt_enable(); if (vm86->flags & VM86_SCREEN_BITMAP) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 5e1458f609a1..8bde0a419f86 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -55,19 +55,22 @@ jiffies_64 = jiffies; * so we can enable protection checks as well as retain 2MB large page * mappings for kernel text. */ -#define X64_ALIGN_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); +#define X86_ALIGN_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); -#define X64_ALIGN_RODATA_END \ +#define X86_ALIGN_RODATA_END \ . = ALIGN(HPAGE_SIZE); \ - __end_rodata_hpage_align = .; + __end_rodata_hpage_align = .; \ + __end_rodata_aligned = .; #define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE); #define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE); #else -#define X64_ALIGN_RODATA_BEGIN -#define X64_ALIGN_RODATA_END +#define X86_ALIGN_RODATA_BEGIN +#define X86_ALIGN_RODATA_END \ + . = ALIGN(PAGE_SIZE); \ + __end_rodata_aligned = .; #define ALIGN_ENTRY_TEXT_BEGIN #define ALIGN_ENTRY_TEXT_END @@ -141,9 +144,9 @@ SECTIONS /* .text should occupy whole number of pages */ . = ALIGN(PAGE_SIZE); - X64_ALIGN_RODATA_BEGIN + X86_ALIGN_RODATA_BEGIN RO_DATA(PAGE_SIZE) - X64_ALIGN_RODATA_END + X86_ALIGN_RODATA_END /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) { diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 3ab867603e81..2792b5573818 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -109,7 +109,7 @@ struct x86_cpuinit_ops x86_cpuinit = { static void default_nmi_init(void) { }; struct x86_platform_ops x86_platform __ro_after_init = { - .calibrate_cpu = native_calibrate_cpu, + .calibrate_cpu = native_calibrate_cpu_early, .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_rtc_mmss, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 7e042e3d47fd..7bcfa61375c0 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -621,7 +621,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | (1 << KVM_FEATURE_PV_UNHALT) | (1 << KVM_FEATURE_PV_TLB_FLUSH) | - (1 << KVM_FEATURE_ASYNC_PF_VMEXIT); + (1 << KVM_FEATURE_ASYNC_PF_VMEXIT) | + (1 << KVM_FEATURE_PV_SEND_IPI); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4c4f4263420c..106482da6388 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4191,7 +4191,7 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) maxphyaddr = 36; rsvd = rsvd_bits(maxphyaddr, 63); if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PCIDE) - rsvd &= ~CR3_PCID_INVD; + rsvd &= ~X86_CR3_PCID_NOFLUSH; } if (new_val & rsvd) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index af8caf965baa..01d209ab5481 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -235,7 +235,7 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, struct kvm_vcpu *vcpu = synic_to_vcpu(synic); int ret; - if (!synic->active) + if (!synic->active && !host) return 1; trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host); @@ -295,11 +295,12 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, return ret; } -static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata) +static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata, + bool host) { int ret; - if (!synic->active) + if (!synic->active && !host) return 1; ret = 0; @@ -1014,6 +1015,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, case HV_X64_MSR_TSC_EMULATION_STATUS: hv->hv_tsc_emulation_status = data; break; + case HV_X64_MSR_TIME_REF_COUNT: + /* read-only, but still ignore it if host-initiated */ + if (!host) + return 1; + break; default: vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", msr, data); @@ -1101,6 +1107,12 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return stimer_set_count(vcpu_to_stimer(vcpu, timer_index), data, host); } + case HV_X64_MSR_TSC_FREQUENCY: + case HV_X64_MSR_APIC_FREQUENCY: + /* read-only, but still ignore it if host-initiated */ + if (!host) + return 1; + break; default: vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", msr, data); @@ -1156,7 +1168,8 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } -static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, + bool host) { u64 data = 0; struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; @@ -1183,7 +1196,7 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case HV_X64_MSR_SIMP: case HV_X64_MSR_EOM: case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: - return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata); + return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata, host); case HV_X64_MSR_STIMER0_CONFIG: case HV_X64_MSR_STIMER1_CONFIG: case HV_X64_MSR_STIMER2_CONFIG: @@ -1229,7 +1242,7 @@ int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return kvm_hv_set_msr(vcpu, msr, data, host); } -int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { if (kvm_hv_msr_partition_wide(msr)) { int r; @@ -1239,7 +1252,7 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock); return r; } else - return kvm_hv_get_msr(vcpu, msr, pdata); + return kvm_hv_get_msr(vcpu, msr, pdata, host); } static __always_inline int get_sparse_bank_no(u64 valid_bank_mask, int bank_no) diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 837465d69c6d..d6aa969e20f1 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -48,7 +48,7 @@ static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic) } int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); -int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host); bool kvm_hv_hypercall_enabled(struct kvm *kvm); int kvm_hv_hypercall(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index b5cd8465d44f..0cefba28c864 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -547,6 +547,46 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, irq->level, irq->trig_mode, dest_map); } +int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, + unsigned long ipi_bitmap_high, int min, + unsigned long icr, int op_64_bit) +{ + int i; + struct kvm_apic_map *map; + struct kvm_vcpu *vcpu; + struct kvm_lapic_irq irq = {0}; + int cluster_size = op_64_bit ? 64 : 32; + int count = 0; + + irq.vector = icr & APIC_VECTOR_MASK; + irq.delivery_mode = icr & APIC_MODE_MASK; + irq.level = (icr & APIC_INT_ASSERT) != 0; + irq.trig_mode = icr & APIC_INT_LEVELTRIG; + + if (icr & APIC_DEST_MASK) + return -KVM_EINVAL; + if (icr & APIC_SHORT_MASK) + return -KVM_EINVAL; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + /* Bits above cluster_size are masked in the caller. */ + for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } + + min += cluster_size; + for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } + + rcu_read_unlock(); + return count; +} + static int pv_eoi_put_user(struct kvm_vcpu *vcpu, u8 val) { @@ -1379,7 +1419,7 @@ static void apic_timer_expired(struct kvm_lapic *apic) * using swait_active() is safe. */ if (swait_active(q)) - swake_up(q); + swake_up_one(q); if (apic_lvtt_tscdeadline(apic)) ktimer->expired_tscdeadline = ktimer->tscdeadline; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d594690d8b95..a282321329b5 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -178,7 +178,24 @@ struct kvm_shadow_walk_iterator { unsigned index; }; -#define for_each_shadow_entry(_vcpu, _addr, _walker) \ +static const union kvm_mmu_page_role mmu_base_role_mask = { + .cr0_wp = 1, + .cr4_pae = 1, + .nxe = 1, + .smep_andnot_wp = 1, + .smap_andnot_wp = 1, + .smm = 1, + .guest_mode = 1, + .ad_disabled = 1, +}; + +#define for_each_shadow_entry_using_root(_vcpu, _root, _addr, _walker) \ + for (shadow_walk_init_using_root(&(_walker), (_vcpu), \ + (_root), (_addr)); \ + shadow_walk_okay(&(_walker)); \ + shadow_walk_next(&(_walker))) + +#define for_each_shadow_entry(_vcpu, _addr, _walker) \ for (shadow_walk_init(&(_walker), _vcpu, _addr); \ shadow_walk_okay(&(_walker)); \ shadow_walk_next(&(_walker))) @@ -221,7 +238,20 @@ static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK | PT64_EPT_EXECUTABLE_MASK; static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT; +/* + * This mask must be set on all non-zero Non-Present or Reserved SPTEs in order + * to guard against L1TF attacks. + */ +static u64 __read_mostly shadow_nonpresent_or_rsvd_mask; + +/* + * The number of high-order 1 bits to use in the mask above. + */ +static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; + static void mmu_spte_set(u64 *sptep, u64 spte); +static union kvm_mmu_page_role +kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) { @@ -308,9 +338,13 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, { unsigned int gen = kvm_current_mmio_generation(vcpu); u64 mask = generation_mmio_spte_mask(gen); + u64 gpa = gfn << PAGE_SHIFT; access &= ACC_WRITE_MASK | ACC_USER_MASK; - mask |= shadow_mmio_value | access | gfn << PAGE_SHIFT; + mask |= shadow_mmio_value | access; + mask |= gpa | shadow_nonpresent_or_rsvd_mask; + mask |= (gpa & shadow_nonpresent_or_rsvd_mask) + << shadow_nonpresent_or_rsvd_mask_len; trace_mark_mmio_spte(sptep, gfn, access, gen); mmu_spte_set(sptep, mask); @@ -323,8 +357,14 @@ static bool is_mmio_spte(u64 spte) static gfn_t get_mmio_spte_gfn(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask; - return (spte & ~mask) >> PAGE_SHIFT; + u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask | + shadow_nonpresent_or_rsvd_mask; + u64 gpa = spte & ~mask; + + gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len) + & shadow_nonpresent_or_rsvd_mask; + + return gpa >> PAGE_SHIFT; } static unsigned get_mmio_spte_access(u64 spte) @@ -381,7 +421,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); -static void kvm_mmu_clear_all_pte_masks(void) +static void kvm_mmu_reset_all_pte_masks(void) { shadow_user_mask = 0; shadow_accessed_mask = 0; @@ -391,6 +431,18 @@ static void kvm_mmu_clear_all_pte_masks(void) shadow_mmio_mask = 0; shadow_present_mask = 0; shadow_acc_track_mask = 0; + + /* + * If the CPU has 46 or less physical address bits, then set an + * appropriate mask to guard against L1TF attacks. Otherwise, it is + * assumed that the CPU is not vulnerable to L1TF. + */ + if (boot_cpu_data.x86_phys_bits < + 52 - shadow_nonpresent_or_rsvd_mask_len) + shadow_nonpresent_or_rsvd_mask = + rsvd_bits(boot_cpu_data.x86_phys_bits - + shadow_nonpresent_or_rsvd_mask_len, + boot_cpu_data.x86_phys_bits - 1); } static int is_cpuid_PSE36(void) @@ -890,7 +942,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = (void *)__get_free_page(GFP_KERNEL); + page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); if (!page) return -ENOMEM; cache->objects[cache->nobjs++] = page; @@ -1986,7 +2038,7 @@ static int nonpaging_sync_page(struct kvm_vcpu *vcpu, return 0; } -static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva) +static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root) { } @@ -2117,12 +2169,8 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { - if (sp->role.cr4_pae != !!is_pae(vcpu)) { - kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); - return false; - } - - if (vcpu->arch.mmu.sync_page(vcpu, sp) == 0) { + if (sp->role.cr4_pae != !!is_pae(vcpu) + || vcpu->arch.mmu.sync_page(vcpu, sp) == 0) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return false; } @@ -2392,11 +2440,12 @@ out: return sp; } -static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, - struct kvm_vcpu *vcpu, u64 addr) +static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterator, + struct kvm_vcpu *vcpu, hpa_t root, + u64 addr) { iterator->addr = addr; - iterator->shadow_addr = vcpu->arch.mmu.root_hpa; + iterator->shadow_addr = root; iterator->level = vcpu->arch.mmu.shadow_root_level; if (iterator->level == PT64_ROOT_4LEVEL && @@ -2405,6 +2454,12 @@ static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, --iterator->level; if (iterator->level == PT32E_ROOT_LEVEL) { + /* + * prev_root is currently only used for 64-bit hosts. So only + * the active root_hpa is valid here. + */ + BUG_ON(root != vcpu->arch.mmu.root_hpa); + iterator->shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3]; iterator->shadow_addr &= PT64_BASE_ADDR_MASK; @@ -2414,6 +2469,13 @@ static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, } } +static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, + struct kvm_vcpu *vcpu, u64 addr) +{ + shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu.root_hpa, + addr); +} + static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) { if (iterator->level < PT_PAGE_TABLE_LEVEL) @@ -2702,6 +2764,45 @@ static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_unsync_page(vcpu, sp); } + /* + * We need to ensure that the marking of unsync pages is visible + * before the SPTE is updated to allow writes because + * kvm_mmu_sync_roots() checks the unsync flags without holding + * the MMU lock and so can race with this. If the SPTE was updated + * before the page had been marked as unsync-ed, something like the + * following could happen: + * + * CPU 1 CPU 2 + * --------------------------------------------------------------------- + * 1.2 Host updates SPTE + * to be writable + * 2.1 Guest writes a GPTE for GVA X. + * (GPTE being in the guest page table shadowed + * by the SP from CPU 1.) + * This reads SPTE during the page table walk. + * Since SPTE.W is read as 1, there is no + * fault. + * + * 2.2 Guest issues TLB flush. + * That causes a VM Exit. + * + * 2.3 kvm_mmu_sync_pages() reads sp->unsync. + * Since it is false, so it just returns. + * + * 2.4 Guest accesses GVA X. + * Since the mapping in the SP was not updated, + * so the old mapping for GVA X incorrectly + * gets used. + * 1.1 Host marks SP + * as unsync + * (sp->unsync = true) + * + * The write barrier below ensures that 1.1 happens before 1.2 and thus + * the situation in 2.4 does not arise. The implicit barrier in 2.2 + * pairs with this write barrier. + */ + smp_wmb(); + return false; } @@ -2724,6 +2825,10 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) return true; } +/* Bits which may be returned by set_spte() */ +#define SET_SPTE_WRITE_PROTECTED_PT BIT(0) +#define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1) + static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, gfn_t gfn, kvm_pfn_t pfn, bool speculative, @@ -2800,7 +2905,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (mmu_need_write_protect(vcpu, gfn, can_unsync)) { pgprintk("%s: found shadow page for %llx, marking ro\n", __func__, gfn); - ret = 1; + ret |= SET_SPTE_WRITE_PROTECTED_PT; pte_access &= ~ACC_WRITE_MASK; spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE); } @@ -2816,7 +2921,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, set_pte: if (mmu_spte_update(sptep, spte)) - kvm_flush_remote_tlbs(vcpu->kvm); + ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; done: return ret; } @@ -2827,7 +2932,9 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, { int was_rmapped = 0; int rmap_count; + int set_spte_ret; int ret = RET_PF_RETRY; + bool flush = false; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); @@ -2844,22 +2951,25 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, child = page_header(pte & PT64_BASE_ADDR_MASK); drop_parent_pte(child, sptep); - kvm_flush_remote_tlbs(vcpu->kvm); + flush = true; } else if (pfn != spte_to_pfn(*sptep)) { pgprintk("hfn old %llx new %llx\n", spte_to_pfn(*sptep), pfn); drop_spte(vcpu->kvm, sptep); - kvm_flush_remote_tlbs(vcpu->kvm); + flush = true; } else was_rmapped = 1; } - if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative, - true, host_writable)) { + set_spte_ret = set_spte(vcpu, sptep, pte_access, level, gfn, pfn, + speculative, true, host_writable); + if (set_spte_ret & SET_SPTE_WRITE_PROTECTED_PT) { if (write_fault) ret = RET_PF_EMULATE; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } + if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH || flush) + kvm_flush_remote_tlbs(vcpu->kvm); if (unlikely(is_mmio_spte(*sptep))) ret = RET_PF_EMULATE; @@ -3358,26 +3468,47 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, *root_hpa = INVALID_PAGE; } -void kvm_mmu_free_roots(struct kvm_vcpu *vcpu) +/* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */ +void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free) { int i; LIST_HEAD(invalid_list); struct kvm_mmu *mmu = &vcpu->arch.mmu; + bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT; - if (!VALID_PAGE(mmu->root_hpa)) - return; + BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG); + + /* Before acquiring the MMU lock, see if we need to do any real work. */ + if (!(free_active_root && VALID_PAGE(mmu->root_hpa))) { + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if ((roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) && + VALID_PAGE(mmu->prev_roots[i].hpa)) + break; + + if (i == KVM_MMU_NUM_PREV_ROOTS) + return; + } spin_lock(&vcpu->kvm->mmu_lock); - if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL && - (mmu->root_level >= PT64_ROOT_4LEVEL || mmu->direct_map)) { - mmu_free_root_page(vcpu->kvm, &mmu->root_hpa, &invalid_list); - } else { - for (i = 0; i < 4; ++i) - if (mmu->pae_root[i] != 0) - mmu_free_root_page(vcpu->kvm, &mmu->pae_root[i], - &invalid_list); - mmu->root_hpa = INVALID_PAGE; + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) + mmu_free_root_page(vcpu->kvm, &mmu->prev_roots[i].hpa, + &invalid_list); + + if (free_active_root) { + if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL && + (mmu->root_level >= PT64_ROOT_4LEVEL || mmu->direct_map)) { + mmu_free_root_page(vcpu->kvm, &mmu->root_hpa, + &invalid_list); + } else { + for (i = 0; i < 4; ++i) + if (mmu->pae_root[i] != 0) + mmu_free_root_page(vcpu->kvm, + &mmu->pae_root[i], + &invalid_list); + mmu->root_hpa = INVALID_PAGE; + } } kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); @@ -3546,7 +3677,7 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu) return mmu_alloc_shadow_roots(vcpu); } -static void mmu_sync_roots(struct kvm_vcpu *vcpu) +void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) { int i; struct kvm_mmu_page *sp; @@ -3558,14 +3689,39 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) return; vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); - kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); + if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; + sp = page_header(root); + + /* + * Even if another CPU was marking the SP as unsync-ed + * simultaneously, any guest page table changes are not + * guaranteed to be visible anyway until this VCPU issues a TLB + * flush strictly after those changes are made. We only need to + * ensure that the other CPU sets these flags before any actual + * changes to the page tables are made. The comments in + * mmu_need_write_protect() describe what could go wrong if this + * requirement isn't satisfied. + */ + if (!smp_load_acquire(&sp->unsync) && + !smp_load_acquire(&sp->unsync_children)) + return; + + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); + mmu_sync_children(vcpu, sp); + kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); + spin_unlock(&vcpu->kvm->mmu_lock); return; } + + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); + for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -3575,13 +3731,8 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) mmu_sync_children(vcpu, sp); } } - kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); -} -void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) -{ - spin_lock(&vcpu->kvm->mmu_lock); - mmu_sync_roots(vcpu); + kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); spin_unlock(&vcpu->kvm->mmu_lock); } EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); @@ -3840,6 +3991,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, { int r = 1; + vcpu->arch.l1tf_flush_l1d = true; switch (vcpu->arch.apf.host_apf_reason) { default: trace_kvm_page_fault(fault_address, error_code); @@ -3947,16 +4099,107 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu, context->update_pte = nonpaging_update_pte; context->root_level = 0; context->shadow_root_level = PT32E_ROOT_LEVEL; - context->root_hpa = INVALID_PAGE; context->direct_map = true; context->nx = false; } -void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu) +/* + * Find out if a previously cached root matching the new CR3/role is available. + * The current root is also inserted into the cache. + * If a matching root was found, it is assigned to kvm_mmu->root_hpa and true is + * returned. + * Otherwise, the LRU root from the cache is assigned to kvm_mmu->root_hpa and + * false is returned. This root should now be freed by the caller. + */ +static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3, + union kvm_mmu_page_role new_role) +{ + uint i; + struct kvm_mmu_root_info root; + struct kvm_mmu *mmu = &vcpu->arch.mmu; + + root.cr3 = mmu->get_cr3(vcpu); + root.hpa = mmu->root_hpa; + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + swap(root, mmu->prev_roots[i]); + + if (new_cr3 == root.cr3 && VALID_PAGE(root.hpa) && + page_header(root.hpa) != NULL && + new_role.word == page_header(root.hpa)->role.word) + break; + } + + mmu->root_hpa = root.hpa; + + return i < KVM_MMU_NUM_PREV_ROOTS; +} + +static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, + union kvm_mmu_page_role new_role, + bool skip_tlb_flush) { - kvm_mmu_free_roots(vcpu); + struct kvm_mmu *mmu = &vcpu->arch.mmu; + + /* + * For now, limit the fast switch to 64-bit hosts+VMs in order to avoid + * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs + * later if necessary. + */ + if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL && + mmu->root_level >= PT64_ROOT_4LEVEL) { + if (mmu_check_root(vcpu, new_cr3 >> PAGE_SHIFT)) + return false; + + if (cached_root_available(vcpu, new_cr3, new_role)) { + /* + * It is possible that the cached previous root page is + * obsolete because of a change in the MMU + * generation number. However, that is accompanied by + * KVM_REQ_MMU_RELOAD, which will free the root that we + * have set here and allocate a new one. + */ + + kvm_make_request(KVM_REQ_LOAD_CR3, vcpu); + if (!skip_tlb_flush) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_x86_ops->tlb_flush(vcpu, true); + } + + /* + * The last MMIO access's GVA and GPA are cached in the + * VCPU. When switching to a new CR3, that GVA->GPA + * mapping may no longer be valid. So clear any cached + * MMIO info even when we don't need to sync the shadow + * page tables. + */ + vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); + + __clear_sp_write_flooding_count( + page_header(mmu->root_hpa)); + + return true; + } + } + + return false; } +static void __kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, + union kvm_mmu_page_role new_role, + bool skip_tlb_flush) +{ + if (!fast_cr3_switch(vcpu, new_cr3, new_role, skip_tlb_flush)) + kvm_mmu_free_roots(vcpu, KVM_MMU_ROOT_CURRENT); +} + +void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush) +{ + __kvm_mmu_new_cr3(vcpu, new_cr3, kvm_mmu_calc_root_page_role(vcpu), + skip_tlb_flush); +} +EXPORT_SYMBOL_GPL(kvm_mmu_new_cr3); + static unsigned long get_cr3(struct kvm_vcpu *vcpu) { return kvm_read_cr3(vcpu); @@ -4431,7 +4674,6 @@ static void paging64_init_context_common(struct kvm_vcpu *vcpu, context->invlpg = paging64_invlpg; context->update_pte = paging64_update_pte; context->shadow_root_level = level; - context->root_hpa = INVALID_PAGE; context->direct_map = false; } @@ -4461,7 +4703,6 @@ static void paging32_init_context(struct kvm_vcpu *vcpu, context->invlpg = paging32_invlpg; context->update_pte = paging32_update_pte; context->shadow_root_level = PT32E_ROOT_LEVEL; - context->root_hpa = INVALID_PAGE; context->direct_map = false; } @@ -4471,20 +4712,32 @@ static void paging32E_init_context(struct kvm_vcpu *vcpu, paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); } +static union kvm_mmu_page_role +kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu) +{ + union kvm_mmu_page_role role = {0}; + + role.guest_mode = is_guest_mode(vcpu); + role.smm = is_smm(vcpu); + role.ad_disabled = (shadow_accessed_mask == 0); + role.level = kvm_x86_ops->get_tdp_level(vcpu); + role.direct = true; + role.access = ACC_ALL; + + return role; +} + static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *context = &vcpu->arch.mmu; - context->base_role.word = 0; - context->base_role.guest_mode = is_guest_mode(vcpu); - context->base_role.smm = is_smm(vcpu); - context->base_role.ad_disabled = (shadow_accessed_mask == 0); + context->base_role.word = mmu_base_role_mask.word & + kvm_calc_tdp_mmu_root_page_role(vcpu).word; context->page_fault = tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu); - context->root_hpa = INVALID_PAGE; context->direct_map = true; context->set_cr3 = kvm_x86_ops->set_tdp_cr3; context->get_cr3 = get_cr3; @@ -4519,13 +4772,36 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) reset_tdp_shadow_zero_bits_mask(vcpu, context); } -void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) +static union kvm_mmu_page_role +kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu) { + union