diff options
169 files changed, 2744 insertions, 1363 deletions
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 4710e4afef19..d603fa078235 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -718,8 +718,21 @@ generates appropriate diffstats by default.) See more details on the proper patch format in the following references. +15) Explicit In-Reply-To headers +-------------------------------- + +It can be helpful to manually add In-Reply-To: headers to a patch +(e.g., when using "git send email") to associate the patch with +previous relevant discussion, e.g. to link a bug fix to the email with +the bug report. However, for a multi-patch series, it is generally +best to avoid using In-Reply-To: to link to older versions of the +series. This way multiple versions of the patch don't become an +unmanageable forest of references in email clients. If a link is +helpful, you can use the https://lkml.kernel.org/ redirector (e.g., in +the cover email text) to link to an earlier version of the patch series. + -15) Sending "git pull" requests +16) Sending "git pull" requests ------------------------------- If you have a series of patches, it may be most convenient to have the diff --git a/Documentation/dontdiff b/Documentation/dontdiff index 9de9813d0ec5..8ea834f6b289 100644 --- a/Documentation/dontdiff +++ b/Documentation/dontdiff @@ -165,7 +165,6 @@ mach-types.h machtypes.h map map_hugetlb -media mconf miboot* mk_elfconfig diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt index aba85b39a400..2d485dea8cec 100644 --- a/Documentation/email-clients.txt +++ b/Documentation/email-clients.txt @@ -176,11 +176,47 @@ To use 'vim' with mutt: if you want to include the patch inline. (a)ttach works fine without "set paste". +You can also generate patches with 'git format-patch' and then use Mutt +to send them: + $ mutt -H 0001-some-bug-fix.patch + Config options: It should work with default settings. However, it's a good idea to set the "send_charset" to: set send_charset="us-ascii:utf-8" +Mutt is highly customizable. Here is a minimum configuration to start +using Mutt to send patches through Gmail: + +# .muttrc +# ================ IMAP ==================== +set imap_user = 'yourusername@gmail.com' +set imap_pass = 'yourpassword' +set spoolfile = imaps://imap.gmail.com/INBOX +set folder = imaps://imap.gmail.com/ +set record="imaps://imap.gmail.com/[Gmail]/Sent Mail" +set postponed="imaps://imap.gmail.com/[Gmail]/Drafts" +set mbox="imaps://imap.gmail.com/[Gmail]/All Mail" + +# ================ SMTP ==================== +set smtp_url = "smtp://username@smtp.gmail.com:587/" +set smtp_pass = $imap_pass +set ssl_force_tls = yes # Require encrypted connection + +# ================ Composition ==================== +set editor = `echo \$EDITOR` +set edit_headers = yes # See the headers when editing +set charset = UTF-8 # value of $LANG; also fallback for send_charset +# Sender, email address, and sign-off line must match +unset use_domain # because joe@localhost is just embarrassing +set realname = "YOUR NAME" +set from = "username@gmail.com" +set use_from = yes + +The Mutt docs have lots more information: + http://dev.mutt.org/trac/wiki/UseCases/Gmail + http://dev.mutt.org/doc/manual.html + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Pine (TUI) diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index 6db0e5d1da07..28091457b71a 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -1,4 +1,5 @@ -Written by: Neil Brown <neilb@suse.de> +Written by: Neil Brown +Please see MAINTAINERS file for where to send questions. Overlay Filesystem ================== diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt index 4636b94518da..05fd83bb3596 100644 --- a/Documentation/networking/can.txt +++ b/Documentation/networking/can.txt @@ -681,7 +681,7 @@ solution for a couple of reasons: addr.can_family = AF_CAN; addr.can_ifindex = ifr.ifr_ifindex; - connect(s, (struct sockaddr *)&addr, sizeof(addr)) + connect(s, (struct sockaddr *)&addr, sizeof(addr)); (..) diff --git a/MAINTAINERS b/MAINTAINERS index 35fe7ae0492e..ecc43c255eb8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2210,6 +2210,7 @@ F: drivers/leds/leds-blinkm.c BLOCK LAYER M: Jens Axboe <axboe@kernel.dk> +L: linux-block@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: block/ @@ -5505,7 +5506,8 @@ S: Supported F: drivers/idle/intel_idle.c INTEL PSTATE DRIVER -M: Kristen Carlson Accardi <kristen@linux.intel.com> +M: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> +M: Len Brown <lenb@kernel.org> L: linux-pm@vger.kernel.org S: Supported F: drivers/cpufreq/intel_pstate.c diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 851fe11c6069..9ac16a482ff1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -27,6 +27,7 @@ config ARM64 select CPU_PM if (SUSPEND || CPU_IDLE) select DCACHE_WORD_ACCESS select EDAC_SUPPORT + select FRAME_POINTER select GENERIC_ALLOCATOR select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index c24d6adc0420..04fb73b973f1 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -2,10 +2,6 @@ menu "Kernel hacking" source "lib/Kconfig.debug" -config FRAME_POINTER - bool - default y - config ARM64_PTDUMP bool "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 2f71f9cdd39c..bdd7aa358d2a 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -224,3 +224,4 @@ CONFIG_CRYPTO_GHASH_ARM64_CE=y CONFIG_CRYPTO_AES_ARM64_CE_CCM=y CONFIG_CRYPTO_AES_ARM64_CE_BLK=y CONFIG_CRYPTO_AES_ARM64_NEON_BLK=y +CONFIG_CRYPTO_CRC32_ARM64=y diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index 74d0b8eb0799..f61c84f6ba02 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -233,7 +233,7 @@ __CMPXCHG_CASE( , , mb_8, dmb ish, , l, "memory") #undef __CMPXCHG_CASE #define __CMPXCHG_DBL(name, mb, rel, cl) \ -__LL_SC_INLINE int \ +__LL_SC_INLINE long \ __LL_SC_PREFIX(__cmpxchg_double##name(unsigned long old1, \ unsigned long old2, \ unsigned long new1, \ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index 1fce7908e690..197e06afbf71 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -387,7 +387,7 @@ __CMPXCHG_CASE(x, , mb_8, al, "memory") #define __LL_SC_CMPXCHG_DBL(op) __LL_SC_CALL(__cmpxchg_double##op) #define __CMPXCHG_DBL(name, mb, cl...) \ -static inline int __cmpxchg_double##name(unsigned long old1, \ +static inline long __cmpxchg_double##name(unsigned long old1, \ unsigned long old2, \ unsigned long new1, \ unsigned long new2, \ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index f3acf421ded4..9819a9426b69 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -80,6 +80,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) +#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 0cd7b5947dfc..2d4ca4bb0dd3 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -32,7 +32,7 @@ #ifndef __ASSEMBLY__ #include <linux/psci.h> -#include <asm/types.h> +#include <linux/types.h> #include <asm/ptrace.h> #define __KVM_HAVE_GUEST_DEBUG diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 52f0d7a5a1c2..c8cf89223b5a 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -696,7 +696,7 @@ static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap) } /* Check if we have a particular HWCAP enabled */ -static bool cpus_have_hwcap(const struct arm64_cpu_capabilities *cap) +static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities *cap) { bool rc; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 2bbdc0e4fd14..b1adc51b2c2e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -473,7 +473,7 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, * cpu logical map array containing MPIDR values related to logical * cpus. Assumes that cpu_logical_map(0) has already been initialized. */ -void __init of_parse_and_init_cpus(void) +static void __init of_parse_and_init_cpus(void) { struct device_node *dn = NULL; diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 40f7b33a22da..fce95e17cf7f 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -41,7 +41,7 @@ void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr, * time the notifier runs debug exceptions might have been enabled already, * with HW breakpoints registers content still in an unknown state. */ -void (*hw_breakpoint_restore)(void *); +static void (*hw_breakpoint_restore)(void *); void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) { /* Prevent multiple restore hook initializations */ diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index f6fe17d88da5..b467fd0a384b 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -15,6 +15,9 @@ ccflags-y := -shared -fno-common -fno-builtin ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +# Disable gcov profiling for VDSO code +GCOV_PROFILE := n + # Workaround for bare-metal (ELF) toolchains that neglect to pass -shared # down to collect2, resulting in silent corruption of the vDSO image. ccflags-y += -Wl,-shared diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index c2fa6b56613c..e3f563c81c48 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -146,7 +146,7 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr, if (((addr | next | phys) & ~CONT_MASK) == 0) { /* a block of CONT_PTES */ __populate_init_pte(pte, addr, next, phys, - prot | __pgprot(PTE_CONT)); + __pgprot(pgprot_val(prot) | PTE_CONT)); } else { /* * If the range being split is already inside of a @@ -165,7 +165,7 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr, } while (addr != end); } -void split_pud(pud_t *old_pud, pmd_t *pmd) +static void split_pud(pud_t *old_pud, pmd_t *pmd) { unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT; pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr); @@ -447,7 +447,7 @@ static void __init map_mem(void) memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); } -void __init fixup_executable(void) +static void __init fixup_executable(void) { #ifdef CONFIG_DEBUG_RODATA /* now that we are actually fully mapped, make the start/end more fine grained */ @@ -691,7 +691,7 @@ void __set_fixmap(enum fixed_addresses idx, void *__init fixmap_remap_fdt(phys_addr_t dt_phys) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); - pgprot_t prot = PAGE_KERNEL | PTE_RDONLY; + pgprot_t prot = PAGE_KERNEL_RO; int size, offset; void *dt_virt; diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 98a26ce82d26..aee5637ea436 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -1,7 +1,7 @@ /* * BPF JIT compiler for ARM64 * - * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.com> + * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.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 @@ -35,6 +35,7 @@ aarch64_insn_gen_comp_branch_imm(0, offset, Rt, A64_VARIANT(sf), \ AARCH64_INSN_BRANCH_COMP_##type) #define A64_CBZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, ZERO) +#define A64_CBNZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, NONZERO) /* Conditional branch (immediate) */ #define A64_COND_BRANCH(cond, offset) \ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index a44e5293c6f5..cf3c7d4a1b58 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1,7 +1,7 @@ /* * BPF JIT compiler for ARM64 * - * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.com> + * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.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 @@ -225,6 +225,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) u8 jmp_cond; s32 jmp_offset; +#define check_imm(bits, imm) do { \ + if ((((imm) > 0) && ((imm) >> (bits))) || \ + (((imm) < 0) && (~(imm) >> (bits)))) { \ + pr_info("[%2d] imm=%d(0x%x) out of range\n", \ + i, imm, imm); \ + return -EINVAL; \ + } \ +} while (0) +#define check_imm19(imm) check_imm(19, imm) +#define check_imm26(imm) check_imm(26, imm) + switch (code) { /* dst = src */ case BPF_ALU | BPF_MOV | BPF_X: @@ -258,15 +269,33 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) break; case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: - emit(A64_UDIV(is64, dst, dst, src), ctx); - break; case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_X: - ctx->tmp_used = 1; - emit(A64_UDIV(is64, tmp, dst, src), ctx); - emit(A64_MUL(is64, tmp, tmp, src), ctx); - emit(A64_SUB(is64, dst, dst, tmp), ctx); + { + const u8 r0 = bpf2a64[BPF_REG_0]; + + /* if (src == 0) return 0 */ + jmp_offset = 3; /* skip ahead to else path */ + check_imm19(jmp_offset); + emit(A64_CBNZ(is64, src, jmp_offset), ctx); + emit(A64_MOVZ(1, r0, 0, 0), ctx); + jmp_offset = epilogue_offset(ctx); + check_imm26(jmp_offset); + emit(A64_B(jmp_offset), ctx); + /* else */ + switch (BPF_OP(code)) { + case BPF_DIV: + emit(A64_UDIV(is64, dst, dst, src), ctx); + break; + case BPF_MOD: + ctx->tmp_used = 1; + emit(A64_UDIV(is64, tmp, dst, src), ctx); + emit(A64_MUL(is64, tmp, tmp, src), ctx); + emit(A64_SUB(is64, dst, dst, tmp), ctx); + break; + } break; + } case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU64 | BPF_LSH | BPF_X: emit(A64_LSLV(is64, dst, dst, src), ctx); @@ -393,17 +422,6 @@ emit_bswap_uxt: emit(A64_ASR(is64, dst, dst, imm), ctx); break; -#define check_imm(bits, imm) do { \ - if ((((imm) > 0) && ((imm) >> (bits))) || \ - (((imm) < 0) && (~(imm) >> (bits)))) { \ - pr_info("[%2d] imm=%d(0x%x) out of range\n", \ - i, imm, imm); \ - return -EINVAL; \ - } \ -} while (0) -#define check_imm19(imm) check_imm(19, imm) -#define check_imm26(imm) check_imm(26, imm) - /* JUMP off */ case BPF_JMP | BPF_JA: jmp_offset = bpf2a64_offset(i + off, i, ctx); diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index db589167838c..dd3ac75776ad 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -16,6 +16,7 @@ config H8300 select OF_EARLY_FLATTREE select HAVE_MEMBLOCK select HAVE_DMA_ATTRS + select CLKSRC_OF config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/arch/h8300/Makefile b/arch/h8300/Makefile index 0d2d96e52d9f..e1c02ca230cb 100644 --- a/arch/h8300/Makefile +++ b/arch/h8300/Makefile @@ -22,7 +22,9 @@ KBUILD_CFLAGS += -DUTS_SYSNAME=\"uClinux\" KBUILD_AFLAGS += $(aflags-y) LDFLAGS += $(ldflags-y) +ifeq ($(CROSS_COMPILE),) CROSS_COMPILE := h8300-unknown-linux- +endif core-y += arch/$(ARCH)/kernel/ arch/$(ARCH)/mm/ ifneq '$(CONFIG_H8300_BUILTIN_DTB)' '""' diff --git a/arch/h8300/boot/compressed/Makefile b/arch/h8300/boot/compressed/Makefile index 87d03b7ee97e..d7bc3fa7f2c6 100644 --- a/arch/h8300/boot/compressed/Makefile +++ b/arch/h8300/boot/compressed/Makefile @@ -14,11 +14,12 @@ OBJECTS = $(obj)/head.o $(obj)/misc.o # in order to suppress error message. # CONFIG_MEMORY_START ?= 0x00400000 -CONFIG_BOOT_LINK_OFFSET ?= 0x00140000 +CONFIG_BOOT_LINK_OFFSET ?= 0x00280000 IMAGE_OFFSET := $(shell printf "0x%08x" $$(($(CONFIG_MEMORY_START)+$(CONFIG_BOOT_LINK_OFFSET)))) LIBGCC := $(shell $(CROSS-COMPILE)$(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) -LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -estartup $(obj)/vmlinux.lds +LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -estartup -T $(obj)/vmlinux.lds \ + --defsym output=$(CONFIG_MEMORY_START) $(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(LIBGCC) FORCE $(call if_changed,ld) diff --git a/arch/h8300/boot/compressed/head.S b/arch/h8300/boot/compressed/head.S index 74c0d8cc40ba..0436350c1df5 100644 --- a/arch/h8300/boot/compressed/head.S +++ b/arch/h8300/boot/compressed/head.S @@ -9,8 +9,8 @@ .section .text..startup,"ax" .global startup startup: + mov.l #startup, sp mov.l er0, er4 - mov.l er0, sp mov.l #__sbss, er0 mov.l #__ebss, er1 sub.l er0, er1 @@ -24,7 +24,7 @@ startup: bne 1b jsr @decompress_kernel mov.l er4, er0 - jmp @0x400000 + jmp @output .align 9 fake_headers_as_bzImage: diff --git a/arch/h8300/boot/compressed/misc.c b/arch/h8300/boot/compressed/misc.c index c4f2cfcb117b..6029c5351895 100644 --- a/arch/h8300/boot/compressed/misc.c +++ b/arch/h8300/boot/compressed/misc.c @@ -28,7 +28,7 @@ static unsigned long free_mem_end_ptr; extern char input_data[]; extern int input_len; -static unsigned char *output; +extern char output[]; #define HEAP_SIZE 0x10000 @@ -56,15 +56,10 @@ void *memcpy(void *dest, const void *src, size_t n) static void error(char *x) { - while (1) ; /* Halt */ } -#define STACK_SIZE (4096) -long user_stack[STACK_SIZE]; -long *stack_start = &user_stack[STACK_SIZE]; - void decompress_kernel(void) { free_mem_ptr = (unsigned long)&_end; diff --git a/arch/h8300/boot/compressed/vmlinux.lds b/arch/h8300/boot/compressed/vmlinux.lds index a0a3a0ed54ef..44fd209db88a 100644 --- a/arch/h8300/boot/compressed/vmlinux.lds +++ b/arch/h8300/boot/compressed/vmlinux.lds @@ -27,6 +27,6 @@ SECTIONS *(.bss*) . = ALIGN(0x4) ; __ebss = . ; - __end = . ; } + _end = . ; } diff --git a/arch/h8300/boot/dts/edosk2674.dts b/arch/h8300/boot/dts/edosk2674.dts index dfb5c102f8da..4ce9fa874a57 100644 --- a/arch/h8300/boot/dts/edosk2674.dts +++ b/arch/h8300/boot/dts/edosk2674.dts @@ -7,7 +7,7 @@ chosen { bootargs = "console=ttySC2,38400"; - stdout-path = <&sci2>; + stdout-path = &sci2; }; aliases { serial0 = &sci0; @@ -25,13 +25,13 @@ compatible = "renesas,h8s2678-pll-clock"; clocks = <&xclk>; #clock-cells = <0>; - reg = <0xfee03b 2>, <0xfee045 2>; + reg = <0xffff3b 1>, <0xffff45 1>; }; core_clk: core_clk { compatible = "renesas,h8300-div-clock"; clocks = <&pllclk>; #clock-cells = <0>; - reg = <0xfee03b 2>; + reg = <0xffff3b 1>; renesas,width = <3>; }; fclk: fclk { diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h index 1d09b2f2e0fe..bb837cded268 100644 --- a/arch/h8300/include/asm/io.h +++ b/arch/h8300/include/asm/io.h @@ -36,20 +36,20 @@ static inline void ctrl_outl(unsigned long b, unsigned long addr) *(volatile unsigned long *)addr = b; } -static inline void ctrl_bclr(int b, unsigned long addr) +static inline void ctrl_bclr(int b, unsigned char *addr) { if (__builtin_constant_p(b)) - __asm__("bclr %1,%0" : : "WU"(addr), "i"(b)); + __asm__("bclr %1,%0" : "+WU"(*addr): "i"(b)); else - __asm__("bclr %w1,%0" : : "WU"(addr), "r"(b)); + __asm__("bclr %w1,%0" : "+WU"(*addr): "r"(b)); } -static inline void ctrl_bset(int b, unsigned long addr) +static inline void ctrl_bset(int b, unsigned char *addr) { if (__builtin_constant_p(b)) - __asm__("bset %1,%0" : : "WU"(addr), "i"(b)); + __asm__("bset %1,%0" : "+WU"(*addr): "i"(b)); else - __asm__("bset %w1,%0" : : "WU"(addr), "r"(b)); + __asm__("bset %w1,%0" : "+WU"(*addr): "r"(b)); } #endif /* __KERNEL__ */ diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h index 544c30785ad4..b408fe660cf8 100644 --- a/arch/h8300/include/asm/thread_info.h +++ b/arch/h8300/include/asm/thread_info.h @@ -13,6 +13,12 @@ #ifdef __KERNEL__ +/* + * Size of kernel stack for each process. This must be a power of 2... + */ +#define THREAD_SIZE_ORDER 1 +#define THREAD_SIZE 8192 /* 2 pages */ + #ifndef __ASSEMBLY__ /* @@ -46,14 +52,6 @@ struct thread_info { #define init_thread_info (init_thread_union.thread_info) #define init_stack (init_thread_union.stack) - -/* - * Size of kernel stack for each process. This must be a power of 2... - */ -#define THREAD_SIZE_ORDER 1 -#define THREAD_SIZE 8192 /* 2 pages */ - - /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) { diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c index 0fd1fe65c0b8..c772abe6d19c 100644 --- a/arch/h8300/kernel/setup.c +++ b/arch/h8300/kernel/setup.c @@ -29,6 +29,7 @@ #include <linux/clk-provider.h> #include <linux/memblock.h> #include <linux/screen_info.h> +#include <linux/clocksource.h> #include <asm/setup.h> #include <asm/irq.h> @@ -252,4 +253,5 @@ void __init calibrate_delay(void) void __init time_init(void) { of_clk_init(NULL); + clocksource_probe(); } diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S index 7c302dcf5249..cb5dfb02c88d 100644 --- a/arch/h8300/kernel/vmlinux.lds.S +++ b/arch/h8300/kernel/vmlinux.lds.S @@ -1,5 +1,6 @@ #include <asm-generic/vmlinux.lds.h> #include <asm/page.h> +#include <asm/thread_info.h> #define ROMTOP 0x000000 #define RAMTOP 0x400000 @@ -42,11 +43,10 @@ SECTIONS . = RAMTOP; _ramstart = .; #define ADDR(x) ROMEND -#else #endif _sdata = . ; __data_start = . ; - RW_DATA_SECTION(0,0,0) + RW_DATA_SECTION(0, PAGE_SIZE, THREAD_SIZE) #if defined(CONFIG_ROMKERNEL) #undef ADDR #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 9c26c5a96ea2..54b45b73195f 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2019,7 +2019,7 @@ static bool can_split_piggybacked_subcores(struct core_info *cip) return false; n_subcores += (cip->subcore_threads[sub] - 1) >> 1; } - if (n_subcores > 3 || large_sub < 0) + if (large_sub < 0 || !subcore_config_ok(n_subcores + 1, 2)) return false; /* diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index b1dab8d1d885..3c6badcd53ef 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1749,7 +1749,8 @@ kvmppc_hdsi: beq 3f clrrdi r0, r4, 28 PPC_SLBFEE_DOT(R5, R0) /* if so, look up SLB */ - bne 1f /* if no SLB entry found */ + li r0, BOOK3S_INTERRUPT_DATA_SEGMENT + bne 7f /* if no SLB entry found */ 4: std r4, VCPU_FAULT_DAR(r9) stw r6, VCPU_FAULT_DSISR(r9) @@ -1768,14 +1769,15 @@ kvmppc_hdsi: cmpdi r3, -2 /* MMIO emulation; need instr word */ beq 2f - /* Synthesize a DSI for the guest */ + /* Synthesize a DSI (or DSegI) for the guest */ ld r4, VCPU_FAULT_DAR(r9) mr r6, r3 -1: mtspr SPRN_DAR, r4 +1: li r0, BOOK3S_INTERRUPT_DATA_STORAGE mtspr SPRN_DSISR, r6 +7: mtspr SPRN_DAR, r4 mtspr SPRN_SRR0, r10 mtspr SPRN_SRR1, r11 - li r10, BOOK3S_INTERRUPT_DATA_STORAGE + mr r10, r0 bl kvmppc_msr_interrupt fast_interrupt_c_return: 6: ld r7, VCPU_CTR(r9) @@ -1823,7 +1825,8 @@ kvmppc_hisi: beq 3f clrrdi r0, r10, 28 PPC_SLBFEE_DOT(R5, R0) /* if so, look up SLB */ - bne 1f /* if no SLB entry found */ + li r0, BOOK3S_INTERRUPT_INST_SEGMENT + bne 7f /* if no SLB entry found */ 4: /* Search the hash table. */ mr r3, r9 /* vcpu pointer */ @@ -1840,11 +1843,12 @@ kvmppc_hisi: cmpdi r3, -1 /* handle in kernel mode */ beq guest_exit_cont - /* Synthesize an ISI for the guest */ + /* Synthesize an ISI (or ISegI) for the guest */ mr r11, r3 -1: mtspr SPRN_SRR0, r10 +1: li r0, BOOK3S_INTERRUPT_INST_STORAGE +7: mtspr SPRN_SRR0, r10 mtspr SPRN_SRR1, r11 - li r10, BOOK3S_INTERRUPT_INST_STORAGE + mr r10, r0 bl kvmppc_msr_interrupt b fast_interrupt_c_return diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9265196e877f..30cfd64295a0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -505,6 +505,7 @@ struct kvm_vcpu_arch { u32 virtual_tsc_mult; u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; + u64 tsc_scaling_ratio; atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ @@ -777,7 +778,7 @@ struct kvm_x86_ops { void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); - void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu); + void (*update_bp_intercept)(struct kvm_vcpu *vcpu); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); @@ -844,7 +845,7 @@ struct kvm_x86_ops { int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); bool (*invpcid_supported)(void); - void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host); + void (*adjust_tsc_offset_guest)(struct kvm_vcpu *vcpu, s64 adjustment); void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -852,11 +853,9 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale); u64 (*read_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); - u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); @@ -923,17 +922,6 @@ struct kvm_arch_async_pf { extern struct kvm_x86_ops *kvm_x86_ops; -static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, - s64 adjustment) -{ - kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, false); -} - -static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) -{ - kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, true); -} - int kvm_mmu_module_init(void); void kvm_mmu_module_exit(void); @@ -986,10 +974,12 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); /* control of guest tsc rate supported? */ extern bool kvm_has_tsc_control; -/* minimum supported tsc_khz for guests */ -extern u32 kvm_min_guest_tsc_khz; /* maximum supported tsc_khz for guests */ extern u32 kvm_max_guest_tsc_khz; +/* number of bits of the fractional part of the TSC scaling ratio */ +extern u8 kvm_tsc_scaling_ratio_frac_bits; +/* maximum allowed value of TSC scaling ratio */ +extern u64 kvm_max_tsc_scaling_ratio; enum emulation_result { EMULATE_DONE, /* no further processing */ @@ -1235,6 +1225,9 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); +u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); + unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index aa336ff3e03e..14c63c7e8337 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -73,6 +73,7 @@ #define SECONDARY_EXEC_ENABLE_PML 0x00020000 #define SECONDARY_EXEC_XSAVES 0x00100000 #define SECONDARY_EXEC_PCOMMIT 0x00200000 +#define SECONDARY_EXEC_TSC_SCALING 0x02000000 #define PIN_BASED_EXT_INTR_MASK 0x00000001 #define PIN_BASED_NMI_EXITING 0x00000008 @@ -167,6 +168,8 @@ enum vmcs_field { VMWRITE_BITMAP = 0x00002028, XSS_EXIT_BITMAP = 0x0000202C, XSS_EXIT_BITMAP_HIGH = 0x0000202D, + TSC_MULTIPLIER = 0x00002032, + TSC_MULTIPLIER_HIGH = 0x00002033, GUEST_PHYSICAL_ADDRESS = 0x00002400, GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401, VMCS_LINK_POINTER = 0x00002800, diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index b5d7640abc5d..8a4add8e4639 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -100,6 +100,7 @@ { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + AC_VECTOR, "AC excp" }, \ { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ { SVM_EXIT_INTR, "interrupt" }, \ { SVM_EXIT_NMI, "nmi" }, \ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ecd4ea1d28a8..4d30b865be30 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1250,7 +1250,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) tsc_deadline = apic->lapic_timer.expired_tscdeadline; apic->lapic_timer.expired_tscdeadline = 0; - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc()); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ @@ -1318,7 +1318,7 @@ static void start_apic_timer(struct kvm_lapic *apic) local_irq_save(flags); now = apic->lapic_timer.timer.base->get_time(); - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc()); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); if (likely(tscdeadline > guest_tsc)) { ns = (tscdeadline - guest_tsc) * 1000000ULL; do_div(ns, this_tsc_khz); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7d85bcae3332..e7c2c1428a69 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3359,7 +3359,7 @@ exit: return reserved; } -int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) +int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; bool reserved; @@ -3368,7 +3368,7 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) return RET_MMIO_PF_EMULATE; reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte); - if (unlikely(reserved)) + if (WARN_ON(reserved)) return RET_MMIO_PF_BUG; if (is_mmio_spte(spte)) { @@ -3392,17 +3392,7 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) */ return RET_MMIO_PF_RETRY; } -EXPORT_SYMBOL_GPL(handle_mmio_page_fault_common); - -static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, - u32 error_code, bool direct) -{ - int ret; - - ret = handle_mmio_page_fault_common(vcpu, addr, direct); - WARN_ON(ret == RET_MMIO_PF_BUG); - return ret; -} +EXPORT_SYMBOL_GPL(handle_mmio_page_fault); static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, bool prefault) @@ -3413,7 +3403,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, gva, error_code, true); + r = handle_mmio_page_fault(vcpu, gva, true); if (likely(r != RET_MMIO_PF_INVALID)) return r; @@ -3503,7 +3493,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, gpa, error_code, true); + r = handle_mmio_page_fault(vcpu, gpa, true); if (likely(r != RET_MMIO_PF_INVALID)) return r; diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e4202e41d535..55ffb7b0f95e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -56,13 +56,13 @@ void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); /* - * Return values of handle_mmio_page_fault_common: + * Return values of handle_mmio_page_fault: * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction * directly. * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page * fault path update the mmio spte. * RET_MMIO_PF_RETRY: let CPU fault again on the address. - * RET_MMIO_PF_BUG: bug is detected. + * RET_MMIO_PF_BUG: a bug was detected (and a WARN was printed). */ enum { RET_MMIO_PF_EMULATE = 1, @@ -71,7 +71,7 @@ enum { RET_MMIO_PF_BUG = -1 }; -int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); +int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index b41faa91a6f9..3058a22a658d 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -705,8 +705,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, addr, error_code, - mmu_is_nested(vcpu)); + r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu)); if (likely(r != RET_MMIO_PF_INVALID)) return r; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f2c8e4917688..83a1c643f9a5 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -158,8 +158,6 @@ struct vcpu_svm { unsigned long int3_rip; u32 apf_reason; - u64 tsc_ratio; - /* cached guest cpuid flags for faster access */ bool nrips_enabled : 1; }; @@ -214,7 +212,6 @@ static int nested_svm_intercept(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); -static u64 __scale_tsc(u64 ratio, u64 tsc); enum { VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, @@ -894,20 +891,9 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_FFXSR); if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { - u64 max; - kvm_has_tsc_control = true; - - /* - * Make sure the user can only configure tsc_khz values that - * fit into a signed integer. - * A min value is not calculated needed because it will always - * be 1 on all machines and a value of 0 is used to disable - * tsc-scaling for the vcpu. - */ - max = min(0x7fffffffULL, __scale_tsc(tsc_khz, TSC_RATIO_MAX)); - - kvm_max_guest_tsc_khz = max; + kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX; + kvm_tsc_scaling_ratio_frac_bits = 32; } if (nested) { @@ -971,68 +957,6 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 __scale_tsc(u64 ratio, u64 tsc) -{ - u64 mult, frac, _tsc; - - mult = ratio >> 32; - frac = ratio & ((1ULL << 32) - 1); - - _tsc = tsc; - _tsc *= mult; - _tsc += (tsc >> 32) * frac; - _tsc += ((tsc & ((1ULL << 32) - 1)) * frac) >> 32; - - return _tsc; -} - -static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 _tsc = tsc; - - if (svm->tsc_ratio != TSC_RATIO_DEFAULT) - _tsc = __scale_tsc(svm->tsc_ratio, tsc); - - return _tsc; -} - -static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 ratio; - u64 khz; - - /* Guest TSC same frequency as host TSC? */ - if (!scale) { - svm->tsc_ratio = TSC_RATIO_DEFAULT; - return; - } - - /* TSC scaling supported? */ - if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { - if (user_tsc_khz > tsc_khz) { - vcpu->arch.tsc_catchup = 1; - vcpu->arch.tsc_always_catchup = 1; - } else - WARN(1, "user requested TSC rate below hardware speed\n"); - return; - } - - khz = user_tsc_khz; - - /* TSC scaling required - calculate ratio */ - ratio = khz << 32; - do_div(ratio, tsc_khz); - - if (ratio == 0 || ratio & TSC_RATIO_RSVD) { - WARN_ONCE(1, "Invalid TSC ratio - virtual-tsc-khz=%u\n", - user_tsc_khz); - return; - } - svm->tsc_ratio = ratio; -} - static u64 svm_read_tsc_offset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1059,16 +983,10 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) +static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { struct vcpu_svm *svm = to_svm(vcpu); - if (host) { - if (svm->tsc_ratio != TSC_RATIO_DEFAULT) - WARN_ON(adjustment < 0); - adjustment = svm_scale_tsc(vcpu, (u64)adjustment); - } - svm->vmcb->control.tsc_offset += adjustment; if (is_guest_mode(vcpu)) svm->nested.hsave->control.tsc_offset += adjustment; @@ -1080,15 +998,6 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) -{ - u64 tsc; - - tsc = svm_scale_tsc(vcpu, rdtsc()); - - return target_tsc - tsc; -} - static void init_vmcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -1110,6 +1019,8 @@ static void init_vmcb(struct vcpu_svm *svm) set_exception_intercept(svm, PF_VECTOR); set_exception_intercept(svm, UD_VECTOR); set_exception_intercept(svm, MC_VECTOR); + set_exception_intercept(svm, AC_VECTOR); + set_exception_intercept(svm, DB_VECTOR); set_intercept(svm, INTERCEPT_INTR); set_intercept(svm, INTERCEPT_NMI); @@ -1235,8 +1146,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } - svm->tsc_ratio = TSC_RATIO_DEFAULT; - err = kvm_vcpu_init(&svm->vcpu, kvm, id); if (err) goto free_svm; @@ -1322,10 +1231,12 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - if (static_cpu_has(X86_FEATURE_TSCRATEMSR) && - svm->tsc_ratio != __this_cpu_read(current_tsc_ratio)) { - __this_cpu_write(current_tsc_ratio, svm->tsc_ratio); - wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio); + if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { + u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; + if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) { + __this_cpu_write(current_tsc_ratio, tsc_ratio); + wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); + } } } @@ -1644,20 +1555,13 