diff options
141 files changed, 1537 insertions, 672 deletions
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index de79efdad46c..8c68768ebee5 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -128,16 +128,44 @@ X!Edrivers/base/interface.c !Edrivers/base/platform.c !Edrivers/base/bus.c </sect1> - <sect1><title>Device Drivers DMA Management</title> + <sect1> + <title>Buffer Sharing and Synchronization</title> + <para> + The dma-buf subsystem provides the framework for sharing buffers + for hardware (DMA) access across multiple device drivers and + subsystems, and for synchronizing asynchronous hardware access. + </para> + <para> + This is used, for example, by drm "prime" multi-GPU support, but + is of course not limited to GPU use cases. + </para> + <para> + The three main components of this are: (1) dma-buf, representing + a sg_table and exposed to userspace as a file descriptor to allow + passing between devices, (2) fence, which provides a mechanism + to signal when one device as finished access, and (3) reservation, + which manages the shared or exclusive fence(s) associated with + the buffer. + </para> + <sect2><title>dma-buf</title> !Edrivers/dma-buf/dma-buf.c +!Iinclude/linux/dma-buf.h + </sect2> + <sect2><title>reservation</title> +!Pdrivers/dma-buf/reservation.c Reservation Object Overview +!Edrivers/dma-buf/reservation.c +!Iinclude/linux/reservation.h + </sect2> + <sect2><title>fence</title> !Edrivers/dma-buf/fence.c -!Edrivers/dma-buf/seqno-fence.c !Iinclude/linux/fence.h +!Edrivers/dma-buf/seqno-fence.c !Iinclude/linux/seqno-fence.h -!Edrivers/dma-buf/reservation.c -!Iinclude/linux/reservation.h !Edrivers/dma-buf/sync_file.c !Iinclude/linux/sync_file.h + </sect2> + </sect1> + <sect1><title>Device Drivers DMA Management</title> !Edrivers/base/dma-coherent.c !Edrivers/base/dma-mapping.c </sect1> diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index 631b0f7ae16f..9d05ed7f7da5 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -369,8 +369,6 @@ does not allocate any driver private context space. Switch configuration -------------------- -- priv_size: additional size needed by the switch driver for its private context - - tag_protocol: this is to indicate what kind of tagging protocol is supported, should be a valid value from the dsa_tag_protocol enum @@ -416,11 +414,6 @@ PHY devices and link management to the switch port MDIO registers. If unavailable return a negative error code. -- poll_link: Function invoked by DSA to query the link state of the switch - builtin Ethernet PHYs, per port. This function is responsible for calling - netif_carrier_{on,off} when appropriate, and can be used to poll all ports in a - single call. Executes from workqueue context. - - adjust_link: Function invoked by the PHY library when a slave network device is attached to a PHY device. This function is responsible for appropriately configuring the switch port link parameters: speed, duplex, pause based on @@ -542,6 +535,16 @@ Bridge layer Bridge VLAN filtering --------------------- +- port_vlan_filtering: bridge layer function invoked when the bridge gets + configured for turning on or off VLAN filtering. If nothing specific needs to + be done at the hardware level, this callback does not need to be implemented. + When VLAN filtering is turned on, the hardware must be programmed with + rejecting 802.1Q frames which have VLAN IDs outside of the programmed allowed + VLAN ID map/rules. If there is no PVID programmed into the switch port, + untagged frames must be rejected as well. When turned off the switch must + accept any 802.1Q frames irrespective of their VLAN ID, and untagged frames are + allowed. + - port_vlan_prepare: bridge layer function invoked when the bridge prepares the configuration of a VLAN on the given port. If the operation is not supported by the hardware, this function should return -EOPNOTSUPP to inform the bridge diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 6c7f365b1515..9ae929395b24 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1036,15 +1036,17 @@ proxy_arp_pvlan - BOOLEAN shared_media - BOOLEAN Send(router) or accept(host) RFC1620 shared media redirects. - Overrides ip_secure_redirects. + Overrides secure_redirects. shared_media for the interface will be enabled if at least one of conf/{all,interface}/shared_media is set to TRUE, it will be disabled otherwise default TRUE secure_redirects - BOOLEAN - Accept ICMP redirect messages only for gateways, - listed in default gateway list. + Accept ICMP redirect messages only to gateways listed in the + interface's current gateway list. Even if disabled, RFC1122 redirect + rules still apply. + Overridden by shared_media. secure_redirects for the interface will be enabled if at least one of conf/{all,interface}/secure_redirects is set to TRUE, it will be disabled otherwise diff --git a/MAINTAINERS b/MAINTAINERS index 7304d2e37a98..ed42cb65a19b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7989,6 +7989,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ 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/davem/net-next.git S: Odd Fixes +F: Documentation/devicetree/bindings/net/ F: drivers/net/ F: include/linux/if_* F: include/linux/netdevice.h @@ -8944,6 +8945,7 @@ M: Linus Walleij <linus.walleij@linaro.org> L: linux-gpio@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git S: Maintained +F: Documentation/devicetree/bindings/pinctrl/ F: drivers/pinctrl/ F: include/linux/pinctrl/ diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index ef9119f7462e..4d9375814b53 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target, if (ret) return ret; - vfp_flush_hwstate(thread); thread->vfpstate.hard = new_vfp; + vfp_flush_hwstate(thread); return 0; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 57a9f67971d3..5a0a691d4220 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -113,6 +113,18 @@ config ARCH_PHYS_ADDR_T_64BIT config MMU def_bool y +config ARM64_PAGE_SHIFT + int + default 16 if ARM64_64K_PAGES + default 14 if ARM64_16K_PAGES + default 12 + +config ARM64_CONT_SHIFT + int + default 5 if ARM64_64K_PAGES + default 7 if ARM64_16K_PAGES + default 4 + config ARCH_MMAP_RND_BITS_MIN default 14 if ARM64_64K_PAGES default 16 if ARM64_16K_PAGES diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index 710fde4ad0f0..0cc758cdd0dc 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -12,7 +12,8 @@ config ARM64_PTDUMP who are working in architecture specific areas of the kernel. It is probably not a good idea to enable this feature in a production kernel. - If in doubt, say "N" + + If in doubt, say N. config PID_IN_CONTEXTIDR bool "Write the current PID to the CONTEXTIDR register" @@ -38,15 +39,15 @@ config ARM64_RANDOMIZE_TEXT_OFFSET value. config DEBUG_SET_MODULE_RONX - bool "Set loadable kernel module data as NX and text as RO" - depends on MODULES - help - This option helps catch unintended modifications to loadable - kernel module's text and read-only data. It also prevents execution - of module data. Such protection may interfere with run-time code - patching and dynamic kernel tracing - and they might also protect - against certain classes of kernel exploits. - If in doubt, say "N". + bool "Set loadable kernel module data as NX and text as RO" + depends on MODULES + default y + help + Is this is set, kernel module text and rodata will be made read-only. + This is to help catch accidental or malicious attempts to change the + kernel's executable code. + + If in doubt, say Y. config DEBUG_RODATA bool "Make kernel text and rodata read-only" @@ -56,7 +57,7 @@ config DEBUG_RODATA is to help catch accidental or malicious attempts to change the kernel's executable code. - If in doubt, say Y + If in doubt, say Y. config DEBUG_ALIGN_RODATA depends on DEBUG_RODATA @@ -69,7 +70,7 @@ config DEBUG_ALIGN_RODATA alignment and potentially wasted space. Turn on this option if performance is more important than memory pressure. - If in doubt, say N + If in doubt, say N. source "drivers/hwtracing/coresight/Kconfig" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 354d75402ace..7085e322dc42 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -60,7 +60,9 @@ head-y := arch/arm64/kernel/head.o # The byte offset of the kernel image in RAM from the start of RAM. ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y) -TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}') +TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \ + int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \ + rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}") else TEXT_OFFSET := 0x00080000 endif diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 7a09c48c0475..579b6e654f2d 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -160,14 +160,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #define STACK_RND_MASK (0x3ffff >> (PAGE_SHIFT - 12)) #endif -#ifdef CONFIG_COMPAT - #ifdef __AARCH64EB__ #define COMPAT_ELF_PLATFORM ("v8b") #else #define COMPAT_ELF_PLATFORM ("v8l") #endif +#ifdef CONFIG_COMPAT + #define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3) /* AArch32 registers. */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 72a3025bb583..31b73227b41f 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -55,8 +55,9 @@ #define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)) /* - * PAGE_OFFSET - the virtual address of the start of the kernel image (top + * PAGE_OFFSET - the virtual address of the start of the linear map (top * (VA_BITS - 1)) + * KIMAGE_VADDR - the virtual address of the start of the kernel image * VA_BITS - the maximum number of bits for virtual addresses. * VA_START - the first kernel virtual address. * TASK_SIZE - the maximum size of a user space task. diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index 17b45f7d96d3..8472c6def5ef 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -23,16 +23,8 @@ /* PAGE_SHIFT determines the page size */ /* CONT_SHIFT determines the number of pages which can be tracked together */ -#ifdef CONFIG_ARM64_64K_PAGES -#define PAGE_SHIFT 16 -#define CONT_SHIFT 5 -#elif defined(CONFIG_ARM64_16K_PAGES) -#define PAGE_SHIFT 14 -#define CONT_SHIFT 7 -#else -#define PAGE_SHIFT 12 -#define CONT_SHIFT 4 -#endif +#define PAGE_SHIFT CONFIG_ARM64_PAGE_SHIFT +#define CONT_SHIFT CONFIG_ARM64_CONT_SHIFT #define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 0685d74572af..9e397a542756 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -81,19 +81,6 @@ static inline void set_fs(mm_segment_t fs) #define segment_eq(a, b) ((a) == (b)) /* - * Return 1 if addr < current->addr_limit, 0 otherwise. - */ -#define __addr_ok(addr) \ -({ \ - unsigned long flag; \ - asm("cmp %1, %0; cset %0, lo" \ - : "=&r" (flag) \ - : "r" (addr), "0" (current_thread_info()->addr_limit) \ - : "cc"); \ - flag; \ -}) - -/* * Test whether a block of memory is a valid user space address. * Returns 1 if the range is valid, 0 otherwise. * diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 41e58fe3c041..e78ac26324bd 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2) #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5) -#define __NR_compat_syscalls 390 +#define __NR_compat_syscalls 394 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 5b925b761a2a..b7e8ef16ff0d 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -801,6 +801,14 @@ __SYSCALL(__NR_execveat, compat_sys_execveat) __SYSCALL(__NR_userfaultfd, sys_userfaultfd) #define __NR_membarrier 389 __SYSCALL(__NR_membarrier, sys_membarrier) +#define __NR_mlock2 390 +__SYSCALL(__NR_mlock2, sys_mlock2) +#define __NR_copy_file_range 391 +__SYSCALL(__NR_copy_file_range, sys_copy_file_range) +#define __NR_preadv2 392 +__SYSCALL(__NR_preadv2, compat_sys_preadv2) +#define __NR_pwritev2 393 +__SYSCALL(__NR_pwritev2, compat_sys_pwritev2) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 3808470486f3..c173d329397f 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -22,6 +22,8 @@ #include <linux/bitops.h> #include <linux/bug.h> +#include <linux/compat.h> +#include <linux/elf.