diff options
| author | Olof Johansson <olof@lixom.net> | 2013-12-28 15:38:32 -0800 |
|---|---|---|
| committer | Olof Johansson <olof@lixom.net> | 2013-12-28 15:38:32 -0800 |
| commit | 9b17c16525552b247cb2d9bb8eeadc87950b36ff (patch) | |
| tree | 449426f2b37bb340e286fe0def9bf9cef29ec2a7 | |
| parent | 4cff6123536236fa84f826d9b93452903b90fe2e (diff) | |
| parent | 82f4fe707836e80b0fcaae9a4a1756e6e89c5e62 (diff) | |
Merge tag 'omap-for-v3.13/intc-ldp-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into fixes
From Tony Lindgren:
Fix a regression for wrong interrupt numbers for some devices after
the sparse IRQ conversion, fix DRA7 console output for earlyprintk,
and fix the LDP LCD backlight when DSS is built into the kernel and
not as a loadable module.
* tag 'omap-for-v3.13/intc-ldp-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap:
ARM: OMAP2+: Fix LCD panel backlight regression for LDP legacy booting
ARM: OMAP2+: hwmod_data: fix missing OMAP_INTC_START in irq data
ARM: DRA7: hwmod: Fix boot crash with DEBUG_LL
+ v3.13-rc5
Signed-off-by: Olof Johansson <olof@lixom.net>
217 files changed, 2035 insertions, 1092 deletions
diff --git a/Documentation/module-signing.txt b/Documentation/module-signing.txt new file mode 100644 index 000000000000..2b40e04d3c49 --- /dev/null +++ b/Documentation/module-signing.txt @@ -0,0 +1,240 @@ + ============================== + KERNEL MODULE SIGNING FACILITY + ============================== + +CONTENTS + + - Overview. + - Configuring module signing. + - Generating signing keys. + - Public keys in the kernel. + - Manually signing modules. + - Signed modules and stripping. + - Loading signed modules. + - Non-valid signatures and unsigned modules. + - Administering/protecting the private key. + + +======== +OVERVIEW +======== + +The kernel module signing facility cryptographically signs modules during +installation and then checks the signature upon loading the module. This +allows increased kernel security by disallowing the loading of unsigned modules +or modules signed with an invalid key. Module signing increases security by +making it harder to load a malicious module into the kernel. The module +signature checking is done by the kernel so that it is not necessary to have +trusted userspace bits. + +This facility uses X.509 ITU-T standard certificates to encode the public keys +involved. The signatures are not themselves encoded in any industrial standard +type. The facility currently only supports the RSA public key encryption +standard (though it is pluggable and permits others to be used). The possible +hash algorithms that can be used are SHA-1, SHA-224, SHA-256, SHA-384, and +SHA-512 (the algorithm is selected by data in the signature). + + +========================== +CONFIGURING MODULE SIGNING +========================== + +The module signing facility is enabled by going to the "Enable Loadable Module +Support" section of the kernel configuration and turning on + + CONFIG_MODULE_SIG "Module signature verification" + +This has a number of options available: + + (1) "Require modules to be validly signed" (CONFIG_MODULE_SIG_FORCE) + + This specifies how the kernel should deal with a module that has a + signature for which the key is not known or a module that is unsigned. + + If this is off (ie. "permissive"), then modules for which the key is not + available and modules that are unsigned are permitted, but the kernel will + be marked as being tainted. + + If this is on (ie. "restrictive"), only modules that have a valid + signature that can be verified by a public key in the kernel's possession + will be loaded. All other modules will generate an error. + + Irrespective of the setting here, if the module has a signature block that + cannot be parsed, it will be rejected out of hand. + + + (2) "Automatically sign all modules" (CONFIG_MODULE_SIG_ALL) + + If this is on then modules will be automatically signed during the + modules_install phase of a build. If this is off, then the modules must + be signed manually using: + + scripts/sign-file + + + (3) "Which hash algorithm should modules be signed with?" + + This presents a choice of which hash algorithm the installation phase will + sign the modules with: + + CONFIG_SIG_SHA1 "Sign modules with SHA-1" + CONFIG_SIG_SHA224 "Sign modules with SHA-224" + CONFIG_SIG_SHA256 "Sign modules with SHA-256" + CONFIG_SIG_SHA384 "Sign modules with SHA-384" + CONFIG_SIG_SHA512 "Sign modules with SHA-512" + + The algorithm selected here will also be built into the kernel (rather + than being a module) so that modules signed with that algorithm can have + their signatures checked without causing a dependency loop. + + +======================= +GENERATING SIGNING KEYS +======================= + +Cryptographic keypairs are required to generate and check signatures. A +private key is used to generate a signature and the corresponding public key is +used to check it. The private key is only needed during the build, after which +it can be deleted or stored securely. The public key gets built into the +kernel so that it can be used to check the signatures as the modules are +loaded. + +Under normal conditions, the kernel build will automatically generate a new +keypair using openssl if one does not exist in the files: + + signing_key.priv + signing_key.x509 + +during the building of vmlinux (the public part of the key needs to be built +into vmlinux) using parameters in the: + + x509.genkey + +file (which is also generated if it does not already exist). + +It is strongly recommended that you provide your own x509.genkey file. + +Most notably, in the x509.genkey file, the req_distinguished_name section +should be altered from the default: + + [ req_distinguished_name ] + O = Magrathea + CN = Glacier signing key + emailAddress = slartibartfast@magrathea.h2g2 + +The generated RSA key size can also be set with: + + [ req ] + default_bits = 4096 + + +It is also possible to manually generate the key private/public files using the +x509.genkey key generation configuration file in the root node of the Linux +kernel sources tree and the openssl command. The following is an example to +generate the public/private key files: + + openssl req -new -nodes -utf8 -sha256 -days 36500 -batch -x509 \ + -config x509.genkey -outform DER -out signing_key.x509 \ + -keyout signing_key.priv + + +========================= +PUBLIC KEYS IN THE KERNEL +========================= + +The kernel contains a ring of public keys that can be viewed by root. They're +in a keyring called ".system_keyring" that can be seen by: + + [root@deneb ~]# cat /proc/keys + ... + 223c7853 I------ 1 perm 1f030000 0 0 keyring .system_keyring: 1 + 302d2d52 I------ 1 perm 1f010000 0 0 asymmetri Fedora kernel signing key: d69a84e6bce3d216b979e9505b3e3ef9a7118079: X509.RSA a7118079 [] + ... + +Beyond the public key generated specifically for module signing, any file +placed in the kernel source root directory or the kernel build root directory +whose name is suffixed with ".x509" will be assumed to be an X.509 public key +and will be added to the keyring. + +Further, the architecture code may take public keys from a hardware store and +add those in also (e.g. from the UEFI key database). + +Finally, it is possible to add additional public keys by doing: + + keyctl padd asymmetric "" [.system_keyring-ID] <[key-file] + +e.g.: + + keyctl padd asymmetric "" 0x223c7853 <my_public_key.x509 + +Note, however, that the kernel will only permit keys to be added to +.system_keyring _if_ the new key's X.509 wrapper is validly signed by a key +that is already resident in the .system_keyring at the time the key was added. + + +========================= +MANUALLY SIGNING MODULES +========================= + +To manually sign a module, use the scripts/sign-file tool available in +the Linux kernel source tree. The script requires 4 arguments: + + 1. The hash algorithm (e.g., sha256) + 2. The private key filename + 3. The public key filename + 4. The kernel module to be signed + +The following is an example to sign a kernel module: + + scripts/sign-file sha512 kernel-signkey.priv \ + kernel-signkey.x509 module.ko + +The hash algorithm used does not have to match the one configured, but if it +doesn't, you should make sure that hash algorithm is either built into the +kernel or can be loaded without requiring itself. + + +============================ +SIGNED MODULES AND STRIPPING +============================ + +A signed module has a digital signature simply appended at the end. The string +"~Module signature appended~." at the end of the module's file confirms that a +signature is present but it does not confirm that the signature is valid! + +Signed modules are BRITTLE as the signature is outside of the defined ELF +container. Thus they MAY NOT be stripped once the signature is computed and +attached. Note the entire module is the signed payload, including any and all +debug information present at the time of signing. + + +====================== +LOADING SIGNED MODULES +====================== + +Modules are loaded with insmod, modprobe, init_module() or finit_module(), +exactly as for unsigned modules as no processing is done in userspace. The +signature checking is all done within the kernel. + + +========================================= +NON-VALID SIGNATURES AND UNSIGNED MODULES +========================================= + +If CONFIG_MODULE_SIG_FORCE is enabled or enforcemodulesig=1 is supplied on +the kernel command line, the kernel will only load validly signed modules +for which it has a public key. Otherwise, it will also load modules that are +unsigned. Any module for which the kernel has a key, but which proves to have +a signature mismatch will not be permitted to load. + +Any module that has an unparseable signature will be rejected. + + +========================================= +ADMINISTERING/PROTECTING THE PRIVATE KEY +========================================= + +Since the private key is used to sign modules, viruses and malware could use +the private key to sign modules and compromise the operating system. The +private key must be either destroyed or moved to a secure location and not kept +in the root node of the kernel source tree. diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 3c12d9a7ed00..8a984e994e61 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -16,8 +16,12 @@ ip_default_ttl - INTEGER Default: 64 (as recommended by RFC1700) ip_no_pmtu_disc - BOOLEAN - Disable Path MTU Discovery. - default FALSE + Disable Path MTU Discovery. If enabled and a + fragmentation-required ICMP is received, the PMTU to this + destination will be set to min_pmtu (see below). You will need + to raise min_pmtu to the smallest interface MTU on your system + manually if you want to avoid locally generated fragments. + Default: FALSE min_pmtu - INTEGER default 552 - minimum discovered Path MTU diff --git a/MAINTAINERS b/MAINTAINERS index 5593bc604146..d5e4ff328cc7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3763,9 +3763,11 @@ F: include/uapi/linux/gigaset_dev.h GPIO SUBSYSTEM M: Linus Walleij <linus.walleij@linaro.org> -S: Maintained +M: Alexandre Courbot <gnurou@gmail.com> L: linux-gpio@vger.kernel.org -F: Documentation/gpio.txt +T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git +S: Maintained +F: Documentation/gpio/ F: drivers/gpio/ F: include/linux/gpio* F: include/asm-generic/gpio.h @@ -3833,6 +3835,12 @@ T: git git://linuxtv.org/media_tree.git S: Maintained F: drivers/media/usb/gspca/ +GUID PARTITION TABLE (GPT) +M: Davidlohr Bueso <davidlohr@hp.com> +L: linux-efi@vger.kernel.org +S: Maintained +F: block/partitions/efi.* + STK1160 USB VIDEO CAPTURE DRIVER M: Ezequiel Garcia <elezegarcia@gmail.com> L: linux-media@vger.kernel.org @@ -5913,12 +5921,21 @@ M: Steffen Klassert <steffen.klassert@secunet.com> M: Herbert Xu <herbert@gondor.apana.org.au> M: "David S. Miller" <davem@davemloft.net> L: netdev@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git S: Maintained F: net/xfrm/ F: net/key/ F: net/ipv4/xfrm* +F: net/ipv4/esp4.c +F: net/ipv4/ah4.c +F: net/ipv4/ipcomp.c +F: net/ipv4/ip_vti.c F: net/ipv6/xfrm* +F: net/ipv6/esp6.c +F: net/ipv6/ah6.c +F: net/ipv6/ipcomp6.c +F: net/ipv6/ip6_vti.c F: include/uapi/linux/xfrm.h F: include/net/xfrm.h @@ -9573,7 +9590,7 @@ F: drivers/xen/*swiotlb* XFS FILESYSTEM P: Silicon Graphics Inc -M: Dave Chinner <dchinner@fromorbit.com> +M: Dave Chinner <david@fromorbit.com> M: Ben Myers <bpm@sgi.com> M: xfs@oss.sgi.com L: xfs@oss.sgi.com @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = One Giant Leap for Frogkind # *DOCUMENTATION* @@ -732,19 +732,15 @@ export mod_strip_cmd # Select initial ramdisk compression format, default is gzip(1). # This shall be used by the dracut(8) tool while creating an initramfs image. # -INITRD_COMPRESS=gzip -ifeq ($(CONFIG_RD_BZIP2), y) - INITRD_COMPRESS=bzip2 -else ifeq ($(CONFIG_RD_LZMA), y) - INITRD_COMPRESS=lzma -else ifeq ($(CONFIG_RD_XZ), y) - INITRD_COMPRESS=xz -else ifeq ($(CONFIG_RD_LZO), y) - INITRD_COMPRESS=lzo -else ifeq ($(CONFIG_RD_LZ4), y) - INITRD_COMPRESS=lz4 -endif -export INITRD_COMPRESS +INITRD_COMPRESS-y := gzip +INITRD_COMPRESS-$(CONFIG_RD_BZIP2) := bzip2 +INITRD_COMPRESS-$(CONFIG_RD_LZMA) := lzma +INITRD_COMPRESS-$(CONFIG_RD_XZ) := xz +INITRD_COMPRESS-$(CONFIG_RD_LZO) := lzo +INITRD_COMPRESS-$(CONFIG_RD_LZ4) := lz4 +# do not export INITRD_COMPRESS, since we didn't actually +# choose a sane default compression above. +# export INITRD_COMPRESS := $(INITRD_COMPRESS-y) ifdef CONFIG_MODULE_SIG_ALL MODSECKEY = ./signing_key.priv diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h index 68125dd766c6..39e58d1cdf90 100644 --- a/arch/arc/include/uapi/asm/unistd.h +++ b/arch/arc/include/uapi/asm/unistd.h @@ -8,7 +8,11 @@ /******** no-legacy-syscalls-ABI *******/ -#ifndef _UAPI_ASM_ARC_UNISTD_H +/* + * Non-typical guard macro to enable inclusion twice in ARCH sys.c + * That is how the Generic syscall wrapper generator works + */ +#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL) #define _UAPI_ASM_ARC_UNISTD_H #define __ARCH_WANT_SYS_EXECVE @@ -36,4 +40,6 @@ __SYSCALL(__NR_arc_gettls, sys_arc_gettls) #define __NR_sysfs (__NR_arch_specific_syscall + 3) __SYSCALL(__NR_sysfs, sys_sysfs) +#undef __SYSCALL + #endif diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c index 4ec8d82b0492..44a59c3abfb0 100644 --- a/arch/arm/mach-omap2/board-ldp.c +++ b/arch/arm/mach-omap2/board-ldp.c @@ -242,12 +242,18 @@ static void __init ldp_display_init(void) static int ldp_twl_gpio_setup(struct device *dev, unsigned gpio, unsigned ngpio) { + int res; + /* LCD enable GPIO */ ldp_lcd_pdata.enable_gpio = gpio + 7; /* Backlight enable GPIO */ ldp_lcd_pdata.backlight_gpio = gpio + 15; + res = platform_device_register(&ldp_lcd_device); + if (res) + pr_err("Unable to register LCD: %d\n", res); + return 0; } @@ -346,7 +352,6 @@ static struct omap2_hsmmc_info mmc[] __initdata = { static struct platform_device *ldp_devices[] __initdata = { &ldp_gpio_keys_device, - &ldp_lcd_device, }; #ifdef CONFIG_OMAP_MUX diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c index 56cebb05509e..d23c77fadb31 100644 --- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c @@ -796,7 +796,7 @@ struct omap_hwmod omap2xxx_counter_32k_hwmod = { /* gpmc */ static struct omap_hwmod_irq_info omap2xxx_gpmc_irqs[] = { - { .irq = 20 }, + { .irq = 20 + OMAP_INTC_START, }, { .irq = -1 } }; @@ -841,7 +841,7 @@ static struct omap_hwmod_class omap2_rng_hwmod_class = { }; static struct omap_hwmod_irq_info omap2_rng_mpu_irqs[] = { - { .irq = 52 }, + { .irq = 52 + OMAP_INTC_START, }, { .irq = -1 } }; diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index d33742908f97..4c3b1e6df508 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -2165,7 +2165,7 @@ static struct omap_hwmod_class omap3xxx_gpmc_hwmod_class = { }; static struct omap_hwmod_irq_info omap3xxx_gpmc_irqs[] = { - { .irq = 20 }, + { .irq = 20 + OMAP_INTC_START, }, { .irq = -1 } }; @@ -2999,7 +2999,7 @@ static struct omap_mmu_dev_attr mmu_isp_dev_attr = { static struct omap_hwmod omap3xxx_mmu_isp_hwmod; static struct omap_hwmod_irq_info omap3xxx_mmu_isp_irqs[] = { - { .irq = 24 }, + { .irq = 24 + OMAP_INTC_START, }, { .irq = -1 } }; @@ -3041,7 +3041,7 @@ static struct omap_mmu_dev_attr mmu_iva_dev_attr = { static struct omap_hwmod omap3xxx_mmu_iva_hwmod; static struct omap_hwmod_irq_info omap3xxx_mmu_iva_irqs[] = { - { .irq = 28 }, + { .irq = 28 + OMAP_INTC_START, }, { .irq = -1 } }; diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index db32d5380b11..18f333c440db 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -1637,7 +1637,7 @@ static struct omap_hwmod dra7xx_uart1_hwmod = { .class = &dra7xx_uart_hwmod_class, .clkdm_name = "l4per_clkdm", .main_clk = "uart1_gfclk_mux", - .flags = HWMOD_SWSUP_SIDLE_ACT, + .flags = HWMOD_SWSUP_SIDLE_ACT | DEBUG_OMAP2UART1_FLAGS, .prcm = { .omap4 = { .clkctrl_offs = DRA7XX_CM_L4PER_UART1_CLKCTRL_OFFSET, diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 83e4f959ee47..85501238b425 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -96,7 +96,7 @@ static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, struct remap_data *info = data; struct page *page = info->pages[info->index++]; unsigned long pfn = page_to_pfn(page); - pte_t pte = pfn_pte(pfn, info->prot); + pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot)); if (map_foreign_page(pfn, info->fgmfn, info->domid)) return -EFAULT; @@ -224,10 +224,10 @@ static int __init xen_guest_init(void) } if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res)) return 0; - xen_hvm_resume_frames = res.start >> PAGE_SHIFT; + xen_hvm_resume_frames = res.start; xen_events_irq = irq_of_parse_and_map(node, 0); pr_info("Xen %s support found, events_irq=%d gnttab_frame_pfn=%lx\n", - version, xen_events_irq, xen_hvm_resume_frames); + version, xen_events_irq, (xen_hvm_resume_frames >> PAGE_SHIFT)); xen_domain_type = XEN_HVM_DOMAIN; xen_setup_features(); diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h index 2820f1a6eebe..dde3fc9c49f0 100644 --- a/arch/arm64/include/asm/xen/page-coherent.h +++ b/arch/arm64/include/asm/xen/page-coherent.h @@ -23,25 +23,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); } static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); } static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { - __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir); } static inline void xen_dma_sync_single_for_device(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { - __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir); } #endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 6777a2192b83..6a8928bba03c 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -214,31 +214,29 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, { int err, len, type, disabled = !ctrl.enabled; - if (disabled) { - len = 0; - type = HW_BREAKPOINT_EMPTY; - } else { - err = arch_bp_generic_fields(ctrl, &len, &type); - if (err) - return err; - - switch (note_type) { - case NT_ARM_HW_BREAK: - if ((type & HW_BREAKPOINT_X) != type) - return -EINVAL; - break; - case NT_ARM_HW_WATCH: - if ((type & HW_BREAKPOINT_RW) != type) - return -EINVAL; - break; - default: + attr->disabled = disabled; + if (disabled) + return 0; + + err = arch_bp_generic_fields(ctrl, &len, &type); + if (err) + return err; + + switch (note_type) { + case NT_ARM_HW_BREAK: + if ((type & HW_BREAKPOINT_X) != type) return -EINVAL; - } + break; + case NT_ARM_HW_WATCH: + if ((type & HW_BREAKPOINT_RW) != type) + return -EINVAL; + break; + default: + return -EINVAL; } attr->bp_len = len; attr->bp_type = type; - attr->disabled = disabled; return 0; } diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 4a594b76674d..bc23b1ba7980 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -192,6 +192,10 @@ extern void kvmppc_load_up_vsx(void); extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst); extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst); extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd); +extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, + struct kvm_vcpu *vcpu); +extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, + struct kvmppc_book3s_shadow_vcpu *svcpu); static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 0bd9348a4db9..192917d2239c 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -79,6 +79,7 @@ struct kvmppc_host_state { ulong vmhandler; ulong scratch0; ulong scratch1; + ulong scratch2; u8 in_guest; u8 restore_hid5; u8 napping; @@ -106,6 +107,7 @@ struct kvmppc_host_state { }; struct kvmppc_book3s_shadow_vcpu { + bool in_use; ulong gpr[14]; u32 cr; u32 xer; diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 033c06be1d84..7bdcf340016c 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -720,13 +720,13 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe, int64_t opal_pci_poll(uint64_t phb_id); int64_t opal_return_cpu(void); -int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, uint64_t *val); +int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val); int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val); int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type, uint32_t addr, uint32_t data, uint32_t sz); int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type, - uint32_t addr, uint32_t *data, uint32_t sz); + uint32_t addr, __be32 *data, uint32_t sz); int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result); int64_t opal_manage_flash(uint8_t op); int64_t opal_update_flash(uint64_t blk_list); diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 9ee12610af02..aace90547614 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -35,7 +35,7 @@ extern void giveup_vsx(struct task_struct *); extern void enable_kernel_spe(void); extern void giveup_spe(struct task_struct *); extern void load_up_spe(struct task_struct *); -extern void switch_booke_debug_regs(struct thread_struct *new_thread); +extern void switch_booke_debug_regs(struct debug_reg *new_debug); #ifndef CONFIG_SMP extern void discard_lazy_cpu_state(void); diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 2ea5cc033ec8..d3de01066f7d 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -576,6 +576,7 @@ int main(void) HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler); HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); + HSTATE_FIELD(HSTATE_SCRATCH2, scratch2); HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); HSTATE_FIELD(HSTATE_NAPPING, napping); diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 779a78c26435..11c1d069d920 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -124,15 +124,15 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) { unsigned long addr; - const u32 *basep, *sizep; + const __be32 *basep, *sizep; unsigned int rtas_start = 0, rtas_end = 0; basep = of_get_property(rtas.dev, "linux,rtas-base", NULL); sizep = of_get_property(rtas.dev, "rtas-size", NULL); if (basep && sizep) { - rtas_start = *basep; - rtas_end = *basep + *sizep; + rtas_start = be32_to_cpup(basep); + rtas_end = rtas_start + be32_to_cpup(sizep); } for (addr = begin; addr < end; addr += PAGE_SIZE) { diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3386d8ab7eb0..4a96556fd2d4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -339,7 +339,7 @@ static void set_debug_reg_defaults(struct thread_struct *thread) #endif } -static void prime_debug_regs(struct thread_struct *thread) +static void prime_debug_regs(struct debug_reg *debug) { /* * We could have inherited MSR_DE from userspace, since @@ -348,22 +348,22 @@ static void prime_debug_regs(struct thread_struct *thread) */ mtmsr(mfmsr() & ~MSR_DE); - mtspr(SPRN_IAC1, thread->debug.iac1); - mtspr(SPRN_IAC2, thread->debug.iac2); + mtspr(SPRN_IAC1, debug->iac1); + mtspr(SPRN_IAC2, debug->iac2); #if CONFIG_PPC_ADV_DEBUG_IACS > 2 - mtspr(SPRN_IAC3, thread->debug.iac3); - mtspr(SPRN_IAC4, thread->debug.iac4); + mtspr(SPRN_IAC3, debug->iac3); + mtspr(SPRN_IAC4, debug->iac4); #endif - mtspr(SPRN_DAC1, thread->debug.dac1); - mtspr(SPRN_DAC2, thread->debug.dac2); + mtspr(SPRN_DAC1, debug->dac1); + mtspr(SPRN_DAC2, debug->dac2); #if CONFIG_PPC_ADV_DEBUG_DVCS > 0 - mtspr(SPRN_DVC1, thread->debug.dvc1); - mtspr(SPRN_DVC2, thread->debug.dvc2); + mtspr(SPRN_DVC1, debug->dvc1); + mtspr(SPRN_DVC2, debug->dvc2); #endif - mtspr(SPRN_DBCR0, thread->debug.dbcr0); - mtspr(SPRN_DBCR1, thread->debug.dbcr1); + mtspr(SPRN_DBCR0, debug->dbcr0); + mtspr(SPRN_DBCR1, debug->dbcr1); #ifdef CONFIG_BOOKE - mtspr(SPRN_DBCR2, thread->debug.dbcr2); + mtspr(SPRN_DBCR2, debug->dbcr2); #endif } /* @@ -371,11 +371,11 @@ static void prime_debug_regs(struct thread_struct *thread) * debug registers, set the debug registers from the values * stored in the new thread. */ -void switch_booke_debug_regs(struct thread_struct *new_thread) +void switch_booke_debug_regs(struct debug_reg *new_debug) { if ((current->thread.debug.dbcr0 & DBCR0_IDM) - || (new_thread->debug.dbcr0 & DBCR0_IDM)) - prime_debug_regs(new_thread); + || (new_debug->dbcr0 & DBCR0_IDM)) + prime_debug_regs(new_debug); } EXPORT_SYMBOL_GPL(switch_booke_debug_regs); #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ @@ -683,7 +683,7 @@ struct task_struct *__switch_to(struct task_struct *prev, #endif /* CONFIG_SMP */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS - switch_booke_debug_regs(&new->thread); + switch_booke_debug_regs(&new->thread.debug); #else /* * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 75fb40498b41..2e3d2bf536c5 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1555,7 +1555,7 @@ long arch_ptrace(struct task_struct *child, long request, flush_fp_to_thread(child); if (fpidx < (PT_FPSCR - PT_FPR0)) - memcpy(&tmp, &child->thread.fp_state.fpr, + memcpy(&tmp, &child->thread.TS_FPR(fpidx), sizeof(long)); else tmp = child->thread.fp_state.fpscr; @@ -1588,7 +1588,7 @@ long arch_ptrace(struct task_struct *child, long request, flush_fp_to_thread(child); if (fpidx < (PT_FPSCR - PT_FPR0)) - memcpy(&child->thread.fp_state.fpr, &data, + memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long)); else child->thread.fp_state.fpscr = data; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index febc80445d25..bc76cc6b419c 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -479,7 +479,7 @@ void __init smp_setup_cpu_maps(void) if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR) && (dn = of_find_node_by_path("/rtas"))) { int num_addr_cell, num_size_cell, maxcpus; - const unsigned int *ireg; + const __be32 *ireg; num_addr_cell = of_n_addr_cells(dn); num_size_cell = of_n_size_cells(dn); @@ -489,7 +489,7 @@ void __init smp_setup_cpu_maps(void) if (!ireg) goto out; - maxcpus = ireg[num_addr_cell + num_size_cell]; + maxcpus = be32_to_cpup(ireg + num_addr_cell + num_size_cell); /* Double maxcpus for processors which have SMT capability */ if (cpu_has_feature(CPU_FTR_SMT)) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index a3b64f3bf9a2..c1cf4a1522d9 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -580,7 +580,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) int cpu_to_core_id(int cpu) { struct device_node *np; - const int *reg; + const __be32 *reg; int id = -1; np = of_get_cpu_node(cpu, NULL); @@ -591,7 +591,7 @@ int cpu_to_core_id(int cpu) if (!reg) goto out; - id = *reg; + id = be32_to_cpup(reg); out: of_node_put(np); return id; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index f3ff587a8b7d..c5d148434c08 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -469,11 +469,14 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, slb_v = vcpu->kvm->arch.vrma_slb_v; } + preempt_disable(); /* Find the HPTE in the hash table */ index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v, HPTE_V_VALID | HPTE_V_ABSENT); - if (index < 0) + if (index < 0) { + preempt_enable(); return -ENOENT; + } hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4)); v = hptep[0] & ~HPTE_V_HVLOCK; gr = kvm->arch.revmap[index].guest_rpte; @@ -481,6 +484,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, /* Unlock the HPTE */ asm volatile("lwsync" : : : "memory"); hptep[0] = v; + preempt_enable(); gpte->eaddr = eaddr; gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff); @@ -665,6 +669,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, return -EFAULT; } else { page = pages[0]; + pfn = page_to_pfn(page); if (PageHuge(page)) { page = compound_head(page); pte_size <<= compound_order(page); @@ -689,7 +694,6 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } rcu_read_unlock_sched(); } - pfn = page_to_pfn(page); } ret = -EFAULT; @@ -707,8 +711,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M; } - /* Set the HPTE to point to pfn */ - r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT); + /* + * Set the HPTE to point to pfn. + * Since the pfn is at PAGE_SIZE granularity, make sure we + * don't mask out lower-order bits if psize < PAGE_SIZE. + */ + if (psize < PAGE_SIZE) + psize = PAGE_SIZE; + r = (r & ~(HPTE_R_PP0 - psize)) | ((pfn << PAGE_SHIFT) & ~(psize - 1)); if (hpte_is_writable(r) && !write_ok) r = hpte_make_readonly(r); ret = RESUME_GUEST; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 072287f1c3bc..b51d5db78068 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -131,8 +131,9 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; + unsigned long flags; - spin_lock(&vcpu->arch.tbacct_lock); + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE && vc->preempt_tb != TB_NIL) { vc->stolen_tb += mftb() - vc->preempt_tb; @@ -143,19 +144,20 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt; vcpu->arch.busy_preempt = TB_NIL; } - spin_unlock(&vcpu->arch.tbacct_lock); + spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); } static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; + unsigned long flags; - spin_lock(&vcpu->arch.tbacct_lock); + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) vc->preempt_tb = mftb(); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) vcpu->arch.busy_preempt = mftb(); - spin_unlock(&vcpu->arch.tbacct_lock); + spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); } static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) @@ -486,11 +488,11 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) */ if (vc->vcore_state != VCORE_INACTIVE && vc->runner->arch.run_task != current) { - spin_lock(&vc->runner->arch.tbacct_lock); + spin_lock_irq(&vc->runner->arch.tbacct_lock); p = vc->stolen_tb; if (vc->preempt_tb != TB_NIL) p += now - vc->preempt_tb; - spin_unlock(&vc->runner->arch.tbacct_lock); + spin_unlock_irq(&vc->runner->arch.tbacct_lock); } else { p = vc->stolen_tb; } @@ -512,10 +514,10 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, core_stolen = vcore_stolen_time(vc, now); stolen = core_stolen - vcpu->arch.stolen_logged; vcpu->arch.stolen_logged = core_stolen; - spin_lock(&vcpu->arch.tbacct_lock); + spin_lock_irq(&vcpu->arch.tbacct_lock); stolen += vcpu->arch.busy_stolen; vcpu->arch.busy_stolen = 0; - spin_unlock(&vcpu->arch.tbacct_lock); + spin_unlock_irq(&vcpu->arch.tbacct_lock); if (!dt || !vpa) return; memset(dt, 0, sizeof(struct dtl_entry)); @@ -589,7 +591,9 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) if (list_empty(&vcpu->kvm->arch.rtas_tokens)) return RESUME_HOST; + idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvmppc_rtas_hcall(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); if (rc == -ENOENT) return RESUME_HOST; @@ -1115,13 +1119,13 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE) return; - spin_lock(&vcpu->arch.tbacct_lock); + spin_lock_irq(&vcpu->arch.tbacct_lock); now = mftb(); vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) - vcpu->arch.stolen_logged; vcpu->arch.busy_preempt = now; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; - spin_unlock(&vcpu->arch.tbacct_lock); + spin_unlock_irq(&vcpu->arch.tbacct_lock); --vc->n_runnable; list_del(&vcpu->arch.run_list); } diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 9c515440ad1a..8689e2e30857 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -225,6 +225,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, is_io = pa & (HPTE_R_I | HPTE_R_W); pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK); pa &= PAGE_MASK; + pa |= gpa & ~PAGE_MASK; } else { /* Translate to host virtual address */ hva = __gfn_to_hva_memslot(memslot, gfn); @@ -238,13 +239,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, ptel = hpte_make_readonly(ptel); is_io = hpte_cache_bits(pte_val(pte)); pa = pte_pfn(pte) << PAGE_SHIFT; + pa |= hva & (pte_size - 1); + pa |= gpa & ~PAGE_MASK; } } if (pte_size < psize) return H_PARAMETER; - if (pa && pte_size > psize) - pa |= gpa & (pte_size - 1); ptel &= ~(HPTE_R_PP0 - psize); ptel |= pa; @@ -749,6 +750,10 @@ static int slb_base_page_shift[4] = { 20, /* 1M, unsupported */ }; +/* When called from virtmode, this func should be protected by + * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK + * can trigger deadlock issue. + */ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, unsigned long valid) { diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index bc8de75b1925..be4fa04a37c9 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -153,7 +153,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) 13: b machine_check_fwnmi - /* * We come in here when wakened from nap mode on a secondary hw thread. * Relocation is off and most register values are lost. @@ -224,6 +223,11 @@ kvm_start_guest: /* Clear our vcpu pointer so we don't come back in early */ li r0, 0 std r0, HSTATE_KVM_VCPU(r13) + /* + * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing + * the nap_count, because once the increment to nap_count is + * visible we could be given another vcpu. + */ lwsync /* Clear any pending IPI - we're an offline thread */ ld r5, HSTATE_XICS_PHYS(r13) @@ -241,7 +245,6 @@ kvm_start_guest: /* increment the nap count and then go to nap mode */ ld r4, HSTATE_KVM_VCORE(r13) addi r4, r4, VCORE_NAP_COUNT - lwsync /* make previous updates visible */ 51: lwarx r3, 0, r4 addi r3, r3, 1 stwcx. r3, 0, r4 @@ -751,15 +754,14 @@ kvmppc_interrupt_hv: * guest CR, R12 saved in shadow VCPU SCRATCH1/0 * guest R13 saved in SPRN_SCRATCH0 */ - /* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */ - std r9, HSTATE_HOST_R2(r13) + std r9, HSTATE_SCRATCH2(r13) lbz r9, HSTATE_IN_GUEST(r13) cmpwi r9, KVM_GUEST_MODE_HOST_HV beq kvmppc_bad_host_intr #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE cmpwi r9, KVM_GUEST_MODE_GUEST - ld r9, HSTATE_HOST_R2(r13) + ld r9, HSTATE_SCRATCH2(r13) beq kvmppc_interrupt_pr #endif /* We're now back in the host but in guest MMU context */ @@ -779,7 +781,7 @@ kvmppc_interrupt_hv: std r6, VCPU_GPR(R6)(r9) std r7, VCPU_GPR(R7)(r9) std r8, VCPU_GPR(R8)(r9) - ld r0, HSTATE_HOST_R2(r13) + ld r0, HSTATE_SCRATCH2(r13) std r0, VCPU_GPR(R9)(r9) std r10, VCPU_GPR(R10)(r9) std r11, VCPU_GPR(R11)(r9) @@ -990,14 +992,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) */ /* Increment the threads-exiting-guest count in the 0xff00 bits of vcore->entry_exit_count */ - lwsync ld r5,HSTATE_KVM_VCORE(r13) addi r6,r5,VCORE_ENTRY_EXIT 41: lwarx r3,0,r6 addi r0,r3,0x100 stwcx. r0,0,r6 bne 41b - lwsync + isync /* order stwcx. vs. reading napping_threads */ /* * At this point we have an interrupt that we have to pass @@ -1030,6 +1031,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) sld r0,r0,r4 andc. r3,r3,r0 /* no sense IPI'ing ourselves */ beq 43f + /* Order entry/exit update vs. IPIs */ + sync mulli r4,r4,PACA_SIZE /* get paca for thread 0 */ subf r6,r4,r13 42: andi. r0,r3,1 @@ -1638,10 +1641,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) bge kvm_cede_exit stwcx. r4,0,r6 bne 31b + /* order napping_threads update vs testing entry_exit_count */ + isync li r0,1 stb r0,HSTATE_NAPPING(r13) - /* order napping_threads update vs testing entry_exit_count */ - lwsync mr r4,r3 lwz r7,VCORE_ENTRY_EXIT(r5) cmpwi r7,0x100 diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index f4dd041c14ea..f779450cb07c 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -129,29 +129,32 @@ kvm_start_lightweight: * R12 = exit handler id * R13 = PACA * SVCPU.* = guest * + * MSR.EE = 1 * */ + PPC_LL r3, GPR4(r1) /* vcpu pointer */ + + /* + * kvmppc_copy_from_svcpu can clobber volatile registers, save + * the exit handler id to the vcpu and restore it from there later. + */ + stw r12, VCPU_TRAP(r3) + /* Transfer reg values from shadow vcpu back to vcpu struct */ /* On 64-bit, interrupts are still off at this point */ - PPC_LL r3, GPR4(r1) /* vcpu pointer */ + GET_SHADOW_VCPU(r4) bl FUNC(kvmppc_copy_from_svcpu) nop #ifdef CONFIG_PPC_BOOK3S_64 - /* Re-enable interrupts */ - ld r3, HSTATE_HOST_MSR(r13) - ori r3, r3, MSR_EE - MTMSR_EERI(r3) - /* * Reload kernel SPRG3 value. * No need to save guest value as usermode can't modify SPRG3. */ ld r3, PACA_SPRG3(r13) mtspr SPRN_SPRG3, r3 - #endif /* CONFIG_PPC_BOOK3S_64 */ /* R7 = vcpu */ @@ -177,7 +180,7 @@ kvm_start_lightweight: PPC_STL r31, VCPU_GPR(R31)(r7) /* Pass the exit number as 3rd argument to kvmppc_handle_exit */ - mr r5, r12 + lwz r5, VCPU_TRAP(r7) /* Restore r3 (kvm_run) and r4 (vcpu) */ REST_2GPRS(3, r1) diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index fe14ca3dd171..5b9e9063cfaf 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -66,6 +66,7 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb)); svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max; + svcpu->in_use = 0; svcpu_put(svcpu); #endif vcpu->cpu = smp_processor_id(); @@ -78,6 +79,9 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) { #ifdef CONFIG_PPC_BOOK3S_64 struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); + if (svcpu->in_use) { + kvmppc_copy_from_svcpu(vcpu, svcpu); + } memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; svcpu_put(svcpu); @@ -110,12 +114,26 @@ void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, svcpu->ctr = vcpu->arch.ctr; svcpu->lr = vcpu->arch.lr; svcpu->pc = vcpu->arch.pc; + svcpu->in_use = true; } /* Copy data touched by real-mode code from shadow vcpu back to vcpu */ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, struct kvmppc_book3s_shadow_vcpu *svcpu) { + /* + * vcpu_put would just call us again because in_use hasn't + * been updated yet. + */ + preempt_disable(); + + /* + * Maybe we were already preempted and synced the svcpu from + * our preempt notifiers. Don't bother touching this svcpu then. + */ + if (!svcpu->in_use) + goto out; + vcpu->arch.gpr[0] = svcpu->gpr[0]; vcpu->arch.gpr[1] = svcpu->gpr[1]; vcpu->arch.gpr[2] = svcpu->gpr[2]; @@ -139,6 +157,10 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, vcpu->arch.fault_dar = svcpu->fault_dar; vcpu->arch.fault_dsisr = svcpu->fault_dsisr; vcpu->arch.last_inst = svcpu->last_inst; + svcpu->in_use = false; + +out: + preempt_enable(); } static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index a38c4c9edab8..c3c5231adade 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -153,15 +153,11 @@ _GLOBAL(kvmppc_entry_trampoline) li r6, MSR_IR | MSR_DR andc r6, r5, r6 /* Clear DR and IR in MSR value */ -#ifdef CONFIG_PPC_BOOK3S_32 /* * Set EE in HOST_MSR so that it's enabled when we get into our - * C exit handler function. On 64-bit we delay enabling - * interrupts until we have finished transferring stuff - * to or from the PACA. + * C exit handler function. */ ori r5, r5, MSR_EE -#endif mtsrr0 r7 mtsrr1 r6 RFI diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 53e65a210b9a..0591e05db74b 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -681,7 +681,7 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret, s; - struct thread_struct thread; + struct debug_reg debug; #ifdef CONFIG_PPC_FPU struct thread_fp_state fp; int fpexc_mode; @@ -723,9 +723,9 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) #endif /* Switch to guest debug context */ - thread.debug = vcpu->arch.shadow_dbg_reg; - switch_booke_debug_regs(&thread); - thread.debug = current->thread.debug; + debug = vcpu->arch.shadow_dbg_reg; + switch_booke_debug_regs(&debug); + debug = current->thread.debug; current->thread.debug = vcpu->arch.shadow_dbg_reg; kvmppc_fix_ee_before_entry(); @@ -736,8 +736,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) We also get here with interrupts enabled. */ /* Switch back to user space debug context */ - switch_booke_debug_regs(&thread); - current->thread.debug = thread.debug; + switch_booke_debug_regs(&debug); + current->thread.debug = debug; #ifdef CONFIG_PPC_FPU kvmppc_save_guest_fp(vcpu); diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c index e7e59e4f9892..79d83cad3d67 100644 --- a/arch/powerpc/platforms/powernv/opal-lpc.c +++ b/arch/powerpc/platforms/powernv/opal-lpc.c @@ -24,25 +24,25 @@ static int opal_lpc_chip_id = -1; static u8 opal_lpc_inb(unsigned long port) { int64_t rc; - uint32_t data; + __be32 data; if (opal_lpc_chip_id < 0 || port > 0xffff) return 0xff; rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 1); - return rc ? 0xff : data; + return rc ? 0xff : be32_to_cpu(data); } static __le16 __opal_lpc_inw(unsigned long port) { int64_t rc; - uint32_t data; + __be32 data; if (opal_lpc_chip_id < 0 || port > 0xfffe) return 0xffff; if (port & 1) return (__le16)opal_lpc_inb(port) << 8 | opal_lpc_inb(port + 1); rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 2); - return rc ? 0xffff : data; + return rc ? 0xffff : be32_to_cpu(data); } static u16 opal_lpc_inw(unsigned long port) { @@ -52,7 +52,7 @@ static u16 opal_lpc_inw(unsigned long port) static __le32 __opal_lpc_inl(unsigned long port) { int64_t rc; - uint32_t data; + __be32 data; if (opal_lpc_chip_id < 0 || port > 0xfffc) return 0xffffffff; @@ -62,7 +62,7 @@ static __le32 __opal_lpc_inl(unsigned long port) (__le32)opal_lpc_inb(port + 2) << 8 | opal_lpc_inb(port + 3); rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 4); - return rc ? 0xffffffff : data; + return rc ? 0xffffffff : be32_to_cpu(data); } static u32 opal_lpc_inl(unsigned long port) diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 4d99a8fd55ac..4fbf276ac99e 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -96,9 +96,11 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) { struct opal_scom_map *m = map; int64_t rc; + __be64 v; reg = opal_scom_unmangle(reg); - rc = opal_xscom_read(m->chip, m->addr + reg, (uint64_t *)__pa(value)); + rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v)); + *value = be64_to_cpu(v); return opal_xscom_err_xlate(rc); } diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index e738007eae64..c9fecf09b8fa 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -157,7 +157,7 @@ static void parse_ppp_data(struct seq_file *m) { struct hvcall_ppp_data ppp_data; struct device_node *root; - const int *perf_level; + const __be32 *perf_level; int rc; rc = h_get_ppp(&ppp_data); @@ -201,7 +201,7 @@ static void parse_ppp_data(struct seq_file *m) perf_level = of_get_property(root, "ibm,partition-performance-parameters-level", NULL); - if (perf_level && (*perf_level >= 1)) { + if (perf_level && (be32_to_cpup(perf_level) >= 1)) { seq_printf(m, "physical_procs_allocated_to_virtualization=%d\n", ppp_data.phys_platform_procs); @@ -435,7 +435,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) int partition_potential_processors; int partition_active_processors; struct device_node *rtas_node; - const int *lrdrp = NULL; + const __be32 *lrdrp = NULL; rtas_node = of_find_node_by_path("/rtas"); if (rtas_node) @@ -444,7 +444,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) if (lrdrp == NULL) { partition_potential_processors = vdso_data->processorCount; } else { - partition_potential_processors = *(lrdrp + 4); + partition_potential_processors = be32_to_cpup(lrdrp + 4); } of_node_put(rtas_node); @@ -654,7 +654,7 @@ static int lparcfg_data(struct seq_file *m, void *v) const char *model = ""; const char *system_id = ""; const char *tmp; - const unsigned int *lp_index_ptr; + const __be32 *lp_index_ptr; unsigned int lp_index = 0; seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS); @@ -670,7 +670,7 @@ static int lparcfg_data(struct seq_file *m, void *v) lp_index_ptr = of_get_property(rootdn, "ibm,partition-no", NULL); if (lp_index_ptr) - lp_index = *lp_index_ptr; + lp_index = be32_to_cpup(lp_index_ptr); of_node_put(rootdn); } seq_printf(m, "serial_number=%s\n", system_id); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 6d2f0abce6fa..0c882e83c4ce 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -130,7 +130,8 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) { struct device_node *dn; struct pci_dn *pdn; - const u32 *req_msi; + const __be32 *p; + u32 req_msi; pdn = pci_get_pdn(pdev); if (!pdn) @@ -138,19 +139,20 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) dn = pdn->node; - req_msi = of_get_property(dn, prop_name, NULL); - if (!req_msi) { + p = of_get_property(dn, prop_name, NULL); + if (!p) { pr_debug("rtas_msi: No %s on %s\n", prop_name, dn->full_name); return -ENOENT; } - if (*req_msi < nvec) { + req_msi = be32_to_cpup(p); + if (req_msi < nvec) { pr_debug("rtas_msi: %s requests < %d MSIs\n", prop_name, nvec); - if (*req_msi == 0) /* Be paranoid */ + if (req_msi == 0) /* Be paranoid */ return -ENOSPC; - return *req_msi; + return req_msi; } return 0; @@ -171,7 +173,7 @@ static int check_req_msix(struct pci_dev *pdev, int nvec) static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) { struct device_node *dn; - const u32 *p; + const __be32 *p; dn = of_node_get(pci_device_to_OF_node(dev)); while (dn) { @@ -179,7 +181,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) if (p) { pr_debug("rtas_msi: found prop on dn %s\n", dn->full_name); - *total = *p; + *total = be32_to_cpup(p); return dn; } @@ -232,13 +234,13 @@ struct msi_counts { static void *count_non_bridge_devices(struct device_node *dn, void *data) { struct msi_counts *counts = data; - const u32 *p; + const __be32 *p; u32 class; pr_debug("rtas_msi: counting %s\n", dn->full_name); p = of_get_property(dn, "class-code", NULL); - class = p ? *p : 0; + class = p ? be32_to_cpup(p) : 0; if ((class >> 8) != PCI_CLASS_BRIDGE_PCI) counts->num_devices++; @@ -249,7 +251,7 @@ static void *count_non_bridge_devices(struct device_node *dn, void *data) static void *count_spare_msis(struct device_node *dn, void *data) { struct msi_counts *counts = data; - const u32 *p; + const __be32 *p; int req; if (dn == counts->requestor) @@ -260,11 +262,11 @@ static void *count_spare_msis(struct device_node *dn, void *data) req = 0; p = of_get_property(dn, "ibm,req#msi", NULL); if (p) - req = *p; + req = be32_to_cpup(p); p = of_get_property(dn, "ibm,req#msi-x", NULL); if (p) - req = max(req, (int)*p); + req = max(req, (int)be32_to_cpup(p)); } if (req < counts->quota) diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 7bfaf58d4664..d7096f2f7751 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -43,8 +43,8 @@ static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); struct err_log_info { - int error_type; - unsigned int seq_num; + __be32 error_type; + __be32 seq_num; }; struct nvram_os_partition { @@ -79,9 +79,9 @@ static const char *pseries_nvram_os_partitions[] = { }; struct oops_log_info { - u16 version; - u16 report_length; - u64 timestamp; + __be16 version; + __be16 report_length; + __be64 timestamp; } __attribute__((packed)); static void oops_to_nvram(struct kmsg_dumper *dumper, @@ -291,8 +291,8 @@ int nvram_write_os_partition(struct nvram_os_partition *part, char * buff, length = part->size; } - info.error_type = err_type; - info.seq_num = error_log_cnt; + info.error_type = cpu_to_be32(err_type); + info.seq_num = cpu_to_be32(error_log_cnt); tmp_index = part->index; @@ -364,8 +364,8 @@ int nvram_read_partition(struct nvram_os_partition *part, char *buff, } if (part->os_partition) { - *error_log_cnt = info.seq_num; - *err_type = info.error_type; + *error_log_cnt = be32_to_cpu(info.seq_num); + *err_type = be32_to_cpu(info.error_type); } return 0; @@ -529,9 +529,9 @@ static int zip_oops(size_t text_len) pr_err("nvram: logging uncompressed oops/panic report\n"); return -1; } - oops_hdr->version = OOPS_HDR_VERSION; - oops_hdr->report_length = (u16) zipped_len; - oops_hdr->timestamp = get_seconds(); + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(zipped_len); + oops_hdr->timestamp = cpu_to_be64(get_seconds()); return 0; } @@ -574,9 +574,9 @@ static int nvram_pstore_write(enum pstore_type_id type, clobbering_unread_rtas_event()) return -1; - oops_hdr->version = OOPS_HDR_VERSION; - oops_hdr->report_length = (u16) size; - oops_hdr->timestamp = get_seconds(); + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(size); + oops_hdr->timestamp = cpu_to_be64(get_seconds()); if (compressed) err_type = ERR_TYPE_KERNEL_PANIC_GZ; @@ -670,16 +670,16 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, size_t length, hdr_size; oops_hdr = (struct oops_log_info *)buff; - if (oops_hdr->version < OOPS_HDR_VERSION) { + if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) { /* Old format oops header had 2-byte record size */ hdr_size = sizeof(u16); - length = oops_hdr->version; + length = be16_to_cpu(oops_hdr->version); time->tv_sec = 0; time->tv_nsec = 0; } else { hdr_size = sizeof(*oops_hdr); - length = oops_hdr->report_length; - time->tv_sec = oops_hdr->timestamp; + length = be16_to_cpu(oops_hdr->report_length); + time->tv_sec = be64_to_cpu(oops_hdr->timestamp); time->tv_nsec = 0; } *buf = kmalloc(length, GFP_KERNEL); @@ -889,13 +889,13 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, kmsg_dump_get_buffer(dumper, false, oops_data, oops_data_sz, &text_len); err_type = ERR_TYPE_KERNEL_PANIC; - oops_hdr->version = OOPS_HDR_VERSION; - oops_hdr->report_length = (u16) text_len; - oops_hdr->timestamp = get_seconds(); + oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); + oops_hdr->report_length = cpu_to_be16(text_len); + oops_hdr->timestamp = cpu_to_be64(get_seconds()); } (void) nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type, + (int) (sizeof(*oops_hdr) + text_len), err_type, ++oops_count); spin_unlock_irqrestore(&lock, flags); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 5f93856cdf47..70670a2d9cf2 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -113,7 +113,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) { struct device_node *dn, *pdn; struct pci_bus *bus; - const uint32_t *pcie_link_speed_stats; + const __be32 *pcie_link_speed_stats; bus = bridge->bus; @@ -122,7 +122,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) return 0; for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) { - pcie_link_speed_stats = (const uint32_t *) of_get_property(pdn, + pcie_link_speed_stats = of_get_property(pdn, "ibm,pcie-link-speed-stats", NULL); if (pcie_link_speed_stats) break; @@ -135,7 +135,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) return 0; } - switch (pcie_link_speed_stats[0]) { + switch (be32_to_cpup(pcie_link_speed_stats)) { case 0x01: bus->max_bus_speed = PCIE_SPEED_2_5GT; break; @@ -147,7 +147,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) break; } - switch (pcie_link_speed_stats[1]) { + switch (be32_to_cpup(pcie_link_speed_stats)) { case 0x01: bus->cur_bus_speed = PCIE_SPEED_2_5GT; break; diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile index 7b95f29e3174..3baff31e58cf 100644 --- a/arch/sh/lib/Makefile +++ b/arch/sh/lib/Makefile @@ -6,7 +6,7 @@ lib-y = delay.o memmove.o memchr.o \ checksum.o strlen.o div64.o div64-generic.o # Extracted from libgcc -lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \ +obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \ ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \ udiv_qrnnd.o diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 8358dc144959..0f9e94537eee 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -619,7 +619,7 @@ static inline unsigned long pte_present(pte_t pte) } #define pte_accessible pte_accessible -static inline unsigned long pte_accessible(pte_t a) +static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) { return pte_val(a) & _PAGE_VALID; } @@ -847,7 +847,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U * and SUN4V pte layout, so this inline test is fine. */ - if (likely(mm != &init_mm) && pte_accessible(orig)) + if (likely(mm != &init_mm) && pte_accessible(mm, orig)) tlb_batch_add(mm, addr, ptep, orig, fullmm); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e903c71f7e69..0952ecd60eca 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -26,6 +26,7 @@ config X86 select HAVE_AOUT if X86_32 select HAVE_UNSTABLE_SCHED_CLOCK select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_INT128 if X86_64 select ARCH_WANTS_PROT_NUMA_PROT_NONE select HAVE_IDE select HAVE_OPROFILE diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 3d1999458709..bbc8b12fa443 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -452,9 +452,16 @@ static inline int pte_present(pte_t a) } #define pte_accessible pte_accessible -static inline int pte_accessible(pte_t a) +static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { - return pte_flags(a) & _PAGE_PRESENT; + if (pte_flags(a) & _PAGE_PRESENT) + return true; + + if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) && + mm_tlb_flush_pending(mm)) + return true; + + return false; } static inline int pte_hidden(pte_t pte) diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 8729723636fd..c8b051933b1b 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -8,6 +8,12 @@ DECLARE_PER_CPU(int, __preempt_count); /* + * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such + * that a decrement hitting 0 means we can and should reschedule. + */ +#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) + +/* * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users * that think a non-zero value indicates we cannot preempt. */ @@ -74,6 +80,11 @@ static __always_inline void __preempt_count_sub(int val) __this_cpu_add_4(__preempt_count, -val); } +/* + * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ static __always_inline bool __preempt_count_dec_and_test(void) { GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e"); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index fd00bb29425d..c1a861829d81 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -262,11 +262,20 @@ struct cpu_hw_events { __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) -#define EVENT_CONSTRAINT_END \ - EVENT_CONSTRAINT(0, 0, 0) +/* + * We define the end marker as having a weight of -1 + * to enable blacklisting of events using a counter bitmask + * of zero and thus a weight of zero. + * The end marker has a weight that cannot possibly be + * obtained from counting the bits in the bitmask. + */ +#define EVENT_CONSTRAINT_END { .weight = -1 } +/* + * Check for end marker with weight == -1 + */ #define for_each_event_constraint(e, c) \ - for ((e) = (c); (e)->weight; (e)++) + for ((e) = (c); (e)->weight != -1; (e)++) /* * Extra registers for specific events. diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index dd74e46828c0..0596e8e0cc19 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -83,6 +83,12 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, pte_t pte = gup_get_pte(ptep); struct page *page; + /* Similar to the PMD case, NUMA hinting must take slow path */ + if (pte_numa(pte)) { + pte_unmap(ptep); + return 0; + } + if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { pte_unmap(ptep); return 0; @@ -167,6 +173,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, if (pmd_none(pmd) || pmd_trans_splitting(pmd)) return 0; if (unlikely(pmd_large(pmd))) { + /* + * NUMA hinting faults need to be handled in the GUP + * slowpath for accounting purposes and so that they + * can be serialised against THP migration. + */ + if (pmd_numa(pmd)) + return 0; if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) return 0; } else { diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 26311f23c824..cb1d557fc22c 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -942,6 +942,7 @@ static int erst_clearer(enum pstore_type_id type, u64 id, int count, static struct pstore_info erst_info = { .owner = THIS_MODULE, .name = "erst", + .flags = PSTORE_FLAGS_FRAGILE, .open = erst_open_pstore, .close = erst_close_pstore, .read = erst_reader, diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c index 7be41e676a64..00a3abe103a5 100644 --- a/drivers/clk/clk-s2mps11.c +++ b/drivers/clk/clk-s2mps11.c @@ -60,7 +60,7 @@ static int s2mps11_clk_prepare(struct clk_hw *hw) struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw); int ret; - ret = regmap_update_bits(s2mps11->iodev->regmap, + ret = regmap_update_bits(s2mps11->iodev->regmap_pmic, S2MPS11_REG_RTC_CTRL, s2mps11->mask, s2mps11->mask); if (!ret) @@ -74,7 +74,7 @@ static void s2mps11_clk_unprepare(struct clk_hw *hw) struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw); int ret; - ret = regmap_update_bits(s2mps11->iodev->regmap, S2MPS11_REG_RTC_CTRL, + ret = regmap_update_bits(s2mps11->iodev->regmap_pmic, S2MPS11_REG_RTC_CTRL, s2mps11->mask, ~s2mps11->mask); if (!ret) @@ -174,7 +174,7 @@ static int s2mps11_clk_probe(struct platform_device *pdev) s2mps11_clk->hw.init = &s2mps11_clks_init[i]; s2mps11_clk->mask = 1 << i; - ret = regmap_read(s2mps11_clk->iodev->regmap, + ret = regmap_read(s2mps11_clk->iodev->regmap_pmic, S2MPS11_REG_RTC_CTRL, &val); if (ret < 0) goto err_reg; diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 5c07a56962db..634c4d6dd45a 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -75,6 +75,7 @@ config CLKSRC_DBX500_PRCMU_SCHED_CLOCK config CLKSRC_EFM32 bool "Clocksource for Energy Micro's EFM32 SoCs" if !ARCH_EFM32 depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST) + select CLKSRC_MMIO default ARCH_EFM32 help Support to use the timers of EFM32 SoCs as clock source and clock diff --git a/drivers/clocksource/clksrc-of.c b/drivers/clocksource/clksrc-of.c index 35639cf4e5a2..b9ddd9e3a2f5 100644 --- a/drivers/clocksource/clksrc-of.c +++ b/drivers/clocksource/clksrc-of.c @@ -35,6 +35,5 @@ void __init clocksource_of_init(void) init_func = match->data; init_func(np); - of_node_put(np); } } diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c index 45ba8aecc729..2a2ea2717f3a 100644 --- a/drivers/clocksource/dw_apb_timer_of.c +++ b/drivers/clocksource/dw_apb_timer_of.c @@ -108,12 +108,11 @@ static void __init add_clocksource(struct device_node *source_timer) static u64 read_sched_clock(void) { - return __raw_readl(sched_io_base); + return ~__raw_readl(sched_io_base); } static const struct of_device_id sptimer_ids[] __initconst = { { .compatible = "picochip,pc3x2-rtc" }, - { .compatible = "snps,dw-apb-timer-sp" }, { /* Sentinel */ }, }; @@ -151,4 +150,6 @@ static void __init dw_apb_timer_init(struct device_node *timer) num_called++; } CLOCKSOURCE_OF_DECLARE(pc3x2_timer, "picochip,pc3x2-timer", dw_apb_timer_init); -CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer-osc", dw_apb_timer_init); +CLOCKSOURCE_OF_DECLARE(apb_timer_osc, "snps,dw-apb-timer-osc", dw_apb_timer_init); +CLOCKSOURCE_OF_DECLARE(apb_timer_sp, "snps,dw-apb-timer-sp", dw_apb_timer_init); +CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer", dw_apb_timer_init); diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c index 2fb4695a28d8..a4f6119aafd8 100644 --- a/drivers/clocksource/sun4i_timer.c +++ b/drivers/clocksource/sun4i_timer.c @@ -179,6 +179,9 @@ static void __init sun4i_timer_init(struct device_node *node) writel(TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M), timer_base + TIMER_CTL_REG(0)); + /* Make sure timer is stopped before playing with interrupts */ + sun4i_clkevt_time_stop(0); + ret = setup_irq(irq, &sun4i_timer_irq); if (ret) pr_warn("failed to setup irq %d\n", irq); diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c index d8e47e502785..4e7f6802e840 100644 --- a/drivers/clocksource/time-armada-370-xp.c +++ b/drivers/clocksource/time-armada-370-xp.c @@ -256,11 +256,6 @@ static void __init armada_370_xp_timer_common_init(struct device_node *np) ticks_per_jiffy = (timer_clk + HZ / 2) / HZ; /* - * Set scale and timer for sched_clock. - */ - sched_clock_register(armada_370_xp_read_sched_clock, 32, timer_clk); - - /* * Setup free-running clocksource timer (interrupts * disabled). */ @@ -270,6 +265,11 @@ static void __init armada_370_xp_timer_common_init(struct device_node *np) timer_ctrl_clrset(0, TIMER0_EN | TIMER0_RELOAD_EN | TIMER0_DIV(TIMER_DIVIDER_SHIFT)); + /* + * Set scale and timer for sched_clock. + */ + sched_clock_register(armada_370_xp_read_sched_clock, 32, timer_clk); + clocksource_mmio_init(timer_base + TIMER0_VAL_OFF, "armada_370_xp_clocksource", timer_clk, 300, 32, clocksource_mmio_readl_down); diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 446687cc2334..c823daaf9043 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -62,6 +62,7 @@ config