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, mark_dirty(svm->vmcb, VMCB_SEG); } -static void update_db_bp_intercept(struct kvm_vcpu *vcpu) +static void update_bp_intercept(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - clr_exception_intercept(svm, DB_VECTOR); clr_exception_intercept(svm, BP_VECTOR); - if (svm->nmi_singlestep) - set_exception_intercept(svm, DB_VECTOR); - if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - set_exception_intercept(svm, DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) set_exception_intercept(svm, BP_VECTOR); } else @@ -1763,7 +1667,6 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_bp_intercept(&svm->vcpu); } if (svm->vcpu.guest_debug & @@ -1798,6 +1701,12 @@ static int ud_interception(struct vcpu_svm *svm) return 1; } +static int ac_interception(struct vcpu_svm *svm) +{ + kvm_queue_exception_e(&svm->vcpu, AC_VECTOR, 0); + return 1; +} + static void svm_fpu_activate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3075,8 +2984,7 @@ static int cr8_write_interception(struct vcpu_svm *svm) static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); - return vmcb->control.tsc_offset + - svm_scale_tsc(vcpu, host_tsc); + return vmcb->control.tsc_offset + host_tsc; } static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -3086,7 +2994,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_IA32_TSC: { msr_info->data = svm->vmcb->control.tsc_offset + - svm_scale_tsc(vcpu, rdtsc()); + kvm_scale_tsc(vcpu, rdtsc()); break; } @@ -3362,6 +3270,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, + [SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception, [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = nop_on_interception, @@ -3745,7 +3654,6 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_bp_intercept(vcpu); } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -4371,7 +4279,7 @@ static struct kvm_x86_ops svm_x86_ops = { .vcpu_load = svm_vcpu_load, .vcpu_put = svm_vcpu_put, - .update_db_bp_intercept = update_db_bp_intercept, + .update_bp_intercept = update_bp_intercept, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, @@ -4443,11 +4351,9 @@ static struct kvm_x86_ops svm_x86_ops = { .has_wbinvd_exit = svm_has_wbinvd_exit, - .set_tsc_khz = svm_set_tsc_khz, .read_tsc_offset = svm_read_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, - .adjust_tsc_offset = svm_adjust_tsc_offset, - .compute_tsc_offset = svm_compute_tsc_offset, + .adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest, .read_l1_tsc = svm_read_l1_tsc, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5eb56ed77c1f..87acc5221740 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -107,6 +107,8 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL + #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE) #define KVM_VM_CR0_ALWAYS_ON \ @@ -1172,6 +1174,12 @@ static inline bool cpu_has_vmx_pml(void) return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML; } +static inline bool cpu_has_vmx_tsc_scaling(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_TSC_SCALING; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -1631,7 +1639,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << NM_VECTOR) | (1u << DB_VECTOR); + (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) @@ -2053,6 +2061,12 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + + /* Setup TSC multiplier */ + if (cpu_has_vmx_tsc_scaling()) + vmcs_write64(TSC_MULTIPLIER, + vcpu->arch.tsc_scaling_ratio); + vmx->loaded_vmcs->cpu = cpu; } @@ -2357,15 +2371,16 @@ static void setup_msrs(struct vcpu_vmx *vmx) /* * reads and returns guest's timestamp counter "register" - * guest_tsc = host_tsc + tsc_offset -- 21.3 + * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset + * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3 */ -static u64 guest_read_tsc(void) +static u64 guest_read_tsc(struct kvm_vcpu *vcpu) { u64 host_tsc, tsc_offset; host_tsc = rdtsc(); tsc_offset = vmcs_read64(TSC_OFFSET); - return host_tsc + tsc_offset; + return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset; } /* @@ -2382,22 +2397,6 @@ static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) return host_tsc + tsc_offset; } -/* - * Engage any workarounds for mis-matched TSC rates. Currently limited to - * software catchup for faster rates on slower CPUs. - */ -static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) -{ - if (!scale) - return; - - if (user_tsc_khz > tsc_khz) { - vcpu->arch.tsc_catchup = 1; - vcpu->arch.tsc_always_catchup = 1; - } else - WARN(1, "user requested TSC rate below hardware speed\n"); -} - static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu) { return vmcs_read64(TSC_OFFSET); @@ -2429,7 +2428,7 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) } } -static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) +static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { u64 offset = vmcs_read64(TSC_OFFSET); @@ -2442,11 +2441,6 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho offset + adjustment); } -static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) -{ - return target_tsc - rdtsc(); -} - static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0); @@ -2778,7 +2772,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_TSC: - msr_info->data = guest_read_tsc(); + msr_info->data = guest_read_tsc(vcpu); break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); @@ -3154,7 +3148,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_XSAVES | SECONDARY_EXEC_ENABLE_PML | - SECONDARY_EXEC_PCOMMIT; + SECONDARY_EXEC_PCOMMIT | + SECONDARY_EXEC_TSC_SCALING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -5266,6 +5261,9 @@ static int handle_exception(struct kvm_vcpu *vcpu) return handle_rmode_exception(vcpu, ex_no, error_code); switch (ex_no) { + case AC_VECTOR: + kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); + return 1; case DB_VECTOR: dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & @@ -5908,7 +5906,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) return 1; } - ret = handle_mmio_page_fault_common(vcpu, gpa, true); + ret = handle_mmio_page_fault(vcpu, gpa, true); if (likely(ret == RET_MMIO_PF_EMULATE)) return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == EMULATE_DONE; @@ -6199,6 +6197,12 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) enable_apicv = 0; + if (cpu_has_vmx_tsc_scaling()) { + kvm_has_tsc_control = true; + kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; + kvm_tsc_scaling_ratio_frac_bits = 48; + } + if (enable_apicv) kvm_x86_ops->update_cr8_intercept = NULL; else { @@ -8008,6 +8012,9 @@ static void dump_vmcs(void) vmcs_read32(IDT_VECTORING_INFO_FIELD), vmcs_read32(IDT_VECTORING_ERROR_CODE)); pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET)); + if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) + pr_err("TSC Multiplier = 0x%016lx\n", + vmcs_readl(TSC_MULTIPLIER)); if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) @@ -10752,7 +10759,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, - .update_db_bp_intercept = update_exception_bitmap, + .update_bp_intercept = update_exception_bitmap, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, @@ -10826,11 +10833,9 @@ static struct kvm_x86_ops vmx_x86_ops = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .set_tsc_khz = vmx_set_tsc_khz, .read_tsc_offset = vmx_read_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, - .adjust_tsc_offset = vmx_adjust_tsc_offset, - .compute_tsc_offset = vmx_compute_tsc_offset, + .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest, .read_l1_tsc = vmx_read_l1_tsc, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4a6eff166fc6..00462bd63129 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -93,10 +93,10 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); -struct kvm_x86_ops *kvm_x86_ops; +struct kvm_x86_ops *kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); -static bool ignore_msrs = 0; +static bool __read_mostly ignore_msrs = 0; module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); unsigned int min_timer_period_us = 500; @@ -105,20 +105,25 @@ module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); static bool __read_mostly kvmclock_periodic_sync = true; module_param(kvmclock_periodic_sync, bool, S_IRUGO); -bool kvm_has_tsc_control; +bool __read_mostly kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); -u32 kvm_max_guest_tsc_khz; +u32 __read_mostly kvm_max_guest_tsc_khz; EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); +u8 __read_mostly kvm_tsc_scaling_ratio_frac_bits; +EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits); +u64 __read_mostly kvm_max_tsc_scaling_ratio; +EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); +static u64 __read_mostly kvm_default_tsc_scaling_ratio; /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ -static u32 tsc_tolerance_ppm = 250; +static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); /* lapic timer advance (tscdeadline mode only) in nanoseconds */ -unsigned int lapic_timer_advance_ns = 0; +unsigned int __read_mostly lapic_timer_advance_ns = 0; module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); -static bool backwards_tsc_observed = false; +static bool __read_mostly backwards_tsc_observed = false; #define KVM_NR_SHARED_MSRS 16 @@ -1249,14 +1254,53 @@ static u32 adjust_tsc_khz(u32 khz, s32 ppm) return v; } -static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) +static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) +{ + u64 ratio; + + /* Guest TSC same frequency as host TSC? */ + if (!scale) { + vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + return 0; + } + + /* TSC scaling supported? */ + if (!kvm_has_tsc_control) { + if (user_tsc_khz > tsc_khz) { + vcpu->arch.tsc_catchup = 1; + vcpu->arch.tsc_always_catchup = 1; + return 0; + } else { + WARN(1, "user requested TSC rate below hardware speed\n"); + return -1; + } + } + + /* TSC scaling required - calculate ratio */ + ratio = mul_u64_u32_div(1ULL << kvm_tsc_scaling_ratio_frac_bits, + user_tsc_khz, tsc_khz); + + if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) { + WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); + return -1; + } + + vcpu->arch.tsc_scaling_ratio = ratio; + return 0; +} + +static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) { u32 thresh_lo, thresh_hi; int use_scaling = 0; /* tsc_khz can be zero if TSC calibration fails */ - if (this_tsc_khz == 0) - return; + if (this_tsc_khz == 0) { + /* set tsc_scaling_ratio to a safe value */ + vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + return -1; + } /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, @@ -1276,7 +1320,7 @@ static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } - kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling); + return set_tsc_khz(vcpu, this_tsc_khz, use_scaling); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) @@ -1322,6 +1366,48 @@ static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } +/* + * Multiply tsc by a fixed point number represented by ratio. + * + * The most significant 64-N bits (mult) of ratio represent the + * integral part of the fixed point number; the remaining N bits + * (frac) represent the fractional part, ie. ratio represents a fixed + * point number (mult + frac * 2^(-N)). + * + * N equals to kvm_tsc_scaling_ratio_frac_bits. + */ +static inline u64 __scale_tsc(u64 ratio, u64 tsc) +{ + return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits); +} + +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +{ + u64 _tsc = tsc; + u64 ratio = vcpu->arch.tsc_scaling_ratio; + + if (ratio != kvm_default_tsc_scaling_ratio) + _tsc = __scale_tsc(ratio, tsc); + + return _tsc; +} +EXPORT_SYMBOL_GPL(kvm_scale_tsc); + +static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +{ + u64 tsc; + + tsc = kvm_scale_tsc(vcpu, rdtsc()); + + return target_tsc - tsc; +} + +u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) +{ + return kvm_x86_ops->read_l1_tsc(vcpu, kvm_scale_tsc(vcpu, host_tsc)); +} +EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); + void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct kvm *kvm = vcpu->kvm; @@ -1333,7 +1419,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); - offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + offset = kvm_compute_tsc_offset(vcpu, data); ns = get_kernel_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; @@ -1390,7 +1476,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; - offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + offset = kvm_compute_tsc_offset(vcpu, data); pr_debug("kvm: adjusted tsc offset by %llu\n", delta); } matched = true; @@ -1447,6 +1533,20 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) EXPORT_SYMBOL_GPL(kvm_write_tsc); +static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, + s64 adjustment) +{ + kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment); +} + +static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) +{ + if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) + WARN_ON(adjustment < 0); + adjustment = kvm_scale_tsc(vcpu, (u64) adjustment); + kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment); +} + #ifdef CONFIG_X86_64 static cycle_t read_tsc(void) @@ -1608,7 +1708,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) static int kvm_guest_time_update(struct kvm_vcpu *v) { - unsigned long flags, this_tsc_khz; + unsigned long flags, this_tsc_khz, tgt_tsc_khz; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; @@ -1645,7 +1745,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) kernel_ns = get_kernel_ns(); } - tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, host_tsc); + tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); /* * We may have to catch up the TSC to match elapsed wall clock @@ -1671,7 +1771,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) return 0; if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) { - kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz, + tgt_tsc_khz = kvm_has_tsc_control ? + vcpu->virtual_tsc_khz : this_tsc_khz; + kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz, &vcpu->hv_clock.tsc_shift, &vcpu->hv_clock.tsc_to_system_mul); vcpu->hw_tsc_khz = this_tsc_khz; @@ -2617,7 +2719,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (check_tsc_unstable()) { - u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu, + u64 offset = kvm_compute_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_x86_ops->write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; @@ -3319,9 +3421,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; - kvm_set_tsc_khz(vcpu, user_tsc_khz); + if (!kvm_set_tsc_khz(vcpu, user_tsc_khz)) + r = 0; - r = 0; goto out; } case KVM_GET_TSC_KHZ: { @@ -6452,8 +6554,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, - rdtsc()); + vcpu->arch.last_guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -7015,7 +7116,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - kvm_x86_ops->update_db_bp_intercept(vcpu); + kvm_x86_ops->update_bp_intercept(vcpu); r = 0; @@ -7364,6 +7465,20 @@ int kvm_arch_hardware_setup(void) if (r != 0) return r; + if (kvm_has_tsc_control) { + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated needed because it will always + * be 1 on all machines. + */ + u64 max = min(0x7fffffffULL, + __scale_tsc(kvm_max_tsc_scaling_ratio, tsc_khz)); + kvm_max_guest_tsc_khz = max; + + kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; + } + kvm_init_msr_list(); return 0; } diff --git a/block/blk-core.c b/block/blk-core.c index 2bbf08cd2900..5131993b23a1 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1575,6 +1575,9 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req, * @q: request_queue new bio is being queued at * @bio: new bio being queued * @request_count: out parameter for number of traversed plugged requests + * @same_queue_rq: pointer to &struct request that gets filled in when + * another request associated with @q is found on the plug list + * (optional, may be %NULL) * * Determine whether @bio being queued on @q can be merged with a request * on %current's plugged list. Returns %true if merge was successful, diff --git a/block/blk-mq.c b/block/blk-mq.c index 86bd5b25288e..3ae09de62f19 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -358,7 +358,7 @@ static void blk_mq_ipi_complete_request(struct request *rq) put_cpu(); } -void __blk_mq_complete_request(struct request *rq) +static void __blk_mq_complete_request(struct request *rq) { struct request_queue *q = rq->q; diff --git a/block/blk-mq.h b/block/blk-mq.h index b44dce165761..713820b47b31 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -25,7 +25,6 @@ struct blk_mq_ctx { struct kobject kobj; } ____cacheline_aligned_in_smp; -void __blk_mq_complete_request(struct request *rq); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 3000ea3b6687..021d39c0ba75 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -531,7 +531,11 @@ int x509_decode_time(time64_t *_t, size_t hdrlen, if (*p != 'Z') goto unsupported_time; - mon_len = month_lengths[mon]; + if (year < 1970 || + mon < 1 || mon > 12) + goto invalid_time; + + mon_len = month_lengths[mon - 1]; if (mon == 2) { if (year % 4 == 0) { mon_len = 29; @@ -543,14 +547,12 @@ int x509_decode_time(time64_t *_t, size_t hdrlen, } } - if (year < 1970 || - mon < 1 || mon > 12 || - day < 1 || day > mon_len || + if (day < 1 || day > mon_len || hour > 23 || min > 59 || sec > 59) goto invalid_time; - + *_t = mktime64(year, mon, day, hour, min, sec); return 0; diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index 06a67d5f2846..296b7a14893a 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -103,7 +103,12 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev) pdevinfo.res = resources; pdevinfo.num_res = count; pdevinfo.fwnode = acpi_fwnode_handle(adev); - pdevinfo.dma_mask = acpi_check_dma(adev, NULL) ? DMA_BIT_MASK(32) : 0; + + if (acpi_dma_supported(adev)) + pdevinfo.dma_mask = DMA_BIT_MASK(32); + else + pdevinfo.dma_mask = 0; + pdev = platform_device_register_full(&pdevinfo); if (IS_ERR(pdev)) dev_err(&adev->dev, "platform device creation failed: %ld\n", diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 5778e8e4313a..3405f7a41e25 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -77,6 +77,12 @@ module_param(allow_duplicates, bool, 0644); static int disable_backlight_sysfs_if = -1; module_param(disable_backlight_sysfs_if, int, 0444); +static bool device_id_scheme = false; +module_param(device_id_scheme, bool, 0444); + +static bool only_lcd = false; +module_param(only_lcd, bool, 0444); + static int register_count; static DEFINE_MUTEX(register_count_mutex); static struct mutex video_list_lock; @@ -394,6 +400,18 @@ static int video_disable_backlight_sysfs_if( return 0; } +static int video_set_device_id_scheme(const struct dmi_system_id *d) +{ + device_id_scheme = true; + return 0; +} + +static int video_enable_only_lcd(const struct dmi_system_id *d) +{ + only_lcd = true; + return 0; +} + static struct dmi_system_id video_dmi_table[] = { /* * Broken _BQC workaround http://bugzilla.kernel.org/show_bug.cgi?id=13121 @@ -455,6 +473,33 @@ static struct dmi_system_id video_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE R830"), }, }, + /* + * Some machine's _DOD IDs don't have bit 31(Device ID Scheme) set + * but the IDs actually follow the Device ID Scheme. + */ + { + /* https://bugzilla.kernel.org/show_bug.cgi?id=104121 */ + .callback = video_set_device_id_scheme, + .ident = "ESPRIMO Mobile M9410", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "ESPRIMO Mobile M9410"), + }, + }, + /* + * Some machines have multiple video output devices, but only the one + * that is the type of LCD can do the backlight control so we should not + * register backlight interface for other video output devices. + */ + { + /* https://bugzilla.kernel.org/show_bug.cgi?id=104121 */ + .callback = video_enable_only_lcd, + .ident = "ESPRIMO Mobile M9410", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "ESPRIMO Mobile M9410"), + }, + }, {} }; @@ -1003,7 +1048,7 @@ acpi_video_bus_get_one_device(struct acpi_device *device, attribute = acpi_video_get_device_attr(video, device_id); - if (attribute && attribute->device_id_scheme) { + if (attribute && (attribute->device_id_scheme || device_id_scheme)) { switch (attribute->display_type) { case ACPI_VIDEO_DISPLAY_CRT: data->flags.crt = 1; @@ -1568,15 +1613,6 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device) static int count; char *name; - /* - * Do not create backlight device for video output - * device that is not in the enumerated list. - */ - if (!acpi_video_device_in_dod(device)) { - dev_dbg(&device->dev->dev, "not in _DOD list, ignore\n"); - return; - } - result = acpi_video_init_brightness(device); if (result) return; @@ -1657,6 +1693,22 @@ static void acpi_video_run_bcl_for_osi(struct acpi_video_bus *video) mutex_unlock(&video->device_list_lock); } +static bool acpi_video_should_register_backlight(struct acpi_video_device *dev) +{ + /* + * Do not create backlight device for video output + * device that is not in the enumerated list. + */ + if (!acpi_video_device_in_dod(dev)) { + dev_dbg(&dev->dev->dev, "not in _DOD list, ignore\n"); + return false; + } + + if (only_lcd) + return dev->flags.lcd; + return true; +} + static int acpi_video_bus_register_backlight(struct acpi_video_bus *video) { struct acpi_video_device *dev; @@ -1670,8 +1722,10 @@ static int acpi_video_bus_register_backlight(struct acpi_video_bus *video) return 0; mutex_lock(&video->device_list_lock); - list_for_each_entry(dev, &video->video_device_list, entry) - acpi_video_dev_register_backlight(dev); + list_for_each_entry(dev, &video->video_device_list, entry) { + if (acpi_video_should_register_backlight(dev)) + acpi_video_dev_register_backlight(dev); + } mutex_unlock(&video->device_list_lock); video->backlight_registered = true; diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 1470ae4f98c0..5ea5dc219f56 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -168,7 +168,7 @@ int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev) struct list_head *physnode_list; unsigned int node_id; int retval = -EINVAL; - bool coherent; + enum dev_dma_attr attr; if (has_acpi_companion(dev)) { if (acpi_dev) { @@ -225,8 +225,10 @@ int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev) if (!has_acpi_companion(dev)) ACPI_COMPANION_SET(dev, acpi_dev); - if (acpi_check_dma(acpi_dev, &coherent)) - arch_setup_dma_ops(dev, 0, 0, NULL, coherent); + attr = acpi_get_dma_attr(acpi_dev); + if (attr != DEV_DMA_NOT_SUPPORTED) + arch_setup_dma_ops(dev, 0, 0, NULL, + attr == DEV_DMA_COHERENT); acpi_physnode_link_name(physical_node_name, node_id); retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj, diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index daf9fc8329e6..78d5f02a073b 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1308,6 +1308,48 @@ void acpi_free_pnp_ids(struct acpi_device_pnp *pnp) kfree(pnp->unique_id); } +/** + * acpi_dma_supported - Check DMA support for the specified device. + * @adev: The pointer to acpi device + * + * Return false if DMA is not supported. Otherwise, return true + */ +bool acpi_dma_supported(struct acpi_device *adev) +{ + if (!adev) + return false; + + if (adev->flags.cca_seen) + return true; + + /* + * Per ACPI 6.0 sec 6.2.17, assume devices can do cache-coherent + * DMA on "Intel platforms". Presumably that includes all x86 and + * ia64, and other arches will set CONFIG_ACPI_CCA_REQUIRED=y. + */ + if (!IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED)) + return true; + + return false; +} + +/** + * acpi_get_dma_attr - Check the supported DMA attr for the specified device. + * @adev: The pointer to acpi device + * + * Return enum dev_dma_attr. + */ +enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) +{ + if (!acpi_dma_supported(adev)) + return DEV_DMA_NOT_SUPPORTED; + + if (adev->flags.coherent_dma) + return DEV_DMA_COHERENT; + else + return DEV_DMA_NON_COHERENT; +} + static void acpi_init_coherency(struct acpi_device *adev) { unsigned long long cca = 0; diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 0d3a384b508a..daaf1c4e1e0f 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -233,6 +233,15 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, }, { + /* https://bugzilla.redhat.com/show_bug.cgi?id=1272633 */ + .callback = video_detect_force_video, + .ident = "Dell XPS14 L421X", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS L421X"), + }, + }, + { /* https://bugzilla.redhat.com/show_bug.cgi?id=1163574 */ .callback = video_detect_force_video, .ident = "Dell XPS15 L521X", diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 80e298870388..e03b1ad25a90 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -321,8 +321,7 @@ static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async) if (stat > PM_QOS_FLAGS_NONE) return -EBUSY; - if (pdd->dev->driver && (!pm_runtime_suspended(pdd->dev) - || pdd->dev->power.irq_safe)) + if (!pm_runtime_suspended(pdd->dev) || pdd->dev->power.irq_safe) not_suspended++; } @@ -1312,13 +1311,17 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *subdomain) { - struct gpd_link *link; + struct gpd_link *link, *itr; int ret = 0; if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain) || genpd == subdomain) return -EINVAL; + link = kzalloc(sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; + mutex_lock(&genpd->lock); mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING); @@ -1328,18 +1331,13 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, goto out; } - list_for_each_entry(link, &genpd->master_links, master_node) { - if (link->slave == subdomain && link->master == genpd) { + list_for_each_entry(itr, &genpd->master_links, master_node) { + if (itr->slave == subdomain && itr->master == genpd) { ret = -EINVAL; goto out; } } - link = kzalloc(sizeof(*link), GFP_KERNEL); - if (!link) { - ret = -ENOMEM; - goto out; - } link->master = genpd; list_add_tail(&link->master_node, &genpd->master_links); link->slave = subdomain; @@ -1350,7 +1348,8 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, out: mutex_unlock(&subdomain->lock); mutex_unlock(&genpd->lock); - + if (ret) + kfree(link); return ret; } EXPORT_SYMBOL_GPL(pm_genpd_add_subdomain); diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index 270902007055..b8e76f75073b 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -11,6 +11,8 @@ * published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/errno.h> #include <linux/err.h> #include <linux/slab.h> @@ -27,7 +29,7 @@ */ static LIST_HEAD(dev_opp_list); /* Lock to allow exclusive modification to the device and opp lists */ -static DEFINE_MUTEX(dev_opp_list_lock); +DEFINE_MUTEX(dev_opp_list_lock); #define opp_rcu_lockdep_assert() \ do { \ @@ -79,14 +81,18 @@ static struct device_opp *_managed_opp(const struct device_node *np) * Return: pointer to 'struct device_opp' if found, otherwise -ENODEV or * -EINVAL based on type of error. * - * Locking: This function must be called under rcu_read_lock(). device_opp - * is a RCU protected pointer. This means that device_opp is valid as long - * as we are under RCU lock. + * Locking: For readers, this function must be called under rcu_read_lock(). + * device_opp is a RCU protected pointer, which means that device_opp is valid + * as long as we are under RCU lock. + * + * For Writers, this function must be called with dev_opp_list_lock held. */ struct device_opp *_find_device_opp(struct device *dev) { struct device_opp *dev_opp; + opp_rcu_lockdep_assert(); + if (IS_ERR_OR_NULL(dev)) { pr_err("%s: Invalid parameters\n", __func__); return ERR_PTR(-EINVAL); @@ -701,7 +707,7 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, } /** - * _opp_add_dynamic() - Allocate a dynamic OPP. + * _opp_add_v1() - Allocate a OPP based on v1 bindings. * @dev: device for which we do this operation * @freq: Frequency in Hz for this OPP * @u_volt: Voltage in uVolts for this OPP @@ -727,8 +733,8 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, * Duplicate OPPs (both freq and volt are same) and !opp->available * -ENOMEM Memory allocation failure */ -static int _opp_add_dynamic(struct device *dev, unsigned long freq, - long u_volt, bool dynamic) +static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, + bool dynamic) { struct device_opp *dev_opp; struct dev_pm_opp *new_opp; @@ -770,9 +776,10 @@ unlock: } /* TODO: Support multiple regulators */ -static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev) +static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev) { u32 microvolt[3] = {0}; + u32 val; int count, ret; /* Missing property isn't a problem, but an invalid entry is */ @@ -805,6 +812,9 @@ static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev) opp->u_volt_min = microvolt[1]; opp->u_volt_max = microvolt[2]; + if (!of_property_read_u32(opp->np, "opp-microamp", &val)) + opp->u_amp = val; + return 0; } @@ -869,13 +879,10 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) if (!of_property_read_u32(np, "clock-latency-ns", &val)) new_opp->clock_latency_ns = val; - ret = opp_get_microvolt(new_opp, dev); + ret = opp_parse_supplies(new_opp, dev); if (ret) goto free_opp; - if (!of_property_read_u32(new_opp->np, "opp-microamp", &val)) - new_opp->u_amp = val; - ret = _opp_add(dev, new_opp, dev_opp); if (ret) goto free_opp; @@ -939,7 +946,7 @@ unlock: */ int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt) { - return _opp_add_dynamic(dev, freq, u_volt, true); + return _opp_add_v1(dev, freq, u_volt, true); } EXPORT_SYMBOL_GPL(dev_pm_opp_add); @@ -1172,13 +1179,17 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) struct device_opp *dev_opp; int ret = 0, count = 0; + mutex_lock(&dev_opp_list_lock); + dev_opp = _managed_opp(opp_np); if (dev_opp) { /* OPPs are already managed */ if (!