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/personality.h> @@ -104,6 +106,7 @@ static const char *const compat_hwcap2_str[] = { static int c_show(struct seq_file *m, void *v) { int i, j; + bool compat = personality(current->personality) == PER_LINUX32; for_each_online_cpu(i) { struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i); @@ -115,6 +118,9 @@ static int c_show(struct seq_file *m, void *v) * "processor". Give glibc what it expects. */ seq_printf(m, "processor\t: %d\n", i); + if (compat) + seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n", + MIDR_REVISION(midr), COMPAT_ELF_PLATFORM); seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", loops_per_jiffy / (500000UL/HZ), @@ -127,7 +133,7 @@ static int c_show(struct seq_file *m, void *v) * software which does already (at least for 32-bit). */ seq_puts(m, "Features\t:"); - if (personality(current->personality) == PER_LINUX32) { + if (compat) { #ifdef CONFIG_COMPAT for (j = 0; compat_hwcap_str[j]; j++) if (compat_elf_hwcap & (1 << j)) diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index c5392081b49b..f7cf463107df 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -477,8 +477,9 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) void __user *pc = (void __user *)instruction_pointer(regs); console_verbose(); - pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n", - handler[reason], esr, esr_get_class_string(esr)); + pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n", + handler[reason], smp_processor_id(), esr, + esr_get_class_string(esr)); __show_regs(regs); info.si_signo = SIGILL; diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index fff7cd42b3a3..5f8f80b4a224 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -169,7 +169,8 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu) * Make sure stores to the GIC via the memory mapped interface * are now visible to the system register interface. */ - dsb(st); + if (!cpu_if->vgic_sre) + dsb(st); cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2); @@ -190,12 +191,11 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu) if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i))) continue; - if (cpu_if->vgic_elrsr & (1 << i)) { + if (cpu_if->vgic_elrsr & (1 << i)) cpu_if->vgic_lr[i] &= ~ICH_LR_STATE; - continue; - } + else + cpu_if->vgic_lr[i] = __gic_v3_get_lr(i); - cpu_if->vgic_lr[i] = __gic_v3_get_lr(i); __gic_v3_set_lr(0, i); } @@ -236,8 +236,12 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu) val = read_gicreg(ICC_SRE_EL2); write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); - isb(); /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */ - write_gicreg(1, ICC_SRE_EL1); + + if (!cpu_if->vgic_sre) { + /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */ + isb(); + write_gicreg(1, ICC_SRE_EL1); + } } void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) @@ -256,8 +260,10 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) * been actually programmed with the value we want before * starting to mess with the rest of the GIC. */ - write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1); - isb(); + if (!cpu_if->vgic_sre) { + write_gicreg(0, ICC_SRE_EL1); + isb(); + } val = read_gicreg(ICH_VTR_EL2); max_lr_idx = vtr_to_max_lr_idx(val); @@ -306,18 +312,18 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) * (re)distributors. This ensure the guest will read the * correct values from the memory-mapped interface. */ - isb(); - dsb(sy); + if (!cpu_if->vgic_sre) { + isb(); + dsb(sy); + } vcpu->arch.vgic_cpu.live_lrs = live_lrs; /* * Prevent the guest from touching the GIC system registers if * SRE isn't enabled for GICv3 emulation. */ - if (!cpu_if->vgic_sre) { - write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE, - ICC_SRE_EL2); - } + write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE, + ICC_SRE_EL2); } void __hyp_text __vgic_v3_init_lrs(void) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7bbe3ff02602..a57d650f552c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -134,6 +134,17 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu, return true; } +static bool access_gic_sre(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre; + return true; +} + static bool trap_raz_wi(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) @@ -958,7 +969,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { access_gic_sgi }, /* ICC_SRE_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101), - trap_raz_wi }, + access_gic_sre }, /* CONTEXTIDR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001), diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 8404190fe2bd..ccfde237d6e6 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -150,6 +150,7 @@ static const struct prot_bits pte_bits[] = { struct pg_level { const struct prot_bits *bits; + const char *name; size_t num; u64 mask; }; @@ -157,15 +158,19 @@ struct pg_level { static struct pg_level pg_level[] = { { }, { /* pgd */ + .name = "PGD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pud */ + .name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pmd */ + .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pte */ + .name = "PTE", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, @@ -214,7 +219,8 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, delta >>= 10; unit++; } - seq_printf(st->seq, "%9lu%c", delta, *unit); + seq_printf(st->seq, "%9lu%c %s", delta, *unit, + pg_level[st->level].name); if (pg_level[st->level].bits) dump_prot(st, pg_level[st->level].bits, pg_level[st->level].num); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index aa8aee7d6929..2e49bd252fe7 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -306,6 +306,10 @@ static __init int setup_hugepagesz(char *opt) hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else if (ps == (PAGE_SIZE * CONT_PTES)) { + hugetlb_add_hstate(CONT_PTE_SHIFT); + } else if (ps == (PMD_SIZE * CONT_PMDS)) { + hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT); } else { hugetlb_bad_size(); pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); @@ -314,3 +318,13 @@ static __init int setup_hugepagesz(char *opt) return 1; } __setup("hugepagesz=", setup_hugepagesz); + +#ifdef CONFIG_ARM64_64K_PAGES +static __init int add_default_hugepagesz(void) +{ + if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) + hugetlb_add_hstate(CONT_PMD_SHIFT); + return 0; +} +arch_initcall(add_default_hugepagesz); +#endif diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c1e82e968506..a0948f40bc7b 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -717,7 +717,7 @@ #define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 -#define SPRN_MMCR2 769 +#define SPRN_MMCR2 785 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -754,13 +754,13 @@ #define SPRN_PMC6 792 #define SPRN_PMC7 793 #define SPRN_PMC8 794 -#define SPRN_SIAR 780 -#define SPRN_SDAR 781 #define SPRN_SIER 784 #define SIER_SIPR 0x2000000 /* Sampled MSR_PR */ #define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ #define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ #define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ +#define SPRN_SIAR 796 +#define SPRN_SDAR 797 #define SPRN_TACR 888 #define SPRN_TCSCR 889 #define SPRN_CSIGR 890 diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index da5192590c44..ccd2037c797f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -656,6 +656,7 @@ unsigned char ibm_architecture_vec[] = { W(0xffff0000), W(0x003e0000), /* POWER6 */ W(0xffff0000), W(0x003f0000), /* POWER7 */ W(0xffff0000), W(0x004b0000), /* POWER8E */ + W(0xffff0000), W(0x004c0000), /* POWER8NVL */ W(0xffff0000), W(0x004d0000), /* POWER8 */ W(0xffffffff), W(0x0f000004), /* all 2.07-compliant */ W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */ diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 59268969a0bc..b2740c67e172 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -159,6 +159,19 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = { }, }; +/* + * 'R' and 'C' update notes: + * - Under pHyp or KVM, the updatepp path will not set C, thus it *will* + * create writeable HPTEs without C set, because the hcall H_PROTECT + * that we use in that case will not update C + * - The above is however not a problem, because we also don't do that + * fancy "no flush" variant of eviction and we use H_REMOVE which will + * do the right thing and thus we don't have the race I described earlier + * + * - Under bare metal, we do have the race, so we need R and C set + * - We make sure R is always set and never lost + * - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping + */ unsigned long htab_convert_pte_flags(unsigned long pteflags) { unsigned long rflags = 0; @@ -186,9 +199,14 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) rflags |= 0x1; } /* - * Always add "C" bit for perf. Memory coherence is always enabled + * We can't allow hardware to update hpte bits. Hence always + * set 'R' bit and set 'C' if it is a write fault + * Memory coherence is always enabled */ - rflags |= HPTE_R_C | HPTE_R_M; + rflags |= HPTE_R_R | HPTE_R_M; + + if (pteflags & _PAGE_DIRTY) + rflags |= HPTE_R_C; /* * Add in WIG bits */ diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index eb4451144746..670318766545 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -33,10 +33,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, changed = !pmd_same(*(pmdp), entry); if (changed) { __ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry)); - /* - * Since we are not supporting SW TLB systems, we don't - * have any thing similar to flush_tlb_page_nohash() - */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 18b2c11604fa..c939e6e57a9e 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -296,11 +296,6 @@ found: void __init radix__early_init_mmu(void) { unsigned long lpcr; - /* - * setup LPCR UPRT based on mmu_features - */ - lpcr = mfspr(SPRN_LPCR); - mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); #ifdef CONFIG_PPC_64K_PAGES /* PAGE_SIZE mappings */ @@ -343,8 +338,11 @@ void __init radix__early_init_mmu(void) __pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT; radix_init_page_sizes(); - if (!firmware_has_feature(FW_FEATURE_LPAR)) + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); radix_init_partition_table(); + } radix_init_pgtable(); } @@ -353,16 +351,15 @@ void radix__early_init_mmu_secondary(void) { unsigned long lpcr; /* - * setup LPCR UPRT based on mmu_features + * update partition table control register and UPRT */ - lpcr = mfspr(SPRN_LPCR); - mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); - /* - * update partition table control register, 64 K size. - */ - if (!firmware_has_feature(FW_FEATURE_LPAR)) + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); + mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); + } } void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index ac3ffd97e059..3998e0f9a03b 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -53,7 +53,6 @@ static int ibm_read_slot_reset_state2; static int ibm_slot_error_detail; static int ibm_get_config_addr_info; static int ibm_get_config_addr_info2; -static int ibm_configure_bridge; static int ibm_configure_pe; /* @@ -81,7 +80,14 @@ static int pseries_eeh_init(void) ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); ibm_configure_pe = rtas_token("ibm,configure-pe"); - ibm_configure_bridge = rtas_token("ibm,configure-bridge"); + + /* + * ibm,configure-pe and ibm,configure-bridge have the same semantics, + * however ibm,configure-pe can be faster. If we can't find + * ibm,configure-pe then fall back to using ibm,configure-bridge. + */ + if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE) + ibm_configure_pe = rtas_token("ibm,configure-bridge"); /* * Necessary