INTEL_IOATDMA tristate "Intel I/OAT DMA support" depends on PCI && X86 select DMA_ENGINE + select DMA_ENGINE_RAID select DCA help Enable support for the Intel(R) I/OAT DMA engine present @@ -112,6 +113,7 @@ config MV_XOR bool "Marvell XOR engine support" depends on PLAT_ORION select DMA_ENGINE + select DMA_ENGINE_RAID select ASYNC_TX_ENABLE_CHANNEL_SWITCH ---help--- Enable support for the Marvell XOR engine. @@ -187,6 +189,7 @@ config AMCC_PPC440SPE_ADMA tristate "AMCC PPC440SPe ADMA support" depends on 440SPe || 440SP select DMA_ENGINE + select DMA_ENGINE_RAID select ARCH_HAS_ASYNC_TX_FIND_CHANNEL select ASYNC_TX_ENABLE_CHANNEL_SWITCH help @@ -352,6 +355,7 @@ config NET_DMA bool "Network: TCP receive copy offload" depends on DMA_ENGINE && NET default (INTEL_IOATDMA || FSL_DMA) + depends on BROKEN help This enables the use of DMA engines in the network stack to offload receive copy-to-user operations, freeing CPU cycles. @@ -377,4 +381,7 @@ config DMATEST Simple DMA test client. Say N unless you're debugging a DMA Device driver. +config DMA_ENGINE_RAID + bool + endif diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h index f31d647acdfa..2787aba60c6b 100644 --- a/drivers/dma/at_hdmac_regs.h +++ b/drivers/dma/at_hdmac_regs.h @@ -347,10 +347,6 @@ static struct device *chan2dev(struct dma_chan *chan) { return &chan->dev->device; } -static struct device *chan2parent(struct dma_chan *chan) -{ - return chan->dev->device.parent; -} #if defined(VERBOSE_DEBUG) static void vdbg_dump_regs(struct at_dma_chan *atchan) diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index ea806bdc12ef..ef63b9058f3c 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -912,7 +912,7 @@ struct dmaengine_unmap_pool { #define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) } static struct dmaengine_unmap_pool unmap_pool[] = { __UNMAP_POOL(2), - #if IS_ENABLED(CONFIG_ASYNC_TX_DMA) + #if IS_ENABLED(CONFIG_DMA_ENGINE_RAID) __UNMAP_POOL(16), __UNMAP_POOL(128), __UNMAP_POOL(256), @@ -1054,7 +1054,7 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg, dma_cookie_t cookie; unsigned long flags; - unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOIO); + unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOWAIT); if (!unmap) return -ENOMEM; diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 20f9a3aaf926..9dfcaf5c1288 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -539,9 +539,9 @@ static int dmatest_func(void *data) um->len = params->buf_size; for (i = 0; i < src_cnt; i++) { - unsigned long buf = (unsigned long) thread->srcs[i]; + void *buf = thread->srcs[i]; struct page *pg = virt_to_page(buf); - unsigned pg_off = buf & ~PAGE_MASK; + unsigned pg_off = (unsigned long) buf & ~PAGE_MASK; um->addr[i] = dma_map_page(dev->dev, pg, pg_off, um->len, DMA_TO_DEVICE); @@ -559,9 +559,9 @@ static int dmatest_func(void *data) /* map with DMA_BIDIRECTIONAL to force writeback/invalidate */ dsts = &um->addr[src_cnt]; for (i = 0; i < dst_cnt; i++) { - unsigned long buf = (unsigned long) thread->dsts[i]; + void *buf = thread->dsts[i]; struct page *pg = virt_to_page(buf); - unsigned pg_off = buf & ~PAGE_MASK; + unsigned pg_off = (unsigned long) buf & ~PAGE_MASK; dsts[i] = dma_map_page(dev->dev, pg, pg_off, um->len, DMA_BIDIRECTIONAL); diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 7086a16a55f2..f157c6f76b32 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -86,11 +86,6 @@ static void set_desc_cnt(struct fsldma_chan *chan, hw->count = CPU_TO_DMA(chan, count, 32); } -static u32 get_desc_cnt(struct fsldma_chan *chan, struct fsl_desc_sw *desc) -{ - return DMA_TO_CPU(chan, desc->hw.count, 32); -} - static void set_desc_src(struct fsldma_chan *chan, struct fsl_dma_ld_hw *hw, dma_addr_t src) { @@ -101,16 +96,6 @@ static void set_desc_src(struct fsldma_chan *chan, hw->src_addr = CPU_TO_DMA(chan, snoop_bits | src, 64); } -static dma_addr_t get_desc_src(struct fsldma_chan *chan, - struct fsl_desc_sw *desc) -{ - u64 snoop_bits; - - snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) - ? ((u64)FSL_DMA_SATR_SREADTYPE_SNOOP_READ << 32) : 0; - return DMA_TO_CPU(chan, desc->hw.src_addr, 64) & ~snoop_bits; -} - static void set_desc_dst(struct fsldma_chan *chan, struct fsl_dma_ld_hw *hw, dma_addr_t dst) { @@ -121,16 +106,6 @@ static void set_desc_dst(struct fsldma_chan *chan, hw->dst_addr = CPU_TO_DMA(chan, snoop_bits | dst, 64); } -static dma_addr_t get_desc_dst(struct fsldma_chan *chan, - struct fsl_desc_sw *desc) -{ - u64 snoop_bits; - - snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) - ? ((u64)FSL_DMA_DATR_DWRITETYPE_SNOOP_WRITE << 32) : 0; - return DMA_TO_CPU(chan, desc->hw.dst_addr, 64) & ~snoop_bits; -} - static void set_desc_next(struct fsldma_chan *chan, struct fsl_dma_ld_hw *hw, dma_addr_t next) { @@ -408,7 +383,7 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx) struct fsl_desc_sw *desc = tx_to_fsl_desc(tx); struct fsl_desc_sw *child; unsigned long flags; - dma_cookie_t cookie; + dma_cookie_t cookie = -EINVAL; spin_lock_irqsave(&chan->desc_lock, flags); @@ -854,10 +829,6 @@ static void fsldma_cleanup_descriptor(struct fsldma_chan *chan, struct fsl_desc_sw *desc) { struct dma_async_tx_descriptor *txd = &desc->async_tx; - struct device *dev = chan->common.device->dev; - dma_addr_t src = get_desc_src(chan, desc); - dma_addr_t dst = get_desc_dst(chan, desc); - u32 len = get_desc_cnt(chan, desc); /* Run the link descriptor callback function */ if (txd->callback) { diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 7807f0ef4e20..53fb0c8365b0 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -54,12 +54,6 @@ static void mv_desc_init(struct mv_xor_desc_slot *desc, unsigned long flags) hw_desc->desc_command = (1 << 31); } -static u32 mv_desc_get_dest_addr(struct mv_xor_desc_slot *desc) -{ - struct mv_xor_desc *hw_desc = desc->hw_desc; - return hw_desc->phy_dest_addr; -} - static void mv_desc_set_byte_count(struct mv_xor_desc_slot *desc, u32 byte_count) { @@ -787,7 +781,6 @@ static void mv_xor_issue_pending(struct dma_chan *chan) /* * Perform a transaction to verify the HW works. */ -#define MV_XOR_TEST_SIZE 2000 static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan) { @@ -797,20 +790,21 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan) struct dma_chan *dma_chan; dma_cookie_t cookie; struct dma_async_tx_descriptor *tx; + struct dmaengine_unmap_data *unmap; int err = 0; - src = kmalloc(sizeof(u8) * MV_XOR_TEST_SIZE, GFP_KERNEL); + src = kmalloc(sizeof(u8) * PAGE_SIZE, GFP_KERNEL); if (!src) return -ENOMEM; - dest = kzalloc(sizeof(u8) * MV_XOR_TEST_SIZE, GFP_KERNEL); + dest = kzalloc(sizeof(u8) * PAGE_SIZE, GFP_KERNEL); if (!dest) { kfree(src); return -ENOMEM; } /* Fill in src buffer */ - for (i = 0; i < MV_XOR_TEST_SIZE; i++) + for (i = 0; i < PAGE_SIZE; i++) ((u8 *) src)[i] = (u8)i; dma_chan = &mv_chan->dmachan; @@ -819,14 +813,26 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan) goto out; } - dest_dma = dma_map_single(dma_chan->device->dev, dest, - MV_XOR_TEST_SIZE, DMA_FROM_DEVICE); + unmap = dmaengine_get_unmap_data(dma_chan->device->dev, 2, GFP_KERNEL); + if (!unmap) { + err = -ENOMEM; + goto free_resources; + } + + src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), 0, + PAGE_SIZE, DMA_TO_DEVICE); + unmap->to_cnt = 1; + unmap->addr[0] = src_dma; - src_dma = dma_map_single(dma_chan->device->dev, src, - MV_XOR_TEST_SIZE, DMA_TO_DEVICE); + dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), 0, + PAGE_SIZE, DMA_FROM_DEVICE); + unmap->from_cnt = 1; + unmap->addr[1] = dest_dma; + + unmap->len = PAGE_SIZE; tx = mv_xor_prep_dma_memcpy(dma_chan, dest_dma, src_dma, - MV_XOR_TEST_SIZE, 0); + PAGE_SIZE, 0); cookie = mv_xor_tx_submit(tx); mv_xor_issue_pending(dma_chan); async_tx_ack(tx); @@ -841,8 +847,8 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan) } dma_sync_single_for_cpu(dma_chan->device->dev, dest_dma, - MV_XOR_TEST_SIZE, DMA_FROM_DEVICE); - if (memcmp(src, dest, MV_XOR_TEST_SIZE)) { + PAGE_SIZE, DMA_FROM_DEVICE); + if (memcmp(src, dest, PAGE_SIZE)) { dev_err(dma_chan->device->dev, "Self-test copy failed compare, disabling\n"); err = -ENODEV; @@ -850,6 +856,7 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan) } free_resources: + dmaengine_unmap_put(unmap); mv_xor_free_chan_resources(dma_chan); out: kfree(src); @@ -867,13 +874,15 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan) dma_addr_t dma_srcs[MV_XOR_NUM_SRC_TEST]; dma_addr_t dest_dma; struct dma_async_tx_descriptor *tx; + struct dmaengine_unmap_data *unmap; struct dma_chan *dma_chan; dma_cookie_t cookie; u8 cmp_byte = 0; u32 cmp_word; int err = 0; + int src_count = MV_XOR_NUM_SRC_TEST; - for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) { + for (src_idx = 0; src_idx < src_count; src_idx++) { xor_srcs[src_idx] = alloc_page(GFP_KERNEL); if (!xor_srcs[src_idx]) { while (src_idx--) @@ -890,13 +899,13 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan) } /* Fill in src buffers */ - for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) { + for (src_idx = 0; src_idx < src_count; src_idx++) { u8 *ptr = page_address(xor_srcs[src_idx]); for (i = 0; i < PAGE_SIZE; i++) ptr[i] = (1 << src_idx); } - for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) + for (src_idx = 0; src_idx < src_count; src_idx++) cmp_byte ^= (u8) (1 << src_idx); cmp_word = (cmp_byte << 24) | (cmp_byte << 16) | @@ -910,16 +919,29 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan) goto out; } + unmap = dmaengine_get_unmap_data(dma_chan->device->dev, src_count + 1, + GFP_KERNEL); + if (!unmap) { + err = -ENOMEM; + goto free_resources; + } + /* test xor */ - dest_dma = dma_map_page(dma_chan->device->dev, dest, 0, PAGE_SIZE, - DMA_FROM_DEVICE); + for (i = 0; i < src_count; i++) { + unmap->addr[i] = dma_map_page(dma_chan->device->dev, xor_srcs[i], + 0, PAGE_SIZE, DMA_TO_DEVICE); + dma_srcs[i] = unmap->addr[i]; + unmap->to_cnt++; + } - for (i = 0; i < MV_XOR_NUM_SRC_TEST; i++) - dma_srcs[i] = dma_map_page(dma_chan->device->dev, xor_srcs[i], - 0, PAGE_SIZE, DMA_TO_DEVICE); + unmap->addr[src_count] = dma_map_page(dma_chan->device->dev, dest, 0, PAGE_SIZE, + DMA_FROM_DEVICE); + dest_dma = unmap->addr[src_count]; + unmap->from_cnt = 1; + unmap->len = PAGE_SIZE; tx = mv_xor_prep_dma_xor(dma_chan, dest_dma, dma_srcs, - MV_XOR_NUM_SRC_TEST, PAGE_SIZE, 0); + src_count, PAGE_SIZE, 0); cookie = mv_xor_tx_submit(tx); mv_xor_issue_pending(dma_chan); @@ -948,9 +970,10 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan) } free_resources: + dmaengine_unmap_put(unmap); mv_xor_free_chan_resources(dma_chan); out: - src_idx = MV_XOR_NUM_SRC_TEST; + src_idx = src_count; while (src_idx--) __free_page(xor_srcs[src_idx]); __free_page(dest); @@ -1176,6 +1199,7 @@ static int mv_xor_probe(struct platform_device *pdev) int i = 0; for_each_child_of_node(pdev->dev.of_node, np) { + struct mv_xor_chan *chan; dma_cap_mask_t cap_mask; int irq; @@ -1193,21 +1217,21 @@ static int mv_xor_probe(struct platform_device *pdev) goto err_channel_add; } - xordev->channels[i] = - mv_xor_channel_add(xordev, pdev, i, - cap_mask, irq); - if (IS_ERR(xordev->channels[i])) { - ret = PTR_ERR(xordev->channels[i]); - xordev->channels[i] = NULL; + chan = mv_xor_channel_add(xordev, pdev, i, + cap_mask, irq); + if (IS_ERR(chan)) { + ret = PTR_ERR(chan); irq_dispose_mapping(irq); goto err_channel_add; } + xordev->channels[i] = chan; i++; } } else if (pdata && pdata->channels) { for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) { struct mv_xor_channel_data *cd; + struct mv_xor_chan *chan; int irq; cd = &pdata->channels[i]; @@ -1222,13 +1246,14 @@ static int mv_xor_probe(struct platform_device *pdev) goto err_channel_add; } - xordev->channels[i] = - mv_xor_channel_add(xordev, pdev, i, - cd->cap_mask, irq); - if (IS_ERR(xordev->channels[i])) { - ret = PTR_ERR(xordev->channels[i]); + chan = mv_xor_channel_add(xordev, pdev, i, + cd->cap_mask, irq); + if (IS_ERR(chan)) { + ret = PTR_ERR(chan); goto err_channel_add; } + + xordev->channels[i] = chan; } } diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index cdf0483b8f2d..536632f6479c 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2492,12 +2492,9 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx) static inline void _init_desc(struct dma_pl330_desc *desc) { - desc->pchan = NULL; desc->req.x = &desc->px; desc->req.token = desc; desc->rqcfg.swap = SWAP_NO; - desc->rqcfg.privileged = 0; - desc->rqcfg.insnaccess = 0; desc->rqcfg.scctl = SCCTRL0; desc->rqcfg.dcctl = DCCTRL0; desc->req.cfg = &desc->rqcfg; @@ -2517,7 +2514,7 @@ static int add_desc(struct dma_pl330_dmac *pdmac, gfp_t flg, int count) if (!pdmac) return 0; - desc = kmalloc(count * sizeof(*desc), flg); + desc = kcalloc(count, sizeof(*desc), flg); if (!desc) return 0; diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c index 8da48c6b2a38..8bba298535b0 100644 --- a/drivers/dma/ppc4xx/adma.c +++ b/drivers/dma/ppc4xx/adma.c @@ -533,29 +533,6 @@ static void ppc440spe_desc_init_memcpy(struct ppc440spe_adma_desc_slot *desc, } /** - * ppc440spe_desc_init_memset - initialize the descriptor for MEMSET operation - */ -static void ppc440spe_desc_init_memset(struct ppc440spe_adma_desc_slot *desc, - int value, unsigned long flags) -{ - struct dma_cdb *hw_desc = desc->hw_desc; - - memset(desc->hw_desc, 0, sizeof(struct dma_cdb)); - desc->hw_next = NULL; - desc->src_cnt = 1; - desc->dst_cnt = 1; - - if (flags & DMA_PREP_INTERRUPT) - set_bit(PPC440SPE_DESC_INT, &desc->flags); - else - clear_bit(PPC440SPE_DESC_INT, &desc->flags); - - hw_desc->sg1u = hw_desc->sg1l = cpu_to_le32((u32)value); - hw_desc->sg3u = hw_desc->sg3l = cpu_to_le32((u32)value); - hw_desc->opc = DMA_CDB_OPC_DFILL128; -} - -/** * ppc440spe_desc_set_src_addr - set source address into the descriptor */ static void ppc440spe_desc_set_src_addr(struct ppc440spe_adma_desc_slot *desc, @@ -1504,8 +1481,6 @@ static dma_cookie_t ppc440spe_adma_run_tx_complete_actions( struct ppc440spe_adma_chan *chan, dma_cookie_t cookie) { - int i; - BUG_ON(desc->async_tx.cookie < 0); if (desc->async_tx.cookie > 0) { cookie = desc->async_tx.cookie; @@ -3898,7 +3873,7 @@ static void ppc440spe_adma_init_capabilities(struct ppc440spe_adma_device *adev) ppc440spe_adma_prep_dma_interrupt; } pr_info("%s: AMCC(R) PPC440SP(E) ADMA Engine: " - "( %s%s%s%s%s%s%s)\n", + "( %s%s%s%s%s%s)\n", dev_name(adev->dev), dma_has_cap(DMA_PQ, adev->common.cap_mask) ? "pq " : "", dma_has_cap(DMA_PQ_VAL, adev->common.cap_mask) ? "pq_val " : "", diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c index bae6c29f5502..17686caf64d5 100644 --- a/drivers/dma/txx9dmac.c +++ b/drivers/dma/txx9dmac.c @@ -406,7 +406,6 @@ txx9dmac_descriptor_complete(struct txx9dmac_chan *dc, dma_async_tx_callback callback; void *param; struct dma_async_tx_descriptor *txd = &desc->txd; - struct txx9dmac_slave *ds = dc->chan.private; dev_vdbg(chan2dev(&dc->chan), "descriptor %u %p complete\n", txd->cookie, desc); diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index b0bb056458a3..281029daf98c 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -1623,7 +1623,6 @@ static struct scsi_host_template scsi_driver_template = { .cmd_per_lun = 1, .can_queue = 1, .sdev_attrs = sbp2_scsi_sysfs_attrs, - .no_write_same = 1, }; MODULE_AUTHOR("Kristian Hoegsberg <krh@bitplanet.net>"); diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index 743fd426f21b..4b9dc836dcf9 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -356,6 +356,7 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, static struct pstore_info efi_pstore_info = { .owner = THIS_MODULE, .name = "efi", + .flags = PSTORE_FLAGS_FRAGILE, .open = efi_pstore_open, .close = efi_pstore_close, .read = efi_pstore_read, diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c index 7b37300973db..2baf0ddf7e02 100644 --- a/drivers/gpio/gpio-msm-v2.c +++ b/drivers/gpio/gpio-msm-v2.c @@ -252,7 +252,7 @@ static void msm_gpio_irq_mask(struct irq_data *d) spin_lock_irqsave(&tlmm_lock, irq_flags); writel(TARGET_PROC_NONE, GPIO_INTR_CFG_SU(gpio)); - clear_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio)); + clear_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio)); __clear_bit(gpio, msm_gpio.enabled_irqs); spin_unlock_irqrestore(&tlmm_lock, irq_flags); } @@ -264,7 +264,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d) spin_lock_irqsave(&tlmm_lock, irq_flags); __set_bit(gpio, msm_gpio.enabled_irqs); - set_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio)); + set_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio)); writel(TARGET_PROC_SCORPION, GPIO_INTR_CFG_SU(gpio)); spin_unlock_irqrestore(&tlmm_lock, irq_flags); } diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index fe088a30567a..8b7e719a68c3 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -169,7 +169,8 @@ static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id) u32 pending; unsigned int offset, irqs_handled = 0; - while ((pending = gpio_rcar_read(p, INTDT))) { + while ((pending = gpio_rcar_read(p, INTDT) & + gpio_rcar_read(p, INTMSK))) { offset = __ffs(pending); gpio_rcar_write(p, INTCLR, BIT(offset)); generic_handle_irq(irq_find_mapping(p->irq_domain, offset)); diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c index b97d6a6577b9..f9996899c1f2 100644 --- a/drivers/gpio/gpio-twl4030.c +++ b/drivers/gpio/gpio-twl4030.c @@ -300,7 +300,7 @@ static int twl_direction_in(struct gpio_chip *chip, unsigned offset) if (offset < TWL4030_GPIO_MAX) ret = twl4030_set_gpio_direction(offset, 1); else - ret = -EINVAL; + ret = -EINVAL; /* LED outputs can't be set as input */ if (!ret) priv->direction &= ~BIT(offset); @@ -354,11 +354,20 @@ static void twl_set(struct gpio_chip *chip, unsigned offset, int value) static int twl_direction_out(struct gpio_chip *chip, unsigned offset, int value) { struct gpio_twl4030_priv *priv = to_gpio_twl4030(chip); - int ret = -EINVAL; + int ret = 0; mutex_lock(&priv->mutex); - if (offset < TWL4030_GPIO_MAX) + if (offset < TWL4030_GPIO_MAX) { ret = twl4030_set_gpio_direction(offset, 0); + if (ret) { + mutex_unlock(&priv->mutex); + return ret; + } + } + + /* + * LED gpios i.e. offset >= TWL4030_GPIO_MAX are always output + */ priv->direction |= BIT(offset); mutex_unlock(&priv->mutex); diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h index eef09ec9a5ff..a72cae03b99b 100644 --- a/drivers/gpu/drm/armada/armada_drm.h +++ b/drivers/gpu/drm/armada/armada_drm.h @@ -103,6 +103,7 @@ void armada_drm_queue_unref_work(struct drm_device *, extern const struct drm_mode_config_funcs armada_drm_mode_config_funcs; int armada_fbdev_init(struct drm_device *); +void armada_fbdev_lastclose(struct drm_device *); void armada_fbdev_fini(struct drm_device *); int armada_overlay_plane_create(struct drm_device *, unsigned long); diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 4f2b28354915..62d0ff3efddf 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -321,6 +321,11 @@ static struct drm_ioctl_desc armada_ioctls[] = { DRM_UNLOCKED), }; +static void armada_drm_lastclose(struct drm_device *dev) +{ + armada_fbdev_lastclose(dev); +} + static const struct file_operations armada_drm_fops = { .owner = THIS_MODULE, .llseek = no_llseek, @@ -337,7 +342,7 @@ static struct drm_driver armada_drm_driver = { .open = NULL, .preclose = NULL, .postclose = NULL, - .lastclose = NULL, + .lastclose = armada_drm_lastclose, .unload = armada_drm_unload, .get_vblank_counter = drm_vblank_count, .enable_vblank = armada_drm_enable_vblank, diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c index dd5ea77dac96..948cb14c561e 100644 --- a/drivers/gpu/drm/armada/armada_fbdev.c +++ b/drivers/gpu/drm/armada/armada_fbdev.c @@ -105,9 +105,9 @@ static int armada_fb_create(struct drm_fb_helper *fbh, drm_fb_helper_fill_fix(info, dfb->fb.pitches[0], dfb->fb.depth); drm_fb_helper_fill_var(info, fbh, sizes->fb_width, sizes->fb_height); - DRM_DEBUG_KMS("allocated %dx%d %dbpp fb: 0x%08x\n", - dfb->fb.width, dfb->fb.height, - dfb->fb.bits_per_pixel, obj->phys_addr); + DRM_DEBUG_KMS("allocated %dx%d %dbpp fb: 0x%08llx\n", + dfb->fb.width, dfb->fb.height, dfb->fb.bits_per_pixel, + (unsigned long long)obj->phys_addr); return 0; @@ -177,6 +177,16 @@ int armada_fbdev_init(struct drm_device *dev) return ret; } +void armada_fbdev_lastclose(struct drm_device *dev) +{ + struct armada_private *priv = dev->dev_private; + + drm_modeset_lock_all(dev); + if (priv->fbdev) + drm_fb_helper_restore_fbdev_mode(priv->fbdev); + drm_modeset_unlock_all(dev); +} + void armada_fbdev_fini(struct drm_device *dev) { struct armada_private *priv = dev->dev_private; @@ -192,11 +202,11 @@ void armada_fbdev_fini(struct drm_device *dev) framebuffer_release(info); } + drm_fb_helper_fini(fbh); + if (fbh->fb) fbh->fb->funcs->destroy(fbh->fb); - drm_fb_helper_fini(fbh); - priv->fbdev = NULL; } } diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index 9f2356bae7fd..887816f43476 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -172,8 +172,9 @@ armada_gem_linear_back(struct drm_device *dev, struct armada_gem_object *obj) obj->dev_addr = obj->linear->start; } - DRM_DEBUG_DRIVER("obj %p phys %#x dev %#x\n", - obj, obj->phys_addr, obj->dev_addr); + DRM_DEBUG_DRIVER("obj %p phys %#llx dev %#llx\n", obj, + (unsigned long long)obj->phys_addr, + (unsigned long long)obj->dev_addr); return 0; } @@ -557,7 +558,6 @@ armada_gem_prime_import(struct drm_device *dev, struct dma_buf *buf) * refcount on the gem object itself. */ drm_gem_object_reference(obj); - dma_buf_put(buf); return obj; } } @@ -573,6 +573,7 @@ armada_gem_prime_import(struct drm_device *dev, struct dma_buf *buf) } dobj->obj.import_attach = attach; + get_dma_buf(buf); /* * Don't call dma_buf_map_attachment() here - it maps the diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 0a1e4a5f4234..8835dcddfac3 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -68,6 +68,8 @@ #define EDID_QUIRK_DETAILED_SYNC_PP (1 << 6) /* Force reduced-blanking timings for detailed modes */ #define EDID_QUIRK_FORCE_REDUCED_BLANKING (1 << 7) +/* Force 8bpc */ +#define EDID_QUIRK_FORCE_8BPC (1 << 8) struct detailed_mode_closure { struct drm_connector *connector; @@ -128,6 +130,9 @@ static struct edid_quirk { /* Medion MD 30217 PG */ { "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 }, + + /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */ + { "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC }, }; /* @@ -3435,6 +3440,9 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) drm_add_display_info(edid, &connector->display_info); + if (quirks & EDID_QUIRK_FORCE_8BPC) + connector->display_info.bpc = 8; + return num_modes; } EXPORT_SYMBOL(drm_add_edid_modes); diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index f53d5246979c..66dd3a001cf1 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -566,11 +566,11 @@ err_unload: if (dev->driver->unload) dev->driver->unload(dev); err_primary_node: - drm_put_minor(dev->primary); + drm_unplug_minor(dev->primary); err_render_node: - drm_put_minor(dev->render); + drm_unplug_minor(dev->render); err_control_node: - drm_put_minor(dev->control); + drm_unplug_minor(dev->control); err_agp: if (dev->driver->bus->agp_destroy) dev->driver->bus->agp_destroy(dev); diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 0cab2d045135..5c648425c1e0 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -83,6 +83,14 @@ void i915_update_dri1_breadcrumb(struct drm_device *dev) drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_master_private *master_priv; + /* + * The dri breadcrumb update races against the drm master disappearing. + * Instead of trying to fix this (this is by far not the only ums issue) + * just don't do the update in kms mode. + */ + if (drm_core_check_feature(dev, DRIVER_MODESET)) + return; + if (dev->primary->master) { master_priv = dev->primary->master->driver_priv; if (master_priv->sarea_priv) @@ -1490,16 +1498,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) spin_lock_init(&dev_priv->uncore.lock); spin_lock_init(&dev_priv->mm.object_stat_lock); mutex_init(&dev_priv->dpio_lock); - mutex_init(&dev_priv->rps.hw_lock); mutex_init(&dev_priv->modeset_restore_lock); - mutex_init(&dev_priv->pc8.lock); - dev_priv->pc8.requirements_met = false; - dev_priv->pc8.gpu_idle = false; - dev_priv->pc8.irqs_disabled = false; - dev_priv->pc8.enabled = false; - dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */ - INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work); + intel_pm_setup(dev); intel_display_crc_init(dev); @@ -1603,7 +1604,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) } intel_irq_init(dev); - intel_pm_init(dev); intel_uncore_sanitize(dev); /* Try to make sure MCHBAR is enabled before poking at it */ @@ -1848,8 +1848,10 @@ void i915_driver_lastclose(struct drm_device * dev) void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv) { + mutex_lock(&dev->struct_mutex); i915_gem_context_close(dev, file_priv); i915_gem_release(dev, file_priv); + mutex_unlock(&dev->struct_mutex); } void i915_driver_postclose(struct drm_device *dev, struct drm_file *file) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 2e367a1c6a64..5b7b7e06cb3a 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -651,6 +651,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings) intel_modeset_init_hw(dev); drm_modeset_lock_all(dev); + drm_mode_config_reset(dev); intel_modeset_setup_hw_state(dev, true); drm_modeset_unlock_all(dev); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index ccdbecca070d..90fcccba17b0 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1755,8 +1755,13 @@ struct drm_i915_file_private { #define IS_MOBILE(dev) (INTEL_INFO(dev)->is_mobile) #define IS_HSW_EARLY_SDV(dev) (IS_HASWELL(dev) && \ ((dev)->pdev->device & 0xFF00) == 0x0C00) -#define IS_ULT(dev) (IS_HASWELL(dev) && \ +#define IS_BDW_ULT(dev) (IS_BROADWELL(dev) && \ + (((dev)->pdev->device & 0xf) == 0x2 || \ + ((dev)->pdev->device & 0xf) == 0x6 || \ + ((dev)->pdev->device & 0xf) == 0xe)) +#define IS_HSW_ULT(dev) (IS_HASWELL(dev) && \ ((dev)->pdev->device & 0xFF00) == 0x0A00) +#define IS_ULT(dev) (IS_HSW_ULT(dev) || IS_BDW_ULT(dev)) #define IS_HSW_GT3(dev) (IS_HASWELL(dev) && \ ((dev)->pdev->device & 0x00F0) == 0x0020) #define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary) @@ -1901,9 +1906,7 @@ void i915_queue_hangcheck(struct drm_device *dev); void i915_handle_error(struct drm_device *dev, bool wedged); extern void intel_irq_init(struct drm_device *dev); -extern void intel_pm_init(struct drm_device *dev); extern void intel_hpd_init(struct drm_device *dev); -extern void intel_pm_init(struct drm_device *dev); extern void intel_uncore_sanitize(struct drm_device *dev); extern void intel_uncore_early_sanitize(struct drm_device *dev); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 72a3df32292f..b0f42b9ca037 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -347,10 +347,8 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file) { struct drm_i915_file_private *file_priv = file->driver_priv; - mutex_lock(&dev->struct_mutex); idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL); idr_destroy(&file_priv->context_idr); - mutex_unlock(&dev->struct_mutex); } static struct i915_hw_context * @@ -423,11 +421,21 @@ static int do_switch(struct i915_hw_context *to) if (ret) return ret; - /* Clear this page out of any CPU caches for coherent swap-in/out. Note + /* + * Pin can switch back to the default context if we end up calling into + * evict_everything - as a last ditch gtt defrag effort that also + * switches to the default context. Hence we need to reload from here. + */ + from = ring->last_context; + + /* + * Clear this page out of any CPU caches for coherent swap-in/out. Note * that thanks to write = false in this call and us not setting any gpu * write domains when putting a context object onto the active list * (when switching away from it), this won't block. - * XXX: We need a real interface to do this instead of trickery. */ + * + * XXX: We need a real interface to do this instead of trickery. + */ ret = i915_gem_object_set_to_gtt_domain(to->obj, false); if (ret) { i915_gem_object_unpin(to->obj); diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index b7376533633d..8f3adc7d0dc8 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -88,6 +88,7 @@ i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm, } else drm_mm_init_scan(&vm->mm, min_size, alignment, cache_level); +search_again: /* First see if there is a large enough contiguous idle region... */ list_for_each_entry(vma, &vm->inactive_list, mm_list) { if (mark_free(vma, &unwind_list)) @@ -115,10 +116,17 @@ none: list_del_init(&vma->exec_list); } - /* We expect the caller to unpin, evict all and try again, or give up. - * So calling i915_gem_evict_vm() is unnecessary. + /* Can we unpin some objects such as idle hw contents, + * or pending flips? */ - return -ENOSPC; + ret = nonblocking ? -ENOSPC : i915_gpu_idle(dev); + if (ret) + return ret; + + /* Only idle the GPU and repeat the search once */ + i915_gem_retire_requests(dev); + nonblocking = true; + goto search_again; found: /* drm_mm doesn't allow any other other operations while diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 38cb8d44a013..c79dd2b1f70e 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -337,8 +337,8 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm) kfree(ppgtt->gen8_pt_dma_addr[i]); } - __free_pages(ppgtt->gen8_pt_pages, ppgtt->num_pt_pages << PAGE_SHIFT); - __free_pages(ppgtt->pd_pages, ppgtt->num_pd_pages << PAGE_SHIFT); + __free_pages(ppgtt->gen8_pt_pages, get_order(ppgtt->num_pt_pages << PAGE_SHIFT)); + __free_pages(ppgtt->pd_pages, get_order(ppgtt->num_pd_pages << PAGE_SHIFT)); } /** @@ -1241,6 +1241,11 @@ static inline unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl) bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK; if (bdw_gmch_ctl) bdw_gmch_ctl = 1 << bdw_gmch_ctl; + if (bdw_gmch_ctl > 4) { + WARN_ON(!i915_preliminary_hw_support); + return 4<<20; + } + return bdw_gmch_ctl << 20; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 080f6fd4e839..8b8bde7dce53 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -9135,7 +9135,7 @@ intel_pipe_config_compare(struct drm_device *dev, if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5) PIPE_CONF_CHECK_I(pipe_bpp); - if (!IS_HASWELL(dev)) { + if (!HAS_DDI(dev)) { PIPE_CONF_CHECK_CLOCK_FUZZY(adjusted_mode.crtc_clock); PIPE_CONF_CHECK_CLOCK_FUZZY(port_clock); } @@ -11036,8 +11036,6 @@ void intel_modeset_setup_hw_state(struct drm_device *dev, } intel_modeset_check_state(dev); - - drm_mode_config_reset(dev); } void intel_modeset_gem_init(struct drm_device *dev) @@ -11046,7 +11044,10 @@ void intel_modeset_gem_init(struct drm_device *dev) intel_setup_overlay(dev); + drm_modeset_lock_all(dev); + drm_mode_config_reset(dev); intel_modeset_setup_hw_state(dev, false); + drm_modeset_unlock_all(dev); } void intel_modeset_cleanup(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index a18e88b3e425..79f91f26e288 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -821,6 +821,7 @@ void intel_update_sprite_watermarks(struct drm_plane *plane, uint32_t sprite_width, int pixel_size, bool enabled, bool scaled); void intel_init_pm(struct drm_device *dev); +void intel_pm_setup(struct drm_device *dev); bool intel_fbc_enabled(struct drm_device *dev); void intel_update_fbc(struct drm_device *dev); void intel_gpu_ips_init(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index f161ac02c4f6..e6f782d1c669 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -451,7 +451,9 @@ static u32 intel_panel_get_backlight(struct drm_device *dev, spin_lock_irqsave(&dev_priv->backlight.lock, flags); - if (HAS_PCH_SPLIT(dev)) { + if (IS_BROADWELL(dev)) { + val = I915_READ(BLC_PWM_PCH_CTL2) & BACKLIGHT_DUTY_CYCLE_MASK; + } else if (HAS_PCH_SPLIT(dev)) { val = I915_READ(BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK; } else { if (IS_VALLEYVIEW(dev)) @@ -479,6 +481,13 @@ static u32 intel_panel_get_backlight(struct drm_device *dev, return val; } +static void intel_bdw_panel_set_backlight(struct drm_device *dev, u32 level) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 val = I915_READ(BLC_PWM_PCH_CTL2) & ~BACKLIGHT_DUTY_CYCLE_MASK; + I915_WRITE(BLC_PWM_PCH_CTL2, val | level); +} + static void intel_pch_panel_set_backlight(struct drm_device *dev, u32 level) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -496,7 +505,9 @@ static void intel_panel_actually_set_backlight(struct drm_device *dev, DRM_DEBUG_DRIVER("set backlight PWM = %d\n", level); level = intel_panel_compute_brightness(dev, pipe, level); - if (HAS_PCH_SPLIT(dev)) + if (IS_BROADWELL(dev)) + return intel_bdw_panel_set_backlight(dev, level); + else if (HAS_PCH_SPLIT(dev)) return intel_pch_panel_set_backlight(dev, level); if (is_backlight_combination_mode(dev)) { @@ -666,7 +677,16 @@ void intel_panel_enable_backlight(struct intel_connector *connector) POSTING_READ(reg); I915_WRITE(reg, tmp | BLM_PWM_ENABLE); - if (HAS_PCH_SPLIT(dev) && + if (IS_BROADWELL(dev)) { + /* + * Broadwell requires PCH override to drive the PCH + * backlight pin. The above will configure the CPU + * backlight pin, which we don't plan to use. + */ + tmp = I915_READ(BLC_PWM_PCH_CTL1); + tmp |= BLM_PCH_OVERRIDE_ENABLE | BLM_PCH_PWM_ENABLE; + I915_WRITE(BLC_PWM_PCH_CTL1, tmp); + } else if (HAS_PCH_SPLIT(dev) && !(dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE)) { tmp = I915_READ(BLC_PWM_PCH_CTL1); tmp |= BLM_PCH_PWM_ENABLE; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 6e0d5e075b15..3657ab43c8fd 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5685,6 +5685,7 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable) { struct drm_i915_private *dev_priv = dev->dev_private; bool is_enabled, enable_requested; + unsigned long irqflags; uint32_t tmp; tmp = I915_READ(HSW_PWR_WELL_DRIVER); @@ -5702,9 +5703,24 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable) HSW_PWR_WELL_STATE_ENABLED), 20)) DRM_ERROR("Timeout enabling power well\n"); } + + if (IS_BROADWELL(dev)) { + spin_lock_irqsave(&dev_priv->irq_lock, irqflags); + I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_B), + dev_priv->de_irq_mask[PIPE_B]); + I915_WRITE(GEN8_DE_PIPE_IER(PIPE_B), + ~dev_priv->de_irq_mask[PIPE_B] | + GEN8_PIPE_VBLANK); + I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_C), + dev_priv->de_irq_mask[PIPE_C]); + I915_WRITE(GEN8_DE_PIPE_IER(PIPE_C), + ~dev_priv->de_irq_mask[PIPE_C] | + GEN8_PIPE_VBLANK); + POSTING_READ(GEN8_DE_PIPE_IER(PIPE_C)); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + } } else { if (enable_requested) { - unsigned long irqflags; enum pipe p; I915_WRITE(HSW_PWR_WELL_DRIVER, 0); @@ -6130,10 +6146,19 @@ int vlv_freq_opcode(int ddr_freq, int val) return val; } -void intel_pm_init(struct drm_device *dev) +void intel_pm_setup(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + mutex_init(&dev_priv->rps.hw_lock); + + mutex_init(&dev_priv->pc8.lock); + dev_priv->pc8.requirements_met = false; + dev_priv->pc8.gpu_idle = false; + dev_priv->pc8.irqs_disabled = false; + dev_priv->pc8.enabled = false; + dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */ + INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work); INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work, intel_gen6_powersave_work); } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index b620337e6d67..c2f09d456300 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -965,6 +965,7 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring) } else if (IS_GEN6(ring->dev)) { mmio = RING_HWS_PGA_GEN6(ring->mmio_base); } else { + /* XXX: gen8 returns to sanity */ mmio = RING_HWS_PGA(ring->mmio_base); } diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 0b02078a0b84..25cbe073c388 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -784,6 +784,7 @@ static int gen6_do_reset(struct drm_device *dev) int intel_gpu_reset(struct drm_device *dev) { switch (INTEL_INFO(dev)->gen) { + case 8: case 7: case 6: return gen6_do_reset(dev); case 5: return ironlake_do_reset(dev); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 7a3759f1c41a..98a22e6e27a1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -858,6 +858,12 @@ static int nouveau_pmops_runtime_suspend(struct device *dev) if (nouveau_runtime_pm == 0) return -EINVAL; + /* are we optimus enabled? */ + if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) { + DRM_DEBUG_DRIVER("failing to power off - not optimus\n"); + return -EINVAL; + } + nv_debug_level(SILENT); drm_kms_helper_poll_disable(drm_dev); vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF); diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 80a20120e625..b1970596a782 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1196,7 +1196,9 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, } else if ((rdev->family == CHIP_TAHITI) || (rdev->family == CHIP_PITCAIRN)) fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16); - else if (rdev->family == CHIP_VERDE) + else if ((rdev->family == CHIP_VERDE) || + (rdev->family == CHIP_OLAND) || + (rdev->family == CHIP_HAINAN)) /* for completeness. HAINAN has no display hw */ fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P4_8x16); switch (radeon_crtc->crtc_id) { diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c index 0300727a4f70..d08b83c6267b 100644 --- a/drivers/gpu/drm/radeon/cik_sdma.c +++ b/drivers/gpu/drm/radeon/cik_sdma.c @@ -458,7 +458,7 @@ int cik_copy_dma(struct radeon_device *rdev, radeon_ring_write(ring, 0); /* src/dst endian swap */ radeon_ring_write(ring, src_offset & 0xffffffff); radeon_ring_write(ring, upper_32_bits(src_offset) & 0xffffffff); - radeon_ring_write(ring, dst_offset & 0xfffffffc); + radeon_ring_write(ring, dst_offset & 0xffffffff); radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xffffffff); src_offset += cur_size_in_bytes; dst_offset += cur_size_in_bytes; diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index e354ce94cdd1..c0425bb6223a 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -2021,7 +2021,7 @@ static struct radeon_asic ci_asic = { .hdmi_setmode = &evergreen_hdmi_setmode, }, .copy = { - .blit = NULL, + .blit = &cik_copy_cpdma, .blit_ring_index = RADEON_RING_TYPE_GFX_INDEX, .dma = &cik_copy_dma, .dma_ring_index = R600_RING_TYPE_DMA_INDEX, @@ -2122,7 +2122,7 @@ static struct radeon_asic kv_asic = { .hdmi_setmode = &evergreen_hdmi_setmode, }, .copy = { - .blit = NULL, + .blit = &cik_copy_cpdma, .blit_ring_index = RADEON_RING_TYPE_GFX_INDEX, .dma = &cik_copy_dma, .dma_ring_index = R600_RING_TYPE_DMA_INDEX, diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 9f5ff28864f6..1958b36ad0e5 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -508,15 +508,6 @@ static const struct file_operations radeon_driver_kms_fops = { #endif }; - -static void -radeon_pci_shutdown(struct pci_dev *pdev) -{ - struct drm_device *dev = pci_get_drvdata(pdev); - - radeon_driver_unload_kms(dev); -} - static struct drm_driver kms_driver = { .driver_features = DRIVER_USE_AGP | @@ -586,7 +577,6 @@ static struct pci_driver radeon_kms_pci_driver = { .probe = radeon_pci_probe, .remove = radeon_pci_remove, .driver.pm = &radeon_pm_ops, - .shutdown = radeon_pci_shutdown, }; static int __init radeon_init(void) diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index 1c560629575a..e7dab069cccf 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -162,6 +162,16 @@ static void rs690_mc_init(struct radeon_device *rdev) base = RREG32_MC(R_000100_MCCFG_FB_LOCATION); base = G_000100_MC_FB_START(base) << 16; rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev); + /* Some boards seem to be configured for 128MB of sideport memory, + * but really only have 64MB. Just skip the sideport and use + * UMA memory. + */ + if (rdev->mc.igp_sideport_enabled && + (rdev->mc.real_vram_size == (384 * 1024 * 1024))) { + base += 128 * 1024 * 1024; + rdev->mc.real_vram_size -= 128 * 1024 * 1024; + rdev->mc.mc_vram_size = rdev->mc.real_vram_size; + } /* Use K8 direct mapping for fast fb access. */ rdev->fastfb_working = false; diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index b249ab9b1eb2..6440eeac22d2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -169,9 +169,9 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } page_offset = ((address - vma->vm_start) >> PAGE_SHIFT) + - drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff; - page_last = vma_pages(vma) + - drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff; + vma->vm_pgoff - drm_vma_node_start(&bo->vma_node); + page_last = vma_pages(vma) + vma->vm_pgoff - + drm_vma_node_start(&bo->vma_node); if (unlikely(page_offset >= bo->num_pages)) { retval = VM_FAULT_SIGBUS; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index a51f48e3e917..45d5b5ab6ca9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -68,6 +68,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, SVGA_FIFO_3D_HWVERSION)); break; } + case DRM_VMW_PARAM_MAX_SURF_MEMORY: + param->value = dev_priv->memory_size; + break; default: DRM_ERROR("Illegal vmwgfx get param request: %d\n", param->param); diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c index acb7f90359a3..749a6cadab8b 100644 --- a/drivers/iio/adc/ad7887.c +++ b/drivers/iio/adc/ad7887.c @@ -200,7 +200,13 @@ static const struct ad7887_chip_info ad7887_chip_info_tbl[] = { .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = 1, .scan_index = 1, - .scan_type = IIO_ST('u', 12, 16, 0), + .scan_type = { + .sign = 'u', + .realbits = 12, + .storagebits = 16, + .shift = 0, + .endianness = IIO_BE, + }, }, .channel[1] = { .type = IIO_VOLTAGE, @@ -210,7 +216,13 @@ static const struct ad7887_chip_info ad7887_chip_info_tbl[] = { .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = 0, .scan_index = 0, - .scan_type = IIO_ST('u', 12, 16, 0), + .scan_type = { + .sign = 'u', + .realbits = 12, + .storagebits = 16, + .shift = 0, + .endianness = IIO_BE, + }, }, .channel[2] = IIO_CHAN_SOFT_TIMESTAMP(2), .int_vref_mv = 2500, diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c index 3fb7757a1028..368660dfe135 100644 --- a/drivers/iio/imu/adis16400_core.c +++ b/drivers/iio/imu/adis16400_core.c @@ -651,7 +651,12 @@ static const struct iio_chan_spec adis16448_channels[] = { .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), .address = ADIS16448_BARO_OUT, .scan_index = ADIS16400_SCAN_BARO, - .scan_type = IIO_ST('s', 16, 16, 0), + .scan_type = { + .sign = 's', + .realbits = 16, + .storagebits = 16, + .endianness = IIO_BE, + }, }, ADIS16400_TEMP_CHAN(ADIS16448_TEMP_OUT, 12), IIO_CHAN_SOFT_TIMESTAMP(11) diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c index 21df57130018..0922e39b0ea9 100644 --- a/drivers/iio/light/cm36651.c +++ b/drivers/iio/light/cm36651.c @@ -387,7 +387,7 @@ static int cm36651_read_int_time(struct cm36651_data *cm36651, return -EINVAL; } - return IIO_VAL_INT_PLUS_MICRO; + return IIO_VAL_INT; } static int cm36651_write_int_time(struct cm36651_data *cm36651, diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 6be57c38638d..9804fca6bf06 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -207,7 +207,9 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn) isert_conn->conn_rx_descs = NULL; } +static void isert_cq_tx_work(struct work_struct *); static void isert_cq_tx_callback(struct ib_cq *, void *); +static void isert_cq_rx_work(struct work_struct *); static void isert_cq_rx_callback(struct ib_cq *, void *); static int @@ -259,26 +261,36 @@ isert_create_device_ib_res(struct isert_device *device) cq_desc[i].device = device; cq_desc[i].cq_index = i; + INIT_WORK(&cq_desc[i].cq_rx_work, isert_cq_rx_work); device->dev_rx_cq[i] = ib_create_cq(device->ib_device, isert_cq_rx_callback, isert_cq_event_callback, (void *)&cq_desc[i], ISER_MAX_RX_CQ_LEN, i); - if (IS_ERR(device->dev_rx_cq[i])) + if (IS_ERR(device->dev_rx_cq[i])) { + ret = PTR_ERR(device->dev_rx_cq[i]); + device->dev_rx_cq[i] = NULL; goto out_cq; + } + INIT_WORK(&cq_desc[i].cq_tx_work, isert_cq_tx_work); device->dev_tx_cq[i] = ib_create_cq(device->ib_device, isert_cq_tx_callback, isert_cq_event_callback, (void *)&cq_desc[i], ISER_MAX_TX_CQ_LEN, i); - if (IS_ERR(device->dev_tx_cq[i])) + if (IS_ERR(device->dev_tx_cq[i])) { + ret = PTR_ERR(device->dev_tx_cq[i]); + device->dev_tx_cq[i] = NULL; goto out_cq; + } - if (ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP)) + ret = ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP); + if (ret) goto out_cq; - if (ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP)) + ret = ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP); + if (ret) goto out_cq; } @@ -1724,7 +1736,6 @@ isert_cq_tx_callback(struct ib_cq *cq, void *context) { struct isert_cq_desc *cq_desc = (struct isert_cq_desc *)context; - INIT_WORK(&cq_desc->cq_tx_work, isert_cq_tx_work); queue_work(isert_comp_wq, &cq_desc->cq_tx_work); } @@ -1768,7 +1779,6 @@ isert_cq_rx_callback(struct ib_cq *cq, void *context) { struct isert_cq_desc *cq_desc = (struct isert_cq_desc *)context; - INIT_WORK(&cq_desc->cq_rx_work, isert_cq_rx_work); queue_work(isert_rx_wq, &cq_desc->cq_rx_work); } diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 5f9a7ad9b964..8aeec0b4601a 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -625,6 +625,7 @@ static int ems_usb_start(struct ems_usb *dev) usb_unanchor_urb(urb); usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf, urb->transfer_dma); + usb_free_urb(urb); break; } @@ -798,8 +799,8 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne * allowed (MAX_TX_URBS). */ if (!context) { - usb_unanchor_urb(urb); usb_free_coherent(dev->udev, size, buf, urb->transfer_dma); + usb_free_urb(urb); netdev_warn(netdev, "couldn't find free context\n"); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 8ee9d1556e6e..263dd921edc4 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -927,6 +927,9 @@ static int pcan_usb_pro_init(struct peak_usb_device *dev) /* set LED in default state (end of init phase) */ pcan_usb_pro_set_led(dev, 0, 1); + kfree(bi); + kfree(fi); + return 0; err_out: diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index b1cb0ffb15c7..6055d397a29e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -447,8 +447,9 @@ irqreturn_t qlcnic_83xx_intr(int irq, void *data) qlcnic_83xx_poll_process_aen(adapter); - if (ahw->diag_test == QLCNIC_INTERRUPT_TEST) { - ahw->diag_cnt++; + if (ahw->diag_test) { + if (ahw->diag_test == QLCNIC_INTERRUPT_TEST) + ahw->diag_cnt++; qlcnic_83xx_enable_legacy_msix_mbx_intr(adapter); return IRQ_HANDLED; } @@ -1345,11 +1346,6 @@ static int qlcnic_83xx_diag_alloc_res(struct net_device *netdev, int test, } if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) { - /* disable and free mailbox interrupt */ - if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) { - qlcnic_83xx_enable_mbx_poll(adapter); - qlcnic_83xx_free_mbx_intr(adapter); - } adapter->ahw->loopback_state = 0; adapter->ahw->hw_ops->setup_link_event(adapter, 1); } @@ -1363,33 +1359,20 @@ static void qlcnic_83xx_diag_free_res(struct net_device *netdev, { struct qlcnic_adapter *adapter = netdev_priv(netdev); struct qlcnic_host_sds_ring *sds_ring; - int ring, err; + int ring; clear_bit(__QLCNIC_DEV_UP, &adapter->state); if (adapter->ahw->diag_test == QLCNIC_INTERRUPT_TEST) { for (ring = 0; ring < adapter->drv_sds_rings; ring++) { sds_ring = &adapter->recv_ctx->sds_rings[ring]; - qlcnic_83xx_disable_intr(adapter, sds_ring); - if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) - qlcnic_83xx_enable_mbx_poll(adapter); + if (adapter->flags & QLCNIC_MSIX_ENABLED) + qlcnic_83xx_disable_intr(adapter, sds_ring); } } qlcnic_fw_destroy_ctx(adapter); qlcnic_detach(adapter); - if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) { - if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) { - err = qlcnic_83xx_setup_mbx_intr(adapter); - qlcnic_83xx_disable_mbx_poll(adapter); - if (err) { - dev_err(&adapter->pdev->dev, - "%s: failed to setup mbx interrupt\n", - __func__); - goto out; - } - } - } adapter->ahw->diag_test = 0; adapter->drv_sds_rings = drv_sds_rings; @@ -1399,9 +1382,6 @@ static void qlcnic_83xx_diag_free_res(struct net_device *netdev, if (netif_running(netdev)) __qlcnic_up(adapter, netdev); - if (adapter->ahw->diag_test == QLCNIC_INTERRUPT_TEST && - !(adapter->flags & QLCNIC_MSIX_ENABLED)) - qlcnic_83xx_disable_mbx_poll(adapter); out: netif_device_attach(netdev); } @@ -3754,6 +3734,19 @@ static void qlcnic_83xx_decode_mbx_rsp(struct qlcnic_adapter *adapter, return; } +static inline void qlcnic_dump_mailbox_registers(struct qlcnic_adapter *adapter) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + u32 offset; + + offset = QLCRDX(ahw, QLCNIC_DEF_INT_MASK); + dev_info(&adapter->pdev->dev, "Mbx interrupt mask=0x%x, Mbx interrupt enable=0x%x, Host mbx control=0x%x, Fw mbx control=0x%x", + readl(ahw->pci_base0 + offset), + QLCRDX(ahw, QLCNIC_MBX_INTR_ENBL), + QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL), + QLCRDX(ahw, QLCNIC_FW_MBX_CTRL)); +} + static void qlcnic_83xx_mailbox_worker(struct work_struct *work) { struct qlcnic_mailbox *mbx = container_of(work, struct qlcnic_mailbox, @@ -3798,6 +3791,8 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) __func__, cmd->cmd_op, cmd->type, ahw->pci_func, ahw->op_mode); clear_bit(QLC_83XX_MBX_READY, &mbx->status); + qlcnic_dump_mailbox_registers(adapter); + qlcnic_83xx_get_mbx_data(adapter, cmd); qlcnic_dump_mbx(adapter, cmd); qlcnic_83xx_idc_request_reset(adapter, QLCNIC_FORCE_FW_DUMP_KEY); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index 4cae6caa6bfa..a6a33508e401 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -662,4 +662,5 @@ pci_ers_result_t qlcnic_83xx_io_error_detected(struct pci_dev *, pci_channel_state_t); pci_ers_result_t qlcnic_83xx_io_slot_reset(struct pci_dev *); void qlcnic_83xx_io_resume(struct pci_dev *); +void qlcnic_83xx_stop_hw(struct qlcnic_adapter *); #endif diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index 89208e5b25d6..918e18ddf038 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -740,6 +740,7 @@ static int qlcnic_83xx_idc_unknown_state(struct qlcnic_adapter *adapter) adapter->ahw->idc.err_code = -EIO; dev_err(&adapter->pdev->dev, "%s: Device in unknown state\n", __func__); + clear_bit(__QLCNIC_RESETTING, &adapter->state); return 0; } @@ -818,7 +819,6 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter) struct qlcnic_hardware_context *ahw = adapter->ahw; struct qlcnic_mailbox *mbx = ahw->mailbox; int ret = 0; - u32 owner; u32 val; /* Perform NIC configuration based ready state entry actions */ @@ -848,9 +848,9 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter) set_bit(__QLCNIC_RESETTING, &adapter->state); qlcnic_83xx_idc_enter_need_reset_state(adapter, 1); } else { - owner = qlcnic_83xx_idc_find_reset_owner_id(adapter); - if (ahw->pci_func == owner) - qlcnic_dump_fw(adapter); + netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n", + __func__); + qlcnic_83xx_idc_enter_failed_state(adapter, 1); } return -EIO; } @@ -948,13 +948,26 @@ static int qlcnic_83xx_idc_need_quiesce_state(struct qlcnic_adapter *adapter) return 0; } -static int qlcnic_83xx_idc_failed_state(struct qlcnic_adapter *adapter) +static void qlcnic_83xx_idc_failed_state(struct qlcnic_adapter *adapter) { - dev_err(&adapter->pdev->dev, "%s: please restart!!\n", __func__); + struct qlcnic_hardware_context *ahw = adapter->ahw; + u32 val, owner; + + val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL); + if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) { + owner = qlcnic_83xx_idc_find_reset_owner_id(adapter); + if (ahw->pci_func == owner) { + qlcnic_83xx_stop_hw(adapter); + qlcnic_dump_fw(adapter); + } + } + + netdev_warn(adapter->netdev, "%s: Reboot will be required to recover the adapter!!\n", + __func__); clear_bit(__QLCNIC_RESETTING, &adapter->state); - adapter->ahw->idc.err_code = -EIO; + ahw->idc.err_code = -EIO; - return 0; + return; } static int qlcnic_83xx_idc_quiesce_state(struct qlcnic_adapter *adapter) @@ -1063,12 +1076,6 @@ void qlcnic_83xx_idc_poll_dev_state(struct work_struct *work) adapter->ahw->idc.prev_state = adapter->ahw->idc.curr_state; qlcnic_83xx_periodic_tasks(adapter); - /* Do not reschedule if firmaware is in hanged state and auto - * recovery is disabled - */ - if ((adapter->flags & QLCNIC_FW_HANG) && !qlcnic_auto_fw_reset) - return; - /* Re-schedule the function */ if (test_bit(QLC_83XX_MODULE_LOADED, &adapter->ahw->idc.status)) qlcnic_schedule_work(adapter, qlcnic_83xx_idc_poll_dev_state, @@ -1219,10 +1226,10 @@ void qlcnic_83xx_idc_request_reset(struct qlcnic_adapter *adapter, u32 key) } val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL); - if ((val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) || - !qlcnic_auto_fw_reset) { - dev_err(&adapter->pdev->dev, - "%s:failed, device in non reset mode\n", __func__); + if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) { + netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n", + __func__); + qlcnic_83xx_idc_enter_failed_state(adapter, 0); qlcnic_83xx_unlock_driver(adapter); return; } @@ -1254,24 +1261,24 @@ static int qlcnic_83xx_copy_bootloader(struct qlcnic_adapter *adapter) if (size & 0xF) size = (size + 16) & ~0xF; - p_cache = kzalloc(size, GFP_KERNEL); + p_cache = vzalloc(size); if (p_cache == NULL) return -ENOMEM; ret = qlcnic_83xx_lockless_flash_read32(adapter, src, p_cache, size / sizeof(u32)); if (ret) { - kfree(p_cache); + vfree(p_cache); return ret; } /* 16 byte write to MS memory */ ret = qlcnic_83xx_ms_mem_write128(adapter, dest, (u32 *)p_cache, size / 16); if (ret) { - kfree(p_cache); + vfree(p_cache); return ret; } - kfree(p_cache); + vfree(p_cache); return ret; } @@ -1939,7 +1946,7 @@ static void qlcnic_83xx_exec_template_cmd(struct qlcnic_adapter *p_dev, p_dev->ahw->reset.seq_index = index; } -static void qlcnic_83xx_stop_hw(struct qlcnic_adapter *p_dev) +void qlcnic_83xx_stop_hw(struct qlcnic_adapter *p_dev) { p_dev->ahw->reset.seq_index = 0; @@ -1994,6 +2001,14 @@ static int qlcnic_83xx_restart_hw(struct qlcnic_adapter *adapter) val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL); if (!(val & QLC_83XX_IDC_GRACEFULL_RESET)) qlcnic_dump_fw(adapter); + + if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) { + netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n", + __func__); + qlcnic_83xx_idc_enter_failed_state(adapter, 1); + return err; + } + qlcnic_83xx_init_hw(adapter); if (qlcnic_83xx_copy_bootloader(adapter)) @@ -2073,8 +2088,8 @@ int qlcnic_83xx_configure_opmode(struct qlcnic_adapter *adapter) ahw->nic_mode = QLCNIC_DEFAULT_MODE; adapter->nic_ops->init_driver = qlcnic_83xx_init_default_driver; ahw->idc.state_entry = qlcnic_83xx_idc_ready_state_entry; - adapter->max_sds_rings = ahw->max_rx_ques; - adapter->max_tx_rings = ahw->max_tx_ques; + adapter->max_sds_rings = QLCNIC_MAX_SDS_RINGS; + adapter->max_tx_rings = QLCNIC_MAX_TX_RINGS; } else { return -EIO; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index b36c02fafcfd..e3be2760665c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -667,30 +667,25 @@ qlcnic_set_ringparam(struct net_device *dev, static int qlcnic_validate_ring_count(struct qlcnic_adapter *adapter, u8 rx_ring, u8 tx_ring) { + if (rx_ring == 0 || tx_ring == 0) + return -EINVAL; + if (rx_ring != 0) { if (rx_ring > adapter->max_sds_rings) { - netdev_err(adapter->netdev, "Invalid ring count, SDS ring count %d should not be greater than max %d driver sds rings.\n", + netdev_err(adapter->netdev, + "Invalid ring count, SDS ring count %d should not be greater than max %d driver sds rings.\n", rx_ring, adapter->max_sds_rings); return -EINVAL; } } if (tx_ring != 0) { - if (qlcnic_82xx_check(adapter) && - (tx_ring > adapter->max_tx_rings)) { + if (tx_ring > adapter->max_tx_rings) { netdev_err(adapter->netdev, "Invalid ring count, Tx ring count %d should not be greater than max %d driver Tx rings.\n", tx_ring, adapter->max_tx_rings); return -EINVAL; } - - if (qlcnic_83xx_check(adapter) && - (tx_ring > QLCNIC_SINGLE_RING)) { - netdev_err(adapter->netdev, - "Invalid ring count, Tx ring count %d should not be greater than %d driver Tx rings.\n", - tx_ring, QLCNIC_SINGLE_RING); - return -EINVAL; - } } return 0; @@ -948,6 +943,7 @@ static int qlcnic_irq_test(struct net_device *netdev) struct qlcnic_hardware_context *ahw = adapter->ahw; struct qlcnic_cmd_args cmd; int ret, drv_sds_rings = adapter->drv_sds_rings; + int drv_tx_rings = adapter->drv_tx_rings; if (qlcnic_83xx_check(adapter)) return qlcnic_83xx_interrupt_test(netdev); @@ -980,6 +976,7 @@ free_diag_res: clear_diag_irq: adapter->drv_sds_rings = drv_sds_rings; + adapter->drv_tx_rings = drv_tx_rings; clear_bit(__QLCNIC_RESETTING, &adapter->state); return ret; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 0149c9495347..eda6c691d897 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -687,17 +687,11 @@ void qlcnic_advert_link_change(struct qlcnic_adapter *adapter, int linkup) if (adapter->ahw->linkup && !linkup) { netdev_info(netdev, "NIC Link is down\n"); adapter->ahw->linkup = 0; - if (netif_running(netdev)) { - netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); - } + netif_carrier_off(netdev); } else if (!adapter->ahw->linkup && linkup) { netdev_info(netdev, "NIC Link is up\n"); adapter->ahw->linkup = 1; - if (netif_running(netdev)) { - netif_carrier_on(netdev); - netif_wake_queue(netdev); - } + netif_carrier_on(netdev); } } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 05c1eef8df13..2c8cac0c6a55 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -1178,6 +1178,7 @@ qlcnic_initialize_nic(struct qlcnic_adapter *adapter) } else { adapter->ahw->nic_mode = QLCNIC_DEFAULT_MODE; adapter->max_tx_rings = QLCNIC_MAX_HW_TX_RINGS; + adapter->max_sds_rings = QLCNIC_MAX_SDS_RINGS; adapter->flags &= ~QLCNIC_ESWITCH_ENABLED; } @@ -1940,7 +1941,6 @@ int qlcnic_diag_alloc_res(struct net_device *netdev, int test) qlcnic_detach(adapter); adapter->drv_sds_rings = QLCNIC_SINGLE_RING; - adapter->drv_tx_rings = QLCNIC_SINGLE_RING; adapter->ahw->diag_test = test; adapter->ahw->linkup = 0; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 524f713f6017..f8135725bcf6 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -327,7 +327,6 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) return -EINVAL; nvdev->start_remove = true; - cancel_delayed_work_sync(&ndevctx->dwork); cancel_work_sync(&ndevctx->work); netif_tx_disable(ndev); rndis_filter_device_remove(hdev); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index e884ee1fe7ed..27bbe58dcbe7 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1197,6 +1197,9 @@ static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb, err = -EPROTO; + if (fragment) + goto out; + switch (ip_hdr(skb)->protocol) { case IPPROTO_TCP: err = maybe_pull_tail(skb, diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index a344f3d52361..330ef2d06567 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -24,8 +24,8 @@ config PHY_EXYNOS_MIPI_VIDEO config OMAP_USB2 tristate "OMAP USB2 PHY Driver" depends on ARCH_OMAP2PLUS + depends on USB_PHY select GENERIC_PHY - select USB_PHY select OMAP_CONTROL_USB help Enable this to support the transceiver that is part of SOC. This @@ -36,8 +36,8 @@ config OMAP_USB2 config TWL4030_USB tristate "TWL4030 USB Transceiver Driver" depends on TWL4030_CORE && REGULATOR_TWL4030 && USB_MUSB_OMAP2PLUS + depends on USB_PHY select GENERIC_PHY - select USB_PHY help Enable this to support the USB OTG transceiver on TWL4030 family chips (including the TWL5030 and TPS659x0 devices). diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 03cf8fb81554..58e0e9739028 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -437,23 +437,18 @@ struct phy *phy_create(struct device *dev, const struct phy_ops *ops, int id; struct phy *phy; - if (!dev) { - dev_WARN(dev, "no device provided for PHY\n"); - ret = -EINVAL; - goto err0; - } + if (WARN_ON(!dev)) + return ERR_PTR(-EINVAL); phy = kzalloc(sizeof(*phy), GFP_KERNEL); - if (!phy) { - ret = -ENOMEM; - goto err0; - } + if (!phy) + return ERR_PTR(-ENOMEM); id = ida_simple_get(&phy_ida, 0, 0, GFP_KERNEL); if (id < 0) { dev_err(dev, "unable to get id\n"); ret = id; - goto err0; + goto free_phy; } device_initialize(&phy->dev); @@ -468,11 +463,11 @@ struct phy *phy_create(struct device *dev, const struct phy_ops *ops, ret = dev_set_name(&phy->dev, "phy-%s.