kvm_mmu_page_role role = {0}; bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); - struct kvm_mmu *context = &vcpu->arch.mmu; - MMU_WARN_ON(VALID_PAGE(context->root_hpa)); + role.nxe = is_nx(vcpu); + role.cr4_pae = !!is_pae(vcpu); + role.cr0_wp = is_write_protection(vcpu); + role.smep_andnot_wp = smep && !is_write_protection(vcpu); + role.smap_andnot_wp = smap && !is_write_protection(vcpu); + role.guest_mode = is_guest_mode(vcpu); + role.smm = is_smm(vcpu); + role.direct = !is_paging(vcpu); + role.access = ACC_ALL; + + if (!is_long_mode(vcpu)) + role.level = PT32E_ROOT_LEVEL; + else if (is_la57_mode(vcpu)) + role.level = PT64_ROOT_5LEVEL; + else + role.level = PT64_ROOT_4LEVEL; + + return role; +} + +void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu *context = &vcpu->arch.mmu; if (!is_paging(vcpu)) nonpaging_init_context(vcpu, context); @@ -4536,26 +4812,34 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) else paging32_init_context(vcpu, context); - context->base_role.nxe = is_nx(vcpu); - context->base_role.cr4_pae = !!is_pae(vcpu); - context->base_role.cr0_wp = is_write_protection(vcpu); - context->base_role.smep_andnot_wp - = smep && !is_write_protection(vcpu); - context->base_role.smap_andnot_wp - = smap && !is_write_protection(vcpu); - context->base_role.guest_mode = is_guest_mode(vcpu); - context->base_role.smm = is_smm(vcpu); + context->base_role.word = mmu_base_role_mask.word & + kvm_calc_shadow_mmu_root_page_role(vcpu).word; reset_shadow_zero_bits_mask(vcpu, context); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); +static union kvm_mmu_page_role +kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty) +{ + union kvm_mmu_page_role role = vcpu->arch.mmu.base_role; + + role.level = PT64_ROOT_4LEVEL; + role.direct = false; + role.ad_disabled = !accessed_dirty; + role.guest_mode = true; + role.access = ACC_ALL; + + return role; +} + void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty) + bool accessed_dirty, gpa_t new_eptp) { struct kvm_mmu *context = &vcpu->arch.mmu; + union kvm_mmu_page_role root_page_role = + kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty); - MMU_WARN_ON(VALID_PAGE(context->root_hpa)); - + __kvm_mmu_new_cr3(vcpu, new_eptp, root_page_role, false); context->shadow_root_level = PT64_ROOT_4LEVEL; context->nx = true; @@ -4566,10 +4850,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->invlpg = ept_invlpg; context->update_pte = ept_update_pte; context->root_level = PT64_ROOT_4LEVEL; - context->root_hpa = INVALID_PAGE; context->direct_map = false; - context->base_role.ad_disabled = !accessed_dirty; - context->base_role.guest_mode = 1; + context->base_role.word = root_page_role.word & mmu_base_role_mask.word; update_permission_bitmask(vcpu, context, true); update_pkru_bitmask(vcpu, context, true); update_last_nonleaf_level(vcpu, context); @@ -4632,8 +4914,17 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) update_last_nonleaf_level(vcpu, g_context); } -static void init_kvm_mmu(struct kvm_vcpu *vcpu) +void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots) { + if (reset_roots) { + uint i; + + vcpu->arch.mmu.root_hpa = INVALID_PAGE; + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; + } + if (mmu_is_nested(vcpu)) init_kvm_nested_mmu(vcpu); else if (tdp_enabled) @@ -4641,11 +4932,21 @@ static void init_kvm_mmu(struct kvm_vcpu *vcpu) else init_kvm_softmmu(vcpu); } +EXPORT_SYMBOL_GPL(kvm_init_mmu); + +static union kvm_mmu_page_role +kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu) +{ + if (tdp_enabled) + return kvm_calc_tdp_mmu_root_page_role(vcpu); + else + return kvm_calc_shadow_mmu_root_page_role(vcpu); +} void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); - init_kvm_mmu(vcpu); + kvm_init_mmu(vcpu, true); } EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); @@ -4660,8 +4961,8 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) kvm_mmu_sync_roots(vcpu); if (r) goto out; - /* set_cr3() should ensure TLB has been flushed */ - vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa); + kvm_mmu_load_cr3(vcpu); + kvm_x86_ops->tlb_flush(vcpu, true); out: return r; } @@ -4669,7 +4970,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load); void kvm_mmu_unload(struct kvm_vcpu *vcpu) { - kvm_mmu_free_roots(vcpu); + kvm_mmu_free_roots(vcpu, KVM_MMU_ROOTS_ALL); WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); } EXPORT_SYMBOL_GPL(kvm_mmu_unload); @@ -4822,16 +5123,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, u64 entry, gentry, *spte; int npte; bool remote_flush, local_flush; - union kvm_mmu_page_role mask = { }; - - mask.cr0_wp = 1; - mask.cr4_pae = 1; - mask.nxe = 1; - mask.smep_andnot_wp = 1; - mask.smap_andnot_wp = 1; - mask.smm = 1; - mask.guest_mode = 1; - mask.ad_disabled = 1; /* * If we don't have indirect shadow pages, it means no page is @@ -4875,7 +5166,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mmu_page_zap_pte(vcpu->kvm, sp, spte); if (gentry && !((sp->role.word ^ vcpu->arch.mmu.base_role.word) - & mask.word) && rmap_can_add(vcpu)) + & mmu_base_role_mask.word) && rmap_can_add(vcpu)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); if (need_remote_flush(entry, *spte)) remote_flush = true; @@ -5000,12 +5291,67 @@ EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { - vcpu->arch.mmu.invlpg(vcpu, gva); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + struct kvm_mmu *mmu = &vcpu->arch.mmu; + int i; + + /* INVLPG on a * non-canonical address is a NOP according to the SDM. */ + if (is_noncanonical_address(gva, vcpu)) + return; + + mmu->invlpg(vcpu, gva, mmu->root_hpa); + + /* + * INVLPG is required to invalidate any global mappings for the VA, + * irrespective of PCID. Since it would take us roughly similar amount + * of work to determine whether any of the prev_root mappings of the VA + * is marked global, or to just sync it blindly, so we might as well + * just always sync it. + * + * Mappings not reachable via the current cr3 or the prev_roots will be + * synced when switching to that cr3, so nothing needs to be done here + * for them. + */ + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (VALID_PAGE(mmu->prev_roots[i].hpa)) + mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); + + kvm_x86_ops->tlb_flush_gva(vcpu, gva); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); +void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) +{ + struct kvm_mmu *mmu = &vcpu->arch.mmu; + bool tlb_flush = false; + uint i; + + if (pcid == kvm_get_active_pcid(vcpu)) { + mmu->invlpg(vcpu, gva, mmu->root_hpa); + tlb_flush = true; + } + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + if (VALID_PAGE(mmu->prev_roots[i].hpa) && + pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].cr3)) { + mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); + tlb_flush = true; + } + } + + if (tlb_flush) + kvm_x86_ops->tlb_flush_gva(vcpu, gva); + + ++vcpu->stat.invlpg; + + /* + * Mappings not reachable via the current cr3 or the prev_roots will be + * synced when switching to that cr3, so nothing needs to be done here + * for them. + */ +} +EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva); + void kvm_enable_tdp(void) { tdp_enabled = true; @@ -5029,6 +5375,9 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) struct page *page; int i; + if (tdp_enabled) + return 0; + /* * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64. * Therefore we need to allocate shadow page tables in the first @@ -5047,11 +5396,16 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) int kvm_mmu_create(struct kvm_vcpu *vcpu) { + uint i; + vcpu->arch.walk_mmu = &vcpu->arch.mmu; vcpu->arch.mmu.root_hpa = INVALID_PAGE; vcpu->arch.mmu.translate_gpa = translate_gpa; vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; + return alloc_mmu_pages(vcpu); } @@ -5059,7 +5413,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) { MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); - init_kvm_mmu(vcpu); + kvm_init_mmu(vcpu, true); } static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, @@ -5499,7 +5853,7 @@ int kvm_mmu_module_init(void) { int ret = -ENOMEM; - kvm_mmu_clear_all_pte_masks(); + kvm_mmu_reset_all_pte_masks(); pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 5b408c0ad612..1fab69c0b2f3 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -61,9 +61,10 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); +void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, - bool accessed_dirty); + bool accessed_dirty, gpa_t new_eptp); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); @@ -85,6 +86,27 @@ static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) return kvm_mmu_load(vcpu); } +static inline unsigned long kvm_get_pcid(struct kvm_vcpu *vcpu, gpa_t cr3) +{ + BUILD_BUG_ON((X86_CR3_PCID_MASK & PAGE_MASK) != 0); + + return kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE) + ? cr3 & X86_CR3_PCID_MASK + : 0; +} + +static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) +{ + return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu)); +} + +static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu) +{ + if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) + vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa | + kvm_get_active_pcid(vcpu)); +} + /* * Currently, we have two sorts of write-protection, a) the first one * write-protects guest page to sync the guest modification, b) another one is diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6288e9d7068e..14ffd973df54 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -181,7 +181,7 @@ no_present: * set bit 0 if execute only is supported. Here, we repurpose ACC_USER_MASK * to signify readability since it isn't used in the EPT case */ -static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte) +static inline unsigned FNAME(gpte_access)(u64 gpte) { unsigned access; #if PTTYPE == PTTYPE_EPT @@ -394,8 +394,8 @@ retry_walk: accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0; /* Convert to ACC_*_MASK flags for struct guest_walker. */ - walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask); - walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask); + walker->pt_access = FNAME(gpte_access)(pt_access ^ walk_nx_mask); + walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask); errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access); if (unlikely(errcode)) goto error; @@ -508,7 +508,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); gfn = gpte_to_gfn(gpte); - pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte); + pte_access = sp->role.access & FNAME(gpte_access)(gpte); FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte); pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn, no_dirty_log && (pte_access & ACC_WRITE_MASK)); @@ -856,7 +856,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); } -static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) +static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -871,13 +871,13 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) */ mmu_topup_memory_caches(vcpu); - if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) { + if (!VALID_PAGE(root_hpa)) { WARN_ON(1); return; } spin_lock(&vcpu->kvm->mmu_lock); - for_each_shadow_entry(vcpu, gva, iterator) { + for_each_shadow_entry_using_root(vcpu, root_hpa, gva, iterator) { level = iterator.level; sptep = iterator.sptep; @@ -968,6 +968,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) int i, nr_present = 0; bool host_writable; gpa_t first_pte_gpa; + int set_spte_ret = 0; /* direct kvm_mmu_page can not be unsync. */ BUG_ON(sp->role.direct); @@ -1002,7 +1003,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) gfn = gpte_to_gfn(gpte); pte_access = sp->role.access; - pte_access &= FNAME(gpte_access)(vcpu, gpte); + pte_access &= FNAME(gpte_access)(gpte); FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte); if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access, @@ -1024,12 +1025,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE; - set_spte(vcpu, &sp->spt[i], pte_access, - PT_PAGE_TABLE_LEVEL, gfn, - spte_to_pfn(sp->spt[i]), true, false, - host_writable); + set_spte_ret |= set_spte(vcpu, &sp->spt[i], + pte_access, PT_PAGE_TABLE_LEVEL, + gfn, spte_to_pfn(sp->spt[i]), + true, false, host_writable); } + if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH) + kvm_flush_remote_tlbs(vcpu->kvm); + return nr_present; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f059a73f0fd0..73e27a98456f 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2884,7 +2884,6 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); - svm_flush_tlb(vcpu, true); } static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, @@ -5435,6 +5434,13 @@ static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) svm->asid_generation--; } +static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + invlpga(gva, svm->vmcb->control.asid); +} + static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) { } @@ -5766,7 +5772,6 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_CR); - svm_flush_tlb(vcpu, true); } static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) @@ -5779,8 +5784,6 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) /* Also sync guest cr3 here in case we live migrate */ svm->vmcb->save.cr3 = kvm_read_cr3(vcpu); mark_dirty(svm->vmcb, VMCB_CR); - - svm_flush_tlb(vcpu, true); } static int is_disabled(void) @@ -7090,6 +7093,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .set_rflags = svm_set_rflags, .tlb_flush = svm_flush_tlb, + .tlb_flush_gva = svm_flush_tlb_gva, .run = svm_vcpu_run, .handle_exit = handle_exit, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e30da9a2430c..1519f030fd73 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -38,6 +38,7 @@ #include "kvm_cache_regs.h" #include "x86.h" +#include <asm/asm.h> #include <asm/cpu.h> #include <asm/io.h> #include <asm/desc.h> @@ -188,23 +189,198 @@ module_param(ple_window_max, uint, 0444); extern const ulong vmx_return; +static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); +static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); +static DEFINE_MUTEX(vmx_l1d_flush_mutex); + +/* Storage for pre module init parameter parsing */ +static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO; + +static const struct { + const char *option; + enum vmx_l1d_flush_state cmd; +} vmentry_l1d_param[] = { + {"auto", VMENTER_L1D_FLUSH_AUTO}, + {"never", VMENTER_L1D_FLUSH_NEVER}, + {"cond", VMENTER_L1D_FLUSH_COND}, + {"always", VMENTER_L1D_FLUSH_ALWAYS}, +}; + +#define L1D_CACHE_ORDER 4 +static void *vmx_l1d_flush_pages; + +static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) +{ + struct page *page; + unsigned int i; + + if (!enable_ept) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; + return 0; + } + + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { + u64 msr; + + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); + if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; + return 0; + } + } + + /* If set to auto use the default l1tf mitigation method */ + if (l1tf == VMENTER_L1D_FLUSH_AUTO) { + switch (l1tf_mitigation) { + case L1TF_MITIGATION_OFF: + l1tf = VMENTER_L1D_FLUSH_NEVER; + break; + case L1TF_MITIGATION_FLUSH_NOWARN: + case L1TF_MITIGATION_FLUSH: + case L1TF_MITIGATION_FLUSH_NOSMT: + l1tf = VMENTER_L1D_FLUSH_COND; + break; + case L1TF_MITIGATION_FULL: + case L1TF_MITIGATION_FULL_FORCE: + l1tf = VMENTER_L1D_FLUSH_ALWAYS; + break; + } + } else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) { + l1tf = VMENTER_L1D_FLUSH_ALWAYS; + } + + if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages && + !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) { + page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); + if (!page) + return -ENOMEM; + vmx_l1d_flush_pages = page_address(page); + + /* + * Initialize each page with a different pattern in + * order to protect against KSM in the nested + * virtualization case. + */ + for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) { + memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1, + PAGE_SIZE); + } + } + + l1tf_vmx_mitigation = l1tf; + + if (l1tf != VMENTER_L1D_FLUSH_NEVER) + static_branch_enable(&vmx_l1d_should_flush); + else + static_branch_disable(&vmx_l1d_should_flush); + + if (l1tf == VMENTER_L1D_FLUSH_COND) + static_branch_enable(&vmx_l1d_flush_cond); + else + static_branch_disable(&vmx_l1d_flush_cond); + return 0; +} + +static int vmentry_l1d_flush_parse(const char *s) +{ + unsigned int i; + + if (s) { + for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) { + if (sysfs_streq(s, vmentry_l1d_param[i].option)) + return vmentry_l1d_param[i].cmd; + } + } + return -EINVAL; +} + +static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) +{ + int l1tf, ret; + + if (!boot_cpu_has(X86_BUG_L1TF)) + return 0; + + l1tf = vmentry_l1d_flush_parse(s); + if (l1tf < 0) + return l1tf; + + /* + * Has vmx_init() run already? If not then this is the pre init + * parameter parsing. In that case just store the value and let + * vmx_init() do the proper setup after enable_ept has been + * established. + */ + if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) { + vmentry_l1d_flush_param = l1tf; + return 0; + } + + mutex_lock(&vmx_l1d_flush_mutex); + ret = vmx_setup_l1d_flush(l1tf); + mutex_unlock(&vmx_l1d_flush_mutex); + return ret; +} + +static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) +{ + return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); +} + +static const struct kernel_param_ops vmentry_l1d_flush_ops = { + .set = vmentry_l1d_flush_set, + .get = vmentry_l1d_flush_get, +}; +module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); + +enum ept_pointers_status { + EPT_POINTERS_CHECK = 0, + EPT_POINTERS_MATCH = 1, + EPT_POINTERS_MISMATCH = 2 +}; + struct kvm_vmx { struct kvm kvm; unsigned int tss_addr; bool ept_identity_pagetable_done; gpa_t ept_identity_map_addr; + + enum ept_pointers_status ept_pointers_match; + spinlock_t ept_pointer_lock; }; #define NR_AUTOLOAD_MSRS 8 +struct vmcs_hdr { + u32 revision_id:31; + u32 shadow_vmcs:1; +}; + struct vmcs { - u32 revision_id; + struct vmcs_hdr hdr; u32 abort; char data[0]; }; /* + * vmcs_host_state tracks registers that are loaded from the VMCS on VMEXIT + * and whose values change infrequently, but are not constant. I.e. this is + * used as a write-through cache of the corresponding VMCS fields. + */ +struct vmcs_host_state { + unsigned long cr3; /* May not match real cr3 */ + unsigned long cr4; /* May not match real cr4 */ + unsigned long gs_base; + unsigned long fs_base; + + u16 fs_sel, gs_sel, ldt_sel; +#ifdef CONFIG_X86_64 + u16 ds_sel, es_sel; +#endif +}; + +/* * Track a VMCS that may be loaded on a certain CPU. If it is (cpu!=-1), also * remember whether it was VMLAUNCHed, and maintain a linked list of all VMCSs * loaded on this CPU (so we can clear them if the CPU goes down). @@ -215,14 +391,13 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; - unsigned long vmcs_host_cr3; /* May not match real cr3 */ - unsigned long vmcs_host_cr4; /* May not match real cr4 */ /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; ktime_t entry_time; s64 vnmi_blocked_time; unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; + struct vmcs_host_state host_state; }; struct shared_msr_entry { @@ -253,7 +428,7 @@ struct __packed vmcs12 { /* According to the Intel spec, a VMCS region must start with the * following two fields. Then follow implementation-specific data. */ - u32 revision_id; + struct vmcs_hdr hdr; u32 abort; u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */ @@ -421,7 +596,7 @@ struct __packed vmcs12 { "Offset of " #field " in struct vmcs12 has changed.") static inline void vmx_check_vmcs12_offsets(void) { - CHECK_OFFSET(revision_id, 0); + CHECK_OFFSET(hdr, 0); CHECK_OFFSET(abort, 4); CHECK_OFFSET(launch_state, 8); CHECK_OFFSET(io_bitmap_a, 40); @@ -640,6 +815,12 @@ struct nested_vmx { */ struct vmcs12 *cached_vmcs12; /* + * Cache of the guest's shadow VMCS, existing outside of guest + * memory. Loaded from guest memory during VM entry. Flushed + * to guest memory during VM exit. + */ + struct vmcs12 *cached_shadow_vmcs12; + /* * Indicates if the shadow vmcs must be updated with the * data hold by vmcs12 */ @@ -757,6 +938,11 @@ static inline int pi_test_sn(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } +struct vmx_msrs { + unsigned int nr; + struct vmx_msr_entry val[NR_AUTOLOAD_MSRS]; +}; + struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; @@ -784,26 +970,20 @@ struct vcpu_vmx { /* * loaded_vmcs points to the VMCS currently used in this vcpu. For a * non-nested (L1) guest, it always points to vmcs01. For a nested - * guest (L2), it points to a different VMCS. + * guest (L2), it points to a different VMCS. loaded_cpu_state points + * to the VMCS whose state is loaded into the CPU registers that only + * need to be switched when transitioning to/from the kernel; a NULL + * value indicates that host state is loaded. */ struct loaded_vmcs vmcs01; struct loaded_vmcs *loaded_vmcs; + struct loaded_vmcs *loaded_cpu_state; bool __launched; /* temporary, used in vmx_vcpu_run */ struct msr_autoload { - unsigned nr; - struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS]; - struct vmx_msr_entry host[NR_AUTOLOAD_MSRS]; + struct vmx_msrs guest; + struct vmx_msrs host; } msr_autoload; - struct { - int loaded; - u16 fs_sel, gs_sel, ldt_sel; -#ifdef CONFIG_X86_64 - u16 ds_sel, es_sel; -#endif - int gs_ldt_reload_needed; - int fs_reload_needed; - u64 msr_host_bndcfgs; - } host_state; + struct { int vm86_active; ulong save_rflags; @@ -853,6 +1033,7 @@ struct vcpu_vmx { */ u64 msr_ia32_feature_control; u64 msr_ia32_feature_control_valid_bits; + u64 ept_pointer; }; enum segment_cache_field { @@ -1072,6 +1253,11 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) return to_vmx(vcpu)->nested.cached_vmcs12; } +static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.cached_shadow_vmcs12; +} + static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu); static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu); static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa); @@ -1342,6 +1528,48 @@ static void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) * GUEST_IA32_RTIT_CTL = 0x00002814, */ } + +/* check_ept_pointer() should be under protection of ept_pointer_lock. */ +static void check_ept_pointer_match(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + u64 tmp_eptp = INVALID_PAGE; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!VALID_PAGE(tmp_eptp)) { + tmp_eptp = to_vmx(vcpu)->ept_pointer; + } else if (tmp_eptp != to_vmx(vcpu)->ept_pointer) { + to_kvm_vmx(kvm)->ept_pointers_match + = EPT_POINTERS_MISMATCH; + return; + } + } + + to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH; +} + +static int vmx_hv_remote_flush_tlb(struct kvm *kvm) +{ + int ret; + + spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); + + if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK) + check_ept_pointer_match(kvm); + + if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) { + ret = -ENOTSUPP; + goto out; + } + + ret = hyperv_flush_guest_mapping( + to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer); + +out: + spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); + return ret; +} #else /* !IS_ENABLED(CONFIG_HYPERV) */ static inline void evmcs_write64(unsigned long field, u64 value) {} static inline void evmcs_write32(unsigned long field, u32 value) {} @@ -1716,6 +1944,12 @@ static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu) CPU_BASED_MONITOR_TRAP_FLAG; } +static inline bool nested_cpu_has_vmx_shadow_vmcs(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.secondary_ctls_high & + SECONDARY_EXEC_SHADOW_VMCS; +} + static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit) { return vmcs12->cpu_based_vm_exec_control & bit; @@ -1796,6 +2030,11 @@ static inline bool nested_cpu_has_eptp_switching(struct vmcs12 *vmcs12) VMX_VMFUNC_EPTP_SWITCHING); } +static inline bool nested_cpu_has_shadow_vmcs(struct vmcs12 *vmcs12) +{ + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS); +} + static inline bool is_nmi(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) @@ -1826,11 +2065,12 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva) u64 rsvd : 48; u64 gva; } operand = { vpid, 0, gva }; + bool error; - asm volatile (__ex(ASM_VMX_INVVPID) - /* CF==1 or ZF==1 --> rc = -1 */ - "; ja 1f ; ud2 ; 1:" - : : "a"(&operand), "c"(ext) : "cc", "memory"); + asm volatile (__ex(ASM_VMX_INVVPID) CC_SET(na) + : CC_OUT(na) (error) : "a"(&operand), "c"(ext) + : "memory"); + BUG_ON(error); } static inline void __invept(int ext, u64 eptp, gpa_t gpa) @@ -1838,11 +2078,12 @@ static inline void __invept(int ext, u64 eptp, gpa_t gpa) struct { u64 eptp, gpa; } operand = {eptp, gpa}; + bool