sanity check. We needn't check "get-config-addr-info" @@ -93,8 +99,7 @@ static int pseries_eeh_init(void) (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE && ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) || ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE || - (ibm_configure_pe == RTAS_UNKNOWN_SERVICE && - ibm_configure_bridge == RTAS_UNKNOWN_SERVICE)) { + ibm_configure_pe == RTAS_UNKNOWN_SERVICE) { pr_info("EEH functionality not supported\n"); return -EINVAL; } @@ -615,29 +620,41 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { int config_addr; int ret; + /* Waiting 0.2s maximum before skipping configuration */ + int max_wait = 200; /* Figure out the PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - /* Use new configure-pe function, if supported */ - if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { + while (max_wait > 0) { ret = rtas_call(ibm_configure_pe, 3, 1, NULL, config_addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid)); - } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else { - return -EFAULT; - } - if (ret) - pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", - __func__, pe->phb->global_number, pe->addr, ret); + if (!ret) + return ret; + + /* + * If RTAS returns a delay value that's above 100ms, cut it + * down to 100ms in case firmware made a mistake. For more + * on how these delay values work see rtas_busy_delay_time + */ + if (ret > RTAS_EXTENDED_DELAY_MIN+2 && + ret <= RTAS_EXTENDED_DELAY_MAX) + ret = RTAS_EXTENDED_DELAY_MIN+2; + + max_wait -= rtas_busy_delay_time(ret); + + if (max_wait < 0) + break; + + rtas_busy_delay(ret); + } + pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, ret); return ret; } diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 0ac42cc4f880..d5ec71b2ed02 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -1,8 +1,7 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_AUDIT=y -CONFIG_NO_HZ=y +CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y @@ -13,19 +12,19 @@ CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_PIDS=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CPUSETS=y -CONFIG_CGROUP_CPUACCT=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y -CONFIG_MEMCG_KMEM=y -CONFIG_CGROUP_HUGETLB=y -CONFIG_CGROUP_PERF=y +CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y -CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y @@ -55,7 +54,6 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_CFQ_GROUP_IOSCHED=y CONFIG_DEFAULT_DEADLINE=y CONFIG_LIVEPATCH=y -CONFIG_MARCH_Z196=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=256 CONFIG_NUMA=y @@ -65,6 +63,15 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_CLEANCACHE=y +CONFIG_FRONTSWAP=y +CONFIG_CMA=y +CONFIG_MEM_SOFT_DIRTY=y +CONFIG_ZPOOL=m +CONFIG_ZBUD=m +CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC_STAT=y +CONFIG_IDLE_PAGE_TRACKING=y CONFIG_PCI=y CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y @@ -452,6 +459,7 @@ CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m CONFIG_HANGCHECK_TIMER=m CONFIG_TN3270_FS=y +# CONFIG_HWMON is not set CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m @@ -537,6 +545,8 @@ CONFIG_DLM=m CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 CONFIG_READABLE_ASM=y CONFIG_UNUSED_SYMBOLS=y @@ -555,13 +565,17 @@ CONFIG_SLUB_DEBUG_ON=y CONFIG_SLUB_STATS=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_VM=y +CONFIG_DEBUG_VM_VMACACHE=y CONFIG_DEBUG_VM_RB=y +CONFIG_DEBUG_VM_PGFLAGS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_DEBUG_SHIRQ=y CONFIG_DETECT_HUNG_TASK=y +CONFIG_WQ_WATCHDOG=y CONFIG_PANIC_ON_OOPS=y +CONFIG_DEBUG_TIMEKEEPING=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y @@ -596,6 +610,8 @@ CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_UPROBE_EVENT=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_TRACE_ENUM_MAP_FILE=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y CONFIG_KPROBES_SANITY_TEST=y @@ -607,7 +623,6 @@ CONFIG_TEST_STRING_HELPERS=y CONFIG_TEST_KSTRTOX=y CONFIG_DMA_API_DEBUG=y CONFIG_TEST_BPF=m -# CONFIG_STRICT_DEVMEM is not set CONFIG_S390_PTDUMP=y CONFIG_ENCRYPTED_KEYS=m CONFIG_SECURITY=y @@ -651,7 +666,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=y CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m @@ -664,7 +678,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_ASYMMETRIC_KEY_TYPE=m +CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m CONFIG_CRC7=m diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index a31dcd56f7c0..f46a35115d2d 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -1,8 +1,7 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_AUDIT=y -CONFIG_NO_HZ=y +CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y @@ -13,17 +12,17 @@ CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_PIDS=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CPUSETS=y -CONFIG_CGROUP_CPUACCT=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y -CONFIG_MEMCG_KMEM=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y -CONFIG_BLK_CGROUP=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y @@ -53,7 +52,6 @@ CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y CONFIG_CFQ_GROUP_IOSCHED=y CONFIG_DEFAULT_DEADLINE=y -CONFIG_MARCH_Z196=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=256 CONFIG_NUMA=y @@ -62,6 +60,14 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_CLEANCACHE=y +CONFIG_FRONTSWAP=y +CONFIG_CMA=y +CONFIG_ZSWAP=y +CONFIG_ZBUD=m +CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC_STAT=y +CONFIG_IDLE_PAGE_TRACKING=y CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y @@ -530,6 +536,8 @@ CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_FRAME_WARN=1024 CONFIG_UNUSED_SYMBOLS=y @@ -547,13 +555,13 @@ CONFIG_LATENCYTOP=y CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_KPROBE_EVENT is not set +CONFIG_TRACE_ENUM_MAP_FILE=y CONFIG_LKDTM=m CONFIG_RBTREE_TEST=m CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -# CONFIG_STRICT_DEVMEM is not set CONFIG_S390_PTDUMP=y CONFIG_ENCRYPTED_KEYS=m CONFIG_SECURITY=y @@ -597,8 +605,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=y -CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m CONFIG_CRYPTO_USER_API_HASH=m @@ -610,7 +616,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_ASYMMETRIC_KEY_TYPE=m +CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m CONFIG_CRC7=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 7b73bf353345..ba0f2a58b8cd 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -1,8 +1,7 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_AUDIT=y -CONFIG_NO_HZ=y +CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y @@ -14,17 +13,17 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y # CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_PIDS=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CPUSETS=y -CONFIG_CGROUP_CPUACCT=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y -CONFIG_MEMCG_KMEM=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y -CONFIG_BLK_CGROUP=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y @@ -53,7 +52,6 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_CFQ_GROUP_IOSCHED=y CONFIG_DEFAULT_DEADLINE=y CONFIG_LIVEPATCH=y -CONFIG_MARCH_Z196=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y @@ -62,6 +60,14 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_CLEANCACHE=y +CONFIG_FRONTSWAP=y +CONFIG_CMA=y +CONFIG_ZSWAP=y +CONFIG_ZBUD=m +CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC_STAT=y +CONFIG_IDLE_PAGE_TRACKING=y CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y @@ -447,6 +453,7 @@ CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m CONFIG_HANGCHECK_TIMER=m CONFIG_TN3270_FS=y +# CONFIG_HWMON is not set CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m @@ -530,6 +537,8 @@ CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_FRAME_WARN=1024 CONFIG_UNUSED_SYMBOLS=y @@ -546,11 +555,12 @@ CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_UPROBE_EVENT=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_TRACE_ENUM_MAP_FILE=y CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -# CONFIG_STRICT_DEVMEM is not set CONFIG_S390_PTDUMP=y CONFIG_ENCRYPTED_KEYS=m CONFIG_SECURITY=y @@ -594,8 +604,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=y -CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m CONFIG_CRYPTO_USER_API_HASH=m @@ -607,7 +615,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_ASYMMETRIC_KEY_TYPE=m +CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m CONFIG_CRC7=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 1719843a55a2..4366a3e3e754 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -1,5 +1,5 @@ # CONFIG_SWAP is not set -CONFIG_NO_HZ=y +CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -7,7 +7,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y -CONFIG_MARCH_Z196=y CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 @@ -64,7 +63,6 @@ CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 # CONFIG_FTRACE is not set -# CONFIG_STRICT_DEVMEM is not set # CONFIG_PFAULT is not set # CONFIG_S390_HYPFS_FS is not set # CONFIG_VIRTUALIZATION is not set diff --git a/arch/s390/defconfig b/arch/s390/defconfig index e24f2af4c73b..3f571ea89509 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,8 +1,8 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y +CONFIG_USELIB=y CONFIG_AUDIT=y -CONFIG_NO_HZ=y +CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y @@ -11,19 +11,19 @@ CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_CGROUPS=y -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_PIDS=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CPUSETS=y -CONFIG_CGROUP_CPUACCT=y CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y -CONFIG_MEMCG_KMEM=y -CONFIG_CGROUP_HUGETLB=y -CONFIG_CGROUP_PERF=y +CONFIG_BLK_CGROUP=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y -CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y @@ -44,7 +44,6 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y CONFIG_LIVEPATCH=y -CONFIG_MARCH_Z196=y CONFIG_NR_CPUS=256 CONFIG_NUMA=y CONFIG_HZ_100=y @@ -52,6 +51,14 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_CLEANCACHE=y +CONFIG_FRONTSWAP=y +CONFIG_CMA=y +CONFIG_ZSWAP=y +CONFIG_ZBUD=m +CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC_STAT=y +CONFIG_IDLE_PAGE_TRACKING=y CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y @@ -61,7 +68,6 @@ CONFIG_UNIX=y CONFIG_NET_KEY=y CONFIG_INET=y CONFIG_IP_MULTICAST=y -# CONFIG_INET_LRO is not set CONFIG_L2TP=m CONFIG_L2TP_DEBUGFS=m CONFIG_VLAN_8021Q=y @@ -144,6 +150,9 @@ CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y # CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y @@ -158,20 +167,21 @@ CONFIG_LOCK_STAT=y CONFIG_DEBUG_LOCKDEP=y CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_PI_LIST=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_RCU_TRACE=y CONFIG_LATENCYTOP=y CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y -CONFIG_TRACER_SNAPSHOT=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_UPROBE_EVENT=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_TRACE_ENUM_MAP_FILE=y CONFIG_KPROBES_SANITY_TEST=y -# CONFIG_STRICT_DEVMEM is not set CONFIG_S390_PTDUMP=y CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_AUTHENC=m @@ -212,8 +222,6 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m -CONFIG_CRYPTO_ZLIB=m -CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m CONFIG_CRYPTO_ANSI_CPRNG=m diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 7a3144017301..19288c1b36d3 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -250,6 +250,7 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code) report_user_fault(regs, SIGSEGV, 1); si.si_signo = SIGSEGV; + si.si_errno = 0; si.si_code = si_code; si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK); force_sig_info(SIGSEGV, &si, current); diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h