%d", dev_name(dev), id); if (ret) - goto err1; + goto put_dev; ret = device_add(&phy->dev); if (ret) - goto err1; + goto put_dev; if (pm_runtime_enabled(dev)) { pm_runtime_enable(&phy->dev); @@ -481,12 +476,11 @@ struct phy *phy_create(struct device *dev, const struct phy_ops *ops, return phy; -err1: - ida_remove(&phy_ida, phy->id); +put_dev: put_device(&phy->dev); + ida_remove(&phy_ida, phy->id); +free_phy: kfree(phy); - -err0: return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(phy_create); diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h index 11bd0d970a52..e2142956a8e5 100644 --- a/drivers/pinctrl/sh-pfc/sh_pfc.h +++ b/drivers/pinctrl/sh-pfc/sh_pfc.h @@ -254,7 +254,7 @@ struct sh_pfc_soc_info { #define PINMUX_GPIO(_pin) \ [GPIO_##_pin] = { \ .pin = (u16)-1, \ - .name = __stringify(name), \ + .name = __stringify(GPIO_##_pin), \ .enum_id = _pin##_DATA, \ } diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index 333677d68d0e..9e61922d8230 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -438,7 +438,7 @@ common_reg: platform_set_drvdata(pdev, s2mps11); config.dev = &pdev->dev; - config.regmap = iodev->regmap; + config.regmap = iodev->regmap_pmic; config.driver_data = s2mps11; for (i = 0; i < S2MPS11_REGULATOR_MAX; i++) { if (!reg_np) { diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 596480022b0a..38a1257e76e1 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -471,7 +471,7 @@ static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess, schedule_delayed_work(&tgt->sess_del_work, 0); else schedule_delayed_work(&tgt->sess_del_work, - jiffies - sess->expires); + sess->expires - jiffies); } /* ha->hardware_lock supposed to be held on entry */ @@ -550,13 +550,14 @@ static void qlt_del_sess_work_fn(struct delayed_work *work) struct scsi_qla_host *vha = tgt->vha; struct qla_hw_data *ha = vha->hw; struct qla_tgt_sess *sess; - unsigned long flags; + unsigned long flags, elapsed; spin_lock_irqsave(&ha->hardware_lock, flags); while (!list_empty(&tgt->del_sess_list)) { sess = list_entry(tgt->del_sess_list.next, typeof(*sess), del_list_entry); - if (time_after_eq(jiffies, sess->expires)) { + elapsed = jiffies; + if (time_after_eq(elapsed, sess->expires)) { qlt_undelete_sess(sess); ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004, @@ -566,7 +567,7 @@ static void qlt_del_sess_work_fn(struct delayed_work *work) ha->tgt.tgt_ops->put_sess(sess); } else { schedule_delayed_work(&tgt->sess_del_work, - jiffies - sess->expires); + sess->expires - elapsed); break; } } @@ -4290,6 +4291,7 @@ int qlt_lport_register(struct qla_tgt_func_tmpl *qla_tgt_ops, u64 wwpn, if (rc != 0) { ha->tgt.tgt_ops = NULL; ha->tgt.target_lport_ptr = NULL; + scsi_host_put(host); } mutex_unlock(&qla_tgt_mutex); return rc; diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c index 8f02bf66e20b..4964d2a2fc7d 100644 --- a/drivers/staging/comedi/drivers.c +++ b/drivers/staging/comedi/drivers.c @@ -446,7 +446,7 @@ int comedi_load_firmware(struct comedi_device *dev, release_firmware(fw); } - return ret; + return ret < 0 ? ret : 0; } EXPORT_SYMBOL_GPL(comedi_load_firmware); diff --git a/drivers/staging/comedi/drivers/8255_pci.c b/drivers/staging/comedi/drivers/8255_pci.c index 432e3f9c3301..c55f234b29e6 100644 --- a/drivers/staging/comedi/drivers/8255_pci.c +++ b/drivers/staging/comedi/drivers/8255_pci.c @@ -63,7 +63,8 @@ enum pci_8255_boardid { BOARD_ADLINK_PCI7296, BOARD_CB_PCIDIO24, BOARD_CB_PCIDIO24H, - BOARD_CB_PCIDIO48H, + BOARD_CB_PCIDIO48H_OLD, + BOARD_CB_PCIDIO48H_NEW, BOARD_CB_PCIDIO96H, BOARD_NI_PCIDIO96, BOARD_NI_PCIDIO96B, @@ -106,11 +107,16 @@ static const struct pci_8255_boardinfo pci_8255_boards[] = { .dio_badr = 2, .n_8255 = 1, }, - [BOARD_CB_PCIDIO48H] = { + [BOARD_CB_PCIDIO48H_OLD] = { .name = "cb_pci-dio48h", .dio_badr = 1, .n_8255 = 2, }, + [BOARD_CB_PCIDIO48H_NEW] = { + .name = "cb_pci-dio48h", + .dio_badr = 2, + .n_8255 = 2, + }, [BOARD_CB_PCIDIO96H] = { .name = "cb_pci-dio96h", .dio_badr = 2, @@ -263,7 +269,10 @@ static DEFINE_PCI_DEVICE_TABLE(pci_8255_pci_table) = { { PCI_VDEVICE(ADLINK, 0x7296), BOARD_ADLINK_PCI7296 }, { PCI_VDEVICE(CB, 0x0028), BOARD_CB_PCIDIO24 }, { PCI_VDEVICE(CB, 0x0014), BOARD_CB_PCIDIO24H }, - { PCI_VDEVICE(CB, 0x000b), BOARD_CB_PCIDIO48H }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CB, 0x000b, 0x0000, 0x0000), + .driver_data = BOARD_CB_PCIDIO48H_OLD }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CB, 0x000b, PCI_VENDOR_ID_CB, 0x000b), + .driver_data = BOARD_CB_PCIDIO48H_NEW }, { PCI_VDEVICE(CB, 0x0017), BOARD_CB_PCIDIO96H }, { PCI_VDEVICE(NI, 0x0160), BOARD_NI_PCIDIO96 }, { PCI_VDEVICE(NI, 0x1630), BOARD_NI_PCIDIO96B }, diff --git a/drivers/staging/iio/magnetometer/hmc5843.c b/drivers/staging/iio/magnetometer/hmc5843.c index 99421f90d189..0485d7f39867 100644 --- a/drivers/staging/iio/magnetometer/hmc5843.c +++ b/drivers/staging/iio/magnetometer/hmc5843.c @@ -451,7 +451,12 @@ done: .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) | \ BIT(IIO_CHAN_INFO_SAMP_FREQ), \ .scan_index = idx, \ - .scan_type = IIO_ST('s', 16, 16, IIO_BE), \ + .scan_type = { \ + .sign = 's', \ + .realbits = 16, \ + .storagebits = 16, \ + .endianness = IIO_BE, \ + }, \ } static const struct iio_chan_spec hmc5843_channels[] = { diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c index 6bd015ac9d68..96e4eee344ef 100644 --- a/drivers/staging/imx-drm/imx-drm-core.c +++ b/drivers/staging/imx-drm/imx-drm-core.c @@ -88,8 +88,9 @@ static int imx_drm_driver_unload(struct drm_device *drm) imx_drm_device_put(); - drm_mode_config_cleanup(imxdrm->drm); + drm_vblank_cleanup(imxdrm->drm); drm_kms_helper_poll_fini(imxdrm->drm); + drm_mode_config_cleanup(imxdrm->drm); return 0; } @@ -199,8 +200,8 @@ static void imx_drm_driver_preclose(struct drm_device *drm, if (!file->is_master) return; - for (i = 0; i < 4; i++) - imx_drm_disable_vblank(drm , i); + for (i = 0; i < MAX_CRTC; i++) + imx_drm_disable_vblank(drm, i); } static const struct file_operations imx_drm_driver_fops = { @@ -376,8 +377,6 @@ static int imx_drm_crtc_register(struct imx_drm_crtc *imx_drm_crtc) struct imx_drm_device *imxdrm = __imx_drm_device(); int ret; - drm_crtc_init(imxdrm->drm, imx_drm_crtc->crtc, - imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs); ret = drm_mode_crtc_set_gamma_size(imx_drm_crtc->crtc, 256); if (ret) return ret; @@ -385,6 +384,9 @@ static int imx_drm_crtc_register(struct imx_drm_crtc *imx_drm_crtc) drm_crtc_helper_add(imx_drm_crtc->crtc, imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs); + drm_crtc_init(imxdrm->drm, imx_drm_crtc->crtc, + imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs); + drm_mode_group_reinit(imxdrm->drm); return 0; @@ -428,11 +430,11 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags) ret = drm_mode_group_init_legacy_group(imxdrm->drm, &imxdrm->drm->primary->mode_group); if (ret) - goto err_init; + goto err_kms; ret = drm_vblank_init(imxdrm->drm, MAX_CRTC); if (ret) - goto err_init; + goto err_kms; /* * with vblank_disable_allowed = true, vblank interrupt will be disabled @@ -441,12 +443,19 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags) */ imxdrm->drm->vblank_disable_allowed = true; - if (!imx_drm_device_get()) + if (!imx_drm_device_get()) { ret = -EINVAL; + goto err_vblank; + } - ret = 0; + mutex_unlock(&imxdrm->mutex); + return 0; -err_init: +err_vblank: + drm_vblank_cleanup(drm); +err_kms: + drm_kms_helper_poll_fini(drm); + drm_mode_config_cleanup(drm); mutex_unlock(&imxdrm->mutex); return ret; @@ -492,6 +501,15 @@ int imx_drm_add_crtc(struct drm_crtc *crtc, mutex_lock(&imxdrm->mutex); + /* + * The vblank arrays are dimensioned by MAX_CRTC - we can't + * pass IDs greater than this to those functions. + */ + if (imxdrm->pipes >= MAX_CRTC) { + ret = -EINVAL; + goto err_busy; + } + if (imxdrm->drm->open_count) { ret = -EBUSY; goto err_busy; @@ -528,6 +546,7 @@ int imx_drm_add_crtc(struct drm_crtc *crtc, return 0; err_register: + list_del(&imx_drm_crtc->list); kfree(imx_drm_crtc); err_alloc: err_busy: diff --git a/drivers/staging/imx-drm/imx-tve.c b/drivers/staging/imx-drm/imx-tve.c index 680f4c8fa081..2c44fef8d58b 100644 --- a/drivers/staging/imx-drm/imx-tve.c +++ b/drivers/staging/imx-drm/imx-tve.c @@ -114,7 +114,6 @@ struct imx_tve { struct drm_encoder encoder; struct imx_drm_encoder *imx_drm_encoder; struct device *dev; - spinlock_t enable_lock; /* serializes tve_enable/disable */ spinlock_t lock; /* register lock */ bool enabled; int mode; @@ -146,10 +145,8 @@ __releases(&tve->lock) static void tve_enable(struct imx_tve *tve) { - unsigned long flags; int ret; - spin_lock_irqsave(&tve->enable_lock, flags); if (!tve->enabled) { tve->enabled = true; clk_prepare_enable(tve->clk); @@ -169,23 +166,18 @@ static void tve_enable(struct imx_tve *tve) TVE_CD_SM_IEN | TVE_CD_LM_IEN | TVE_CD_MON_END_IEN); - - spin_unlock_irqrestore(&tve->enable_lock, flags); } static void tve_disable(struct imx_tve *tve) { - unsigned long flags; int ret; - spin_lock_irqsave(&tve->enable_lock, flags); if (tve->enabled) { tve->enabled = false; ret = regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_IPU_CLK_EN | TVE_EN, 0); clk_disable_unprepare(tve->clk); } - spin_unlock_irqrestore(&tve->enable_lock, flags); } static int tve_setup_tvout(struct imx_tve *tve) @@ -601,7 +593,6 @@ static int imx_tve_probe(struct platform_device *pdev) tve->dev = &pdev->dev; spin_lock_init(&tve->lock); - spin_lock_init(&tve->enable_lock); ddc_node = of_parse_phandle(np, "ddc", 0); if (ddc_node) { diff --git a/drivers/staging/imx-drm/ipu-v3/ipu-common.c b/drivers/staging/imx-drm/ipu-v3/ipu-common.c index 7a22ce619ed2..97ca6924dbb3 100644 --- a/drivers/staging/imx-drm/ipu-v3/ipu-common.c +++ b/drivers/staging/imx-drm/ipu-v3/ipu-common.c @@ -996,35 +996,35 @@ static const struct ipu_platform_reg client_reg[] = { }, }; +static DEFINE_MUTEX(ipu_client_id_mutex); static int ipu_client_id; -static int ipu_add_subdevice_pdata(struct device *dev, - const struct ipu_platform_reg *reg) -{ - struct platform_device *pdev; - - pdev = platform_device_register_data(dev, reg->name, ipu_client_id++, - ®->pdata, sizeof(struct ipu_platform_reg)); - - return PTR_ERR_OR_ZERO(pdev); -} - static int ipu_add_client_devices(struct ipu_soc *ipu) { - int ret; - int i; + struct device *dev = ipu->dev; + unsigned i; + int id, ret; + + mutex_lock(&ipu_client_id_mutex); + id = ipu_client_id; + ipu_client_id += ARRAY_SIZE(client_reg); + mutex_unlock(&ipu_client_id_mutex); for (i = 0; i < ARRAY_SIZE(client_reg); i++) { const struct ipu_platform_reg *reg = &client_reg[i]; - ret = ipu_add_subdevice_pdata(ipu->dev, reg); - if (ret) + struct platform_device *pdev; + + pdev = platform_device_register_data(dev, reg->name, + id++, ®->pdata, sizeof(reg->pdata)); + + if (IS_ERR(pdev)) goto err_register; } return 0; err_register: - platform_device_unregister_children(to_platform_device(ipu->dev)); + platform_device_unregister_children(to_platform_device(dev)); return ret; } diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index d70e9119e906..00867190413c 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -465,6 +465,7 @@ int iscsit_del_np(struct iscsi_np *np) */ send_sig(SIGINT, np->np_thread, 1); kthread_stop(np->np_thread); + np->np_thread = NULL; } np->np_transport->iscsit_free_np(np); @@ -823,24 +824,22 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, if (((hdr->flags & ISCSI_FLAG_CMD_READ) || (hdr->flags & ISCSI_FLAG_CMD_WRITE)) && !hdr->data_length) { /* - * Vmware ESX v3.0 uses a modified Cisco Initiator (v3.4.2) - * that adds support for RESERVE/RELEASE. There is a bug - * add with this new functionality that sets R/W bits when - * neither CDB carries any READ or WRITE datapayloads. + * From RFC-3720 Section 10.3.1: + * + * "Either or both of R and W MAY be 1 when either the + * Expected Data Transfer Length and/or Bidirectional Read + * Expected Data Transfer Length are 0" + * + * For this case, go ahead and clear the unnecssary bits + * to avoid any confusion with ->data_direction. */ - if ((hdr->cdb[0] == 0x16) || (hdr->cdb[0] == 0x17)) { - hdr->flags &= ~ISCSI_FLAG_CMD_READ; - hdr->flags &= ~ISCSI_FLAG_CMD_WRITE; - goto done; - } + hdr->flags &= ~ISCSI_FLAG_CMD_READ; + hdr->flags &= ~ISCSI_FLAG_CMD_WRITE; - pr_err("ISCSI_FLAG_CMD_READ or ISCSI_FLAG_CMD_WRITE" + pr_warn("ISCSI_FLAG_CMD_READ or ISCSI_FLAG_CMD_WRITE" " set when Expected Data Transfer Length is 0 for" - " CDB: 0x%02x. Bad iSCSI Initiator.\n", hdr->cdb[0]); - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_BOOKMARK_INVALID, buf); + " CDB: 0x%02x, Fixing up flags\n", hdr->cdb[0]); } -done: if (!(hdr->flags & ISCSI_FLAG_CMD_READ) && !(hdr->flags & ISCSI_FLAG_CMD_WRITE) && (hdr->data_length != 0)) { diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index e3318edb233d..1c0088fe9e99 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -474,7 +474,8 @@ static ssize_t __iscsi_##prefix##_store_##name( \ \ if (!capable(CAP_SYS_ADMIN)) \ return -EPERM; \ - \ + if (count >= sizeof(auth->name)) \ + return -EINVAL; \ snprintf(auth->name, sizeof(auth->name), "%s", page); \ if (!strncmp("NULL", auth->name, 4)) \ auth->naf_flags &= ~flags; \ diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 4eb93b2b6473..e29279e6b577 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -1403,11 +1403,6 @@ old_sess_out: out: stop = kthread_should_stop(); - if (!stop && signal_pending(current)) { - spin_lock_bh(&np->np_thread_lock); - stop = (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN); - spin_unlock_bh(&np->np_thread_lock); - } /* Wait for another socket.. */ if (!stop) return 1; @@ -1415,7 +1410,6 @@ exit: iscsi_stop_login_thread_timer(np); spin_lock_bh(&np->np_thread_lock); np->np_thread_state = ISCSI_NP_THREAD_EXIT; - np->np_thread = NULL; spin_unlock_bh(&np->np_thread_lock); return 0; diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 207b340498a3..d06de84b069b 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -1106,6 +1106,11 @@ int se_dev_set_block_size(struct se_device *dev, u32 block_size) dev->dev_attrib.block_size = block_size; pr_debug("dev[%p]: SE Device block_size changed to %u\n", dev, block_size); + + if (dev->dev_attrib.max_bytes_per_io) + dev->dev_attrib.hw_max_sectors = + dev->dev_attrib.max_bytes_per_io / block_size; + return 0; } diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 0e34cda3271e..78241a53b555 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -66,9 +66,8 @@ static int fd_attach_hba(struct se_hba *hba, u32 host_id) pr_debug("CORE_HBA[%d] - TCM FILEIO HBA Driver %s on Generic" " Target Core Stack %s\n", hba->hba_id, FD_VERSION, TARGET_CORE_MOD_VERSION); - pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic" - " MaxSectors: %u\n", - hba->hba_id, fd_host->fd_host_id, FD_MAX_SECTORS); + pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic\n", + hba->hba_id, fd_host->fd_host_id); return 0; } @@ -220,7 +219,8 @@ static int fd_configure_device(struct se_device *dev) } dev->dev_attrib.hw_block_size = fd_dev->fd_block_size; - dev->dev_attrib.hw_max_sectors = FD_MAX_SECTORS; + dev->dev_attrib.max_bytes_per_io = FD_MAX_BYTES; + dev->dev_attrib.hw_max_sectors = FD_MAX_BYTES / fd_dev->fd_block_size; dev->dev_attrib.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH; if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) { diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h index 37ffc5bd2399..d7772c167685 100644 --- a/drivers/target/target_core_file.h +++ b/drivers/target/target_core_file.h @@ -7,7 +7,10 @@ #define FD_DEVICE_QUEUE_DEPTH 32 #define FD_MAX_DEVICE_QUEUE_DEPTH 128 #define FD_BLOCKSIZE 512 -#define FD_MAX_SECTORS 2048 +/* + * Limited by the number of iovecs (2048) per vfs_[writev,readv] call + */ +#define FD_MAX_BYTES 8388608 #define RRF_EMULATE_CDB 0x01 #define RRF_GOT_LBA 0x02 diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index f697f8baec54..2a573de19a9f 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -278,7 +278,6 @@ struct se_node_acl *core_tpg_check_initiator_node_acl( snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname); acl->se_tpg = tpg; acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX); - spin_lock_init(&acl->stats_lock); acl->dynamic_node_acl = 1; tpg->se_tpg_tfo->set_default_node_attributes(acl); @@ -406,7 +405,6 @@ struct se_node_acl *core_tpg_add_initiator_node_acl( snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname); acl->se_tpg = tpg; acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX); - spin_lock_init(&acl->stats_lock); tpg->se_tpg_tfo->set_default_node_attributes(acl); @@ -658,15 +656,9 @@ static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg) spin_lock_init(&lun->lun_sep_lock); init_completion(&lun->lun_ref_comp); - ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release); - if (ret < 0) - return ret; - ret = core_tpg_post_addlun(se_tpg, lun, lun_access, dev); - if (ret < 0) { - percpu_ref_cancel_init(&lun->lun_ref); + if (ret < 0) return ret; - } return 0; } diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 268b62768f2b..34aacaaae14a 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -93,6 +93,7 @@ struct n_tty_data { size_t canon_head; size_t echo_head; size_t echo_commit; + size_t echo_mark; DECLARE_BITMAP(char_map, 256); /* private to n_tty_receive_overrun (single-threaded) */ @@ -336,6 +337,7 @@ static void reset_buffer_flags(struct n_tty_data *ldata) { ldata->read_head = ldata->canon_head = ldata->read_tail = 0; ldata->echo_head = ldata->echo_tail = ldata->echo_commit = 0; + ldata->echo_mark = 0; ldata->line_start = 0; ldata->erasing = 0; @@ -787,6 +789,7 @@ static void commit_echoes(struct tty_struct *tty) size_t head; head = ldata->echo_head; + ldata->echo_mark = head; old = ldata->echo_commit - ldata->echo_tail; /* Process committed echoes if the accumulated # of bytes @@ -811,10 +814,11 @@ static void process_echoes(struct tty_struct *tty) size_t echoed; if ((!L_ECHO(tty) && !L_ECHONL(tty)) || - ldata->echo_commit == ldata->echo_tail) + ldata->echo_mark == ldata->echo_tail) return; mutex_lock(&ldata->output_lock); + ldata->echo_commit = ldata->echo_mark; echoed = __process_echoes(tty); mutex_unlock(&ldata->output_lock); @@ -822,6 +826,7 @@ static void process_echoes(struct tty_struct *tty) tty->ops->flush_chars(tty); } +/* NB: echo_mark and echo_head should be equivalent here */ static void flush_echoes(struct tty_struct *tty) { struct n_tty_data *ldata = tty->disc_data; diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index 4658e3e0ec42..06525f10e364 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -96,7 +96,8 @@ static void dw8250_serial_out(struct uart_port *p, int offset, int value) if (offset == UART_LCR) { int tries = 1000; while (tries--) { - if (value == p->serial_in(p, UART_LCR)) + unsigned int lcr = p->serial_in(p, UART_LCR); + if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR)) return; dw8250_force_idle(p); writeb(value, p->membase + (UART_LCR << p->regshift)); @@ -132,7 +133,8 @@ static void dw8250_serial_out32(struct uart_port *p, int offset, int value) if (offset == UART_LCR) { int tries = 1000; while (tries--) { - if (value == p->serial_in(p, UART_LCR)) + unsigned int lcr = p->serial_in(p, UART_LCR); + if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR)) return; dw8250_force_idle(p); writel(value, p->membase + (UART_LCR << p->regshift)); @@ -455,6 +457,8 @@ MODULE_DEVICE_TABLE(of, dw8250_of_match); static const struct acpi_device_id dw8250_acpi_match[] = { { "INT33C4", 0 }, { "INT33C5", 0 }, + { "INT3434", 0 }, + { "INT3435", 0 }, { "80860F0A", 0 }, { }, }; diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index e46e9f3f19b9..f619ad5b5eae 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -240,6 +240,7 @@ static irqreturn_t xuartps_isr(int irq, void *dev_id) continue; } +#ifdef SUPPORT_SYSRQ /* * uart_handle_sysrq_char() doesn't work if * spinlocked, for some reason @@ -253,6 +254,7 @@ static irqreturn_t xuartps_isr(int irq, void *dev_id) } spin_lock(&port->lock); } +#endif port->icount.rx++; diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c index 22fad8ad5ac2..d8a55e87877f 100644 --- a/drivers/tty/tty_ldsem.c +++ b/drivers/tty/tty_ldsem.c @@ -86,11 +86,21 @@ static inline long ldsem_atomic_update(long delta, struct ld_semaphore *sem) return atomic_long_add_return(delta, (atomic_long_t *)&sem->count); } +/* + * ldsem_cmpxchg() updates @*old with the last-known sem->count value. + * Returns 1 if count was successfully changed; @*old will have @new value. + * Returns 0 if count was not changed; @*old will have most recent sem->count + */ static inline int ldsem_cmpxchg(long *old, long new, struct ld_semaphore *sem) { - long tmp = *old; - *old = atomic_long_cmpxchg(&sem->count, *old, new); - return *old == tmp; + long tmp = atomic_long_cmpxchg(&sem->count, *old, new); + if (tmp == *old) { + *old = new; + return 1; + } else { + *old = tmp; + return 0; + } } /* diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 5d8981c5235e..6e73f8cd60e5 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -642,6 +642,10 @@ static int ci_hdrc_probe(struct platform_device *pdev) : CI_ROLE_GADGET; } + /* only update vbus status for peripheral */ + if (ci->role == CI_ROLE_GADGET) + ci_handle_vbus_change(ci); + ret = ci_role_start(ci, ci->role); if (ret) { dev_err(dev, "can't start %s role\n", ci_role(ci)->name); diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c index 59e6020ea753..526cd77563d8 100644 --- a/drivers/usb/chipidea/host.c +++ b/drivers/usb/chipidea/host.c @@ -88,7 +88,8 @@ static int host_start(struct ci_hdrc *ci) return ret; disable_reg: - regulator_disable(ci->platdata->reg_vbus); + if (ci->platdata->reg_vbus) + regulator_disable(ci->platdata->reg_vbus); put_hcd: usb_put_hcd(hcd); diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index b34c81969cba..69d20fbb38a2 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1795,9 +1795,6 @@ static int udc_start(struct ci_hdrc *ci) pm_runtime_no_callbacks(&ci->gadget.dev); pm_runtime_enable(&ci->gadget.dev); - /* Update ci->vbus_active */ - ci_handle_vbus_change(ci); - return retval; destroy_eps: diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 4d387596f3f0..0b23a8639311 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -854,13 +854,11 @@ static int wdm_manage_power(struct usb_interface *intf, int on) { /* need autopm_get/put here to ensure the usbcore sees the new value */ int rv = usb_autopm_get_interface(intf); - if (rv < 0) - goto err; intf->needs_remote_wakeup = on; - usb_autopm_put_interface(intf); -err: - return rv; + if (!rv) + usb_autopm_put_interface(intf); + return 0; } static int wdm_probe(struct usb_interface *intf, const struct usb_device_id *id) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 74f9cf02da07..a49217ae3533 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -455,9 +455,6 @@ static int dwc3_probe(struct platform_device *pdev) if (IS_ERR(regs)) return PTR_ERR(regs); - usb_phy_set_suspend(dwc->usb2_phy, 0); - usb_phy_set_suspend(dwc->usb3_phy, 0); - spin_lock_init(&dwc->lock); platform_set_drvdata(pdev, dwc); @@ -488,6 +485,9 @@ static int dwc3_probe(struct platform_device *pdev) goto err0; } + usb_phy_set_suspend(dwc->usb2_phy, 0); + usb_phy_set_suspend(dwc->usb3_phy, 0); + ret = dwc3_event_buffers_setup(dwc); if (ret) { dev_err(dwc->dev, "failed to setup event buffers\n"); @@ -569,6 +569,8 @@ err2: dwc3_event_buffers_cleanup(dwc); err1: + usb_phy_set_suspend(dwc->usb2_phy, 1); + usb_phy_set_suspend(dwc->usb3_phy, 1); dwc3_core_exit(dwc); err0: diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index 418444ebb1b8..8c356af79409 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -136,23 +136,27 @@ static int usb_hcd_at91_probe(const struct hc_driver *driver, struct ohci_hcd *ohci; int retval; struct usb_hcd *hcd = NULL; - - if (pdev->num_resources != 2) { - pr_debug("hcd probe: invalid num_resources"); - return -ENODEV; + struct device *dev = &pdev->dev; + struct resource *res; + int irq; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_dbg(dev, "hcd probe: missing memory resource\n"); + return -ENXIO; } - if ((pdev->resource[0].flags != IORESOURCE_MEM) - || (pdev->resource[1].flags != IORESOURCE_IRQ)) { - pr_debug("hcd probe: invalid resource type\n"); - return -ENODEV; + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_dbg(dev, "hcd probe: missing irq resource\n"); + return irq; } hcd = usb_create_hcd(driver, &pdev->dev, "at91"); if (!hcd) return -ENOMEM; - hcd->rsrc_start = pdev->resource[0].start; - hcd->rsrc_len = resource_size(&pdev->resource[0]); + hcd->rsrc_start = res->start; + hcd->rsrc_len = resource_size(res); if (!request_mem_region(hcd->rsrc_start, hcd->rsrc_len, hcd_name)) { pr_debug("request_mem_region failed\n"); @@ -199,7 +203,7 @@ static int usb_hcd_at91_probe(const struct hc_driver *driver, ohci->num_ports = board->ports; at91_start_hc(pdev); - retval = usb_add_hcd(hcd, pdev->resource[1].start, IRQF_SHARED); + retval = usb_add_hcd(hcd, irq, IRQF_SHARED); if (retval == 0) return retval; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index b8dffd59eb25..73f5208714a4 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -128,7 +128,12 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) * any other sleep) on Haswell machines with LPT and LPT-LP * with the new Intel BIOS */ - xhci->quirks |= XHCI_SPURIOUS_WAKEUP; + /* Limit the quirk to only known vendors, as this triggers + * yet another BIOS bug on some other machines + * https://bugzilla.kernel.org/show_bug.cgi?id=66171 + */ + if (pdev->subsystem_vendor == PCI_VENDOR_ID_HP) + xhci->quirks |= XHCI_SPURIOUS_WAKEUP; } if (pdev->vendor == PCI_VENDOR_ID_ETRON && pdev->device == PCI_DEVICE_ID_ASROCK_P67) { diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig index 08e2f39027ec..2b41c636a52a 100644 --- a/drivers/usb/phy/Kconfig +++ b/drivers/usb/phy/Kconfig @@ -19,8 +19,9 @@ config AB8500_USB in host mode, low speed. config FSL_USB2_OTG - bool "Freescale USB OTG Transceiver Driver" + tristate "Freescale USB OTG Transceiver Driver" depends on USB_EHCI_FSL && USB_FSL_USB2 && PM_RUNTIME + depends on USB select USB_OTG select USB_PHY help @@ -29,6 +30,7 @@ config FSL_USB2_OTG config ISP1301_OMAP tristate "Philips ISP1301 with OMAP OTG" depends on I2C && ARCH_OMAP_OTG + depends on USB select USB_PHY help If you say yes here you get support for the Philips ISP1301 diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index 82232acf1ab6..bbe4f8e6e8d7 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -876,7 +876,7 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, tegra_phy->pad_regs = devm_ioremap(&pdev->dev, res->start, resource_size(res)); - if (!tegra_phy->regs) { + if (!tegra_phy->pad_regs) { dev_err(&pdev->dev, "Failed to remap UTMI Pad regs\n"); return -ENOMEM; } diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c index 30e8a61552d4..bad57ce77ba5 100644 --- a/drivers/usb/phy/phy-twl6030-usb.c +++ b/drivers/usb/phy/phy-twl6030-usb.c @@ -127,7 +127,8 @@ static inline int twl6030_writeb(struct twl6030_usb *twl, u8 module, static inline u8 twl6030_readb(struct twl6030_usb *twl, u8 module, u8 address) { - u8 data, ret = 0; + u8 data; + int ret; ret = twl_i2c_read_u8(module, &data, address); if (ret >= 0) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 496b7e39d5be..cc7a24154490 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -251,6 +251,7 @@ static void option_instat_callback(struct urb *urb); #define ZTE_PRODUCT_MF628 0x0015 #define ZTE_PRODUCT_MF626 0x0031 #define ZTE_PRODUCT_MC2718 0xffe8 +#define ZTE_PRODUCT_AC2726 0xfff1 #define BENQ_VENDOR_ID 0x04a5 #define BENQ_PRODUCT_H10 0x4068 @@ -1453,6 +1454,7 @@ static const struct usb_device_id option_ids[] = { { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) }, { USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) }, { USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) }, { USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) }, diff --git a/drivers/usb/serial/zte_ev.c b/drivers/usb/serial/zte_ev.c index fca4c752a4ed..eae2c873b39f 100644 --- a/drivers/usb/serial/zte_ev.c +++ b/drivers/usb/serial/zte_ev.c @@ -281,8 +281,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x19d2, 0xfffd) }, { USB_DEVICE(0x19d2, 0xfffc) }, { USB_DEVICE(0x19d2, 0xfffb) }, - /* AC2726, AC8710_V3 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfff1, 0xff, 0xff, 0xff) }, + /* AC8710_V3 */ { USB_DEVICE(0x19d2, 0xfff6) }, { USB_DEVICE(0x19d2, 0xfff7) }, { USB_DEVICE(0x19d2, 0xfff8) }, diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 55ea73f7c70b..4c02e2b94103 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -350,17 +350,19 @@ static enum bp_state increase_reservation(unsigned long nr_pages) pfn = page_to_pfn(page); - set_phys_to_machine(pfn, frame_list[i]); - #ifdef CONFIG_XEN_HAVE_PVMMU - /* Link back into the page tables if not highmem. */ - if (xen_pv_domain() && !PageHighMem(page)) { - int ret; - ret = HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - mfn_pte(frame_list[i], PAGE_KERNEL), - 0); - BUG_ON(ret); + if (!xen_feature(XENFEAT_auto_translated_physmap)) { + set_phys_to_machine(pfn, frame_list[i]); + + /* Link back into the page tables if not highmem. */ + if (!PageHighMem(page)) { + int ret; + ret = HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + mfn_pte(frame_list[i], PAGE_KERNEL), + 0); + BUG_ON(ret); + } } #endif @@ -378,7 +380,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) enum bp_state state = BP_DONE; unsigned long pfn, i; struct page *page; - struct page *scratch_page; int ret; struct xen_memory_reservation reservation = { .address_bits = 0, @@ -411,27 +412,29 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) scrub_page(page); +#ifdef CONFIG_XEN_HAVE_PVMMU /* * Ballooned out frames are effectively replaced with * a scratch frame. Ensure direct mappings and the * p2m are consistent. */ - scratch_page = get_balloon_scratch_page(); -#ifdef CONFIG_XEN_HAVE_PVMMU - if (xen_pv_domain() && !PageHighMem(page)) { - ret = HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - pfn_pte(page_to_pfn(scratch_page), - PAGE_KERNEL_RO), 0); - BUG_ON(ret); - } -#endif if (!xen_feature(XENFEAT_auto_translated_physmap)) { unsigned long p; + struct page *scratch_page = get_balloon_scratch_page(); + + if (!PageHighMem(page)) { + ret = HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + pfn_pte(page_to_pfn(scratch_page), + PAGE_KERNEL_RO), 0); + BUG_ON(ret); + } p = page_to_pfn(scratch_page); __set_phys_to_machine(pfn, pfn_to_mfn(p)); + + put_balloon_scratch_page(); } - put_balloon_scratch_page(); +#endif balloon_append(pfn_to_page(pfn)); } @@ -627,15 +630,17 @@ static int __init balloon_init(void) if (!xen_domain()) return -ENODEV; - for_each_online_cpu(cpu) - { - per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL); - if (per_cpu(balloon_scratch_page, cpu) == NULL) { - pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu); - return -ENOMEM; + if (!xen_feature(XENFEAT_auto_translated_physmap)) { + for_each_online_cpu(cpu) + { + per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL); + if (per_cpu(balloon_scratch_page, cpu) == NULL) { + pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu); + return -ENOMEM; + } } + register_cpu_notifier(&balloon_cpu_notifier); } - register_cpu_notifier(&balloon_cpu_notifier); pr_info("Initialising balloon driver\n"); diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 028387192b60..aa846a48f400 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -1176,7 +1176,8 @@ static int gnttab_setup(void) gnttab_shared.addr = xen_remap(xen_hvm_resume_frames, PAGE_SIZE * max_nr_gframes); if (gnttab_shared.addr == NULL) { - pr_warn("Failed to ioremap gnttab share frames!