error; - asm volatile (__ex(ASM_VMX_INVEPT) - /* CF==1 or ZF==1 --> rc = -1 */ - "; ja 1f ; ud2 ; 1:\n" - : : "a" (&operand), "c" (ext) : "cc", "memory"); + asm volatile (__ex(ASM_VMX_INVEPT) CC_SET(na) + : CC_OUT(na) (error) : "a" (&operand), "c" (ext) + : "memory"); + BUG_ON(error); } static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) @@ -1858,12 +2099,12 @@ static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) static void vmcs_clear(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); - u8 error; + bool error; - asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) "; setna %0" - : "=qm"(error) : "a"(&phys_addr), "m"(phys_addr) - : "cc", "memory"); - if (error) + asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) CC_SET(na) + : CC_OUT(na) (error) : "a"(&phys_addr), "m"(phys_addr) + : "memory"); + if (unlikely(error)) printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n", vmcs, phys_addr); } @@ -1880,15 +2121,15 @@ static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) static void vmcs_load(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); - u8 error; + bool error; if (static_branch_unlikely(&enable_evmcs)) return evmcs_load(phys_addr); - asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0" - : "=qm"(error) : "a"(&phys_addr), "m"(phys_addr) - : "cc", "memory"); - if (error) + asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) CC_SET(na) + : CC_OUT(na) (error) : "a"(&phys_addr), "m"(phys_addr) + : "memory"); + if (unlikely(error)) printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n", vmcs, phys_addr); } @@ -1966,6 +2207,19 @@ static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) __loaded_vmcs_clear, loaded_vmcs, 1); } +static inline bool vpid_sync_vcpu_addr(int vpid, gva_t addr) +{ + if (vpid == 0) + return true; + + if (cpu_has_vmx_invvpid_individual_addr()) { + __invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR, vpid, addr); + return true; + } + + return false; +} + static inline void vpid_sync_vcpu_single(int vpid) { if (vpid == 0) @@ -2100,10 +2354,10 @@ static noinline void vmwrite_error(unsigned long field, unsigned long value) static __always_inline void __vmcs_writel(unsigned long field, unsigned long value) { - u8 error; + bool error; - asm volatile (__ex(ASM_VMX_VMWRITE_RAX_RDX) "; setna %0" - : "=q"(error) : "a"(value), "d"(field) : "cc"); + asm volatile (__ex(ASM_VMX_VMWRITE_RAX_RDX) CC_SET(na) + : CC_OUT(na) (error) : "a"(value), "d"(field)); if (unlikely(error)) vmwrite_error(field, value); } @@ -2377,9 +2631,20 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, vm_exit_controls_clearbit(vmx, exit); } +static int find_msr(struct vmx_msrs *m, unsigned int msr) +{ + unsigned int i; + + for (i = 0; i < m->nr; ++i) { + if (m->val[i].index == msr) + return i; + } + return -ENOENT; +} + static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) { - unsigned i; + int i; struct msr_autoload *m = &vmx->msr_autoload; switch (msr) { @@ -2400,18 +2665,21 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) } break; } + i = find_msr(&m->guest, msr); + if (i < 0) + goto skip_guest; + --m->guest.nr; + m->guest.val[i] = m->guest.val[m->guest.nr]; + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); - for (i = 0; i < m->nr; ++i) - if (m->guest[i].index == msr) - break; - - if (i == m->nr) +skip_guest: + i = find_msr(&m->host, msr); + if (i < 0) return; - --m->nr; - m->guest[i] = m->guest[m->nr]; - m->host[i] = m->host[m->nr]; - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); + + --m->host.nr; + m->host.val[i] = m->host.val[m->host.nr]; + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); } static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, @@ -2426,9 +2694,9 @@ static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, } static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, - u64 guest_val, u64 host_val) + u64 guest_val, u64 host_val, bool entry_only) { - unsigned i; + int i, j = 0; struct msr_autoload *m = &vmx->msr_autoload; switch (msr) { @@ -2463,24 +2731,31 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } - for (i = 0; i < m->nr; ++i) - if (m->guest[i].index == msr) - break; + i = find_msr(&m->guest, msr); + if (!entry_only) + j = find_msr(&m->host, msr); - if (i == NR_AUTOLOAD_MSRS) { + if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; - } else if (i == m->nr) { - ++m->nr; - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); } + if (i < 0) { + i = m->guest.nr++; + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); + } + m->guest.val[i].index = msr; + m->guest.val[i].value = guest_val; + + if (entry_only) + return; - m->guest[i].index = msr; - m->guest[i].value = guest_val; - m->host[i].index = msr; - m->host[i].value = host_val; + if (j < 0) { + j = m->host.nr++; + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); + } + m->host.val[j].index = msr; + m->host.val[j].value = host_val; } static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) @@ -2524,7 +2799,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, - guest_efer, host_efer); + guest_efer, host_efer, false); return false; } else { guest_efer &= ~ignore_bits; @@ -2566,121 +2841,150 @@ static unsigned long segment_base(u16 selector) } #endif -static void vmx_save_host_state(struct kvm_vcpu *vcpu) +static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs_host_state *host_state; #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); - unsigned long fs_base, kernel_gs_base; #endif + unsigned long fs_base, gs_base; + u16 fs_sel, gs_sel; int i; - if (vmx->host_state.loaded) + if (vmx->loaded_cpu_state) return; - vmx->host_state.loaded = 1; + vmx->loaded_cpu_state = vmx->loaded_vmcs; + host_state = &vmx->loaded_cpu_state->host_state; + /* * Set host fs and gs selectors. Unfortunately, 22.2.3 does not * allow segment selectors with cpl > 0 or ti == 1. */ - vmx->host_state.ldt_sel = kvm_read_ldt(); - vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel; + host_state->ldt_sel = kvm_read_ldt(); #ifdef CONFIG_X86_64 + savesegment(ds, host_state->ds_sel); + savesegment(es, host_state->es_sel); + + gs_base = cpu_kernelmode_gs_base(cpu); if (likely(is_64bit_mm(current->mm))) { save_fsgs_for_kvm(); - vmx->host_state.fs_sel = current->thread.fsindex; - vmx->host_state.gs_sel = current->thread.gsindex; + fs_sel = current->thread.fsindex; + gs_sel = current->thread.gsindex; fs_base = current->thread.fsbase; - kernel_gs_base = current->thread.gsbase; + vmx->msr_host_kernel_gs_base = current->thread.gsbase; } else { -#endif - savesegment(fs, vmx->host_state.fs_sel); - savesegment(gs, vmx->host_state.gs_sel); -#ifdef CONFIG_X86_64 + savesegment(fs, fs_sel); + savesegment(gs, gs_sel); fs_base = read_msr(MSR_FS_BASE); - kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); - } -#endif - if (!(vmx->host_state.fs_sel & 7)) { - vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel); - vmx->host_state.fs_reload_needed = 0; - } else { - vmcs_write16(HOST_FS_SELECTOR, 0); - vmx->host_state.fs_reload_needed = 1; - } - if (!(vmx->host_state.gs_sel & 7)) - vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel); - else { - vmcs_write16(HOST_GS_SELECTOR, 0); - vmx->host_state.gs_ldt_reload_needed = 1; + vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); } -#ifdef CONFIG_X86_64 - savesegment(ds, vmx->host_state.ds_sel); - savesegment(es, vmx->host_state.es_sel); - - vmcs_writel(HOST_FS_BASE, fs_base); - vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu)); - - vmx->msr_host_kernel_gs_base = kernel_gs_base; if (is_long_mode(&vmx->vcpu)) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else - vmcs_writel(HOST_FS_BASE, segment_base(vmx->host_state.fs_sel)); - vmcs_writel(HOST_GS_BASE, segment_base(vmx->host_state.gs_sel)); + savesegment(fs, fs_sel); + savesegment(gs, gs_sel); + fs_base = segment_base(fs_sel); + gs_base = segment_base(gs_sel); #endif - if (boot_cpu_has(X86_FEATURE_MPX)) - rdmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs); + + if (unlikely(fs_sel != host_state->fs_sel)) { + if (!(fs_sel & 7)) + vmcs_write16(HOST_FS_SELECTOR, fs_sel); + else + vmcs_write16(HOST_FS_SELECTOR, 0); + host_state->fs_sel = fs_sel; + } + if (unlikely(gs_sel != host_state->gs_sel)) { + if (!(gs_sel & 7)) + vmcs_write16(HOST_GS_SELECTOR, gs_sel); + else + vmcs_write16(HOST_GS_SELECTOR, 0); + host_state->gs_sel = gs_sel; + } + if (unlikely(fs_base != host_state->fs_base)) { + vmcs_writel(HOST_FS_BASE, fs_base); + host_state->fs_base = fs_base; + } + if (unlikely(gs_base != host_state->gs_base)) { + vmcs_writel(HOST_GS_BASE, gs_base); + host_state->gs_base = gs_base; + } + for (i = 0; i < vmx->save_nmsrs; ++i) kvm_set_shared_msr(vmx->guest_msrs[i].index, vmx->guest_msrs[i].data, vmx->guest_msrs[i].mask); } -static void __vmx_load_host_state(struct vcpu_vmx *vmx) +static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) { - if (!vmx->host_state.loaded) + struct vmcs_host_state *host_state; + + if (!vmx->loaded_cpu_state) return; + WARN_ON_ONCE(vmx->loaded_cpu_state != vmx->loaded_vmcs); + host_state = &vmx->loaded_cpu_state->host_state; + ++vmx->vcpu.stat.host_state_reload; - vmx->host_state.loaded = 0; + vmx->loaded_cpu_state = NULL; + #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif - if (vmx->host_state.gs_ldt_reload_needed) { - kvm_load_ldt(vmx->host_state.ldt_sel); + if (host_state->ldt_sel || (host_state->gs_sel & 7)) { + kvm_load_ldt(host_state->ldt_sel); #ifdef CONFIG_X86_64 - load_gs_index(vmx->host_state.gs_sel); + load_gs_index(host_state->gs_sel); #else - loadsegment(gs, vmx->host_state.gs_sel); + loadsegment(gs, host_state->gs_sel); #endif } - if (vmx->host_state.fs_reload_needed) - loadsegment(fs, vmx->host_state.fs_sel); + if (host_state->fs_sel & 7) + loadsegment(fs, host_state->fs_sel); #ifdef CONFIG_X86_64 - if (unlikely(vmx->host_state.ds_sel | vmx->host_state.es_sel)) { - loadsegment(ds, vmx->host_state.ds_sel); - loadsegment(es, vmx->host_state.es_sel); + if (unlikely(host_state->ds_sel | host_state->es_sel)) { + loadsegment(ds, host_state->ds_sel); + loadsegment(es, host_state->es_sel); } #endif invalidate_tss_limit(); #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif - if (vmx->host_state.msr_host_bndcfgs) - wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs); load_fixmap_gdt(raw_smp_processor_id()); } -static void vmx_load_host_state(struct vcpu_vmx *vmx) +#ifdef CONFIG_X86_64 +static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) { - preempt_disable(); - __vmx_load_host_state(vmx); - preempt_enable(); + if (is_long_mode(&vmx->vcpu)) { + preempt_disable(); + if (vmx->loaded_cpu_state) + rdmsrl(MSR_KERNEL_GS_BASE, + vmx->msr_guest_kernel_gs_base); + preempt_enable(); + } + return vmx->msr_guest_kernel_gs_base; } +static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) +{ + if (is_long_mode(&vmx->vcpu)) { + preempt_disable(); + if (vmx->loaded_cpu_state) + wrmsrl(MSR_KERNEL_GS_BASE, data); + preempt_enable(); + } + vmx->msr_guest_kernel_gs_base = data; +} +#endif + static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -2822,7 +3126,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { vmx_vcpu_pi_put(vcpu); - __vmx_load_host_state(to_vmx(vcpu)); + vmx_prepare_switch_to_host(to_vmx(vcpu)); } static bool emulation_required(struct kvm_vcpu *vcpu) @@ -3043,7 +3347,7 @@ static bool vmx_rdtscp_supported(void) static bool vmx_invpcid_supported(void) { - return cpu_has_vmx_invpcid() && enable_ept; + return cpu_has_vmx_invpcid(); } /* @@ -3286,6 +3590,12 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING; + /* + * We can emulate "VMCS shadowing," even if the hardware + * doesn't support it. + */ + msrs->secondary_ctls_high |= + SECONDARY_EXEC_SHADOW_VMCS; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ @@ -3753,8 +4063,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: - vmx_load_host_state(vmx); - msr_info->data = vmx->msr_guest_kernel_gs_base; + msr_info->data = vmx_read_guest_kernel_gs_base(vmx); break; #endif case MSR_EFER: @@ -3854,8 +4163,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_GS_BASE, data); break; case MSR_KERNEL_GS_BASE: - vmx_load_host_state(vmx); - vmx->msr_guest_kernel_gs_base = data; + vmx_write_guest_kernel_gs_base(vmx, data); break; #endif case MSR_IA32_SYSENTER_CS: @@ -3987,7 +4295,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.ia32_xss = data; if (vcpu->arch.ia32_xss != host_xss) add_atomic_switch_msr(vmx, MSR_IA32_XSS, - vcpu->arch.ia32_xss, host_xss); + vcpu->arch.ia32_xss, host_xss, false); else clear_atomic_switch_msr(vmx, MSR_IA32_XSS); break; @@ -4390,7 +4698,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) return 0; } -static struct vmcs *alloc_vmcs_cpu(int cpu) +static struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu) { int node = cpu_to_node(cpu); struct page *pages; @@ -4404,10 +4712,12 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) /* KVM supports Enlightened VMCS v1 only */ if (static_branch_unlikely(&enable_evmcs)) - vmcs->revision_id = KVM_EVMCS_VERSION; + vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else - vmcs->revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmcs_config.revision_id; + if (shadow) + vmcs->hdr.shadow_vmcs = 1; return vmcs; } @@ -4431,14 +4741,14 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } -static struct vmcs *alloc_vmcs(void) +static struct vmcs *alloc_vmcs(bool shadow) { - return alloc_vmcs_cpu(raw_smp_processor_id()); + return alloc_vmcs_cpu(shadow, raw_smp_processor_id()); } static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) { - loaded_vmcs->vmcs = alloc_vmcs(); + loaded_vmcs->vmcs = alloc_vmcs(false); if (!loaded_vmcs->vmcs) return -ENOMEM; @@ -4460,6 +4770,9 @@ static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) evmcs->hv_enlightenments_control.msr_bitmap = 1; } } + + memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); + return 0; out_vmcs: @@ -4569,7 +4882,7 @@ static __init int alloc_kvm_area(void) for_each_possible_cpu(cpu) { struct vmcs *vmcs; - vmcs = alloc_vmcs_cpu(cpu); + vmcs = alloc_vmcs_cpu(false, cpu); if (!vmcs) { free_kvm_area(); return -ENOMEM; @@ -4586,7 +4899,7 @@ static __init int alloc_kvm_area(void) * physical CPU. */ if (static_branch_unlikely(&enable_evmcs)) - vmcs->revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmcs_config.revision_id; per_cpu(vmxarea, cpu) = vmcs; } @@ -4743,10 +5056,18 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) return; /* - * Force kernel_gs_base reloading before EFER changes, as control - * of this msr depends on is_long_mode(). + * MSR_KERNEL_GS_BASE is not intercepted when the guest is in + * 64-bit mode as a 64-bit kernel may frequently access the + * MSR. This means we need to manually save/restore the MSR + * when switching between guest and host state, but only if + * the guest is in 64-bit mode. Sync our cached value if the + * guest is transitioning to 32-bit mode and the CPU contains + * guest state, i.e. the cache is stale. */ - vmx_load_host_state(to_vmx(vcpu)); +#ifdef CONFIG_X86_64 + if (!(efer & EFER_LMA)) + (void)vmx_read_guest_kernel_gs_base(vmx); +#endif vcpu->arch.efer = efer; if (efer & EFER_LMA) { vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); @@ -4803,6 +5124,20 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa); } +static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +{ + int vpid = to_vmx(vcpu)->vpid; + + if (!vpid_sync_vcpu_addr(vpid, addr)) + vpid_sync_context(vpid); + + /* + * If VPIDs are not supported or enabled, then the above is a no-op. + * But we don't really need a TLB flush in that case anyway, because + * each VM entry/exit includes an implicit flush when VPID is 0. + */ +} + static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; @@ -4984,6 +5319,7 @@ static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { + struct kvm *kvm = vcpu->kvm; unsigned long guest_cr3; u64 eptp; @@ -4991,15 +5327,23 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (enable_ept) { eptp = construct_eptp(vcpu, cr3); vmcs_write64(EPT_POINTER, eptp); + + if (kvm_x86_ops->tlb_remote_flush) { + spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); + to_vmx(vcpu)->ept_pointer = eptp; + to_kvm_vmx(kvm)->ept_pointers_match + = EPT_POINTERS_CHECK; + spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); + } + if (enable_unrestricted_guest || is_paging(vcpu) || is_guest_mode(vcpu)) guest_cr3 = kvm_read_cr3(vcpu); else - guest_cr3 = to_kvm_vmx(vcpu->kvm)->ept_identity_map_addr; + guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; ept_load_pdptrs(vcpu); } - vmx_flush_tlb(vcpu, true); vmcs_writel(GUEST_CR3, guest_cr3); } @@ -5935,19 +6279,19 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->loaded_vmcs->vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->host_state.cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->loaded_vmcs->vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->host_state.cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 /* * Load null selectors, so we can avoid reloading them in - * __vmx_load_host_state(), in case userspace uses the null selectors - * too (the expected case). + * vmx_prepare_switch_to_host(), in case userspace uses + * the null selectors too (the expected case). */ vmcs_write16(HOST_DS_SELECTOR, 0); vmcs_write16(HOST_ES_SELECTOR, 0); @@ -6072,8 +6416,6 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; enable_unrestricted_guest = 0; - /* Enable INVPCID for non-ept guests may cause performance regression. */ - exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; @@ -6202,9 +6544,6 @@ static void ept_set_mmio_spte_mask(void) */ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) { -#ifdef CONFIG_X86_64 - unsigned long a; -#endif int i; if (enable_shadow_vmcs) { @@ -6259,24 +6598,17 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */ vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */ vmx_set_constant_host_state(vmx); -#ifdef CONFIG_X86_64 - rdmsrl(MSR_FS_BASE, a); - vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */ - rdmsrl(MSR_GS_BASE, a); - vmcs_writel(HOST_GS_BASE, a); /* 22.2.4 */ -#else vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */ vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */ -#endif if (cpu_has_vmx_vmfunc()) vmcs_write64(VM_FUNCTION_CONTROL, 0); vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); - vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); + vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); - vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); + vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); @@ -6296,8 +6628,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); + vmx->arch_capabilities = kvm_get_arch_capabilities(); vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); @@ -7502,6 +7833,7 @@ static void vmx_enable_tdp(void) static __init int hardware_setup(void) { + unsigned long host_bndcfgs; int r = -ENOMEM, i; rdmsrl_safe(MSR_EFER, &host_efer); @@ -7526,6 +7858,11 @@ static __init int hardware_setup(void) if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); + if (boot_cpu_has(X86_FEATURE_MPX)) { + rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs); + WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); + } + if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; @@ -7562,6 +7899,12 @@ static __init int hardware_setup(void) if (enable_ept && !cpu_has_vmx_ept_2m_page()) kvm_disable_largepages(); +#if IS_ENABLED(CONFIG_HYPERV) + if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH + && enable_ept) + kvm_x86_ops->tlb_remote_flush = vmx_hv_remote_flush_tlb; +#endif + if (!cpu_has_vmx_ple()) { ple_gap = 0; ple_window = 0; @@ -7588,6 +7931,11 @@ static __init int hardware_setup(void) else kvm_disable_tdp(); + if (!nested) { + kvm_x86_ops->get_nested_state = NULL; + kvm_x86_ops->set_nested_state = NULL; + } + /* * Only enable PML when hardware supports PML feature, and both EPT * and EPT A/D bit features are enabled -- PML depends on them to work. @@ -7864,10 +8212,35 @@ static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) return 0; } +/* + * Allocate a shadow VMCS and associate it with the currently loaded + * VMCS, unless such a shadow VMCS already exists. The newly allocated + * VMCS is also VMCLEARed, so that it is ready for use. + */ +static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs; + + /* + * We should allocate a shadow vmcs for vmcs01 only when L1 + * executes VMXON and free it when L1 executes VMXOFF. + * As it is invalid to execute VMXON twice, we shouldn't reach + * here when vmcs01 already have an allocated shadow vmcs. + */ + WARN_ON(loaded_vmcs == &vmx->vmcs01 && loaded_vmcs->shadow_vmcs); + + if (!loaded_vmcs->shadow_vmcs) { + loaded_vmcs->shadow_vmcs = alloc_vmcs(true); + if (loaded_vmcs->shadow_vmcs) + vmcs_clear(loaded_vmcs->shadow_vmcs); + } + return loaded_vmcs->shadow_vmcs; +} + static int enter_vmx_operation(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct vmcs *shadow_vmcs; int r; r = alloc_loaded_vmcs(&vmx->nested.vmcs02); @@ -7878,25 +8251,26 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; - if (enable_shadow_vmcs) { - shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) - goto out_shadow_vmcs; - /* mark vmcs as shadow */ - shadow_vmcs->revision_id |= (1u << 31); - /* init shadow vmcs */ - vmcs_clear(shadow_vmcs); - vmx->vmcs01.shadow_vmcs = shadow_vmcs; - } + vmx->nested.cached_shadow_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); + if (!vmx->nested.cached_shadow_vmcs12) + goto out_cached_shadow_vmcs12; + + if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu)) + goto out_shadow_vmcs; hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + vmx->nested.vpid02 = allocate_vpid(); + vmx->nested.vmxon = true; return 0; out_shadow_vmcs: + kfree(vmx->nested.cached_shadow_vmcs12); + +out_cached_shadow_vmcs12: kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: @@ -7939,7 +8313,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) /* CPL=0 must be checked manually. */ if (vmx_get_cpl(vcpu)) { - kvm_queue_exception(vcpu, UD_VECTOR); + kvm_inject_gp(vcpu, 0); return 1; } @@ -8002,15 +8376,16 @@ static int handle_vmon(struct kvm_vcpu *vcpu) */ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) { - if (vmx_get_cpl(vcpu)) { + if (!to_vmx(vcpu)->nested.vmxon) { kvm_queue_exception(vcpu, UD_VECTOR); return 0; } - if (!to_vmx(vcpu)->nested.vmxon) { - kvm_queue_exception(vcpu, UD_VECTOR); + if (vmx_get_cpl(vcpu)) { + kvm_inject_gp(vcpu, 0); return 0; } + return 1; } @@ -8063,6 +8438,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); + kfree(vmx->nested.cached_shadow_vmcs12); /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); @@ -8148,7 +8524,7 @@ static int handle_vmresume(struct kvm_vcpu *vcpu) * some of the bits we return here (e.g., on 32-bit guests, only 32 bits of * 64-bit fields are to be returned). */ -static inline int vmcs12_read_any(struct kvm_vcpu *vcpu, +static inline int vmcs12_read_any(struct vmcs12 *vmcs12, unsigned long field, u64 *ret) { short offset = vmcs_field_to_offset(field); @@ -8157,7 +8533,7 @@ static inline int vmcs12_read_any(struct kvm_vcpu *vcpu, if (offset < 0) return offset; - p = ((char *)(get_vmcs12(vcpu))) + offset; + p = (char *)vmcs12 + offset; switch (vmcs_field_width(field)) { case VMCS_FIELD_WIDTH_NATURAL_WIDTH: @@ -8179,10 +8555,10 @@ static inline int vmcs12_read_any(struct kvm_vcpu *vcpu, } -static inline int vmcs12_write_any(struct kvm_vcpu *vcpu, +static inline int vmcs12_write_any(struct vmcs12 *vmcs12, unsigned long field, u64 field_value){ short offset = vmcs_field_to_offset(field); - char *p = ((char *) get_vmcs12(vcpu)) + offset; + char *p = (char *)vmcs12 + offset; if (offset < 0) return offset; @@ -8235,7 +8611,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) for (i = 0; i < max_fields[q]; i++) { field = fields[q][i]; field_value = __vmcs_readl(field); - vmcs12_write_any(&vmx->vcpu, field, field_value); + vmcs12_write_any(get_vmcs12(&vmx->vcpu), field, field_value); } /* * Skip the VM-exit information fields if they are read-only. @@ -8270,7 +8646,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) for (q = 0; q < ARRAY_SIZE(fields); q++) { for (i = 0; i < max_fields[q]; i++) { field = fields[q][i]; - vmcs12_read_any(&vmx->vcpu, field, &field_value); + vmcs12_read_any(get_vmcs12(&vmx->vcpu), field, &field_value); __vmcs_writel(field, field_value); } } @@ -8300,6 +8676,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); gva_t gva = 0; + struct vmcs12 *vmcs12; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -8307,10 +8684,24 @@ static int handle_vmread(struct kvm_vcpu *vcpu) if (!nested_vmx_check_vmcs12(vcpu)) return kvm_skip_emulated_instruction(vcpu); + if (!is_guest_mode(vcpu)) + vmcs12 = get_vmcs12(vcpu); + else { + /* + * When vmcs->vmcs_link_pointer is -1ull, any VMREAD + * to shadowed-field sets the ALU flags for VMfailInvalid. + */ + if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) { + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + vmcs12 = get_shadow_vmcs12(vcpu); + } + /* Decode instruction info and find the field to read */ field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); /* Read the field, zero-extended to a u64 field_value */ - if (vmcs12_read_any(vcpu, field, &field_value) < 0) { + if (vmcs12_read_any(vmcs12, field, &field_value) < 0) { nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); return kvm_skip_emulated_instruction(vcpu); } @@ -8352,6 +8743,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) */ u64 field_value = 0; struct x86_exception e; + struct vmcs12 *vmcs12; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -8386,23 +8778,44 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } - if (vmcs12_write_any(vcpu, field, field_value) < 0) { + if (!is_guest_mode(vcpu)) + vmcs12 = get_vmcs12(vcpu); + else { + /* + * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE + * to shadowed-field sets the ALU flags for VMfailInvalid. + */ + if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) { + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + vmcs12 = get_shadow_vmcs12(vcpu); + + } + + if (vmcs12_write_any(vmcs12, field, field_value) < 0) { nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); return kvm_skip_emulated_instruction(vcpu); } - switch (field) { + /* + * Do not track vmcs12 dirty-state if in guest-mode + * as we actually dirty shadow vmcs12 instead of vmcs12. + */ + if (!is_guest_mode(vcpu)) { + switch (field) { #define SHADOW_FIELD_RW(x) case x: #include "vmx_shadow_fields.h" - /* - * The fields that can be updated by L1 without a vmexit are - * always updated in the vmcs02, the others go down the slow - * path of prepare_vmcs02. - */ - break; - default: - vmx->nested.dirty_vmcs12 = true; - break; + /* + * The fields that can be updated by L1 without a vmexit are + * always updated in the vmcs02, the others go down the slow + * path of prepare_vmcs02. + */ + break; + default: + vmx->nested.dirty_vmcs12 = true; + break; + } } nested_vmx_succeed(vcpu); @@ -8453,7 +8866,9 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } new_vmcs12 = kmap(page); - if (new_vmcs12->revision_id != VMCS12_REVISION) { + if (new_vmcs12->hdr.revision_id != VMCS12_REVISION || + (new_vmcs12->hdr.shadow_vmcs && + !nested_cpu_has_vmx_shadow_vmcs(vcpu))) { kunmap(page); kvm_release_page_clean(page); nested_vmx_failValid(vcpu, @@ -8480,21 +8895,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) /* Emulate the VMPTRST instruction */ static int handle_vmptrst(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - gva_t vmcs_gva; + unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION); + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr; struct x86_exception e; + gva_t gva; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, &vmcs_gva)) + if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva)) return 1; /* *_system ok, nested_vmx_check_permission has verified cpl=0 */ - if (kvm_write_guest_virt_system(vcpu, vmcs_gva, - (void *)&to_vmx(vcpu)->nested.current_vmptr, - sizeof(u64), &e)) { + if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr, + sizeof(gpa_t), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } @@ -8652,6 +9066,105 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } +static int handle_invpcid(struct kvm_vcpu *vcpu) +{ + u32 vmx_instruction_info; + unsigned long type; + bool pcid_enabled; + gva_t gva; + struct x86_exception e; + unsigned i; + unsigned long roots_to_free = 0; + struct { + u64 pcid; + u64 gla; + } operand; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); + + if (type > 3) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + /* According to the Intel instruction reference, the memory operand + * is read even if it isn't needed (e.g., for type==all) + */ + if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + vmx_instruction_info, false, &gva)) + return 1; + + if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } + + if (operand.pcid >> 12 != 0) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); + + switch (type) { + case INVPCID_TYPE_INDIV_ADDR: + if ((!pcid_enabled && (operand.pcid != 0)) || + is_noncanonical_address(operand.gla, vcpu)) { + kvm_inject_gp(vcpu, 0); + return 1; + } + kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid); + return kvm_skip_emulated_instruction(vcpu); + + case INVPCID_TYPE_SINGLE_CTXT: + if (!pcid_enabled && (operand.pcid != 0)) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + if (kvm_get_active_pcid(vcpu) == operand.pcid) { + kvm_mmu_sync_roots(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + } + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (kvm_get_pcid(vcpu, vcpu->arch.mmu.prev_roots[i].cr3) + == operand.pcid) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + + kvm_mmu_free_roots(vcpu, roots_to_free); + /* + * If neither the current cr3 nor any of the prev_roots use the + * given PCID, then nothing needs to be done here because a + * resync will happen anyway before switching to any other CR3. + */ + + return kvm_skip_emulated_instruction(vcpu); + + case INVPCID_TYPE_ALL_NON_GLOBAL: + /* + * Currently, KVM doesn't mark global entries in the shadow + * page tables, so a non-global flush just degenerates to a + * global flush. If needed, we could optimize this later by + * keeping track of global entries in shadow page tables. + */ + + /* fall-through */ + case INVPCID_TYPE_ALL_INCL_GLOBAL: + kvm_mmu_unload(vcpu); + return kvm_skip_emulated_instruction(vcpu); + + default: + BUG(); /* We have already checked above that type <= 3 */ + } +} + static int handle_pml_full(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; @@ -8855,6 +9368,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_XSAVES] = handle_xsaves, [EXIT_REASON_XRSTORS] = handle_xrstors, [EXIT_REASON_PML_FULL] = handle_pml_full, + [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmfunc, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, }; @@ -9027,6 +9541,30 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, return false; } +static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12, gpa_t bitmap) +{ + u32 vmx_instruction_info; + unsigned long field; + u8 b; + + if (!nested_cpu_has_shadow_vmcs(vmcs12)) + return true; + + /* Decode instruction info and find the field to access */ + vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); + + /* Out-of-range fields always cause a VM exit from L2 to L1 */ + if (field >> 15) + return true; + + if (kvm_vcpu_read_guest(vcpu, bitmap + field/8, &b, 1)) + return true; + + return 1 & (b >> (field & 7)); +} + /* * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we * should handle it ourselves in L0 (and then continue L2). Only call this @@ -9111,10 +9649,15 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDSEED_EXITING); case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP: return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING); + case EXIT_REASON_VMREAD: + return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12, + vmcs12->vmread_bitmap); + case EXIT_REASON_VMWRITE: + return nested_vmx_exit_handled_vmcs_access(vcpu, vmcs12, + vmcs12->vmwrite_bitmap); case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR: case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD: - case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD: - case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE: + case EXIT_REASON_VMPTRST: case EXIT_REASON_VMRESUME: case EXIT_REASON_VMOFF: case EXIT_REASON_VMON: case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID: /* @@ -9547,6 +10090,79 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } } +/* + * Software based L1D cache flush which is used when microcode providing + * the cache control MSR is not loaded. + * + * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to + * flush it is required to read in 64 KiB because the replacement algorithm + * is not exactly LRU. This could be sized at runtime via topology + * information but as all relevant affected CPUs have 32KiB L1D cache size + * there is no point in doing so. + */ +#define L1D_CACHE_ORDER 4 +static void *vmx_l1d_flush_pages; + +static void vmx_l1d_flush(struct kvm_vcpu *vcpu) +{ + int size = PAGE_SIZE << L1D_CACHE_ORDER; + + /* + * This code is only executed when the the flush mode is 'cond' or + * 'always' + */ + if (static_branch_likely(&vmx_l1d_flush_cond)) { + bool flush_l1d; + + /* + * Clear the per-vcpu flush bit, it gets set again + * either from vcpu_run() or from one of the unsafe + * VMEXIT handlers. + */ + flush_l1d = vcpu->arch.l1tf_flush_l1d; + vcpu->arch.l1tf_flush_l1d = false; + + /* + * Clear the per-cpu flush bit, it gets set again from + * the interrupt handlers. + */ + flush_l1d |= kvm_get_cpu_l1tf_flush_l1d(); + kvm_clear_cpu_l1tf_flush_l1d(); + + if (!flush_l1d) + return; + } + + vcpu->stat.l1d_flush++; + + if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { + wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + return; + } + + asm volatile( + /* First ensure the pages are in the TLB */ + "xorl %%eax, %%eax\n" + ".Lpopulate_tlb:\n\t" + "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" + "addl $4096, %%eax\n\t" + "cmpl %%eax, %[size]\n\t" + "jne .Lpopulate_tlb\n\t" + "xorl %%eax, %%eax\n\t" + "cpuid\n\t" + /* Now fill the cache */ + "xorl %%eax, %%eax\n" + ".Lfill_cache:\n" + "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" + "addl $64, %%eax\n\t" + "cmpl %%eax, %[size]\n\t" + "jne .Lfill_cache\n\t" + "lfence\n" + :: [flush_pages] "r" (vmx_l1d_flush_pages), + [size] "r" (size) + : "eax", "ebx", "ecx", "edx"); +} + static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -9948,7 +10564,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) clear_atomic_switch_msr(vmx, msrs[i].msr); else add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest, - msrs[i].host); + msrs[i].host, false); } static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) @@ -10002,15 +10618,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) { + if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->host_state.cr3 = cr3; } cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) { + if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); - vmx->loaded_vmcs->vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->host_state.cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the @@ -10043,6 +10659,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) evmcs_rsp = static_branch_unlikely(&enable_evmcs) ? (unsigned long)¤t_evmcs->host_rsp : 0; + if (static_branch_unlikely(&vmx_l1d_should_flush)) + vmx_l1d_flush(vcpu); + asm( /* Store host registers */ "push %%" _ASM_DX "; push %%" _ASM_BP ";" @@ -10203,9 +10822,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * The sysexit path does not restore ds/es, so we must set them to * a reasonable value ourselves. * - * We can't defer this to vmx_load_host_state() since that function - * may be executed in interrupt context, which saves and restore segments - * around it, nullifying its effect. + * We can't defer this to vmx_prepare_switch_to_host() since that + * function may be executed in interrupt context, which saves and + * restore segments around it, nullifying its effect. */ loadsegment(ds, __USER_DS); loadsegment(es, __USER_DS); @@ -10266,8 +10885,8 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) return; cpu = get_cpu(); - vmx->loaded_vmcs = vmcs; vmx_vcpu_put(vcpu); + vmx->loaded_vmcs = vmcs; vmx_vcpu_load(vcpu, cpu); put_cpu(); } @@ -10370,11 +10989,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vmcs; } - if (nested) { + if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, kvm_vcpu_apicv_active(&vmx->vcpu)); - vmx->nested.vpid02 = allocate_vpid(); - } vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -10391,7 +11008,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return &vmx->vcpu; free_vmcs: - free_vpid(vmx->nested.vpid02); free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); @@ -10405,10 +11021,39 @@ free_vcpu: return ERR_PTR(err); } +#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n" +#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n" + static int vmx_vm_init(struct kvm *kvm) { + spin_lock_init(&to_kvm_vmx(kvm)->ept_pointer_lock); + if (!ple_gap) kvm->arch.pause_in_guest = true; + + if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) { + switch (l1tf_mitigation) { + case L1TF_MITIGATION_OFF: + case L1TF_MITIGATION_FLUSH_NOWARN: + /* 'I explicitly don't care' is set */ + break; + case L1TF_MITIGATION_FLUSH: + case L1TF_MITIGATION_FLUSH_NOSMT: + case L1TF_MITIGATION_FULL: + /* + * Warn upon starting the first VM in a potentially + * insecure environment. + */ + if (cpu_smt_control == CPU_SMT_ENABLED) + pr_warn_once(L1TF_MSG_SMT); + if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) + pr_warn_once(L1TF_MSG_L1D); + break; + case L1TF_MITIGATION_FULL_FORCE: + /* Flush is enforced */ + break; + } + } return 0; } @@ -10607,11 +11252,11 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) if (!valid_ept_address(vcpu, nested_ept_get_cr3(vcpu))) return 1; - kvm_mmu_unload(vcpu); kvm_init_shadow_ept_mmu(vcpu, to_vmx(vcpu)->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT, - nested_ept_ad_enabled(vcpu)); + nested_ept_ad_enabled(vcpu), + nested_ept_get_cr3(vcpu)); vcpu->arch.mmu.set_cr3 = vmx_set_cr3; vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3; vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault; @@ -10659,9 +11304,9 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); -static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); struct page *page; u64 hpa; @@ -10902,6 +11547,38 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, return true; } +static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + struct vmcs12 *shadow; + struct page *page; + + if (!nested_cpu_has_shadow_vmcs(vmcs12) || + vmcs12->vmcs_link_pointer == -1ull) + return; + + shadow = get_shadow_vmcs12(vcpu); + page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->vmcs_link_pointer); + + memcpy(shadow, kmap(page), VMCS12_SIZE); + + kunmap(page); + kvm_release_page_clean(page); +} + +static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!nested_cpu_has_shadow_vmcs(vmcs12) || + vmcs12->vmcs_link_pointer == -1ull) + return; + + kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer, + get_shadow_vmcs12(vcpu), VMCS12_SIZE); +} + static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -10959,11 +11636,12 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, unsigned long count_field, unsigned long addr_field) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); int maxphyaddr; u64 count, addr; - if (vmcs12_read_any(vcpu, count_field, &count) || - vmcs12_read_any(vcpu, addr_field, &addr)) { + if (vmcs12_read_any(vmcs12, count_field, &count) || + vmcs12_read_any(vmcs12, addr_field, &addr)) { WARN_ON(1); return -EINVAL; } @@ -11013,6 +11691,19 @@ static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu, return 0; } +static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + if (!nested_cpu_has_shadow_vmcs(vmcs12)) + return 0; + + if (!page_address_valid(vcpu, vmcs12->vmread_bitmap) || + !page_address_valid(vcpu, vmcs12->vmwrite_bitmap)) + return -EINVAL; + + return 0; +} + static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { @@ -11162,12 +11853,16 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne return 1; } } - - vcpu->arch.cr3 = cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); } - kvm_mmu_reset_context(vcpu); + if (!nested_ept) + kvm_mmu_new_cr3(vcpu, cr3, false); + + vcpu->arch.cr3 = cr3; + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + + kvm_init_mmu(vcpu, false); + return 0; } @@ -11254,7 +11949,8 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * Set host-state according to L0's settings (vmcs12 is irrelevant here) * Some constant fields are set here by vmx_set_constant_host_state(). * Other fields are different per CPU, and will be set later when - * vmx_vcpu_load() is called, and when vmx_save_host_state() is called. + * vmx_vcpu_load() is called, and when vmx_prepare_switch_to_guest() + * is called. */ vmx_set_constant_host_state(vmx); @@ -11262,10 +11958,10 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * Set the MSR load/store lists to match L0's settings. */ vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); + vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); + vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); set_cr4_guest_host_mask(vmx); @@ -11326,11 +12022,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base); vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base); - /* - * Not in vmcs02: GUEST_PML_INDEX, HOST_FS_SELECTOR, HOST_GS_SELECTOR, - * HOST_FS_BASE, HOST_GS_BASE. - */ - if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); @@ -11395,6 +12086,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control |= vmcs12_exec_ctrl; } + /* VMCS shadowing for L2 is emulated for now */ + exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; + if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) vmcs_write16(GUEST_INTR_STATUS, vmcs12->guest_intr_status); @@ -11614,6 +12308,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (nested_vmx_check_pml_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_shadow_vmcs_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control, vmx->nested.msrs.procbased_ctls_low, vmx->nested.msrs.procbased_ctls_high) || @@ -11714,6 +12411,33 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) return 0; } +static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + int r; + struct page *page; + struct vmcs12 *shadow; + + if (vmcs12->vmcs_link_pointer == -1ull) + return 0; + + if (!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)) + return -EINVAL; + + page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->vmcs_link_pointer); + if (is_error_page(page)) + return -EINVAL; + + r = 0; + shadow = kmap(page); + if (shadow->hdr.revision_id != VMCS12_REVISION || + shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)) + r = -EINVAL; + kunmap(page); + kvm_release_page_clean(page); + return r; +} + static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 *exit_qual) { @@ -11725,8 +12449,7 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) return 1; - if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS) && - vmcs12->vmcs_link_pointer != -1ull) { + if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) { *exit_qual = ENTRY_FAIL_VMCS_LINK_PTR; return 1; } @@ -11773,12 +12496,17 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, return 0; } -static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) +/* + * If exit_qual is NULL, this is being called from state restore (either RSM + * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. + */ +static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u32 exit_qual; - int r; + bool from_vmentry = !!exit_qual; + u32 dummy_exit_qual; + int r = 0; enter_guest_mode(vcpu); @@ -11792,17 +12520,28 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) vcpu->arch.tsc_offset += vmcs12->tsc_offset; r = EXIT_REASON_INVALID_STATE; - if (prepare_vmcs02(vcpu, vmcs12, &exit_qual)) + if (prepare_vmcs02(vcpu, vmcs12, from_vmentry ? exit_qual : &dummy_exit_qual)) goto fail; - nested_get_vmcs12_pages(vcpu, vmcs12); + if (from_vmentry) { + nested_get_vmcs12_pages(vcpu); - r = EXIT_REASON_MSR_LOAD_FAIL; - exit_qual = nested_vmx_load_msr(vcpu, - vmcs12->vm_entry_msr_load_addr, - vmcs12->vm_entry_msr_load_count); - if (exit_qual) - goto fail; + r = EXIT_REASON_MSR_LOAD_FAIL; + *exit_qual = nested_vmx_load_msr(vcpu, + vmcs12->vm_entry_msr_load_addr, + vmcs12->vm_entry_msr_load_count); + if (*exit_qual) + goto fail; + } else { + /* + * The MMU is not initialized to point at the right entities yet and + * "get pages" would need to read data from the guest (i.e. we will + * need to perform gpa to hpa translation). Request a call + * to nested_get_vmcs12_pages before the next VM-entry. The MSRs + * have already been set at vmentry time and should not be reset. + */ + kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu); + } /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point @@ -11817,8 +12556,7 @@ fail: vcpu->arch.tsc_offset -= vmcs12->tsc_offset; leave_guest_mode(vcpu); vmx_switch_vmcs(vcpu, &vmx->vmcs01); - nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual); - return 1; + return r; } /* @@ -11841,6 +12579,17 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmcs12 = get_vmcs12(vcpu); + /* + * Can't VMLAUNCH or VMRESUME a shadow VMCS. Despite the fact + * that there *is* a valid VMCS pointer, RFLAGS.CF is set + * rather than RFLAGS.ZF, and no error number is stored to the + * VM-instruction error field. + */ + if (vmcs12->hdr.shadow_vmcs) { + nested_vmx_failInvalid(vcpu); + goto out; + } + if (enable_shadow_vmcs) copy_shadow_to_vmcs12(vmx); @@ -11895,12 +12644,28 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) */ vmx->nested.nested_run_pending = 1; - ret = enter_vmx_non_root_mode(vcpu); + ret = enter_vmx_non_root_mode(vcpu, &exit_qual); if (ret) { + nested_vmx_entry_failure(vcpu, vmcs12, ret, exit_qual); vmx->nested.nested_run_pending = 0; - return ret; + return 1; } + /* Hide L1D cache contents from the nested guest. */ + vmx->vcpu.arch.l1tf_flush_l1d = true; + + /* + * Must happen outside of enter_vmx_non_root_mode() as it will + * also be used as part of restoring nVMX state for + * snapshot restore (migration). + * + * In this flow, it is assumed that vmcs12 cache was + * trasferred as part of captured nVMX state and should + * therefore not be read from guest memory (which may not + * exist on destination host yet). + */ + nested_cache_shadow_vmcs12(vcpu, vmcs12); + /* * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken * by event injection, halt vcpu. @@ -12410,6 +13175,17 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, exit_qualification); + /* + * Must happen outside of sync_vmcs12() as it will + * also be used to capture vmcs12 cache as part of + * capturing nVMX state for snapshot (migration). + * + * Otherwise, this flush will dirty guest memory at a + * point it is already assumed by user-space to be + * immutable. + */ + nested_flush_cached_shadow_vmcs12(vcpu, vmcs12); + if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr, vmcs12->vm_exit_msr_store_count)) nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); @@ -12421,8 +13197,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmx_segment_cache_clear(vmx); /* Update any VMCS fields that might have changed while L2 ran */ - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); if (vmx->hv_deadline_tsc == -1) vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, @@ -12984,7 +13760,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) if (vmx->nested.smm.guest_mode) { vcpu->arch.hflags &= ~HF_SMM_MASK; - ret = enter_vmx_non_root_mode(vcpu); + ret = enter_vmx_non_root_mode(vcpu, NULL); vcpu->arch.hflags |= HF_SMM_MASK; if (ret) return ret; @@ -12999,6 +13775,199 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static int vmx_get_nested_state(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + u32 user_data_size) +{ + struct vcpu_vmx *vmx; + struct vmcs12 *vmcs12; + struct kvm_nested_state kvm_state = { + .flags = 0, + .format = 0, + .size = sizeof(kvm_state), + .vmx.vmxon_pa = -1ull, + .vmx.vmcs_pa = -1ull, + }; + + if (!vcpu) + return kvm_state.size + 2 * VMCS12_SIZE; + + vmx = to_vmx(vcpu); + vmcs12 = get_vmcs12(vcpu); + if (nested_vmx_allowed(vcpu) && + (vmx->nested.vmxon || vmx->nested.smm.vmxon)) { + kvm_state.vmx.vmxon_pa = vmx->nested.vmxon_ptr; + kvm_state.vmx.vmcs_pa = vmx->nested.current_vmptr; + + if (vmx->nested.current_vmptr != -1ull) { + kvm_state.size += VMCS12_SIZE; + + if (is_guest_mode(vcpu) && + nested_cpu_has_shadow_vmcs(vmcs12) && + vmcs12->vmcs_link_pointer != -1ull) + kvm_state.size += VMCS12_SIZE; + } + + if (vmx->nested.smm.vmxon) + kvm_state.vmx.smm.flags |= KVM_STATE_NESTED_SMM_VMXON; + + if (vmx->nested.smm.guest_mode) + kvm_state.vmx.smm.flags |= KVM_STATE_NESTED_SMM_GUEST_MODE; + + if (is_guest_mode(vcpu)) { + kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE; + + if (vmx->nested.nested_run_pending) + kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; + } + } + + if (user_data_size < kvm_state.size) + goto out; + + if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state))) + return -EFAULT; + + if (vmx->nested.current_vmptr == -1ull) + goto out; + + /* + * When running L2, the authoritative vmcs12 state is in the + * vmcs02. When running L1, the authoritative vmcs12 state is + * in the shadow vmcs linked to vmcs01, unless + * sync_shadow_vmcs is set, in which case, the authoritative + * vmcs12 state is in the vmcs12 already. + */ + if (is_guest_mode(vcpu)) + sync_vmcs12(vcpu, vmcs12); + else if (enable_shadow_vmcs && !vmx->nested.sync_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + + if (copy_to_user(user_kvm_nested_state->data, vmcs12, sizeof(*vmcs12))) + return -EFAULT; + + if (nested_cpu_has_shadow_vmcs(vmcs12) && + vmcs12->vmcs_link_pointer != -1ull) { + if (copy_to_user(user_kvm_nested_state->data + VMCS12_SIZE, + get_shadow_vmcs12(vcpu), sizeof(*vmcs12))) + return -EFAULT; + } + +out: + return kvm_state.size; +} + +static int vmx_set_nested_state(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + struct kvm_nested_state *kvm_state) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs12 *vmcs12; + u32 exit_qual; + int ret; + + if (kvm_state->format != 0) + return -EINVAL; + + if (!nested_vmx_allowed(vcpu)) + return kvm_state->vmx.vmxon_pa == -1ull ? 