_add_list_dev(dev, dev_opp)) ret = -ENOMEM; + mutex_unlock(&dev_opp_list_lock); return ret; } + mutex_unlock(&dev_opp_list_lock); /* We have opp-list node now, iterate over it and add OPPs */ for_each_available_child_of_node(opp_np, np) { @@ -1196,15 +1207,20 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) if (WARN_ON(!count)) return -ENOENT; + mutex_lock(&dev_opp_list_lock); + dev_opp = _find_device_opp(dev); if (WARN_ON(IS_ERR(dev_opp))) { ret = PTR_ERR(dev_opp); + mutex_unlock(&dev_opp_list_lock); goto free_table; } dev_opp->np = opp_np; dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared"); + mutex_unlock(&dev_opp_list_lock); + return 0; free_table: @@ -1241,7 +1257,7 @@ static int _of_add_opp_table_v1(struct device *dev) unsigned long freq = be32_to_cpup(val++) * 1000; unsigned long volt = be32_to_cpup(val++); - if (_opp_add_dynamic(dev, freq, volt, false)) + if (_opp_add_v1(dev, freq, volt, false)) dev_warn(dev, "%s: Failed to add OPP %ld\n", __func__, freq); nr -= 2; diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c index 7654c5606307..7b445e88a0d5 100644 --- a/drivers/base/power/opp/cpu.c +++ b/drivers/base/power/opp/cpu.c @@ -10,6 +10,9 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/err.h> @@ -124,12 +127,12 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) struct device *dev; int cpu, ret = 0; - rcu_read_lock(); + mutex_lock(&dev_opp_list_lock); dev_opp = _find_device_opp(cpu_dev); if (IS_ERR(dev_opp)) { ret = -EINVAL; - goto out_rcu_read_unlock; + goto unlock; } for_each_cpu(cpu, cpumask) { @@ -150,10 +153,10 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) continue; } } -out_rcu_read_unlock: - rcu_read_unlock(); +unlock: + mutex_unlock(&dev_opp_list_lock); - return 0; + return ret; } EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus); diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h index dcb38f78dae4..7366b2aa8997 100644 --- a/drivers/base/power/opp/opp.h +++ b/drivers/base/power/opp/opp.h @@ -21,6 +21,9 @@ #include <linux/rculist.h> #include <linux/rcupdate.h> +/* Lock to allow exclusive modification to the device and opp lists */ +extern struct mutex dev_opp_list_lock; + /* * Internal data structure organization with the OPP layer library is as * follows: diff --git a/drivers/base/property.c b/drivers/base/property.c index de40623bbd8a..1325ff225cc4 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -598,18 +598,34 @@ unsigned int device_get_child_node_count(struct device *dev) } EXPORT_SYMBOL_GPL(device_get_child_node_count); -bool device_dma_is_coherent(struct device *dev) +bool device_dma_supported(struct device *dev) { - bool coherent = false; - + /* For DT, this is always supported. + * For ACPI, this depends on CCA, which + * is determined by the acpi_dma_supported(). + */ if (IS_ENABLED(CONFIG_OF) && dev->of_node) - coherent = of_dma_is_coherent(dev->of_node); - else - acpi_check_dma(ACPI_COMPANION(dev), &coherent); + return true; + + return acpi_dma_supported(ACPI_COMPANION(dev)); +} +EXPORT_SYMBOL_GPL(device_dma_supported); - return coherent; +enum dev_dma_attr device_get_dma_attr(struct device *dev) +{ + enum dev_dma_attr attr = DEV_DMA_NOT_SUPPORTED; + + if (IS_ENABLED(CONFIG_OF) && dev->of_node) { + if (of_dma_is_coherent(dev->of_node)) + attr = DEV_DMA_COHERENT; + else + attr = DEV_DMA_NON_COHERENT; + } else + attr = acpi_get_dma_attr(ACPI_COMPANION(dev)); + + return attr; } -EXPORT_SYMBOL_GPL(device_dma_is_coherent); +EXPORT_SYMBOL_GPL(device_get_dma_attr); /** * device_get_phy_mode - Get phy mode for given device diff --git a/drivers/block/brd.c b/drivers/block/brd.c index c9f9c30d6467..a5880f4ab40e 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -337,6 +337,9 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) goto io_error; if (unlikely(bio->bi_rw & REQ_DISCARD)) { + if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) || + bio->bi_iter.bi_size & PAGE_MASK) + goto io_error; discard_from_brd(brd, sector, bio->bi_iter.bi_size); goto out; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 128e7df5b807..235708c7c46e 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -418,8 +418,6 @@ MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (d static int rbd_img_request_submit(struct rbd_img_request *img_request); -static void rbd_dev_device_release(struct device *dev); - static ssize_t rbd_add(struct bus_type *bus, const char *buf, size_t count); static ssize_t rbd_remove(struct bus_type *bus, const char *buf, @@ -3991,14 +3989,12 @@ static const struct attribute_group *rbd_attr_groups[] = { NULL }; -static void rbd_sysfs_dev_release(struct device *dev) -{ -} +static void rbd_dev_release(struct device *dev); static struct device_type rbd_device_type = { .name = "rbd", .groups = rbd_attr_groups, - .release = rbd_sysfs_dev_release, + .release = rbd_dev_release, }; static struct rbd_spec *rbd_spec_get(struct rbd_spec *spec) @@ -4041,6 +4037,25 @@ static void rbd_spec_free(struct kref *kref) kfree(spec); } +static void rbd_dev_release(struct device *dev) +{ + struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); + bool need_put = !!rbd_dev->opts; + + rbd_put_client(rbd_dev->rbd_client); + rbd_spec_put(rbd_dev->spec); + kfree(rbd_dev->opts); + kfree(rbd_dev); + + /* + * This is racy, but way better than putting module outside of + * the release callback. The race window is pretty small, so + * doing something similar to dm (dm-builtin.c) is overkill. + */ + if (need_put) + module_put(THIS_MODULE); +} + static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, struct rbd_spec *spec, struct rbd_options *opts) @@ -4057,6 +4072,11 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, INIT_LIST_HEAD(&rbd_dev->node); init_rwsem(&rbd_dev->header_rwsem); + rbd_dev->dev.bus = &rbd_bus_type; + rbd_dev->dev.type = &rbd_device_type; + rbd_dev->dev.parent = &rbd_root_dev; + device_initialize(&rbd_dev->dev); + rbd_dev->rbd_client = rbdc; rbd_dev->spec = spec; rbd_dev->opts = opts; @@ -4068,15 +4088,21 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, rbd_dev->layout.fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER); rbd_dev->layout.fl_pg_pool = cpu_to_le32((u32) spec->pool_id); + /* + * If this is a mapping rbd_dev (as opposed to a parent one), + * pin our module. We have a ref from do_rbd_add(), so use + * __module_get(). + */ + if (rbd_dev->opts) + __module_get(THIS_MODULE); + return rbd_dev; } static void rbd_dev_destroy(struct rbd_device *rbd_dev) { - rbd_put_client(rbd_dev->rbd_client); - rbd_spec_put(rbd_dev->spec); - kfree(rbd_dev->opts); - kfree(rbd_dev); + if (rbd_dev) + put_device(&rbd_dev->dev); } /* @@ -4702,27 +4728,6 @@ static int rbd_dev_header_info(struct rbd_device *rbd_dev) return rbd_dev_v2_header_info(rbd_dev); } -static int rbd_bus_add_dev(struct rbd_device *rbd_dev) -{ - struct device *dev; - int ret; - - dev = &rbd_dev->dev; - dev->bus = &rbd_bus_type; - dev->type = &rbd_device_type; - dev->parent = &rbd_root_dev; - dev->release = rbd_dev_device_release; - dev_set_name(dev, "%d", rbd_dev->dev_id); - ret = device_register(dev); - - return ret; -} - -static void rbd_bus_del_dev(struct rbd_device *rbd_dev) -{ - device_unregister(&rbd_dev->dev); -} - /* * Get a unique rbd identifier for the given new rbd_dev, and add * the rbd_dev to the global list. @@ -5225,7 +5230,8 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE); set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only); - ret = rbd_bus_add_dev(rbd_dev); + dev_set_name(&rbd_dev->dev, "%d", rbd_dev->dev_id); + ret = device_add(&rbd_dev->dev); if (ret) goto err_out_mapping; @@ -5248,8 +5254,6 @@ err_out_blkdev: unregister_blkdev(rbd_dev->major, rbd_dev->name); err_out_id: rbd_dev_id_put(rbd_dev); - rbd_dev_mapping_clear(rbd_dev); - return ret; } @@ -5397,7 +5401,7 @@ static ssize_t do_rbd_add(struct bus_type *bus, struct rbd_spec *spec = NULL; struct rbd_client *rbdc; bool read_only; - int rc = -ENOMEM; + int rc; if (!try_module_get(THIS_MODULE)) return -ENODEV; @@ -5405,7 +5409,7 @@ static ssize_t do_rbd_add(struct bus_type *bus, /* parse add command */ rc = rbd_add_parse_args(buf, &ceph_opts, &rbd_opts, &spec); if (rc < 0) - goto err_out_module; + goto out; rbdc = rbd_get_client(ceph_opts); if (IS_ERR(rbdc)) { @@ -5432,8 +5436,10 @@ static ssize_t do_rbd_add(struct bus_type *bus, } rbd_dev = rbd_dev_create(rbdc, spec, rbd_opts); - if (!rbd_dev) + if (!rbd_dev) { + rc = -ENOMEM; goto err_out_client; + } rbdc = NULL; /* rbd_dev now owns this */ spec = NULL; /* rbd_dev now owns this */ rbd_opts = NULL; /* rbd_dev now owns this */ @@ -5458,10 +5464,13 @@ static ssize_t do_rbd_add(struct bus_type *bus, */ rbd_dev_header_unwatch_sync(rbd_dev); rbd_dev_image_release(rbd_dev); - goto err_out_module; + goto out; } - return count; + rc = count; +out: + module_put(THIS_MODULE); + return rc; err_out_rbd_dev: rbd_dev_destroy(rbd_dev); @@ -5470,12 +5479,7 @@ err_out_client: err_out_args: rbd_spec_put(spec); kfree(rbd_opts); -err_out_module: - module_put(THIS_MODULE); - - dout("Error adding device %s\n", buf); - - return (ssize_t)rc; + goto out; } static ssize_t rbd_add(struct bus_type *bus, @@ -5495,17 +5499,15 @@ static ssize_t rbd_add_single_major(struct bus_type *bus, return do_rbd_add(bus, buf, count); } -static void rbd_dev_device_release(struct device *dev) +static void rbd_dev_device_release(struct rbd_device *rbd_dev) { - struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); - rbd_free_disk(rbd_dev); clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags); + device_del(&rbd_dev->dev); rbd_dev_mapping_clear(rbd_dev); if (!single_major) unregister_blkdev(rbd_dev->major, rbd_dev->name); rbd_dev_id_put(rbd_dev); - rbd_dev_mapping_clear(rbd_dev); } static void rbd_dev_remove_parent(struct rbd_device *rbd_dev) @@ -5590,9 +5592,8 @@ static ssize_t do_rbd_remove(struct bus_type *bus, * rbd_bus_del_dev() will race with rbd_watch_cb(), resulting * in a potential use after free of rbd_dev->disk or rbd_dev. */ - rbd_bus_del_dev(rbd_dev); + rbd_dev_device_release(rbd_dev); rbd_dev_image_release(rbd_dev); - module_put(THIS_MODULE); return count; } @@ -5663,10 +5664,8 @@ static int rbd_slab_init(void) if (rbd_segment_name_cache) return 0; out_err: - if (rbd_obj_request_cache) { - kmem_cache_destroy(rbd_obj_request_cache); - rbd_obj_request_cache = NULL; - } + kmem_cache_destroy(rbd_obj_request_cache); + rbd_obj_request_cache = NULL; kmem_cache_destroy(rbd_img_request_cache); rbd_img_request_cache = NULL; diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index f26b0ae23bea..45cc39aabeee 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -226,21 +226,23 @@ int tpm_chip_register(struct tpm_chip *chip) if (rc) goto out_err; - if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { - rc = __compat_only_sysfs_link_entry_to_kobj(&chip->pdev->kobj, - &chip->dev.kobj, - "ppi"); - if (rc) - goto out_err; - } - /* Make the chip available. */ spin_lock(&driver_lock); - list_add_rcu(&chip->list, &tpm_chip_list); + list_add_tail_rcu(&chip->list, &tpm_chip_list); spin_unlock(&driver_lock); chip->flags |= TPM_CHIP_FLAG_REGISTERED; + if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { + rc = __compat_only_sysfs_link_entry_to_kobj(&chip->pdev->kobj, + &chip->dev.kobj, + "ppi"); + if (rc && rc != -ENOENT) { + tpm_chip_unregister(chip); + return rc; + } + } + return 0; out_err: tpm1_chip_unregister(chip); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index bd7039fafa8a..c12130485fc1 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -443,12 +443,13 @@ int tpm2_seal_trusted(struct tpm_chip *chip, TPM_DIGEST_SIZE); /* sensitive */ - tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len); + tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1); tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE); tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE); - tpm_buf_append_u16(&buf, payload->key_len); + tpm_buf_append_u16(&buf, payload->key_len + 1); tpm_buf_append(&buf, payload->key, payload->key_len); + tpm_buf_append_u8(&buf, payload->migratable); /* public */ tpm_buf_append_u16(&buf, 14); @@ -573,6 +574,8 @@ static int tpm2_unseal(struct tpm_chip *chip, u32 blob_handle) { struct tpm_buf buf; + u16 data_len; + u8 *data; int rc; rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); @@ -591,11 +594,13 @@ static int tpm2_unseal(struct tpm_chip *chip, rc = -EPERM; if (!rc) { - payload->key_len = be16_to_cpup( + data_len = be16_to_cpup( (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); + data = &buf.data[TPM_HEADER_SIZE + 6]; - memcpy(payload->key, &buf.data[TPM_HEADER_SIZE + 6], - payload->key_len); + memcpy(payload->key, data, data_len - 1); + payload->key_len = data_len - 1; + payload->migratable = data[data_len - 1]; } tpm_buf_destroy(&buf); diff --git a/drivers/char/tpm/tpm_of.c b/drivers/char/tpm/tpm_of.c index 1141456a4b1f..570f30c5c5f4 100644 --- a/drivers/char/tpm/tpm_of.c +++ b/drivers/char/tpm/tpm_of.c @@ -53,17 +53,18 @@ int read_log(struct tpm_bios_log *log) goto cleanup_eio; } - of_node_put(np); log->bios_event_log = kmalloc(*sizep, GFP_KERNEL); if (!log->bios_event_log) { pr_err("%s: ERROR - Not enough memory for BIOS measurements\n", __func__); + of_node_put(np); return -ENOMEM; } log->bios_event_log_end = log->bios_event_log + *sizep; memcpy(log->bios_event_log, __va(*basep), *sizep); + of_node_put(np); return 0; diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 696ef1d56b4f..65f7eecc45b0 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -645,6 +645,7 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info, { u32 vendor, intfcaps, intmask; int rc, i, irq_s, irq_e, probe; + int irq_r = -1; struct tpm_chip *chip; struct priv_data *priv; @@ -751,6 +752,7 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info, irq_s = ioread8(chip->vendor.iobase + TPM_INT_VECTOR(chip->vendor.locality)); + irq_r = irq_s; if (irq_s) { irq_e = irq_s; } else { @@ -805,6 +807,8 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info, iowrite32(intmask, chip->vendor.iobase + TPM_INT_ENABLE(chip->vendor.locality)); + + devm_free_irq(dev, i, chip); } } if (chip->vendor.irq) { @@ -831,7 +835,9 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info, chip->vendor.iobase + TPM_INT_ENABLE(chip->vendor.locality)); } - } + } else if (irq_r != -1) + iowrite8(irq_r, chip->vendor.iobase + + TPM_INT_VECTOR(chip->vendor.locality)); if (chip->flags & TPM_CHIP_FLAG_TPM2) { chip->vendor.timeout_a = msecs_to_jiffies(TPM2_TIMEOUT_A); diff --git a/drivers/clk/h8300/clk-div.c b/drivers/clk/h8300/clk-div.c index 1dd5d14d5dbe..d71d01157dbb 100644 --- a/drivers/clk/h8300/clk-div.c +++ b/drivers/clk/h8300/clk-div.c @@ -19,6 +19,7 @@ static void __init h8300_div_clk_setup(struct device_node *node) const char *parent_name; void __iomem *divcr = NULL; int width; + int offset; num_parents = of_clk_get_parent_count(node); if (num_parents < 1) { @@ -31,11 +32,14 @@ static void __init h8300_div_clk_setup(struct device_node *node) pr_err("%s: failed to map divide register", clk_name); goto error; } + offset = (unsigned long)divcr & 3; + offset = (3 - offset) * 8; + divcr = (void *)((unsigned long)divcr & ~3); parent_name = of_clk_get_parent_name(node, 0); of_property_read_u32(node, "renesas,width", &width); clk = clk_register_divider(NULL, clk_name, parent_name, - CLK_SET_RATE_GATE, divcr, 0, width, + CLK_SET_RATE_GATE, divcr, offset, width, CLK_DIVIDER_POWER_OF_TWO, &clklock); if (!IS_ERR(clk)) { of_clk_add_provider(node, of_clk_src_simple_get, clk); diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c index f1e42f8ce0fc..c5d256caa664 100644 --- a/drivers/cpufreq/arm_big_little.c +++ b/drivers/cpufreq/arm_big_little.c @@ -149,6 +149,19 @@ bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate) __func__, cpu, old_cluster, new_cluster, new_rate); ret = clk_set_rate(clk[new_cluster], new_rate * 1000); + if (!ret) { + /* + * FIXME: clk_set_rate hasn't returned an error here however it + * may be that clk_change_rate failed due to hardware or + * firmware issues and wasn't able to report that due to the + * current design of the clk core layer. To work around this + * problem we will read back the clock rate and check it is + * correct. This needs to be removed once clk core is fixed. + */ + if (clk_get_rate(clk[new_cluster]) != new_rate * 1000) + ret = -EIO; + } + if (WARN_ON(ret)) { pr_err("clk_set_rate failed: %d, new cluster: %d\n", ret, new_cluster); @@ -189,15 +202,6 @@ bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate) mutex_unlock(&cluster_lock[old_cluster]); } - /* - * FIXME: clk_set_rate has to handle the case where clk_change_rate - * can fail due to hardware or firmware issues. Until the clk core - * layer is fixed, we can check here. In most of the cases we will - * be reading only the cached value anyway. This needs to be removed - * once clk core is fixed. - */ - if (bL_cpufreq_get_rate(cpu) != new_rate) - return -EIO; return 0; } diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 93c219fab850..e8cb334094b0 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -166,8 +166,7 @@ static int __init cppc_cpufreq_init(void) out: for_each_possible_cpu(i) - if (all_cpu_data[i]) - kfree(all_cpu_data[i]); + kfree(all_cpu_data[i]); kfree(all_cpu_data); return -ENODEV; diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 11258c4c1b17..b260576ddb12 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -171,10 +171,6 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy, { int i; - mutex_lock(&cpufreq_governor_lock); - if (!policy->governor_enabled) - goto out_unlock; - if (!all_cpus) { /* * Use raw_smp_processor_id() to avoid preemptible warnings. @@ -188,9 +184,6 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy, for_each_cpu(i, policy->cpus) __gov_queue_work(i, dbs_data, delay); } - -out_unlock: - mutex_unlock(&cpufreq_governor_lock); } EXPORT_SYMBOL_GPL(gov_queue_work); @@ -229,13 +222,24 @@ static void dbs_timer(struct work_struct *work) struct cpu_dbs_info *cdbs = container_of(work, struct cpu_dbs_info, dwork.work); struct cpu_common_dbs_info *shared = cdbs->shared; - struct cpufreq_policy *policy = shared->policy; - struct dbs_data *dbs_data = policy->governor_data; + struct cpufreq_policy *policy; + struct dbs_data *dbs_data; unsigned int sampling_rate, delay; bool modify_all = true; mutex_lock(&shared->timer_mutex); + policy = shared->policy; + + /* + * Governor might already be disabled and there is no point continuing + * with the work-handler. + */ + if (!policy) + goto unlock; + + dbs_data = policy->governor_data; + if (dbs_data->cdata->governor == GOV_CONSERVATIVE) { struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; @@ -252,6 +256,7 @@ static void dbs_timer(struct work_struct *work) delay = dbs_data->cdata->gov_dbs_timer(cdbs, dbs_data, modify_all); gov_queue_work(dbs_data, policy, delay, modify_all); +unlock: mutex_unlock(&shared->timer_mutex); } @@ -478,9 +483,17 @@ static int cpufreq_governor_stop(struct cpufreq_policy *policy, if (!shared || !shared->policy) return -EBUSY; + /* + * Work-handler must see this updated, as it should not proceed any + * further after governor is disabled. And so timer_mutex is taken while + * updating this value. + */ + mutex_lock(&shared->timer_mutex); + shared->policy = NULL; + mutex_unlock(&shared->timer_mutex); + gov_cancel_work(dbs_data, policy); - shared->policy = NULL; mutex_destroy(&shared->timer_mutex); return 0; } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 93a3c635ea27..2e31d097def6 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -684,8 +684,6 @@ static void __init intel_pstate_sysfs_expose_params(void) static void intel_pstate_hwp_enable(struct cpudata *cpudata) { - pr_info("intel_pstate: HWP enabled\n"); - wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); } @@ -1557,8 +1555,10 @@ static int __init intel_pstate_init(void) if (!all_cpu_data) return -ENOMEM; - if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) + if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) { + pr_info("intel_pstate: HWP enabled\n"); hwp_active++; + } if (!hwp_active && hwp_only) goto out; @@ -1593,8 +1593,10 @@ static int __init intel_pstate_setup(char *str) if (!strcmp(str, "disable")) no_load = 1; - if (!strcmp(str, "no_hwp")) + if (!strcmp(str, "no_hwp")) { + pr_info("intel_pstate: HWP disabled\n"); no_hwp = 1; + } if (!strcmp(str, "force")) force_load = 1; if (!strcmp(str, "hwp_only")) diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index 9e231f52150c..051a8a8224cd 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -212,11 +212,11 @@ static void s5pv210_set_refresh(enum s5pv210_dmc_port ch, unsigned long freq) /* Find current DRAM frequency */ tmp = s5pv210_dram_conf[ch].freq; - do_div(tmp, freq); + tmp /= freq; tmp1 = s5pv210_dram_conf[ch].refresh; - do_div(tmp1, tmp); + tmp1 /= tmp; __raw_writel(tmp1, reg); } diff --git a/drivers/crypto/ccp/ccp-platform.c b/drivers/crypto/ccp/ccp-platform.c index 8b923b7e9389..01b50cb4c982 100644 --- a/drivers/crypto/ccp/ccp-platform.c +++ b/drivers/crypto/ccp/ccp-platform.c @@ -94,6 +94,7 @@ static int ccp_platform_probe(struct platform_device *pdev) struct ccp_device *ccp; struct ccp_platform *ccp_platform; struct device *dev = &pdev->dev; + enum dev_dma_attr attr; struct resource *ior; int ret; @@ -118,18 +119,24 @@ static int ccp_platform_probe(struct platform_device *pdev) } ccp->io_regs = ccp->io_map; - ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)); - if (ret) { - dev_err(dev, "dma_set_mask_and_coherent failed (%d)\n", ret); + attr = device_get_dma_attr(dev); + if (attr == DEV_DMA_NOT_SUPPORTED) { + dev_err(dev, "DMA is not supported"); goto e_err; } - ccp_platform->coherent = device_dma_is_coherent(ccp->dev); + ccp_platform->coherent = (attr == DEV_DMA_COHERENT); if (ccp_platform->coherent) ccp->axcache = CACHE_WB_NO_ALLOC; else ccp->axcache = CACHE_NONE; + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)); + if (ret) { + dev_err(dev, "dma_set_mask_and_coherent failed (%d)\n", ret); + goto e_err; + } + dev_set_drvdata(dev, ccp); ret = ccp_init(ccp); diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index eba6337f5860..2151ea551d3b 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -616,10 +616,18 @@ int drm_control(struct drm_device *dev, void *data, void drm_calc_timestamping_constants(struct drm_crtc *crtc, const struct drm_display_mode *mode) { - struct drm_vblank_crtc *vblank = &crtc->dev->vblank[drm_crtc_index(crtc)]; + struct drm_device *dev = crtc->dev; + unsigned int pipe = drm_crtc_index(crtc); + struct drm_vblank_crtc *vblank = &dev->vblank[pipe]; int linedur_ns = 0, framedur_ns = 0; int dotclock = mode->crtc_clock; + if (!dev->num_crtcs) + return; + + if (WARN_ON(pipe >= dev->num_crtcs)) + return; + /* Valid dotclock? */ if (dotclock > 0) { int frame_size = mode->crtc_htotal * mode->crtc_vtotal; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index d26e0cc7dc4b..f22e1e1ee64a 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -19,7 +19,6 @@ #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_fb_helper.h> -#include <drm/drm_of.h> #include <linux/dma-mapping.h> #include <linux/pm_runtime.h> #include <linux/module.h> @@ -419,6 +418,29 @@ static int compare_of(struct device *dev, void *data) return dev->of_node == np; } +static void rockchip_add_endpoints(struct device *dev, + struct component_match **match, + struct device_node *port) +{ + struct device_node *ep, *remote; + + for_each_child_of_node(port, ep) { + remote = of_graph_get_remote_port_parent(ep); + if (!remote || !of_device_is_available(remote)) { + of_node_put(remote); + continue; + } else if (!of_device_is_available(remote->parent)) { + dev_warn(dev, "parent device of %s is not available\n", + remote->full_name); + of_node_put(remote); + continue; + } + + component_match_add(dev, match, compare_of, remote); + of_node_put(remote); + } +} + static int rockchip_drm_bind(struct device *dev) { struct drm_device *drm; @@ -461,14 +483,61 @@ static const struct component_master_ops rockchip_drm_ops = { static int rockchip_drm_platform_probe(struct platform_device *pdev) { - int ret = drm_of_component_probe(&pdev->dev, compare_of, - &rockchip_drm_ops); + struct device *dev = &pdev->dev; + struct component_match *match = NULL; + struct device_node *np = dev->of_node; + struct device_node *port; + int i; - /* keep compatibility with old code that was returning -ENODEV */ - if (ret == -EINVAL) + if (!np) return -ENODEV; + /* + * Bind the crtc ports first, so that + * drm_of_find_possible_crtcs called from encoder .bind callbacks + * works as expected. + */ + for (i = 0;; i++) { + port = of_parse_phandle(np, "ports", i); + if (!port) + break; + + if (!of_device_is_available(port->parent)) { + of_node_put(port); + continue; + } - return ret; + component_match_add(dev, &match, compare_of, port->parent); + of_node_put(port); + } + + if (i == 0) { + dev_err(dev, "missing 'ports' property\n"); + return -ENODEV; + } + + if (!match) { + dev_err(dev, "No available vop found for display-subsystem.\n"); + return -ENODEV; + } + /* + * For each bound crtc, bind the encoders attached to its + * remote endpoint. + */ + for (i = 0;; i++) { + port = of_parse_phandle(np, "ports", i); + if (!port) + break; + + if (!of_device_is_available(port->parent)) { + of_node_put(port); + continue; + } + + rockchip_add_endpoints(dev, &match, port); + of_node_put(port); + } + + return component_master_add_with_match(dev, &rockchip_drm_ops, match); } static int rockchip_drm_platform_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/sti/Kconfig b/drivers/gpu/drm/sti/Kconfig index fbccc105819b..10c1b1926e6f 100644 --- a/drivers/gpu/drm/sti/Kconfig +++ b/drivers/gpu/drm/sti/Kconfig @@ -6,12 +6,6 @@ config DRM_STI select DRM_GEM_CMA_HELPER select DRM_KMS_CMA_HELPER select DRM_PANEL - select FW_LOADER_USER_HELPER_FALLBACK + select FW_LOADER help Choose this option to enable DRM on STM stiH41x chipset - -config DRM_STI_FBDEV - bool "DRM frame buffer device for STMicroelectronics SoC stiH41x Serie" - depends on DRM_STI - help - Choose this option to enable FBDEV on top of DRM for STM stiH41x chipset diff --git a/drivers/gpu/drm/sti/Makefile b/drivers/gpu/drm/sti/Makefile index e27490b492a5..b8057620b3b3 100644 --- a/drivers/gpu/drm/sti/Makefile +++ b/drivers/gpu/drm/sti/Makefile @@ -1,26 +1,23 @@ -sticompositor-y := \ +sti-drm-y := \ sti_mixer.o \ sti_gdp.o \ sti_vid.o \ sti_cursor.o \ sti_compositor.o \ sti_crtc.o \ - sti_plane.o - -stihdmi-y := sti_hdmi.o \ + sti_plane.o \ + sti_crtc.o \ + sti_plane.o \ + sti_hdmi.o \ sti_hdmi_tx3g0c55phy.o \ sti_hdmi_tx3g4c28phy.o \ - -stidvo-y := sti_dvo.o \ - sti_awg_utils.o - -obj-$(CONFIG_DRM_STI) = \ + sti_dvo.o \ + sti_awg_utils.o \ sti_vtg.o \ sti_vtac.o \ - stihdmi.o \ sti_hda.o \ sti_tvout.o \ - sticompositor.o \ sti_hqvdp.o \ - stidvo.o \ sti_drv.o + +obj-$(CONFIG_DRM_STI) = sti-drm.o diff --git a/drivers/gpu/drm/sti/sti_awg_utils.c b/drivers/gpu/drm/sti/sti_awg_utils.c index 6029a2e3db1d..00d0698be9d3 100644 --- a/drivers/gpu/drm/sti/sti_awg_utils.c +++ b/drivers/gpu/drm/sti/sti_awg_utils.c @@ -65,7 +65,6 @@ static int awg_generate_instr(enum opcode opcode, mux = 0; data_enable = 0; - arg = (arg << 22) >> 22; arg &= (0x3ff); break; case REPEAT: @@ -77,14 +76,12 @@ static int awg_generate_instr(enum opcode opcode, mux = 0; data_enable = 0; - arg = (arg << 22) >> 22; arg &= (0x3ff); break; case JUMP: mux = 0; data_enable = 0; arg |= 0x40; /* for jump instruction 7th bit is 1 */ - arg = (arg << 22) >> 22; arg &= 0x3ff; break; case STOP: @@ -94,7 +91,6 @@ static int awg_generate_instr(enum opcode opcode, case RPTSET: case RPLSET: case HOLD: - arg = (arg << 24) >> 24; arg &= (0x0ff); break; default: diff --git a/drivers/gpu/drm/sti/sti_compositor.c b/drivers/gpu/drm/sti/sti_compositor.c index c652627b1bca..afed2171beb9 100644 --- a/drivers/gpu/drm/sti/sti_compositor.c +++ b/drivers/gpu/drm/sti/sti_compositor.c @@ -263,7 +263,7 @@ static int sti_compositor_remove(struct platform_device *pdev) return 0; } -static struct platform_driver sti_compositor_driver = { +struct platform_driver sti_compositor_driver = { .driver = { .name = "sti-compositor", .of_match_table = compositor_of_match, @@ -272,8 +272,6 @@ static struct platform_driver sti_compositor_driver = { .remove = sti_compositor_remove, }; -module_platform_driver(sti_compositor_driver); - MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sti/sti_crtc.c b/drivers/gpu/drm/sti/sti_crtc.c index 493c4a3006ad..3ae09dcd4fd8 100644 --- a/drivers/gpu/drm/sti/sti_crtc.c +++ b/drivers/gpu/drm/sti/sti_crtc.c @@ -226,7 +226,7 @@ static void sti_crtc_atomic_flush(struct drm_crtc *crtc, } } -static struct drm_crtc_helper_funcs sti_crtc_helper_funcs = { +static const struct drm_crtc_helper_funcs sti_crtc_helper_funcs = { .enable = sti_crtc_enable, .disable = sti_crtc_disabling, .mode_fixup = sti_crtc_mode_fixup, @@ -254,15 +254,17 @@ static int sti_crtc_set_property(struct drm_crtc *crtc, int sti_crtc_vblank_cb(struct notifier_block *nb, unsigned long event, void *data) { - struct drm_device *drm_dev; struct sti_compositor *compo = container_of(nb, struct sti_compositor, vtg_vblank_nb); - int *crtc = data; + struct drm_crtc *crtc = data; + struct sti_mixer *mixer; unsigned long flags; struct sti_private *priv; + unsigned int pipe; - drm_dev = compo->mixer[*crtc]->drm_crtc.dev; - priv = drm_dev->dev_private; + priv = crtc->dev->dev_private; + pipe = drm_crtc_index(crtc); + mixer = compo->mixer[pipe]; if ((event != VTG_TOP_FIELD_EVENT) && (event != VTG_BOTTOM_FIELD_EVENT)) { @@ -270,30 +272,30 @@ int sti_crtc_vblank_cb(struct notifier_block *nb, return -EINVAL; } - drm_handle_vblank(drm_dev, *crtc); + drm_crtc_handle_vblank(crtc); - spin_lock_irqsave(&drm_dev->event_lock, flags); - if (compo->mixer[*crtc]->pending_event) { - drm_send_vblank_event(drm_dev, -1, - compo->mixer[*crtc]->pending_event); - drm_vblank_put(drm_dev, *crtc); - compo->mixer[*crtc]->pending_event = NULL; + spin_lock_irqsave(&crtc->dev->event_lock, flags); + if (mixer->pending_event) { + drm_crtc_send_vblank_event(crtc, mixer->pending_event); + drm_crtc_vblank_put(crtc); + mixer->pending_event = NULL; } - spin_unlock_irqrestore(&drm_dev->event_lock, flags); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); - if (compo->mixer[*crtc]->status == STI_MIXER_DISABLING) { + if (mixer->status == STI_MIXER_DISABLING) { struct drm_plane *p; /* Disable mixer only if all overlay planes (GDP and VDP) * are disabled */ - list_for_each_entry(p, &drm_dev->mode_config.plane_list, head) { + list_for_each_entry(p, &crtc->dev->mode_config.plane_list, + head) { struct sti_plane *plane = to_sti_plane(p); if ((plane->desc & STI_PLANE_TYPE_MASK) <= STI_VDP) if (plane->status != STI_PLANE_DISABLED) return 0; } - sti_crtc_disable(&compo->mixer[*crtc]->drm_crtc); + sti_crtc_disable(crtc); } return 0; @@ -304,25 +306,26 @@ int sti_crtc_enable_vblank(struct drm_device *dev, unsigned int pipe) struct sti_private *dev_priv = dev->dev_private; struct sti_compositor *compo = dev_priv->compo; struct notifier_block *vtg_vblank_nb = &compo->vtg_vblank_nb; + struct drm_crtc *crtc = &compo->mixer[pipe]->drm_crtc; DRM_DEBUG_DRIVER("\n"); if (sti_vtg_register_client(pipe == STI_MIXER_MAIN ? compo->vtg_main : compo->vtg_aux, - vtg_vblank_nb, pipe)) { + vtg_vblank_nb, crtc)) { DRM_ERROR("Cannot register VTG notifier\n"); return -EINVAL; } return 0; } -EXPORT_SYMBOL(sti_crtc_enable_vblank); void sti_crtc_disable_vblank(struct drm_device *drm_dev, unsigned int pipe) { struct sti_private *priv = drm_dev->dev_private; struct sti_compositor *compo = priv->compo; struct notifier_block *vtg_vblank_nb = &compo->vtg_vblank_nb; + struct drm_crtc *crtc = &compo->mixer[pipe]->drm_crtc; DRM_DEBUG_DRIVER("\n"); @@ -332,13 +335,12 @@ void sti_crtc_disable_vblank(struct drm_device *drm_dev, unsigned int pipe) /* free the resources of the pending requests */ if (compo->mixer[pipe]->pending_event) { - drm_vblank_put(drm_dev, pipe); + drm_crtc_vblank_put(crtc); compo->mixer[pipe]->pending_event = NULL; } } -EXPORT_SYMBOL(sti_crtc_disable_vblank); -static struct drm_crtc_funcs sti_crtc_funcs = { +static const struct drm_crtc_funcs sti_crtc_funcs = { .