\n"); + pr_warn("Failed to ioremap gnttab share frames (addr=0x%08lx)!\n", + xen_hvm_resume_frames); return -ENOMEM; } } diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 8e74590fa1bb..569a13b9e856 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -533,12 +533,17 @@ static void privcmd_close(struct vm_area_struct *vma) { struct page **pages = vma->vm_private_data; int numpgs = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + int rc; if (!xen_feature(XENFEAT_auto_translated_physmap) || !numpgs || !pages) return; - xen_unmap_domain_mfn_range(vma, numpgs, pages); - free_xenballooned_pages(numpgs, pages); + rc = xen_unmap_domain_mfn_range(vma, numpgs, pages); + if (rc == 0) + free_xenballooned_pages(numpgs, pages); + else + pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n", + numpgs, rc); kfree(pages); } @@ -244,9 +244,14 @@ static void aio_free_ring(struct kioctx *ctx) int i; for (i = 0; i < ctx->nr_pages; i++) { + struct page *page; pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i, page_count(ctx->ring_pages[i])); - put_page(ctx->ring_pages[i]); + page = ctx->ring_pages[i]; + if (!page) + continue; + ctx->ring_pages[i] = NULL; + put_page(page); } put_aio_ring_file(ctx); @@ -280,18 +285,38 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, unsigned long flags; int rc; + rc = 0; + + /* Make sure the old page hasn't already been changed */ + spin_lock(&mapping->private_lock); + ctx = mapping->private_data; + if (ctx) { + pgoff_t idx; + spin_lock_irqsave(&ctx->completion_lock, flags); + idx = old->index; + if (idx < (pgoff_t)ctx->nr_pages) { + if (ctx->ring_pages[idx] != old) + rc = -EAGAIN; + } else + rc = -EINVAL; + spin_unlock_irqrestore(&ctx->completion_lock, flags); + } else + rc = -EINVAL; + spin_unlock(&mapping->private_lock); + + if (rc != 0) + return rc; + /* Writeback must be complete */ BUG_ON(PageWriteback(old)); - put_page(old); + get_page(new); - rc = migrate_page_move_mapping(mapping, new, old, NULL, mode); + rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1); if (rc != MIGRATEPAGE_SUCCESS) { - get_page(old); + put_page(new); return rc; } - get_page(new); - /* We can potentially race against kioctx teardown here. Use the * address_space's private data lock to protect the mapping's * private_data. @@ -303,13 +328,24 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, spin_lock_irqsave(&ctx->completion_lock, flags); migrate_page_copy(new, old); idx = old->index; - if (idx < (pgoff_t)ctx->nr_pages) - ctx->ring_pages[idx] = new; + if (idx < (pgoff_t)ctx->nr_pages) { + /* And only do the move if things haven't changed */ + if (ctx->ring_pages[idx] == old) + ctx->ring_pages[idx] = new; + else + rc = -EAGAIN; + } else + rc = -EINVAL; spin_unlock_irqrestore(&ctx->completion_lock, flags); } else rc = -EBUSY; spin_unlock(&mapping->private_lock); + if (rc == MIGRATEPAGE_SUCCESS) + put_page(old); + else + put_page(new); + return rc; } #endif @@ -326,7 +362,7 @@ static int aio_setup_ring(struct kioctx *ctx) struct aio_ring *ring; unsigned nr_events = ctx->max_reqs; struct mm_struct *mm = current->mm; - unsigned long size, populate; + unsigned long size, unused; int nr_pages; int i; struct file *file; @@ -347,6 +383,20 @@ static int aio_setup_ring(struct kioctx *ctx) return -EAGAIN; } + ctx->aio_ring_file = file; + nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) + / sizeof(struct io_event); + + ctx->ring_pages = ctx->internal_pages; + if (nr_pages > AIO_RING_PAGES) { + ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), + GFP_KERNEL); + if (!ctx->ring_pages) { + put_aio_ring_file(ctx); + return -ENOMEM; + } + } + for (i = 0; i < nr_pages; i++) { struct page *page; page = find_or_create_page(file->f_inode->i_mapping, @@ -358,19 +408,14 @@ static int aio_setup_ring(struct kioctx *ctx) SetPageUptodate(page); SetPageDirty(page); unlock_page(page); + + ctx->ring_pages[i] = page; } - ctx->aio_ring_file = file; - nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) - / sizeof(struct io_event); + ctx->nr_pages = i; - ctx->ring_pages = ctx->internal_pages; - if (nr_pages > AIO_RING_PAGES) { - ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), - GFP_KERNEL); - if (!ctx->ring_pages) { - put_aio_ring_file(ctx); - return -ENOMEM; - } + if (unlikely(i != nr_pages)) { + aio_free_ring(ctx); + return -EAGAIN; } ctx->mmap_size = nr_pages * PAGE_SIZE; @@ -379,9 +424,9 @@ static int aio_setup_ring(struct kioctx *ctx) down_write(&mm->mmap_sem); ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, 0, &populate); + MAP_SHARED, 0, &unused); + up_write(&mm->mmap_sem); if (IS_ERR((void *)ctx->mmap_base)) { - up_write(&mm->mmap_sem); ctx->mmap_size = 0; aio_free_ring(ctx); return -EAGAIN; @@ -389,27 +434,6 @@ static int aio_setup_ring(struct kioctx *ctx) pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base); - /* We must do this while still holding mmap_sem for write, as we - * need to be protected against userspace attempting to mremap() - * or munmap() the ring buffer. - */ - ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages, - 1, 0, ctx->ring_pages, NULL); - - /* Dropping the reference here is safe as the page cache will hold - * onto the pages for us. It is also required so that page migration - * can unmap the pages and get the right reference count. - */ - for (i = 0; i < ctx->nr_pages; i++) - put_page(ctx->ring_pages[i]); - - up_write(&mm->mmap_sem); - - if (unlikely(ctx->nr_pages != nr_pages)) { - aio_free_ring(ctx); - return -EAGAIN; - } - ctx->user_id = ctx->mmap_base; ctx->nr_events = nr_events; /* trusted copy */ @@ -652,7 +676,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) aio_nr += ctx->max_reqs; spin_unlock(&aio_nr_lock); - percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */ + percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */ + percpu_ref_get(&ctx->reqs); /* free_ioctx_users() will drop this */ err = ioctx_add_table(ctx, mm); if (err) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 1e561c059539..ec3ba43b9faa 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page) if (err < 0) { SetPageError(page); goto out; - } else if (err < PAGE_CACHE_SIZE) { + } else { + if (err < PAGE_CACHE_SIZE) { /* zero fill remainder of page */ - zero_user_segment(page, err, PAGE_CACHE_SIZE); + zero_user_segment(page, err, PAGE_CACHE_SIZE); + } else { + flush_dcache_page(page); + } } SetPageUptodate(page); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 9a8e396aed89..278fd2891288 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -978,7 +978,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, struct ceph_mds_reply_inode *ininfo; struct ceph_vino vino; struct ceph_fs_client *fsc = ceph_sb_to_client(sb); - int i = 0; int err = 0; dout("fill_trace %p is_dentry %d is_target %d\n", req, @@ -1039,6 +1038,29 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, } } + if (rinfo->head->is_target) { + vino.ino = le64_to_cpu(rinfo->targeti.in->ino); + vino.snap = le64_to_cpu(rinfo->targeti.in->snapid); + + in = ceph_get_inode(sb, vino); + if (IS_ERR(in)) { + err = PTR_ERR(in); + goto done; + } + req->r_target_inode = in; + + err = fill_inode(in, &rinfo->targeti, NULL, + session, req->r_request_started, + (le32_to_cpu(rinfo->head->result) == 0) ? + req->r_fmode : -1, + &req->r_caps_reservation); + if (err < 0) { + pr_err("fill_inode badness %p %llx.%llx\n", + in, ceph_vinop(in)); + goto done; + } + } + /* * ignore null lease/binding on snapdir ENOENT, or else we * will have trouble splicing in the virtual snapdir later @@ -1108,7 +1130,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, ceph_dentry(req->r_old_dentry)->offset); dn = req->r_old_dentry; /* use old_dentry */ - in = dn->d_inode; } /* null dentry? */ @@ -1130,44 +1151,28 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, } /* attach proper inode */ - ininfo = rinfo->targeti.in; - vino.ino = le64_to_cpu(ininfo->ino); - vino.snap = le64_to_cpu(ininfo->snapid); - in = dn->d_inode; - if (!in) { - in = ceph_get_inode(sb, vino); - if (IS_ERR(in)) { - pr_err("fill_trace bad get_inode " - "%llx.%llx\n", vino.ino, vino.snap); - err = PTR_ERR(in); - d_drop(dn); - goto done; - } + if (!dn->d_inode) { + ihold(in); dn = splice_dentry(dn, in, &have_lease, true); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; } req->r_dentry = dn; /* may have spliced */ - ihold(in); - } else if (ceph_ino(in) == vino.ino && - ceph_snap(in) == vino.snap) { - ihold(in); - } else { + } else if (dn->d_inode && dn->d_inode != in) { dout(" %p links to %p %llx.%llx, not %llx.%llx\n", - dn, in, ceph_ino(in), ceph_snap(in), - vino.ino, vino.snap); + dn, dn->d_inode, ceph_vinop(dn->d_inode), + ceph_vinop(in)); have_lease = false; - in = NULL; } if (have_lease) update_dentry_lease(dn, rinfo->dlease, session, req->r_request_started); dout(" final dn %p\n", dn); - i++; - } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP || - req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) { + } else if (!req->r_aborted && + (req->r_op == CEPH_MDS_OP_LOOKUPSNAP || + req->r_op == CEPH_MDS_OP_MKSNAP)) { struct dentry *dn = req->r_dentry; /* fill out a snapdir LOOKUPSNAP dentry */ @@ -1177,52 +1182,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, ininfo = rinfo->targeti.in; vino.ino = le64_to_cpu(ininfo->ino); vino.snap = le64_to_cpu(ininfo->snapid); - in = ceph_get_inode(sb, vino); - if (IS_ERR(in)) { - pr_err("fill_inode get_inode badness %llx.%llx\n", - vino.ino, vino.snap); - err = PTR_ERR(in); - d_delete(dn); - goto done; - } dout(" linking snapped dir %p to dn %p\n", in, dn); + ihold(in); dn = splice_dentry(dn, in, NULL, true); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; } req->r_dentry = dn; /* may have spliced */ - ihold(in); - rinfo->head->is_dentry = 1; /* fool notrace handlers */ - } - - if (rinfo->head->is_target) { - vino.ino = le64_to_cpu(rinfo->targeti.in->ino); - vino.snap = le64_to_cpu(rinfo->targeti.in->snapid); - - if (in == NULL || ceph_ino(in) != vino.ino || - ceph_snap(in) != vino.snap) { - in = ceph_get_inode(sb, vino); - if (IS_ERR(in)) { - err = PTR_ERR(in); - goto done; - } - } - req->r_target_inode = in; - - err = fill_inode(in, - &rinfo->targeti, NULL, - session, req->r_request_started, - (le32_to_cpu(rinfo->head->result) == 0) ? - req->r_fmode : -1, - &req->r_caps_reservation); - if (err < 0) { - pr_err("fill_inode badness %p %llx.%llx\n", - in, ceph_vinop(in)); - goto done; - } } - done: dout("fill_trace done err=%d\n", err); return err; @@ -1272,7 +1240,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, struct qstr dname; struct dentry *dn; struct inode *in; - int err = 0, i; + int err = 0, ret, i; struct inode *snapdir = NULL; struct ceph_mds_request_head *rhead = req->r_request->front.iov_base; struct ceph_dentry_info *di; @@ -1305,6 +1273,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir); } + /* FIXME: release caps/leases if error occurs */ for (i = 0; i < rinfo->dir_nr; i++) { struct ceph_vino vino; @@ -1329,9 +1298,10 @@ retry_lookup: err = -ENOMEM; goto out; } - err = ceph_init_dentry(dn); - if (err < 0) { + ret = ceph_init_dentry(dn); + if (ret < 0) { dput(dn); + err = ret; goto out; } } else if (dn->d_inode && @@ -1351,9 +1321,6 @@ retry_lookup: spin_unlock(&parent->d_lock); } - di = dn->d_fsdata; - di->offset = ceph_make_fpos(frag, i + r_readdir_offset); - /* inode */ if (dn->d_inode) { in = dn->d_inode; @@ -1366,26 +1333,39 @@ retry_lookup: err = PTR_ERR(in); goto out; } - dn = splice_dentry(dn, in, NULL, false); - if (IS_ERR(dn)) - dn = NULL; } if (fill_inode(in, &rinfo->dir_in[i], NULL, session, req->r_request_started, -1, &req->r_caps_reservation) < 0) { pr_err("fill_inode badness on %p\n", in); + if (!dn->d_inode) + iput(in); + d_drop(dn); goto next_item; } - if (dn) - update_dentry_lease(dn, rinfo->dir_dlease[i], - req->r_session, - req->r_request_started); + + if (!dn->d_inode) { + dn = splice_dentry(dn, in, NULL, false); + if (IS_ERR(dn)) { + err = PTR_ERR(dn); + dn = NULL; + goto next_item; + } + } + + di = dn->d_fsdata; + di->offset = ceph_make_fpos(frag, i + r_readdir_offset); + + update_dentry_lease(dn, rinfo->dir_dlease[i], + req->r_session, + req->r_request_started); next_item: if (dn) dput(dn); } - req->r_did_prepopulate = true; + if (err == 0) + req->r_did_prepopulate = true; out: if (snapdir) { diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index b8e93a40a5d3..78c3c2097787 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -443,8 +443,11 @@ int pstore_register(struct pstore_info *psi) pstore_get_records(0); kmsg_dump_register(&pstore_dumper); - pstore_register_console(); - pstore_register_ftrace(); + + if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) { + pstore_register_console(); + pstore_register_ftrace(); + } if (pstore_update_ms >= 0) { pstore_timer.expires = jiffies + diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index b94f93685093..35e7d08fe629 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -609,7 +609,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file) struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; struct sysfs_open_file *of; - bool has_read, has_write, has_mmap; + bool has_read, has_write; int error = -EACCES; /* need attr_sd for attr and ops, its parent for kobj */ @@ -621,7 +621,6 @@ static int sysfs_open_file(struct inode *inode, struct file *file) has_read = battr->read || battr->mmap; has_write = battr->write || battr->mmap; - has_mmap = battr->mmap; } else { const struct sysfs_ops *ops = sysfs_file_ops(attr_sd); @@ -633,7 +632,6 @@ static int sysfs_open_file(struct inode *inode, struct file *file) has_read = ops->show; has_write = ops->store; - has_mmap = false; } /* check perms and supported operations */ @@ -661,9 +659,9 @@ static int sysfs_open_file(struct inode *inode, struct file *file) * open file has a separate mutex, it's okay as long as those don't * happen on the same file. At this point, we can't easily give * each file a separate locking class. Let's differentiate on - * whether the file has mmap or not for now. + * whether the file is bin or not for now. */ - if (has_mmap) + if (sysfs_is_bin(attr_sd)) mutex_init(&of->mutex); else mutex_init(&of->mutex); diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 3ef11b22e750..3b2c14b6f0fb 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -1635,7 +1635,7 @@ xfs_bmap_last_extent( * blocks at the end of the file which do not start at the previous data block, * we will try to align the new blocks at stripe unit boundaries. * - * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be + * Returns 1 in bma->aeof if the file (fork) is empty as any new write will be * at, or past the EOF. */ STATIC int @@ -1650,9 +1650,14 @@ xfs_bmap_isaeof( bma->aeof = 0; error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec, &is_empty); - if (error || is_empty) + if (error) return error; + if (is_empty) { + bma->aeof = 1; + return 0; + } + /* * Check if we are allocation or past the last extent, or at least into * the last delayed allocated extent. @@ -3643,10 +3648,19 @@ xfs_bmap_btalloc( int isaligned; int tryagain; int error; + int stripe_align; ASSERT(ap->length); mp = ap->ip->i_mount; + + /* stripe alignment for allocation is determined by mount parameters */ + stripe_align = 0; + if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC)) + stripe_align = mp->m_swidth; + else if (mp->m_dalign) + stripe_align = mp->m_dalign; + align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0; if (unlikely(align)) { error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, @@ -3655,6 +3669,8 @@ xfs_bmap_btalloc( ASSERT(!error); ASSERT(ap->length); } + + nullfb = *ap->firstblock == NULLFSBLOCK; fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock); if (nullfb) { @@ -3730,7 +3746,7 @@ xfs_bmap_btalloc( */ if (!ap->flist->xbf_low && ap->aeof) { if (!ap->offset) { - args.alignment = mp->m_dalign; + args.alignment = stripe_align; atype = args.type; isaligned = 1; /* @@ -3755,13 +3771,13 @@ xfs_bmap_btalloc( * of minlen+alignment+slop doesn't go up * between the calls. */ - if (blen > mp->m_dalign && blen <= args.maxlen) - nextminlen = blen - mp->m_dalign; + if (blen > stripe_align && blen <= args.maxlen) + nextminlen = blen - stripe_align; else nextminlen = args.minlen; - if (nextminlen + mp->m_dalign > args.minlen + 1) + if (nextminlen + stripe_align > args.minlen + 1) args.minalignslop = - nextminlen + mp->m_dalign - + nextminlen + stripe_align - args.minlen - 1; else args.minalignslop = 0; @@ -3783,7 +3799,7 @@ xfs_bmap_btalloc( */ args.type = atype; args.fsbno = ap->blkno; - args.alignment = mp->m_dalign; + args.alignment = stripe_align; args.minlen = nextminlen; args.minalignslop = 0; isaligned = 1; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 5887e41c0323..1394106ed22d 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1187,7 +1187,12 @@ xfs_zero_remaining_bytes( XFS_BUF_UNWRITE(bp); XFS_BUF_READ(bp); XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock)); - xfsbdstrat(mp, bp); + + if (XFS_FORCED_SHUTDOWN(mp)) { + error = XFS_ERROR(EIO); + break; + } + xfs_buf_iorequest(bp); error = xfs_buf_iowait(bp); if (error) { xfs_buf_ioerror_alert(bp, @@ -1200,7 +1205,12 @@ xfs_zero_remaining_bytes( XFS_BUF_UNDONE(bp); XFS_BUF_UNREAD(bp); XFS_BUF_WRITE(bp); - xfsbdstrat(mp, bp); + + if (XFS_FORCED_SHUTDOWN(mp)) { + error = XFS_ERROR(EIO); + break; + } + xfs_buf_iorequest(bp); error = xfs_buf_iowait(bp); if (error) { xfs_buf_ioerror_alert(bp, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index c7f0b77dcb00..afe7645e4b2b 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -698,7 +698,11 @@ xfs_buf_read_uncached( bp->b_flags |= XBF_READ; bp->b_ops = ops; - xfsbdstrat(target->bt_mount, bp); + if (XFS_FORCED_SHUTDOWN(target->bt_mount)) { + xfs_buf_relse(bp); + return NULL; + } + xfs_buf_iorequest(bp); xfs_buf_iowait(bp); return bp; } @@ -1089,7 +1093,7 @@ xfs_bioerror( * This is meant for userdata errors; metadata bufs come with * iodone functions attached, so that we can track down errors. */ -STATIC int +int xfs_bioerror_relse( struct xfs_buf *bp) { @@ -1152,7 +1156,7 @@ xfs_bwrite( ASSERT(xfs_buf_islocked(bp)); bp->b_flags |= XBF_WRITE; - bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); + bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL); xfs_bdstrat_cb(bp); @@ -1164,25 +1168,6 @@ xfs_bwrite( return error; } -/* - * Wrapper around bdstrat so that we can stop data from going to disk in case - * we are shutting down the filesystem. Typically user data goes thru this - * path; one of the exceptions is the superblock. - */ -void -xfsbdstrat( - struct xfs_mount *mp, - struct xfs_buf *bp) -{ - if (XFS_FORCED_SHUTDOWN(mp)) { - trace_xfs_bdstrat_shut(bp, _RET_IP_); - xfs_bioerror_relse(bp); - return; - } - - xfs_buf_iorequest(bp); -} - STATIC void _xfs_buf_ioend( xfs_buf_t *bp, @@ -1516,6 +1501,12 @@ xfs_wait_buftarg( struct xfs_buf *bp; bp = list_first_entry(&dispose, struct xfs_buf, b_lru); list_del_init(&bp->b_lru); + if (bp->b_flags & XBF_WRITE_FAIL) { + xfs_alert(btp->bt_mount, +"Corruption Alert: Buffer at block 0x%llx had permanent write failures!\n" +"Please run xfs_repair to determine the extent of the problem.", + (long long)bp->b_bn); + } xfs_buf_rele(bp); } if (loop++ != 0) @@ -1799,7 +1790,7 @@ __xfs_buf_delwri_submit( blk_start_plug(&plug); list_for_each_entry_safe(bp, n, io_list, b_list) { - bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC); + bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL); bp->b_flags |= XBF_WRITE; if (!wait) { diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index e65683361017..1cf21a4a9f22 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -45,6 +45,7 @@ typedef enum { #define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ #define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ #define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ +#define XBF_WRITE_FAIL (1 << 24)/* async writes have failed on this buffer */ /* I/O hints for the BIO layer */ #define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ @@ -70,6 +71,7 @@ typedef unsigned int xfs_buf_flags_t; { XBF_ASYNC, "ASYNC" }, \ { XBF_DONE, "DONE" }, \ { XBF_STALE, "STALE" }, \ + { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ { XBF_SYNCIO, "SYNCIO" }, \ { XBF_FUA, "FUA" }, \ { XBF_FLUSH, "FLUSH" }, \ @@ -80,6 +82,7 @@ typedef unsigned int xfs_buf_flags_t; { _XBF_DELWRI_Q, "DELWRI_Q" }, \ { _XBF_COMPOUND, "COMPOUND" } + /* * Internal state flags. */ @@ -269,9 +272,6 @@ extern void xfs_buf_unlock(xfs_buf_t *); /* Buffer Read and Write Routines */ extern int xfs_bwrite(struct xfs_buf *bp); - -extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *); - extern void xfs_buf_ioend(xfs_buf_t *, int); extern void xfs_buf_ioerror(xfs_buf_t *, int); extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func); @@ -282,6 +282,8 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *, #define xfs_buf_zero(bp, off, len) \ xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO) +extern int xfs_bioerror_relse(struct xfs_buf *); + static inline int xfs_buf_geterror(xfs_buf_t *bp) { return bp ? bp->b_error : ENOMEM; @@ -301,7 +303,8 @@ extern void xfs_buf_terminate(void); #define XFS_BUF_ZEROFLAGS(bp) \ ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \ - XBF_SYNCIO|XBF_FUA|XBF_FLUSH)) + XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \ + XBF_WRITE_FAIL)) void xfs_buf_stale(struct xfs_buf *bp); #define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE) diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index a64f67ba25d3..2227b9b050bb 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -496,6 +496,14 @@ xfs_buf_item_unpin( } } +/* + * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30 + * seconds so as to not spam logs too much on repeated detection of the same + * buffer being bad.. + */ + +DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10); + STATIC uint xfs_buf_item_push( struct xfs_log_item *lip, @@ -524,6 +532,14 @@ xfs_buf_item_push( trace_xfs_buf_item_push(bip); + /* has a previous flush failed due to IO errors? */ + if ((bp->b_flags & XBF_WRITE_FAIL) && + ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) { + xfs_warn(bp->b_target->bt_mount, +"Detected failing async write on buffer block 0x%llx. Retrying async write.\n", + (long long)bp->b_bn); + } + if (!xfs_buf_delwri_queue(bp, buffer_list)) rval = XFS_ITEM_FLUSHING; xfs_buf_unlock(bp); @@ -1096,8 +1112,9 @@ xfs_buf_iodone_callbacks( xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */ - if (!XFS_BUF_ISSTALE(bp)) { - bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE; + if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) { + bp->b_flags |= XBF_WRITE | XBF_ASYNC | + XBF_DONE | XBF_WRITE_FAIL; xfs_buf_iorequest(bp); } else { xfs_buf_relse(bp); diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c index 56369d4509d5..48c7d18f68c3 100644 --- a/fs/xfs/xfs_dir2_node.c +++ b/fs/xfs/xfs_dir2_node.c @@ -2067,12 +2067,12 @@ xfs_dir2_node_lookup( */ int /* error */ xfs_dir2_node_removename( - xfs_da_args_t *args) /* operation arguments */ + struct xfs_da_args *args) /* operation arguments */ { - xfs_da_state_blk_t *blk; /* leaf block */ + struct xfs_da_state_blk *blk; /* leaf block */ int error; /* error return value */ int rval; /* operation return value */ - xfs_da_state_t *state; /* btree cursor */ + struct xfs_da_state *state; /* btree cursor */ trace_xfs_dir2_node_removename(args); @@ -2084,19 +2084,18 @@ xfs_dir2_node_removename( state->mp = args->dp->i_mount; state->blocksize = state->mp->m_dirblksize; state->node_ents = state->mp->m_dir_node_ents; - /* - * Look up the entry we're deleting, set up the cursor. - */ + + /* Look up the entry we're deleting, set up the cursor. */ error = xfs_da3_node_lookup_int(state, &rval); if (error) - rval = error; - /* - * Didn't find it, upper layer screwed up. - */ + goto out_free; + + /* Didn't find it, upper layer screwed up. */ if (rval != EEXIST) { - xfs_da_state_free(state); - return rval; + error = rval; + goto out_free; } + blk = &state->path.blk[state->path.active - 1]; ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC); ASSERT(state->extravalid); @@ -2107,7 +2106,7 @@ xfs_dir2_node_removename( error = xfs_dir2_leafn_remove(args, blk->bp, blk->index, &state->extrablk, &rval); if (error) - return error; + goto out_free; /* * Fix the hash values up the btree. */ @@ -2122,6 +2121,7 @@ xfs_dir2_node_removename( */ if (!error) error = xfs_dir2_node_to_leaf(state); +out_free: xfs_da_state_free(state); return error; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 27e0e544e963..104455b8046c 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -618,7 +618,8 @@ xfs_setattr_nonsize( } if (!gid_eq(igid, gid)) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) { - ASSERT(!XFS_IS_PQUOTA_ON(mp)); + ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) || + !XFS_IS_PQUOTA_ON(mp)); ASSERT(mask & ATTR_GID); ASSERT(gdqp); olddquot2 = xfs_qm_vop_chown(tp, ip, diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index b6b669df40f3..eae16920655b 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -193,7 +193,10 @@ xlog_bread_noalign( bp->b_io_length = nbblks; bp->b_error = 0; - xfsbdstrat(log->l_mp, bp); + if (XFS_FORCED_SHUTDOWN(log->l_mp)) + return XFS_ERROR(EIO); + + xfs_buf_iorequest(bp); error = xfs_buf_iowait(bp); if (error) xfs_buf_ioerror_alert(bp, __func__); @@ -4397,7 +4400,13 @@ xlog_do_recover( XFS_BUF_READ(bp); XFS_BUF_UNASYNC(bp); bp->b_ops = &xfs_sb_buf_ops; - xfsbdstrat(log->l_mp, bp); + + if (XFS_FORCED_SHUTDOWN(log->l_mp)) { + xfs_buf_relse(bp); + return XFS_ERROR(EIO); + } + + xfs_buf_iorequest(bp); error = xfs_buf_iowait(bp); if (error) { xfs_buf_ioerror_alert(bp, __func__); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 14a4996cfec6..dd88f0e27bd8 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -134,8 +134,6 @@ xfs_qm_dqpurge( { struct xfs_mount *mp = dqp->q_mount; struct xfs_quotainfo *qi = mp->m_quotainfo; - struct xfs_dquot *gdqp = NULL; - struct xfs_dquot *pdqp = NULL; xfs_dqlock(dqp); if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) { @@ -143,21 +141,6 @@ xfs_qm_dqpurge( return EAGAIN; } - /* - * If this quota has a hint attached, prepare for releasing it now. - */ - gdqp = dqp->q_gdquot; - if (gdqp) { - xfs_dqlock(gdqp); - dqp->q_gdquot = NULL; - } - - pdqp = dqp->q_pdquot; - if (pdqp) { - xfs_dqlock(pdqp); - dqp->q_pdquot = NULL; - } - dqp->dq_flags |= XFS_DQ_FREEING; xfs_dqflock(dqp); @@ -206,11 +189,47 @@ xfs_qm_dqpurge( XFS_STATS_DEC(xs_qm_dquot_unused); xfs_qm_dqdestroy(dqp); + return 0; +} + +/* + * Release the group or project dquot pointers the user dquots maybe carrying + * around as a hint, and proceed to purge the user dquot cache if requested. +*/ +STATIC int +xfs_qm_dqpurge_hints( + struct xfs_dquot *dqp, + void *data) +{ + struct xfs_dquot *gdqp = NULL; + struct xfs_dquot *pdqp = NULL; + uint flags = *((uint *)data); + + xfs_dqlock(dqp); + if (dqp->dq_flags & XFS_DQ_FREEING) { + xfs_dqunlock(dqp); + return EAGAIN; + } + + /* If this quota has a hint attached, prepare for releasing it now */ + gdqp = dqp->q_gdquot; + if (gdqp) + dqp->q_gdquot = NULL; + + pdqp = dqp->q_pdquot; + if (pdqp) + dqp->q_pdquot = NULL; + + xfs_dqunlock(dqp); if (gdqp) - xfs_qm_dqput(gdqp); + xfs_qm_dqrele(gdqp); if (pdqp) - xfs_qm_dqput(pdqp); + xfs_qm_dqrele(pdqp); + + if (flags & XFS_QMOPT_UQUOTA) + return xfs_qm_dqpurge(dqp, NULL); + return 0; } @@ -222,8 +241,18 @@ xfs_qm_dqpurge_all( struct xfs_mount *mp, uint flags) { - if (flags & XFS_QMOPT_UQUOTA) - xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL); + /* + * We have to release group/project dquot hint(s) from the user dquot + * at first if they are there, otherwise we would run into an infinite + * loop while walking through radix tree to purge other type of dquots + * since their refcount is not zero if the user dquot refers to them + * as hint. + * + * Call the special xfs_qm_dqpurge_hints() will end up go through the + * general xfs_qm_dqpurge() against user dquot cache if requested. + */ + xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge_hints, &flags); + if (flags & XFS_QMOPT_GQUOTA) xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL); if (flags & XFS_QMOPT_PQUOTA) @@ -2082,24 +2111,21 @@ xfs_qm_vop_create_dqattach( ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ASSERT(XFS_IS_QUOTA_RUNNING(mp)); - if (udqp) { + if (udqp && XFS_IS_UQUOTA_ON(mp)) { ASSERT(ip->i_udquot == NULL); - ASSERT(XFS_IS_UQUOTA_ON(mp)); ASSERT(ip->i_d.di_uid == be32_to_cpu(udqp->q_core.d_id)); ip->i_udquot = xfs_qm_dqhold(udqp); xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1); } - if (gdqp) { + if (gdqp && XFS_IS_GQUOTA_ON(mp)) { ASSERT(ip->i_gdquot == NULL); - ASSERT(XFS_IS_GQUOTA_ON(mp)); ASSERT(ip->i_d.di_gid == be32_to_cpu(gdqp->q_core.d_id)); ip->i_gdquot = xfs_qm_dqhold(gdqp); xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1); } - if (pdqp) { + if (pdqp && XFS_IS_PQUOTA_ON(mp)) { ASSERT(ip->i_pdquot == NULL); - ASSERT(XFS_IS_PQUOTA_ON(mp)); ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id)); ip->i_pdquot = xfs_qm_dqhold(pdqp); diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index c035d11b7734..647b6f1d8923 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -314,7 +314,18 @@ xfs_trans_read_buf_map( ASSERT(bp->b_iodone == NULL); XFS_BUF_READ(bp); bp->b_ops = ops; - xfsbdstrat(tp->t_mountp, bp); + + /* + * XXX(hch): clean up the error handling here to be less + * of a mess.. + */ + if (XFS_FORCED_SHUTDOWN(mp)) { + trace_xfs_bdstrat_shut(bp, _RET_IP_); + xfs_bioerror_relse(bp); + } else { + xfs_buf_iorequest(bp); + } + error = xfs_buf_iowait(bp); if (error) { xfs_buf_ioerror_alert(bp, __func__); diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f330d28e4d0e..db0923458940 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -217,7 +217,7 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) #endif #ifndef pte_accessible -# define pte_accessible(pte) ((void)(pte),1) +# define pte_accessible(mm, pte) ((void)(pte), 1) #endif #ifndef flush_tlb_fix_spurious_fault @@ -599,11 +599,10 @@ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) #ifdef CONFIG_TRANSPARENT_HUGEPAGE barrier(); #endif - if (pmd_none(pmdval)) + if (pmd_none(pmdval) || pmd_trans_huge(pmdval)) return 1; if (unlikely(pmd_bad(pmdval))) { - if (!pmd_trans_huge(pmdval)) - pmd_clear_bad(pmd); + pmd_clear_bad(pmd); return 1; } return 0; diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h index ddf2b420ac8f..1cd3f5d767a8 100644 --- a/include/asm-generic/preempt.h +++ b/include/asm-generic/preempt.h @@ -3,13 +3,11 @@ #include <linux/thread_info.h> -/* - * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users - * that think a non-zero value indicates we cannot preempt. - */ +#define PREEMPT_ENABLED (0) + static __always_inline int preempt_count(void) { - return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED; + return current_thread_info()->preempt_count; } static __always_inline int *preempt_count_ptr(void) @@ -17,11 +15,6 @@ static __always_inline int *preempt_count_ptr(void) return ¤t_thread_info()->preempt_count; } -/* - * We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the - * alternative is loosing a reschedule. Better schedule too often -- also this - * should be a very rare operation. - */ static __always_inline void preempt_count_set(int pc) { *preempt_count_ptr() = pc; @@ -41,28 +34,17 @@ static __always_inline void preempt_count_set(int pc) task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \ } while (0) -/* - * We fold the NEED_RESCHED bit into the preempt count such that - * preempt_enable() can decrement and test for needing to reschedule with a - * single instruction. - * - * We invert the actual bit, so that when the decrement hits 0 we know we both - * need to resched (the bit is cleared) and can resched (no preempt count). - */ - static __always_inline void set_preempt_need_resched(void) { - *preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED; } static __always_inline void clear_preempt_need_resched(void) { - *preempt_count_ptr() |= PREEMPT_NEED_RESCHED; } static __always_inline bool test_preempt_need_resched(void) { - return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED); + return false; } /* @@ -81,7 +63,12 @@ static __always_inline void __preempt_count_sub(int val) static __always_inline bool __preempt_count_dec_and_test(void) { - return !