0 : -EINVAL; + + if (kvm_state->vmx.vmxon_pa == -1ull) { + if (kvm_state->vmx.smm.flags) + return -EINVAL; + + if (kvm_state->vmx.vmcs_pa != -1ull) + return -EINVAL; + + vmx_leave_nested(vcpu); + return 0; + } + + if (!page_address_valid(vcpu, kvm_state->vmx.vmxon_pa)) + return -EINVAL; + + if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12)) + return -EINVAL; + + if (kvm_state->vmx.vmcs_pa == kvm_state->vmx.vmxon_pa || + !page_address_valid(vcpu, kvm_state->vmx.vmcs_pa)) + return -EINVAL; + + if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) && + (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) + return -EINVAL; + + if (kvm_state->vmx.smm.flags & + ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON)) + return -EINVAL; + + if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) && + !(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON)) + return -EINVAL; + + vmx_leave_nested(vcpu); + if (kvm_state->vmx.vmxon_pa == -1ull) + return 0; + + vmx->nested.vmxon_ptr = kvm_state->vmx.vmxon_pa; + ret = enter_vmx_operation(vcpu); + if (ret) + return ret; + + set_current_vmptr(vmx, kvm_state->vmx.vmcs_pa); + + if (kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) { + vmx->nested.smm.vmxon = true; + vmx->nested.vmxon = false; + + if (kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) + vmx->nested.smm.guest_mode = true; + } + + vmcs12 = get_vmcs12(vcpu); + if (copy_from_user(vmcs12, user_kvm_nested_state->data, sizeof(*vmcs12))) + return -EFAULT; + + if (vmcs12->hdr.revision_id != VMCS12_REVISION) + return -EINVAL; + + if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) + return 0; + + vmx->nested.nested_run_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + + if (nested_cpu_has_shadow_vmcs(vmcs12) && + vmcs12->vmcs_link_pointer != -1ull) { + struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); + if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12)) + return -EINVAL; + + if (copy_from_user(shadow_vmcs12, + user_kvm_nested_state->data + VMCS12_SIZE, + sizeof(*vmcs12))) + return -EFAULT; + + if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION || + !shadow_vmcs12->hdr.shadow_vmcs) + return -EINVAL; + } + + if (check_vmentry_prereqs(vcpu, vmcs12) || + check_vmentry_postreqs(vcpu, vmcs12, &exit_qual)) + return -EINVAL; + + if (kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING) + vmx->nested.nested_run_pending = 1; + + vmx->nested.dirty_vmcs12 = true; + ret = enter_vmx_non_root_mode(vcpu, NULL); + if (ret) + return -EINVAL; + + return 0; +} + static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -13018,7 +13987,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .vcpu_free = vmx_free_vcpu, .vcpu_reset = vmx_vcpu_reset, - .prepare_guest_switch = vmx_save_host_state, + .prepare_guest_switch = vmx_prepare_switch_to_guest, .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, @@ -13051,6 +14020,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .set_rflags = vmx_set_rflags, .tlb_flush = vmx_flush_tlb, + .tlb_flush_gva = vmx_flush_tlb_gva, .run = vmx_vcpu_run, .handle_exit = vmx_handle_exit, @@ -13133,12 +14103,61 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .setup_mce = vmx_setup_mce, + .get_nested_state = vmx_get_nested_state, + .set_nested_state = vmx_set_nested_state, + .get_vmcs12_pages = nested_get_vmcs12_pages, + .smi_allowed = vmx_smi_allowed, .pre_enter_smm = vmx_pre_enter_smm, .pre_leave_smm = vmx_pre_leave_smm, .enable_smi_window = enable_smi_window, }; +static void vmx_cleanup_l1d_flush(void) +{ + if (vmx_l1d_flush_pages) { + free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); + vmx_l1d_flush_pages = NULL; + } + /* Restore state so sysfs ignores VMX */ + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; +} + +static void vmx_exit(void) +{ +#ifdef CONFIG_KEXEC_CORE + RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); + synchronize_rcu(); +#endif + + kvm_exit(); + +#if IS_ENABLED(CONFIG_HYPERV) + if (static_branch_unlikely(&enable_evmcs)) { + int cpu; + struct hv_vp_assist_page *vp_ap; + /* + * Reset everything to support using non-enlightened VMCS + * access later (e.g. when we reload the module with + * enlightened_vmcs=0) + */ + for_each_online_cpu(cpu) { + vp_ap = hv_get_vp_assist_page(cpu); + + if (!vp_ap) + continue; + + vp_ap->current_nested_vmcs = 0; + vp_ap->enlighten_vmentry = 0; + } + + static_branch_disable(&enable_evmcs); + } +#endif + vmx_cleanup_l1d_flush(); +} +module_exit(vmx_exit); + static int __init vmx_init(void) { int r; @@ -13173,10 +14192,25 @@ static int __init vmx_init(void) #endif r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); + __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) return r; + /* + * Must be called after kvm_init() so enable_ept is properly set + * up. Hand the parameter mitigation value in which was stored in + * the pre module init parser. If no parameter was given, it will + * contain 'auto' which will be turned into the default 'cond' + * mitigation mode. + */ + if (boot_cpu_has(X86_BUG_L1TF)) { + r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); + if (r) { + vmx_exit(); + return r; + } + } + #ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); @@ -13185,39 +14219,4 @@ static int __init vmx_init(void) return 0; } - -static void __exit vmx_exit(void) -{ -#ifdef CONFIG_KEXEC_CORE - RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); - synchronize_rcu(); -#endif - - kvm_exit(); - -#if IS_ENABLED(CONFIG_HYPERV) - if (static_branch_unlikely(&enable_evmcs)) { - int cpu; - struct hv_vp_assist_page *vp_ap; - /* - * Reset everything to support using non-enlightened VMCS - * access later (e.g. when we reload the module with - * enlightened_vmcs=0) - */ - for_each_online_cpu(cpu) { - vp_ap = hv_get_vp_assist_page(cpu); - - if (!vp_ap) - continue; - - vp_ap->current_nested_vmcs = 0; - vp_ap->enlighten_vmentry = 0; - } - - static_branch_disable(&enable_evmcs); - } -#endif -} - -module_init(vmx_init) -module_exit(vmx_exit) +module_init(vmx_init); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2b812b3c5088..f7dff0457846 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -195,6 +195,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "irq_injections", VCPU_STAT(irq_injections) }, { "nmi_injections", VCPU_STAT(nmi_injections) }, { "req_event", VCPU_STAT(req_event) }, + { "l1d_flush", VCPU_STAT(l1d_flush) }, { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, { "mmu_pte_write", VM_STAT(mmu_pte_write) }, { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, @@ -847,16 +848,21 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { + bool skip_tlb_flush = false; #ifdef CONFIG_X86_64 bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); - if (pcid_enabled) - cr3 &= ~CR3_PCID_INVD; + if (pcid_enabled) { + skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; + cr3 &= ~X86_CR3_PCID_NOFLUSH; + } #endif if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + if (!skip_tlb_flush) { + kvm_mmu_sync_roots(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + } return 0; } @@ -867,9 +873,10 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) return 1; + kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush); vcpu->arch.cr3 = cr3; __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); - kvm_mmu_new_cr3(vcpu); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr3); @@ -1102,11 +1109,35 @@ static u32 msr_based_features[] = { static unsigned int num_msr_based_features; +u64 kvm_get_arch_capabilities(void) +{ + u64 data; + + rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data); + + /* + * If we're doing cache flushes (either "always" or "cond") + * we will do one whenever the guest does a vmlaunch/vmresume. + * If an outer hypervisor is doing the cache flush for us + * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that + * capability to the guest too, and if EPT is disabled we're not + * vulnerable. Overall, only VMENTER_L1D_FLUSH_NEVER will + * require a nested hypervisor to do a flush of its own. + */ + if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) + data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + + return data; +} +EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); + static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { - case MSR_IA32_UCODE_REV: case MSR_IA32_ARCH_CAPABILITIES: + msr->data = kvm_get_arch_capabilities(); + break; + case MSR_IA32_UCODE_REV: rdmsrl_safe(msr->index, &msr->data); break; default: @@ -2160,10 +2191,11 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.mcg_status = data; break; case MSR_IA32_MCG_CTL: - if (!(mcg_cap & MCG_CTL_P)) + if (!(mcg_cap & MCG_CTL_P) && + (data || !msr_info->host_initiated)) return 1; if (data != 0 && data != ~(u64)0) - return -1; + return 1; vcpu->arch.mcg_ctl = data; break; default: @@ -2551,7 +2583,7 @@ int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) } EXPORT_SYMBOL_GPL(kvm_get_msr); -static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data; u64 mcg_cap = vcpu->arch.mcg_cap; @@ -2566,7 +2598,7 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = vcpu->arch.mcg_cap; break; case MSR_IA32_MCG_CTL: - if (!(mcg_cap & MCG_CTL_P)) + if (!(mcg_cap & MCG_CTL_P) && !host) return 1; data = vcpu->arch.mcg_ctl; break; @@ -2699,7 +2731,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: - return get_msr_mce(vcpu, msr_info->index, &msr_info->data); + return get_msr_mce(vcpu, msr_info->index, &msr_info->data, + msr_info->host_initiated); case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other @@ -2720,7 +2753,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: return kvm_hv_get_msr_common(vcpu, - msr_info->index, &msr_info->data); + msr_info->index, &msr_info->data, + msr_info->host_initiated); break; case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current @@ -2944,6 +2978,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X2APIC_API: r = KVM_X2APIC_API_VALID_FLAGS; break; + case KVM_CAP_NESTED_STATE: + r = kvm_x86_ops->get_nested_state ? + kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0; + break; default: break; } @@ -3960,6 +3998,56 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break; } + case KVM_GET_NESTED_STATE: { + struct kvm_nested_state __user *user_kvm_nested_state = argp; + u32 user_data_size; + + r = -EINVAL; + if (!kvm_x86_ops->get_nested_state) + break; + + BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); + if (get_user(user_data_size, &user_kvm_nested_state->size)) + return -EFAULT; + + r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state, + user_data_size); + if (r < 0) + return r; + + if (r > user_data_size) { + if (put_user(r, &user_kvm_nested_state->size)) + return -EFAULT; + return -E2BIG; + } + r = 0; + break; + } + case KVM_SET_NESTED_STATE: { + struct kvm_nested_state __user *user_kvm_nested_state = argp; + struct kvm_nested_state kvm_state; + + r = -EINVAL; + if (!kvm_x86_ops->set_nested_state) + break; + + if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state))) + return -EFAULT; + + if (kvm_state.size < sizeof(kvm_state)) + return -EINVAL; + + if (kvm_state.flags & + ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE)) + return -EINVAL; + + /* nested_run_pending implies guest_mode. */ + if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING) + return -EINVAL; + + r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + break; + } default: r = -EINVAL; } @@ -4876,6 +4964,9 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { + /* kvm_write_guest_virt_system can pull in tons of pages. */ + vcpu->arch.l1tf_flush_l1d = true; + return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); } @@ -6052,6 +6143,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, bool writeback = true; bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; + vcpu->arch.l1tf_flush_l1d = true; + /* * Clear write_fault_to_shadow_pgtable here to ensure it is * never reused. @@ -6473,8 +6566,12 @@ static void kvm_set_mmio_spte_mask(void) * Set the reserved bits and the present bit of an paging-structure * entry to generate page fault with PFER.RSV = 1. */ - /* Mask the reserved physical address bits. */ - mask = rsvd_bits(maxphyaddr, 51); + + /* + * Mask the uppermost physical address bit, which would be reserved as + * long as the supported physical address width is less than 52. + */ + mask = 1ull << 51; /* Set the present bit. */ mask |= 1ull; @@ -6739,6 +6836,9 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) case KVM_HC_CLOCK_PAIRING: ret = kvm_pv_clock_pairing(vcpu, a0, a1); break; + case KVM_HC_SEND_IPI: + ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit); + break; #endif default: ret = -KVM_ENOSYS; @@ -7257,6 +7357,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_immediate_exit = false; if (kvm_request_pending(vcpu)) { + if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) + kvm_x86_ops->get_vmcs12_pages(vcpu); if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) kvm_mmu_unload(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) @@ -7272,6 +7374,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); + if (kvm_check_request(KVM_REQ_LOAD_CR3, vcpu)) + kvm_mmu_load_cr3(vcpu); if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) kvm_vcpu_flush_tlb(vcpu, true); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { @@ -7581,6 +7685,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + vcpu->arch.l1tf_flush_l1d = true; for (;;) { if (kvm_vcpu_running(vcpu)) { @@ -7982,6 +8087,10 @@ EXPORT_SYMBOL_GPL(kvm_task_switch); static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + (sregs->cr4 & X86_CR4_OSXSAVE)) + return -EINVAL; + if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in @@ -8012,10 +8121,6 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) struct desc_ptr dt; int ret = -EINVAL; - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - (sregs->cr4 & X86_CR4_OSXSAVE)) - goto out; - if (kvm_valid_sregs(vcpu, sregs)) goto out; @@ -8700,6 +8805,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { + vcpu->arch.l1tf_flush_l1d = true; kvm_x86_ops->sched_in(vcpu, cpu); } diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 298ef1479240..3b24dc05251c 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -256,7 +256,7 @@ ENTRY(__memcpy_mcsafe) /* Copy successful. Return zero */ .L_done_memcpy_trap: - xorq %rax, %rax + xorl %eax, %eax ret ENDPROC(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 2f3c9196b834..a12afff146d1 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -111,6 +111,8 @@ static struct addr_marker address_markers[] = { [END_OF_SPACE_NR] = { -1, NULL } }; +#define INIT_PGD ((pgd_t *) &init_top_pgt) + #else /* CONFIG_X86_64 */ enum address_markers_idx { @@ -121,6 +123,9 @@ enum address_markers_idx { #ifdef CONFIG_HIGHMEM PKMAP_BASE_NR, #endif +#ifdef CONFIG_MODIFY_LDT_SYSCALL + LDT_NR, +#endif CPU_ENTRY_AREA_NR, FIXADDR_START_NR, END_OF_SPACE_NR, @@ -134,11 +139,16 @@ static struct addr_marker address_markers[] = { #ifdef CONFIG_HIGHMEM [PKMAP_BASE_NR] = { 0UL, "Persistent kmap() Area" }, #endif +#ifdef CONFIG_MODIFY_LDT_SYSCALL + [LDT_NR] = { 0UL, "LDT remap" }, +#endif [CPU_ENTRY_AREA_NR] = { 0UL, "CPU entry area" }, [FIXADDR_START_NR] = { 0UL, "Fixmap area" }, [END_OF_SPACE_NR] = { -1, NULL } }; +#define INIT_PGD (swapper_pg_dir) + #endif /* !CONFIG_X86_64 */ /* Multipliers for offsets within the PTEs */ @@ -496,11 +506,7 @@ static inline bool is_hypervisor_range(int idx) static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, bool checkwx, bool dmesg) { -#ifdef CONFIG_X86_64 - pgd_t *start = (pgd_t *) &init_top_pgt; -#else - pgd_t *start = swapper_pg_dir; -#endif + pgd_t *start = INIT_PGD; pgprotval_t prot, eff; int i; struct pg_state st = {}; @@ -563,12 +569,13 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user) } EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs); -static void ptdump_walk_user_pgd_level_checkwx(void) +void ptdump_walk_user_pgd_level_checkwx(void) { #ifdef CONFIG_PAGE_TABLE_ISOLATION - pgd_t *pgd = (pgd_t *) &init_top_pgt; + pgd_t *pgd = INIT_PGD; - if (!static_cpu_has(X86_FEATURE_PTI)) + if (!(__supported_pte_mask & _PAGE_NX) || + !static_cpu_has(X86_FEATURE_PTI)) return; pr_info("x86/mm: Checking user space page tables\n"); @@ -580,7 +587,6 @@ static void ptdump_walk_user_pgd_level_checkwx(void) void ptdump_walk_pgd_level_checkwx(void) { ptdump_walk_pgd_level_core(NULL, NULL, true, false); - ptdump_walk_user_pgd_level_checkwx(); } static int __init pt_dump_init(void) @@ -609,6 +615,9 @@ static int __init pt_dump_init(void) # endif address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE; +# ifdef CONFIG_MODIFY_LDT_SYSCALL + address_markers[LDT_NR].start_address = LDT_BASE_ADDR; +# endif #endif return 0; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2aafa6ab6103..b9123c497e0a 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -16,6 +16,7 @@ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ #include <linux/uaccess.h> /* faulthandler_disabled() */ +#include <linux/mm_types.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ @@ -317,8 +318,6 @@ static noinline int vmalloc_fault(unsigned long address) if (!(address >= VMALLOC_START && address < VMALLOC_END)) return -1; - WARN_ON_ONCE(in_nmi()); - /* * Synchronize this task's top level page-table * with the 'reference' page table. @@ -1001,7 +1000,7 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, u32 *pkey, unsigned int fault) + unsigned long address, u32 *pkey, vm_fault_t fault) { if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) { no_context(regs, error_code, address, 0, 0); @@ -1215,7 +1214,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; - int fault, major = 0; + vm_fault_t fault, major = 0; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; u32 pkey; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index cee58a972cb2..acfab322fbe0 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -4,6 +4,8 @@ #include <linux/swap.h> #include <linux/memblock.h> #include <linux/bootmem.h> /* for max_low_pfn */ +#include <linux/swapfile.h> +#include <linux/swapops.h> #include <asm/set_memory.h> #include <asm/e820/api.h> @@ -773,13 +775,44 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) } } +/* + * begin/end can be in the direct map or the "high kernel mapping" + * used for the kernel image only. free_init_pages() will do the + * right thing for either kind of address. + */ +void free_kernel_image_pages(void *begin, void *end) +{ + unsigned long begin_ul = (unsigned long)begin; + unsigned long end_ul = (unsigned long)end; + unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT; + + + free_init_pages("unused kernel image", begin_ul, end_ul); + + /* + * PTI maps some of the kernel into userspace. For performance, + * this includes some kernel areas that do not contain secrets. + * Those areas might be adjacent to the parts of the kernel image + * being freed, which may contain secrets. Remove the "high kernel + * image mapping" for these freed areas, ensuring they are not even + * potentially vulnerable to Meltdown regardless of the specific + * optimizations PTI is currently using. + * + * The "noalias" prevents unmapping the direct map alias which is + * needed to access the freed pages. + * + * This is only valid for 64bit kernels. 32bit has only one mapping + * which can't be treated in this way for obvious reasons. + */ + if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI)) + set_memory_np_noalias(begin_ul, len_pages); +} + void __ref free_initmem(void) { e820__reallocate_tables(); - free_init_pages("unused kernel", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); + free_kernel_image_pages(&__init_begin, &__init_end); } #ifdef CONFIG_BLK_DEV_INITRD @@ -880,3 +913,26 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) __cachemode2pte_tbl[cache] = __cm_idx2pte(entry); __pte2cachemode_tbl[entry] = cache; } + +#ifdef CONFIG_SWAP +unsigned long max_swapfile_size(void) +{ + unsigned long pages; + + pages = generic_max_swapfile_size(); + + if (boot_cpu_has_bug(X86_BUG_L1TF)) { + /* Limit the swap file size to MAX_PA/2 for L1TF workaround */ + unsigned long l1tf_limit = l1tf_pfn_limit() + 1; + /* + * We encode swap offsets also with 3 bits below those for pfn + * which makes the usable limit higher. + */ +#if CONFIG_PGTABLE_LEVELS > 2 + l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT; +#endif + pages = min_t(unsigned long, l1tf_limit, pages); + } + return pages; +} +#endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a688617c727e..dd519f372169 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1283,20 +1283,10 @@ void mark_rodata_ro(void) set_memory_ro(start, (end-start) >> PAGE_SHIFT); #endif - free_init_pages("unused kernel", - (unsigned long) __va(__pa_symbol(text_end)), - (unsigned long) __va(__pa_symbol(rodata_start))); - free_init_pages("unused kernel", - (unsigned long) __va(__pa_symbol(rodata_end)), - (unsigned long) __va(__pa_symbol(_sdata))); + free_kernel_image_pages((void *)text_end, (void *)rodata_start); + free_kernel_image_pages((void *)rodata_end, (void *)_sdata); debug_checkwx(); - - /* - * Do this after all of the manipulation of the - * kernel text page tables are complete. - */ - pti_clone_kernel_text(); } int kern_addr_valid(unsigned long addr) diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 7c8686709636..79eb55ce69a9 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -126,24 +126,29 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr) static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old) { + pmd_t new_pmd; pmdval_t v = pmd_val(*pmd); if (clear) { - *old = v & _PAGE_PRESENT; - v &= ~_PAGE_PRESENT; - } else /* presume this has been called with clear==true previously */ - v |= *old; - set_pmd(pmd, __pmd(v)); + *old = v; + new_pmd = pmd_mknotpresent(*pmd); + } else { + /* Presume this has been called with clear==true previously */ + new_pmd = __pmd(*old); + } + set_pmd(pmd, new_pmd); } static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old) { pteval_t v = pte_val(*pte); if (clear) { - *old = v & _PAGE_PRESENT; - v &= ~_PAGE_PRESENT; - } else /* presume this has been called with clear==true previously */ - v |= *old; - set_pte_atomic(pte, __pte(v)); + *old = v; + /* Nothing should care about address */ + pte_clear(&init_mm, 0, pte); + } else { + /* Presume this has been called with clear==true previously */ + set_pte_atomic(pte, __pte(*old)); + } } static int clear_page_presence(struct kmmio_fault_page *f, bool clear) diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 48c591251600..f40ab8185d94 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -240,3 +240,24 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t count) return phys_addr_valid(addr + count - 1); } + +/* + * Only allow root to set high MMIO mappings to PROT_NONE. + * This prevents an unpriv. user to set them to PROT_NONE and invert + * them, then pointing to valid memory for L1TF speculation. + * + * Note: for locked down kernels may want to disable the root override. + */ +bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return true; + if (!