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, .destroy = sti_crtc_destroy, @@ -357,7 +359,6 @@ bool sti_crtc_is_main(struct drm_crtc *crtc) return false; } -EXPORT_SYMBOL(sti_crtc_is_main); int sti_crtc_init(struct drm_device *drm_dev, struct sti_mixer *mixer, struct drm_plane *primary, struct drm_plane *cursor) diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c index f8469967a0bf..1469987949d8 100644 --- a/drivers/gpu/drm/sti/sti_drv.c +++ b/drivers/gpu/drm/sti/sti_drv.c @@ -107,7 +107,7 @@ static int sti_atomic_commit(struct drm_device *drm, return 0; } -static struct drm_mode_config_funcs sti_mode_config_funcs = { +static const struct drm_mode_config_funcs sti_mode_config_funcs = { .fb_create = drm_fb_cma_create, .atomic_check = drm_atomic_helper_check, .atomic_commit = sti_atomic_commit, @@ -123,8 +123,8 @@ static void sti_mode_config_init(struct drm_device *dev) * this value would be used to check framebuffer size limitation * at drm_mode_addfb(). */ - dev->mode_config.max_width = STI_MAX_FB_HEIGHT; - dev->mode_config.max_height = STI_MAX_FB_WIDTH; + dev->mode_config.max_width = STI_MAX_FB_WIDTH; + dev->mode_config.max_height = STI_MAX_FB_HEIGHT; dev->mode_config.funcs = &sti_mode_config_funcs; } @@ -160,11 +160,10 @@ static int sti_load(struct drm_device *dev, unsigned long flags) drm_mode_config_reset(dev); -#ifdef CONFIG_DRM_STI_FBDEV drm_fbdev_cma_init(dev, 32, dev->mode_config.num_crtc, dev->mode_config.num_connector); -#endif + return 0; } @@ -287,7 +286,29 @@ static struct platform_driver sti_platform_driver = { }, }; -module_platform_driver(sti_platform_driver); +static struct platform_driver * const drivers[] = { + &sti_tvout_driver, + &sti_vtac_driver, + &sti_hqvdp_driver, + &sti_hdmi_driver, + &sti_hda_driver, + &sti_dvo_driver, + &sti_vtg_driver, + &sti_compositor_driver, + &sti_platform_driver, +}; + +static int sti_drm_init(void) +{ + return platform_register_drivers(drivers, ARRAY_SIZE(drivers)); +} +module_init(sti_drm_init); + +static void sti_drm_exit(void) +{ + platform_unregister_drivers(drivers, ARRAY_SIZE(drivers)); +} +module_exit(sti_drm_exit); MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); diff --git a/drivers/gpu/drm/sti/sti_drv.h b/drivers/gpu/drm/sti/sti_drv.h index 9372f69e1859..30ddc20841c3 100644 --- a/drivers/gpu/drm/sti/sti_drv.h +++ b/drivers/gpu/drm/sti/sti_drv.h @@ -32,4 +32,13 @@ struct sti_private { } commit; }; +extern struct platform_driver sti_tvout_driver; +extern struct platform_driver sti_vtac_driver; +extern struct platform_driver sti_hqvdp_driver; +extern struct platform_driver sti_hdmi_driver; +extern struct platform_driver sti_hda_driver; +extern struct platform_driver sti_dvo_driver; +extern struct platform_driver sti_vtg_driver; +extern struct platform_driver sti_compositor_driver; + #endif diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c index d141d645bd13..45cbe2bf7dd6 100644 --- a/drivers/gpu/drm/sti/sti_dvo.c +++ b/drivers/gpu/drm/sti/sti_dvo.c @@ -329,7 +329,8 @@ struct drm_encoder *sti_dvo_best_encoder(struct drm_connector *connector) return dvo_connector->encoder; } -static struct drm_connector_helper_funcs sti_dvo_connector_helper_funcs = { +static const +struct drm_connector_helper_funcs sti_dvo_connector_helper_funcs = { .get_modes = sti_dvo_connector_get_modes, .mode_valid = sti_dvo_connector_mode_valid, .best_encoder = sti_dvo_best_encoder, @@ -364,7 +365,7 @@ static void sti_dvo_connector_destroy(struct drm_connector *connector) kfree(dvo_connector); } -static struct drm_connector_funcs sti_dvo_connector_funcs = { +static const struct drm_connector_funcs sti_dvo_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .fill_modes = drm_helper_probe_single_connector_modes, .detect = sti_dvo_connector_detect, @@ -557,8 +558,6 @@ struct platform_driver sti_dvo_driver = { .remove = sti_dvo_remove, }; -module_platform_driver(sti_dvo_driver); - MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c index 9365670427ad..c85dc7d6b005 100644 --- a/drivers/gpu/drm/sti/sti_gdp.c +++ b/drivers/gpu/drm/sti/sti_gdp.c @@ -492,7 +492,7 @@ static void sti_gdp_atomic_update(struct drm_plane *drm_plane, /* Register gdp callback */ if (sti_vtg_register_client(mixer->id == STI_MIXER_MAIN ? compo->vtg_main : compo->vtg_aux, - &gdp->vtg_field_nb, mixer->id)) { + &gdp->vtg_field_nb, crtc)) { DRM_ERROR("Cannot register VTG notifier\n"); return; } diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index 598cd78b0b16..d735daccd458 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -589,7 +589,8 @@ struct drm_encoder *sti_hda_best_encoder(struct drm_connector *connector) return hda_connector->encoder; } -static struct drm_connector_helper_funcs sti_hda_connector_helper_funcs = { +static const +struct drm_connector_helper_funcs sti_hda_connector_helper_funcs = { .get_modes = sti_hda_connector_get_modes, .mode_valid = sti_hda_connector_mode_valid, .best_encoder = sti_hda_best_encoder, @@ -611,7 +612,7 @@ static void sti_hda_connector_destroy(struct drm_connector *connector) kfree(hda_connector); } -static struct drm_connector_funcs sti_hda_connector_funcs = { +static const struct drm_connector_funcs sti_hda_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .fill_modes = drm_helper_probe_single_connector_modes, .detect = sti_hda_connector_detect, @@ -784,8 +785,6 @@ struct platform_driver sti_hda_driver = { .remove = sti_hda_remove, }; -module_platform_driver(sti_hda_driver); - MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index 09e29e43423e..cd501563c0cc 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -628,7 +628,8 @@ struct drm_encoder *sti_hdmi_best_encoder(struct drm_connector *connector) return hdmi_connector->encoder; } -static struct drm_connector_helper_funcs sti_hdmi_connector_helper_funcs = { +static const +struct drm_connector_helper_funcs sti_hdmi_connector_helper_funcs = { .get_modes = sti_hdmi_connector_get_modes, .mode_valid = sti_hdmi_connector_mode_valid, .best_encoder = sti_hdmi_best_encoder, @@ -663,7 +664,7 @@ static void sti_hdmi_connector_destroy(struct drm_connector *connector) kfree(hdmi_connector); } -static struct drm_connector_funcs sti_hdmi_connector_funcs = { +static const struct drm_connector_funcs sti_hdmi_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .fill_modes = drm_helper_probe_single_connector_modes, .detect = sti_hdmi_connector_detect, @@ -700,18 +701,17 @@ static int sti_hdmi_bind(struct device *dev, struct device *master, void *data) encoder = sti_hdmi_find_encoder(drm_dev); if (!encoder) - goto err_adapt; + return -EINVAL; connector = devm_kzalloc(dev, sizeof(*connector), GFP_KERNEL); if (!connector) - goto err_adapt; - + return -EINVAL; connector->hdmi = hdmi; bridge = devm_kzalloc(dev, sizeof(*bridge), GFP_KERNEL); if (!bridge) - goto err_adapt; + return -EINVAL; bridge->driver_private = hdmi; bridge->funcs = &sti_hdmi_bridge_funcs; @@ -748,8 +748,7 @@ err_sysfs: drm_connector_unregister(drm_connector); err_connector: drm_connector_cleanup(drm_connector); -err_adapt: - put_device(&hdmi->ddc_adapt->dev); + return -EINVAL; } @@ -794,13 +793,10 @@ static int sti_hdmi_probe(struct platform_device *pdev) ddc = of_parse_phandle(pdev->dev.of_node, "ddc", 0); if (ddc) { - hdmi->ddc_adapt = of_find_i2c_adapter_by_node(ddc); - if (!hdmi->ddc_adapt) { - of_node_put(ddc); - return -EPROBE_DEFER; - } - + hdmi->ddc_adapt = of_get_i2c_adapter_by_node(ddc); of_node_put(ddc); + if (!hdmi->ddc_adapt) + return -EPROBE_DEFER; } hdmi->dev = pdev->dev; @@ -809,24 +805,29 @@ static int sti_hdmi_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hdmi-reg"); if (!res) { DRM_ERROR("Invalid hdmi resource\n"); - return -ENOMEM; + ret = -ENOMEM; + goto release_adapter; } hdmi->regs = devm_ioremap_nocache(dev, res->start, resource_size(res)); - if (!hdmi->regs) - return -ENOMEM; + if (!hdmi->regs) { + ret = -ENOMEM; + goto release_adapter; + } if (of_device_is_compatible(np, "st,stih416-hdmi")) { res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "syscfg"); if (!res) { DRM_ERROR("Invalid syscfg resource\n"); - return -ENOMEM; + ret = -ENOMEM; + goto release_adapter; } hdmi->syscfg = devm_ioremap_nocache(dev, res->start, resource_size(res)); - if (!hdmi->syscfg) - return -ENOMEM; - + if (!hdmi->syscfg) { + ret = -ENOMEM; + goto release_adapter; + } } hdmi->phy_ops = (struct hdmi_phy_ops *) @@ -836,25 +837,29 @@ static int sti_hdmi_probe(struct platform_device *pdev) hdmi->clk_pix = devm_clk_get(dev, "pix"); if (IS_ERR(hdmi->clk_pix)) { DRM_ERROR("Cannot get hdmi_pix clock\n"); - return PTR_ERR(hdmi->clk_pix); + ret = PTR_ERR(hdmi->clk_pix); + goto release_adapter; } hdmi->clk_tmds = devm_clk_get(dev, "tmds"); if (IS_ERR(hdmi->clk_tmds)) { DRM_ERROR("Cannot get hdmi_tmds clock\n"); - return PTR_ERR(hdmi->clk_tmds); + ret = PTR_ERR(hdmi->clk_tmds); + goto release_adapter; } hdmi->clk_phy = devm_clk_get(dev, "phy"); if (IS_ERR(hdmi->clk_phy)) { DRM_ERROR("Cannot get hdmi_phy clock\n"); - return PTR_ERR(hdmi->clk_phy); + ret = PTR_ERR(hdmi->clk_phy); + goto release_adapter; } hdmi->clk_audio = devm_clk_get(dev, "audio"); if (IS_ERR(hdmi->clk_audio)) { DRM_ERROR("Cannot get hdmi_audio clock\n"); - return PTR_ERR(hdmi->clk_audio); + ret = PTR_ERR(hdmi->clk_audio); + goto release_adapter; } hdmi->hpd = readl(hdmi->regs + HDMI_STA) & HDMI_STA_HOT_PLUG; @@ -867,7 +872,7 @@ static int sti_hdmi_probe(struct platform_device *pdev) hdmi_irq_thread, IRQF_ONESHOT, dev_name(dev), hdmi); if (ret) { DRM_ERROR("Failed to register HDMI interrupt\n"); - return ret; + goto release_adapter; } hdmi->reset = devm_reset_control_get(dev, "hdmi"); @@ -878,16 +883,20 @@ static int sti_hdmi_probe(struct platform_device *pdev) platform_set_drvdata(pdev, hdmi); return component_add(&pdev->dev, &sti_hdmi_ops); + + release_adapter: + i2c_put_adapter(hdmi->ddc_adapt); + + return ret; } static int sti_hdmi_remove(struct platform_device *pdev) { struct sti_hdmi *hdmi = dev_get_drvdata(&pdev->dev); - if (hdmi->ddc_adapt) - put_device(&hdmi->ddc_adapt->dev); - + i2c_put_adapter(hdmi->ddc_adapt); component_del(&pdev->dev, &sti_hdmi_ops); + return 0; } @@ -901,8 +910,6 @@ struct platform_driver sti_hdmi_driver = { .remove = sti_hdmi_remove, }; -module_platform_driver(sti_hdmi_driver); - MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c index 7c8f9b8bfae1..ea0690bc77d5 100644 --- a/drivers/gpu/drm/sti/sti_hqvdp.c +++ b/drivers/gpu/drm/sti/sti_hqvdp.c @@ -628,6 +628,153 @@ static void sti_hqvdp_init(struct sti_hqvdp *hqvdp) memset(hqvdp->hqvdp_cmd, 0, size); } +static void sti_hqvdp_init_plugs(struct sti_hqvdp *hqvdp) +{ + /* Configure Plugs (same for RD & WR) */ + writel(PLUG_PAGE_SIZE_256, hqvdp->regs + HQVDP_RD_PLUG_PAGE_SIZE); + writel(PLUG_MIN_OPC_8, hqvdp->regs + HQVDP_RD_PLUG_MIN_OPC); + writel(PLUG_MAX_OPC_64, hqvdp->regs + HQVDP_RD_PLUG_MAX_OPC); + writel(PLUG_MAX_CHK_2X, hqvdp->regs + HQVDP_RD_PLUG_MAX_CHK); + writel(PLUG_MAX_MSG_1X, hqvdp->regs + HQVDP_RD_PLUG_MAX_MSG); + writel(PLUG_MIN_SPACE_1, hqvdp->regs + HQVDP_RD_PLUG_MIN_SPACE); + writel(PLUG_CONTROL_ENABLE, hqvdp->regs + HQVDP_RD_PLUG_CONTROL); + + writel(PLUG_PAGE_SIZE_256, hqvdp->regs + HQVDP_WR_PLUG_PAGE_SIZE); + writel(PLUG_MIN_OPC_8, hqvdp->regs + HQVDP_WR_PLUG_MIN_OPC); + writel(PLUG_MAX_OPC_64, hqvdp->regs + HQVDP_WR_PLUG_MAX_OPC); + writel(PLUG_MAX_CHK_2X, hqvdp->regs + HQVDP_WR_PLUG_MAX_CHK); + writel(PLUG_MAX_MSG_1X, hqvdp->regs + HQVDP_WR_PLUG_MAX_MSG); + writel(PLUG_MIN_SPACE_1, hqvdp->regs + HQVDP_WR_PLUG_MIN_SPACE); + writel(PLUG_CONTROL_ENABLE, hqvdp->regs + HQVDP_WR_PLUG_CONTROL); +} + +/** + * sti_hqvdp_start_xp70 + * @hqvdp: hqvdp pointer + * + * Run the xP70 initialization sequence + */ +static void sti_hqvdp_start_xp70(struct sti_hqvdp *hqvdp) +{ + const struct firmware *firmware; + u32 *fw_rd_plug, *fw_wr_plug, *fw_pmem, *fw_dmem; + u8 *data; + int i; + struct fw_header { + int rd_size; + int wr_size; + int pmem_size; + int dmem_size; + } *header; + + DRM_DEBUG_DRIVER("\n"); + + if (hqvdp->xp70_initialized) { + DRM_INFO("HQVDP XP70 already initialized\n"); + return; + } + + /* Request firmware */ + if (request_firmware(&firmware, HQVDP_FMW_NAME, hqvdp->dev)) { + DRM_ERROR("Can't get HQVDP firmware\n"); + return; + } + + /* Check firmware parts */ + if (!firmware) { + DRM_ERROR("Firmware not available\n"); + return; + } + + header = (struct fw_header *)firmware->data; + if (firmware->size < sizeof(*header)) { + DRM_ERROR("Invalid firmware size (%d)\n", firmware->size); + goto out; + } + if ((sizeof(*header) + header->rd_size + header->wr_size + + header->pmem_size + header->dmem_size) != firmware->size) { + DRM_ERROR("Invalid fmw structure (%d+%d+%d+%d+%d != %d)\n", + sizeof(*header), header->rd_size, header->wr_size, + header->pmem_size, header->dmem_size, + firmware->size); + goto out; + } + + data = (u8 *)firmware->data; + data += sizeof(*header); + fw_rd_plug = (void *)data; + data += header->rd_size; + fw_wr_plug = (void *)data; + data += header->wr_size; + fw_pmem = (void *)data; + data += header->pmem_size; + fw_dmem = (void *)data; + + /* Enable clock */ + if (clk_prepare_enable(hqvdp->clk)) + DRM_ERROR("Failed to prepare/enable HQVDP clk\n"); + + /* Reset */ + writel(SW_RESET_CTRL_FULL, hqvdp->regs + HQVDP_MBX_SW_RESET_CTRL); + + for (i = 0; i < POLL_MAX_ATTEMPT; i++) { + if (readl(hqvdp->regs + HQVDP_MBX_STARTUP_CTRL1) + & STARTUP_CTRL1_RST_DONE) + break; + msleep(POLL_DELAY_MS); + } + if (i == POLL_MAX_ATTEMPT) { + DRM_ERROR("Could not reset\n"); + goto out; + } + + /* Init Read & Write plugs */ + for (i = 0; i < header->rd_size / 4; i++) + writel(fw_rd_plug[i], hqvdp->regs + HQVDP_RD_PLUG + i * 4); + for (i = 0; i < header->wr_size / 4; i++) + writel(fw_wr_plug[i], hqvdp->regs + HQVDP_WR_PLUG + i * 4); + + sti_hqvdp_init_plugs(hqvdp); + + /* Authorize Idle Mode */ + writel(STARTUP_CTRL1_AUTH_IDLE, hqvdp->regs + HQVDP_MBX_STARTUP_CTRL1); + + /* Prevent VTG interruption during the boot */ + writel(SOFT_VSYNC_SW_CTRL_IRQ, hqvdp->regs + HQVDP_MBX_SOFT_VSYNC); + writel(0, hqvdp->regs + HQVDP_MBX_NEXT_CMD); + + /* Download PMEM & DMEM */ + for (i = 0; i < header->pmem_size / 4; i++) + writel(fw_pmem[i], hqvdp->regs + HQVDP_PMEM + i * 4); + for (i = 0; i < header->dmem_size / 4; i++) + writel(fw_dmem[i], hqvdp->regs + HQVDP_DMEM + i * 4); + + /* Enable fetch */ + writel(STARTUP_CTRL2_FETCH_EN, hqvdp->regs + HQVDP_MBX_STARTUP_CTRL2); + + /* Wait end of boot */ + for (i = 0; i < POLL_MAX_ATTEMPT; i++) { + if (readl(hqvdp->regs + HQVDP_MBX_INFO_XP70) + & INFO_XP70_FW_READY) + break; + msleep(POLL_DELAY_MS); + } + if (i == POLL_MAX_ATTEMPT) { + DRM_ERROR("Could not boot\n"); + goto out; + } + + /* Launch Vsync */ + writel(SOFT_VSYNC_HW, hqvdp->regs + HQVDP_MBX_SOFT_VSYNC); + + DRM_INFO("HQVDP XP70 initialized\n"); + + hqvdp->xp70_initialized = true; + +out: + release_firmware(firmware); +} + static void sti_hqvdp_atomic_update(struct drm_plane *drm_plane, struct drm_plane_state *oldstate) { @@ -754,6 +901,9 @@ static void sti_hqvdp_atomic_update(struct drm_plane *drm_plane, sti_hqvdp_update_hvsrc(HVSRC_VERT, scale_v, &cmd->hvsrc); if (first_prepare) { + /* Start HQVDP XP70 coprocessor */ + sti_hqvdp_start_xp70(hqvdp); + /* Prevent VTG shutdown */ if (clk_prepare_enable(hqvdp->clk_pix_main)) { DRM_ERROR("Failed to prepare/enable pix main clk\n"); @@ -763,7 +913,7 @@ static void sti_hqvdp_atomic_update(struct drm_plane *drm_plane, /* Register VTG Vsync callback to handle bottom fields */ if (sti_vtg_register_client(hqvdp->vtg, &hqvdp->vtg_nb, - mixer->id)) { + crtc)) { DRM_ERROR("Cannot register VTG notifier\n"); return; } @@ -836,168 +986,16 @@ static struct drm_plane *sti_hqvdp_create(struct drm_device *drm_dev, return &hqvdp->plane.drm_plane; } -static void sti_hqvdp_init_plugs(struct sti_hqvdp *hqvdp) -{ - /* Configure Plugs (same for RD & WR) */ - writel(PLUG_PAGE_SIZE_256, hqvdp->regs + HQVDP_RD_PLUG_PAGE_SIZE); - writel(PLUG_MIN_OPC_8, hqvdp->regs + HQVDP_RD_PLUG_MIN_OPC); - writel(PLUG_MAX_OPC_64, hqvdp->regs + HQVDP_RD_PLUG_MAX_OPC); - writel(PLUG_MAX_CHK_2X, hqvdp->regs + HQVDP_RD_PLUG_MAX_CHK); - writel(PLUG_MAX_MSG_1X, hqvdp->regs + HQVDP_RD_PLUG_MAX_MSG); - writel(PLUG_MIN_SPACE_1, hqvdp->regs + HQVDP_RD_PLUG_MIN_SPACE); - writel(PLUG_CONTROL_ENABLE, hqvdp->regs + HQVDP_RD_PLUG_CONTROL); - - writel(PLUG_PAGE_SIZE_256, hqvdp->regs + HQVDP_WR_PLUG_PAGE_SIZE); - writel(PLUG_MIN_OPC_8, hqvdp->regs + HQVDP_WR_PLUG_MIN_OPC); - writel(PLUG_MAX_OPC_64, hqvdp->regs + HQVDP_WR_PLUG_MAX_OPC); - writel(PLUG_MAX_CHK_2X, hqvdp->regs + HQVDP_WR_PLUG_MAX_CHK); - writel(PLUG_MAX_MSG_1X, hqvdp->regs + HQVDP_WR_PLUG_MAX_MSG); - writel(PLUG_MIN_SPACE_1, hqvdp->regs + HQVDP_WR_PLUG_MIN_SPACE); - writel(PLUG_CONTROL_ENABLE, hqvdp->regs + HQVDP_WR_PLUG_CONTROL); -} - -/** - * sti_hqvdp_start_xp70 - * @firmware: firmware found - * @ctxt: hqvdp structure - * - * Run the xP70 initialization sequence - */ -static void sti_hqvdp_start_xp70(const struct firmware *firmware, void *ctxt) -{ - struct sti_hqvdp *hqvdp = ctxt; - u32 *fw_rd_plug, *fw_wr_plug, *fw_pmem, *fw_dmem; - u8 *data; - int i; - struct fw_header { - int rd_size; - int wr_size; - int pmem_size; - int dmem_size; - } *header; - - DRM_DEBUG_DRIVER("\n"); - - if (hqvdp->xp70_initialized) { - DRM_INFO("HQVDP XP70 already initialized\n"); - return; - } - - /* Check firmware parts */ - if (!firmware) { - DRM_ERROR("Firmware not available\n"); - return; - } - - header = (struct fw_header *) firmware->data; - if (firmware->size < sizeof(*header)) { - DRM_ERROR("Invalid firmware size (%d)\n", firmware->size); - goto out; - } - if ((sizeof(*header) + header->rd_size + header->wr_size + - header->pmem_size + header->dmem_size) != firmware->size) { - DRM_ERROR("Invalid fmw structure (%d+%d+%d+%d+%d != %d)\n", - sizeof(*header), header->rd_size, header->wr_size, - header->pmem_size, header->dmem_size, - firmware->size); - goto out; - } - - data = (u8 *) firmware->data; - data += sizeof(*header); - fw_rd_plug = (void *) data; - data += header->rd_size; - fw_wr_plug = (void *) data; - data += header->wr_size; - fw_pmem = (void *) data; - data += header->pmem_size; - fw_dmem = (void *) data; - - /* Enable clock */ - if (clk_prepare_enable(hqvdp->clk)) - DRM_ERROR("Failed to prepare/enable HQVDP clk\n"); - - /* Reset */ - writel(SW_RESET_CTRL_FULL, hqvdp->regs + HQVDP_MBX_SW_RESET_CTRL); - - for (i = 0; i < POLL_MAX_ATTEMPT; i++) { - if (readl(hqvdp->regs + HQVDP_MBX_STARTUP_CTRL1) - & STARTUP_CTRL1_RST_DONE) - break; - msleep(POLL_DELAY_MS); - } - if (i == POLL_MAX_ATTEMPT) { - DRM_ERROR("Could not reset\n"); - goto out; - } - - /* Init Read & Write plugs */ - for (i = 0; i < header->rd_size / 4; i++) - writel(fw_rd_plug[i], hqvdp->regs + HQVDP_RD_PLUG + i * 4); - for (i = 0; i < header->wr_size / 4; i++) - writel(fw_wr_plug[i], hqvdp->regs + HQVDP_WR_PLUG + i * 4); - - sti_hqvdp_init_plugs(hqvdp); - - /* Authorize Idle Mode */ - writel(STARTUP_CTRL1_AUTH_IDLE, hqvdp->regs + HQVDP_MBX_STARTUP_CTRL1); - - /* Prevent VTG interruption during the boot */ - writel(SOFT_VSYNC_SW_CTRL_IRQ, hqvdp->regs + HQVDP_MBX_SOFT_VSYNC); - writel(0, hqvdp->regs + HQVDP_MBX_NEXT_CMD); - - /* Download PMEM & DMEM */ - for (i = 0; i < header->pmem_size / 4; i++) - writel(fw_pmem[i], hqvdp->regs + HQVDP_PMEM + i * 4); - for (i = 0; i < header->dmem_size / 4; i++) - writel(fw_dmem[i], hqvdp->regs + HQVDP_DMEM + i * 4); - - /* Enable fetch */ - writel(STARTUP_CTRL2_FETCH_EN, hqvdp->regs + HQVDP_MBX_STARTUP_CTRL2); - - /* Wait end of boot */ - for (i = 0; i < POLL_MAX_ATTEMPT; i++) { - if (readl(hqvdp->regs + HQVDP_MBX_INFO_XP70) - & INFO_XP70_FW_READY) - break; - msleep(POLL_DELAY_MS); - } - if (i == POLL_MAX_ATTEMPT) { - DRM_ERROR("Could not boot\n"); - goto out; - } - - /* Launch Vsync */ - writel(SOFT_VSYNC_HW, hqvdp->regs + HQVDP_MBX_SOFT_VSYNC); - - DRM_INFO("HQVDP XP70 initialized\n"); - - hqvdp->xp70_initialized = true; - -out: - release_firmware(firmware); -} - int sti_hqvdp_bind(struct device *dev, struct device *master, void *data) { struct sti_hqvdp *hqvdp = dev_get_drvdata(dev); struct drm_device *drm_dev = data; struct drm_plane *plane; - int err; DRM_DEBUG_DRIVER("\n"); hqvdp->drm_dev = drm_dev; - /* Request for firmware */ - err = request_firmware_nowait(THIS_MODULE, FW_ACTION_HOTPLUG, - HQVDP_FMW_NAME, hqvdp->dev, - GFP_KERNEL, hqvdp, sti_hqvdp_start_xp70); - if (err) { - DRM_ERROR("Can't get HQVDP firmware\n"); - return err; - } - /* Create HQVDP plane once xp70 is initialized */ plane = sti_hqvdp_create(drm_dev, hqvdp->dev, STI_HQVDP_0); if (!plane) @@ -1090,8 +1088,6 @@ struct platform_driver sti_hqvdp_driver = { .remove = sti_hqvdp_remove, }; -module_platform_driver(sti_hqvdp_driver); - MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sti/sti_mixer.c b/drivers/gpu/drm/sti/sti_mixer.c index 0182e9365004..49db835dce03 100644 --- a/drivers/gpu/drm/sti/sti_mixer.c +++ b/drivers/gpu/drm/sti/sti_mixer.c @@ -10,6 +10,11 @@ #include "sti_mixer.h" #include "sti_vtg.h" +/* Module parameter to set the background color of the mixer */ +static unsigned int bkg_color = 0x000000; +MODULE_PARM_DESC(bkgcolor, "Value of the background color 0xRRGGBB"); +module_param_named(bkgcolor, bkg_color, int, 0644); + /* Identity: G=Y , B=Cb , R=Cr */ static const u32 mixerColorSpaceMatIdentity[] = { 0x10000000, 0x00000000, 0x10000000, 0x00001000, @@ -58,7 +63,6 @@ const char *sti_mixer_to_str(struct sti_mixer *mixer) return "<UNKNOWN MIXER>"; } } -EXPORT_SYMBOL(sti_mixer_to_str); static inline u32 sti_mixer_reg_read(struct sti_mixer *mixer, u32 reg_id) { @@ -81,11 +85,9 @@ void sti_mixer_set_background_status(struct sti_mixer *mixer, bool enable) } static void sti_mixer_set_background_color(struct sti_mixer *mixer, - u8 red, u8 green, u8 blue) + unsigned int rgb) { - u32 val = (red << 16) | (green << 8) | blue; - - sti_mixer_reg_write(mixer, GAM_MIXER_BKC, val); + sti_mixer_reg_write(mixer, GAM_MIXER_BKC, rgb); } static void sti_mixer_set_background_area(struct sti_mixer *mixer, @@ -175,7 +177,7 @@ int sti_mixer_active_video_area(struct sti_mixer *mixer, sti_mixer_reg_write(mixer, GAM_MIXER_AVO, ydo << 16 | xdo); sti_mixer_reg_write(mixer, GAM_MIXER_AVS, yds << 16 | xds); - sti_mixer_set_background_color(mixer, 0xFF, 0, 0); + sti_mixer_set_background_color(mixer, bkg_color); sti_mixer_set_background_area(mixer, mode); sti_mixer_set_background_status(mixer, true); diff --git a/drivers/gpu/drm/sti/sti_plane.c b/drivers/gpu/drm/sti/sti_plane.c index d5c5e91f2956..2e5c751910c5 100644 --- a/drivers/gpu/drm/sti/sti_plane.c +++ b/drivers/gpu/drm/sti/sti_plane.c @@ -42,7 +42,6 @@ const char *sti_plane_to_str(struct sti_plane *plane) return "<UNKNOWN PLANE>"; } } -EXPORT_SYMBOL(sti_plane_to_str); static void sti_plane_destroy(struct drm_plane *drm_plane) { @@ -108,7 +107,6 @@ void sti_plane_init_property(struct sti_plane *plane, plane->drm_plane.base.id, sti_plane_to_str(plane), plane->zorder); } -EXPORT_SYMBOL(sti_plane_init_property); struct drm_plane_funcs sti_plane_helpers_funcs = { .update_plane = drm_atomic_helper_update_plane, @@ -119,4 +117,3 @@ struct drm_plane_funcs sti_plane_helpers_funcs = { .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, }; -EXPORT_SYMBOL(sti_plane_helpers_funcs); diff --git a/drivers/gpu/drm/sti/sti_tvout.c b/drivers/gpu/drm/sti/sti_tvout.c index c1aac8e66fb5..c8a4c5dae2b6 100644 --- a/drivers/gpu/drm/sti/sti_tvout.c +++ b/drivers/gpu/drm/sti/sti_tvout.c @@ -735,8 +735,6 @@ struct platform_driver sti_tvout_driver = { .remove = sti_tvout_remove, }; -module_platform_driver(sti_tvout_driver); - MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sti/sti_vtac.c b/drivers/gpu/drm/sti/sti_vtac.c index 97bcdac23ae1..b1eb0d77630d 100644 --- a/drivers/gpu/drm/sti/sti_vtac.c +++ b/drivers/gpu/drm/sti/sti_vtac.c @@ -216,8 +216,6 @@ struct platform_driver sti_vtac_driver = { .remove = sti_vtac_remove, }; -module_platform_driver(sti_vtac_driver); - MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sti/sti_vtg.c b/drivers/gpu/drm/sti/sti_vtg.c index aa8097137701..d56630c60039 100644 --- a/drivers/gpu/drm/sti/sti_vtg.c +++ b/drivers/gpu/drm/sti/sti_vtg.c @@ -79,7 +79,7 @@ LIST_HEAD(vtg_lookup); * @irq: VTG irq * @type: VTG type (main or aux) * @notifier_list: notifier callback - * @crtc_id: the crtc id for vblank event + * @crtc: the CRTC for vblank event * @slave: slave vtg * @link: List node to link the structure in lookup list */ @@ -90,7 +90,7 @@ struct sti_vtg { int irq; u32 irq_status; struct raw_notifier_head notifier_list; - int crtc_id; + struct drm_crtc *crtc; struct sti_vtg *slave; struct list_head link; }; @@ -110,7 +110,6 @@ struct sti_vtg *of_vtg_find(struct device_node *np) } return NULL; } -EXPORT_SYMBOL(of_vtg_find); static void vtg_reset(struct sti_vtg *vtg) { @@ -242,7 +241,6 @@ void sti_vtg_set_config(struct sti_vtg *vtg, else vtg_enable_irq(vtg); } -EXPORT_SYMBOL(sti_vtg_set_config); /** * sti_vtg_get_line_number @@ -265,7 +263,6 @@ u32 sti_vtg_get_line_number(struct drm_display_mode mode, int y) return start_line + y; } -EXPORT_SYMBOL(sti_vtg_get_line_number); /** * sti_vtg_get_pixel_number @@ -281,18 +278,16 @@ u32 sti_vtg_get_pixel_number(struct drm_display_mode mode, int x) { return mode.htotal - mode.hsync_start + x; } -EXPORT_SYMBOL(sti_vtg_get_pixel_number); -int sti_vtg_register_client(struct sti_vtg *vtg, - struct notifier_block *nb, int crtc_id) +int sti_vtg_register_client(struct sti_vtg *vtg, struct notifier_block *nb, + struct drm_crtc *crtc) { if (vtg->slave) - return sti_vtg_register_client(vtg->slave, nb, crtc_id); + return sti_vtg_register_client(vtg->slave, nb, crtc); - vtg->crtc_id = crtc_id; + vtg->crtc = crtc; return raw_notifier_chain_register(&vtg->notifier_list, nb); } -EXPORT_SYMBOL(sti_vtg_register_client); int sti_vtg_unregister_client(struct sti_vtg *vtg, struct notifier_block *nb) { @@ -301,7 +296,6 @@ int sti_vtg_unregister_client(struct sti_vtg *vtg, struct notifier_block *nb) return raw_notifier_chain_unregister(&vtg->notifier_list, nb); } -EXPORT_SYMBOL(sti_vtg_unregister_client); static irqreturn_t vtg_irq_thread(int irq, void *arg) { @@ -311,7 +305,7 @@ static irqreturn_t vtg_irq_thread(int irq, void *arg) event = (vtg->irq_status & VTG_IRQ_TOP) ? VTG_TOP_FIELD_EVENT : VTG_BOTTOM_FIELD_EVENT; - raw_notifier_call_chain(&vtg->notifier_list, event, &vtg->crtc_id); + raw_notifier_call_chain(&vtg->notifier_list, event, vtg->crtc); return IRQ_HANDLED; } @@ -406,8 +400,6 @@ struct platform_driver sti_vtg_driver = { .remove = vtg_remove, }; -module_platform_driver(sti_vtg_driver); - MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); MODULE_DESCRIPTION("STMicroelectronics SoC DRM driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/sti/sti_vtg.h b/drivers/gpu/drm/sti/sti_vtg.h index e84d23f1f57f..cd2439f89d05 100644 --- a/drivers/gpu/drm/sti/sti_vtg.h +++ b/drivers/gpu/drm/sti/sti_vtg.h @@ -17,8 +17,8 @@ struct notifier_block; struct sti_vtg *of_vtg_find(struct device_node *np); void sti_vtg_set_config(struct sti_vtg *vtg, const struct drm_display_mode *mode); -int sti_vtg_register_client(struct sti_vtg *vtg, - struct notifier_block *nb, int crtc_id); +int sti_vtg_register_client(struct sti_vtg *vtg, struct notifier_block *nb, + struct drm_crtc *crtc); int sti_vtg_unregister_client(struct sti_vtg *vtg, struct notifier_block *nb); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 7dd893331785..618d952c2984 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -342,6 +342,7 @@ static int xgbe_probe(struct platform_device *pdev) struct resource *res; const char *phy_mode; unsigned int i, phy_memnum, phy_irqnum; + enum dev_dma_attr attr; int ret; DBGPR("--> xgbe_probe\n"); @@ -609,7 +610,12 @@ static int xgbe_probe(struct platform_device *pdev) goto err_io; /* Set the DMA coherency values */ - pdata->coherent = device_dma_is_coherent(pdata->dev); + attr = device_get_dma_attr(dev); + if (attr == DEV_DMA_NOT_SUPPORTED) { + dev_err(dev, "DMA is not supported"); + goto err_io; + } + pdata->coherent = (attr == DEV_DMA_COHERENT); if (pdata->coherent) { pdata->axdomain = XGBE_DMA_OS_AXDOMAIN; pdata->arcache = XGBE_DMA_OS_ARCACHE; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 3dfc28875cc3..8187df204695 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1725,7 +1725,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) { int result; u32 aqa; - u64 cap = readq(&dev->bar->cap); + u64 cap = lo_hi_readq(&dev->bar->cap); struct nvme_queue *nvmeq; unsigned page_shift = PAGE_SHIFT; unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12; @@ -1774,8 +1774,8 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES; writel(aqa, &dev->bar->aqa); - writeq(nvmeq->sq_dma_addr, &dev->bar->asq); - writeq(nvmeq->cq_dma_addr, &dev->bar->acq); + lo_hi_writeq(nvmeq->sq_dma_addr, &dev->bar->asq); + lo_hi_writeq(nvmeq->cq_dma_addr, &dev->bar->acq); result = nvme_enable_ctrl(dev, cap); if (result) @@ -2606,7 +2606,7 @@ static int nvme_dev_add(struct nvme_dev *dev) struct pci_dev *pdev = to_pci_dev(dev->dev); int res; struct nvme_id_ctrl *ctrl; - int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12; + int shift = NVME_CAP_MPSMIN(lo_hi_readq(&dev->bar->cap)) + 12; res = nvme_identify_ctrl(dev, &ctrl); if (res) { @@ -2622,6 +2622,8 @@ static int nvme_dev_add(struct nvme_dev *dev) memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr)); if (ctrl->mdts) dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9); + else + dev->max_hw_sectors = UINT_MAX; if ((pdev->vendor == PCI_VENDOR_ID_INTEL) && (pdev->device == 0x0953) && ctrl->vs[3]) { unsigned int max_hw_sectors; @@ -2695,7 +2697,7 @@ static int nvme_dev_map(struct nvme_dev *dev) goto unmap; } - cap = readq(&dev->bar->cap); + cap = lo_hi_readq(&dev->bar->cap); dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH); dev->db_stride = 1 << NVME_CAP_STRIDE(cap); dev->dbs = ((void __iomem *)dev->bar) + 4096; @@ -2758,7 +2760,7 @@ static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev) * queues than admin tags. */ set_current_state(TASK_RUNNING); - nvme_disable_ctrl(dev, readq(&dev->bar->cap)); + nvme_disable_ctrl(dev, lo_hi_readq(&dev->bar->cap)); nvme_clear_queue(dev->queues[0]); flush_kthread_worker(dq->worker); nvme_disable_queue(dev, 0); @@ -3401,6 +3403,7 @@ static const struct pci_error_handlers nvme_err_handler = { static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, + { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { 0, } }; MODULE_DEVICE_TABLE(pci, nvme_id_table); diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c index ff27177f49ed..b1449f71601c 100644 --- a/drivers/of/of_pci.c +++ b/drivers/of/of_pci.c @@ -143,26 +143,6 @@ void of_pci_check_probe_only(void) } EXPORT_SYMBOL_GPL(of_pci_check_probe_only); -/** - * of_pci_dma_configure - Setup DMA configuration - * @dev: ptr to pci_dev struct of the PCI device - * - * Function to update PCI devices's DMA configuration using the same - * info from the OF node of host bridge's parent (if any). - */ -void of_pci_dma_configure(struct pci_dev *pci_dev) -{ - struct device *dev = &pci_dev->dev; - struct device *bridge = pci_get_host_bridge_device(pci_dev); - - if (!bridge->parent) - return; - - of_dma_configure(dev, bridge->parent->of_node); - pci_put_host_bridge_device(bridge); -} -EXPORT_SYMBOL_GPL(of_pci_dma_configure); - #if defined(CONFIG_OF_ADDRESS) /** * of_pci_get_host_bridge_resources - Parse PCI host bridge resources from DT diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index f53b8e85f137..e735c728e3b3 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -6,6 +6,7 @@ #include <linux/delay.h> #include <linux/init.h> #include <linux/pci.h> +#include <linux/of_device.h> #include <linux/of_pci.h> #include <linux/pci_hotplug.h> #include <linux/slab.h> @@ -13,6 +14,7 @@ #include <linux/cpumask.h> #include <linux/pci-aspm.h> #include <linux/aer.h> +#include <linux/acpi.h> #include <asm-generic/pci-bridge.h> #include "pci.h" @@ -1672,6 +1674,34 @@ static void pci_set_msi_domain(struct pci_dev *dev) dev_set_msi_domain(&dev->dev, d); } +/** + * pci_dma_configure - Setup DMA configuration + * @dev: ptr to pci_dev struct of the PCI device + * + * Function to update PCI devices's DMA configuration using the same + * info from the OF node or ACPI node of host bridge's parent (if any). + */ +static void pci_dma_configure(struct pci_dev *dev) +{ + struct device *bridge = pci_get_host_bridge_device(dev); + + if (IS_ENABLED(CONFIG_OF) && dev->dev.of_node) { + if (bridge->parent) + of_dma_configure(&dev->dev, bridge->parent->of_node); + } else if (has_acpi_companion(bridge)) { + struct acpi_device *adev = to_acpi_device_node(bridge->fwnode); + enum dev_dma_attr attr = acpi_get_dma_attr(adev); + + if (attr == DEV_DMA_NOT_SUPPORTED) + dev_warn(&dev->dev, "DMA not supported.