--*preempt_count_ptr(); + /* + * Because of load-store architectures cannot do per-cpu atomic + * operations; we cannot use PREEMPT_NEED_RESCHED because it might get + * lost. + */ + return !--*preempt_count_ptr() && tif_need_resched(); } /* @@ -89,7 +76,7 @@ static __always_inline bool __preempt_count_dec_and_test(void) */ static __always_inline bool should_resched(void) { - return unlikely(!*preempt_count_ptr()); + return unlikely(!preempt_count() && tif_need_resched()); } #ifdef CONFIG_PREEMPT diff --git a/include/linux/lockref.h b/include/linux/lockref.h index c8929c3832db..4bfde0e99ed5 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -19,7 +19,7 @@ #define USE_CMPXCHG_LOCKREF \ (IS_ENABLED(CONFIG_ARCH_USE_CMPXCHG_LOCKREF) && \ - IS_ENABLED(CONFIG_SMP) && !BLOATED_SPINLOCKS) + IS_ENABLED(CONFIG_SMP) && SPINLOCK_SIZE <= 4) struct lockref { union { diff --git a/include/linux/math64.h b/include/linux/math64.h index 69ed5f5e9f6e..c45c089bfdac 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -133,4 +133,34 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) return ret; } +#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) + +#ifndef mul_u64_u32_shr +static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) +{ + return (u64)(((unsigned __int128)a * mul) >> shift); +} +#endif /* mul_u64_u32_shr */ + +#else + +#ifndef mul_u64_u32_shr +static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) +{ + u32 ah, al; + u64 ret; + + al = a; + ah = a >> 32; + + ret = ((u64)al * mul) >> shift; + if (ah) + ret += ((u64)ah * mul) << (32 - shift); + + return ret; +} +#endif /* mul_u64_u32_shr */ + +#endif + #endif /* _LINUX_MATH64_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index f5096b58b20d..f015c059e159 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -55,7 +55,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, - struct buffer_head *head, enum migrate_mode mode); + struct buffer_head *head, enum migrate_mode mode, + int extra_count); #else static inline void putback_lru_pages(struct list_head *l) {} @@ -90,10 +91,19 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_NUMA_BALANCING +extern bool pmd_trans_migrating(pmd_t pmd); +extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd); extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); extern bool migrate_ratelimited(int node); #else +static inline bool pmd_trans_migrating(pmd_t pmd) +{ + return false; +} +static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd) +{ +} static inline int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 1cedd000cf29..35527173cf50 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1317,7 +1317,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ #if USE_SPLIT_PTE_PTLOCKS -#if BLOATED_SPINLOCKS +#if ALLOC_SPLIT_PTLOCKS extern bool ptlock_alloc(struct page *page); extern void ptlock_free(struct page *page); @@ -1325,7 +1325,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page) { return page->ptl; } -#else /* BLOATED_SPINLOCKS */ +#else /* ALLOC_SPLIT_PTLOCKS */ static inline bool ptlock_alloc(struct page *page) { return true; @@ -1339,7 +1339,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page) { return &page->ptl; } -#endif /* BLOATED_SPINLOCKS */ +#endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bd299418a934..290901a8c1de 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -26,6 +26,7 @@ struct address_space; #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) +#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) /* * Each physical page in the system has a struct page associated with @@ -155,7 +156,7 @@ struct page { * system if PG_buddy is set. */ #if USE_SPLIT_PTE_PTLOCKS -#if BLOATED_SPINLOCKS +#if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else spinlock_t ptl; @@ -443,6 +444,14 @@ struct mm_struct { /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; #endif +#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) + /* + * An operation with batched TLB flushing is going on. Anything that + * can move process memory needs to flush the TLB when moving a + * PROT_NONE or PROT_NUMA mapped page. + */ + bool tlb_flush_pending; +#endif struct uprobes_state uprobes_state; }; @@ -459,4 +468,45 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return mm->cpu_vm_mask_var; } +#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) +/* + * Memory barriers to keep this state in sync are graciously provided by + * the page table locks, outside of which no page table modifications happen. + * The barriers below prevent the compiler from re-ordering the instructions + * around the memory barriers that are already present in the code. + */ +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + barrier(); + return mm->tlb_flush_pending; +} +static inline void set_tlb_flush_pending(struct mm_struct *mm) +{ + mm->tlb_flush_pending = true; + + /* + * Guarantee that the tlb_flush_pending store does not leak into the + * critical section updating the page tables + */ + smp_mb__before_spinlock(); +} +/* Clearing is done after a TLB flush, which also provides a barrier. */ +static inline void clear_tlb_flush_pending(struct mm_struct *mm) +{ + barrier(); + mm->tlb_flush_pending = false; +} +#else +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + return false; +} +static inline void set_tlb_flush_pending(struct mm_struct *mm) +{ +} +static inline void clear_tlb_flush_pending(struct mm_struct *mm) +{ +} +#endif + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/pstore.h b/include/linux/pstore.h index abd437d0a8a7..ece0c6bbfcc5 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -51,6 +51,7 @@ struct pstore_info { char *buf; size_t bufsize; struct mutex read_mutex; /* serialize open/read/close */ + int flags; int (*open)(struct pstore_info *psi); int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, @@ -70,6 +71,8 @@ struct pstore_info { void *data; }; +#define PSTORE_FLAGS_FRAGILE 1 + #ifdef CONFIG_PSTORE extern int pstore_register(struct pstore_info *); extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason); diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 8e00f9f6f963..9e7db9e73cc1 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -43,6 +43,7 @@ extern int unregister_reboot_notifier(struct notifier_block *); * Architecture-specific implementations of sys_reboot commands. */ +extern void migrate_to_reboot_cpu(void); extern void machine_restart(char *cmd); extern void machine_halt(void); extern void machine_power_off(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 768b037dfacb..53f97eb8dbc7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -440,8 +440,6 @@ struct task_cputime { .sum_exec_runtime = 0, \ } -#define PREEMPT_ENABLED (PREEMPT_NEED_RESCHED) - #ifdef CONFIG_PREEMPT_COUNT #define PREEMPT_DISABLED (1 + PREEMPT_ENABLED) #else @@ -932,7 +930,8 @@ struct pipe_inode_info; struct uts_namespace; struct load_weight { - unsigned long weight, inv_weight; + unsigned long weight; + u32 inv_weight; }; struct sched_avg { diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 45412a6afa69..321301c0a643 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -517,10 +517,6 @@ struct se_node_acl { u32 acl_index; #define MAX_ACL_TAG_SIZE 64 char acl_tag[MAX_ACL_TAG_SIZE]; - u64 num_cmds; - u64 read_bytes; - u64 write_bytes; - spinlock_t stats_lock; /* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */ atomic_t acl_pr_ref_count; struct se_dev_entry **device_list; @@ -624,6 +620,7 @@ struct se_dev_attrib { u32 unmap_granularity; u32 unmap_granularity_alignment; u32 max_write_same_len; + u32 max_bytes_per_io; struct se_device *da_dev; struct config_group da_group; }; diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index bcb0912afe7a..f854ca4a1372 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -75,6 +75,7 @@ #define DRM_VMW_PARAM_FIFO_CAPS 4 #define DRM_VMW_PARAM_MAX_FB_SIZE 5 #define DRM_VMW_PARAM_FIFO_HW_VERSION 6 +#define DRM_VMW_PARAM_MAX_SURF_MEMORY 7 /** * struct drm_vmw_getparam_arg diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index e1802d6153ae..959d454f76a1 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -679,6 +679,7 @@ enum perf_event_type { * * { u64 weight; } && PERF_SAMPLE_WEIGHT * { u64 data_src; } && PERF_SAMPLE_DATA_SRC + * { u64 transaction; } && PERF_SAMPLE_TRANSACTION * }; */ PERF_RECORD_SAMPLE = 9, diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h index 65e12099ef89..ae665ac59c36 100644 --- a/include/xen/interface/io/blkif.h +++ b/include/xen/interface/io/blkif.h @@ -146,7 +146,7 @@ struct blkif_request_segment_aligned { struct blkif_request_rw { uint8_t nr_segments; /* number of segments */ blkif_vdev_t handle; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad1; /* offsetof(blkif_request,u.rw.id) == 8 */ #endif uint64_t id; /* private guest value, echoed in resp */ @@ -163,7 +163,7 @@ struct blkif_request_discard { uint8_t flag; /* BLKIF_DISCARD_SECURE or zero. */ #define BLKIF_DISCARD_SECURE (1<<0) /* ignored if discard-secure=0 */ blkif_vdev_t _pad1; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad2; /* offsetof(blkif_req..,u.discard.id)==8*/ #endif uint64_t id; /* private guest value, echoed in resp */ @@ -175,7 +175,7 @@ struct blkif_request_discard { struct blkif_request_other { uint8_t _pad1; blkif_vdev_t _pad2; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad3; /* offsetof(blkif_req..,u.other.id)==8*/ #endif uint64_t id; /* private guest value, echoed in resp */ @@ -184,7 +184,7 @@ struct blkif_request_other { struct blkif_request_indirect { uint8_t indirect_op; uint16_t nr_segments; -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad1; /* offsetof(blkif_...,u.indirect.id) == 8 */ #endif uint64_t id; @@ -192,7 +192,7 @@ struct blkif_request_indirect { blkif_vdev_t handle; uint16_t _pad2; grant_ref_t indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST]; -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad3; /* make it 64 byte aligned */ #else uint64_t _pad3; /* make it 64 byte aligned */ diff --git a/init/Kconfig b/init/Kconfig index 79383d3aa5dc..4e5d96ab2034 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -809,6 +809,12 @@ config GENERIC_SCHED_CLOCK config ARCH_SUPPORTS_NUMA_BALANCING bool +# +# For architectures that know their GCC __int128 support is sound +# +config ARCH_SUPPORTS_INT128 + bool + # For architectures that (ab)use NUMA to represent different memory regions # all cpu-local but of different latencies, such as SuperH. # diff --git a/kernel/Makefile b/kernel/Makefile index bbaf7d59c1bb..bc010ee272b6 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -137,9 +137,10 @@ $(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE ############################################################################### ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y) X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509) -X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509 -X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \ +X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += $(objtree)/signing_key.x509 +X509_CERTIFICATES-raw := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \ $(or $(realpath $(CERT)),$(CERT)))) +X509_CERTIFICATES := $(subst $(realpath $(objtree))/,,$(X509_CERTIFICATES-raw)) ifeq ($(X509_CERTIFICATES),) $(warning *** No X.509 certificates found ***) @@ -164,9 +165,9 @@ $(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list targets += $(obj)/.x509.list $(obj)/.x509.list: @echo $(X509_CERTIFICATES) >$@ +endif clean-files := x509_certificate_list .x509.list -endif ifeq ($(CONFIG_MODULE_SIG),y) ############################################################################### diff --git a/kernel/bounds.c b/kernel/bounds.c index 5253204afdca..9fd4246b04b8 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -22,6 +22,6 @@ void foo(void) #ifdef CONFIG_SMP DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); #endif - DEFINE(BLOATED_SPINLOCKS, sizeof(spinlock_t) > sizeof(int)); + DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); /* End of constants */ } diff --git a/kernel/events/core.c b/kernel/events/core.c index 72348dc192c1..f5744010a8d2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1396,6 +1396,8 @@ event_sched_out(struct perf_event *event, if (event->state != PERF_EVENT_STATE_ACTIVE) return; + perf_pmu_disable(event->pmu); + event->state = PERF_EVENT_STATE_INACTIVE; if (event->pending_disable) { event->pending_disable = 0; @@ -1412,6 +1414,8 @@ event_sched_out(struct perf_event *event, ctx->nr_freq--; if (event->attr.exclusive || !cpuctx->active_oncpu) cpuctx->exclusive = 0; + + perf_pmu_enable(event->pmu); } static void @@ -1652,6 +1656,7 @@ event_sched_in(struct perf_event *event, struct perf_event_context *ctx) { u64 tstamp = perf_event_time(event); + int ret = 0; if (event->state <= PERF_EVENT_STATE_OFF) return 0; @@ -1674,10 +1679,13 @@ event_sched_in(struct perf_event *event, */ smp_wmb(); + perf_pmu_disable(event->pmu); + if (event->pmu->add(event, PERF_EF_START)) { event->state = PERF_EVENT_STATE_INACTIVE; event->oncpu = -1; - return -EAGAIN; + ret = -EAGAIN; + goto out; } event->tstamp_running += tstamp - event->tstamp_stopped; @@ -1693,7 +1701,10 @@ event_sched_in(struct perf_event *event, if (event->attr.exclusive) cpuctx->exclusive = 1; - return 0; +out: + perf_pmu_enable(event->pmu); + + return ret; } static int @@ -2743,6 +2754,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, if (!event_filter_match(event)) continue; + perf_pmu_disable(event->pmu); + hwc = &event->hw; if (hwc->interrupts == MAX_INTERRUPTS) { @@ -2752,7 +2765,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, } if (!event->attr.freq || !event->attr.sample_freq) - continue; + goto next; /* * stop the event and update event->count @@ -2774,6 +2787,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, perf_adjust_period(event, period, delta, false); event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0); + next: + perf_pmu_enable(event->pmu); } perf_pmu_enable(ctx->pmu); diff --git a/kernel/fork.c b/kernel/fork.c index 728d5be9548c..5721f0e3f2da 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -537,6 +537,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) spin_lock_init(&mm->page_table_lock); mm_init_aio(mm); mm_init_owner(mm, p); + clear_tlb_flush_pending(mm); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; diff --git a/kernel/kexec.c b/kernel/kexec.c index d0d8fca54065..9c970167e402 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1680,6 +1680,7 @@ int kernel_kexec(void) { kexec_in_progress = true; kernel_restart_prepare(NULL); + migrate_to_reboot_cpu(); printk(KERN_EMERG "Starting new kernel\n"); machine_shutdown(); } diff --git a/kernel/reboot.c b/kernel/reboot.c index f813b3474646..662c83fc16b7 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -104,7 +104,7 @@ int unregister_reboot_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_reboot_notifier); -static void migrate_to_reboot_cpu(void) +void migrate_to_reboot_cpu(void) { /* The boot cpu is always logical cpu 0 */ int cpu = reboot_cpu; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e85cda20ab2b..a88f4a485c5e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4902,6 +4902,7 @@ DEFINE_PER_CPU(struct sched_domain *, sd_asym); static void update_top_cache_domain(int cpu) { struct sched_domain *sd; + struct sched_domain *busy_sd = NULL; int id = cpu; int size = 1; @@ -4909,9 +4910,9 @@ static void update_top_cache_domain(int cpu) if (sd) { id = cpumask_first(sched_domain_span(sd)); size = cpumask_weight(sched_domain_span(sd)); - sd = sd->parent; /* sd_busy */ + busy_sd = sd->parent; /* sd_busy */ } - rcu_assign_pointer(per_cpu(sd_busy, cpu), sd); + rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd); rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); per_cpu(sd_llc_size, cpu) = size; @@ -5112,6 +5113,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) * die on a /0 trap. */ sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span); + sg->sgp->power_orig = sg->sgp->power; /* * Make sure the first group of this domain contains the diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fd773ade1a31..c7395d97e4cb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -178,59 +178,61 @@ void sched_init_granularity(void) update_sysctl(); } -#if BITS_PER_LONG == 32 -# define WMULT_CONST (~0UL) -#else -# define WMULT_CONST (1UL << 32) -#endif - +#define WMULT_CONST (~0U) #define WMULT_SHIFT 32 -/* - * Shift right and round: - */ -#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) +static void __update_inv_weight(struct load_weight *lw) +{ + unsigned long w; + + if (likely(lw->inv_weight)) + return; + + w = scale_load_down(lw->weight); + + if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) + lw->inv_weight = 1; + else if (unlikely(!w)) + lw->inv_weight = WMULT_CONST; + else + lw->inv_weight = WMULT_CONST / w; +} /* - * delta *= weight / lw + * delta_exec * weight / lw.weight + * OR + * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT + * + * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case + * we're guaranteed shift stays positive because inv_weight is guaranteed to + * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22. + * + * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus + * weight/lw.weight <= 1, and therefore our shift will also be positive. */ -static unsigned long -calc_delta_mine(unsigned long delta_exec, unsigned long weight, - struct load_weight *lw) +static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw) { - u64 tmp; - - /* - * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched - * entities since MIN_SHARES = 2. Treat weight as 1 if less than - * 2^SCHED_LOAD_RESOLUTION. - */ - if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION))) - tmp = (u64)delta_exec * scale_load_down(weight); - else - tmp = (u64)delta_exec; + u64 fact = scale_load_down(weight); + int shift = WMULT_SHIFT; - if (!lw->inv_weight) { - unsigned long w = scale_load_down(lw->weight); + __update_inv_weight(lw); - if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) - lw->inv_weight = 1; - else if (unlikely(!w)) - lw->inv_weight = WMULT_CONST; - else - lw->inv_weight = WMULT_CONST / w; + if (unlikely(fact >> 32)) { + while (fact >> 32) { + fact >>= 1; + shift--; + } } - /* - * Check whether we'd overflow the 64-bit multiplication: - */ - if (unlikely(tmp > WMULT_CONST)) - tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight, - WMULT_SHIFT/2); - else - tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT); + /* hint to use a 32x32->64 mul */ + fact = (u64)(u32)fact * lw->inv_weight; + + while (fact >> 32) { + fact >>= 1; + shift--; + } - return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); + return mul_u64_u32_shr(delta_exec, fact, shift); } @@ -443,7 +445,7 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) #endif /* CONFIG_FAIR_GROUP_SCHED */ static __always_inline -void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec); +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); /************************************************************** * Scheduling class tree data structure manipulation methods: @@ -612,11 +614,10 @@ int sched_proc_update_handler(struct ctl_table *table, int write, /* * delta /= w */ -static inline unsigned long -calc_delta_fair(unsigned long delta, struct sched_entity *se) +static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se) { if (unlikely(se->load.weight != NICE_0_LOAD)) - delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load); + delta = __calc_delta(delta, NICE_0_LOAD, &se->load); return delta; } @@ -665,7 +666,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) update_load_add(&lw, se->load.weight); load = &lw; } - slice = calc_delta_mine(slice, se->load.weight, load); + slice = __calc_delta(slice, se->load.weight, load); } return slice; } @@ -703,47 +704,32 @@ void init_task_runnable_average(struct task_struct *p) #endif /* - * Update the current task's runtime statistics. Skip current tasks that - * are not in our scheduling class. + * Update the current task's runtime statistics. */ -static inline void -__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, - unsigned long delta_exec) -{ - unsigned long delta_exec_weighted; - - schedstat_set(curr->statistics.exec_max, - max((u64)delta_exec, curr->statistics.exec_max)); - - curr->sum_exec_runtime += delta_exec; - schedstat_add(cfs_rq, exec_clock, delta_exec); - delta_exec_weighted = calc_delta_fair(delta_exec, curr); - - curr->vruntime += delta_exec_weighted; - update_min_vruntime(cfs_rq); -} - static void update_curr(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; u64 now = rq_clock_task(rq_of(cfs_rq)); - unsigned long delta_exec; + u64 delta_exec; if (unlikely(!curr)) return; - /* - * Get the amount of time the current task was running - * since the last time we changed load (this cannot - * overflow on 32 bits): - */ - delta_exec = (unsigned long)(now - curr->exec_start); - if (!delta_exec) + delta_exec = now - curr->exec_start; + if (unlikely((s64)delta_exec <= 0)) return; - __update_curr(cfs_rq, curr, delta_exec); curr->exec_start = now; + schedstat_set(curr->statistics.exec_max, + max(delta_exec, curr->statistics.exec_max)); + + curr->sum_exec_runtime += delta_exec; + schedstat_add(cfs_rq, exec_clock, delta_exec); + + curr->vruntime += calc_delta_fair(delta_exec, curr); + update_min_vruntime(cfs_rq); + if (entity_is_task(curr)) { struct task_struct *curtask = task_of(curr); @@ -1752,6 +1738,13 @@ void task_numa_work(struct callback_head *work) (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ))) continue; + /* + * Skip inaccessible VMAs to avoid any confusion between + * PROT_NONE and NUMA hinting ptes + */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) + continue; + do { start = max(start, vma->vm_start); end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); @@ -3015,8 +3008,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) } } -static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec) +static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ cfs_rq->runtime_remaining -= delta_exec; @@ -3034,7 +3026,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, } static __always_inline -void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec) +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled) return; @@ -3574,8 +3566,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) return rq_clock_task(rq_of(cfs_rq)); } -static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec) {} +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7d57275fc396..1c4065575fa2 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -901,6 +901,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif if (rq->online && prio < prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, prio); } @@ -910,6 +917,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif if (rq->online && rt_rq->highest_prio.curr != prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0e9f9eaade2f..72a0f81dc5a8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -775,7 +775,7 @@ static int ftrace_profile_init(void) int cpu; int ret = 0; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { ret = ftrace_profile_init_cpu(cpu); if (ret) break; diff --git a/kernel/user.c b/kernel/user.c index a3a0dbfda329..c006131beb77 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -51,9 +51,9 @@ struct user_namespace init_user_ns = { .