index f010c93a88b1..fda605dbc1b4 100644 --- a/arch/s390/net/bpf_jit.h +++ b/arch/s390/net/bpf_jit.h @@ -37,7 +37,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; * | | | * +---------------+ | * | 8 byte skbp | | - * R15+170 -> +---------------+ | + * R15+176 -> +---------------+ | * | 8 byte hlen | | * R15+168 -> +---------------+ | * | 4 byte align | | @@ -58,7 +58,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; #define STK_OFF (STK_SPACE - STK_160_UNUSED) #define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */ #define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */ -#define STK_OFF_SKBP 170 /* Offset of SKB pointer on stack */ +#define STK_OFF_SKBP 176 /* Offset of SKB pointer on stack */ #define STK_OFF_R6 (160 - 11 * 8) /* Offset of r6 on stack */ #define STK_OFF_TCCNT (160 - 12 * 8) /* Offset of tail_call_cnt on stack */ diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 9133b0ec000b..bee281f3163d 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -45,7 +45,7 @@ struct bpf_jit { int labels[1]; /* Labels for local jumps */ }; -#define BPF_SIZE_MAX 0x7ffff /* Max size for program (20 bit signed displ) */ +#define BPF_SIZE_MAX 0xffff /* Max size for program (16 bit branches) */ #define SEEN_SKB 1 /* skb access */ #define SEEN_MEM 2 /* use mem[] for temporary storage */ @@ -450,7 +450,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit) emit_load_skb_data_hlen(jit); if (jit->seen & SEEN_SKB_CHANGE) /* stg %b1,ST_OFF_SKBP(%r0,%r15) */ - EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, + EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15, STK_OFF_SKBP); } diff --git a/arch/sparc/include/asm/head_64.h b/arch/sparc/include/asm/head_64.h index 10e9dabc4c41..f0700cfeedd7 100644 --- a/arch/sparc/include/asm/head_64.h +++ b/arch/sparc/include/asm/head_64.h @@ -15,6 +15,10 @@ #define PTREGS_OFF (STACK_BIAS + STACKFRAME_SZ) +#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE) +#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV) +#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG) + #define __CHEETAH_ID 0x003e0014 #define __JALAPENO_ID 0x003e0016 #define __SERRANO_ID 0x003e0022 diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h index 71b5a67522ab..781b9f1dbdc2 100644 --- a/arch/sparc/include/asm/ttable.h +++ b/arch/sparc/include/asm/ttable.h @@ -589,8 +589,8 @@ user_rtt_fill_64bit: \ restored; \ nop; nop; nop; nop; nop; nop; \ nop; nop; nop; nop; nop; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ + ba,a,pt %xcc, user_rtt_fill_fixup_dax; \ + ba,a,pt %xcc, user_rtt_fill_fixup_mna; \ ba,a,pt %xcc, user_rtt_fill_fixup; @@ -652,8 +652,8 @@ user_rtt_fill_32bit: \ restored; \ nop; nop; nop; nop; nop; \ nop; nop; nop; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ + ba,a,pt %xcc, user_rtt_fill_fixup_dax; \ + ba,a,pt %xcc, user_rtt_fill_fixup_mna; \ ba,a,pt %xcc, user_rtt_fill_fixup; diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index 7cf9c6ea3f1f..fdb13327fded 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg CFLAGS_REMOVE_pcr.o := -pg endif +obj-$(CONFIG_SPARC64) += urtt_fill.o obj-$(CONFIG_SPARC32) += entry.o wof.o wuf.o obj-$(CONFIG_SPARC32) += etrap_32.o obj-$(CONFIG_SPARC32) += rtrap_32.o diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index d08bdaffdbfc..216948ca4382 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -14,10 +14,6 @@ #include <asm/visasm.h> #include <asm/processor.h> -#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE) -#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV) -#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG) - #ifdef CONFIG_CONTEXT_TRACKING # define SCHEDULE_USER schedule_user #else @@ -242,52 +238,17 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 wrpr %g1, %cwp ba,a,pt %xcc, user_rtt_fill_64bit -user_rtt_fill_fixup: - rdpr %cwp, %g1 - add %g1, 1, %g1 - wrpr %g1, 0x0, %cwp - - rdpr %wstate, %g2 - sll %g2, 3, %g2 - wrpr %g2, 0x0, %wstate - - /* We know %canrestore and %otherwin are both zero. */ - - sethi %hi(sparc64_kern_pri_context), %g2 - ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2 - mov PRIMARY_CONTEXT, %g1 - -661: stxa %g2, [%g1] ASI_DMMU - .section .sun4v_1insn_patch, "ax" - .word 661b - stxa %g2, [%g1] ASI_MMU - .previous - - sethi %hi(KERNBASE), %g1 - flush %g1 +user_rtt_fill_fixup_dax: + ba,pt %xcc, user_rtt_fill_fixup_common + mov 1, %g3 - or %g4, FAULT_CODE_WINFIXUP, %g4 - stb %g4, [%g6 + TI_FAULT_CODE] - stx %g5, [%g6 + TI_FAULT_ADDR] +user_rtt_fill_fixup_mna: + ba,pt %xcc, user_rtt_fill_fixup_common + mov 2, %g3 - mov %g6, %l1 - wrpr %g0, 0x0, %tl - -661: nop - .section .sun4v_1insn_patch, "ax" - .word 661b - SET_GL(0) - .previous - - wrpr %g0, RTRAP_PSTATE, %pstate - - mov %l1, %g6 - ldx [%g6 + TI_TASK], %g4 - LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3) - call do_sparc64_fault - add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop +user_rtt_fill_fixup: + ba,pt %xcc, user_rtt_fill_fixup_common + clr %g3 user_rtt_pre_restore: add %g1, 1, %g1 diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 3c25241fa5cb..91cc2f4ae4d9 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -138,12 +138,24 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) return 0; } +/* Checks if the fp is valid. We always build signal frames which are + * 16-byte aligned, therefore we can always enforce that the restore + * frame has that property as well. + */ +static bool invalid_frame_pointer(void __user *fp, int fplen) +{ + if ((((unsigned long) fp) & 15) || + ((unsigned long)fp) > 0x100000000ULL - fplen) + return true; + return false; +} + void do_sigreturn32(struct pt_regs *regs) { struct signal_frame32 __user *sf; compat_uptr_t fpu_save; compat_uptr_t rwin_save; - unsigned int psr; + unsigned int psr, ufp; unsigned int pc, npc; sigset_t set; compat_sigset_t seta; @@ -158,11 +170,16 @@ void do_sigreturn32(struct pt_regs *regs) sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || - (((unsigned long) sf) & 3)) + if (invalid_frame_pointer(sf, sizeof(*sf))) + goto segv; + + if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) + goto segv; + + if (ufp & 0x7) goto segv; - if (get_user(pc, &sf->info.si_regs.pc) || + if (__get_user(pc, &sf->info.si_regs.pc) || __get_user(npc, &sf->info.si_regs.npc)) goto segv; @@ -227,7 +244,7 @@ segv: asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) { struct rt_signal_frame32 __user *sf; - unsigned int psr, pc, npc; + unsigned int psr, pc, npc, ufp; compat_uptr_t fpu_save; compat_uptr_t rwin_save; sigset_t set; @@ -242,11 +259,16 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || - (((unsigned long) sf) & 3)) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv; - if (get_user(pc, &sf->regs.pc) || + if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) + goto segv; + + if (ufp & 0x7) + goto segv; + + if (__get_user(pc, &sf->regs.pc) || __get_user(npc, &sf->regs.npc)) goto segv; @@ -307,14 +329,6 @@ segv: force_sig(SIGSEGV, current); } -/* Checks if the fp is valid */ -static int invalid_frame_pointer(void __user *fp, int fplen) -{ - if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen) - return 1; - return 0; -} - static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) { unsigned long sp; diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 52aa5e4ce5e7..c3c12efe0bc0 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -60,10 +60,22 @@ struct rt_signal_frame { #define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7))) #define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame) + 7) & (~7))) +/* Checks if the fp is valid. We always build signal frames which are + * 16-byte aligned, therefore we can always enforce that the restore + * frame has that property as well. + */ +static inline bool invalid_frame_pointer(void __user *fp, int fplen) +{ + if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen)) + return true; + + return false; +} + asmlinkage void do_sigreturn(struct pt_regs *regs) { + unsigned long up_psr, pc, npc, ufp; struct signal_frame __user *sf; - unsigned long up_psr, pc, npc; sigset_t set; __siginfo_fpu_t __user *fpu_save; __siginfo_rwin_t __user *rwin_save; @@ -77,10 +89,13 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) sf = (struct signal_frame __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!access_ok(VERIFY_READ, sf, sizeof(*sf))) + if (!invalid_frame_pointer(sf, sizeof(*sf))) + goto segv_and_exit; + + if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) goto segv_and_exit; - if (((unsigned long) sf) & 3) + if (ufp & 0x7) goto segv_and_exit; err = __get_user(pc, &sf->info.si_regs.pc); @@ -127,7 +142,7 @@ segv_and_exit: asmlinkage void do_rt_sigreturn(struct pt_regs *regs) { struct rt_signal_frame __user *sf; - unsigned int psr, pc, npc; + unsigned int psr, pc, npc, ufp; __siginfo_fpu_t __user *fpu_save; __siginfo_rwin_t __user *rwin_save; sigset_t set; @@ -135,8 +150,13 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) synchronize_user_stack(); sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP]; - if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || - (((unsigned long) sf) & 0x03)) + if (!invalid_frame_pointer(sf, sizeof(*sf))) + goto segv; + + if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) + goto segv; + + if (ufp & 0x7) goto segv; err = __get_user(pc, &sf->regs.pc); @@ -178,15 +198,6 @@ segv: force_sig(SIGSEGV, current); } -/* Checks if the fp is valid */ -static inline int invalid_frame_pointer(void __user *fp, int fplen) -{ - if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen)) - return 1; - - return 0; -} - static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) { unsigned long sp = regs->u_regs[UREG_FP]; diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 39aaec173f66..5ee930c48f4c 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -234,6 +234,17 @@ do_sigsegv: goto out; } +/* Checks if the fp is valid. We always build rt signal frames which + * are 16-byte aligned, therefore we can always enforce that the + * restore frame has that property as well. + */ +static bool invalid_frame_pointer(void __user *fp) +{ + if (((unsigned long) fp) & 15) + return true; + return false; +} + struct rt_signal_frame { struct sparc_stackf ss; siginfo_t info; @@ -246,8 +257,8 @@ struct rt_signal_frame { void do_rt_sigreturn(struct pt_regs *regs) { + unsigned long tpc, tnpc, tstate, ufp; struct rt_signal_frame __user *sf; - unsigned long tpc, tnpc, tstate; __siginfo_fpu_t __user *fpu_save; __siginfo_rwin_t __user *rwin_save; sigset_t set; @@ -261,10 +272,16 @@ void do_rt_sigreturn(struct pt_regs *regs) (regs->u_regs [UREG_FP] + STACK_BIAS); /* 1. Make sure we are not getting garbage from the user */ - if (((unsigned long) sf) & 3) + if (invalid_frame_pointer(sf)) + goto segv; + + if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) goto segv; - err = get_user(tpc, &sf->regs.tpc); + if ((ufp + STACK_BIAS) & 0x7) + goto segv; + + err = __get_user(tpc, &sf->regs.tpc); err |= __get_user(tnpc, &sf->regs.tnpc); if (test_thread_flag(TIF_32BIT)) { tpc &= 0xffffffff; @@ -308,14 +325,6 @@ segv: force_sig(SIGSEGV, current); } -/* Checks if the fp is valid */ -static int invalid_frame_pointer(void __user *fp) -{ - if (((unsigned long) fp) & 15) - return 1; - return 0; -} - static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) { unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS; diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c index 0f6eebe71e6c..e5fe8cef9a69 100644 --- a/arch/sparc/kernel/sigutil_32.c +++ b/arch/sparc/kernel/sigutil_32.c @@ -48,6 +48,10 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) { int err; + + if (((unsigned long) fpu) & 3) + return -EFAULT; + #ifdef CONFIG_SMP if (test_tsk_thread_flag(current, TIF_USEDFPU)) regs->psr &= ~PSR_EF; @@ -97,7 +101,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp) struct