__pte_needs_invert(pgprot_val(prot))) + return true; + /* If it's real memory always allow */ + if (pfn_valid(pfn)) + return true; + if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN)) + return false; + return true; +} diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 34a2a3bfde9c..b54d52a2d00a 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -61,7 +61,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei, eb->nid = nid; if (emu_nid_to_phys[nid] == NUMA_NO_NODE) - emu_nid_to_phys[nid] = nid; + emu_nid_to_phys[nid] = pb->nid; pb->start += size; if (pb->start >= pb->end) { @@ -198,40 +198,73 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) return end; } +static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes) +{ + unsigned long max_pfn = PHYS_PFN(max_addr); + unsigned long base_pfn = PHYS_PFN(base); + unsigned long hole_pfns = PHYS_PFN(hole); + + return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes); +} + /* * Sets up fake nodes of `size' interleaved over physical nodes ranging from * `addr' to `max_addr'. * * Returns zero on success or negative on error. */ -static int __init split_nodes_size_interleave(struct numa_meminfo *ei, +static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, struct numa_meminfo *pi, - u64 addr, u64 max_addr, u64 size) + u64 addr, u64 max_addr, u64 size, + int nr_nodes, struct numa_memblk *pblk, + int nid) { nodemask_t physnode_mask = numa_nodes_parsed; + int i, ret, uniform = 0; u64 min_size; - int nid = 0; - int i, ret; - if (!size) + if ((!size && !nr_nodes) || (nr_nodes && !pblk)) return -1; + /* - * The limit on emulated nodes is MAX_NUMNODES, so the size per node is - * increased accordingly if the requested size is too small. This - * creates a uniform distribution of node sizes across the entire - * machine (but not necessarily over physical nodes). + * In the 'uniform' case split the passed in physical node by + * nr_nodes, in the non-uniform case, ignore the passed in + * physical block and try to create nodes of at least size + * @size. + * + * In the uniform case, split the nodes strictly by physical + * capacity, i.e. ignore holes. In the non-uniform case account + * for holes and treat @size as a minimum floor. */ - min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES; - min_size = max(min_size, FAKE_NODE_MIN_SIZE); - if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size) - min_size = (min_size + FAKE_NODE_MIN_SIZE) & - FAKE_NODE_MIN_HASH_MASK; + if (!nr_nodes) + nr_nodes = MAX_NUMNODES; + else { + nodes_clear(physnode_mask); + node_set(pblk->nid, physnode_mask); + uniform = 1; + } + + if (uniform) { + min_size = uniform_size(max_addr, addr, 0, nr_nodes); + size = min_size; + } else { + /* + * The limit on emulated nodes is MAX_NUMNODES, so the + * size per node is increased accordingly if the + * requested size is too small. This creates a uniform + * distribution of node sizes across the entire machine + * (but not necessarily over physical nodes). + */ + min_size = uniform_size(max_addr, addr, + mem_hole_size(addr, max_addr), nr_nodes); + } + min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE); if (size < min_size) { pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", size >> 20, min_size >> 20); size = min_size; } - size &= FAKE_NODE_MIN_HASH_MASK; + size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE); /* * Fill physical nodes with fake nodes of size until there is no memory @@ -248,10 +281,14 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, node_clear(i, physnode_mask); continue; } + start = pi->blk[phys_blk].start; limit = pi->blk[phys_blk].end; - end = find_end_of_node(start, limit, size); + if (uniform) + end = start + size; + else + end = find_end_of_node(start, limit, size); /* * If there won't be at least FAKE_NODE_MIN_SIZE of * non-reserved memory in ZONE_DMA32 for the next node, @@ -266,7 +303,8 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * next node, this one must extend to the end of the * physical node. */ - if (limit - end - mem_hole_size(end, limit) < size) + if ((limit - end - mem_hole_size(end, limit) < size) + && !uniform) end = limit; ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, @@ -276,7 +314,15 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, return ret; } } - return 0; + return nid; +} + +static int __init split_nodes_size_interleave(struct numa_meminfo *ei, + struct numa_meminfo *pi, + u64 addr, u64 max_addr, u64 size) +{ + return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, + 0, NULL, NUMA_NO_NODE); } int __init setup_emu2phys_nid(int *dfl_phys_nid) @@ -346,7 +392,28 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) * the fixed node size. Otherwise, if it is just a single number N, * split the system RAM into N fake nodes. */ - if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { + if (strchr(emu_cmdline, 'U')) { + nodemask_t physnode_mask = numa_nodes_parsed; + unsigned long n; + int nid = 0; + + n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); + ret = -1; + for_each_node_mask(i, physnode_mask) { + ret = split_nodes_size_interleave_uniform(&ei, &pi, + pi.blk[i].start, pi.blk[i].end, 0, + n, &pi.blk[i], nid); + if (ret < 0) + break; + if (ret < n) { + pr_info("%s: phys: %d only got %d of %ld nodes, failing\n", + __func__, i, ret, n); + ret = -1; + break; + } + nid = ret; + } + } else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { u64 size; size = memparse(emu_cmdline, &emu_cmdline); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 3bded76e8d5c..8d6c34fe49be 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -53,6 +53,7 @@ static DEFINE_SPINLOCK(cpa_lock); #define CPA_FLUSHTLB 1 #define CPA_ARRAY 2 #define CPA_PAGES_ARRAY 4 +#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */ #ifdef CONFIG_PROC_FS static unsigned long direct_pages_count[PG_LEVEL_NUM]; @@ -1014,8 +1015,8 @@ static long populate_pmd(struct cpa_data *cpa, pmd = pmd_offset(pud, start); - set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | - massage_pgprot(pmd_pgprot))); + set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn, + canon_pgprot(pmd_pgprot)))); start += PMD_SIZE; cpa->pfn += PMD_SIZE >> PAGE_SHIFT; @@ -1087,8 +1088,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d, * Map everything starting from the Gb boundary, possibly with 1G pages */ while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) { - set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | - massage_pgprot(pud_pgprot))); + set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn, + canon_pgprot(pud_pgprot)))); start += PUD_SIZE; cpa->pfn += PUD_SIZE >> PAGE_SHIFT; @@ -1486,6 +1487,9 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, /* No alias checking for _NX bit modifications */ checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX; + /* Has caller explicitly disabled alias checking? */ + if (in_flag & CPA_NO_CHECK_ALIAS) + checkalias = 0; ret = __change_page_attr_set_clr(&cpa, checkalias); @@ -1772,6 +1776,15 @@ int set_memory_np(unsigned long addr, int numpages) return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); } +int set_memory_np_noalias(unsigned long addr, int numpages) +{ + int cpa_flags = CPA_NO_CHECK_ALIAS; + + return change_page_attr_set_clr(&addr, numpages, __pgprot(0), + __pgprot(_PAGE_PRESENT), 0, + cpa_flags, NULL); +} + int set_memory_4k(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(0), @@ -1784,6 +1797,12 @@ int set_memory_nonglobal(unsigned long addr, int numpages) __pgprot(_PAGE_GLOBAL), 0); } +int set_memory_global(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, + __pgprot(_PAGE_GLOBAL), 0); +} + static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) { struct cpa_data cpa; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 47b5951e592b..3ef095c70ae3 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -182,6 +182,14 @@ static void pgd_dtor(pgd_t *pgd) */ #define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD +/* + * We allocate separate PMDs for the kernel part of the user page-table + * when PTI is enabled. We need them to map the per-process LDT into the + * user-space page-table. + */ +#define PREALLOCATED_USER_PMDS (static_cpu_has(X86_FEATURE_PTI) ? \ + KERNEL_PGD_PTRS : 0) + void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); @@ -202,14 +210,14 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) /* No need to prepopulate any pagetable entries in non-PAE modes. */ #define PREALLOCATED_PMDS 0 - +#define PREALLOCATED_USER_PMDS 0 #endif /* CONFIG_X86_PAE */ -static void free_pmds(struct mm_struct *mm, pmd_t *pmds[]) +static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; - for(i = 0; i < PREALLOCATED_PMDS; i++) + for (i = 0; i < count; i++) if (pmds[i]) { pgtable_pmd_page_dtor(virt_to_page(pmds[i])); free_page((unsigned long)pmds[i]); @@ -217,7 +225,7 @@ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[]) } } -static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) +static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; bool failed = false; @@ -226,7 +234,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; - for(i = 0; i < PREALLOCATED_PMDS; i++) { + for (i = 0; i < count; i++) { pmd_t *pmd = (pmd_t *)__get_free_page(gfp); if (!pmd) failed = true; @@ -241,7 +249,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) } if (failed) { - free_pmds(mm, pmds); + free_pmds(mm, pmds, count); return -ENOMEM; } @@ -254,23 +262,38 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) * preallocate which never got a corresponding vma will need to be * freed manually. */ +static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) +{ + pgd_t pgd = *pgdp; + + if (pgd_val(pgd) != 0) { + pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); + + *pgdp = native_make_pgd(0); + + paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); + pmd_free(mm, pmd); + mm_dec_nr_pmds(mm); + } +} + static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) { int i; - for(i = 0; i < PREALLOCATED_PMDS; i++) { - pgd_t pgd = pgdp[i]; + for (i = 0; i < PREALLOCATED_PMDS; i++) + mop_up_one_pmd(mm, &pgdp[i]); - if (pgd_val(pgd) != 0) { - pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); +#ifdef CONFIG_PAGE_TABLE_ISOLATION - pgdp[i] = native_make_pgd(0); + if (!static_cpu_has(X86_FEATURE_PTI)) + return; - paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); - pmd_free(mm, pmd); - mm_dec_nr_pmds(mm); - } - } + pgdp = kernel_to_user_pgdp(pgdp); + + for (i = 0; i < PREALLOCATED_USER_PMDS; i++) + mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]); +#endif } static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) @@ -296,6 +319,38 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) } } +#ifdef CONFIG_PAGE_TABLE_ISOLATION +static void pgd_prepopulate_user_pmd(struct mm_struct *mm, + pgd_t *k_pgd, pmd_t *pmds[]) +{ + pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir); + pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); + p4d_t *u_p4d; + pud_t *u_pud; + int i; + + u_p4d = p4d_offset(u_pgd, 0); + u_pud = pud_offset(u_p4d, 0); + + s_pgd += KERNEL_PGD_BOUNDARY; + u_pud += KERNEL_PGD_BOUNDARY; + + for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) { + pmd_t *pmd = pmds[i]; + + memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd), + sizeof(pmd_t) * PTRS_PER_PMD); + + pud_populate(mm, u_pud, pmd); + } + +} +#else +static void pgd_prepopulate_user_pmd(struct mm_struct *mm, + pgd_t *k_pgd, pmd_t *pmds[]) +{ +} +#endif /* * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also * assumes that pgd should be in one page. @@ -329,9 +384,6 @@ static int __init pgd_cache_init(void) */ pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN, SLAB_PANIC, NULL); - if (!pgd_cache) - return -ENOMEM; - return 0; } core_initcall(pgd_cache_init); @@ -343,7 +395,8 @@ static inline pgd_t *_pgd_alloc(void) * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) - return (pgd_t *)__get_free_page(PGALLOC_GFP); + return (pgd_t *)__get_free_pages(PGALLOC_GFP, + PGD_ALLOCATION_ORDER); /* * Now PAE kernel is not running as a Xen domain. We can allocate @@ -355,7 +408,7 @@ static inline pgd_t *_pgd_alloc(void) static inline void _pgd_free(pgd_t *pgd) { if (!SHARED_KERNEL_PMD) - free_page((unsigned long)pgd); + free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); else kmem_cache_free(pgd_cache, pgd); } @@ -375,6 +428,7 @@ static inline void _pgd_free(pgd_t *pgd) pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; + pmd_t *u_pmds[PREALLOCATED_USER_PMDS]; pmd_t *pmds[PREALLOCATED_PMDS]; pgd = _pgd_alloc(); @@ -384,12 +438,15 @@ pgd_t *pgd_alloc(struct mm_struct *mm) mm->pgd = pgd; - if (preallocate_pmds(mm, pmds) != 0) + if (preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0) goto out_free_pgd; - if (paravirt_pgd_alloc(mm) != 0) + if (preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0) goto out_free_pmds; + if (paravirt_pgd_alloc(mm) != 0) + goto out_free_user_pmds; + /* * Make sure that pre-populating the pmds is atomic with * respect to anything walking the pgd_list, so that they @@ -399,13 +456,16 @@ pgd_t *pgd_alloc(struct mm_struct *mm) pgd_ctor(mm, pgd); pgd_prepopulate_pmd(mm, pgd, pmds); + pgd_prepopulate_user_pmd(mm, pgd, u_pmds); spin_unlock(&pgd_lock); return pgd; +out_free_user_pmds: + free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS); out_free_pmds: - free_pmds(mm, pmds); + free_pmds(mm, pmds, PREALLOCATED_PMDS); out_free_pgd: _pgd_free(pgd); out: @@ -719,28 +779,50 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } +#ifdef CONFIG_X86_64 /** * pud_free_pmd_page - Clear pud entry and free pmd page. * @pud: Pointer to a PUD. + * @addr: Virtual address associated with pud. * - * Context: The pud range has been unmaped and TLB purged. + * Context: The pud range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. + * + * NOTE: Callers must allow a single page allocation. */ -int pud_free_pmd_page(pud_t *pud) +int pud_free_pmd_page(pud_t *pud, unsigned long addr) { - pmd_t *pmd; + pmd_t *pmd, *pmd_sv; + pte_t *pte; int i; if (pud_none(*pud)) return 1; pmd = (pmd_t *)pud_page_vaddr(*pud); + pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL); + if (!pmd_sv) + return 0; - for (i = 0; i < PTRS_PER_PMD; i++) - if (!pmd_free_pte_page(&pmd[i])) - return 0; + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd_sv[i] = pmd[i]; + if (!pmd_none(pmd[i])) + pmd_clear(&pmd[i]); + } pud_clear(pud); + + /* INVLPG to clear all paging-structure caches */ + flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); + + for (i = 0; i < PTRS_PER_PMD; i++) { + if (!pmd_none(pmd_sv[i])) { + pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]); + free_page((unsigned long)pte); + } + } + + free_page((unsigned long)pmd_sv); free_page((unsigned long)pmd); return 1; @@ -749,11 +831,12 @@ int pud_free_pmd_page(pud_t *pud) /** * pmd_free_pte_page - Clear pmd entry and free pte page. * @pmd: Pointer to a PMD. + * @addr: Virtual address associated with pmd. * - * Context: The pmd range has been unmaped and TLB purged. + * Context: The pmd range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ -int pmd_free_pte_page(pmd_t *pmd) +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { pte_t *pte; @@ -762,8 +845,30 @@ int pmd_free_pte_page(pmd_t *pmd) pte = (pte_t *)pmd_page_vaddr(*pmd); pmd_clear(pmd); + + /* INVLPG to clear all paging-structure caches */ + flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); + free_page((unsigned long)pte); return 1; } + +#else /* !CONFIG_X86_64 */ + +int pud_free_pmd_page(pud_t *pud, unsigned long addr) +{ + return pud_none(*pud); +} + +/* + * Disable free page handling on x86-PAE. This assures that ioremap() + * does not update sync'd pmd entries. See vmalloc_sync_one(). + */ +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) +{ + return pmd_none(*pmd); +} + +#endif /* CONFIG_X86_64 */ #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 4d418e705878..31341ae7309f 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -45,6 +45,7 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/desc.h> +#include <asm/sections.h> #undef pr_fmt #define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt @@ -54,6 +55,16 @@ #define __GFP_NOTRACK 0 #endif +/* + * Define the page-table levels we clone for user-space on 32 + * and 64 bit. + */ +#ifdef CONFIG_X86_64 +#define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PMD +#else +#define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PTE +#endif + static void __init pti_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) @@ -117,7 +128,7 @@ enable: setup_force_cpu_cap(X86_FEATURE_PTI); } -pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) +pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { /* * Changes to the high (kernel) portion of the kernelmode page @@ -176,7 +187,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) if (pgd_none(*pgd)) { unsigned long new_p4d_page = __get_free_page(gfp); - if (!new_p4d_page) + if (WARN_ON_ONCE(!new_p4d_page)) return NULL; set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); @@ -195,13 +206,17 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); - p4d_t *p4d = pti_user_pagetable_walk_p4d(address); + p4d_t *p4d; pud_t *pud; + p4d = pti_user_pagetable_walk_p4d(address); + if (!p4d) + return NULL; + BUILD_BUG_ON(p4d_large(*p4d) != 0); if (p4d_none(*p4d)) { unsigned long new_pud_page = __get_free_page(gfp); - if (!new_pud_page) + if (WARN_ON_ONCE(!new_pud_page)) return NULL; set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); @@ -215,7 +230,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) } if (pud_none(*pud)) { unsigned long new_pmd_page = __get_free_page(gfp); - if (!new_pmd_page) + if (WARN_ON_ONCE(!new_pmd_page)) return NULL; set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); @@ -224,7 +239,6 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) return pmd_offset(pud, address); } -#ifdef CONFIG_X86_VSYSCALL_EMULATION /* * Walk the shadow copy of the page tables (optionally) trying to allocate * page table pages on the way down. Does not support large pages. @@ -237,9 +251,13 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); - pmd_t *pmd = pti_user_pagetable_walk_pmd(address); + pmd_t *pmd; pte_t *pte; + pmd = pti_user_pagetable_walk_pmd(address); + if (!pmd) + return NULL; + /* We can't do anything sensible if we hit a large mapping. */ if (pmd_large(*pmd)) { WARN_ON(1); @@ -262,6 +280,7 @@ static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address) return pte; } +#ifdef CONFIG_X86_VSYSCALL_EMULATION static void __init pti_setup_vsyscall(void) { pte_t *pte, *target_pte; @@ -282,8 +301,14 @@ static void __init pti_setup_vsyscall(void) static void __init pti_setup_vsyscall(void) { } #endif +enum pti_clone_level { + PTI_CLONE_PMD, + PTI_CLONE_PTE, +}; + static void -pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear) +pti_clone_pgtable(unsigned long start, unsigned long end, + enum pti_clone_level level) { unsigned long addr; @@ -291,59 +316,105 @@ pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear) * Clone the populated PMDs which cover start to end. These PMD areas * can have holes. */ - for (addr = start; addr < end; addr += PMD_SIZE) { + for (addr = start; addr < end;) { + pte_t *pte, *target_pte; pmd_t *pmd, *target_pmd; pgd_t *pgd; p4d_t *p4d; pud_t *pud; + /* Overflow check */ + if (addr < start) + break; + pgd = pgd_offset_k(addr); if (WARN_ON(pgd_none(*pgd))) return; p4d = p4d_offset(pgd, addr); if (WARN_ON(p4d_none(*p4d))) return; + pud = pud_offset(p4d, addr); - if (pud_none(*pud)) + if (pud_none(*pud)) { + addr += PUD_SIZE; continue; + } + pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + if (pmd_none(*pmd)) { + addr += PMD_SIZE; continue; + } - target_pmd = pti_user_pagetable_walk_pmd(addr); - if (WARN_ON(!target_pmd)) - return; - - /* - * Only clone present PMDs. This ensures only setting - * _PAGE_GLOBAL on present PMDs. This should only be - * called on well-known addresses anyway, so a non- - * present PMD would be a surprise. - */ - if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT))) - return; - - /* - * Setting 'target_pmd' below creates a mapping in both - * the user and kernel page tables. It is effectively - * global, so set it as global in both copies. Note: - * the X86_FEATURE_PGE check is not _required_ because - * the CPU ignores _PAGE_GLOBAL when PGE is not - * supported. The check keeps consistentency with - * code that only set this bit when supported. - */ - if (boot_cpu_has(X86_FEATURE_PGE)) - *pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL); - - /* - * Copy the PMD. That is, the kernelmode and usermode - * tables will share the last-level page tables of this - * address range - */ - *target_pmd = pmd_clear_flags(*pmd, clear); + if (pmd_large(*pmd) || level == PTI_CLONE_PMD) { + target_pmd = pti_user_pagetable_walk_pmd(addr); + if (WARN_ON(!target_pmd)) + return; + + /* + * Only clone present PMDs. This ensures only setting + * _PAGE_GLOBAL on present PMDs. This should only be + * called on well-known addresses anyway, so a non- + * present PMD would be a surprise. + */ + if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT))) + return; + + /* + * Setting 'target_pmd' below creates a mapping in both + * the user and kernel page tables. It is effectively + * global, so set it as global in both copies. Note: + * the X86_FEATURE_PGE check is not _required_ because + * the CPU ignores _PAGE_GLOBAL when PGE is not + * supported. The check keeps consistentency with + * code that only set this bit when supported. + */ + if (boot_cpu_has(X86_FEATURE_PGE)) + *pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL); + + /* + * Copy the PMD. That is, the kernelmode and usermode + * tables will share the last-level page tables of this + * address range + */ + *target_pmd = *pmd; + + addr += PMD_SIZE; + + } else if (level == PTI_CLONE_PTE) { + + /* Walk the page-table down to the pte level */ + pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) { + addr += PAGE_SIZE; + continue; + } + + /* Only clone present PTEs */ + if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT))) + return; + + /* Allocate PTE in the user page-table */ + target_pte = pti_user_pagetable_walk_pte(addr); + if (WARN_ON(!target_pte)) + return; + + /* Set GLOBAL bit in both PTEs */ + if (boot_cpu_has(X86_FEATURE_PGE)) + *pte = pte_set_flags(*pte, _PAGE_GLOBAL); + + /* Clone the PTE */ + *target_pte = *pte; + + addr += PAGE_SIZE; + + } else { + BUG(); + } } } +#ifdef CONFIG_X86_64 /* * Clone a single p4d (i.e. a top-level entry on 4-level systems and a * next-level entry on 5-level systems. @@ -354,6 +425,9 @@ static void __init pti_clone_p4d(unsigned long addr) pgd_t *kernel_pgd; user_p4d = pti_user_pagetable_walk_p4d(addr); + if (!user_p4d) + return; + kernel_pgd = pgd_offset_k(addr); kernel_p4d = p4d_offset(kernel_pgd, addr); *user_p4d = *kernel_p4d; @@ -367,6 +441,25 @@ static void __init pti_clone_user_shared(void) pti_clone_p4d(CPU_ENTRY_AREA_BASE); } +#else /* CONFIG_X86_64 */ + +/* + * On 32 bit PAE systems with 1GB of Kernel address space there is only + * one pgd/p4d for the whole kernel. Cloning that would map the whole + * address space into the user page-tables, making PTI useless. So clone + * the page-table on the PMD level to prevent that. + */ +static void __init pti_clone_user_shared(void) +{ + unsigned long start, end; + + start = CPU_ENTRY_AREA_BASE; + end = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES); + + pti_clone_pgtable(start, end, PTI_CLONE_PMD); +} +#endif /* CONFIG_X86_64 */ + /* * Clone the ESPFIX P4D into the user space visible page table */ @@ -380,11 +473,11 @@ static void __init pti_setup_espfix64(void) /* * Clone the populated PMDs of the entry and irqentry text and force it RO. */ -static void __init pti_clone_entry_text(void) +static void pti_clone_entry_text(void) { - pti_clone_pmds((unsigned long) __entry_text_start, - (unsigned long) __irqentry_text_end, - _PAGE_RW); + pti_clone_pgtable((unsigned long) __entry_text_start, + (unsigned long) __irqentry_text_end, + PTI_CLONE_PMD); } /* @@ -435,10 +528,17 @@ static inline bool pti_kernel_image_global_ok(void) } /* + * This is the only user for these and it is not arch-generic + * like the other set_memory.h functions. Just extern them. + */ +extern int set_memory_nonglobal(unsigned long addr, int numpages); +extern int set_memory_global(unsigned long addr, int numpages); + +/* * For some configurations, map all of kernel text into the user page * tables. This reduces TLB misses, especially on non-PCID systems. */ -void pti_clone_kernel_text(void) +static void pti_clone_kernel_text(void) { /* * rodata is part of the kernel image and is normally @@ -446,7 +546,8 @@ void pti_clone_kernel_text(void) * clone the areas past rodata, they might contain secrets. */ unsigned long start = PFN_ALIGN(_text); - unsigned long end = (unsigned long)__end_rodata_hpage_align; + unsigned long end_clone = (unsigned long)__end_rodata_aligned; + unsigned long end_global = PFN_ALIGN((unsigned long)__stop___ex_table); if (!pti_kernel_image_global_ok()) return; @@ -458,14 +559,18 @@ void pti_clone_kernel_text(void) * pti_set_kernel_image_nonglobal() did to clear the * global bit. */ - pti_clone_pmds(start, end, _PAGE_RW); + pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE); + + /* + * pti_clone_pgtable() will set the global bit in any PMDs + * that it clones, but we also need to get any PTEs in + * the last level for areas that are not huge-page-aligned. + */ + + /* Set the global bit for normal non-__init kernel text: */ + set_memory_global(start, (end_global - start) >> PAGE_SHIFT); } -/* - * This is the only user for it and it is not arch-generic like - * the other set_memory.h functions. Just extern it. - */ -extern int set_memory_nonglobal(unsigned long addr, int numpages); void pti_set_kernel_image_nonglobal(void) { /* @@ -477,9 +582,11 @@ void pti_set_kernel_image_nonglobal(void) unsigned long start = PFN_ALIGN(_text); unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE); - if (pti_kernel_image_global_ok()) - return; - + /* + * This clears _PAGE_GLOBAL from the entire kernel image. + * pti_clone_kernel_text() map put _PAGE_GLOBAL back for + * areas that are mapped to userspace. + */ set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT); } @@ -493,6 +600,28 @@ void __init pti_init(void) pr_info("enabled\n"); +#ifdef CONFIG_X86_32 + /* + * We check for X86_FEATURE_PCID here. But the init-code will + * clear the feature flag on 32 bit because the feature is not + * supported on 32 bit anyway. To print the warning we need to + * check with cpuid directly again. + */ + if (cpuid_ecx(0x1) & BIT(17)) { + /* Use printk to work around pr_fmt() */ + printk(KERN_WARNING "\n"); + printk(KERN_WARNING "************************************************************\n"); + printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n"); + printk(KERN_WARNING "** **\n"); + printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n"); + printk(KERN_WARNING "** Your performance will increase dramatically if you **\n"); + printk(KERN_WARNING "** switch to a 64-bit kernel! **\n"); + printk(KERN_WARNING "** **\n"); + printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n"); + printk(KERN_WARNING "************************************************************\n"); + } +#endif + pti_clone_user_shared(); /* Undo all global bits from the init pagetables in head_64.S: */ @@ -502,3 +631,22 @@ void __init pti_init(void) pti_setup_espfix64(); pti_setup_vsyscall(); } + +/* + * Finalize the kernel mappings in the userspace page-table. Some of the + * mappings for the kernel image might have changed since pti_init() + * cloned them. This is because parts of the kernel image have been + * mapped RO and/or NX. These changes need to be cloned again to the + * userspace page-table. + */ +void pti_finalize(void) +{ + /* + * We need to clone everything (again) that maps parts of the + * kernel image. + */ + pti_clone_entry_text(); + pti_clone_kernel_text(); + + debug_checkwx_user(); +} diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb1f34c3c85..752dbf4e0e50 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -7,6 +7,7 @@ #include <linux/export.h> #include <linux/cpu.h> #include <linux/debugfs.h> +#include <linux/gfp.