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .proc_inum = PROC_USER_INIT_INO, -#ifdef CONFIG_KEYS_KERBEROS_CACHE - .krb_cache_register_sem = - __RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem), +#ifdef CONFIG_PERSISTENT_KEYRINGS + .persistent_keyring_register_sem = + __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem), #endif }; EXPORT_SYMBOL_GPL(init_user_ns); diff --git a/mm/Kconfig b/mm/Kconfig index eb69f352401d..723bbe04a0b0 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -543,7 +543,7 @@ config ZSWAP config MEM_SOFT_DIRTY bool "Track memory changes" - depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY + depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS select PROC_PAGE_MONITOR help This option enables memory changes tracking by introducing a diff --git a/mm/compaction.c b/mm/compaction.c index 805165bcd3dd..f58bcd016f43 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -134,6 +134,10 @@ static void update_pageblock_skip(struct compact_control *cc, bool migrate_scanner) { struct zone *zone = cc->zone; + + if (cc->ignore_skip_hint) + return; + if (!page) return; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 33a5dc492810..7de1bf85f683 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -882,6 +882,10 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = 0; goto out_unlock; } + + /* mmap_sem prevents this happening but warn if that changes */ + WARN_ON(pmd_trans_migrating(pmd)); + if (unlikely(pmd_trans_splitting(pmd))) { /* split huge page running from under us */ spin_unlock(src_ptl); @@ -1243,6 +1247,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) return ERR_PTR(-EFAULT); + /* Full NUMA hinting faults to serialise migration in fault paths */ + if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + goto out; + page = pmd_page(*pmd); VM_BUG_ON(!PageHead(page)); if (flags & FOLL_TOUCH) { @@ -1295,6 +1303,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(!pmd_same(pmd, *pmdp))) goto out_unlock; + /* + * If there are potential migrations, wait for completion and retry + * without disrupting NUMA hinting information. Do not relock and + * check_same as the page may no longer be mapped. + */ + if (unlikely(pmd_trans_migrating(*pmdp))) { + spin_unlock(ptl); + wait_migrate_huge_page(vma->anon_vma, pmdp); + goto out; + } + page = pmd_page(pmd); BUG_ON(is_huge_zero_page(page)); page_nid = page_to_nid(page); @@ -1323,23 +1342,22 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* If the page was locked, there are no parallel migrations */ if (page_locked) goto clear_pmdnuma; + } - /* - * Otherwise wait for potential migrations and retry. We do - * relock and check_same as the page may no longer be mapped. - * As the fault is being retried, do not account for it. - */ + /* Migration could have started since the pmd_trans_migrating check */ + if (!page_locked) { spin_unlock(ptl); wait_on_page_locked(page); page_nid = -1; goto out; } - /* Page is misplaced, serialise migrations and parallel THP splits */ + /* + * Page is misplaced. Page lock serialises migrations. Acquire anon_vma + * to serialises splits + */ get_page(page); spin_unlock(ptl); - if (!page_locked) - lock_page(page); anon_vma = page_lock_anon_vma_read(page); /* Confirm the PMD did not change while page_table_lock was released */ @@ -1351,6 +1369,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_unlock; } + /* Bail if we fail to protect against THP splits for any reason */ + if (unlikely(!anon_vma)) { + put_page(page); + page_nid = -1; + goto clear_pmdnuma; + } + /* * Migrate the THP to the requested node, returns with page unlocked * and pmd_numa cleared. @@ -1517,6 +1542,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, ret = 1; if (!prot_numa) { entry = pmdp_get_and_clear(mm, addr, pmd); + if (pmd_numa(entry)) + entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; BUG_ON(pmd_write(entry)); @@ -1531,7 +1558,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = pmdp_get_and_clear(mm, addr, pmd); + entry = *pmd; entry = pmd_mknuma(entry); ret = HPAGE_PMD_NR; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index b7c171602ba1..db08af92c6fc 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1505,10 +1505,16 @@ static int soft_offline_huge_page(struct page *page, int flags) if (ret > 0) ret = -EIO; } else { - set_page_hwpoison_huge_page(hpage); - dequeue_hwpoisoned_huge_page(hpage); - atomic_long_add(1 << compound_order(hpage), - &num_poisoned_pages); + /* overcommit hugetlb page will be freed to buddy */ + if (PageHuge(page)) { + set_page_hwpoison_huge_page(hpage); + dequeue_hwpoisoned_huge_page(hpage); + atomic_long_add(1 << compound_order(hpage), + &num_poisoned_pages); + } else { + SetPageHWPoison(page); + atomic_long_inc(&num_poisoned_pages); + } } return ret; } diff --git a/mm/memory.c b/mm/memory.c index 5d9025f3b3e1..6768ce9e57d2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4271,7 +4271,7 @@ void copy_user_huge_page(struct page *dst, struct page *src, } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ -#if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS +#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS bool ptlock_alloc(struct page *page) { spinlock_t *ptl; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index eca4a3129129..0cd2c4d4e270 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1197,14 +1197,16 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int * break; vma = vma->vm_next; } + + if (PageHuge(page)) { + if (vma) + return alloc_huge_page_noerr(vma, address, 1); + else + return NULL; + } /* - * queue_pages_range() confirms that @page belongs to some vma, - * so vma shouldn't be NULL. + * if !vma, alloc_page_vma() will use task or system default policy */ - BUG_ON(!vma); - - if (PageHuge(page)) - return alloc_huge_page_noerr(vma, address, 1); return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); } #else @@ -1318,7 +1320,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; } else - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); up_write(&mm->mmap_sem); mpol_out: diff --git a/mm/migrate.c b/mm/migrate.c index bb940045fe85..9194375b2307 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -36,6 +36,7 @@ #include <linux/hugetlb_cgroup.h> #include <linux/gfp.h> #include <linux/balloon_compaction.h> +#include <linux/mmu_notifier.h> #include <asm/tlbflush.h> @@ -316,14 +317,15 @@ static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, */ int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, - struct buffer_head *head, enum migrate_mode mode) + struct buffer_head *head, enum migrate_mode mode, + int extra_count) { - int expected_count = 0; + int expected_count = 1 + extra_count; void **pslot; if (!mapping) { /* Anonymous page without mapping */ - if (page_count(page) != 1) + if (page_count(page) != expected_count) return -EAGAIN; return MIGRATEPAGE_SUCCESS; } @@ -333,7 +335,7 @@ int migrate_page_move_mapping(struct address_space *mapping, pslot = radix_tree_lookup_slot(&mapping->page_tree, page_index(page)); - expected_count = 2 + page_has_private(page); + expected_count += 1 + page_has_private(page); if (page_count(page) != expected_count || radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { spin_unlock_irq(&mapping->tree_lock); @@ -583,7 +585,7 @@ int migrate_page(struct address_space *mapping, BUG_ON(PageWriteback(page)); /* Writeback must be complete */ - rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode); + rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0); if (rc != MIGRATEPAGE_SUCCESS) return rc; @@ -610,7 +612,7 @@ int buffer_migrate_page(struct address_space *mapping, head = page_buffers(page); - rc = migrate_page_move_mapping(mapping, newpage, page, head, mode); + rc = migrate_page_move_mapping(mapping, newpage, page, head, mode, 0); if (rc != MIGRATEPAGE_SUCCESS) return rc; @@ -1654,6 +1656,18 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) return 1; } +bool pmd_trans_migrating(pmd_t pmd) +{ + struct page *page = pmd_page(pmd); + return PageLocked(page); +} + +void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd) +{ + struct page *page = pmd_page(*pmd); + wait_on_page_locked(page); +} + /* * Attempt to migrate a misplaced page to the specified destination * node. Caller is expected to have an elevated reference count on @@ -1716,12 +1730,14 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, struct page *page, int node) { spinlock_t *ptl; - unsigned long haddr = address & HPAGE_PMD_MASK; pg_data_t *pgdat = NODE_DATA(node); int isolated = 0; struct page *new_page = NULL; struct mem_cgroup *memcg = NULL; int page_lru = page_is_file_cache(page); + unsigned long mmun_start = address & HPAGE_PMD_MASK; + unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; + pmd_t orig_entry; /* * Rate-limit the amount of data that is being migrated to a node. @@ -1744,6 +1760,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, goto out_fail; } + if (mm_tlb_flush_pending(mm)) + flush_tlb_range(vma, mmun_start, mmun_end); + /* Prepare a page as a migration target */ __set_page_locked(new_page); SetPageSwapBacked(new_page); @@ -1755,9 +1774,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, WARN_ON(PageLRU(new_page)); /* Recheck the target PMD */ + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_same(*pmd, entry))) { + if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) { +fail_putback: spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); /* Reverse changes made by migrate_page_copy() */ if (TestClearPageActive(new_page)) @@ -1774,7 +1796,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, putback_lru_page(page); mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); - goto out_fail; + + goto out_unlock; } /* @@ -1786,16 +1809,35 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, */ mem_cgroup_prepare_migration(page, new_page, &memcg); + orig_entry = *pmd; entry = mk_pmd(new_page, vma->vm_page_prot); - entry = pmd_mknonnuma(entry); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); entry = pmd_mkhuge(entry); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - pmdp_clear_flush(vma, haddr, pmd); - set_pmd_at(mm, haddr, pmd, entry); - page_add_new_anon_rmap(new_page, vma, haddr); + /* + * Clear the old entry under pagetable lock and establish the new PTE. + * Any parallel GUP will either observe the old page blocking on the + * page lock, block on the page table lock or observe the new page. + * The SetPageUptodate on the new page and page_add_new_anon_rmap + * guarantee the copy is visible before the pagetable update. + */ + flush_cache_range(vma, mmun_start, mmun_end); + page_add_new_anon_rmap(new_page, vma, mmun_start); + pmdp_clear_flush(vma, mmun_start, pmd); + set_pmd_at(mm, mmun_start, pmd, entry); + flush_tlb_range(vma, mmun_start, mmun_end); update_mmu_cache_pmd(vma, address, &entry); + + if (page_count(page) != 2) { + set_pmd_at(mm, mmun_start, pmd, orig_entry); + flush_tlb_range(vma, mmun_start, mmun_end); + update_mmu_cache_pmd(vma, address, &entry); + page_remove_rmap(new_page); + goto fail_putback; + } + page_remove_rmap(page); + /* * Finish the charge transaction under the page table lock to * prevent split_huge_page() from dividing up the charge @@ -1803,6 +1845,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, */ mem_cgroup_end_migration(memcg, page, new_page, true); spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); unlock_page(new_page); unlock_page(page); @@ -1820,10 +1863,15 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, out_fail: count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); out_dropref: - entry = pmd_mknonnuma(entry); - set_pmd_at(mm, haddr, pmd, entry); - update_mmu_cache_pmd(vma, address, &entry); + ptl = pmd_lock(mm, pmd); + if (pmd_same(*pmd, entry)) { + entry = pmd_mknonnuma(entry); + set_pmd_at(mm, mmun_start, pmd, entry); + update_mmu_cache_pmd(vma, address, &entry); + } + spin_unlock(ptl); +out_unlock: unlock_page(page); put_page(page); return 0; diff --git a/mm/mprotect.c b/mm/mprotect.c index 26667971c824..bb53a6591aea 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -52,17 +52,21 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, pte_t ptent; bool updated = false; - ptent = ptep_modify_prot_start(mm, addr, pte); if (!prot_numa) { + ptent = ptep_modify_prot_start(mm, addr, pte); + if (pte_numa(ptent)) + ptent = pte_mknonnuma(ptent); ptent = pte_modify(ptent, newprot); updated = true; } else { struct page *page; + ptent = *pte; page = vm_normal_page(vma, addr, oldpte); if (page) { if (!pte_numa(oldpte)) { ptent = pte_mknuma(ptent); + set_pte_at(mm, addr, pte, ptent); updated = true; } } @@ -79,7 +83,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (updated) pages++; - ptep_modify_prot_commit(mm, addr, pte, ptent); + + /* Only !prot_numa always clears the pte */ + if (!prot_numa) + ptep_modify_prot_commit(mm, addr, pte, ptent); } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); @@ -181,6 +188,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); + set_tlb_flush_pending(mm); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) @@ -192,6 +200,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, /* Only flush the TLB if we actually modified any entries: */ if (pages) flush_tlb_range(vma, start, end); + clear_tlb_flush_pending(mm); return pages; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 580a5f075ed0..5248fe070aa4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1816,7 +1816,7 @@ static void zlc_clear_zones_full(struct zonelist *zonelist) static bool zone_local(struct zone *local_zone, struct zone *zone) { - return node_distance(local_zone->node, zone->node) == LOCAL_DISTANCE; + return local_zone->node == zone->node; } static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) @@ -1913,18 +1913,17 @@ zonelist_scan: * page was allocated in should have no effect on the * time the page has in memory before being reclaimed. * - * When zone_reclaim_mode is enabled, try to stay in - * local zones in the fastpath. If that fails, the - * slowpath is entered, which will do another pass - * starting with the local zones, but ultimately fall - * back to remote zones that do not partake in the - * fairness round-robin cycle of this zonelist. + * Try to stay in local zones in the fastpath. If + * that fails, the slowpath is entered, which will do + * another pass starting with the local zones, but + * ultimately fall back to remote zones that do not + * partake in the fairness round-robin cycle of this + * zonelist. */ if (alloc_flags & ALLOC_WMARK_LOW) { if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) continue; - if (zone_reclaim_mode && - !zone_local(preferred_zone, zone)) + if (!zone_local(preferred_zone, zone)) continue; } /* @@ -2390,7 +2389,7 @@ static void prepare_slowpath(gfp_t gfp_mask, unsigned int order, * thrash fairness information for zones that are not * actually part of this zonelist's round-robin cycle. */ - if (zone_reclaim_mode && !zone_local(preferred_zone, zone)) + if (!zone_local(preferred_zone, zone)) continue; mod_zone_page_state(zone, NR_ALLOC_BATCH, high_wmark_pages(zone) - diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index cbb38545d9d6..a8b919925934 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -110,9 +110,10 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { + struct mm_struct *mm = (vma)->vm_mm; pte_t pte; - pte = ptep_get_and_clear((vma)->vm_mm, address, ptep); - if (pte_accessible(pte)) + pte = ptep_get_and_clear(mm, address, ptep); + if (pte_accessible(mm, pte)) flush_tlb_page(vma, address); return pte; } @@ -191,6 +192,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + pmd_t entry = *pmdp; + if (pmd_numa(entry)) + entry = pmd_mknonnuma(entry); set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp)); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } diff --git a/mm/rmap.c b/mm/rmap.c index 55c8b8dc9ffb..068522d8502a 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -600,7 +600,11 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm, spinlock_t *ptl; if (unlikely(PageHuge(page))) { + /* when pud is not present, pte will be NULL */ pte = huge_pte_offset(mm, address); + if (!pte) + return NULL; + ptl = huge_pte_lockptr(page_hstate(page), mm, pte); goto check; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ca15f32821fb..36b1443f9ae4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1161,6 +1161,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->parms->reachable_time : 0))); neigh->nud_state = new; + notify = 1; } if (lladdr != neigh->ha) { diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index f13bd91d9a56..a313c3fbeb46 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -423,6 +423,7 @@ static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par) static struct xt_target synproxy_tg4_reg __read_mostly = { .name = "SYNPROXY", .family = NFPROTO_IPV4, + .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD), .target = synproxy_tg4, .targetsize = sizeof(struct xt_synproxy_info), .checkentry = synproxy_tg4_check, diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index fff5ba1a33b7..4a5e94ac314a 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -72,7 +72,7 @@ static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_reject *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_REJECT_TYPE, priv->type)) + if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type))) goto nla_put_failure; switch (priv->type) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 62c19fdd102d..f140048334ce 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1600,20 +1600,15 @@ static void flush_stack(struct sock **stack, unsigned int count, } /* For TCP sockets, sk_rx_dst is protected by socket lock - * For UDP, we use sk_dst_lock to guard against concurrent changes. + * For UDP, we use xchg() to guard against concurrent changes. */ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old; - spin_lock(&sk->sk_dst_lock); - old = sk->sk_rx_dst; - if (likely(old != dst)) { - dst_hold(dst); - sk->sk_rx_dst = dst; - dst_release(old); - } - spin_unlock(&sk->sk_dst_lock); + dst_hold(dst); + old = xchg(&sk->sk_rx_dst, dst); + dst_release(old); } /* diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index f78f41aca8e9..a0d17270117c 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -446,6 +446,7 @@ static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par) static struct xt_target synproxy_tg6_reg __read_mostly = { .name = "SYNPROXY", .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD), .target = synproxy_tg6, .targetsize = sizeof(struct xt_synproxy_info), .checkentry = synproxy_tg6_check, diff --git a/net/sctp/probe.c b/net/sctp/probe.c index 53c452efb40b..5e68b94ee640 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -38,6 +38,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> +MODULE_SOFTDEP("pre: sctp"); MODULE_AUTHOR("Wei Yongjun <yjwei@cn.fujitsu.com>"); MODULE_DESCRIPTION("SCTP snooper"); MODULE_LICENSE("GPL"); @@ -182,6 +183,20 @@ static struct jprobe sctp_recv_probe = { .entry = jsctp_sf_eat_sack, }; +static __init int sctp_setup_jprobe(void) +{ + int ret = register_jprobe(&sctp_recv_probe); + + if (ret) { + if (request_module("sctp")) + goto out; + ret = register_jprobe(&sctp_recv_probe); + } + +out: + return ret; +} + static __init int sctpprobe_init(void) { int ret = -ENOMEM; @@ -202,7 +217,7 @@ static __init int sctpprobe_init(void) &sctpprobe_fops)) goto free_kfifo; - ret = register_jprobe(&sctp_recv_probe); + ret = sctp_setup_jprobe(); if (ret) goto remove_proc; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index a0ca162e5bd5..a427623ee574 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -718,7 +718,9 @@ static int unix_autobind(struct socket *sock) int err; unsigned int retries = 0; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) + return err; err = 0; if (u->addr) @@ -877,7 +879,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) + goto out; err = -EINVAL; if (u->addr) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 6e03b465e44e..a2104671f51d 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1937,6 +1937,8 @@ static int wait_for_avail(struct snd_pcm_substream *substream, case SNDRV_PCM_STATE_DISCONNECTED: err = -EBADFD; goto _endloop; + case SNDRV_PCM_STATE_PAUSED: + continue; } if (!tout) { snd_printd("%s write error (DMA or IRQ trouble?)\n", diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 27aa14007cbd..956871d8b3d2 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -3433,6 +3433,10 @@ static void check_probe_mask(struct azx *chip, int dev) * white/black-list for enable_msi */ static struct snd_pci_quirk msi_black_list[] = { + SND_PCI_QUIRK(0x103c, 0x2191, "HP", 0), /* AMD Hudson */ + SND_PCI_QUIRK(0x103c, 0x2192, "HP", 0), /* AMD Hudson */ + SND_PCI_QUIRK(0x103c, 0x21f7, "HP", 0), /* AMD Hudson */ + SND_PCI_QUIRK(0x103c, 0x21fa, "HP", 0), /* AMD Hudson */ SND_PCI_QUIRK(0x1043, 0x81f2, "ASUS", 0), /* Athlon64 X2 + nvidia */ SND_PCI_QUIRK(0x1043, 0x81f6, "ASUS", 0), /* nvidia */ SND_PCI_QUIRK(0x1043, 0x822d, "ASUS", 0), /* Athlon64 X2 + nvidia MCP55 */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 34de5dc2fe9b..c5646941539a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4247,12 +4247,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0606, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0608, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0609, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0610, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0613, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_MONO_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x061f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0629, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS), + SND_PCI_QUIRK(0x1028, 0x063e, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x063f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0640, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c index 8697cedccd21..1ead3c977a51 100644 --- a/sound/soc/atmel/atmel_ssc_dai.c +++ b/sound/soc/atmel/atmel_ssc_dai.c @@ -648,7 +648,7 @@ static int atmel_ssc_prepare(struct snd_pcm_substream *substream, dma_params = ssc_p->dma_params[dir]; - ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_enable); + ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_disable); ssc_writel(ssc_p->ssc->regs, IDR, dma_params->mask->ssc_error); pr_debug("%s enabled SSC_SR=0x%08x\n", @@ -657,6 +657,33 @@ static int atmel_ssc_prepare(struct snd_pcm_substream *substream, return 0; } +static int atmel_ssc_trigger(struct snd_pcm_substream *substream, + int cmd, struct snd_soc_dai *dai) +{ + struct atmel_ssc_info *ssc_p = &ssc_info[dai->id]; + struct atmel_pcm_dma_params *dma_params; + int dir; + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + dir = 0; + else + dir = 1; + + dma_params = ssc_p->dma_params[dir]; + + switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + case SNDRV_PCM_TRIGGER_RESUME: + case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_enable); + break; + default: + ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_disable); + break; + } + + return 0; +} #ifdef CONFIG_PM static int atmel_ssc_suspend(struct snd_soc_dai *cpu_dai) @@ -731,6 +758,7 @@ static const struct snd_soc_dai_ops atmel_ssc_dai_ops = { .startup = atmel_ssc_startup, .shutdown = atmel_ssc_shutdown, .prepare = atmel_ssc_prepare, + .trigger = atmel_ssc_trigger, .hw_params = atmel_ssc_hw_params, .set_fmt = atmel_ssc_set_dai_fmt, .set_clkdiv = atmel_ssc_set_dai_clkdiv, diff --git a/sound/soc/atmel/sam9x5_wm8731.c b/sound/soc/atmel/sam9x5_wm8731.c index 1b372283bd01..7d6a9055874b 100644 --- a/sound/soc/atmel/sam9x5_wm8731.c +++ b/sound/soc/atmel/sam9x5_wm8731.c @@ -109,7 +109,7 @@ static int sam9x5_wm8731_driver_probe(struct platform_device *pdev) dai->stream_name = "WM8731 PCM"; dai->codec_dai_name = "wm8731-hifi"; dai->init = sam9x5_wm8731_init; - dai->dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF + dai->dai_fmt = SND_SOC_DAIFMT_DSP_A | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBM_CFM; ret = snd_soc_of_parse_card_name(card, "atmel,model"); diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index 99b359e19d35..0ab2dc296474 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -1012,7 +1012,7 @@ static const struct snd_soc_dapm_route wm5110_dapm_routes[] = { { "AEC Loopback", "HPOUT3L", "OUT3L" }, { "AEC Loopback", "HPOUT3R", "OUT3R" }, { "HPOUT3L", NULL, "OUT3L" }, - { "HPOUT3R", NULL, "OUT3L" }, + { "HPOUT3R", NULL, "OUT3R" }, { "AEC Loopback", "SPKOUTL", "OUT4L" }, { "SPKOUTLN", NULL, "OUT4L" }, diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 3938fb1c203e..53bbfac6a83a 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -1444,7 +1444,7 @@ static int wm8904_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_DSP_B: - aif1 |= WM8904_AIF_LRCLK_INV; + aif1 |= 0x3 | WM8904_AIF_LRCLK_INV; case SND_SOC_DAIFMT_DSP_A: aif1 |= 0x3; break; diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 543c5c2631b6..0f17ed3e29f4 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2439,7 +2439,20 @@ static void wm8962_configure_bclk(struct snd_soc_codec *codec) snd_soc_update_bits(codec, WM8962_CLOCKING_4, WM8962_SYSCLK_RATE_MASK, clocking4); + /* DSPCLK_DIV can be only generated correctly after enabling SYSCLK. + * So we here provisionally enable it and then disable it afterward + * if current bias_level hasn't reached SND_SOC_BIAS_ON. + */ + if (codec->dapm.bias_level != SND_SOC_BIAS_ON) + snd_soc_update_bits(codec, WM8962_CLOCKING2, + WM8962_SYSCLK_ENA_MASK, WM8962_SYSCLK_ENA); + dspclk = snd_soc_read(codec, WM8962_CLOCKING1); + + if (codec->dapm.bias_level != SND_SOC_BIAS_ON) + snd_soc_update_bits(codec, WM8962_CLOCKING2, + WM8962_SYSCLK_ENA_MASK, 0); + if (dspclk < 0) { dev_err(codec->dev, "Failed to read DSPCLK: %d\n", dspclk); return; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 46ec0e9744d4..4fbcab63e61f 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1474,13 +1474,17 @@ static int wm_adsp2_ena(struct wm_adsp *dsp) return ret; /* Wait for the RAM to start, should be near instantaneous */ - count = 0; - do { + for (count = 0; count < 10; ++count) { ret = regmap_read(dsp->regmap, dsp->base + ADSP2_STATUS1, &val); if (ret != 0) return ret; - } while (!(val & ADSP2_RAM_RDY) && ++count < 10); + + if (val & ADSP2_RAM_RDY) + break; + + msleep(1); + } if (!(val & ADSP2_RAM_RDY)) { adsp_err(dsp, "Failed to start DSP RAM\n"); diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c index 61e48852b9e8..3fd76bc391de 100644 --- a/sound/soc/fsl/imx-wm8962.c +++ b/sound/soc/fsl/imx-wm8962.c @@ -130,8 +130,6 @@ static int imx_wm8962_set_bias_level(struct snd_soc_card *card, break; } - dapm->bias_level = level; - return 0; } diff --git a/sound/soc/kirkwood/kirkwood-i2s.c b/sound/soc/kirkwood/kirkwood-i2s.c index 0b18f654b413..3920a5e8125f 100644 --- a/sound/soc/kirkwood/kirkwood-i2s.c +++ b/sound/soc/kirkwood/kirkwood-i2s.c @@ -473,17 +473,17 @@ static struct snd_soc_dai_driver kirkwood_i2s_dai_extclk[2] = { .playback = { .channels_min = 1, .channels_max = 2, - .rates = SNDRV_PCM_RATE_8000_192000 | - SNDRV_PCM_RATE_CONTINUOUS | - SNDRV_PCM_RATE_KNOT, + .rates = SNDRV_PCM_RATE_CONTINUOUS, + .rate_min = 5512, + .rate_max = 192000, .formats = KIRKWOOD_I2S_FORMATS, }, .capture = { .channels_min = 1, .channels_max = 2, - .rates = SNDRV_PCM_RATE_8000_192000 | - SNDRV_PCM_RATE_CONTINUOUS | - SNDRV_PCM_RATE_KNOT, + .rates = SNDRV_PCM_RATE_CONTINUOUS, + .rate_min = 5512, + .rate_max = 192000, .formats = KIRKWOOD_I2S_FORMATS, }, .ops = &kirkwood_i2s_dai_ops, @@ -494,17 +494,17 @@ static struct snd_soc_dai_driver kirkwood_i2s_dai_extclk[2] = { .playback = { .channels_min = 1, .channels_max = 2, - .rates = SNDRV_PCM_RATE_8000_192000 | - SNDRV_PCM_RATE_CONTINUOUS | - SNDRV_PCM_RATE_KNOT, + .rates = SNDRV_PCM_RATE_CONTINUOUS, + .rate_min = 5512, + .rate_max = 192000, .formats = KIRKWOOD_SPDIF_FORMATS, }, .capture = { .channels_min = 1, .channels_max = 2, - .rates = SNDRV_PCM_RATE_8000_192000 | - SNDRV_PCM_RATE_CONTINUOUS | - SNDRV_PCM_RATE_KNOT, + .rates = SNDRV_PCM_RATE_CONTINUOUS, + .rate_min = 5512, + .rate_max = 192000, .formats = KIRKWOOD_SPDIF_FORMATS, }, .ops = &kirkwood_i2s_dai_ops, diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index cbc9c96ce1f4..41949af3baae 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -305,6 +305,20 @@ static void dmaengine_pcm_request_chan_of(struct dmaengine_pcm *pcm, } } +static void dmaengine_pcm_release_chan(struct dmaengine_pcm *pcm) +{ + unsigned int i; + + for (i = SNDRV_PCM_STREAM_PLAYBACK; i <= SNDRV_PCM_STREAM_CAPTURE; + i++) { + if (!pcm->chan[i]) + continue; + dma_release_channel(pcm->chan[i]); + if (pcm->flags & SND_DMAENGINE_PCM_FLAG_HALF_DUPLEX) + break; + } +} + /** * snd_dmaengine_pcm_register - Register a dmaengine based PCM device * @dev: The parent device for the PCM device @@ -315,6 +329,7 @@ int snd_dmaengine_pcm_register(struct device *dev, const struct snd_dmaengine_pcm_config *config, unsigned int flags) { struct dmaengine_pcm *pcm; + int ret; pcm = kzalloc(sizeof(*pcm), GFP_KERNEL); if (!pcm) @@ -326,11 +341,20 @@ int snd_dmaengine_pcm_register(struct device *dev, dmaengine_pcm_request_chan_of(pcm, dev); if (flags & SND_DMAENGINE_PCM_FLAG_NO_RESIDUE) - return snd_soc_add_platform(dev, &pcm->platform, + ret = snd_soc_add_platform(dev, &pcm->platform, &dmaengine_no_residue_pcm_platform); else - return snd_soc_add_platform(dev, &pcm->platform, + ret = snd_soc_add_platform(dev, &pcm->platform, &dmaengine_pcm_platform); + if (ret) + goto err_free_dma; + + return 0; + +err_free_dma: + dmaengine_pcm_release_chan(pcm); + kfree(pcm); + return ret; } EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_register); @@ -345,7 +369,6 @@ void snd_dmaengine_pcm_unregister(struct device *dev) { struct snd_soc_platform *platform; struct dmaengine_pcm *pcm; - unsigned int i; platform = snd_soc_lookup_platform(dev); if (!platform) @@ -353,15 +376,8 @@ void snd_dmaengine_pcm_unregister(struct device *dev) pcm = soc_platform_to_pcm(platform); - for (i = SNDRV_PCM_STREAM_PLAYBACK; i <= SNDRV_PCM_STREAM_CAPTURE; i++) { - if (pcm->chan[i]) { - dma_release_channel(pcm->chan[i]); - if (pcm->flags & SND_DMAENGINE_PCM_FLAG_HALF_DUPLEX) - break; - } - } - snd_soc_remove_platform(platform); + dmaengine_pcm_release_chan(pcm); kfree(pcm); } EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_unregister); diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 11a90cd027fa..891b9a9bcbf8 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -600,12 +600,13 @@ static int soc_pcm_hw_free(struct snd_pcm_substream *substream) struct snd_soc_platform *platform = rtd->platform; struct snd_soc_dai *cpu_dai = rtd->cpu_dai; struct snd_soc_dai *codec_dai = rtd->codec_dai; - struct snd_soc_codec *codec = rtd->codec; + bool playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass); /* apply codec digital mute */ - if (!codec->active) + if ((playback && codec_dai->playback_active == 1) || + (!playback && codec_dai->capture_active == 1)) snd_soc_dai_digital_mute(codec_dai, 1, substream->stream); /* free any machine hw params */ diff --git a/sound/soc/tegra/tegra20_i2s.c b/sound/soc/tegra/tegra20_i2s.c index 364bf6a907e1..8c819f811470 100644 --- a/sound/soc/tegra/tegra20_i2s.c +++ b/sound/soc/tegra/tegra20_i2s.c @@ -74,7 +74,7 @@ static int tegra20_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { struct tegra20_i2s *i2s = snd_soc_dai_get_drvdata(dai); - unsigned int mask, val; + unsigned int mask = 0, val = 0; switch (fmt & SND_SOC_DAIFMT_INV_MASK) { case SND_SOC_DAIFMT_NB_NF: @@ -83,10 +83,10 @@ static int tegra20_i2s_set_fmt(struct snd_soc_dai *dai, return -EINVAL; } - mask = TEGRA20_I2S_CTRL_MASTER_ENABLE; + mask |= TEGRA20_I2S_CTRL_MASTER_ENABLE; switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { case SND_SOC_DAIFMT_CBS_CFS: - val = TEGRA20_I2S_CTRL_MASTER_ENABLE; + val |= TEGRA20_I2S_CTRL_MASTER_ENABLE; break; case SND_SOC_DAIFMT_CBM_CFM: break; diff --git a/sound/soc/tegra/tegra20_spdif.c b/sound/soc/tegra/tegra20_spdif.c index 08bc6931c7c7..8c7c1028e579 100644 --- a/sound/soc/tegra/tegra20_spdif.c +++ b/sound/soc/tegra/tegra20_spdif.c @@ -67,15 +67,15 @@ static int tegra20_spdif_hw_params(struct snd_pcm_substream *substream, { struct device *dev = dai->dev; struct tegra20_spdif *spdif = snd_soc_dai_get_drvdata(dai); - unsigned int mask, val; + unsigned int mask = 0, val = 0; int ret, spdifclock; - mask = TEGRA20_SPDIF_CTRL_PACK | - TEGRA20_SPDIF_CTRL_BIT_MODE_MASK; + mask |= TEGRA20_SPDIF_CTRL_PACK | + TEGRA20_SPDIF_CTRL_BIT_MODE_MASK; switch (params_format(params)) { case SNDRV_PCM_FORMAT_S16_LE: - val = TEGRA20_SPDIF_CTRL_PACK | - TEGRA20_SPDIF_CTRL_BIT_MODE_16BIT; + val |= TEGRA20_SPDIF_CTRL_PACK | + TEGRA20_SPDIF_CTRL_BIT_MODE_16BIT; break; default: return -EINVAL; diff --git a/sound/soc/tegra/tegra30_i2s.c b/sound/soc/tegra/tegra30_i2s.c index 231a785b3921..02247fee1cf7 100644 --- a/sound/soc/tegra/tegra30_i2s.c +++ b/sound/soc/tegra/tegra30_i2s.c @@ -118,7 +118,7 @@ static int tegra30_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { struct tegra30_i2s *i2s = snd_soc_dai_get_drvdata(dai); - unsigned int mask, val; + unsigned int mask = 0, val = 0; switch (fmt & SND_SOC_DAIFMT_INV_MASK) { case SND_SOC_DAIFMT_NB_NF: @@ -127,10 +127,10 @@ static int tegra30_i2s_set_fmt(struct snd_soc_dai *dai, return -EINVAL; } - mask = TEGRA30_I2S_CTRL_MASTER_ENABLE; + mask |= TEGRA30_I2S_CTRL_MASTER_ENABLE; switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { case SND_SOC_DAIFMT_CBS_CFS: - val = TEGRA30_I2S_CTRL_MASTER_ENABLE; + val |= TEGRA30_I2S_CTRL_MASTER_ENABLE; break; case SND_SOC_DAIFMT_CBM_CFM: break; diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c index dc4de3762111..bcf1d2f0b791 100644 --- a/tools/power/cpupower/utils/cpupower-set.c +++ b/tools/power/cpupower/utils/cpupower-set.c @@ -18,9 +18,9 @@ #include "helpers/bitmask.h" static struct option set_opts[] = { - { .name = "perf-bias", .has_arg = optional_argument, .flag = NULL, .val = 'b'}, - { .name = "sched-mc", .has_arg = optional_argument, .flag = NULL, .val = 'm'}, - { .name = "sched-smt", .has_arg = optional_argument, .flag = NULL, .val = 's'}, + { .name = "perf-bias", .has_arg = required_argument, .flag = NULL, .val = 'b'}, + { .name = "sched-mc", .has_arg = required_argument, .flag = NULL, .val = 'm'}, + { .name = "sched-smt", .has_arg = required_argument, .flag = NULL, .val = 's'}, { }, }; |