thread_info *t = current_thread_info(); int i, wsaved, err; - __get_user(wsaved, &rp->wsaved); + if (((unsigned long) rp) & 3) + return -EFAULT; + + get_user(wsaved, &rp->wsaved); if (wsaved > NSWINS) return -EFAULT; diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c index 387834a9c56a..36aadcbeac69 100644 --- a/arch/sparc/kernel/sigutil_64.c +++ b/arch/sparc/kernel/sigutil_64.c @@ -37,7 +37,10 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) unsigned long fprs; int err; - err = __get_user(fprs, &fpu->si_fprs); + if (((unsigned long) fpu) & 7) + return -EFAULT; + + err = get_user(fprs, &fpu->si_fprs); fprs_write(0); regs->tstate &= ~TSTATE_PEF; if (fprs & FPRS_DL) @@ -72,7 +75,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp) struct thread_info *t = current_thread_info(); int i, wsaved, err; - __get_user(wsaved, &rp->wsaved); + if (((unsigned long) rp) & 7) + return -EFAULT; + + get_user(wsaved, &rp->wsaved); if (wsaved > NSWINS) return -EFAULT; diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S new file mode 100644 index 000000000000..5604a2b051d4 --- /dev/null +++ b/arch/sparc/kernel/urtt_fill.S @@ -0,0 +1,98 @@ +#include <asm/thread_info.h> +#include <asm/trap_block.h> +#include <asm/spitfire.h> +#include <asm/ptrace.h> +#include <asm/head.h> + + .text + .align 8 + .globl user_rtt_fill_fixup_common +user_rtt_fill_fixup_common: + rdpr %cwp, %g1 + add %g1, 1, %g1 + wrpr %g1, 0x0, %cwp + + rdpr %wstate, %g2 + sll %g2, 3, %g2 + wrpr %g2, 0x0, %wstate + + /* We know %canrestore and %otherwin are both zero. */ + + sethi %hi(sparc64_kern_pri_context), %g2 + ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2 + mov PRIMARY_CONTEXT, %g1 + +661: stxa %g2, [%g1] ASI_DMMU + .section .sun4v_1insn_patch, "ax" + .word 661b + stxa %g2, [%g1] ASI_MMU + .previous + + sethi %hi(KERNBASE), %g1 + flush %g1 + + mov %g4, %l4 + mov %g5, %l5 + brnz,pn %g3, 1f + mov %g3, %l3 + + or %g4, FAULT_CODE_WINFIXUP, %g4 + stb %g4, [%g6 + TI_FAULT_CODE] + stx %g5, [%g6 + TI_FAULT_ADDR] +1: + mov %g6, %l1 + wrpr %g0, 0x0, %tl + +661: nop + .section .sun4v_1insn_patch, "ax" + .word 661b + SET_GL(0) + .previous + + wrpr %g0, RTRAP_PSTATE, %pstate + + mov %l1, %g6 + ldx [%g6 + TI_TASK], %g4 + LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3) + + brnz,pn %l3, 1f + nop + + call do_sparc64_fault + add %sp, PTREGS_OFF, %o0 + ba,pt %xcc, rtrap + nop + +1: cmp %g3, 2 + bne,pn %xcc, 2f + nop + + sethi %hi(tlb_type), %g1 + lduw [%g1 + %lo(tlb_type)], %g1 + cmp %g1, 3 + bne,pt %icc, 1f + add %sp, PTREGS_OFF, %o0 + mov %l4, %o2 + call sun4v_do_mna + mov %l5, %o1 + ba,a,pt %xcc, rtrap +1: mov %l4, %o1 + mov %l5, %o2 + call mem_address_unaligned + nop + ba,a,pt %xcc, rtrap + +2: sethi %hi(tlb_type), %g1 + mov %l4, %o1 + lduw [%g1 + %lo(tlb_type)], %g1 + mov %l5, %o2 + cmp %g1, 3 + bne,pt %icc, 1f + add %sp, PTREGS_OFF, %o0 + call sun4v_data_access_exception + nop + ba,a,pt %xcc, rtrap + +1: call spitfire_data_access_exception + nop + ba,a,pt %xcc, rtrap diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 652683cb4b4b..14bb0d5ed3c6 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2824,9 +2824,10 @@ void hugetlb_setup(struct pt_regs *regs) * the Data-TLB for huge pages. */ if (tlb_type == cheetah_plus) { + bool need_context_reload = false; unsigned long ctx; - spin_lock(&ctx_alloc_lock); + spin_lock_irq(&ctx_alloc_lock); ctx = mm->context.sparc64_ctx_val; ctx &= ~CTX_PGSZ_MASK; ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT; @@ -2845,9 +2846,12 @@ void hugetlb_setup(struct pt_regs *regs) * also executing in this address space. */ mm->context.sparc64_ctx_val = ctx; - on_each_cpu(context_reload, mm, 0); + need_context_reload = true; } - spin_unlock(&ctx_alloc_lock); + spin_unlock_irq(&ctx_alloc_lock); + + if (need_context_reload) + on_each_cpu(context_reload, mm, 0); } } #endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 769af907f824..7597b42a8a88 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -181,19 +181,22 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry __user *entries) { int r, i; - struct kvm_cpuid_entry *cpuid_entries; + struct kvm_cpuid_entry *cpuid_entries = NULL; r = -E2BIG; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) goto out; r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent); - if (!cpuid_entries) - goto out; - r = -EFAULT; - if (copy_from_user(cpuid_entries, entries, - cpuid->nent * sizeof(struct kvm_cpuid_entry))) - goto out_free; + if (cpuid->nent) { + cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * + cpuid->nent); + if (!cpuid_entries) + goto out; + r = -EFAULT; + if (copy_from_user(cpuid_entries, entries, + cpuid->nent * sizeof(struct kvm_cpuid_entry))) + goto out; + } for (i = 0; i < cpuid->nent; i++) { vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; @@ -212,9 +215,8 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, kvm_x86_ops->cpuid_update(vcpu); r = kvm_update_cpuid(vcpu); -out_free: - vfree(cpuid_entries); out: + vfree(cpuid_entries); return r; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 24e800116ab4..def97b3a392b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -336,12 +336,12 @@ static gfn_t pse36_gfn_delta(u32 gpte) #ifdef CONFIG_X86_64 static void __set_spte(u64 *sptep, u64 spte) { - *sptep = spte; + WRITE_ONCE(*sptep, spte); } static void __update_clear_spte_fast(u64 *sptep, u64 spte) { - *sptep = spte; + WRITE_ONCE(*sptep, spte); } static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) @@ -390,7 +390,7 @@ static void __set_spte(u64 *sptep, u64 spte) */ smp_wmb(); - ssptep->spte_low = sspte.spte_low; + WRITE_ONCE(ssptep->spte_low, sspte.spte_low); } static void __update_clear_spte_fast(u64 *sptep, u64 spte) @@ -400,7 +400,7 @@ static void __update_clear_spte_fast(u64 *sptep, u64 spte) ssptep = (union split_spte *)sptep; sspte = (union split_spte)spte; - ssptep->spte_low = sspte.spte_low; + WRITE_ONCE(ssptep->spte_low, sspte.spte_low); /* * If we map the spte from present to nonpresent, we should clear diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c805cf494154..902d9da12392 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2314,6 +2314,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_NB_CFG: case MSR_FAM10H_MMIO_CONF_BASE: case MSR_AMD64_BU_CFG2: + case MSR_IA32_PERF_CTL: msr_info->data = 0; break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: @@ -2972,6 +2973,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SMM)) return -EINVAL; + if (events->exception.injected && + (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR)) + return -EINVAL; + process_nmi(vcpu); vcpu->arch.exception.pending = events->exception.injected; vcpu->arch.exception.nr = events->exception.nr; @@ -3036,6 +3041,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (dbgregs->flags) return -EINVAL; + if (dbgregs->dr6 & ~0xffffffffull) + return -EINVAL; + if (dbgregs->dr7 & ~0xffffffffull) + return -EINVAL; + memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; @@ -7815,7 +7825,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) slot = id_to_memslot(slots, id); if (size) { - if (WARN_ON(slot->npages)) + if (slot->npages) return -EEXIST; /* diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig index e28e912000a7..331f6baf2df8 100644 --- a/crypto/asymmetric_keys/Kconfig +++ b/crypto/asymmetric_keys/Kconfig @@ -13,6 +13,7 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE tristate "Asymmetric public-key crypto algorithm subtype" select MPILIB select CRYPTO_HASH_INFO + select CRYPTO_AKCIPHER help This option provides support for asymmetric public key type handling. If signature generation and/or verification are to be used, diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index a969a7e443be..85aaf2222587 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -181,13 +181,17 @@ static char *res_strings[] = { "reserved 27", "reserved 28", "reserved 29", - "reserved 30", + "reserved 30", /* FIXME: The strings between 30-40 might be wrong. */ "reassembly abort: no buffers", "receive buffer overflow", "change in GFC", "receive buffer full", "low priority discard - no receive descriptor", "low priority discard - missing end of packet", + "reserved 37", + "reserved 38", + "reserved 39", + "reseverd 40", "reserved 41", "reserved 42", "reserved 43", diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index 7d00f2994738..809dd1e02091 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -1128,7 +1128,7 @@ static int rx_pkt(struct atm_dev *dev) /* make the ptr point to the corresponding buffer desc entry */ buf_desc_ptr += desc; if (!desc || (desc > iadev->num_rx_desc) || - ((buf_desc_ptr->vc_index & 0xffff) > iadev->num_vc)) { + ((buf_desc_ptr->vc_index & 0xffff) >= iadev->num_vc)) { free_desc(dev, desc); IF_ERR(printk("IA: bad descriptor desc = %d \n", desc);) return -1; diff --git a/drivers/crypto/ccp/ccp-crypto-aes-xts.c b/drivers/crypto/ccp/ccp-crypto-aes-xts.c index 52c7395cb8d8..0d0d4529ee36 100644 --- a/drivers/crypto/ccp/ccp-crypto-aes-xts.c +++ b/drivers/crypto/ccp/ccp-crypto-aes-xts.c @@ -122,6 +122,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req, struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm); struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req); unsigned int unit; + u32 unit_size; int ret; if (!ctx->u.aes.key_len) @@ -133,11 +134,17 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req, if (!req->info) return -EINVAL; - for (unit = 0; unit < ARRAY_SIZE(unit_size_map); unit++) - if (!(req->nbytes & (unit_size_map[unit].size - 1))) - break; + unit_size = CCP_XTS_AES_UNIT_SIZE__LAST; + if (req->nbytes <= unit_size_map[0].size) { + for (unit = 0; unit < ARRAY_SIZE(unit_size_map); unit++) { + if (!(req->nbytes & (unit_size_map[unit].size - 1))) { + unit_size = unit_size_map[unit].value; + break; + } + } + } - if ((unit_size_map[unit].value == CCP_XTS_AES_UNIT_SIZE__LAST) || + if ((unit_size == CCP_XTS_AES_UNIT_SIZE__LAST) || (ctx->u.aes.key_len != AES_KEYSIZE_128)) { /* Use the fallback to process the request for any * unsupported unit sizes or key sizes @@ -158,7 +165,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req, rctx->cmd.engine = CCP_ENGINE_XTS_AES_128; rctx->cmd.u.xts.action = (encrypt) ? CCP_AES_ACTION_ENCRYPT : CCP_AES_ACTION_DECRYPT; - rctx->cmd.u.xts.unit_size = unit_size_map[unit].value; + rctx->cmd.u.xts.unit_size = unit_size; rctx->cmd.u.xts.key = &ctx->u.aes.key_sg; rctx->cmd.u.xts.key_len = ctx->u.aes.key_len; rctx->cmd.u.xts.iv = &rctx->iv_sg; diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c index 6eefaa2fe58f..63464e86f2b1 100644 --- a/drivers/crypto/omap-sham.c +++ b/drivers/crypto/omap-sham.c @@ -1986,7 +1986,7 @@ err_algs: &dd->pdata->algs_info[i].algs_list[j]); err_pm: pm_runtime_disable(dev); - if (dd->polling_mode) + if (!dd->polling_mode) dma_release_channel(dd->dma_lch); data_err: dev_err(dev, "initialization failed.