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -35,7 +36,7 @@ * necessary invalidation by clearing out the 'ctx_id' which * forces a TLB flush when the context is loaded. */ -void clear_asid_other(void) +static void clear_asid_other(void) { u16 asid; @@ -185,8 +186,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, { struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy); unsigned cpu = smp_processor_id(); u64 next_tlb_gen; + bool need_flush; + u16 new_asid; /* * NB: The scheduler will call us with prev == next when switching @@ -240,20 +244,41 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, next->context.ctx_id); /* - * We don't currently support having a real mm loaded without - * our cpu set in mm_cpumask(). We have all the bookkeeping - * in place to figure out whether we would need to flush - * if our cpu were cleared in mm_cpumask(), but we don't - * currently use it. + * Even in lazy TLB mode, the CPU should stay set in the + * mm_cpumask. The TLB shootdown code can figure out from + * from cpu_tlbstate.is_lazy whether or not to send an IPI. */ if (WARN_ON_ONCE(real_prev != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))) cpumask_set_cpu(cpu, mm_cpumask(next)); - return; + /* + * If the CPU is not in lazy TLB mode, we are just switching + * from one thread in a process to another thread in the same + * process. No TLB flush required. + */ + if (!was_lazy) + return; + + /* + * Read the tlb_gen to check whether a flush is needed. + * If the TLB is up to date, just use it. + * The barrier synchronizes with the tlb_gen increment in + * the TLB shootdown code. + */ + smp_mb(); + next_tlb_gen = atomic64_read(&next->context.tlb_gen); + if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) == + next_tlb_gen) + return; + + /* + * TLB contents went out of date while we were in lazy + * mode. Fall through to the TLB switching code below. + */ + new_asid = prev_asid; + need_flush = true; } else { - u16 new_asid; - bool need_flush; u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); /* @@ -285,53 +310,60 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, sync_current_stack_to_mm(next); } - /* Stop remote flushes for the previous mm */ - VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && - real_prev != &init_mm); - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + /* + * Stop remote flushes for the previous mm. + * Skip kernel threads; we never send init_mm TLB flushing IPIs, + * but the bitmap manipulation can cause cache line contention. + */ + if (real_prev != &init_mm) { + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, + mm_cpumask(real_prev))); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + } /* * Start remote flushes and then read tlb_gen. */ - cpumask_set_cpu(cpu, mm_cpumask(next)); + if (next != &init_mm) + cpumask_set_cpu(cpu, mm_cpumask(next)); next_tlb_gen = atomic64_read(&next->context.tlb_gen); choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); + } - if (need_flush) { - this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); - this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - load_new_mm_cr3(next->pgd, new_asid, true); - - /* - * NB: This gets called via leave_mm() in the idle path - * where RCU functions differently. Tracing normally - * uses RCU, so we need to use the _rcuidle variant. - * - * (There is no good reason for this. The idle code should - * be rearranged to call this before rcu_idle_enter().) - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - } else { - /* The new ASID is already up to date. */ - load_new_mm_cr3(next->pgd, new_asid, false); - - /* See above wrt _rcuidle. */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); - } + if (need_flush) { + this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); + load_new_mm_cr3(next->pgd, new_asid, true); /* - * Record last user mm's context id, so we can avoid - * flushing branch buffer with IBPB if we switch back - * to the same user. + * NB: This gets called via leave_mm() in the idle path + * where RCU functions differently. Tracing normally + * uses RCU, so we need to use the _rcuidle variant. + * + * (There is no good reason for this. The idle code should + * be rearranged to call this before rcu_idle_enter().) */ - if (next != &init_mm) - this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + } else { + /* The new ASID is already up to date. */ + load_new_mm_cr3(next->pgd, new_asid, false); - this_cpu_write(cpu_tlbstate.loaded_mm, next); - this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); + /* See above wrt _rcuidle. */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } + /* + * Record last user mm's context id, so we can avoid + * flushing branch buffer with IBPB if we switch back + * to the same user. + */ + if (next != &init_mm) + this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + + this_cpu_write(cpu_tlbstate.loaded_mm, next); + this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); + load_mm_cr4(next); switch_ldt(real_prev, next); } @@ -354,20 +386,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) return; - if (tlb_defer_switch_to_init_mm()) { - /* - * There's a significant optimization that may be possible - * here. We have accurate enough TLB flush tracking that we - * don't need to maintain coherence of TLB per se when we're - * lazy. We do, however, need to maintain coherence of - * paging-structure caches. We could, in principle, leave our - * old mm loaded and only switch to init_mm when - * tlb_remove_page() happens. - */ - this_cpu_write(cpu_tlbstate.is_lazy, true); - } else { - switch_mm(NULL, &init_mm, NULL); - } + this_cpu_write(cpu_tlbstate.is_lazy, true); } /* @@ -454,6 +473,9 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * paging-structure cache to avoid speculatively reading * garbage into our TLB. Since switching to init_mm is barely * slower than a minimal flush, just switch to init_mm. + * + * This should be rare, with native_flush_tlb_others skipping + * IPIs to lazy TLB mode CPUs. */ switch_mm_irqs_off(NULL, &init_mm, NULL); return; @@ -560,6 +582,9 @@ static void flush_tlb_func_remote(void *info) void native_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) { + cpumask_var_t lazymask; + unsigned int cpu; + count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); if (info->end == TLB_FLUSH_ALL) trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); @@ -583,8 +608,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask, * that UV should be updated so that smp_call_function_many(), * etc, are optimal on UV. */ - unsigned int cpu; - cpu = smp_processor_id(); cpumask = uv_flush_tlb_others(cpumask, info); if (cpumask) @@ -592,8 +615,29 @@ void native_flush_tlb_others(const struct cpumask *cpumask, (void *)info, 1); return; } - smp_call_function_many(cpumask, flush_tlb_func_remote, + + /* + * A temporary cpumask is used in order to skip sending IPIs + * to CPUs in lazy TLB state, while keeping them in mm_cpumask(mm). + * If the allocation fails, simply IPI every CPU in mm_cpumask. + */ + if (!alloc_cpumask_var(&lazymask, GFP_ATOMIC)) { + smp_call_function_many(cpumask, flush_tlb_func_remote, (void *)info, 1); + return; + } + + cpumask_copy(lazymask, cpumask); + + for_each_cpu(cpu, lazymask) { + if (per_cpu(cpu_tlbstate.is_lazy, cpu)) + cpumask_clear_cpu(cpu, lazymask); + } + + smp_call_function_many(lazymask, flush_tlb_func_remote, + (void *)info, 1); + + free_cpumask_var(lazymask); } /* @@ -646,6 +690,68 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, put_cpu(); } +void tlb_flush_remove_tables_local(void *arg) +{ + struct mm_struct *mm = arg; + + if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm && + this_cpu_read(cpu_tlbstate.is_lazy)) { + /* + * We're in lazy mode. We need to at least flush our + * paging-structure cache to avoid speculatively reading + * garbage into our TLB. Since switching to init_mm is barely + * slower than a minimal flush, just switch to init_mm. + */ + switch_mm_irqs_off(NULL, &init_mm, NULL); + } +} + +static void mm_fill_lazy_tlb_cpu_mask(struct mm_struct *mm, + struct cpumask *lazy_cpus) +{ + int cpu; + + for_each_cpu(cpu, mm_cpumask(mm)) { + if (!per_cpu(cpu_tlbstate.is_lazy, cpu)) + cpumask_set_cpu(cpu, lazy_cpus); + } +} + +void tlb_flush_remove_tables(struct mm_struct *mm) +{ + int cpu = get_cpu(); + cpumask_var_t lazy_cpus; + + if (cpumask_any_but(mm_cpumask(mm), cpu) >= nr_cpu_ids) { + put_cpu(); + return; + } + + if (!zalloc_cpumask_var(&lazy_cpus, GFP_ATOMIC)) { + /* + * If the cpumask allocation fails, do a brute force flush + * on all the CPUs that have this mm loaded. + */ + smp_call_function_many(mm_cpumask(mm), + tlb_flush_remove_tables_local, (void *)mm, 1); + put_cpu(); + return; + } + + /* + * CPUs with !is_lazy either received a TLB flush IPI while the user + * pages in this address range were unmapped, or have context switched + * and reloaded %CR3 since then. + * + * Shootdown IPIs at page table freeing time only need to be sent to + * CPUs that may have out of date TLB contents. + */ + mm_fill_lazy_tlb_cpu_mask(mm, lazy_cpus); + smp_call_function_many(lazy_cpus, + tlb_flush_remove_tables_local, (void *)mm, 1); + free_cpumask_var(lazy_cpus); + put_cpu(); +} static void do_flush_tlb_all(void *info) { diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 55799873ebe5..8f6cc71e0848 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1441,8 +1441,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth) /* sub esp,STACK_SIZE */ EMIT2_off32(0x81, 0xEC, STACK_SIZE); - /* sub ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16); + /* sub ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12); /* xor ebx,ebx */ EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX)); @@ -1475,8 +1475,8 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) /* mov edx,dword ptr [ebp+off]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1])); - /* add ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16); + /* add ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12); /* mov ebx,dword ptr [ebp-12]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 563049c483a1..d4ec117c1142 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -22,7 +22,6 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | PCI_PROBE_MMCONF; -unsigned int pci_early_dump_regs; static int pci_bf_sort; int pci_routeirq; int noioapicquirk; @@ -599,9 +598,6 @@ char *__init pcibios_setup(char *str) pci_probe |= PCI_BIG_ROOT_WINDOW; return NULL; #endif - } else if (!strcmp(str, "earlydump")) { - pci_early_dump_regs = 1; - return NULL; } else if (!strcmp(str, "routeirq")) { pci_routeirq = 1; return NULL; diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index e5f753cbb1c3..f5fc953e5848 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -57,47 +57,3 @@ int early_pci_allowed(void) PCI_PROBE_CONF1; } -void early_dump_pci_device(u8 bus, u8 slot, u8 func) -{ - u32 value[256 / 4]; - int i; - - pr_info("pci 0000:%02x:%02x.%d config space:\n", bus, slot, func); - - for (i = 0; i < 256; i += 4) - value[i / 4] = read_pci_config(bus, slot, func, i); - - print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1, value, 256, false); -} - -void early_dump_pci_devices(void) -{ - unsigned bus, slot, func; - - if (!early_pci_allowed()) - return; - - for (bus = 0; bus < 256; bus++) { - for (slot = 0; slot < 32; slot++) { - for (func = 0; func < 8; func++) { - u32 class; - u8 type; - - class = read_pci_config(bus, slot, func, - PCI_CLASS_REVISION); - if (class == 0xffffffff) - continue; - - early_dump_pci_device(bus, slot, func); - - if (func == 0) { - type = read_pci_config_byte(bus, slot, - func, - PCI_HEADER_TYPE); - if (!(type & 0x80)) - break; - } - } - } - } -} diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 77873ce700ae..ee5d08f25ce4 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -417,7 +417,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; - if (sev_active()) + if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO) flags |= _PAGE_ENC; pfn = md->phys_addr >> PAGE_SHIFT; @@ -636,6 +636,8 @@ void efi_switch_mm(struct mm_struct *mm) #ifdef CONFIG_EFI_MIXED extern efi_status_t efi64_thunk(u32, ...); +static DEFINE_SPINLOCK(efi_runtime_lock); + #define runtime_service32(func) \ ({ \ u32 table = (u32)(unsigned long)efi.systab; \ @@ -657,17 +659,14 @@ extern efi_status_t efi64_thunk(u32, ...); #define efi_thunk(f, ...) \ ({ \ efi_status_t __s; \ - unsigned long __flags; \ u32 __func; \ \ - local_irq_save(__flags); \ arch_efi_call_virt_setup(); \ \ __func = runtime_service32(f); \ __s = efi64_thunk(__func, __VA_ARGS__); \ \ arch_efi_call_virt_teardown(); \ - local_irq_restore(__flags); \ \ __s; \ }) @@ -702,14 +701,17 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) { efi_status_t status; u32 phys_tm, phys_tc; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); phys_tc = virt_to_phys_or_null(tc); status = efi_thunk(get_time, phys_tm, phys_tc); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -719,13 +721,16 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm) { efi_status_t status; u32 phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(set_time, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -737,8 +742,10 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, { efi_status_t status; u32 phys_enabled, phys_pending, phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_enabled = virt_to_phys_or_null(enabled); phys_pending = virt_to_phys_or_null(pending); @@ -747,6 +754,7 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, status = efi_thunk(get_wakeup_time, phys_enabled, phys_pending, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -757,13 +765,16 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { efi_status_t status; u32 phys_tm; + unsigned long flags; spin_lock(&rtc_lock); + spin_lock_irqsave(&efi_runtime_lock, flags); phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(set_wakeup_time, enabled, phys_tm); + spin_unlock_irqrestore(&efi_runtime_lock, flags); spin_unlock(&rtc_lock); return status; @@ -781,6 +792,9 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, efi_status_t status; u32 phys_name, phys_vendor, phys_attr; u32 phys_data_size, phys_data; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_data_size = virt_to_phys_or_null(data_size); phys_vendor = virt_to_phys_or_null(vendor); @@ -791,6 +805,8 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, status = efi_thunk(get_variable, phys_name, phys_vendor, phys_attr, phys_data_size, phys_data); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -800,6 +816,34 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, { u32 phys_name, phys_vendor, phys_data; efi_status_t status; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); + + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); + phys_vendor = virt_to_phys_or_null(vendor); + phys_data = virt_to_phys_or_null_size(data, data_size); + + /* If data_size is > sizeof(u32) we've got problems */ + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); + + return status; +} + +static efi_status_t +efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, + void *data) +{ + u32 phys_name, phys_vendor, phys_data; + efi_status_t status; + unsigned long flags; + + if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) + return EFI_NOT_READY; phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); phys_vendor = virt_to_phys_or_null(vendor); @@ -809,6 +853,8 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, status = efi_thunk(set_variable, phys_name, phys_vendor, attr, data_size, phys_data); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -819,6 +865,9 @@ efi_thunk_get_next_variable(unsigned long *name_size, { efi_status_t status; u32 phys_name_size, phys_name, phys_vendor; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_name_size = virt_to_phys_or_null(name_size); phys_vendor = virt_to_phys_or_null(vendor); @@ -827,6 +876,8 @@ efi_thunk_get_next_variable(unsigned long *name_size, status = efi_thunk(get_next_variable, phys_name_size, phys_name, phys_vendor); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -835,10 +886,15 @@ efi_thunk_get_next_high_mono_count(u32 *count) { efi_status_t status; u32 phys_count; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_count = virt_to_phys_or_null(count); status = efi_thunk(get_next_high_mono_count, phys_count); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -847,10 +903,15 @@ efi_thunk_reset_system(int reset_type, efi_status_t status, unsigned long data_size, efi_char16_t *data) { u32 phys_data; + unsigned long flags; + + spin_lock_irqsave(&efi_runtime_lock, flags); phys_data = virt_to_phys_or_null_size(data, data_size); efi_thunk(reset_system, reset_type, status, data_size, phys_data); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); } static efi_status_t @@ -872,10 +933,40 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space, { efi_status_t status; u32 phys_storage, phys_remaining, phys_max; + unsigned long flags; + + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + spin_lock_irqsave(&efi_runtime_lock, flags); + + phys_storage = virt_to_phys_or_null(storage_space); + phys_remaining = virt_to_phys_or_null(remaining_space); + phys_max = virt_to_phys_or_null(max_variable_size); + + status = efi_thunk(query_variable_info, attr, phys_storage, + phys_remaining, phys_max); + + spin_unlock_irqrestore(&efi_runtime_lock, flags); + + return status; +} + +static efi_status_t +efi_thunk_query_variable_info_nonblocking(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) +{ + efi_status_t status; + u32 phys_storage, phys_remaining, phys_max; + unsigned long flags; if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; + if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) + return EFI_NOT_READY; + phys_storage = virt_to_phys_or_null(storage_space); phys_remaining = virt_to_phys_or_null(remaining_space); phys_max = virt_to_phys_or_null(max_variable_size); @@ -883,6 +974,8 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space, status = efi_thunk(query_variable_info, attr, phys_storage, phys_remaining, phys_max); + spin_unlock_irqrestore(&efi_runtime_lock, flags); + return status; } @@ -908,9 +1001,11 @@ void efi_thunk_runtime_setup(void) efi.get_variable = efi_thunk_get_variable; efi.get_next_variable = efi_thunk_get_next_variable; efi.set_variable = efi_thunk_set_variable; + efi.set_variable_nonblocking = efi_thunk_set_variable_nonblocking; efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count; efi.reset_system = efi_thunk_reset_system; efi.query_variable_info = efi_thunk_query_variable_info; + efi.query_variable_info_nonblocking = efi_thunk_query_variable_info_nonblocking; efi.update_capsule = efi_thunk_update_capsule; efi.query_capsule_caps = efi_thunk_query_capsule_caps; } diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 36c1f8b9f7e0..844d31cb8a0c 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -105,12 +105,11 @@ early_param("efi_no_storage_paranoia", setup_storage_paranoia); */ void efi_delete_dummy_variable(void) { - efi.set_variable((efi_char16_t *)efi_dummy_name, - &EFI_DUMMY_GUID, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, - 0, NULL); + efi.set_variable_nonblocking((efi_char16_t *)efi_dummy_name, + &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL); } /* @@ -249,7 +248,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) int num_entries; void *new; - if (efi_mem_desc_lookup(addr, &md)) { + if (efi_mem_desc_lookup(addr, &md) || + md.type != EFI_BOOT_SERVICES_DATA) { pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr); return; } diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile index fa021dfab088..5cf886c867c2 100644 --- a/arch/x86/platform/intel-mid/Makefile +++ b/arch/x86/platform/intel-mid/Makefile @@ -1,4 +1,4 @@ -obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o mrfld.o pwr.o +obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o pwr.o # SFI specific code ifdef CONFIG_X86_INTEL_MID diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c index 4f5fa65a1011..2acd6be13375 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c @@ -18,6 +18,7 @@ #include <asm/intel-mid.h> #include <asm/intel_scu_ipc.h> #include <asm/io_apic.h> +#include <asm/hw_irq.h> #define TANGIER_EXT_TIMER0_MSI 12 diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 2ebdf31d9996..56f66eafb94f 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -36,8 +36,6 @@ #include <asm/apb_timer.h> #include <asm/reboot.h> -#include "intel_mid_weak_decls.h" - /* * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock, * cmdline option x86_intel_mid_timer can be used to override the configuration @@ -61,10 +59,6 @@ enum intel_mid_timer_options intel_mid_timer_options; -/* intel_mid_ops to store sub arch ops */ -static struct intel_mid_ops *intel_mid_ops; -/* getter function for sub arch ops*/ -static void *(*get_intel_mid_ops[])(void) = INTEL_MID_OPS_INIT; enum intel_mid_cpu_type __intel_mid_cpu_chip; EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip); @@ -82,11 +76,6 @@ static void intel_mid_reboot(void) intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0); } -static unsigned long __init intel_mid_calibrate_tsc(void) -{ - return 0; -} - static void __init intel_mid_setup_bp_timer(void) { apbt_time_init(); @@ -133,6 +122,7 @@ static void intel_mid_arch_setup(void) case 0x3C: case 0x4A: __intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_TANGIER; + x86_platform.legacy.rtc = 1; break; case 0x27: default: @@ -140,17 +130,7 @@ static void intel_mid_arch_setup(void) break; } - if (__intel_mid_cpu_chip < MAX_CPU_OPS(get_intel_mid_ops)) - intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip](); - else { - intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL](); - pr_info("ARCH: Unknown SoC, assuming Penwell!