\n"); + else + arch_setup_dma_ops(&dev->dev, 0, 0, NULL, + attr == DEV_DMA_COHERENT); + } + + pci_put_host_bridge_device(bridge); +} + void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) { int ret; @@ -1685,7 +1715,7 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dev->dev.dma_mask = &dev->dma_mask; dev->dev.dma_parms = &dev->dma_parms; dev->dev.coherent_dma_mask = 0xffffffffull; - of_pci_dma_configure(dev); + pci_dma_configure(dev); pci_set_dma_max_seg_size(dev, 65536); pci_set_dma_seg_boundary(dev, 0xffffffff); diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 850d86ca685b..da6e2ce77495 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -31,6 +31,21 @@ menuconfig VFIO If you don't know what to do here, say N. +menuconfig VFIO_NOIOMMU + bool "VFIO No-IOMMU support" + depends on VFIO + help + VFIO is built on the ability to isolate devices using the IOMMU. + Only with an IOMMU can userspace access to DMA capable devices be + considered secure. VFIO No-IOMMU mode enables IOMMU groups for + devices without IOMMU backing for the purpose of re-using the VFIO + infrastructure in a non-secure mode. Use of this mode will result + in an unsupportable kernel and will therefore taint the kernel. + Device assignment to virtual machines is also not possible with + this mode since there is no IOMMU to provide DMA translation. + + If you don't know what to do here, say N. + source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" source "virt/lib/Kconfig" diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 964ad572aaee..32b88bd2c82c 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; - group = iommu_group_get(&pdev->dev); + group = vfio_iommu_group_get(&pdev->dev); if (!group) return -EINVAL; vdev = kzalloc(sizeof(*vdev), GFP_KERNEL); if (!vdev) { - iommu_group_put(group); + vfio_iommu_group_put(group, &pdev->dev); return -ENOMEM; } @@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) { - iommu_group_put(group); + vfio_iommu_group_put(group, &pdev->dev); kfree(vdev); return ret; } @@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!vdev) return; - iommu_group_put(pdev->dev.iommu_group); + vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); kfree(vdev); if (vfio_pci_is_vga(pdev)) { diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index ff75ca31a199..fe2b470d7ec6 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -46,7 +46,7 @@ * 0: Removed from the user visible capability list * FF: Variable length */ -static u8 pci_cap_length[] = { +static const u8 pci_cap_length[PCI_CAP_ID_MAX + 1] = { [PCI_CAP_ID_BASIC] = PCI_STD_HEADER_SIZEOF, /* pci config header */ [PCI_CAP_ID_PM] = PCI_PM_SIZEOF, [PCI_CAP_ID_AGP] = PCI_AGP_SIZEOF, @@ -74,7 +74,7 @@ static u8 pci_cap_length[] = { * 0: Removed or masked from the user visible capabilty list * FF: Variable length */ -static u16 pci_ext_cap_length[] = { +static const u16 pci_ext_cap_length[PCI_EXT_CAP_ID_MAX + 1] = { [PCI_EXT_CAP_ID_ERR] = PCI_ERR_ROOT_COMMAND, [PCI_EXT_CAP_ID_VC] = 0xFF, [PCI_EXT_CAP_ID_DSN] = PCI_EXT_CAP_DSN_SIZEOF, @@ -671,6 +671,73 @@ static int __init init_pci_cap_pm_perm(struct perm_bits *perm) return 0; } +static int vfio_vpd_config_write(struct vfio_pci_device *vdev, int pos, + int count, struct perm_bits *perm, + int offset, __le32 val) +{ + struct pci_dev *pdev = vdev->pdev; + __le16 *paddr = (__le16 *)(vdev->vconfig + pos - offset + PCI_VPD_ADDR); + __le32 *pdata = (__le32 *)(vdev->vconfig + pos - offset + PCI_VPD_DATA); + u16 addr; + u32 data; + + /* + * Write through to emulation. If the write includes the upper byte + * of PCI_VPD_ADDR, then the PCI_VPD_ADDR_F bit is written and we + * have work to do. + */ + count = vfio_default_config_write(vdev, pos, count, perm, offset, val); + if (count < 0 || offset > PCI_VPD_ADDR + 1 || + offset + count <= PCI_VPD_ADDR + 1) + return count; + + addr = le16_to_cpu(*paddr); + + if (addr & PCI_VPD_ADDR_F) { + data = le32_to_cpu(*pdata); + if (pci_write_vpd(pdev, addr & ~PCI_VPD_ADDR_F, 4, &data) != 4) + return count; + } else { + if (pci_read_vpd(pdev, addr, 4, &data) != 4) + return count; + *pdata = cpu_to_le32(data); + } + + /* + * Toggle PCI_VPD_ADDR_F in the emulated PCI_VPD_ADDR register to + * signal completion. If an error occurs above, we assume that not + * toggling this bit will induce a driver timeout. + */ + addr ^= PCI_VPD_ADDR_F; + *paddr = cpu_to_le16(addr); + + return count; +} + +/* Permissions for Vital Product Data capability */ +static int __init init_pci_cap_vpd_perm(struct perm_bits *perm) +{ + if (alloc_perm_bits(perm, pci_cap_length[PCI_CAP_ID_VPD])) + return -ENOMEM; + + perm->writefn = vfio_vpd_config_write; + + /* + * We always virtualize the next field so we can remove + * capabilities from the chain if we want to. + */ + p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE); + + /* + * Both the address and data registers are virtualized to + * enable access through the pci_vpd_read/write functions + */ + p_setw(perm, PCI_VPD_ADDR, (u16)ALL_VIRT, (u16)ALL_WRITE); + p_setd(perm, PCI_VPD_DATA, ALL_VIRT, ALL_WRITE); + + return 0; +} + /* Permissions for PCI-X capability */ static int __init init_pci_cap_pcix_perm(struct perm_bits *perm) { @@ -790,6 +857,7 @@ void vfio_pci_uninit_perm_bits(void) free_perm_bits(&cap_perms[PCI_CAP_ID_BASIC]); free_perm_bits(&cap_perms[PCI_CAP_ID_PM]); + free_perm_bits(&cap_perms[PCI_CAP_ID_VPD]); free_perm_bits(&cap_perms[PCI_CAP_ID_PCIX]); free_perm_bits(&cap_perms[PCI_CAP_ID_EXP]); free_perm_bits(&cap_perms[PCI_CAP_ID_AF]); @@ -807,7 +875,7 @@ int __init vfio_pci_init_perm_bits(void) /* Capabilities */ ret |= init_pci_cap_pm_perm(&cap_perms[PCI_CAP_ID_PM]); - cap_perms[PCI_CAP_ID_VPD].writefn = vfio_raw_config_write; + ret |= init_pci_cap_vpd_perm(&cap_perms[PCI_CAP_ID_VPD]); ret |= init_pci_cap_pcix_perm(&cap_perms[PCI_CAP_ID_PCIX]); cap_perms[PCI_CAP_ID_VNDR].writefn = vfio_raw_config_write; ret |= init_pci_cap_exp_perm(&cap_perms[PCI_CAP_ID_EXP]); diff --git a/drivers/vfio/platform/Makefile b/drivers/vfio/platform/Makefile index 9ce8afe28450..41a6224f5e6b 100644 --- a/drivers/vfio/platform/Makefile +++ b/drivers/vfio/platform/Makefile @@ -1,10 +1,12 @@ - -vfio-platform-y := vfio_platform.o vfio_platform_common.o vfio_platform_irq.o +vfio-platform-base-y := vfio_platform_common.o vfio_platform_irq.o +vfio-platform-y := vfio_platform.o obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform.o +obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform-base.o obj-$(CONFIG_VFIO_PLATFORM) += reset/ vfio-amba-y := vfio_amba.o obj-$(CONFIG_VFIO_AMBA) += vfio-amba.o +obj-$(CONFIG_VFIO_AMBA) += vfio-platform-base.o obj-$(CONFIG_VFIO_AMBA) += reset/ diff --git a/drivers/vfio/platform/reset/Kconfig b/drivers/vfio/platform/reset/Kconfig index 746b96b0003b..70cccc582bee 100644 --- a/drivers/vfio/platform/reset/Kconfig +++ b/drivers/vfio/platform/reset/Kconfig @@ -5,3 +5,11 @@ config VFIO_PLATFORM_CALXEDAXGMAC_RESET Enables the VFIO platform driver to handle reset for Calxeda xgmac If you don't know what to do here, say N. + +config VFIO_PLATFORM_AMDXGBE_RESET + tristate "VFIO support for AMD XGBE reset" + depends on VFIO_PLATFORM + help + Enables the VFIO platform driver to handle reset for AMD XGBE + + If you don't know what to do here, say N. diff --git a/drivers/vfio/platform/reset/Makefile b/drivers/vfio/platform/reset/Makefile index 2a486af9f8fa..93f4e232697b 100644 --- a/drivers/vfio/platform/reset/Makefile +++ b/drivers/vfio/platform/reset/Makefile @@ -1,5 +1,7 @@ vfio-platform-calxedaxgmac-y := vfio_platform_calxedaxgmac.o +vfio-platform-amdxgbe-y := vfio_platform_amdxgbe.o ccflags-y += -Idrivers/vfio/platform obj-$(CONFIG_VFIO_PLATFORM_CALXEDAXGMAC_RESET) += vfio-platform-calxedaxgmac.o +obj-$(CONFIG_VFIO_PLATFORM_AMDXGBE_RESET) += vfio-platform-amdxgbe.o diff --git a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c new file mode 100644 index 000000000000..da5356f48d0b --- /dev/null +++ b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c @@ -0,0 +1,127 @@ +/* + * VFIO platform driver specialized for AMD xgbe reset + * reset code is inherited from AMD xgbe native driver + * + * Copyright (c) 2015 Linaro Ltd. + * www.linaro.org + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <uapi/linux/mdio.h> +#include <linux/delay.h> + +#include "vfio_platform_private.h" + +#define DMA_MR 0x3000 +#define MAC_VR 0x0110 +#define DMA_ISR 0x3008 +#define MAC_ISR 0x00b0 +#define PCS_MMD_SELECT 0xff +#define MDIO_AN_INT 0x8002 +#define MDIO_AN_INTMASK 0x8001 + +static unsigned int xmdio_read(void *ioaddr, unsigned int mmd, + unsigned int reg) +{ + unsigned int mmd_address, value; + + mmd_address = (mmd << 16) | ((reg) & 0xffff); + iowrite32(mmd_address >> 8, ioaddr + (PCS_MMD_SELECT << 2)); + value = ioread32(ioaddr + ((mmd_address & 0xff) << 2)); + return value; +} + +static void xmdio_write(void *ioaddr, unsigned int mmd, + unsigned int reg, unsigned int value) +{ + unsigned int mmd_address; + + mmd_address = (mmd << 16) | ((reg) & 0xffff); + iowrite32(mmd_address >> 8, ioaddr + (PCS_MMD_SELECT << 2)); + iowrite32(value, ioaddr + ((mmd_address & 0xff) << 2)); +} + +int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev) +{ + struct vfio_platform_region *xgmac_regs = &vdev->regions[0]; + struct vfio_platform_region *xpcs_regs = &vdev->regions[1]; + u32 dma_mr_value, pcs_value, value; + unsigned int count; + + if (!xgmac_regs->ioaddr) { + xgmac_regs->ioaddr = + ioremap_nocache(xgmac_regs->addr, xgmac_regs->size); + if (!xgmac_regs->ioaddr) + return -ENOMEM; + } + if (!xpcs_regs->ioaddr) { + xpcs_regs->ioaddr = + ioremap_nocache(xpcs_regs->addr, xpcs_regs->size); + if (!xpcs_regs->ioaddr) + return -ENOMEM; + } + + /* reset the PHY through MDIO*/ + pcs_value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_PCS, MDIO_CTRL1); + pcs_value |= MDIO_CTRL1_RESET; + xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_PCS, MDIO_CTRL1, pcs_value); + + count = 50; + do { + msleep(20); + pcs_value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_PCS, + MDIO_CTRL1); + } while ((pcs_value & MDIO_CTRL1_RESET) && --count); + + if (pcs_value & MDIO_CTRL1_RESET) + pr_warn("%s XGBE PHY reset timeout\n", __func__); + + /* disable auto-negotiation */ + value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1); + value &= ~MDIO_AN_CTRL1_ENABLE; + xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1, value); + + /* disable AN IRQ */ + xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_AN_INTMASK, 0); + + /* clear AN IRQ */ + xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_AN_INT, 0); + + /* MAC software reset */ + dma_mr_value = ioread32(xgmac_regs->ioaddr + DMA_MR); + dma_mr_value |= 0x1; + iowrite32(dma_mr_value, xgmac_regs->ioaddr + DMA_MR); + + usleep_range(10, 15); + + count = 2000; + while (count-- && (ioread32(xgmac_regs->ioaddr + DMA_MR) & 1)) + usleep_range(500, 600); + + if (!count) + pr_warn("%s MAC SW reset failed\n", __func__); + + return 0; +} + +module_vfio_reset_handler("amd,xgbe-seattle-v1a", vfio_platform_amdxgbe_reset); + +MODULE_VERSION("0.1"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Eric Auger <eric.auger@linaro.org>"); +MODULE_DESCRIPTION("Reset support for AMD xgbe vfio platform device"); diff --git a/drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c b/drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c index 619dc7d22082..e3d3d948e661 100644 --- a/drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c +++ b/drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c @@ -30,8 +30,6 @@ #define DRIVER_AUTHOR "Eric Auger <eric.auger@linaro.org>" #define DRIVER_DESC "Reset support for Calxeda xgmac vfio platform device" -#define CALXEDAXGMAC_COMPAT "calxeda,hb-xgmac" - /* XGMAC Register definitions */ #define XGMAC_CONTROL 0x00000000 /* MAC Configuration */ @@ -61,24 +59,25 @@ static inline void xgmac_mac_disable(void __iomem *ioaddr) int vfio_platform_calxedaxgmac_reset(struct vfio_platform_device *vdev) { - struct vfio_platform_region reg = vdev->regions[0]; + struct vfio_platform_region *reg = &vdev->regions[0]; - if (!reg.ioaddr) { - reg.ioaddr = - ioremap_nocache(reg.addr, reg.size); - if (!reg.ioaddr) + if (!reg->ioaddr) { + reg->ioaddr = + ioremap_nocache(reg->addr, reg->size); + if (!reg->ioaddr) return -ENOMEM; } /* disable IRQ */ - writel(0, reg.ioaddr + XGMAC_DMA_INTR_ENA); + writel(0, reg->ioaddr + XGMAC_DMA_INTR_ENA); /* Disable the MAC core */ - xgmac_mac_disable(reg.ioaddr); + xgmac_mac_disable(reg->ioaddr); return 0; } -EXPORT_SYMBOL_GPL(vfio_platform_calxedaxgmac_reset); + +module_vfio_reset_handler("calxeda,hb-xgmac", vfio_platform_calxedaxgmac_reset); MODULE_VERSION(DRIVER_VERSION); MODULE_LICENSE("GPL v2"); diff --git a/drivers/vfio/platform/vfio_amba.c b/drivers/vfio/platform/vfio_amba.c index ff0331f72526..a66479bd0edf 100644 --- a/drivers/vfio/platform/vfio_amba.c +++ b/drivers/vfio/platform/vfio_amba.c @@ -67,6 +67,7 @@ static int vfio_amba_probe(struct amba_device *adev, const struct amba_id *id) vdev->flags = VFIO_DEVICE_FLAGS_AMBA; vdev->get_resource = get_amba_resource; vdev->get_irq = get_amba_irq; + vdev->parent_module = THIS_MODULE; ret = vfio_platform_probe_common(vdev, &adev->dev); if (ret) { diff --git a/drivers/vfio/platform/vfio_platform.c b/drivers/vfio/platform/vfio_platform.c index cef645c83996..f1625dcfbb23 100644 --- a/drivers/vfio/platform/vfio_platform.c +++ b/drivers/vfio/platform/vfio_platform.c @@ -65,6 +65,7 @@ static int vfio_platform_probe(struct platform_device *pdev) vdev->flags = VFIO_DEVICE_FLAGS_PLATFORM; vdev->get_resource = get_platform_resource; vdev->get_irq = get_platform_irq; + vdev->parent_module = THIS_MODULE; ret = vfio_platform_probe_common(vdev, &pdev->dev); if (ret) diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index e43efb5e92bf..a1c50d630792 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -23,44 +23,50 @@ #include "vfio_platform_private.h" -static DEFINE_MUTEX(driver_lock); +#define DRIVER_VERSION "0.10" +#define DRIVER_AUTHOR "Antonios Motakis <a.motakis@virtualopensystems.com>" +#define DRIVER_DESC "VFIO platform base module" -static const struct vfio_platform_reset_combo reset_lookup_table[] = { - { - .compat = "calxeda,hb-xgmac", - .reset_function_name = "vfio_platform_calxedaxgmac_reset", - .module_name = "vfio-platform-calxedaxgmac", - }, -}; +static LIST_HEAD(reset_list); +static DEFINE_MUTEX(driver_lock); -static void vfio_platform_get_reset(struct vfio_platform_device *vdev, - struct device *dev) +static vfio_platform_reset_fn_t vfio_platform_lookup_reset(const char *compat, + struct module **module) { - const char *compat; - int (*reset)(struct vfio_platform_device *); - int ret, i; - - ret = device_property_read_string(dev, "compatible", &compat); - if (ret) - return; - - for (i = 0 ; i < ARRAY_SIZE(reset_lookup_table); i++) { - if (!strcmp(reset_lookup_table[i].compat, compat)) { - request_module(reset_lookup_table[i].module_name); - reset = __symbol_get( - reset_lookup_table[i].reset_function_name); - if (reset) { - vdev->reset = reset; - return; - } + struct vfio_platform_reset_node *iter; + vfio_platform_reset_fn_t reset_fn = NULL; + + mutex_lock(&driver_lock); + list_for_each_entry(iter, &reset_list, link) { + if (!strcmp(iter->compat, compat) && + try_module_get(iter->owner)) { + *module = iter->owner; + reset_fn = iter->reset; + break; } } + mutex_unlock(&driver_lock); + return reset_fn; +} + +static void vfio_platform_get_reset(struct vfio_platform_device *vdev) +{ + char modname[256]; + + vdev->reset = vfio_platform_lookup_reset(vdev->compat, + &vdev->reset_module); + if (!vdev->reset) { + snprintf(modname, 256, "vfio-reset:%s", vdev->compat); + request_module(modname); + vdev->reset = vfio_platform_lookup_reset(vdev->compat, + &vdev->reset_module); + } } static void vfio_platform_put_reset(struct vfio_platform_device *vdev) { if (vdev->reset) - symbol_put_addr(vdev->reset); + module_put(vdev->reset_module); } static int vfio_platform_regions_init(struct vfio_platform_device *vdev) @@ -138,15 +144,19 @@ static void vfio_platform_release(void *device_data) mutex_lock(&driver_lock); if (!(--vdev->refcnt)) { - if (vdev->reset) + if (vdev->reset) { + dev_info(vdev->device, "reset\n"); vdev->reset(vdev); + } else { + dev_warn(vdev->device, "no reset function found!\n"); + } vfio_platform_regions_cleanup(vdev); vfio_platform_irq_cleanup(vdev); } mutex_unlock(&driver_lock); - module_put(THIS_MODULE); + module_put(vdev->parent_module); } static int vfio_platform_open(void *device_data) @@ -154,7 +164,7 @@ static int vfio_platform_open(void *device_data) struct vfio_platform_device *vdev = device_data; int ret; - if (!try_module_get(THIS_MODULE)) + if (!try_module_get(vdev->parent_module)) return -ENODEV; mutex_lock(&driver_lock); @@ -168,8 +178,12 @@ static int vfio_platform_open(void *device_data) if (ret) goto err_irq; - if (vdev->reset) + if (vdev->reset) { + dev_info(vdev->device, "reset\n"); vdev->reset(vdev); + } else { + dev_warn(vdev->device, "no reset function found!\n"); + } } vdev->refcnt++; @@ -307,17 +321,17 @@ static long vfio_platform_ioctl(void *device_data, return -ENOTTY; } -static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg, +static ssize_t vfio_platform_read_mmio(struct vfio_platform_region *reg, char __user *buf, size_t count, loff_t off) { unsigned int done = 0; - if (!reg.ioaddr) { - reg.ioaddr = - ioremap_nocache(reg.addr, reg.size); + if (!reg->ioaddr) { + reg->ioaddr = + ioremap_nocache(reg->addr, reg->size); - if (!reg.ioaddr) + if (!reg->ioaddr) return -ENOMEM; } @@ -327,7 +341,7 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg, if (count >= 4 && !(off % 4)) { u32 val; - val = ioread32(reg.ioaddr + off); + val = ioread32(reg->ioaddr + off); if (copy_to_user(buf, &val, 4)) goto err; @@ -335,7 +349,7 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg, } else if (count >= 2 && !(off % 2)) { u16 val; - val = ioread16(reg.ioaddr + off); + val = ioread16(reg->ioaddr + off); if (copy_to_user(buf, &val, 2)) goto err; @@ -343,7 +357,7 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region reg, } else { u8 val; - val = ioread8(reg.ioaddr + off); + val = ioread8(reg->ioaddr + off); if (copy_to_user(buf, &val, 1)) goto err; @@ -376,7 +390,7 @@ static ssize_t vfio_platform_read(void *device_data, char __user *buf, return -EINVAL; if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO) - return vfio_platform_read_mmio(vdev->regions[index], + return vfio_platform_read_mmio(&vdev->regions[index], buf, count, off); else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO) return -EINVAL; /* not implemented */ @@ -384,17 +398,17 @@ static ssize_t vfio_platform_read(void *device_data, char __user *buf, return -EINVAL; } -static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg, +static ssize_t vfio_platform_write_mmio(struct vfio_platform_region *reg, const char __user *buf, size_t count, loff_t off) { unsigned int done = 0; - if (!reg.ioaddr) { - reg.ioaddr = - ioremap_nocache(reg.addr, reg.size); + if (!reg->ioaddr) { + reg->ioaddr = + ioremap_nocache(reg->addr, reg->size); - if (!reg.ioaddr) + if (!reg->ioaddr) return -ENOMEM; } @@ -406,7 +420,7 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg, if (copy_from_user(&val, buf, 4)) goto err; - iowrite32(val, reg.ioaddr + off); + iowrite32(val, reg->ioaddr + off); filled = 4; } else if (count >= 2 && !(off % 2)) { @@ -414,7 +428,7 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg, if (copy_from_user(&val, buf, 2)) goto err; - iowrite16(val, reg.ioaddr + off); + iowrite16(val, reg->ioaddr + off); filled = 2; } else { @@ -422,7 +436,7 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region reg, if (copy_from_user(&val, buf, 1)) goto err; - iowrite8(val, reg.ioaddr + off); + iowrite8(val, reg->ioaddr + off); filled = 1; } @@ -452,7 +466,7 @@ static ssize_t vfio_platform_write(void *device_data, const char __user *buf, return -EINVAL; if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO) - return vfio_platform_write_mmio(vdev->regions[index], + return vfio_platform_write_mmio(&vdev->regions[index], buf, count, off); else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO) return -EINVAL; /* not implemented */ @@ -539,6 +553,14 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev, if (!vdev) return -EINVAL; + ret = device_property_read_string(dev, "compatible", &vdev->compat); + if (ret) { + pr_err("VFIO: cannot retrieve compat for %s\n", vdev->name); + return -EINVAL; + } + + vdev->device = dev; + group = iommu_group_get(dev); if (!group) { pr_err("VFIO: No IOMMU group for device %s\n", vdev->name); @@ -551,7 +573,7 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev, return ret; } - vfio_platform_get_reset(vdev, dev); + vfio_platform_get_reset(vdev); mutex_init(&vdev->igate); @@ -573,3 +595,34 @@ struct vfio_platform_device *vfio_platform_remove_common(struct device *dev) return vdev; } EXPORT_SYMBOL_GPL(vfio_platform_remove_common); + +void __vfio_platform_register_reset(struct vfio_platform_reset_node *node) +{ + mutex_lock(&driver_lock); + list_add(&node->link, &reset_list); + mutex_unlock(&driver_lock); +} +EXPORT_SYMBOL_GPL(__vfio_platform_register_reset); + +void vfio_platform_unregister_reset(const char *compat, + vfio_platform_reset_fn_t fn) +{ + struct vfio_platform_reset_node *iter, *temp; + + mutex_lock(&driver_lock); + list_for_each_entry_safe(iter, temp, &reset_list, link) { + if (!strcmp(iter->compat, compat) && (iter->reset == fn)) { + list_del(&iter->link); + break; + } + } + + mutex_unlock(&driver_lock); + +} +EXPORT_SYMBOL_GPL(vfio_platform_unregister_reset); + +MODULE_VERSION(DRIVER_VERSION); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR(DRIVER_AUTHOR); +MODULE_DESCRIPTION(DRIVER_DESC); diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c index 88bba57b30a8..46d4750f43a8 100644 --- a/drivers/vfio/platform/vfio_platform_irq.c +++ b/drivers/vfio/platform/vfio_platform_irq.c @@ -185,6 +185,7 @@ static int vfio_set_trigger(struct vfio_platform_device *vdev, int index, int ret; if (irq->trigger) { + irq_clear_status_flags(irq->hwirq, IRQ_NOAUTOEN); free_irq(irq->hwirq, irq); kfree(irq->name); eventfd_ctx_put(irq->trigger); diff --git a/drivers/vfio/platform/vfio_platform_private.h b/drivers/vfio/platform/vfio_platform_private.h index 1c9b3d59543c..42816dd280cb 100644 --- a/drivers/vfio/platform/vfio_platform_private.h +++ b/drivers/vfio/platform/vfio_platform_private.h @@ -56,6 +56,10 @@ struct vfio_platform_device { u32 num_irqs; int refcnt; struct mutex igate; + struct module *parent_module; + const char *compat; + struct module *reset_module; + struct device *device; /* * These fields should be filled by the bus specific binder @@ -70,10 +74,13 @@ struct vfio_platform_device { int (*reset)(struct vfio_platform_device *vdev); }; -struct vfio_platform_reset_combo { - const char *compat; - const char *reset_function_name; - const char *module_name; +typedef int (*vfio_platform_reset_fn_t)(struct vfio_platform_device *vdev); + +struct vfio_platform_reset_node { + struct list_head link; + char *compat; + struct module *owner; + vfio_platform_reset_fn_t reset; }; extern int vfio_platform_probe_common(struct vfio_platform_device *vdev, @@ -89,4 +96,29 @@ extern int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, unsigned start, unsigned count, void *data); +extern void __vfio_platform_register_reset(struct vfio_platform_reset_node *n); +extern void vfio_platform_unregister_reset(const char *compat, + vfio_platform_reset_fn_t fn); +#define vfio_platform_register_reset(__compat, __reset) \ +static struct vfio_platform_reset_node __reset ## _node = { \ + .owner = THIS_MODULE, \ + .compat = __compat, \ + .reset = __reset, \ +}; \ +__vfio_platform_register_reset(&__reset ## _node) + +#define module_vfio_reset_handler(compat, reset) \ +MODULE_ALIAS("vfio-reset:" compat); \ +static int __init reset ## _module_init(void) \ +{ \ + vfio_platform_register_reset(compat, reset); \ + return 0; \ +}; \ +static void __exit reset ## _module_exit(void) \ +{ \ + vfio_platform_unregister_reset(compat, reset); \ +}; \ +module_init(reset ## _module_init); \ +module_exit(reset ## _module_exit) + #endif /* VFIO_PLATFORM_PRIVATE_H */ diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 563c510f285c..de632da2e22f 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -25,6 +25,7 @@ #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/pci.h> #include <linux/rwsem.h> #include <linux/sched.h> #include <linux/slab.h> @@ -61,6 +62,7 @@ struct vfio_container { struct rw_semaphore group_lock; struct vfio_iommu_driver *iommu_driver; void *iommu_data; + bool noiommu; }; struct vfio_unbound_dev { @@ -83,6 +85,7 @@ struct vfio_group { struct list_head unbound_list; struct mutex unbound_lock; atomic_t opened; + bool noiommu; }; struct vfio_device { @@ -94,6 +97,147 @@ struct vfio_device { void *device_data; }; +#ifdef CONFIG_VFIO_NOIOMMU +static bool noiommu __read_mostly; +module_param_named(enable_unsafe_noiommu_support, + noiommu, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); +#endif + +/* + * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe + * and remove functions, any use cases other than acquiring the first + * reference for the purpose of calling vfio_add_group_dev() or removing + * that symmetric reference after vfio_del_group_dev() should use the raw + * iommu_group_{get,put} functions. In particular, vfio_iommu_group_put() + * removes the device from the dummy group and cannot be nested. + */ +struct iommu_group *vfio_iommu_group_get(struct device *dev) +{ + struct iommu_group *group; + int __maybe_unused ret; + + group = iommu_group_get(dev); + +#ifdef CONFIG_VFIO_NOIOMMU + /* + * With noiommu enabled, an IOMMU group will be created for a device + * that doesn't already have one and doesn't have an iommu_ops on their + * bus. We use iommu_present() again in the main code to detect these + * fake groups. + */ + if (group || !noiommu || iommu_present(dev->bus)) + return group; + + group = iommu_group_alloc(); + if (IS_ERR(group)) + return NULL; + + iommu_group_set_name(group, "vfio-noiommu"); + ret = iommu_group_add_device(group, dev); + iommu_group_put(group); + if (ret) + return NULL; + + /* + * Where to taint? At this point we've added an IOMMU group for a + * device that is not backed by iommu_ops, therefore any iommu_ + * callback using iommu_ops can legitimately Oops. So, while we may + * be about to give a DMA capable device to a user without IOMMU + * protection, which is clearly taint-worthy, let's go ahead and do + * it here. + */ + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n"); +#endif + + return group; +} +EXPORT_SYMBOL_GPL(vfio_iommu_group_get); + +void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) +{ +#ifdef CONFIG_VFIO_NOIOMMU + if (!iommu_present(dev->bus)) + iommu_group_remove_device(dev); +#endif + + iommu_group_put(group); +} +EXPORT_SYMBOL_GPL(vfio_iommu_group_put); + +#ifdef CONFIG_VFIO_NOIOMMU +static void *vfio_noiommu_open(unsigned long arg) +{ + if (arg != VFIO_NOIOMMU_IOMMU) + return ERR_PTR(-EINVAL); + if (!capable(CAP_SYS_RAWIO)) + return ERR_PTR(-EPERM); + + return NULL; +} + +static void vfio_noiommu_release(void *iommu_data) +{ +} + +static long vfio_noiommu_ioctl(void *iommu_data, + unsigned int cmd, unsigned long arg) +{ + if (cmd == VFIO_CHECK_EXTENSION) + return arg == VFIO_NOIOMMU_IOMMU ? 1 : 0; + + return -ENOTTY; +} + +static int vfio_iommu_present(struct device *dev, void *unused) +{ + return iommu_present(dev->bus) ? 1 : 0; +} + +static int vfio_noiommu_attach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ + return iommu_group_for_each_dev(iommu_group, NULL, + vfio_iommu_present) ? -EINVAL : 0; +} + +static void vfio_noiommu_detach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ +} + +static struct vfio_iommu_driver_ops vfio_noiommu_ops = { + .name = "vfio-noiommu", + .owner = THIS_MODULE, + .open = vfio_noiommu_open, + .release = vfio_noiommu_release, + .ioctl = vfio_noiommu_ioctl, + .attach_group = vfio_noiommu_attach_group, + .detach_group = vfio_noiommu_detach_group, +}; + +static struct vfio_iommu_driver vfio_noiommu_driver = { + .ops = &vfio_noiommu_ops, +}; + +/* + * Wrap IOMMU drivers, the noiommu driver is the one and only driver for + * noiommu groups (and thus containers) and not available for normal groups. + */ +#define vfio_for_each_iommu_driver(con, pos) \ + for (pos = con->noiommu ? &vfio_noiommu_driver : \ + list_first_entry(&vfio.iommu_drivers_list, \ + struct vfio_iommu_driver, vfio_next); \ + (con->noiommu ? pos != NULL : \ + &pos->vfio_next != &vfio.iommu_drivers_list); \ + pos = con->noiommu ? NULL : list_next_entry(pos, vfio_next)) +#else +#define vfio_for_each_iommu_driver(con, pos) \ + list_for_each_entry(pos, &vfio.iommu_drivers_list, vfio_next) +#endif + + /** * IOMMU driver registration */ @@ -198,7 +342,8 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) /** * Group objects - create, release, get, put, search */ -static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) +static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, + bool noiommu) { struct vfio_group *group, *tmp; struct device *dev; @@ -216,6 +361,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) atomic_set(&group->container_users, 0); atomic_set(&group->opened, 0); group->iommu_group = iommu_group; + group->noiommu = noiommu; group->nb.notifier_call = vfio_iommu_group_notifier; @@ -251,7 +397,8 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) dev = device_create(vfio.class, NULL, MKDEV(MAJOR(vfio.group_devt), minor), - group, "%d", iommu_group_id(iommu_group)); + group, "%s%d", noiommu ? "noiommu-" : "", + iommu_group_id(iommu_group)); if (IS_ERR(dev)) { vfio_free_group_minor(minor); vfio_group_unlock_and_free(group); @@ -438,16 +585,33 @@ static struct vfio_device *vfio_group_get_device(struct vfio_group *group, } /* - * Whitelist some drivers that we know are safe (no dma) or just sit on - * a device. It's not always practical to leave a device within a group - * driverless as it could get re-bound to something unsafe. + * Some drivers, like pci-stub, are only used to prevent other drivers from + * claiming a device and are therefore perfectly legitimate for a user owned + * group. The pci-stub driver has no dependencies on DMA or the IOVA mapping + * of the device, but it does prevent the user from having direct access to + * the device, which is useful in some circumstances. + * + * We also assume that we can include PCI interconnect devices, ie. bridges. + * IOMMU grouping on PCI necessitates that if we lack isolation on a bridge + * then all of the downstream devices will be part of the same IOMMU group as + * the bridge. Thus, if placing the bridge into the user owned IOVA space + * breaks anything, it only does so for user owned devices downstream. Note + * that error notification via MSI can be affected for platforms that handle + * MSI within the same IOVA space as DMA. */ -static const char * const vfio_driver_whitelist[] = { "pci-stub", "pcieport" }; +static const char * const vfio_driver_whitelist[] = { "pci-stub" }; -static bool vfio_whitelisted_driver(struct device_driver *drv) +static bool vfio_dev_whitelisted(struct device *dev, struct device_driver *drv) { int i; + if (dev_is_pci(dev)) { + struct pci_dev *pdev = to_pci_dev(dev); + + if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) + return true; + } + for (i = 0; i < ARRAY_SIZE(vfio_driver_whitelist); i++) { if (!strcmp(drv->name, vfio_driver_whitelist[i])) return true; @@ -462,6 +626,7 @@ static bool vfio_whitelisted_driver(struct device_driver *drv) * - driver-less * - bound to a vfio driver * - bound to a whitelisted driver + * - a PCI interconnect device * * We use two methods to determine whether a device is bound to a vfio * driver. The first is to test whether the device exists in the vfio @@ -486,7 +651,7 @@ static int vfio_dev_viable(struct device *dev, void *data) } mutex_unlock(&group->unbound_lock); - if (!ret || !drv || vfio_whitelisted_driver(drv)) + if (!ret || !drv || vfio_dev_whitelisted(dev, drv)) return 0; device = vfio_group_get_device(group, dev); @@ -621,7 +786,8 @@ int vfio_add_group_dev(struct device *dev, group = vfio_group_get_from_iommu(iommu_group); if (!group) { - group = vfio_create_group(iommu_group); + group = vfio_create_group(iommu_group, + !iommu_present(dev->bus)); if (IS_ERR(group)) { iommu_group_put(iommu_group); return PTR_ERR(group); @@ -692,11 +858,12 @@ EXPORT_SYMBOL_GPL(vfio_device_get_from_dev); static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group, char *buf) { - struct vfio_device *device; + struct vfio_device *it, *device = NULL; mutex_lock(&group->device_lock); - list_for_each_entry(device, &group->device_list, group_next) { - if (!strcmp(dev_name(device->dev), buf)) { + list_for_each_entry(it, &group->device_list, group_next) { + if (!strcmp(dev_name(it->dev), buf)) { + device = it; vfio_device_get(device); break; } @@ -832,8 +999,7 @@ static long vfio_ioctl_check_extension(struct vfio_container *container, */ if (!driver) { mutex_lock(&vfio.iommu_drivers_lock); - list_for_each_entry(driver, &vfio.iommu_drivers_list, - vfio_next) { + vfio_for_each_iommu_driver(container, driver) { if (!try_module_get(driver->ops->owner)) continue; @@ -902,7 +1068,7 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, } mutex_lock(&vfio.iommu_drivers_lock); - list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { + vfio_for_each_iommu_driver(container, driver) { void *data; if (!try_module_get(driver->ops->owner)) @@ -1167,6 +1333,9 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) if (atomic_read(&group->container_users)) return -EINVAL; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) + return -EPERM; + f = fdget(container_fd); if (!f.file) return -EBADF; @@ -1182,6 +1351,13 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) down_write(&container->group_lock); + /* Real groups and fake groups cannot mix */ + if (!list_empty(&container->group_list) && + container->noiommu != group->noiommu) { + ret = -EPERM; + goto unlock_out; + } + driver = container->iommu_driver; if (driver) { ret = driver->ops->attach_group(container->iommu_data, @@ -1191,6 +1367,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) } group->container = container; + container->noiommu = group->noiommu; list_add(&group->container_next, &container->group_list); /* Get a reference on the container and mark a user within the group */ @@ -1221,6 +1398,9 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) !group->container->iommu_driver || !vfio_group_viable(group)) return -EINVAL; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) + return -EPERM; + device = vfio_device_get_from_name(group, buf); if (!device) return -ENODEV; @@ -1263,6 +1443,10 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) fd_install(ret, filep); + if (group->noiommu) + dev_warn(device->dev, "vfio-noiommu device opened by user " + "(%s:%d)\n", current->comm, task_pid_nr(current)); + return ret; } @@ -1351,6 +1535,11 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep) if (!group) return -ENODEV; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) { + vfio_group_put(group); + return -EPERM; + } + /* Do we need multiple instances of the group open? Seems not. */ opened = atomic_cmpxchg(&group->opened, 0, 1); if (opened) { @@ -1513,6 +1702,11 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) if (!atomic_inc_not_zero(&group->container_users)) return ERR_PTR(-EINVAL); + if (group->noiommu) { + atomic_dec(&group->container_users); + return ERR_PTR(-EPERM); + } + if (!group->container->iommu_driver || !vfio_group_viable(group)) { atomic_dec(&group->container_users); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 57d8c37a002b..59d47cb638d5 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -403,13 +403,26 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma) static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu) { struct vfio_domain *domain; - unsigned long bitmap = PAGE_MASK; + unsigned long bitmap = ULONG_MAX; mutex_lock(&iommu->lock); list_for_each_entry(domain, &iommu->domain_list, next) bitmap &= domain->domain->ops->pgsize_bitmap; mutex_unlock(&iommu->lock); + /* + * In case the IOMMU supports page sizes smaller than PAGE_SIZE + * we pretend PAGE_SIZE is supported and hide sub-PAGE_SIZE sizes. + * That way the user will be able to map/unmap buffers whose size/ + * start address is aligned with PAGE_SIZE. Pinning code uses that + * granularity while iommu driver can use the sub-PAGE_SIZE size + * to map the buffer. + */ + if (bitmap & ~PAGE_MASK) { + bitmap &= PAGE_MASK; + bitmap |= PAGE_SIZE; + } + return bitmap; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 0a793c7930eb..bb0dfb1c7af1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -50,12 +50,21 @@ struct block_device *I_BDEV(struct inode *inode) } EXPORT_SYMBOL(I_BDEV); -static void bdev_write_inode(struct inode *inode) +static void bdev_write_inode(struct block_device *bdev) { + struct inode *inode = bdev->bd_inode; + int ret; + spin_lock(&inode->i_lock); while (inode->i_state & I_DIRTY) { spin_unlock(&inode->i_lock); - WARN_ON_ONCE(write_inode_now(inode, true)); + ret = write_inode_now(inode, true); + if (ret) { + char name[BDEVNAME_SIZE]; + pr_warn_ratelimited("VFS: Dirty inode writeback failed " + "for block device %s (err=%d).