\n"); diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 4a2c07ee6677..6355ab38d630 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -33,6 +33,7 @@ #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/reservation.h> +#include <linux/mm.h> #include <uapi/linux/dma-buf.h> @@ -90,7 +91,7 @@ static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma) dmabuf = file->private_data; /* check for overflowing the buffer's size */ - if (vma->vm_pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) > + if (vma->vm_pgoff + vma_pages(vma) > dmabuf->size >> PAGE_SHIFT) return -EINVAL; @@ -723,11 +724,11 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, return -EINVAL; /* check for offset overflow */ - if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < pgoff) + if (pgoff + vma_pages(vma) < pgoff) return -EOVERFLOW; /* check for overflowing the buffer's size */ - if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) > + if (pgoff + vma_pages(vma) > dmabuf->size >> PAGE_SHIFT) return -EINVAL; diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index c0bd5722c997..9566a62ad8e3 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -35,6 +35,17 @@ #include <linux/reservation.h> #include <linux/export.h> +/** + * DOC: Reservation Object Overview + * + * The reservation object provides a mechanism to manage shared and + * exclusive fences associated with a buffer. A reservation object + * can have attached one exclusive fence (normally associated with + * write operations) or N shared fences (read operations). The RCU + * mechanism is used to protect read access to fences from locked + * write-side updates. + */ + DEFINE_WW_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); @@ -43,9 +54,17 @@ EXPORT_SYMBOL(reservation_seqcount_class); const char reservation_seqcount_string[] = "reservation_seqcount"; EXPORT_SYMBOL(reservation_seqcount_string); -/* - * Reserve space to add a shared fence to a reservation_object, - * must be called with obj->lock held. + +/** + * reservation_object_reserve_shared - Reserve space to add a shared + * fence to a reservation_object. + * @obj: reservation object + * + * Should be called before reservation_object_add_shared_fence(). Must + * be called with obj->lock held. + * + * RETURNS + * Zero for success, or -errno */ int reservation_object_reserve_shared(struct reservation_object *obj) { @@ -180,7 +199,11 @@ done: fence_put(old_fence); } -/* +/** + * reservation_object_add_shared_fence - Add a fence to a shared slot + * @obj: the reservation object + * @fence: the shared fence to add + * * Add a fence to a shared slot, obj->lock must be held, and * reservation_object_reserve_shared_fence has been called. */ @@ -200,6 +223,13 @@ void reservation_object_add_shared_fence(struct reservation_object *obj, } EXPORT_SYMBOL(reservation_object_add_shared_fence); +/** + * reservation_object_add_excl_fence - Add an exclusive fence. + * @obj: the reservation object + * @fence: the shared fence to add + * + * Add a fence to the exclusive slot. The obj->lock must be held. + */ void reservation_object_add_excl_fence(struct reservation_object *obj, struct fence *fence) { @@ -233,6 +263,18 @@ void reservation_object_add_excl_fence(struct reservation_object *obj, } EXPORT_SYMBOL(reservation_object_add_excl_fence); +/** + * reservation_object_get_fences_rcu - Get an object's shared and exclusive + * fences without update side lock held + * @obj: the reservation object + * @pfence_excl: the returned exclusive fence (or NULL) + * @pshared_count: the number of shared fences returned + * @pshared: the array of shared fence ptrs returned (array is krealloc'd to + * the required size, and must be freed by caller) + * + * RETURNS + * Zero or -errno + */ int reservation_object_get_fences_rcu(struct reservation_object *obj, struct fence **pfence_excl, unsigned *pshared_count, @@ -319,6 +361,18 @@ unlock: } EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu); +/** + * reservation_object_wait_timeout_rcu - Wait on reservation's objects + * shared and/or exclusive fences. + * @obj: the reservation object + * @wait_all: if true, wait on all fences, else wait on just exclusive fence + * @intr: if true, do interruptible wait + * @timeout: timeout value in jiffies or zero to return immediately + * + * RETURNS + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or + * greater than zer on success. + */ long reservation_object_wait_timeout_rcu(struct reservation_object *obj, bool wait_all, bool intr, unsigned long timeout) @@ -416,6 +470,16 @@ reservation_object_test_signaled_single(struct fence *passed_fence) return ret; } +/** + * reservation_object_test_signaled_rcu - Test if a reservation object's + * fences have been signaled. + * @obj: the reservation object + * @test_all: if true, test all fences, otherwise only test the exclusive + * fence + * + * RETURNS + * true if all fences signaled, else false + */ bool reservation_object_test_signaled_rcu(struct reservation_object *obj, bool test_all) { diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c index d39014daeef9..fc5f197906ac 100644 --- a/drivers/gpio/gpio-lpc32xx.c +++ b/drivers/gpio/gpio-lpc32xx.c @@ -29,7 +29,6 @@ #include <mach/hardware.h> #include <mach/platform.h> -#include <mach/irqs.h> #define LPC32XX_GPIO_P3_INP_STATE _GPREG(0x000) #define LPC32XX_GPIO_P3_OUTP_SET _GPREG(0x004) @@ -371,61 +370,16 @@ static int lpc32xx_gpio_request(struct gpio_chip *chip, unsigned pin) static int lpc32xx_gpio_to_irq_p01(struct gpio_chip *chip, unsigned offset) { - return IRQ_LPC32XX_P0_P1_IRQ; + return -ENXIO; } -static const char lpc32xx_gpio_to_irq_gpio_p3_table[] = { - IRQ_LPC32XX_GPIO_00, - IRQ_LPC32XX_GPIO_01, - IRQ_LPC32XX_GPIO_02, - IRQ_LPC32XX_GPIO_03, - IRQ_LPC32XX_GPIO_04, - IRQ_LPC32XX_GPIO_05, -}; - static int lpc32xx_gpio_to_irq_gpio_p3(struct gpio_chip *chip, unsigned offset) { - if (offset < ARRAY_SIZE(lpc32xx_gpio_to_irq_gpio_p3_table)) - return lpc32xx_gpio_to_irq_gpio_p3_table[offset]; return -ENXIO; } -static const char lpc32xx_gpio_to_irq_gpi_p3_table[] = { - IRQ_LPC32XX_GPI_00, - IRQ_LPC32XX_GPI_01, - IRQ_LPC32XX_GPI_02, - IRQ_LPC32XX_GPI_03, - IRQ_LPC32XX_GPI_04, - IRQ_LPC32XX_GPI_05, - IRQ_LPC32XX_GPI_06, - IRQ_LPC32XX_GPI_07, - IRQ_LPC32XX_GPI_08, - IRQ_LPC32XX_GPI_09, - -ENXIO, /* 10 */ - -ENXIO, /* 11 */ - -ENXIO, /* 12 */ - -ENXIO, /* 13 */ - -ENXIO, /* 14 */ - -ENXIO, /* 15 */ - -ENXIO, /* 16 */ - -ENXIO, /* 17 */ - -ENXIO, /* 18 */ - IRQ_LPC32XX_GPI_19, - -ENXIO, /* 20 */ - -ENXIO, /* 21 */ - -ENXIO, /* 22 */ - -ENXIO, /* 23 */ - -ENXIO, /* 24 */ - -ENXIO, /* 25 */ - -ENXIO, /* 26 */ - -ENXIO, /* 27 */ - IRQ_LPC32XX_GPI_28, -}; - static int lpc32xx_gpio_to_irq_gpi_p3(struct gpio_chip *chip, unsigned offset) { - if (offset < ARRAY_SIZE(lpc32xx_gpio_to_irq_gpi_p3_table)) - return lpc32xx_gpio_to_irq_gpi_p3_table[offset]; return -ENXIO; } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index d407f904a31c..24f60d28f0c0 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -20,6 +20,7 @@ #include <linux/cdev.h> #include <linux/fs.h> #include <linux/uaccess.h> +#include <linux/compat.h> #include <uapi/linux/gpio.h> #include "gpiolib.h" @@ -316,7 +317,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct gpio_device *gdev = filp->private_data; struct gpio_chip *chip = gdev->chip; - int __user *ip = (int __user *)arg; + void __user *ip = (void __user *)arg; /* We fail any subsequent ioctl():s when the chip is gone */ if (!chip) @@ -388,6 +389,14 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return -EINVAL; } +#ifdef CONFIG_COMPAT +static long gpio_ioctl_compat(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + return gpio_ioctl(filp, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + /** * gpio_chrdev_open() - open the chardev for ioctl operations * @inode: inode for this chardev @@ -431,7 +440,9 @@ static const struct file_operations gpio_fileops = { .owner = THIS_MODULE, .llseek = noop_llseek, .unlocked_ioctl = gpio_ioctl, - .compat_ioctl = gpio_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = gpio_ioctl_compat, +#endif }; static void gpiodevice_release(struct device *dev) @@ -618,6 +629,8 @@ int gpiochip_add_data(struct gpio_chip *chip, void *data) goto err_free_label; } + spin_unlock_irqrestore(&gpio_lock, flags); + for (i = 0; i < chip->ngpio; i++) { struct gpio_desc *desc = &gdev->descs[i]; @@ -649,8 +662,6 @@ int gpiochip_add_data(struct gpio_chip *chip, void *data) } } - spin_unlock_irqrestore(&gpio_lock, flags); - #ifdef CONFIG_PINCTRL INIT_LIST_HEAD(&gdev->pin_ranges); #endif @@ -1356,10 +1367,13 @@ done: /* * This descriptor validation needs to be inserted verbatim into each * function taking a descriptor, so we need to use a preprocessor - * macro to avoid endless duplication. + * macro to avoid endless duplication. If the desc is NULL it is an + * optional GPIO and calls should just bail out. */ #define VALIDATE_DESC(desc) do { \ - if (!desc || !desc->gdev) { \ + if (!desc) \ + return 0; \ + if (!desc->gdev) { \ pr_warn("%s: invalid GPIO\n", __func__); \ return -EINVAL; \ } \ @@ -1370,7 +1384,9 @@ done: } } while (0) #define VALIDATE_DESC_VOID(desc) do { \ - if (!desc || !desc->gdev) { \ + if (!desc) \ + return; \ + if (!desc->gdev) { \ pr_warn("%s: invalid GPIO\n", __func__); \ return; \ } \ @@ -2066,17 +2082,30 @@ EXPORT_SYMBOL_GPL(gpiod_to_irq); */ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset) { - if (offset >= chip->ngpio) - return -EINVAL; + struct gpio_desc *desc; + + desc = gpiochip_get_desc(chip, offset); + if (IS_ERR(desc)) + return PTR_ERR(desc); + + /* Flush direction if something changed behind our back */ + if (chip->get_direction) { + int dir = chip->get_direction(chip, offset); + + if (dir) + clear_bit(FLAG_IS_OUT, &desc->flags); + else + set_bit(FLAG_IS_OUT, &desc->flags); + } - if (test_bit(FLAG_IS_OUT, &chip->gpiodev->descs[offset].flags)) { + if (test_bit(FLAG_IS_OUT, &desc->flags)) { chip_err(chip, "%s: tried to flag a GPIO set as output for IRQ\n", __func__); return -EIO; } - set_bit(FLAG_USED_AS_IRQ, &chip->gpiodev->descs[offset].flags); + set_bit(FLAG_USED_AS_IRQ, &desc->flags); return 0; } EXPORT_SYMBOL_GPL(gpiochip_lock_as_irq); diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c index 16419f550eff..058460bdd5a6 100644 --- a/drivers/net/ethernet/arc/emac_mdio.c +++ b/drivers/net/ethernet/arc/emac_mdio.c @@ -141,7 +141,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv) priv->bus = bus; bus->priv = priv; bus->parent = priv->dev; - bus->name = "Synopsys MII Bus", + bus->name = "Synopsys MII Bus"; bus->read = &arc_mdio_read; bus->write = &arc_mdio_write; bus->reset = &arc_mdio_reset; diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h index 8fc93c5f6abc..d02c4240b7df 100644 --- a/drivers/net/ethernet/atheros/alx/alx.h +++ b/drivers/net/ethernet/atheros/alx/alx.h @@ -96,6 +96,10 @@ struct alx_priv { unsigned int rx_ringsz; unsigned int rxbuf_size; + struct page *rx_page; + unsigned int rx_page_offset; + unsigned int rx_frag_size; + struct napi_struct napi; struct alx_tx_queue txq; struct alx_rx_queue rxq; diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 9fe8b5e310d1..c98acdc0d14f 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -70,6 +70,35 @@ static void alx_free_txbuf(struct alx_priv *alx, int entry) } } +static struct sk_buff *alx_alloc_skb(struct alx_priv *alx, gfp_t gfp) +{ + struct sk_buff *skb; + struct page *page; + + if (alx->rx_frag_size > PAGE_SIZE) + return __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp); + + page = alx->rx_page; + if (!page) { + alx->rx_page = page = alloc_page(gfp); + if (unlikely(!page)) + return NULL; + alx->rx_page_offset = 0; + } + + skb = build_skb(page_address(page) + alx->rx_page_offset, + alx->rx_frag_size); + if (likely(skb)) { + alx->rx_page_offset += alx->rx_frag_size; + if (alx->rx_page_offset >= PAGE_SIZE) + alx->rx_page = NULL; + else + get_page(page); + } + return skb; +} + + static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp) { struct alx_rx_queue *rxq = &alx->rxq; @@ -86,7 +115,7 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp) while (!cur_buf->skb && next != rxq->read_idx) { struct alx_rfd *rfd = &rxq->rfd[cur]; - skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp); + skb = alx_alloc_skb(alx, gfp); if (!skb) break; dma = dma_map_single(&alx->hw.pdev->dev, @@ -124,6 +153,7 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp) alx_write_mem16(&alx->hw, ALX_RFD_PIDX, cur); } + return count; } @@ -592,6 +622,11 @@ static void alx_free_rings(struct alx_priv *alx) kfree(alx->txq.bufs); kfree(alx->rxq.bufs); + if (alx->rx_page) { + put_page(alx->rx_page); + alx->rx_page = NULL; + } + dma_free_coherent(&alx->hw.pdev->dev, alx->descmem.size, alx->descmem.virt, @@ -646,6 +681,7 @@ static int alx_request_irq(struct alx_priv *alx) alx->dev->name, alx); if (!err) goto out; + /* fall back to legacy interrupt */ pci_disable_msi(alx->hw.pdev); } @@ -689,6 +725,7 @@ static int alx_init_sw(struct alx_priv *alx) struct pci_dev *pdev = alx->hw.pdev; struct alx_hw *hw = &alx->hw; int err; + unsigned int head_size; err = alx_identify_hw(alx); if (err) { @@ -704,7 +741,12 @@ static int alx_init_sw(struct alx_priv *alx) hw->smb_timer = 400; hw->mtu = alx->dev->mtu; + alx->rxbuf_size = ALX_MAX_FRAME_LEN(hw->mtu); + head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + alx->rx_frag_size = roundup_pow_of_two(head_size); + alx->tx_ringsz = 256; alx->rx_ringsz = 512; hw->imt = 200; @@ -806,6 +848,7 @@ static int alx_change_mtu(struct net_device *netdev, int mtu) { struct alx_priv *alx = netdev_priv(netdev); int max_frame = ALX_MAX_FRAME_LEN(mtu); + unsigned int head_size; if ((max_frame < ALX_MIN_FRAME_SIZE) || (max_frame > ALX_MAX_FRAME_SIZE)) @@ -817,6 +860,9 @@ static int alx_change_mtu(struct net_device *netdev, int mtu) netdev->mtu = mtu; alx->hw.mtu = mtu; alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE); + head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + alx->rx_frag_size = roundup_pow_of_two(head_size); netdev_update_features(netdev); if (netif_running(netdev)) alx_reinit(alx); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 0a5b770cefaa..c5fe915870ad 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13941,14 +13941,14 @@ static int bnx2x_init_one(struct pci_dev *pdev, bp->doorbells = bnx2x_vf_doorbells(bp); rc = bnx2x_vf_pci_alloc(bp); if (rc) - goto init_one_exit; + goto init_one_freemem; } else { doorbell_size = BNX2X_L2_MAX_CID(bp) * (1 << BNX2X_DB_SHIFT); if (doorbell_size > pci_resource_len(pdev, 2)) { dev_err(&bp->pdev->dev, "Cannot map doorbells, bar size too small, aborting\n"); rc = -ENOMEM; - goto init_one_exit; + goto init_one_freemem; } bp->doorbells = ioremap_nocache(pci_resource_start(pdev, 2), doorbell_size); @@ -13957,19 +13957,19 @@ static int bnx2x_init_one(struct pci_dev *pdev, dev_err(&bp->pdev->dev, "Cannot map doorbell space, aborting\n"); rc = -ENOMEM; - goto init_one_exit; + goto init_one_freemem; } if (IS_VF(bp)) { rc = bnx2x_vfpf_acquire(bp, tx_count, rx_count); if (rc) - goto init_one_exit; + goto init_one_freemem; } /* Enable SRIOV if capability found in configuration space */ rc = bnx2x_iov_init_one(bp, int_mode, BNX2X_MAX_NUM_OF_VFS); if (rc) - goto init_one_exit; + goto init_one_freemem; /* calc qm_cid_count */ bp->qm_cid_count = bnx2x_set_qm_cid_count(bp); @@ -13988,7 +13988,7 @@ static int bnx2x_init_one(struct pci_dev *pdev, rc = bnx2x_set_int_mode(bp); if (rc) { dev_err(&pdev->dev, "Cannot set interrupts\n"); - goto init_one_exit; + goto init_one_freemem; } BNX2X_DEV_INFO("set interrupts successfully\n"); @@ -13996,7 +13996,7 @@ static int bnx2x_init_one(struct pci_dev *pdev, rc = register_netdev(dev); if (rc) { dev_err(&pdev->dev, "Cannot register net device\n"); - goto init_one_exit; + goto init_one_freemem; } BNX2X_DEV_INFO("device name after netdev register %s\n", dev->name); @@ -14029,6 +14029,9 @@ static int bnx2x_init_one(struct pci_dev *pdev, return 0; +init_one_freemem: + bnx2x_free_mem_bp(bp); + init_one_exit: bnx2x_disable_pcie_error_reporting(bp); diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 085f9125cf42..06f031715b57 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -205,8 +205,10 @@ static int nps_enet_poll(struct napi_struct *napi, int budget) * re-adding ourselves to the poll list. */ - if (priv->tx_skb && !tx_ctrl_ct) + if (priv->tx_skb && !tx_ctrl_ct) { + nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE, 0); napi_reschedule(napi); + } } return work_done; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index ca2cccc594fd..3c0255e98535 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1197,10 +1197,8 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) fec16_to_cpu(bdp->cbd_datlen), DMA_TO_DEVICE); bdp->cbd_bufaddr = cpu_to_fec32(0); - if (!skb) { - bdp = fec_enet_get_nextdesc(bdp, &txq->bd); - continue; - } + if (!skb) + goto skb_done; /* Check for errors. */ if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC | @@ -1239,7 +1237,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) /* Free the sk buffer associated with this last transmit */ dev_kfree_skb_any(skb); - +skb_done: /* Make sure the update to bdp and tx_skbuff are performed * before dirty_tx */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 3d746c887873..67a648c7d3a9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -46,7 +46,6 @@ static u32 hns_nic_get_link(struct net_device *net_dev) u32 link_stat = priv->link; struct hnae_handle *h; - assert(priv && priv->ae_handle); h = priv->ae_handle; if (priv->phy) { @@ -646,8 +645,6 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev, { struct hns_nic_priv *priv = netdev_priv(net_dev); - assert(priv); - strncpy(drvinfo->version, HNAE_DRIVER_VERSION, sizeof(drvinfo->version)); drvinfo->version[sizeof(drvinfo->version) - 1] = '\0'; @@ -720,8 +717,6 @@ static int hns_set_pauseparam(struct net_device *net_dev, struct hnae_handle *h; struct hnae_ae_ops *ops; - assert(priv || priv->ae_handle); - h = priv->ae_handle; ops = h->dev->ops; @@ -780,8 +775,6 @@ static int hns_set_coalesce(struct net_device *net_dev, struct hnae_ae_ops *ops; int ret; - assert(priv || priv->ae_handle); - ops = priv->ae_handle->dev->ops; if (ec->tx_coalesce_usecs != ec->rx_coalesce_usecs) @@ -1111,8 +1104,6 @@ void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd, struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_ae_ops *ops; - assert(priv || priv->ae_handle); - ops = priv->ae_handle->dev->ops; cmd->version = HNS_CHIP_VERSION; @@ -1135,8 +1126,6 @@ static int hns_get_regs_len(struct net_device *net_dev) struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_ae_ops *ops; - assert(priv || priv->ae_handle); - ops = priv->ae_handle->dev->ops; if (!ops->get_regs_len) { netdev_err(net_dev, "ops->get_regs_len is null!\n"); diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c index 01fccec632ec..466939f8f0cf 100644 --- a/drivers/net/ethernet/marvell/mvneta_bm.c +++ b/drivers/net/ethernet/marvell/mvneta_bm.c @@ -189,6 +189,7 @@ struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id, SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); hwbm_pool->construct = mvneta_bm_construct; hwbm_pool->priv = new_pool; + spin_lock_init(&hwbm_pool->lock); /* Create new pool */ err = mvneta_bm_pool_create(priv, new_pool); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index c761194bb323..fc95affaf76b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -362,7 +362,7 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev, for (i = 0; i < NUM_MAIN_STATS; i++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) - data[index++] = ((unsigned long *)&priv->stats)[i]; + data[index++] = ((unsigned long *)&dev->stats)[i]; for (i = 0; i < NUM_PORT_STATS; i++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 92e0624f4cf0..19ceced6736c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1296,15 +1296,16 @@ static void mlx4_en_tx_timeout(struct net_device *dev) } -static struct net_device_stats *mlx4_en_get_stats(struct net_device *dev) +static struct rtnl_link_stats64 * +mlx4_en_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mlx4_en_priv *priv = netdev_priv(dev); spin_lock_bh(&priv->stats_lock); - memcpy(&priv->ret_stats, &priv->stats, sizeof(priv->stats)); + netdev_stats_to_stats64(stats, &dev->stats); spin_unlock_bh(&priv->stats_lock); - return &priv->ret_stats; + return stats; } static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv) @@ -1876,7 +1877,6 @@ static void mlx4_en_clear_stats(struct net_device *dev) if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1)) en_dbg(HW, priv, "Failed dumping statistics\n"); - memset(&priv->stats, 0, sizeof(priv->stats)); memset(&priv->pstats, 0, sizeof(priv->pstats)); memset(&priv->pkstats, 0, sizeof(priv->pkstats)); memset(&priv->port_stats, 0, sizeof(priv->port_stats)); @@ -1892,6 +1892,11 @@ static void mlx4_en_clear_stats(struct net_device *dev) priv->tx_ring[i]->bytes = 0; priv->tx_ring[i]->packets = 0; priv->tx_ring[i]->tx_csum = 0; + priv->tx_ring[i]->tx_dropped = 0; + priv->tx_ring[i]->queue_stopped = 0; + priv->tx_ring[i]->wake_queue = 0; + priv->tx_ring[i]->tso_packets = 0; + priv->tx_ring[i]->xmit_more = 0; } for (i = 0; i < priv->rx_ring_num; i++) { priv->rx_ring[i]->bytes = 0; @@ -2482,7 +2487,7 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_stop = mlx4_en_close, .ndo_start_xmit = mlx4_en_xmit, .ndo_select_queue = mlx4_en_select_queue, - .ndo_get_stats = mlx4_en_get_stats, + .ndo_get_stats64 = mlx4_en_get_stats64, .ndo_set_rx_mode = mlx4_en_set_rx_mode, .ndo_set_mac_address = mlx4_en_set_mac, .ndo_validate_addr = eth_validate_addr, @@ -2514,7 +2519,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .ndo_stop = mlx4_en_close, .ndo_start_xmit = mlx4_en_xmit, .ndo_select_queue = mlx4_en_select_queue, - .ndo_get_stats = mlx4_en_get_stats, + .ndo_get_stats64 = mlx4_en_get_stats64, .ndo_set_rx_mode = mlx4_en_set_rx_mode, .ndo_set_mac_address = mlx4_en_set_mac, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 20b6c2e678b8..5aa8b751f417 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -152,8 +152,9 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) struct mlx4_counter tmp_counter_stats; struct mlx4_en_stat_out_mbox *mlx4_en_stats; struct mlx4_en_stat_out_flow_control_mbox *flowstats; - struct mlx4_en_priv *priv = netdev_priv(mdev->pndev[port]); - struct net_device_stats *stats = &priv->stats; + struct net_device *dev = mdev->pndev[port]; + struct mlx4_en_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; struct mlx4_cmd_mailbox *mailbox; u64 in_mod = reset << 8 | port; int err; @@ -188,6 +189,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) } stats->tx_packets = 0; stats->tx_bytes = 0; + stats->tx_dropped = 0; priv->port_stats.tx_chksum_offload = 0; priv->port_stats.queue_stopped = 0; priv->port_stats.wake_queue = 0; @@ -199,6 +201,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) stats->tx_packets += ring->packets; stats->tx_bytes += ring->bytes; + stats->tx_dropped += ring->tx_dropped; priv->port_stats.tx_chksum_offload += ring->tx_csum; priv->port_stats.queue_stopped += ring->queue_stopped; priv->port_stats.wake_queue += ring->wake_queue; @@ -237,21 +240,12 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) stats->multicast = en_stats_adder(&mlx4_en_stats->MCAST_prio_0, &mlx4_en_stats->MCAST_prio_1, NUM_PRIORITIES); - stats->collisions = 0; stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP) + sw_rx_dropped; stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength); - stats->rx_over_errors = 0; stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC); - stats->rx_frame_errors = 0; stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); - stats->rx_missed_errors = 0; - stats->tx_aborted_errors = 0; - stats->tx_carrier_errors = 0; - stats->tx_fifo_errors = 0; - stats->tx_heartbeat_errors = 0; - stats->tx_window_errors = 0; - stats->tx_dropped = be32_to_cpu(mlx4_en_stats->TDROP); + stats->tx_dropped += be32_to_cpu(mlx4_en_stats->TDROP); /* RX stats */ priv->pkstats.rx_multicast_packets = stats->multicast; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index f6e61570cb2c..76aa4d27183c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -726,12 +726,12 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) bool inline_ok; u32 ring_cons; - if (!priv->port_up) - goto tx_drop; - tx_ind = skb_get_queue_mapping(skb); ring = priv->tx_ring[tx_ind]; + if (!priv->port_up) + goto tx_drop; + /* fetch ring->cons far ahead before needing it to avoid stall */ ring_cons = ACCESS_ONCE(ring->cons); @@ -1030,7 +1030,7 @@ tx_drop_unmap: tx_drop: dev_kfree_skb_any(skb); - priv->stats.tx_dropped++; + ring->tx_dropped++; return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index cc84e09f324a..467d47ed2c39 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -270,6 +270,7 @@ struct mlx4_en_tx_ring { unsigned long tx_csum; unsigned long tso_packets; unsigned long xmit_more; + unsigned int tx_dropped; struct mlx4_bf bf; unsigned long queue_stopped; @@ -482,8 +483,6 @@ struct mlx4_en_priv { struct mlx4_en_port_profile *prof; struct net_device *dev; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - struct net_device_stats stats; - struct net_device_stats ret_stats; struct mlx4_en_port_state port_state; spinlock_t stats_lock; struct ethtool_flow_id ethtool_rules[MAX_NUM_OF_FS_RULES]; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index cbf58e1f9333..21ec1c2df2c7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -192,9 +192,10 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, struct dcbx_app_priority_entry *p_tbl, u32 pri_tc_tbl, int count, bool dcbx_enabled) { - u8 tc, priority, priority_map; + u8 tc, priority_map; enum dcbx_protocol_type type; u16 protocol_id; + int priority; bool enable; int i; @@ -221,7 +222,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, * indication, but we only got here if there was an * app tlv for the protocol, so dcbx must be enabled. */ - enable = !!