\n"); - } - out: - if (intel_mid_ops->arch_setup) - intel_mid_ops->arch_setup(); - /* * Intel MID platforms are using explicitly defined regulators. * @@ -191,7 +171,6 @@ void __init x86_intel_mid_early_setup(void) x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock; - x86_platform.calibrate_tsc = intel_mid_calibrate_tsc; x86_platform.get_nmi_reason = intel_mid_get_nmi_reason; x86_init.pci.arch_init = intel_mid_pci_init; diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h deleted file mode 100644 index 3c1c3866d82b..000000000000 --- a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * intel_mid_weak_decls.h: Weak declarations of intel-mid.c - * - * (C) Copyright 2013 Intel Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ - - -/* For every CPU addition a new get_<cpuname>_ops interface needs - * to be added. - */ -extern void *get_penwell_ops(void); -extern void *get_cloverview_ops(void); -extern void *get_tangier_ops(void); diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c deleted file mode 100644 index e42978d4deaf..000000000000 --- a/arch/x86/platform/intel-mid/mfld.c +++ /dev/null @@ -1,70 +0,0 @@ -/* - * mfld.c: Intel Medfield platform setup code - * - * (C) Copyright 2013 Intel Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ - -#include <linux/init.h> - -#include <asm/apic.h> -#include <asm/intel-mid.h> -#include <asm/intel_mid_vrtc.h> - -#include "intel_mid_weak_decls.h" - -static unsigned long __init mfld_calibrate_tsc(void) -{ - unsigned long fast_calibrate; - u32 lo, hi, ratio, fsb; - - rdmsr(MSR_IA32_PERF_STATUS, lo, hi); - pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi); - ratio = (hi >> 8) & 0x1f; - pr_debug("ratio is %d\n", ratio); - if (!ratio) { - pr_err("read a zero ratio, should be incorrect!\n"); - pr_err("force tsc ratio to 16 ...\n"); - ratio = 16; - } - rdmsr(MSR_FSB_FREQ, lo, hi); - if ((lo & 0x7) == 0x7) - fsb = FSB_FREQ_83SKU; - else - fsb = FSB_FREQ_100SKU; - fast_calibrate = ratio * fsb; - pr_debug("read penwell tsc %lu khz\n", fast_calibrate); - lapic_timer_frequency = fsb * 1000 / HZ; - - /* - * TSC on Intel Atom SoCs is reliable and of known frequency. - * See tsc_msr.c for details. - */ - setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); - setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); - - return fast_calibrate; -} - -static void __init penwell_arch_setup(void) -{ - x86_platform.calibrate_tsc = mfld_calibrate_tsc; -} - -static struct intel_mid_ops penwell_ops = { - .arch_setup = penwell_arch_setup, -}; - -void *get_penwell_ops(void) -{ - return &penwell_ops; -} - -void *get_cloverview_ops(void) -{ - return &penwell_ops; -} diff --git a/arch/x86/platform/intel-mid/mrfld.c b/arch/x86/platform/intel-mid/mrfld.c deleted file mode 100644 index ae7bdeb0e507..000000000000 --- a/arch/x86/platform/intel-mid/mrfld.c +++ /dev/null @@ -1,105 +0,0 @@ -/* - * Intel Merrifield platform specific setup code - * - * (C) Copyright 2013 Intel Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ - -#include <linux/init.h> - -#include <asm/apic.h> -#include <asm/intel-mid.h> - -#include "intel_mid_weak_decls.h" - -static unsigned long __init tangier_calibrate_tsc(void) -{ - unsigned long fast_calibrate; - u32 lo, hi, ratio, fsb, bus_freq; - - /* *********************** */ - /* Compute TSC:Ratio * FSB */ - /* *********************** */ - - /* Compute Ratio */ - rdmsr(MSR_PLATFORM_INFO, lo, hi); - pr_debug("IA32 PLATFORM_INFO is 0x%x : %x\n", hi, lo); - - ratio = (lo >> 8) & 0xFF; - pr_debug("ratio is %d\n", ratio); - if (!ratio) { - pr_err("Read a zero ratio, force tsc ratio to 4 ...\n"); - ratio = 4; - } - - /* Compute FSB */ - rdmsr(MSR_FSB_FREQ, lo, hi); - pr_debug("Actual FSB frequency detected by SOC 0x%x : %x\n", - hi, lo); - - bus_freq = lo & 0x7; - pr_debug("bus_freq = 0x%x\n", bus_freq); - - if (bus_freq == 0) - fsb = FSB_FREQ_100SKU; - else if (bus_freq == 1) - fsb = FSB_FREQ_100SKU; - else if (bus_freq == 2) - fsb = FSB_FREQ_133SKU; - else if (bus_freq == 3) - fsb = FSB_FREQ_167SKU; - else if (bus_freq == 4) - fsb = FSB_FREQ_83SKU; - else if (bus_freq == 5) - fsb = FSB_FREQ_400SKU; - else if (bus_freq == 6) - fsb = FSB_FREQ_267SKU; - else if (bus_freq == 7) - fsb = FSB_FREQ_333SKU; - else { - BUG(); - pr_err("Invalid bus_freq! Setting to minimal value!\n"); - fsb = FSB_FREQ_100SKU; - } - - /* TSC = FSB Freq * Resolved HFM Ratio */ - fast_calibrate = ratio * fsb; - pr_debug("calculate tangier tsc %lu KHz\n", fast_calibrate); - - /* ************************************ */ - /* Calculate Local APIC Timer Frequency */ - /* ************************************ */ - lapic_timer_frequency = (fsb * 1000) / HZ; - - pr_debug("Setting lapic_timer_frequency = %d\n", - lapic_timer_frequency); - - /* - * TSC on Intel Atom SoCs is reliable and of known frequency. - * See tsc_msr.c for details. - */ - setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); - setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); - - return fast_calibrate; -} - -static void __init tangier_arch_setup(void) -{ - x86_platform.calibrate_tsc = tangier_calibrate_tsc; - x86_platform.legacy.rtc = 1; -} - -/* tangier arch ops */ -static struct intel_mid_ops tangier_ops = { - .arch_setup = tangier_arch_setup, -}; - -void *get_tangier_ops(void) -{ - return &tangier_ops; -} diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index 7c3077e58fa0..f0e920fb98ad 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -311,10 +311,8 @@ static int __init add_xo1_platform_devices(void) return PTR_ERR(pdev); pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_ERR_OR_ZERO(pdev); } static int olpc_xo1_ec_probe(struct platform_device *pdev) diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index ca446da48fd2..a4130b84d1ff 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1285,6 +1285,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs) struct msg_desc msgdesc; ack_APIC_irq(); + kvm_set_cpu_l1tf_flush_l1d(); time_start = get_cycles(); bcp = &per_cpu(bau_control, smp_processor_id()); @@ -1607,8 +1608,6 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr, *tunables[cnt].tunp = val; continue; } - if (q == p) - break; } return 0; } diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 67ccf64c8bd8..f8e3b668d20b 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -233,29 +233,35 @@ struct restore_data_record { */ static int get_e820_md5(struct e820_table *table, void *buf) { - struct scatterlist sg; - struct crypto_ahash *tfm; + struct crypto_shash *tfm; + struct shash_desc *desc; int size; int ret = 0; - tfm = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC); + tfm = crypto_alloc_shash("md5", 0, 0); if (IS_ERR(tfm)) return -ENOMEM; - { - AHASH_REQUEST_ON_STACK(req, tfm); - size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries; - ahash_request_set_tfm(req, tfm); - sg_init_one(&sg, (u8 *)table, size); - ahash_request_set_callback(req, 0, NULL, NULL); - ahash_request_set_crypt(req, &sg, buf, size); - - if (crypto_ahash_digest(req)) - ret = -EINVAL; - ahash_request_zero(req); + desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), + GFP_KERNEL); + if (!desc) { + ret = -ENOMEM; + goto free_tfm; } - crypto_free_ahash(tfm); + desc->tfm = tfm; + desc->flags = 0; + + size = offsetof(struct e820_table, entries) + + sizeof(struct e820_entry) * table->nr_entries; + + if (crypto_shash_digest(desc, (u8 *)table, size, buf)) + ret = -EINVAL; + + kzfree(desc); + +free_tfm: + crypto_free_shash(tfm); return ret; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index ce8da3a0412c..fd369a6e9ff8 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -137,7 +137,7 @@ ENTRY(restore_registers) /* Saved in save_processor_state. */ lgdt saved_context_gdt_desc(%rax) - xorq %rax, %rax + xorl %eax, %eax /* tell the hibernation core that we've just restored the memory */ movq %rax, in_suspend(%rip) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 81a8e33115ad..3cf302b26332 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -28,9 +28,8 @@ $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE targets += kexec-purgatory.c -CMD_BIN2C = $(objtree)/scripts/basic/bin2c quiet_cmd_bin2c = BIN2C $@ - cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@ + cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@ $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE $(call if_changed,bin2c) diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 220e97841e49..3a6c8ebc8032 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -67,6 +67,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "__tracedata_(start|end)|" "__(start|stop)_notes|" "__end_rodata|" + "__end_rodata_aligned|" "__initramfs_start|" "(jiffies|jiffies_64)|" #if ELF_BITS == 64 diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 9d529f22fd9d..f518b4744ff8 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -1,13 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -mainmenu "User Mode Linux/$(SUBARCH) $(KERNELVERSION) Kernel Configuration" - -comment "Compiler: $(CC_VERSION_TEXT)" - -source "scripts/Kconfig.include" - -source "arch/um/Kconfig.common" - -menu "UML-specific options" menu "Host processor type and features" @@ -66,9 +57,3 @@ config ARCH_REUSE_HOST_VSYSCALL_AREA config GENERIC_HWEIGHT def_bool y - -source "arch/um/Kconfig.um" - -endmenu - -source "arch/um/Kconfig.rest" diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 744afdc18cf3..56c44d865f7b 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -16,7 +16,7 @@ static int __init gate_vma_init(void) if (!FIXADDR_USER_START) return 0; - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/x86/um/vdso/.gitignore b/arch/x86/um/vdso/.gitignore index 9cac6d072199..f8b69d84238e 100644 --- a/arch/x86/um/vdso/.gitignore +++ b/arch/x86/um/vdso/.gitignore @@ -1,2 +1 @@ -vdso-syms.lds vdso.lds diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index b2d6967262b2..822ccdba93ad 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -53,22 +53,6 @@ $(vobjs): KBUILD_CFLAGS += $(CFL) CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage -targets += vdso-syms.lds -extra-$(VDSO64-y) += vdso-syms.lds - -# -# Match symbols in the DSO that look like VDSO*; produce a file of constants. -# -sed-vdsosym := -e 's/^00*/0/' \ - -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' -quiet_cmd_vdsosym = VDSOSYM $@ -define cmd_vdsosym - $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ -endef - -$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE - $(call if_changed,vdsosym) - # # The DSO images are built using a special linker script. # diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 3b5318505c69..2eeddd814653 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -3,6 +3,7 @@ #endif #include <linux/cpu.h> #include <linux/kexec.h> +#include <linux/slab.h> #include <xen/features.h> #include <xen/page.h> diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 439a94bf89ad..ee3b00c7acda 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -119,6 +119,27 @@ static void __init xen_banner(void) version >> 16, version & 0xffff, extra.extraversion, xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } + +static void __init xen_pv_init_platform(void) +{ + set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info); + HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); + + /* xen clock uses per-cpu vcpu_info, need to init it for boot cpu */ + xen_vcpu_info_reset(0); + + /* pvclock is in shared info area */ + xen_init_time_ops(); +} + +static void __init xen_pv_guest_late_init(void) +{ +#ifndef CONFIG_SMP + /* Setup shared vcpu info for non-smp configurations */ + xen_setup_vcpu_info_placement(); +#endif +} + /* Check if running on Xen version (major, minor) or later */ bool xen_running_on_version_or_later(unsigned int major, unsigned int minor) @@ -947,34 +968,8 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high) xen_write_msr_safe(msr, low, high); } -void xen_setup_shared_info(void) -{ - set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info); - - HYPERVISOR_shared_info = - (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); - - xen_setup_mfn_list_list(); - - if (system_state == SYSTEM_BOOTING) { -#ifndef CONFIG_SMP - /* - * In UP this is as good a place as any to set up shared info. - * Limit this to boot only, at restore vcpu setup is done via - * xen_vcpu_restore(). - */ - xen_setup_vcpu_info_placement(); -#endif - /* - * Now that shared info is set up we can start using routines - * that point to pvclock area. - */ - xen_init_time_ops(); - } -} - /* This is called once we have the cpu_possible_mask */ -void __ref xen_setup_vcpu_info_placement(void) +void __init xen_setup_vcpu_info_placement(void) { int cpu; @@ -1228,6 +1223,8 @@ asmlinkage __visible void __init xen_start_kernel(void) x86_init.irqs.intr_mode_init = x86_init_noop; x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; + x86_init.hyper.init_platform = xen_pv_init_platform; + x86_init.hyper.guest_late_init = xen_pv_guest_late_init; /* * Set up some pagetable state before starting to set any ptes. @@ -1259,6 +1256,9 @@ asmlinkage __visible void __init xen_start_kernel(void) get_cpu_cap(&boot_cpu_data); x86_configure_nx(); + /* Determine virtual and physical address sizes */ + get_cpu_address_sizes(&boot_cpu_data); + /* Let's presume PV guests always boot on vCPU with id 0. */ per_cpu(xen_vcpu_id, 0) = 0; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 2c30cabfda90..52206ad81e4b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1230,8 +1230,7 @@ static void __init xen_pagetable_p2m_free(void) * We roundup to the PMD, which means that if anybody at this stage is * using the __ka address of xen_start_info or * xen_start_info->shared_info they are in going to crash. Fortunatly - * we have already revectored in xen_setup_kernel_pagetable and in - * xen_setup_shared_info. + * we have already revectored in xen_setup_kernel_pagetable. */ size = roundup(size, PMD_SIZE); @@ -1292,8 +1291,7 @@ static void __init xen_pagetable_init(void) /* Remap memory freed due to conflicts with E820 map */ xen_remap_memory(); - - xen_setup_shared_info(); + xen_setup_mfn_list_list(); } static void xen_write_cr2(unsigned long cr2) { diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index dc502ca8263e..2bce7958ce8b 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -80,9 +80,9 @@ void xen_mc_flush(void) and just do the call directly. */ mc = &b->entries[0]; - mc->result = privcmd_call(mc->op, - mc->args[0], mc->args[1], mc->args[2], - mc->args[3], mc->args[4]); + mc->result = xen_single_call(mc->op, mc->args[0], mc->args[1], + mc->args[2], mc->args[3], + mc->args[4]); ret = mc->result < 0; break; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index cd97a62394e7..973f10e05211 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -130,6 +130,10 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen); void __init xen_init_spinlocks(void) { + /* Don't need to use pvqspinlock code if there is only 1 vCPU. */ + if (num_possible_cpus() == 1) + xen_pvspin = false; + if (!xen_pvspin) { printk(KERN_DEBUG "xen: PV spinlocks disabled\n"); return; diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c index a2e0f110af56..8303b58c79a9 100644 --- a/arch/x86/xen/suspend_pv.c +++ b/arch/x86/xen/suspend_pv.c @@ -27,8 +27,9 @@ void xen_pv_pre_suspend(void) void xen_pv_post_suspend(int suspend_cancelled) { xen_build_mfn_list_list(); - - xen_setup_shared_info(); + set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info); + HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); + xen_setup_mfn_list_list(); if (suspend_cancelled) { xen_start_info->store_mfn = diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index e0f1bcf01d63..c84f1e039d84 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -31,6 +31,8 @@ /* Xen may fire a timer up to this many ns early */ #define TIMER_SLOP 100000 +static u64 xen_sched_clock_offset __read_mostly; + /* Get the TSC speed from Xen */ static unsigned long xen_tsc_khz(void) { @@ -40,7 +42,7 @@ static unsigned long xen_tsc_khz(void) return pvclock_tsc_khz(info); } -u64 xen_clocksource_read(void) +static u64 xen_clocksource_read(void) { struct pvclock_vcpu_time_info *src; u64 ret; @@ -57,6 +59,11 @@ static u64 xen_clocksource_get_cycles(struct clocksource *cs) return xen_clocksource_read(); } +static u64 xen_sched_clock(void) +{ + return xen_clocksource_read() - xen_sched_clock_offset; +} + static void xen_read_wallclock(struct timespec64 *ts) { struct shared_info *s = HYPERVISOR_shared_info; @@ -367,7 +374,7 @@ void xen_timer_resume(void) } static const struct pv_time_ops xen_time_ops __initconst = { - .sched_clock = xen_clocksource_read, + .sched_clock = xen_sched_clock, .steal_clock = xen_steal_clock, }; @@ -503,8 +510,9 @@ static void __init xen_time_init(void) pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); } -void __ref xen_init_time_ops(void) +void __init xen_init_time_ops(void) { + xen_sched_clock_offset = xen_clocksource_read(); pv_time_ops = xen_time_ops; x86_init.timers.timer_init = xen_time_init; @@ -542,11 +550,11 @@ void __init xen_hvm_init_time_ops(void) return; if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { - printk(KERN_INFO "Xen doesn't support pvclock on HVM," - "disable pv timer\n"); + pr_info("Xen doesn't support pvclock on HVM, disable pv timer"); return; } + xen_sched_clock_offset = xen_clocksource_read(); pv_time_ops = xen_time_ops; x86_init.timers.setup_percpu_clockev = xen_time_init; x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents; diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 3b34745d0a52..e78684597f57 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -31,7 +31,6 @@ extern struct shared_info xen_dummy_shared_info; extern struct shared_info *HYPERVISOR_shared_info; void xen_setup_mfn_list_list(void); -void xen_setup_shared_info(void); void xen_build_mfn_list_list(void); void xen_setup_machphys_mapping(void); void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); @@ -68,12 +67,11 @@ void xen_init_irq_ops(void); void xen_setup_timer(int cpu); void xen_setup_runstate_info(int cpu); void xen_teardown_timer(int cpu); -u64 xen_clocksource_read(void); void xen_setup_cpu_clockevents(void); void xen_save_time_memory_area(void); void xen_restore_time_memory_area(void); -void __ref xen_init_time_ops(void); -void __init xen_hvm_init_time_ops(void); +void xen_init_time_ops(void); +void xen_hvm_init_time_ops(void); irqreturn_t xen_debug_interrupt(int irq, void *dev_id); diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index d575e8701955..801491e98890 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -60,9 +60,6 @@ config HZ int default 100 -source "init/Kconfig" -source "kernel/Kconfig.freezer" - config LOCKDEP_SUPPORT def_bool y @@ -176,8 +173,6 @@ config XTENSA_UNALIGNED_USER Say Y here to enable unaligned memory access in user space. -source "kernel/Kconfig.preempt" - config HAVE_SMP bool "System Supports SMP (MX)" depends on XTENSA_VARIANT_CUSTOM @@ -491,8 +486,6 @@ config SIMDISK1_FILENAME Another simulated disk in a host file for a buildroot-independent storage. -source "mm/Kconfig" - config FORCE_MAX_ZONEORDER int "Maximum zone order" default "11" @@ -567,30 +560,8 @@ config XTFPGA_LCD_8BIT_ACCESS endmenu -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - menu "Power management options" source "kernel/power/Kconfig" endmenu - -source "net/Kconfig" - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "arch/xtensa/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - - diff --git a/arch/xtensa/Kconfig.debug b/arch/xtensa/Kconfig.debug index f64c14adadb3..39de98e20018 100644 --- a/arch/xtensa/Kconfig.debug +++ b/arch/xtensa/Kconfig.debug @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -menu "Kernel hacking" - -source "lib/Kconfig.debug" config DEBUG_TLB_SANITY bool "Debug TLB sanity" @@ -34,5 +31,3 @@ config S32C1I_SELFTEST It is easy to make wrong hardware configuration, this test should catch it early. Say 'N' on stable hardware. - -endmenu diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile index 53e4178711e6..dc9e0ba7122c 100644 --- a/arch/xtensa/boot/Makefile +++ b/arch/xtensa/boot/Makefile @@ -30,8 +30,7 @@ Image: boot-elf zImage: boot-redboot uImage: $(obj)/uImage -boot-elf boot-redboot: $(addprefix $(obj)/,$(subdir-y)) \ - $(addprefix $(obj)/,$(host-progs)) +boot-elf boot-redboot: $(addprefix $(obj)/,$(subdir-y)) $(Q)$(MAKE) $(build)=$(obj)/$@ $(MAKECMDGOALS) OBJCOPYFLAGS = --strip-all -R .comment -R .note.gnu.build-id -O binary diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index e7a23f2a519a..7de0149e1cf7 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -197,107 +197,9 @@ ATOMIC_OPS(xor) #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -/** - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) - -/** - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc(v) atomic_add(1,(v)) - -/** - * atomic_inc - increment atomic variable - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1. - */ -#define atomic_inc_return(v) atomic_add_return(1,(v)) - -/** - * atomic_dec - decrement atomic variable - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec(v) atomic_sub(1,(v)) - -/** - * atomic_dec_return - decrement atomic variable - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1. - */ -#define atomic_dec_return(v) atomic_sub_return(1,(v)) - -/** - * atomic_dec_and_test - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0) - -/** - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0) - -/** - * atomic_add_negative - add and test if negative - * @v: pointer of type atomic_t - * @i: integer value to add - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0) - #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -/** - * __atomic_add_unless - add unless the number is a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c; -} - #endif /* __KERNEL__ */ #endif /* _XTENSA_ATOMIC_H */ diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h index dbe3053b284a..9f119c1ca0b5 100644 --- a/arch/xtensa/include/asm/hw_breakpoint.h +++ b/arch/xtensa/include/asm/hw_breakpoint.h @@ -30,13 +30,16 @@ struct arch_hw_breakpoint { u16 type; }; +struct perf_event_attr; struct perf_event; struct pt_regs; struct task_struct; int hw_breakpoint_slots(int type); -int arch_check_bp_in_kernelspace(struct perf_event *bp); -int arch_validate_hwbkpt_settings(struct perf_event *bp); +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 75a07b8119a9..1de07a7f7680 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -116,4 +116,7 @@ #define SO_ZEROCOPY 60 +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + #endif /* _XTENSA_SOCKET_H */ diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c index b35656ab7dbd..c2e387c19cda 100644 --- a/arch/xtensa/kernel/hw_breakpoint.c +++ b/arch/xtensa/kernel/hw_breakpoint.c @@ -33,14 +33,13 @@ int hw_breakpoint_slots(int type) } } -int arch_check_bp_in_kernelspace(struct perf_event *bp) +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned int len; unsigned long va; - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - va = info->address; - len = bp->attr.bp_len; + va = hw->address; + len = hw->len; return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -48,50 +47,41 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) /* * Construct an arch_hw_breakpoint from a perf_event. */ -static int arch_build_bp_info(struct perf_event *bp) +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* Type */ - switch (bp->attr.bp_type) { + switch (attr->bp_type) { case HW_BREAKPOINT_X: - info->type = XTENSA_BREAKPOINT_EXECUTE; + hw->type = XTENSA_BREAKPOINT_EXECUTE; break; case HW_BREAKPOINT_R: - info->type = XTENSA_BREAKPOINT_LOAD; + hw->type = XTENSA_BREAKPOINT_LOAD; break; case HW_BREAKPOINT_W: - info->type = XTENSA_BREAKPOINT_STORE; + hw->type = XTENSA_BREAKPOINT_STORE; break; case HW_BREAKPOINT_RW: - info->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE; + hw->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE; break; default: return -EINVAL; } /* Len */ - info->len = bp->attr.bp_len; - if (info->len < 1 || info->len > 64 || !is_power_of_2(info->len)) + hw->len = attr->bp_len; + if (hw->len < 1 || hw->len > 64 || !is_power_of_2(hw->len)) return -EINVAL; /* Address */ - info->address = bp->attr.bp_addr; - if (info->address & (info->len - 1)) + hw->address = attr->bp_addr; + if (hw->address & (hw->len - 1)) return -EINVAL; return 0; } -int arch_validate_hwbkpt_settings(struct perf_event *bp) -{ - int ret; - - /* Build the arch_hw_breakpoint. */ - ret = arch_build_bp_info(bp); - return ret; -} - int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data) { diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 392b4a80ebc2..a02dc563d290 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -137,7 +137,7 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size, if (gfpflags_allow_blocking(flag)) page = dma_alloc_from_contiguous(dev, count, get_order(size), - flag); + flag & __GFP_NOWARN); if (!page) page = alloc_pages(flag, get_order(size)); diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index c111a833205a..2ab0e0dcd166 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -42,7 +42,7 @@ void do_page_fault(struct pt_regs *regs) int code; int is_write, is_exec; - int fault; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; code = SEGV_MAPERR; |