\n", + bdevname(bdev, name), ret); + } spin_lock(&inode->i_lock); } spin_unlock(&inode->i_lock); @@ -1504,7 +1513,7 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) * ->release can cause the queue to disappear, so flush all * dirty data before. */ - bdev_write_inode(bdev->bd_inode); + bdev_write_inode(bdev); } if (bdev->bd_contains == bdev) { if (disk->fops->release) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 640598c0d0e7..974be09e7556 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3780,6 +3780,9 @@ void close_ctree(struct btrfs_root *root) fs_info->closing = 1; smp_mb(); + /* wait for the qgroup rescan worker to stop */ + btrfs_qgroup_wait_for_completion(fs_info); + /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); /* avoid complains from lockdep et al., set sem back to initial state */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 99a8e57da8a1..acf3ed11cfb6 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10279,22 +10279,25 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) block_group = list_first_entry(&fs_info->unused_bgs, struct btrfs_block_group_cache, bg_list); - space_info = block_group->space_info; list_del_init(&block_group->bg_list); + + space_info = block_group->space_info; + if (ret || btrfs_mixed_space_info(space_info)) { btrfs_put_block_group(block_group); continue; } spin_unlock(&fs_info->unused_bgs_lock); - mutex_lock(&root->fs_info->delete_unused_bgs_mutex); + mutex_lock(&fs_info->delete_unused_bgs_mutex); /* Don't want to race with allocators so take the groups_sem */ down_write(&space_info->groups_sem); spin_lock(&block_group->lock); if (block_group->reserved || btrfs_block_group_used(&block_group->item) || - block_group->ro) { + block_group->ro || + list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have * outstanding allocations in this block group. We do @@ -10410,7 +10413,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) end_trans: btrfs_end_transaction(trans, root); next: - mutex_unlock(&root->fs_info->delete_unused_bgs_mutex); + mutex_unlock(&fs_info->delete_unused_bgs_mutex); btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 6bd5ce9d75f0..977e715f0bf2 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -756,8 +756,16 @@ next_slot: } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); - if (key.objectid > ino || - key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) + + if (key.objectid > ino) + break; + if (WARN_ON_ONCE(key.objectid < ino) || + key.type < BTRFS_EXTENT_DATA_KEY) { + ASSERT(del_nr == 0); + path->slots[0]++; + goto next_slot; + } + if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) break; fi = btrfs_item_ptr(leaf, path->slots[0], @@ -776,8 +784,8 @@ next_slot: btrfs_file_extent_inline_len(leaf, path->slots[0], fi); } else { - WARN_ON(1); - extent_end = search_start; + /* can't happen */ + BUG(); } /* diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0e4f2bfcc37d..994490d5fa64 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1304,8 +1304,14 @@ next_slot: num_bytes = 0; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - if (found_key.objectid > ino || - found_key.type > BTRFS_EXTENT_DATA_KEY || + if (found_key.objectid > ino) + break; + if (WARN_ON_ONCE(found_key.objectid < ino) || + found_key.type < BTRFS_EXTENT_DATA_KEY) { + path->slots[0]++; + goto next_slot; + } + if (found_key.type > BTRFS_EXTENT_DATA_KEY || found_key.offset > end) break; @@ -7503,6 +7509,28 @@ struct btrfs_dio_data { u64 reserve; }; +static void adjust_dio_outstanding_extents(struct inode *inode, + struct btrfs_dio_data *dio_data, + const u64 len) +{ + unsigned num_extents; + + num_extents = (unsigned) div64_u64(len + BTRFS_MAX_EXTENT_SIZE - 1, + BTRFS_MAX_EXTENT_SIZE); + /* + * If we have an outstanding_extents count still set then we're + * within our reservation, otherwise we need to adjust our inode + * counter appropriately. + */ + if (dio_data->outstanding_extents) { + dio_data->outstanding_extents -= num_extents; + } else { + spin_lock(&BTRFS_I(inode)->lock); + BTRFS_I(inode)->outstanding_extents += num_extents; + spin_unlock(&BTRFS_I(inode)->lock); + } +} + static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -7538,8 +7566,11 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * If this errors out it's because we couldn't invalidate pagecache for * this range and we need to fallback to buffered. */ - if (lock_extent_direct(inode, lockstart, lockend, &cached_state, create)) - return -ENOTBLK; + if (lock_extent_direct(inode, lockstart, lockend, &cached_state, + create)) { + ret = -ENOTBLK; + goto err; + } em = btrfs_get_extent(inode, NULL, 0, start, len, 0); if (IS_ERR(em)) { @@ -7657,19 +7688,7 @@ unlock: if (start + len > i_size_read(inode)) i_size_write(inode, start + len); - /* - * If we have an outstanding_extents count still set then we're - * within our reservation, otherwise we need to adjust our inode - * counter appropriately. - */ - if (dio_data->outstanding_extents) { - (dio_data->outstanding_extents)--; - } else { - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents++; - spin_unlock(&BTRFS_I(inode)->lock); - } - + adjust_dio_outstanding_extents(inode, dio_data, len); btrfs_free_reserved_data_space(inode, start, len); WARN_ON(dio_data->reserve < len); dio_data->reserve -= len; @@ -7696,8 +7715,17 @@ unlock: unlock_err: clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, unlock_bits, 1, 0, &cached_state, GFP_NOFS); +err: if (dio_data) current->journal_info = dio_data; + /* + * Compensate the delalloc release we do in btrfs_direct_IO() when we + * write less data then expected, so that we don't underflow our inode's + * outstanding extents counter. + */ + if (create && dio_data) + adjust_dio_outstanding_extents(inode, dio_data, len); + return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 46476c226395..93e12c18ffd7 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2198,7 +2198,6 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, int slot; int ret; - path->leave_spinning = 1; mutex_lock(&fs_info->qgroup_rescan_lock); ret = btrfs_search_slot_for_read(fs_info->extent_root, &fs_info->qgroup_rescan_progress, @@ -2286,7 +2285,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) goto out; err = 0; - while (!err) { + while (!err && !btrfs_fs_closing(fs_info)) { trans = btrfs_start_transaction(fs_info->fs_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2307,7 +2306,8 @@ out: btrfs_free_path(path); mutex_lock(&fs_info->qgroup_rescan_lock); - fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; + if (!btrfs_fs_closing(fs_info)) + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; if (err > 0 && fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) { @@ -2336,7 +2336,9 @@ out: } btrfs_end_transaction(trans, fs_info->quota_root); - if (err >= 0) { + if (btrfs_fs_closing(fs_info)) { + btrfs_info(fs_info, "qgroup scan paused"); + } else if (err >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", err > 0 ? " (inconsistency flag cleared)" : ""); } else { @@ -2384,12 +2386,11 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, memset(&fs_info->qgroup_rescan_progress, 0, sizeof(fs_info->qgroup_rescan_progress)); fs_info->qgroup_rescan_progress.objectid = progress_objectid; + init_completion(&fs_info->qgroup_rescan_completion); spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); - init_completion(&fs_info->qgroup_rescan_completion); - memset(&fs_info->qgroup_rescan_work, 0, sizeof(fs_info->qgroup_rescan_work)); btrfs_init_work(&fs_info->qgroup_rescan_work, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 550de89a8661..2907a77fb1f6 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -248,14 +248,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check); static int scrub_setup_recheck_block(struct scrub_block *original_sblock, struct scrub_block *sblocks_for_recheck); static void scrub_recheck_block(struct btrfs_fs_info *fs_info, - struct scrub_block *sblock, int is_metadata, - int have_csum, u8 *csum, u64 generation, - u16 csum_size, int retry_failed_mirror); -static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, - struct scrub_block *sblock, - int is_metadata, int have_csum, - const u8 *csum, u64 generation, - u16 csum_size); + struct scrub_block *sblock, + int retry_failed_mirror); +static void scrub_recheck_block_checksum(struct scrub_block *sblock); static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, struct scrub_block *sblock_good); static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, @@ -889,11 +884,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) struct btrfs_fs_info *fs_info; u64 length; u64 logical; - u64 generation; unsigned int failed_mirror_index; unsigned int is_metadata; unsigned int have_csum; - u8 *csum; struct scrub_block *sblocks_for_recheck; /* holds one for each mirror */ struct scrub_block *sblock_bad; int ret; @@ -918,13 +911,11 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) } length = sblock_to_check->page_count * PAGE_SIZE; logical = sblock_to_check->pagev[0]->logical; - generation = sblock_to_check->pagev[0]->generation; BUG_ON(sblock_to_check->pagev[0]->mirror_num < 1); failed_mirror_index = sblock_to_check->pagev[0]->mirror_num - 1; is_metadata = !(sblock_to_check->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA); have_csum = sblock_to_check->pagev[0]->have_csum; - csum = sblock_to_check->pagev[0]->csum; dev = sblock_to_check->pagev[0]->dev; if (sctx->is_dev_replace && !is_metadata && !have_csum) { @@ -987,8 +978,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) sblock_bad = sblocks_for_recheck + failed_mirror_index; /* build and submit the bios for the failed mirror, check checksums */ - scrub_recheck_block(fs_info, sblock_bad, is_metadata, have_csum, - csum, generation, sctx->csum_size, 1); + scrub_recheck_block(fs_info, sblock_bad, 1); if (!sblock_bad->header_error && !sblock_bad->checksum_error && sblock_bad->no_io_error_seen) { @@ -1101,9 +1091,7 @@ nodatasum_case: sblock_other = sblocks_for_recheck + mirror_index; /* build and submit the bios, check checksums */ - scrub_recheck_block(fs_info, sblock_other, is_metadata, - have_csum, csum, generation, - sctx->csum_size, 0); + scrub_recheck_block(fs_info, sblock_other, 0); if (!sblock_other->header_error && !sblock_other->checksum_error && @@ -1215,9 +1203,7 @@ nodatasum_case: * is verified, but most likely the data comes out * of the page cache. */ - scrub_recheck_block(fs_info, sblock_bad, - is_metadata, have_csum, csum, - generation, sctx->csum_size, 1); + scrub_recheck_block(fs_info, sblock_bad, 1); if (!sblock_bad->header_error && !sblock_bad->checksum_error && sblock_bad->no_io_error_seen) @@ -1318,6 +1304,9 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock, struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info; u64 length = original_sblock->page_count * PAGE_SIZE; u64 logical = original_sblock->pagev[0]->logical; + u64 generation = original_sblock->pagev[0]->generation; + u64 flags = original_sblock->pagev[0]->flags; + u64 have_csum = original_sblock->pagev[0]->have_csum; struct scrub_recover *recover; struct btrfs_bio *bbio; u64 sublen; @@ -1372,6 +1361,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock, sblock = sblocks_for_recheck + mirror_index; sblock->sctx = sctx; + page = kzalloc(sizeof(*page), GFP_NOFS); if (!page) { leave_nomem: @@ -1383,7 +1373,15 @@ leave_nomem: } scrub_page_get(page); sblock->pagev[page_index] = page; + page->sblock = sblock; + page->flags = flags; + page->generation = generation; page->logical = logical; + page->have_csum = have_csum; + if (have_csum) + memcpy(page->csum, + original_sblock->pagev[0]->csum, + sctx->csum_size); scrub_stripe_index_and_offset(logical, bbio->map_type, @@ -1474,15 +1472,12 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, * the pages that are errored in the just handled mirror can be repaired. */ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, - struct scrub_block *sblock, int is_metadata, - int have_csum, u8 *csum, u64 generation, - u16 csum_size, int retry_failed_mirror) + struct scrub_block *sblock, + int retry_failed_mirror) { int page_num; sblock->no_io_error_seen = 1; - sblock->header_error = 0; - sblock->checksum_error = 0; for (page_num = 0; page_num < sblock->page_count; page_num++) { struct bio *bio; @@ -1518,9 +1513,7 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, } if (sblock->no_io_error_seen) - scrub_recheck_block_checksum(fs_info, sblock, is_metadata, - have_csum, csum, generation, - csum_size); + scrub_recheck_block_checksum(sblock); return; } @@ -1535,61 +1528,16 @@ static inline int scrub_check_fsid(u8 fsid[], return !ret; } -static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, - struct scrub_block *sblock, - int is_metadata, int have_csum, - const u8 *csum, u64 generation, - u16 csum_size) +static void scrub_recheck_block_checksum(struct scrub_block *sblock) { - int page_num; - u8 calculated_csum[BTRFS_CSUM_SIZE]; - u32 crc = ~(u32)0; - void *mapped_buffer; - - WARN_ON(!sblock->pagev[0]->page); - if (is_metadata) { - struct btrfs_header *h; - - mapped_buffer = kmap_atomic(sblock->pagev[0]->page); - h = (struct btrfs_header *)mapped_buffer; - - if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h) || - !scrub_check_fsid(h->fsid, sblock->pagev[0]) || - memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, - BTRFS_UUID_SIZE)) { - sblock->header_error = 1; - } else if (generation != btrfs_stack_header_generation(h)) { - sblock->header_error = 1; - sblock->generation_error = 1; - } - csum = h->csum; - } else { - if (!have_csum) - return; - - mapped_buffer = kmap_atomic(sblock->pagev[0]->page); - } - - for (page_num = 0;;) { - if (page_num == 0 && is_metadata) - crc = btrfs_csum_data( - ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE, - crc, PAGE_SIZE - BTRFS_CSUM_SIZE); - else - crc = btrfs_csum_data(mapped_buffer, crc, PAGE_SIZE); - - kunmap_atomic(mapped_buffer); - page_num++; - if (page_num >= sblock->page_count) - break; - WARN_ON(!sblock->pagev[page_num]->page); - - mapped_buffer = kmap_atomic(sblock->pagev[page_num]->page); - } + sblock->header_error = 0; + sblock->checksum_error = 0; + sblock->generation_error = 0; - btrfs_csum_final(crc, calculated_csum); - if (memcmp(calculated_csum, csum, csum_size)) - sblock->checksum_error = 1; + if (sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA) + scrub_checksum_data(sblock); + else + scrub_checksum_tree_block(sblock); } static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad, @@ -1833,6 +1781,18 @@ static int scrub_checksum(struct scrub_block *sblock) u64 flags; int ret; + /* + * No need to initialize these stats currently, + * because this function only use return value + * instead of these stats value. + * + * Todo: + * always use stats + */ + sblock->header_error = 0; + sblock->generation_error = 0; + sblock->checksum_error = 0; + WARN_ON(sblock->page_count < 1); flags = sblock->pagev[0]->flags; ret = 0; @@ -1858,7 +1818,6 @@ static int scrub_checksum_data(struct scrub_block *sblock) struct page *page; void *buffer; u32 crc = ~(u32)0; - int fail = 0; u64 len; int index; @@ -1889,9 +1848,9 @@ static int scrub_checksum_data(struct scrub_block *sblock) btrfs_csum_final(crc, csum); if (memcmp(csum, on_disk_csum, sctx->csum_size)) - fail = 1; + sblock->checksum_error = 1; - return fail; + return sblock->checksum_error; } static int scrub_checksum_tree_block(struct scrub_block *sblock) @@ -1907,8 +1866,6 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) u64 mapped_size; void *p; u32 crc = ~(u32)0; - int fail = 0; - int crc_fail = 0; u64 len; int index; @@ -1923,19 +1880,20 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) * a) don't have an extent buffer and * b) the page is already kmapped */ - if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h)) - ++fail; + sblock->header_error = 1; - if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) - ++fail; + if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) { + sblock->header_error = 1; + sblock->generation_error = 1; + } if (!scrub_check_fsid(h->fsid, sblock->pagev[0])) - ++fail; + sblock->header_error = 1; if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, BTRFS_UUID_SIZE)) - ++fail; + sblock->header_error = 1; len = sctx->nodesize - BTRFS_CSUM_SIZE; mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE; @@ -1960,9 +1918,9 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) btrfs_csum_final(crc, calculated_csum); if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size)) - ++crc_fail; + sblock->checksum_error = 1; - return fail || crc_fail; + return sblock->header_error || sblock->checksum_error; } static int scrub_checksum_super(struct scrub_block *sblock) @@ -2176,39 +2134,27 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) { struct scrub_block *sblock = container_of(work, struct scrub_block, work); struct scrub_ctx *sctx = sblock->sctx; - struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info; - unsigned int is_metadata; - unsigned int have_csum; - u8 *csum; - u64 generation; u64 logical; struct btrfs_device *dev; - is_metadata = !(sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA); - have_csum = sblock->pagev[0]->have_csum; - csum = sblock->pagev[0]->csum; - generation = sblock->pagev[0]->generation; logical = sblock->pagev[0]->logical; dev = sblock->pagev[0]->dev; - if (sblock->no_io_error_seen) { - scrub_recheck_block_checksum(fs_info, sblock, is_metadata, - have_csum, csum, generation, - sctx->csum_size); - } + if (sblock->no_io_error_seen) + scrub_recheck_block_checksum(sblock); if (!sblock->no_io_error_seen) { spin_lock(&sctx->stat_lock); sctx->stat.read_errors++; spin_unlock(&sctx->stat_lock); - btrfs_err_rl_in_rcu(fs_info, + btrfs_err_rl_in_rcu(sctx->dev_root->fs_info, "IO error rebuilding logical %llu for dev %s", logical, rcu_str_deref(dev->name)); } else if (sblock->header_error || sblock->checksum_error) { spin_lock(&sctx->stat_lock); sctx->stat.uncorrectable_errors++; spin_unlock(&sctx->stat_lock); - btrfs_err_rl_in_rcu(fs_info, + btrfs_err_rl_in_rcu(sctx->dev_root->fs_info, "failed to rebuild valid logical %llu for dev %s", logical, rcu_str_deref(dev->name)); } else { @@ -2500,8 +2446,7 @@ static void scrub_block_complete(struct scrub_block *sblock) } } -static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u64 len, - u8 *csum) +static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum) { struct btrfs_ordered_sum *sum = NULL; unsigned long index; @@ -2565,7 +2510,7 @@ static int scrub_extent(struct scrub_ctx *sctx, u64 logical, u64 len, if (flags & BTRFS_EXTENT_FLAG_DATA) { /* push csums to sbio */ - have_csum = scrub_find_csum(sctx, logical, l, csum); + have_csum = scrub_find_csum(sctx, logical, csum); if (have_csum == 0) ++sctx->stat.no_csum; if (sctx->is_dev_replace && !have_csum) { @@ -2703,7 +2648,7 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity, if (flags & BTRFS_EXTENT_FLAG_DATA) { /* push csums to sbio */ - have_csum = scrub_find_csum(sctx, logical, l, csum); + have_csum = scrub_find_csum(sctx, logical, csum); if (have_csum == 0) goto skip; } @@ -3012,6 +2957,9 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, logic_start + map->stripe_len)) { btrfs_err(fs_info, "scrub: tree block %llu spanning stripes, ignored. logical=%llu", key.objectid, logic_start); + spin_lock(&sctx->stat_lock); + sctx->stat.uncorrectable_errors++; + spin_unlock(&sctx->stat_lock); goto next; } again: @@ -3361,6 +3309,9 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, "scrub: tree block %llu spanning " "stripes, ignored. logical=%llu", key.objectid, logical); + spin_lock(&sctx->stat_lock); + sctx->stat.uncorrectable_errors++; + spin_unlock(&sctx->stat_lock); goto next; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9b2dafa5ba59..a6df8fdc1312 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3400,6 +3400,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) u32 count_data = 0; u32 count_meta = 0; u32 count_sys = 0; + int chunk_reserved = 0; /* step one make some room on all the devices */ devices = &fs_info->fs_devices->devices; @@ -3501,6 +3502,7 @@ again: ret = should_balance_chunk(chunk_root, leaf, chunk, found_key.offset); + btrfs_release_path(path); if (!ret) { mutex_unlock(&fs_info->delete_unused_bgs_mutex); @@ -3537,6 +3539,25 @@ again: goto loop; } + if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && !chunk_reserved) { + trans = btrfs_start_transaction(chunk_root, 0); + if (IS_ERR(trans)) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + ret = PTR_ERR(trans); + goto error; + } + + ret = btrfs_force_chunk_alloc(trans, chunk_root, + BTRFS_BLOCK_GROUP_DATA); + if (ret < 0) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + goto error; + } + + btrfs_end_transaction(trans, chunk_root); + chunk_reserved = 1; + } + ret = btrfs_relocate_chunk(chunk_root, found_key.offset); mutex_unlock(&fs_info->delete_unused_bgs_mutex); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 6f518c90e1c1..1fcd7b6e7564 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -313,8 +313,10 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) /* check to make sure this item is what we want */ if (found_key.objectid != key.objectid) break; - if (found_key.type != BTRFS_XATTR_ITEM_KEY) + if (found_key.type > BTRFS_XATTR_ITEM_KEY) break; + if (found_key.type < BTRFS_XATTR_ITEM_KEY) + goto next; di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); if (verify_dir_item(root, leaf, di)) diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 834f9f3723fb..a4766ded1ba7 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -88,7 +88,7 @@ static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data, const struct ceph_inode_info* ci = cookie_netfs_data; uint16_t klen; - /* use ceph virtual inode (id + snaphot) */ + /* use ceph virtual inode (id + snapshot) */ klen = sizeof(ci->i_vino); if (klen > maxbuf) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 27b566874bc1..c69e1253b47b 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1655,9 +1655,8 @@ retry_locked: !S_ISDIR(inode->i_mode) && /* ignore readdir cache */ ci->i_wrbuffer_ref == 0 && /* no dirty pages... */ inode->i_data.nrpages && /* have cached pages */ - (file_wanted == 0 || /* no open files */ - (revoking & (CEPH_CAP_FILE_CACHE| - CEPH_CAP_FILE_LAZYIO))) && /* or revoking cache */ + (revoking & (CEPH_CAP_FILE_CACHE| + CEPH_CAP_FILE_LAZYIO)) && /* or revoking cache */ !tried_invalidate) { dout("check_caps trying to invalidate on %p\n", inode); if (try_nonblocking_invalidate(inode) < 0) { @@ -1971,49 +1970,46 @@ out: } /* - * wait for any uncommitted directory operations to commit. + * wait for any unsafe requests to complete. */ -static int unsafe_dirop_wait(struct inode *inode) +static int unsafe_request_wait(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); - struct list_head *head = &ci->i_unsafe_dirops; - struct ceph_mds_request *req; - u64 last_tid; - int ret = 0; - - if (!S_ISDIR(inode->i_mode)) - return 0; + struct ceph_mds_request *req1 = NULL, *req2 = NULL; + int ret, err = 0; spin_lock(&ci->i_unsafe_lock); - if (list_empty(head)) - goto out; - - req = list_last_entry(head, struct ceph_mds_request, - r_unsafe_dir_item); - last_tid = req->r_tid; - - do { - ceph_mdsc_get_request(req); - spin_unlock(&ci->i_unsafe_lock); + if (S_ISDIR(inode->i_mode) && !list_empty(&ci->i_unsafe_dirops)) { + req1 = list_last_entry(&ci->i_unsafe_dirops, + struct ceph_mds_request, + r_unsafe_dir_item); + ceph_mdsc_get_request(req1); + } + if (!list_empty(&ci->i_unsafe_iops)) { + req2 = list_last_entry(&ci->i_unsafe_iops, + struct ceph_mds_request, + r_unsafe_target_item); + ceph_mdsc_get_request(req2); + } + spin_unlock(&ci->i_unsafe_lock); - dout("unsafe_dirop_wait %p wait on tid %llu (until %llu)\n", - inode, req->r_tid, last_tid); - ret = !wait_for_completion_timeout(&req->r_safe_completion, - ceph_timeout_jiffies(req->r_timeout)); + dout("unsafe_requeset_wait %p wait on tid %llu %llu\n", + inode, req1 ? req1->r_tid : 0ULL, req2 ? req2->r_tid : 0ULL); + if (req1) { + ret = !wait_for_completion_timeout(&req1->r_safe_completion, + ceph_timeout_jiffies(req1->r_timeout)); if (ret) - ret = -EIO; /* timed out */ - - ceph_mdsc_put_request(req); - - spin_lock(&ci->i_unsafe_lock); - if (ret || list_empty(head)) - break; - req = list_first_entry(head, struct ceph_mds_request, - r_unsafe_dir_item); - } while (req->r_tid < last_tid); -out: - spin_unlock(&ci->i_unsafe_lock); - return ret; + err = -EIO; + ceph_mdsc_put_request(req1); + } + if (req2) { + ret = !wait_for_completion_timeout(&req2->r_safe_completion, + ceph_timeout_jiffies(req2->r_timeout)); + if (ret) + err = -EIO; + ceph_mdsc_put_request(req2); + } + return err; } int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) @@ -2039,7 +2035,7 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) dirty = try_flush_caps(inode, &flush_tid); dout("fsync dirty caps are %s\n", ceph_cap_string(dirty)); - ret = unsafe_dirop_wait(inode); + ret = unsafe_request_wait(inode); /* * only wait on non-file metadata writeback (the mds diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 0c62868b5c56..3c68e6aee2f0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -34,6 +34,74 @@ * need to wait for MDS acknowledgement. */ +/* + * Calculate the length sum of direct io vectors that can + * be combined into one page vector. + */ +static size_t dio_get_pagev_size(const struct iov_iter *it) +{ + const struct iovec *iov = it->iov; + const struct iovec *iovend = iov + it->nr_segs; + size_t size; + + size = iov->iov_len - it->iov_offset; + /* + * An iov can be page vectored when both the current tail + * and the next base are page aligned. + */ + while (PAGE_ALIGNED((iov->iov_base + iov->iov_len)) && + (++iov < iovend && PAGE_ALIGNED((iov->iov_base)))) { + size += iov->iov_len; + } + dout("dio_get_pagevlen len = %zu\n", size); + return size; +} + +/* + * Allocate a page vector based on (@it, @nbytes). + * The return value is the tuple describing a page vector, + * that is (@pages, @page_align, @num_pages). + */ +static struct page ** +dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes, + size_t *page_align, int *num_pages) +{ + struct iov_iter tmp_it = *it; + size_t align; + struct page **pages; + int ret = 0, idx, npages; + + align = (unsigned long)(it->iov->iov_base + it->iov_offset) & + (PAGE_SIZE - 1); + npages = calc_pages_for(align, nbytes); + pages = kmalloc(sizeof(*pages) * npages, GFP_KERNEL); + if (!pages) { + pages = vmalloc(sizeof(*pages) * npages); + if (!pages) + return ERR_PTR(-ENOMEM); + } + + for (idx = 0; idx < npages; ) { + size_t start; + ret = iov_iter_get_pages(&tmp_it, pages + idx, nbytes, + npages - idx, &start); + if (ret < 0) + goto fail; + + iov_iter_advance(&tmp_it, ret); + nbytes -= ret; + idx += (ret + start + PAGE_SIZE - 1) / PAGE_SIZE; + } + + BUG_ON(nbytes != 0); + *num_pages = npages; + *page_align = align; + dout("dio_get_pages_alloc: got %d pages align %zu\n", npages, align); + return pages; +fail: + ceph_put_page_vector(pages, idx, false); + return ERR_PTR(ret); +} /* * Prepare an open request. Preallocate ceph_cap to avoid an @@ -458,11 +526,10 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i, size_t start; ssize_t n; - n = iov_iter_get_pages_alloc(i, &pages, INT_MAX, &start); - if (n < 0) - return n; - - num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE; + n = dio_get_pagev_size(i); + pages = dio_get_pages_alloc(i, n, &start, &num_pages); + if (IS_ERR(pages)) + return PTR_ERR(pages); ret = striped_read(inode, off, n, pages, num_pages, checkeof, @@ -592,7 +659,7 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, CEPH_OSD_FLAG_WRITE; while (iov_iter_count(from) > 0) { - u64 len = iov_iter_single_seg_count(from); + u64 len = dio_get_pagev_size(from); size_t start; ssize_t n; @@ -611,14 +678,14 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0); - n = iov_iter_get_pages_alloc(from, &pages, len, &start); - if (unlikely(n < 0)) { - ret = n; + n = len; + pages = dio_get_pages_alloc(from, len, &start, &num_pages); + if (IS_ERR(pages)) { ceph_osdc_put_request(req); + ret = PTR_ERR(pages); break; } - num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE; /* * throw out any page cache pages in this range. this * may block. diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 96d2bd829902..498dcfa2dcdb 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -452,6 +452,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ci->i_unsafe_writes); INIT_LIST_HEAD(&ci->i_unsafe_dirops); + INIT_LIST_HEAD(&ci->i_unsafe_iops); spin_lock_init(&ci->i_unsafe_lock); ci->i_snap_realm = NULL; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 51cb02da75d9..e7b130a637f9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -633,13 +633,8 @@ static void __register_request(struct ceph_mds_client *mdsc, mdsc->oldest_tid = req->r_tid; if (dir) { - struct ceph_inode_info *ci = ceph_inode(dir); - ihold(dir); - spin_lock(&ci->i_unsafe_lock); req->r_unsafe_dir = dir; - list_add_tail(&req->r_unsafe_dir_item, &ci->i_unsafe_dirops); - spin_unlock(&ci->i_unsafe_lock); } } @@ -665,13 +660,20 @@ static void __unregister_request(struct ceph_mds_client *mdsc, rb_erase(&req->r_node, &mdsc->request_tree); RB_CLEAR_NODE(&req->r_node); - if (req->r_unsafe_dir) { + if (req->r_unsafe_dir && req->r_got_unsafe) { struct ceph_inode_info *ci = ceph_inode(req->r_unsafe_dir); - spin_lock(&ci->i_unsafe_lock); list_del_init(&req->r_unsafe_dir_item); spin_unlock(&ci->i_unsafe_lock); + } + if (req->r_target_inode && req->r_got_unsafe) { + struct ceph_inode_info *ci = ceph_inode(req->r_target_inode); + spin_lock(&ci->i_unsafe_lock); + list_del_init(&req->r_unsafe_target_item); + spin_unlock(&ci->i_unsafe_lock); + } + if (req->r_unsafe_dir) { iput(req->r_unsafe_dir); req->r_unsafe_dir = NULL; } @@ -1430,6 +1432,13 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) if ((used | wanted) & CEPH_CAP_ANY_WR) goto out; } + /* The inode has cached pages, but it's no longer used. + * we can safely drop it */ + if (wanted == 0 && used == CEPH_CAP_FILE_CACHE && + !(oissued & CEPH_CAP_FILE_CACHE)) { + used = 0; + oissued = 0; + } if ((used | wanted) & ~oissued & mine) goto out; /* we need these caps */ @@ -1438,7 +1447,7 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) /* we aren't the only cap.. just remove us */ __ceph_remove_cap(cap, true); } else { - /* try to drop referring dentries */ + /* try dropping referring dentries */ spin_unlock(&ci->i_ceph_lock); d_prune_aliases(inode); dout("trim_caps_cb %p cap %p pruned, count now %d\n", @@ -1704,6 +1713,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode) req->r_started = jiffies; req->r_resend_mds = -1; INIT_LIST_HEAD(&req->r_unsafe_dir_item); + INIT_LIST_HEAD(&req->r_unsafe_target_item); req->r_fmode = -1; kref_init(&req->r_kref); INIT_LIST_HEAD(&req->r_wait); @@ -1935,7 +1945,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, len = sizeof(*head) + pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) + - sizeof(struct timespec); + sizeof(struct ceph_timespec); /* calculate (max) length for cap releases */ len += sizeof(struct ceph_mds_request_release) * @@ -2477,6 +2487,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) } else { req->r_got_unsafe = true; list_add_tail(&req->r_unsafe_item, &req->r_session->s_unsafe); + if (req->r_unsafe_dir) { + struct ceph_inode_info *ci = + ceph_inode(req->r_unsafe_dir); + spin_lock(&ci->i_unsafe_lock); + list_add_tail(&req->r_unsafe_dir_item, + &ci->i_unsafe_dirops); + spin_unlock(&ci->i_unsafe_lock); + } } dout("handle_reply tid %lld result %d\n", tid, result); @@ -2518,6 +2536,13 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) up_read(&mdsc->snap_rwsem); if (realm) ceph_put_snap_realm(mdsc, realm); + + if (err == 0 && req->r_got_unsafe && req->r_target_inode) { + struct ceph_inode_info *ci = ceph_inode(req->r_target_inode); + spin_lock(&ci->i_unsafe_lock); + list_add_tail(&req->r_unsafe_target_item, &ci->i_unsafe_iops); + spin_unlock(&ci->i_unsafe_lock); + } out_err: mutex_lock(&mdsc->mutex); if (!req->r_aborted) { @@ -3917,17 +3942,19 @@ static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con, return msg; } -static int sign_message(struct ceph_connection *con, struct ceph_msg *msg) +static int mds_sign_message(struct ceph_msg *msg) { - struct ceph_mds_session *s = con->private; + struct ceph_mds_session *s = msg->con->private; struct ceph_auth_handshake *auth = &s->s_auth; + return ceph_auth_sign_message(auth, msg); } -static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg) +static int mds_check_message_signature(struct ceph_msg *msg) { - struct ceph_mds_session *s = con->private; + struct ceph_mds_session *s = msg->con->private; struct ceph_auth_handshake *auth = &s->s_auth; + return ceph_auth_check_message_signature(auth, msg); } @@ -3940,8 +3967,8 @@ static const struct ceph_connection_operations mds_con_ops = { .invalidate_authorizer = invalidate_authorizer, .peer_reset = peer_reset, .alloc_msg = mds_alloc_msg, - .sign_message = sign_message, - .check_message_signature = check_message_signature, + .sign_message = mds_sign_message, + .check_message_signature = mds_check_message_signature, }; /* eof */ diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index f575eafe2261..ccf11ef0ca87 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -236,6 +236,9 @@ struct ceph_mds_request { struct inode *r_unsafe_dir; struct list_head r_unsafe_dir_item; + /* unsafe requests that modify the target inode */ + struct list_head r_unsafe_target_item; + struct ceph_mds_session *r_session; int r_attempts; /* resend attempts */ diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 2f2460d23a06..75b7d125ce66 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -342,6 +342,7 @@ struct ceph_inode_info { struct list_head i_unsafe_writes; /* uncommitted sync writes */ struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */ + struct list_head i_unsafe_iops; /* uncommitted mds inode ops */ spinlock_t i_unsafe_lock; struct ceph_snap_realm *i_snap_realm; /* snap realm (if caps) */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index e739950ca084..cbc0f4bca0c0 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -454,6 +454,10 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",nocase"); if (tcon->retry) seq_puts(s, ",hard"); + if (tcon->use_persistent) + seq_puts(s, ",persistenthandles"); + else if (tcon->use_resilient) + seq_puts(s, ",resilienthandles"); if (tcon->unix_ext) seq_puts(s, ",unix"); else @@ -921,9 +925,7 @@ const struct file_operations cifs_file_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .llseek = cifs_llseek, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -939,9 +941,7 @@ const struct file_operations cifs_file_strict_ops = { .mmap = cifs_file_strict_mmap, .splice_read = generic_file_splice_read, .llseek = cifs_llseek, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -957,9 +957,7 @@ const struct file_operations cifs_file_direct_ops = { .flush = cifs_flush, .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -975,9 +973,7 @@ const struct file_operations cifs_file_nobrl_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .llseek = cifs_llseek, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -992,9 +988,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .mmap = cifs_file_strict_mmap, .splice_read = generic_file_splice_read, .llseek = cifs_llseek, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1009,9 +1003,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .flush = cifs_flush, .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, -#ifdef CONFIG_CIFS_POSIX .unlocked_ioctl = cifs_ioctl, -#endif /* CONFIG_CIFS_POSIX */ .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index b406a32deb1f..2b510c537a0d 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -493,7 +493,10 @@ struct smb_vol { bool mfsymlinks:1; /* use Minshall+French Symlinks */ bool multiuser:1; bool rwpidforward:1; /* pid forward for read/write operations */ - bool nosharesock; + bool nosharesock:1; + bool persistent:1; + bool nopersistent:1; + bool resilient:1; /* noresilient not required since not fored for CA */ unsigned int rsize; unsigned int wsize; bool sockopt_tcp_nodelay:1; @@ -895,6 +898,8 @@ struct cifs_tcon { bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */ bool broken_sparse_sup; /* if server or share does not support sparse */ bool need_reconnect:1; /* connection reset, tid now invalid */ + bool use_resilient:1; /* use resilient instead of durable handles */ + bool use_persistent:1; /* use persistent instead of durable handles */ #ifdef CONFIG_CIFS_SMB2 bool print:1; /* set if connection to printer share */ bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */ @@ -1015,6 +1020,7 @@ struct cifs_fid { __u64 persistent_fid; /* persist file id for smb2 */ __u64 volatile_fid; /* volatile file id for smb2 */ __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for smb2 */ + __u8 create_guid[16]; #endif struct cifs_pending_open *pending_open; unsigned int epoch; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 3f2228570d44..ecb0803bdb0e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -87,6 +87,8 @@ enum { Opt_sign, Opt_seal, Opt_noac, Opt_fsc, Opt_mfsymlinks, Opt_multiuser, Opt_sloppy, Opt_nosharesock, + Opt_persistent, Opt_nopersistent, + Opt_resilient, Opt_noresilient, /* Mount options which take numeric value */ Opt_backupuid, Opt_backupgid, Opt_uid, @@ -169,6 +171,10 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_multiuser, "multiuser" }, { Opt_sloppy, "sloppy" }, { Opt_nosharesock, "nosharesock" }, + { Opt_persistent, "persistenthandles"}, + { Opt_nopersistent, "nopersistenthandles"}, + { Opt_resilient, "resilienthandles"}, + { Opt_noresilient, "noresilienthandles"}, { Opt_backupuid, "backupuid=%s" }, { Opt_backupgid, "backupgid=%s" }, @@ -1497,6 +1503,33 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, case Opt_nosharesock: vol->nosharesock = true; break; + case Opt_nopersistent: + vol->nopersistent = true; + if (vol->persistent) { + cifs_dbg(VFS, + "persistenthandles mount options conflict\n"); + goto cifs_parse_mount_err; + } + break; + case Opt_persistent: + vol->persistent = true; + if ((vol->nopersistent) || (vol->resilient)) { + cifs_dbg(VFS, + "persistenthandles mount options conflict\n"); + goto cifs_parse_mount_err; + } + break; + case Opt_resilient: + vol->resilient = true; + if (vol->persistent) { + cifs_dbg(VFS, + "persistenthandles mount options conflict\n"); + goto cifs_parse_mount_err; + } + break; + case Opt_noresilient: + vol->resilient = false; /* already the default */ + break; /* Numeric Values */ case Opt_backupuid: @@ -2655,6 +2688,42 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) cifs_dbg(FYI, "DFS disabled (%d)\n", tcon->Flags); } tcon->seal = volume_info->seal; + tcon->use_persistent = false; + /* check if SMB2 or later, CIFS does not support persistent handles */ + if (volume_info->persistent) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "SMB3 or later required for persistent handles\n"); + rc = -EOPNOTSUPP; + goto out_fail; +#ifdef CONFIG_CIFS_SMB2 + } else if (ses->server->capabilities & + SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) + tcon->use_persistent = true; + else /* persistent handles requested but not supported */ { + cifs_dbg(VFS, + "Persistent handles not supported on share\n"); + rc = -EOPNOTSUPP; + goto out_fail; +#endif /* CONFIG_CIFS_SMB2 */ + } +#ifdef CONFIG_CIFS_SMB2 + } else if ((tcon->capabilities & SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY) + && (ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) + && (volume_info->nopersistent == false)) { + cifs_dbg(FYI, "enabling persistent handles\n"); + tcon->use_persistent = true; +#endif /* CONFIG_CIFS_SMB2 */ + } else if (volume_info->resilient) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "SMB2.1 or later required for resilient handles\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } + tcon->use_resilient = true; + } + /* * We can have only one retry value for a connection to a share so for * resources mounted more than once to the same server share the last @@ -3503,6 +3572,15 @@ try_mount_again: goto mount_fail_check; } +#ifdef CONFIG_CIFS_SMB2 + if ((volume_info->persistent == true) && ((ses->server->capabilities & + SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) == 0)) { + cifs_dbg(VFS, "persistent handles not supported by server\n"); + rc = -EOPNOTSUPP; + goto mount_fail_check; + } +#endif /* CONFIG_CIFS_SMB2*/ + /* search for existing tcon to this server share */ tcon = cifs_get_tcon(ses, volume_info); if (IS_ERR(tcon)) { diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 28a77bf1d559..35cf990f87d3 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -85,9 +85,14 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, src_tcon = tlink_tcon(smb_file_src->tlink); target_tcon = tlink_tcon(smb_file_target->tlink); - /* check if source and target are on same tree connection */ - if (src_tcon != target_tcon) { - cifs_dbg(VFS, "file copy src and target on different volume\n"); + /* check source and target on same server (or volume if dup_extents) */ + if (dup_extents && (src_tcon != target_tcon)) { + cifs_dbg(VFS, "source and target of copy not on same share\n"); + goto out_fput; + } + + if (!dup_extents && (src_tcon->ses != target_tcon->ses)) { + cifs_dbg(VFS, "source and target of copy not on same server\n"); goto out_fput; } diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 2ab297dae5a7..f9e766f464be 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -43,6 +43,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, struct smb2_file_all_info *smb2_data = NULL; __u8 smb2_oplock[17]; struct cifs_fid *fid = oparms->fid; + struct network_resiliency_req nr_ioctl_req; smb2_path = cifs_convert_path_to_utf16(oparms->path, oparms->cifs_sb); if (smb2_path == NULL) { @@ -67,6 +68,24 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, if (rc) goto out; + + if (oparms->tcon->use_resilient) { + nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */ + nr_ioctl_req.Reserved = 0; + rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, + fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, true, + (char *)&nr_ioctl_req, sizeof(nr_ioctl_req), + NULL, NULL /* no return info */); + if (rc == -EOPNOTSUPP) { + cifs_dbg(VFS, + "resiliency not supported by server, disabling\n"); + oparms->tcon->use_resilient = false; + } else if (rc) + cifs_dbg(FYI, "error %d setting resiliency\n", rc); + + rc = 0; + } + if (buf) { /* open response does not have IndexNumber field - get it */ rc = SMB2_get_srv_num(xid, oparms->tcon, fid->persistent_fid, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 18da19f4f811..53ccdde6ff18 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -810,7 +810,6 @@ smb2_set_file_size(const unsigned int xid, struct cifs_tcon *tcon, cfile->fid.volatile_fid, cfile->pid, &eof, false); } -#ifdef CONFIG_CIFS_SMB311 static int smb2_duplicate_extents(const unsigned int xid, struct cifsFileInfo *srcfile, @@ -854,8 +853,6 @@ smb2_duplicate_extents(const unsigned int xid, duplicate_extents_out: return rc; } -#endif /* CONFIG_CIFS_SMB311 */ - static int smb2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, @@ -1703,6 +1700,7 @@ struct smb_version_operations smb30_operations = { .create_lease_buf = smb3_create_lease_buf, .parse_lease_buf = smb3_parse_lease_buf, .clone_range = smb2_clone_range, + .duplicate_extents = smb2_duplicate_extents, .validate_negotiate = smb3_validate_negotiate, .wp_retry_size = smb2_wp_retry_size, .dir_needs_close = smb2_dir_needs_close, @@ -1840,7 +1838,7 @@ struct smb_version_values smb21_values = { struct smb_version_values smb30_values = { .version_string = SMB30_VERSION_STRING, .protocol_id = SMB30_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -1860,7 +1858,7 @@ struct smb_version_values smb30_values = { struct smb_version_values smb302_values = { .version_string = SMB302_VERSION_STRING, .protocol_id = SMB302_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -1881,7 +1879,7 @@ struct smb_version_values smb302_values = { struct smb_version_values smb311_values = { .version_string = SMB311_VERSION_STRING, .protocol_id = SMB311_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 61276929d139..767555518d40 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1151,13 +1151,130 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, return 0; } +static struct create_durable_v2 * +create_durable_v2_buf(struct cifs_fid *pfid) +{ + struct create_durable_v2 *buf; + + buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL); + if (!buf) + return NULL; + + buf->ccontext.DataOffset = cpu_to_le16(offsetof + (struct create_durable_v2, dcontext)); + buf->ccontext.DataLength = cpu_to_le32(sizeof(struct durable_context_v2)); + buf->ccontext.NameOffset = cpu_to_le16(offsetof + (struct create_durable_v2, Name)); + buf->ccontext.NameLength = cpu_to_le16(4); + + buf->dcontext.Timeout = 0; /* Should this be configurable by workload */ + buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); + get_random_bytes(buf->dcontext.CreateGuid, 16); + memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16); + + /* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */ + buf->Name[0] = 'D'; + buf->Name[1] = 'H'; + buf->Name[2] = '2'; + buf->Name[3] = 'Q'; + return buf; +} + +static struct create_durable_handle_reconnect_v2 * +create_reconnect_durable_v2_buf(struct cifs_fid *fid) +{ + struct create_durable_handle_reconnect_v2 *buf; + + buf = kzalloc(sizeof(struct create_durable_handle_reconnect_v2), + GFP_KERNEL); + if (!buf) + return NULL; + + buf->ccontext.DataOffset = + cpu_to_le16(offsetof(struct create_durable_handle_reconnect_v2, + dcontext)); + buf->ccontext.DataLength = + cpu_to_le32(sizeof(struct durable_reconnect_context_v2)); + buf->ccontext.NameOffset = + cpu_to_le16(offsetof(struct create_durable_handle_reconnect_v2, + Name)); + buf->ccontext.NameLength = cpu_to_le16(4); + + buf->dcontext.Fid.PersistentFileId = fid->persistent_fid; + buf->dcontext.Fid.VolatileFileId = fid->volatile_fid; + buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); + memcpy(buf->dcontext.CreateGuid, fid->create_guid, 16); + + /* SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 is "DH2C" */ + buf->Name[0] = 'D'; + buf->Name[1] = 'H'; + buf->Name[2] = '2'; + buf->Name[3] = 'C'; + return buf; +} + static int -add_durable_context(struct kvec *iov, unsigned int *num_iovec, +add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec, struct cifs_open_parms *oparms) { struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; + iov[num].iov_base = create_durable_v2_buf(oparms->fid); + if (iov[num].iov_base == NULL) + return -ENOMEM; + iov[num].iov_len = sizeof(struct create_durable_v2); + if (!req->CreateContextsOffset) + req->CreateContextsOffset = + cpu_to_le32(sizeof(struct smb2_create_req) - 4 + + iov[1].iov_len); + le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable_v2)); + inc_rfc1001_len(&req->hdr, sizeof(struct create_durable_v2)); + *num_iovec = num + 1; + return 0; +} + +static int +add_durable_reconnect_v2_context(struct kvec *iov, unsigned int *num_iovec, + struct cifs_open_parms *oparms) +{ + struct smb2_create_req *req = iov[0].iov_base; + unsigned int num = *num_iovec; + + /* indicate that we don't need to relock the file */ + oparms->reconnect = false; + + iov[num].iov_base = create_reconnect_durable_v2_buf(oparms->fid); + if (iov[num].iov_base == NULL) + return -ENOMEM; + iov[num].iov_len = sizeof(struct create_durable_handle_reconnect_v2); + if (!req->CreateContextsOffset) + req->CreateContextsOffset = + cpu_to_le32(sizeof(struct smb2_create_req) - 4 + + iov[1].iov_len); + le32_add_cpu(&req->CreateContextsLength, + sizeof(struct create_durable_handle_reconnect_v2)); + inc_rfc1001_len(&req->hdr, + sizeof(struct create_durable_handle_reconnect_v2)); + *num_iovec = num + 1; + return 0; +} + +static int +add_durable_context(struct kvec *iov, unsigned int *num_iovec, + struct cifs_open_parms *oparms, bool use_persistent) +{ + struct smb2_create_req *req = iov[0].iov_base; + unsigned int num = *num_iovec; + + if (use_persistent) { + if (oparms->reconnect) + return add_durable_reconnect_v2_context(iov, num_iovec, + oparms); + else + return add_durable_v2_context(iov, num_iovec, oparms); + } + if (oparms->reconnect) { iov[num].iov_base = create_reconnect_durable_buf(oparms->fid); /* indicate that we don't need to relock the file */ @@ -1275,7 +1392,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, ccontext->Next = cpu_to_le32(server->vals->create_lease_size); } - rc = add_durable_context(iov, &num_iovecs, oparms); + + rc = add_durable_context(iov, &num_iovecs, oparms, + tcon->use_persistent); if (rc) { cifs_small_buf_release(req); kfree(copy_path); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 451108284a2f..4af52780ec35 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -590,6 +590,44 @@ struct create_durable { } Data; } __packed; +/* See MS-SMB2 2.2.13.2.11 */ +/* Flags */ +#define SMB2_DHANDLE_FLAG_PERSISTENT 0x00000002 +struct durable_context_v2 { + __le32 Timeout; + __le32 Flags; + __u64 Reserved; + __u8 CreateGuid[16]; +} __packed; + +struct create_durable_v2 { + struct create_context ccontext; + __u8 Name[8]; + struct durable_context_v2 dcontext; +} __packed; + +/* See MS-SMB2 2.2.13.2.12 */ +struct durable_reconnect_context_v2 { + struct { + __u64 PersistentFileId; + __u64 VolatileFileId; + } Fid; + __u8 CreateGuid[16]; + __le32 Flags; /* see above DHANDLE_FLAG_PERSISTENT */ +} __packed; + +/* See MS-SMB2 2.2.14.2.12 */ +struct durable_reconnect_context_v2_rsp { + __le32 Timeout; + __le32 Flags; /* see above DHANDLE_FLAG_PERSISTENT */ +} __packed; + +struct create_durable_handle_reconnect_v2 { + struct create_context ccontext; + __u8 Name[8]; + struct durable_reconnect_context_v2 dcontext; +} __packed; + #define COPY_CHUNK_RES_KEY_SIZE 24 struct resume_key_req { char ResumeKey[COPY_CHUNK_RES_KEY_SIZE]; @@ -643,6 +681,13 @@ struct fsctl_get_integrity_information_rsp { /* Integrity flags for above */ #define FSCTL_INTEGRITY_FLAG_CHECKSUM_ENFORCEMENT_OFF 0x00000001 +/* See MS-SMB2 2.2.31.3 */ +struct network_resiliency_req { + __le32 Timeout; + __le32 Reserved; +} __packed; +/* There is no buffer for the response ie no struct network_resiliency_rsp */ + struct validate_negotiate_info_req { __le32 Capabilities; diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h index a639d0dab453..f996daeea271 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/cifs/smbfsctl.h @@ -90,7 +90,7 @@ #define FSCTL_SRV_ENUMERATE_SNAPSHOTS 0x00144064 /* Retrieve an opaque file reference for server-side data movement ie copy */ #define FSCTL_SRV_REQUEST_RESUME_KEY 0x00140078 -#define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 /* BB add struct */ +#define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 #define FSCTL_LMR_GET_LINK_TRACK_INF 0x001400E8 /* BB add struct */ #define FSCTL_LMR_SET_LINK_TRACK_INF 0x001400EC /* BB add struct */ #define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204 @@ -174,8 +174,10 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, else len = iov_iter_zero(max - pos, iter); - if (!len) + if (!len) { + retval = -EFAULT; break; + } pos += len; addr += len; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index d11eff8a4efe..ad0a5ff3d4cd 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -390,39 +390,6 @@ struct acpi_data_node { struct completion kobj_done; }; -static inline bool acpi_check_dma(struct acpi_device *adev, bool *coherent) -{ - bool ret = false; - - if (!adev) - return ret; - - /** - * Currently, we only support _CCA=1 (i.e. coherent_dma=1) - * This should be equivalent to specifyig dma-coherent for - * a device in OF. - * - * For the case when _CCA=0 (i.e. coherent_dma=0 && cca_seen=1), - * There are two cases: - * case 1. Do not support and disable DMA. - * case 2. Support but rely on arch-specific cache maintenance for - * non-coherence DMA operations. - * Currently, we implement case 1 above. - * - * For the case when _CCA is missing (i.e. cca_seen=0) and - * platform specifies ACPI_CCA_REQUIRED, we do not support DMA, - * and fallback to arch-specific default handling. - * - * See acpi_init_coherency() for more info. - */ - if (adev->flags.coherent_dma) { - ret = true; - if (coherent) - *coherent = adev->flags.coherent_dma; - } - return ret; -} - static inline bool is_acpi_node(struct fwnode_handle *fwnode) { return fwnode && (fwnode->type == FWNODE_ACPI @@ -595,6 +562,9 @@ struct acpi_pci_root { /* helper */ +bool acpi_dma_supported(struct acpi_device *adev); +enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev); + struct acpi_device *acpi_find_child_device(struct acpi_device *parent, u64 address, bool check_children); int acpi_is_root_bridge(acpi_handle); diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 72d8803832ff..1bfa602958f2 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -163,9 +163,10 @@ static inline __must_check long __copy_to_user(void __user *to, #define put_user(x, ptr) \ ({ \ + void *__p = (ptr); \ might_fault(); \ - access_ok(VERIFY_WRITE, ptr, sizeof(*ptr)) ? \ - __put_user(x, ptr) : \ + access_ok(VERIFY_WRITE, __p, sizeof(*ptr)) ? \ + __put_user((x), ((__typeof__(*(ptr)) *)__p)) : \ -EFAULT; \ }) @@ -225,9 +226,10 @@ extern int __put_user_bad(void) __attribute__((noreturn)); #define get_user(x, ptr) \ ({ \ + const void *__p = (ptr); \ might_fault(); \ - access_ok(VERIFY_READ, ptr, sizeof(*ptr)) ? \ - __get_user(x, ptr) : \ + access_ok(VERIFY_READ, __p, sizeof(*ptr)) ? \ + __get_user((x), (__typeof__(*(ptr)) *)__p) : \ -EFAULT; \ }) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ebfac2fe0c81..054833939995 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -601,11 +601,16 @@ static inline int acpi_device_modalias(struct device *dev, return -ENODEV; } -static inline bool acpi_check_dma(struct acpi_device *adev, bool *coherent) +static inline bool acpi_dma_supported(struct acpi_device *adev) { return false; } +static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) +{ + return DEV_DMA_NOT_SUPPORTED; +} + #define ACPI_PTR(_ptr) (NULL) #endif /* !CONFIG_ACPI */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 641e5a3ed58c..0fb65843ec1e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -265,7 +265,7 @@ static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) { - return cookie & 0xffff; + return cookie & ((1u << BLK_QC_T_SHIFT) - 1); } #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 397c5cd09794..3e3799cdc6e6 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -29,8 +29,9 @@ #define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */ #define CEPH_OPT_MYIP (1<<2) /* specified my ip */ #define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */ -#define CEPH_OPT_NOMSGAUTH (1<<4) /* not require cephx message signature */ +#define CEPH_OPT_NOMSGAUTH (1<<4) /* don't require msg signing feat */ #define CEPH_OPT_TCP_NODELAY (1<<5) /* TCP_NODELAY on TCP sockets */ +#define CEPH_OPT_NOMSGSIGN (1<<6) /* don't sign msgs */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) @@ -137,6 +138,7 @@ struct ceph_client { #endif }; +#define from_msgr(ms) container_of(ms, struct ceph_client, msgr) /* diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index b2371d9b51fa..71b1d6cdcb5d 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -43,10 +43,9 @@ struct ceph_connection_operations { struct ceph_msg * (*alloc_msg) (struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip); - int (*sign_message) (struct ceph_connection *con, struct ceph_msg *msg); - int (*check_message_signature) (struct ceph_connection *con, - struct ceph_msg *msg); + int (*sign_message) (struct ceph_msg *msg); + int (*check_message_signature) (struct ceph_msg *msg); }; /* use format string %s%d */ @@ -58,8 +57,6 @@ struct ceph_messenger { atomic_t stopping; possible_net_t net; - bool nocrc; - bool tcp_nodelay; /* * the global_seq counts connections i (attempt to) initiate @@ -67,9 +64,6 @@ struct ceph_messenger { */ u32 global_seq; spinlock_t global_seq_lock; - - u64 supported_features; - u64 required_features; }; enum ceph_msg_data_type { @@ -268,11 +262,7 @@ extern void ceph_msgr_exit(void); extern void ceph_msgr_flush(void); extern void ceph_messenger_init(struct ceph_messenger *msgr, - struct ceph_entity_addr *myaddr, - u64 supported_features, - u64 required_features, - bool nocrc, - bool tcp_nodelay); + struct ceph_entity_addr *myaddr); extern void ceph_messenger_fini(struct ceph_messenger *msgr); extern void ceph_con_init(struct ceph_connection *con, void *private, diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 008fc67d0d96..68b575afe5f5 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -10,6 +10,10 @@ #ifdef CONFIG_CONTEXT_TRACKING extern void context_tracking_cpu_set(int cpu); +/* Called with interrupts disabled. */ +extern void __context_tracking_enter(enum ctx_state state); +extern void __context_tracking_exit(enum ctx_state state); + extern void context_tracking_enter(enum ctx_state state); extern void context_tracking_exit(enum ctx_state state); extern void context_tracking_user_enter(void); @@ -18,13 +22,13 @@ extern void context_tracking_user_exit(void); static inline void user_enter(void) { if (context_tracking_is_enabled()) - context_tracking_user_enter(); + context_tracking_enter(CONTEXT_USER); } static inline void user_exit(void) { if (context_tracking_is_enabled()) - context_tracking_user_exit(); + context_tracking_exit(CONTEXT_USER); } static inline enum ctx_state exception_enter(void) @@ -88,13 +92,13 @@ static inline void guest_enter(void) current->flags |= PF_VCPU; if (context_tracking_is_enabled()) - context_tracking_enter(CONTEXT_GUEST); + __context_tracking_enter(CONTEXT_GUEST); } static inline void guest_exit(void) { if (context_tracking_is_enabled()) - context_tracking_exit(CONTEXT_GUEST); + __context_tracking_exit(CONTEXT_GUEST); if (vtime_accounting_enabled()) vtime_guest_exit(current); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 242a6d2b53ff..5706a2108f0a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1183,4 +1183,5 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ + #endif diff --git a/include/linux/math64.h b/include/linux/math64.h index c45c089bfdac..6e8b5b270ffe 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -142,6 +142,13 @@ static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) } #endif /* mul_u64_u32_shr */ +#ifndef mul_u64_u64_shr +static inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift) +{ + return (u64)(((unsigned __int128)a * mul) >> shift); +} +#endif /* mul_u64_u64_shr */ + #else #ifndef mul_u64_u32_shr @@ -161,6 +168,79 @@ static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) } #endif /* mul_u64_u32_shr */ +#ifndef mul_u64_u64_shr +static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) +{ + union { + u64 ll; + struct { +#ifdef __BIG_ENDIAN + u32 high, low; +#else + u32 low, high; +#endif + } l; + } rl, rm, rn, rh, a0, b0; + u64 c; + + a0.ll = a; + b0.ll = b; + + rl.ll = (u64)a0.l.low * b0.l.low; + rm.ll = (u64)a0.l.low * b0.l.high; + rn.ll = (u64)a0.l.high * b0.l.low; + rh.ll = (u64)a0.l.high * b0.l.high; + + /* + * Each of these lines computes a 64-bit intermediate result into "c", + * starting at bits 32-95. The low 32-bits go into the result of the + * multiplication, the high 32-bits are carried into the next step. + */ + rl.l.high = c = (u64)rl.l.high + rm.l.low + rn.l.low; + rh.l.low = c = (c >> 32) + rm.l.high + rn.l.high + rh.l.low; + rh.l.high = (c >> 32) + rh.l.high; + + /* + * The 128-bit result of the multiplication is in rl.ll and rh.ll, + * shift it right and throw away the high part of the result. + */ + if (shift == 0) + return rl.ll; + if (shift < 64) + return (rl.ll >> shift) | (rh.ll << (64 - shift)); + return rh.ll >> (shift & 63); +} +#endif /* mul_u64_u64_shr */ + #endif +#ifndef mul_u64_u32_div +static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) +{ + union { + u64 ll; + struct { +#ifdef __BIG_ENDIAN + u32 high, low; +#else + u32 low, high; +#endif + } l; + } u, rl, rh; + + u.ll = a; + rl.ll = (u64)u.l.low * mul; + rh.ll = (u64)u.l.high * mul + rl.l.high; + + /* Bits 32-63 of the result will be in rh.l.low. */ + rl.l.high = do_div(rh.ll, divisor); + + /* Bits 0-31 of the result will be in rl.l.low. */ + do_div(rl.ll, divisor); + + rl.l.high = rh.l.low; + return rl.ll; +} +#endif /* mul_u64_u32_div */ + #endif /* _LINUX_MATH64_H */ diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 38c0533a3359..2c51ee78b1c0 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -16,7 +16,6 @@ int of_pci_get_devfn(struct device_node *np); int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); -void of_pci_dma_configure(struct pci_dev *pci_dev); void of_pci_check_probe_only(void); #else static inline int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq) @@ -53,8 +52,6 @@ of_get_pci_domain_nr(struct device_node *node) return -1; } -static inline void of_pci_dma_configure(struct pci_dev *pci_dev) { } - static inline void of_pci_check_probe_only(void) { } #endif diff --git a/include/linux/property.h b/include/linux/property.h index 463de52fe891..0a3705a7c9f2 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -27,6 +27,12 @@ enum dev_prop_type { DEV_PROP_MAX, }; +enum dev_dma_attr { + DEV_DMA_NOT_SUPPORTED, + DEV_DMA_NON_COHERENT, + DEV_DMA_COHERENT, +}; + bool device_property_present(struct device *dev, const char *propname); int device_property_read_u8_array(struct device *dev, const char *propname, u8 *val, size_t nval); @@ -168,7 +174,9 @@ struct property_set { void device_add_property_set(struct device *dev, struct property_set *pset); -bool device_dma_is_coherent(struct device *dev); +bool device_dma_supported(struct device *dev); + +enum dev_dma_attr device_get_dma_attr(struct device *dev); int device_get_phy_mode(struct device *dev); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ddb440975382..610a86a892b8 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -44,6 +44,9 @@ struct vfio_device_ops { void (*request)(void *device_data, unsigned int count); }; +extern struct iommu_group *vfio_iommu_group_get(struct device *dev); +extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); + extern int vfio_add_group_dev(struct device *dev, const struct vfio_device_ops *ops, void *device_data); diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 8c5e8b91a3cb..0b69a7753558 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -158,7 +158,7 @@ /* add more to the end as needed */ #define fourcc_mod_code(vendor, val) \ - ((((u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | (val & 0x00ffffffffffffffULL)) + ((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | (val & 0x00ffffffffffffffULL)) /* * Format Modifier tokens: diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 9fd7b5d8df2f..751b69f858c8 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -39,6 +39,13 @@ #define VFIO_SPAPR_TCE_v2_IOMMU 7 /* + * The No-IOMMU IOMMU offers no translation or isolation for devices and + * supports no ioctls outside of VFIO_CHECK_EXTENSION. Use of VFIO's No-IOMMU + * code will taint the host kernel and should be used with extreme caution. + */ +#define VFIO_NOIOMMU_IOMMU 8 + +/* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between * kernel and userspace. We therefore use the _IO() macro for these diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 0a495ab35bc7..d8560ee3bab7 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -58,36 +58,13 @@ static void context_tracking_recursion_exit(void) * instructions to execute won't use any RCU read side critical section * because this function sets RCU in extended quiescent state. */ -void context_tracking_enter(enum ctx_state state) +void __context_tracking_enter(enum ctx_state state) { - unsigned long flags; - - /* - * Repeat the user_enter() check here because some archs may be calling - * this from asm and if no CPU needs context tracking, they shouldn't - * go further. Repeat the check here until they support the inline static - * key check. - */ - if (!context_tracking_is_enabled()) - return; - - /* - * Some contexts may involve an exception occuring in an irq, - * leading to that nesting: - * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() - * This would mess up the dyntick_nesting count though. And rcu_irq_*() - * helpers are enough to protect RCU uses inside the exception. So - * just return immediately if we detect we are in an IRQ. - */ - if (in_interrupt()) - return; - /* Kernel threads aren't supposed to go to userspace */ WARN_ON_ONCE(!current->mm); - local_irq_save(flags); if (!context_tracking_recursion_enter()) - goto out_irq_restore; + return; if ( __this_cpu_read(context_tracking.state) != state) { if (__this_cpu_read(context_tracking.active)) { @@ -120,7 +97,27 @@ void context_tracking_enter(enum ctx_state state) __this_cpu_write(context_tracking.state, state); } context_tracking_recursion_exit(); -out_irq_restore: +} +NOKPROBE_SYMBOL(__context_tracking_enter); +EXPORT_SYMBOL_GPL(__context_tracking_enter); + +void context_tracking_enter(enum ctx_state state) +{ + unsigned long flags; + + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; + + local_irq_save(flags); + __context_tracking_enter(state); local_irq_restore(flags); } NOKPROBE_SYMBOL(context_tracking_enter); @@ -128,7 +125,7 @@ EXPORT_SYMBOL_GPL(context_tracking_enter); void context_tracking_user_enter(void) { - context_tracking_enter(CONTEXT_USER); + user_enter(); } NOKPROBE_SYMBOL(context_tracking_user_enter); @@ -144,19 +141,10 @@ NOKPROBE_SYMBOL(context_tracking_user_enter); * This call supports re-entrancy. This way it can be called from any exception * handler without needing to know if we came from userspace or not. */ -void context_tracking_exit(enum ctx_state state) +void __context_tracking_exit(enum ctx_state state) { - unsigned long flags; - - if (!context_tracking_is_enabled()) - return; - - if (in_interrupt()) - return; - - local_irq_save(flags); if (!context_tracking_recursion_enter()) - goto out_irq_restore; + return; if (__this_cpu_read(context_tracking.state) == state) { if (__this_cpu_read(context_tracking.active)) { @@ -173,7 +161,19 @@ void context_tracking_exit(enum ctx_state state) __this_cpu_write(context_tracking.state, CONTEXT_KERNEL); } context_tracking_recursion_exit(); -out_irq_restore: +} +NOKPROBE_SYMBOL(__context_tracking_exit); +EXPORT_SYMBOL_GPL(__context_tracking_exit); + +void context_tracking_exit(enum ctx_state state) +{ + unsigned long flags; + + if (in_interrupt()) + return; + + local_irq_save(flags); + __context_tracking_exit(state); local_irq_restore(flags); } NOKPROBE_SYMBOL(context_tracking_exit); @@ -181,7 +181,7 @@ EXPORT_SYMBOL_GPL(context_tracking_exit); void context_tracking_user_exit(void) { - context_tracking_exit(CONTEXT_USER); + user_exit(); } NOKPROBE_SYMBOL(context_tracking_user_exit); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2198a630ef58..87fb9801bd9e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -100,8 +100,6 @@ static DEFINE_PER_CPU(bool, trace_cmdline_save); */ static int tracing_disabled = 1; -DEFINE_PER_CPU(int, ftrace_cpu_disabled); - cpumask_var_t __read_mostly tracing_buffer_mask; /* @@ -1775,10 +1773,6 @@ trace_function(struct trace_array *tr, struct ring_buffer_event *event; struct ftrace_entry *entry; - /* If we are reading the ring buffer, don't trace */ - if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) - return; - event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), flags, pc); if (!event) @@ -4554,6 +4548,8 @@ out: return ret; } +#ifdef CONFIG_TRACER_MAX_TRACE + static ssize_t tracing_max_lat_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -4568,6 +4564,8 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, return tracing_nsecs_write(filp->private_data, ubuf, cnt, ppos); } +#endif + static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; @@ -5469,12 +5467,14 @@ static const struct file_operations tracing_thresh_fops = { .llseek = generic_file_llseek, }; +#ifdef CONFIG_TRACER_MAX_TRACE static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, .write = tracing_max_lat_write, .llseek = generic_file_llseek, }; +#endif static const struct file_operations set_tracer_fops = { .open = tracing_open_generic, @@ -6847,7 +6847,9 @@ struct dentry *tracing_init_dentry(void) if (tr->dir) return NULL; - if (WARN_ON(!debugfs_initialized())) + if (WARN_ON(!tracefs_initialized()) || + (IS_ENABLED(CONFIG_DEBUG_FS) && + WARN_ON(!debugfs_initialized()))) return ERR_PTR(-ENODEV); /* diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index dd7620802e72..919d9d07686f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -667,7 +667,6 @@ extern int DYN_FTRACE_TEST_NAME2(void); extern bool ring_buffer_expanded; extern bool tracing_selftest_disabled; -DECLARE_PER_CPU(int, ftrace_cpu_disabled); #ifdef CONFIG_FTRACE_STARTUP_TEST extern int trace_selftest_startup_function(struct tracer *trace, diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 92382af7a213..a663cbb84107 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -288,9 +288,6 @@ int __trace_graph_entry(struct trace_array *tr, struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ftrace_graph_ent_entry *entry; - if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) - return 0; - event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT, sizeof(*entry), flags, pc); if (!event) @@ -403,9 +400,6 @@ void __trace_graph_return(struct trace_array *tr, struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ftrace_graph_ret_entry *entry; - if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) - return; - event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET, sizeof(*entry), flags, pc); if (!event) diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index ba6eb17226da..10d87753ed87 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -8,6 +8,7 @@ #include <linux/ceph/decode.h> #include <linux/ceph/auth.h> +#include <linux/ceph/libceph.h> #include <linux/ceph/messenger.h> #include "crypto.h" @@ -279,6 +280,15 @@ bad: return -EINVAL; } +static void ceph_x_authorizer_cleanup(struct ceph_x_authorizer *au) +{ + ceph_crypto_key_destroy(&au->session_key); + if (au->buf) { + ceph_buffer_put(au->buf); + au->buf = NULL; + } +} + static int ceph_x_build_authorizer(struct ceph_auth_client *ac, struct ceph_x_ticket_handler *th, struct ceph_x_authorizer *au) @@ -297,7 +307,7 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, ceph_crypto_key_destroy(&au->session_key); ret = ceph_crypto_key_clone(&au->session_key, &th->session_key); if (ret) - return ret; + goto out_au; maxlen = sizeof(*msg_a) + sizeof(msg_b) + ceph_x_encrypt_buflen(ticket_blob_len); @@ -309,8 +319,8 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, if (!au->buf) { au->buf = ceph_buffer_new(maxlen, GFP_NOFS); if (!au->buf) { - ceph_crypto_key_destroy(&au->session_key); - return -ENOMEM; + ret = -ENOMEM; + goto out_au; } } au->service = th->service; @@ -340,7 +350,7 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, ret = ceph_x_encrypt(&au->session_key, &msg_b, sizeof(msg_b), p, end - p); if (ret < 0) - goto out_buf; + goto out_au; p += ret; au->buf->vec.iov_len = p - au->buf->vec.iov_base; dout(" built authorizer nonce %llx len %d\n", au->nonce, @@ -348,9 +358,8 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac, BUG_ON(au->buf->vec.iov_len > maxlen); return 0; -out_buf: - ceph_buffer_put(au->buf); - au->buf = NULL; +out_au: + ceph_x_authorizer_cleanup(au); return ret; } @@ -624,8 +633,7 @@ static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac, { struct ceph_x_authorizer *au = (void *)a; - ceph_crypto_key_destroy(&au->session_key); - ceph_buffer_put(au->buf); + ceph_x_authorizer_cleanup(au); kfree(au); } @@ -653,8 +661,7 @@ static void ceph_x_destroy(struct ceph_auth_client *ac) remove_ticket_handler(ac, th); } - if (xi->auth_authorizer.buf) - ceph_buffer_put(xi->auth_authorizer.buf); + ceph_x_authorizer_cleanup(&xi->auth_authorizer); kfree(ac->private); ac->private = NULL; @@ -691,8 +698,10 @@ static int ceph_x_sign_message(struct ceph_auth_handshake *auth, struct ceph_msg *msg) { int ret; - if (!auth->authorizer) + + if (ceph_test_opt(from_msgr(msg->con->msgr), NOMSGSIGN)) return 0; + ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer, msg, &msg->footer.sig); if (ret < 0) @@ -707,8 +716,9 @@ static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth, __le64 sig_check; int ret; - if (!auth->authorizer) + if (ceph_test_opt(from_msgr(msg->con->msgr), NOMSGSIGN)) return 0; + ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer, msg, &sig_check); if (ret < 0) diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 78f098a20796..bcbec33c6a14 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -245,6 +245,8 @@ enum { Opt_nocrc, Opt_cephx_require_signatures, Opt_nocephx_require_signatures, + Opt_cephx_sign_messages, + Opt_nocephx_sign_messages, Opt_tcp_nodelay, Opt_notcp_nodelay, }; @@ -267,6 +269,8 @@ static match_table_t opt_tokens = { {Opt_nocrc, "nocrc"}, {Opt_cephx_require_signatures, "cephx_require_signatures"}, {Opt_nocephx_require_signatures, "nocephx_require_signatures"}, + {Opt_cephx_sign_messages, "cephx_sign_messages"}, + {Opt_nocephx_sign_messages, "nocephx_sign_messages"}, {Opt_tcp_nodelay, "tcp_nodelay"}, {Opt_notcp_nodelay, "notcp_nodelay"}, {-1, NULL} @@ -491,6 +495,12 @@ ceph_parse_options(char *options, const char *dev_name, case Opt_nocephx_require_signatures: opt->flags |= CEPH_OPT_NOMSGAUTH; break; + case Opt_cephx_sign_messages: + opt->flags &= ~CEPH_OPT_NOMSGSIGN; + break; + case Opt_nocephx_sign_messages: + opt->flags |= CEPH_OPT_NOMSGSIGN; + break; case Opt_tcp_nodelay: opt->flags |= CEPH_OPT_TCP_NODELAY; @@ -534,6 +544,8 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client) seq_puts(m, "nocrc,"); if (opt->flags & CEPH_OPT_NOMSGAUTH) seq_puts(m, "nocephx_require_signatures,"); + if (opt->flags & CEPH_OPT_NOMSGSIGN) + seq_puts(m, "nocephx_sign_messages,"); if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0) seq_puts(m, "notcp_nodelay,"); @@ -596,11 +608,7 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, if (ceph_test_opt(client, MYIP)) myaddr = &client->options->my_addr; - ceph_messenger_init(&client->msgr, myaddr, - client->supported_features, - client->required_features, - ceph_test_opt(client, NOCRC), - ceph_test_opt(client, TCP_NODELAY)); + ceph_messenger_init(&client->msgr, myaddr); /* subsystems */ err = ceph_monc_init(&client->monc, client); diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h index d1498224c49d..2e9cab09f37b 100644 --- a/net/ceph/crypto.h +++ b/net/ceph/crypto.h @@ -16,8 +16,10 @@ struct ceph_crypto_key { static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key) { - if (key) + if (key) { kfree(key->key); + key->key = NULL; + } } int ceph_crypto_key_clone(struct ceph_crypto_key *dst, diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b9b0e3b5da49..9981039ef4ff 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -509,7 +509,7 @@ static int ceph_tcp_connect(struct ceph_connection *con) return ret; } - if (con->msgr->tcp_nodelay) { + if (ceph_test_opt(from_msgr(con->msgr), TCP_NODELAY)) { int optval = 1; ret = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, @@ -637,9 +637,6 @@ static int con_close_socket(struct ceph_connection *con) static void ceph_msg_remove(struct ceph_msg *msg) { list_del_init(&msg->list_head); - BUG_ON(msg->con == NULL); - msg->con->ops->put(msg->con); - msg->con = NULL; ceph_msg_put(msg); } @@ -662,15 +659,14 @@ static void reset_connection(struct ceph_connection *con) if (con->in_msg) { BUG_ON(con->in_msg->con != con); - con->in_msg->con = NULL; ceph_msg_put(con->in_msg); con->in_msg = NULL; - con->ops->put(con); } con->connect_seq = 0; con->out_seq = 0; if (con->out_msg) { + BUG_ON(con->out_msg->con != con); ceph_msg_put(con->out_msg); con->out_msg = NULL; } @@ -1205,7 +1201,7 @@ static void prepare_write_message_footer(struct ceph_connection *con) con->out_kvec[v].iov_base = &m->footer; if (con->peer_features & CEPH_FEATURE_MSG_AUTH) { if (con->ops->sign_message) - con->ops->sign_message(con, m); + con->ops->sign_message(m); else m->footer.sig = 0; con->out_kvec[v].iov_len = sizeof(m->footer); @@ -1432,7 +1428,8 @@ static int prepare_write_connect(struct ceph_connection *con) dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con, con->connect_seq, global_seq, proto); - con->out_connect.features = cpu_to_le64(con->msgr->supported_features); + con->out_connect.features = + cpu_to_le64(from_msgr(con->msgr)->supported_features); con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT); con->out_connect.connect_seq = cpu_to_le32(con->connect_seq); con->out_connect.global_seq = cpu_to_le32(global_seq); @@ -1527,7 +1524,7 @@ static int write_partial_message_data(struct ceph_connection *con) { struct ceph_msg *msg = con->out_msg; struct ceph_msg_data_cursor *cursor = &msg->cursor; - bool do_datacrc = !con->msgr->nocrc; + bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC); u32 crc; dout("%s %p msg %p\n", __func__, con, msg); @@ -1552,8 +1549,8 @@ static int write_partial_message_data(struct ceph_connection *con) bool need_crc; int ret; - page = ceph_msg_data_next(&msg->cursor, &page_offset, &length, - &last_piece); + page = ceph_msg_data_next(cursor, &page_offset, &length, + &last_piece); ret = ceph_tcp_sendpage(con->sock, page, page_offset, length, !last_piece); if (ret <= 0) { @@ -1564,7 +1561,7 @@ static int write_partial_message_data(struct ceph_connection *con) } if (do_datacrc && cursor->need_crc) crc = ceph_crc32c_page(crc, page, page_offset, length); - need_crc = ceph_msg_data_advance(&msg->cursor, (size_t)ret); + need_crc = ceph_msg_data_advance(cursor, (size_t)ret); } dout("%s %p msg %p done\n", __func__, con, msg); @@ -2005,8 +2002,8 @@ static int process_banner(struct ceph_connection *con) static int process_connect(struct ceph_connection *con) { - u64 sup_feat = con->msgr->supported_features; - u64 req_feat = con->msgr->required_features; + u64 sup_feat = from_msgr(con->msgr)->supported_features; + u64 req_feat = from_msgr(con->msgr)->required_features; u64 server_feat = ceph_sanitize_features( le64_to_cpu(con->in_reply.features)); int ret; @@ -2232,7 +2229,7 @@ static int read_partial_msg_data(struct ceph_connection *con) { struct ceph_msg *msg = con->in_msg; struct ceph_msg_data_cursor *cursor = &msg->cursor; - const bool do_datacrc = !con->msgr->nocrc; + bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC); struct page *page; size_t page_offset; size_t length; @@ -2246,8 +2243,7 @@ static int read_partial_msg_data(struct ceph_connection *con) if (do_datacrc) crc = con->in_data_crc; while (cursor->resid) { - page = ceph_msg_data_next(&msg->cursor, &page_offset, &length, - NULL); + page = ceph_msg_data_next(cursor, &page_offset, &length, NULL); ret = ceph_tcp_recvpage(con->sock, page, page_offset, length); if (ret <= 0) { if (do_datacrc) @@ -2258,7 +2254,7 @@ static int read_partial_msg_data(struct ceph_connection *con) if (do_datacrc) crc = ceph_crc32c_page(crc, page, page_offset, ret); - (void) ceph_msg_data_advance(&msg->cursor, (size_t)ret); + (void) ceph_msg_data_advance(cursor, (size_t)ret); } if (do_datacrc) con->in_data_crc = crc; @@ -2278,7 +2274,7 @@ static int read_partial_message(struct ceph_connection *con) int end; int ret; unsigned int front_len, middle_len, data_len; - bool do_datacrc = !con->msgr->nocrc; + bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC); bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH); u64 seq; u32 crc; @@ -2423,7 +2419,7 @@ static int read_partial_message(struct ceph_connection *con) } if (need_sign && con->ops->check_message_signature && - con->ops->check_message_signature(con, m)) { + con->ops->check_message_signature(m)) { pr_err("read_partial_message %p signature check failed\n", m); return -EBADMSG; } @@ -2438,13 +2434,10 @@ static int read_partial_message(struct ceph_connection *con) */ static void process_message(struct ceph_connection *con) { - struct ceph_msg *msg; + struct ceph_msg *msg = con->in_msg; BUG_ON(con->in_msg->con != con); - con->in_msg->con = NULL; - msg = con->in_msg; con->in_msg = NULL; - con->ops->put(con); /* if first message, set peer_name */ if (con->peer_name.type == 0) @@ -2677,7 +2670,7 @@ more: if (ret <= 0) { switch (ret) { case -EBADMSG: - con->error_msg = "bad crc"; + con->error_msg = "bad crc/signature"; /* fall through */ case -EBADE: ret = -EIO; @@ -2918,10 +2911,8 @@ static void con_fault(struct ceph_connection *con) if (con->in_msg) { BUG_ON(con->in_msg->con != con); - con->in_msg->con = NULL; ceph_msg_put(con->in_msg); con->in_msg = NULL; - con->ops->put(con); } /* Requeue anything that hasn't been acked */ @@ -2952,15 +2943,8 @@ static void con_fault(struct ceph_connection *con) * initialize a new messenger instance */ void ceph_messenger_init(struct ceph_messenger *msgr, - struct ceph_entity_addr *myaddr, - u64 supported_features, - u64 required_features, - bool nocrc, - bool tcp_nodelay) + struct ceph_entity_addr *myaddr) { - msgr->supported_features = supported_features; - msgr->required_features = required_features; - spin_lock_init(&msgr->global_seq_lock); if (myaddr) @@ -2970,8 +2954,6 @@ void ceph_messenger_init(struct ceph_messenger *msgr, msgr->inst.addr.type = 0; get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce)); encode_my_addr(msgr); - msgr->nocrc = nocrc; - msgr->tcp_nodelay = tcp_nodelay; atomic_set(&msgr->stopping, 0); write_pnet(&msgr->net, get_net(current->nsproxy->net_ns)); @@ -2986,6 +2968,15 @@ void ceph_messenger_fini(struct ceph_messenger *msgr) } EXPORT_SYMBOL(ceph_messenger_fini); +static void msg_con_set(struct ceph_msg *msg, struct ceph_connection *con) +{ + if (msg->con) + msg->con->ops->put(msg->con); + + msg->con = con ? con->ops->get(con) : NULL; + BUG_ON(msg->con != con); +} + static void clear_standby(struct ceph_connection *con) { /* come back from STANDBY? */ @@ -3017,9 +3008,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) return; } - BUG_ON(msg->con != NULL); - msg->con = con->ops->get(con); - BUG_ON(msg->con == NULL); + msg_con_set(msg, con); BUG_ON(!list_empty(&msg->list_head)); list_add_tail(&msg->list_head, &con->out_queue); @@ -3047,16 +3036,15 @@ void ceph_msg_revoke(struct ceph_msg *msg) { struct ceph_connection *con = msg->con; - if (!con) + if (!con) { + dout("%s msg %p null con\n", __func__, msg); return; /* Message not in our possession */ + } mutex_lock(&con->mutex); if (!list_empty(&msg->list_head)) { dout("%s %p msg %p - was on queue\n", __func__, con, msg); list_del_init(&msg->list_head); - BUG_ON(msg->con == NULL); - msg->con->ops->put(msg->con); - msg->con = NULL; msg->hdr.seq = 0; ceph_msg_put(msg); @@ -3080,16 +3068,13 @@ void ceph_msg_revoke(struct ceph_msg *msg) */ void ceph_msg_revoke_incoming(struct ceph_msg *msg) { - struct ceph_connection *con; + struct ceph_connection *con = msg->con; - BUG_ON(msg == NULL); - if (!msg->con) { + if (!con) { dout("%s msg %p null con\n", __func__, msg); - return; /* Message not in our possession */ } - con = msg->con; mutex_lock(&con->mutex); if (con->in_msg == msg) { unsigned int front_len = le32_to_cpu(con->in_hdr.front_len); @@ -3335,9 +3320,8 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) } if (msg) { BUG_ON(*skip); + msg_con_set(msg, con); con->in_msg = msg; - con->in_msg->con = con->ops->get(con); - BUG_ON(con->in_msg->con == NULL); } else { /* * Null message pointer means either we should skip @@ -3384,6 +3368,8 @@ static void ceph_msg_release(struct kref *kref) dout("%s %p\n", __func__, m); WARN_ON(!list_empty(&m->list_head)); + msg_con_set(m, NULL); + /* drop middle, data, if any */ if (m->middle) { ceph_buffer_put(m->middle); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index f79ccac6699f..f8f235930d88 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -120,11 +120,13 @@ static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, } #endif /* CONFIG_BLOCK */ -#define osd_req_op_data(oreq, whch, typ, fld) \ - ({ \ - BUG_ON(whch >= (oreq)->r_num_ops); \ - &(oreq)->r_ops[whch].typ.fld; \ - }) +#define osd_req_op_data(oreq, whch, typ, fld) \ +({ \ + struct ceph_osd_request *__oreq = (oreq); \ + unsigned int __whch = (whch); \ + BUG_ON(__whch >= __oreq->r_num_ops); \ + &__oreq->r_ops[__whch].typ.fld; \ +}) static struct ceph_osd_data * osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which) @@ -1750,8 +1752,7 @@ static void complete_request(struct ceph_osd_request *req) * handle osd op reply. either call the callback if it is specified, * or do the completion to wake up the waiting thread. */ -static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, - struct ceph_connection *con) +static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) { void *p, *end; struct ceph_osd_request *req; @@ -2807,7 +2808,7 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) ceph_osdc_handle_map(osdc, msg); break; case CEPH_MSG_OSD_OPREPLY: - handle_reply(osdc, msg, con); + handle_reply(osdc, msg); break; case CEPH_MSG_WATCH_NOTIFY: handle_watch_notify(osdc, msg); @@ -2849,9 +2850,6 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, goto out; } - if (req->r_reply->con) - dout("%s revoking msg %p from old con %p\n", __func__, - req->r_reply, req->r_reply->con); ceph_msg_revoke_incoming(req->r_reply); if (front_len > req->r_reply->front_alloc_len) { @@ -2978,17 +2976,19 @@ static int invalidate_authorizer(struct ceph_connection *con) return ceph_monc_validate_auth(&osdc->client->monc); } -static int sign_message(struct ceph_connection *con, struct ceph_msg *msg) +static int osd_sign_message(struct ceph_msg *msg) { - struct ceph_osd *o = con->private; + struct ceph_osd *o = msg->con->private; struct ceph_auth_handshake *auth = &o->o_auth; + return ceph_auth_sign_message(auth, msg); } -static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg) +static int osd_check_message_signature(struct ceph_msg *msg) { - struct ceph_osd *o = con->private; + struct ceph_osd *o = msg->con->private; struct ceph_auth_handshake *auth = &o->o_auth; + return ceph_auth_check_message_signature(auth, msg); } @@ -3000,7 +3000,7 @@ static const struct ceph_connection_operations osd_con_ops = { .verify_authorizer_reply = verify_authorizer_reply, .invalidate_authorizer = invalidate_authorizer, .alloc_msg = alloc_msg, - .sign_message = sign_message, - .check_message_signature = check_message_signature, + .sign_message = osd_sign_message, + .check_message_signature = osd_check_message_signature, .fault = osd_reset, }; diff --git a/tools/power/cpupower/debug/i386/dump_psb.c b/tools/power/cpupower/debug/i386/dump_psb.c index 8d6a47514253..2c768cf70128 100644 --- a/tools/power/cpupower/debug/i386/dump_psb.c +++ b/tools/power/cpupower/debug/i386/dump_psb.c @@ -134,7 +134,7 @@ next_one: } static struct option info_opts[] = { - {.name = "numpst", .has_arg=no_argument, .flag=NULL, .val='n'}, + {"numpst", no_argument, NULL, 'n'}, }; void print_help(void) diff --git a/tools/power/cpupower/man/cpupower-idle-set.1 b/tools/power/cpupower/man/cpupower-idle-set.1 index 3e6799d7a79f..580c4e3ea92a 100644 --- a/tools/power/cpupower/man/cpupower-idle-set.1 +++ b/tools/power/cpupower/man/cpupower-idle-set.1 @@ -20,7 +20,9 @@ Disable a specific processor sleep state. Enable a specific processor sleep state. .TP \fB\-D\fR \fB\-\-disable-by-latency\fR <LATENCY> -Disable all idle states with a equal or higher latency than <LATENCY> +Disable all idle states with a equal or higher latency than <LATENCY>. + +Enable all idle states with a latency lower than <LATENCY>. .TP \fB\-E\fR \fB\-\-enable-all\fR Enable all idle states if not enabled already. diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index b4b90a97662c..0e6764330241 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -536,21 +536,21 @@ static int get_latency(unsigned int cpu, unsigned int human) } static struct option info_opts[] = { - { .name = "debug", .has_arg = no_argument, .flag = NULL, .val = 'e'}, - { .name = "boost", .has_arg = no_argument, .flag = NULL, .val = 'b'}, - { .name = "freq", .has_arg = no_argument, .flag = NULL, .val = 'f'}, - { .name = "hwfreq", .has_arg = no_argument, .flag = NULL, .val = 'w'}, - { .name = "hwlimits", .has_arg = no_argument, .flag = NULL, .val = 'l'}, - { .name = "driver", .has_arg = no_argument, .flag = NULL, .val = 'd'}, - { .name = "policy", .has_arg = no_argument, .flag = NULL, .val = 'p'}, - { .name = "governors", .has_arg = no_argument, .flag = NULL, .val = 'g'}, - { .name = "related-cpus", .has_arg = no_argument, .flag = NULL, .val = 'r'}, - { .name = "affected-cpus",.has_arg = no_argument, .flag = NULL, .val = 'a'}, - { .name = "stats", .has_arg = no_argument, .flag = NULL, .val = 's'}, - { .name = "latency", .has_arg = no_argument, .flag = NULL, .val = 'y'}, - { .name = "proc", .has_arg = no_argument, .flag = NULL, .val = 'o'}, - { .name = "human", .has_arg = no_argument, .flag = NULL, .val = 'm'}, - { .name = "no-rounding", .has_arg = no_argument, .flag = NULL, .val = 'n'}, + {"debug", no_argument, NULL, 'e'}, + {"boost", no_argument, NULL, 'b'}, + {"freq", no_argument, NULL, 'f'}, + {"hwfreq", no_argument, NULL, 'w'}, + {"hwlimits", no_argument, NULL, 'l'}, + {"driver", no_argument, NULL, 'd'}, + {"policy", no_argument, NULL, 'p'}, + {"governors", no_argument, NULL, 'g'}, + {"related-cpus", no_argument, NULL, 'r'}, + {"affected-cpus", no_argument, NULL, 'a'}, + {"stats", no_argument, NULL, 's'}, + {"latency", no_argument, NULL, 'y'}, + {"proc", no_argument, NULL, 'o'}, + {"human", no_argument, NULL, 'm'}, + {"no-rounding", no_argument, NULL, 'n'}, { }, }; diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c index 4e213576381e..0fbd1a22c0a9 100644 --- a/tools/power/cpupower/utils/cpufreq-set.c +++ b/tools/power/cpupower/utils/cpufreq-set.c @@ -22,11 +22,11 @@ #define NORM_FREQ_LEN 32 static struct option set_opts[] = { - { .name = "min", .has_arg = required_argument, .flag = NULL, .val = 'd'}, - { .name = "max", .has_arg = required_argument, .flag = NULL, .val = 'u'}, - { .name = "governor", .has_arg = required_argument, .flag = NULL, .val = 'g'}, - { .name = "freq", .has_arg = required_argument, .flag = NULL, .val = 'f'}, - { .name = "related", .has_arg = no_argument, .flag = NULL, .val='r'}, + {"min", required_argument, NULL, 'd'}, + {"max", required_argument, NULL, 'u'}, + {"governor", required_argument, NULL, 'g'}, + {"freq", required_argument, NULL, 'f'}, + {"related", no_argument, NULL, 'r'}, { }, }; diff --git a/tools/power/cpupower/utils/cpuidle-info.c b/tools/power/cpupower/utils/cpuidle-info.c index 75e66de7e7a7..750c1d82c3f7 100644 --- a/tools/power/cpupower/utils/cpuidle-info.c +++ b/tools/power/cpupower/utils/cpuidle-info.c @@ -126,8 +126,8 @@ static void proc_cpuidle_cpu_output(unsigned int cpu) } static struct option info_opts[] = { - { .name = "silent", .has_arg = no_argument, .flag = NULL, .val = 's'}, - { .name = "proc", .has_arg = no_argument, .flag = NULL, .val = 'o'}, + {"silent", no_argument, NULL, 's'}, + {"proc", no_argument, NULL, 'o'}, { }, }; diff --git a/tools/power/cpupower/utils/cpuidle-set.c b/tools/power/cpupower/utils/cpuidle-set.c index d45d8d775c02..d6b6ae44b8c2 100644 --- a/tools/power/cpupower/utils/cpuidle-set.c +++ b/tools/power/cpupower/utils/cpuidle-set.c @@ -13,15 +13,11 @@ #include "helpers/sysfs.h" static struct option info_opts[] = { - { .name = "disable", - .has_arg = required_argument, .flag = NULL, .val = 'd'}, - { .name = "enable", - .has_arg = required_argument, .flag = NULL, .val = 'e'}, - { .name = "disable-by-latency", - .has_arg = required_argument, .flag = NULL, .val = 'D'}, - { .name = "enable-all", - .has_arg = no_argument, .flag = NULL, .val = 'E'}, - { }, + {"disable", required_argument, NULL, 'd'}, + {"enable", required_argument, NULL, 'e'}, + {"disable-by-latency", required_argument, NULL, 'D'}, + {"enable-all", no_argument, NULL, 'E'}, + { }, }; @@ -148,14 +144,21 @@ int cmd_idle_set(int argc, char **argv) (cpu, idlestate); state_latency = sysfs_get_idlestate_latency (cpu, idlestate); - printf("CPU: %u - idlestate %u - state_latency: %llu - latency: %llu\n", - cpu, idlestate, state_latency, latency); - if (disabled == 1 || latency > state_latency) + if (disabled == 1) { + if (latency > state_latency){ + ret = sysfs_idlestate_disable + (cpu, idlestate, 0); + if (ret == 0) + printf(_("Idlestate %u enabled on CPU %u\n"), idlestate, cpu); + } continue; - ret = sysfs_idlestate_disable - (cpu, idlestate, 1); - if (ret == 0) + } + if (latency <= state_latency){ + ret = sysfs_idlestate_disable + (cpu, idlestate, 1); + if (ret == 0) printf(_("Idlestate %u disabled on CPU %u\n"), idlestate, cpu); + } } break; case 'E': diff --git a/tools/power/cpupower/utils/cpupower-info.c b/tools/power/cpupower/utils/cpupower-info.c index 136d979e9586..10299f2e9d2a 100644 --- a/tools/power/cpupower/utils/cpupower-info.c +++ b/tools/power/cpupower/utils/cpupower-info.c @@ -17,8 +17,8 @@ #include "helpers/sysfs.h" static struct option set_opts[] = { - { .name = "perf-bias", .has_arg = optional_argument, .flag = NULL, .val = 'b'}, - { }, + {"perf-bias", optional_argument, NULL, 'b'}, + { }, }; static void print_wrong_arg_exit(void) diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c index 573c75f8e3f5..3e6f374f8dd7 100644 --- a/tools/power/cpupower/utils/cpupower-set.c +++ b/tools/power/cpupower/utils/cpupower-set.c @@ -18,7 +18,7 @@ #include "helpers/bitmask.h" static struct option set_opts[] = { - { .name = "perf-bias", .has_arg = required_argument, .flag = NULL, .val = 'b'}, + {"perf-bias", required_argument, NULL, 'b'}, { }, }; diff --git a/tools/power/cpupower/utils/helpers/topology.c b/tools/power/cpupower/utils/helpers/topology.c index cea398c176e7..9cbb7fd75171 100644 --- a/tools/power/cpupower/utils/helpers/topology.c +++ b/tools/power/cpupower/utils/helpers/topology.c @@ -73,18 +73,22 @@ int get_cpu_topology(struct cpupower_topology *cpu_top) for (cpu = 0; cpu < cpus; cpu++) { cpu_top->core_info[cpu].cpu = cpu; cpu_top->core_info[cpu].is_online = sysfs_is_cpu_online(cpu); - if (!cpu_top->core_info[cpu].is_online) - continue; if(sysfs_topology_read_file( cpu, "physical_package_id", - &(cpu_top->core_info[cpu].pkg)) < 0) - return -1; + &(cpu_top->core_info[cpu].pkg)) < 0) { + cpu_top->core_info[cpu].pkg = -1; + cpu_top->core_info[cpu].core = -1; + continue; + } if(sysfs_topology_read_file( cpu, "core_id", - &(cpu_top->core_info[cpu].core)) < 0) - return -1; + &(cpu_top->core_info[cpu].core)) < 0) { + cpu_top->core_info[cpu].pkg = -1; + cpu_top->core_info[cpu].core = -1; + continue; + } } qsort(cpu_top->core_info, cpus, sizeof(struct cpuid_core_info), @@ -95,12 +99,15 @@ int get_cpu_topology(struct cpupower_topology *cpu_top) done by pkg value. */ last_pkg = cpu_top->core_info[0].pkg; for(cpu = 1; cpu < cpus; cpu++) { - if(cpu_top->core_info[cpu].pkg != last_pkg) { + if (cpu_top->core_info[cpu].pkg != last_pkg && + cpu_top->core_info[cpu].pkg != -1) { + last_pkg = cpu_top->core_info[cpu].pkg; cpu_top->pkgs++; } } - cpu_top->pkgs++; + if (!cpu_top->core_info[0].pkg == -1) + cpu_top->pkgs++; /* Intel's cores count is not consecutively numbered, there may * be a core_id of 3, but none of 2. Assume there always is 0 diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c index c4bae9203a69..05f953f0f0a0 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c @@ -143,6 +143,9 @@ void print_results(int topology_depth, int cpu) /* Be careful CPUs may got resorted for pkg value do not just use cpu */ if (!bitmask_isbitset(cpus_chosen, cpu_top.core_info[cpu].cpu)) return; + if (!cpu_top.core_info[cpu].is_online && + cpu_top.core_info[cpu].pkg == -1) + return; if (topology_depth > 2) printf("%4d|", cpu_top.core_info[cpu].pkg); @@ -191,7 +194,8 @@ void print_results(int topology_depth, int cpu) * It's up to the monitor plug-in to check .is_online, this one * is just for additional info. */ - if (!cpu_top.core_info[cpu].is_online) { + if (!cpu_top.core_info[cpu].is_online && + cpu_top.core_info[cpu].pkg != -1) { printf(_(" *is offline\n")); return; } else @@ -388,6 +392,9 @@ int cmd_monitor(int argc, char **argv) return EXIT_FAILURE; } + if (!cpu_top.core_info[0].is_online) + printf("WARNING: at least one cpu is offline\n"); + /* Default is: monitor all CPUs */ if (bitmask_isallclear(cpus_chosen)) bitmask_setall(cpus_chosen); diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index bde0ef1a63df..d8e4b20b6d54 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -75,6 +75,7 @@ unsigned int aperf_mperf_multiplier = 1; int do_smi; double bclk; double base_hz; +unsigned int has_base_hz; double tsc_tweak = 1.0; unsigned int show_pkg; unsigned int show_core; @@ -96,6 +97,7 @@ unsigned int do_ring_perf_limit_reasons; unsigned int crystal_hz; unsigned long long tsc_hz; int base_cpu; +double discover_bclk(unsigned int family, unsigned int model); #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -511,9 +513,13 @@ int format_counters(struct thread_data *t, struct core_data *c, } /* Bzy_MHz */ - if (has_aperf) - outp += sprintf(outp, "%8.0f", - 1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float); + if (has_aperf) { + if (has_base_hz) + outp += sprintf(outp, "%8.0f", base_hz / units * t->aperf / t->mperf); + else + outp += sprintf(outp, "%8.0f", + 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float); + } /* TSC_MHz */ outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float); @@ -1158,12 +1164,6 @@ int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, static void calculate_tsc_tweak() { - unsigned long long msr; - unsigned int base_ratio; - - get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); - base_ratio = (msr >> 8) & 0xFF; - base_hz = base_ratio * bclk * 1000000; tsc_tweak = base_hz / tsc_hz; } @@ -1440,7 +1440,7 @@ dump_config_tdp(void) get_msr(base_cpu, MSR_TURBO_ACTIVATION_RATIO, &msr); fprintf(stderr, "cpu%d: MSR_TURBO_ACTIVATION_RATIO: 0x%08llx (", base_cpu, msr); - fprintf(stderr, "MAX_NON_TURBO_RATIO=%d", (unsigned int)(msr) & 0xEF); + fprintf(stderr, "MAX_NON_TURBO_RATIO=%d", (unsigned int)(msr) & 0x7F); fprintf(stderr, " lock=%d", (unsigned int)(msr >> 31) & 1); fprintf(stderr, ")\n"); } @@ -1821,6 +1821,7 @@ void check_permissions() int probe_nhm_msrs(unsigned int family, unsigned int model) { unsigned long long msr; + unsigned int base_ratio; int *pkg_cstate_limits; if (!genuine_intel) @@ -1829,6 +1830,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) if (family != 6) return 0; + bclk = discover_bclk(family, model); + switch (model) { case 0x1A: /* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */ case 0x1E: /* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */ @@ -1871,9 +1874,13 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) return 0; } get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); - pkg_cstate_limit = pkg_cstate_limits[msr & 0xF]; + get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); + base_ratio = (msr >> 8) & 0xFF; + + base_hz = base_ratio * bclk * 1000000; + has_base_hz = 1; return 1; } int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model) @@ -2780,7 +2787,6 @@ void process_cpuid() do_skl_residency = has_skl_msrs(family, model); do_slm_cstates = is_slm(family, model); do_knl_cstates = is_knl(family, model); - bclk = discover_bclk(family, model); rapl_probe(family, model); perf_limit_reasons_probe(family, model); |