(type == DCBX_PROTOCOL_ETH); + enable = !(type == DCBX_PROTOCOL_ETH); qed_dcbx_update_app_info(p_data, p_hwfn, enable, true, priority, tc, type); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 089016f46f26..2d89e8c16b32 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -155,12 +155,14 @@ void qed_resc_free(struct qed_dev *cdev) } } -static int qed_init_qm_info(struct qed_hwfn *p_hwfn) +static int qed_init_qm_info(struct qed_hwfn *p_hwfn, bool b_sleepable) { u8 num_vports, vf_offset = 0, i, vport_id, num_ports, curr_queue = 0; struct qed_qm_info *qm_info = &p_hwfn->qm_info; struct init_qm_port_params *p_qm_port; u16 num_pqs, multi_cos_tcs = 1; + u8 pf_wfq = qm_info->pf_wfq; + u32 pf_rl = qm_info->pf_rl; u16 num_vfs = 0; #ifdef CONFIG_QED_SRIOV @@ -182,23 +184,28 @@ static int qed_init_qm_info(struct qed_hwfn *p_hwfn) /* PQs will be arranged as follows: First per-TC PQ then pure-LB quete. */ - qm_info->qm_pq_params = kzalloc(sizeof(*qm_info->qm_pq_params) * - num_pqs, GFP_KERNEL); + qm_info->qm_pq_params = kcalloc(num_pqs, + sizeof(struct init_qm_pq_params), + b_sleepable ? GFP_KERNEL : GFP_ATOMIC); if (!qm_info->qm_pq_params) goto alloc_err; - qm_info->qm_vport_params = kzalloc(sizeof(*qm_info->qm_vport_params) * - num_vports, GFP_KERNEL); + qm_info->qm_vport_params = kcalloc(num_vports, + sizeof(struct init_qm_vport_params), + b_sleepable ? GFP_KERNEL + : GFP_ATOMIC); if (!qm_info->qm_vport_params) goto alloc_err; - qm_info->qm_port_params = kzalloc(sizeof(*qm_info->qm_port_params) * - MAX_NUM_PORTS, GFP_KERNEL); + qm_info->qm_port_params = kcalloc(MAX_NUM_PORTS, + sizeof(struct init_qm_port_params), + b_sleepable ? GFP_KERNEL + : GFP_ATOMIC); if (!qm_info->qm_port_params) goto alloc_err; - qm_info->wfq_data = kcalloc(num_vports, sizeof(*qm_info->wfq_data), - GFP_KERNEL); + qm_info->wfq_data = kcalloc(num_vports, sizeof(struct qed_wfq_data), + b_sleepable ? GFP_KERNEL : GFP_ATOMIC); if (!qm_info->wfq_data) goto alloc_err; @@ -264,10 +271,10 @@ static int qed_init_qm_info(struct qed_hwfn *p_hwfn) for (i = 0; i < qm_info->num_vports; i++) qm_info->qm_vport_params[i].vport_wfq = 1; - qm_info->pf_wfq = 0; - qm_info->pf_rl = 0; qm_info->vport_rl_en = 1; qm_info->vport_wfq_en = 1; + qm_info->pf_rl = pf_rl; + qm_info->pf_wfq = pf_wfq; return 0; @@ -299,7 +306,7 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) qed_qm_info_free(p_hwfn); /* initialize qed's qm data structure */ - rc = qed_init_qm_info(p_hwfn); + rc = qed_init_qm_info(p_hwfn, false); if (rc) return rc; @@ -388,7 +395,7 @@ int qed_resc_alloc(struct qed_dev *cdev) goto alloc_err; /* Prepare and process QM requirements */ - rc = qed_init_qm_info(p_hwfn); + rc = qed_init_qm_info(p_hwfn, true); if (rc) goto alloc_err; @@ -581,7 +588,14 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn) hw_mode |= 1 << MODE_ASIC; + if (p_hwfn->cdev->num_hwfns > 1) + hw_mode |= 1 << MODE_100G; + p_hwfn->hw_info.hw_mode = hw_mode; + + DP_VERBOSE(p_hwfn, (NETIF_MSG_PROBE | NETIF_MSG_IFUP), + "Configuring function for hw_mode: 0x%08x\n", + p_hwfn->hw_info.hw_mode); } /* Init run time data for all PFs on an engine. */ @@ -821,6 +835,11 @@ int qed_hw_init(struct qed_dev *cdev, u32 load_code, param; int rc, mfw_rc, i; + if ((int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) { + DP_NOTICE(cdev, "MSI mode is not supported for CMT devices\n"); + return -EINVAL; + } + if (IS_PF(cdev)) { rc = qed_init_fw_data(cdev, bin_fw_data); if (rc != 0) @@ -2086,6 +2105,13 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev, u32 min_pf_rate) { int i; + if (cdev->num_hwfns > 1) { + DP_VERBOSE(cdev, + NETIF_MSG_LINK, + "WFQ configuration is not supported for this device\n"); + return; + } + for_each_hwfn(cdev, i) { struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 8b22f87033ce..753064679bde 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -413,15 +413,17 @@ static int qed_set_int_mode(struct qed_dev *cdev, bool force_mode) /* Fallthrough */ case QED_INT_MODE_MSI: - rc = pci_enable_msi(cdev->pdev); - if (!rc) { - int_params->out.int_mode = QED_INT_MODE_MSI; - goto out; - } + if (cdev->num_hwfns == 1) { + rc = pci_enable_msi(cdev->pdev); + if (!rc) { + int_params->out.int_mode = QED_INT_MODE_MSI; + goto out; + } - DP_NOTICE(cdev, "Failed to enable MSI\n"); - if (force_mode) - goto out; + DP_NOTICE(cdev, "Failed to enable MSI\n"); + if (force_mode) + goto out; + } /* Fallthrough */ case QED_INT_MODE_INTA: diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 1bc75358cbc4..ad3cae3b7243 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -230,7 +230,10 @@ static int qede_get_sset_count(struct net_device *dev, int stringset) case ETH_SS_PRIV_FLAGS: return QEDE_PRI_FLAG_LEN; case ETH_SS_TEST: - return QEDE_ETHTOOL_TEST_MAX; + if (!IS_VF(edev)) + return QEDE_ETHTOOL_TEST_MAX; + else + return 0; default: DP_VERBOSE(edev, QED_MSG_DEBUG, "Unsupported stringset 0x%08x\n", stringset); diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 337e839ca586..5d00d1404bfc 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1824,7 +1824,7 @@ static int qede_set_vf_rate(struct net_device *dev, int vfidx, { struct qede_dev *edev = netdev_priv(dev); - return edev->ops->iov->set_rate(edev->cdev, vfidx, max_tx_rate, + return edev->ops->iov->set_rate(edev->cdev, vfidx, min_tx_rate, max_tx_rate); } @@ -2091,6 +2091,29 @@ static void qede_vlan_mark_nonconfigured(struct qede_dev *edev) edev->accept_any_vlan = false; } +int qede_set_features(struct net_device *dev, netdev_features_t features) +{ + struct qede_dev *edev = netdev_priv(dev); + netdev_features_t changes = features ^ dev->features; + bool need_reload = false; + + /* No action needed if hardware GRO is disabled during driver load */ + if (changes & NETIF_F_GRO) { + if (dev->features & NETIF_F_GRO) + need_reload = !edev->gro_disable; + else + need_reload = edev->gro_disable; + } + + if (need_reload && netif_running(edev->ndev)) { + dev->features = features; + qede_reload(edev, NULL, NULL); + return 1; + } + + return 0; +} + #ifdef CONFIG_QEDE_VXLAN static void qede_add_vxlan_port(struct net_device *dev, sa_family_t sa_family, __be16 port) @@ -2175,6 +2198,7 @@ static const struct net_device_ops qede_netdev_ops = { #endif .ndo_vlan_rx_add_vid = qede_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = qede_vlan_rx_kill_vid, + .ndo_set_features = qede_set_features, .ndo_get_stats64 = qede_get_stats64, #ifdef CONFIG_QED_SRIOV .ndo_set_vf_link_state = qede_set_vf_link_state, diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 83d72106471c..fd5d1c93b55b 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -4846,7 +4846,6 @@ static void ql_eeh_close(struct net_device *ndev) } /* Disabling the timer */ - del_timer_sync(&qdev->timer); ql_cancel_all_work_sync(qdev); for (i = 0; i < qdev->rss_ring_count; i++) @@ -4873,6 +4872,7 @@ static pci_ers_result_t qlge_io_error_detected(struct pci_dev *pdev, return PCI_ERS_RESULT_CAN_RECOVER; case pci_channel_io_frozen: netif_device_detach(ndev); + del_timer_sync(&qdev->timer); if (netif_running(ndev)) ql_eeh_close(ndev); pci_disable_device(pdev); @@ -4880,6 +4880,7 @@ static pci_ers_result_t qlge_io_error_detected(struct pci_dev *pdev, case pci_channel_io_perm_failure: dev_err(&pdev->dev, "%s: pci_channel_io_perm_failure.\n", __func__); + del_timer_sync(&qdev->timer); ql_eeh_close(ndev); set_bit(QL_EEH_FATAL, &qdev->flags); return PCI_ERS_RESULT_DISCONNECT; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 1681084cc96f..1f309127457d 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -619,6 +619,17 @@ fail: return rc; } +static void efx_ef10_forget_old_piobufs(struct efx_nic *efx) +{ + struct efx_channel *channel; + struct efx_tx_queue *tx_queue; + + /* All our existing PIO buffers went away */ + efx_for_each_channel(channel, efx) + efx_for_each_channel_tx_queue(tx_queue, channel) + tx_queue->piobuf = NULL; +} + #else /* !EFX_USE_PIO */ static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n) @@ -635,6 +646,10 @@ static void efx_ef10_free_piobufs(struct efx_nic *efx) { } +static void efx_ef10_forget_old_piobufs(struct efx_nic *efx) +{ +} + #endif /* EFX_USE_PIO */ static void efx_ef10_remove(struct efx_nic *efx) @@ -1018,6 +1033,7 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx) nic_data->must_realloc_vis = true; nic_data->must_restore_filters = true; nic_data->must_restore_piobufs = true; + efx_ef10_forget_old_piobufs(efx); nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID; /* Driver-created vswitches and vports must be re-created */ diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 0705ec869487..097f363f1630 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1726,14 +1726,33 @@ static int efx_probe_filters(struct efx_nic *efx) #ifdef CONFIG_RFS_ACCEL if (efx->type->offload_features & NETIF_F_NTUPLE) { - efx->rps_flow_id = kcalloc(efx->type->max_rx_ip_filters, - sizeof(*efx->rps_flow_id), - GFP_KERNEL); - if (!efx->rps_flow_id) { + struct efx_channel *channel; + int i, success = 1; + + efx_for_each_channel(channel, efx) { + channel->rps_flow_id = + kcalloc(efx->type->max_rx_ip_filters, + sizeof(*channel->rps_flow_id), + GFP_KERNEL); + if (!channel->rps_flow_id) + success = 0; + else + for (i = 0; + i < efx->type->max_rx_ip_filters; + ++i) + channel->rps_flow_id[i] = + RPS_FLOW_ID_INVALID; + } + + if (!success) { + efx_for_each_channel(channel, efx) + kfree(channel->rps_flow_id); efx->type->filter_table_remove(efx); rc = -ENOMEM; goto out_unlock; } + + efx->rps_expire_index = efx->rps_expire_channel = 0; } #endif out_unlock: @@ -1744,7 +1763,10 @@ out_unlock: static void efx_remove_filters(struct efx_nic *efx) { #ifdef CONFIG_RFS_ACCEL - kfree(efx->rps_flow_id); + struct efx_channel *channel; + + efx_for_each_channel(channel, efx) + kfree(channel->rps_flow_id); #endif down_write(&efx->filter_sem); efx->type->filter_table_remove(efx); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 38c422321cda..d13ddf9703ff 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -403,6 +403,8 @@ enum efx_sync_events_state { * @event_test_cpu: Last CPU to handle interrupt or test event for this channel * @irq_count: Number of IRQs since last adaptive moderation decision * @irq_mod_score: IRQ moderation score + * @rps_flow_id: Flow IDs of filters allocated for accelerated RFS, + * indexed by filter ID * @n_rx_tobe_disc: Count of RX_TOBE_DISC errors * @n_rx_ip_hdr_chksum_err: Count of RX IP header checksum errors * @n_rx_tcp_udp_chksum_err: Count of RX TCP and UDP checksum errors @@ -446,6 +448,8 @@ struct efx_channel { unsigned int irq_mod_score; #ifdef CONFIG_RFS_ACCEL unsigned int rfs_filters_added; +#define RPS_FLOW_ID_INVALID 0xFFFFFFFF + u32 *rps_flow_id; #endif unsigned n_rx_tobe_disc; @@ -889,9 +893,9 @@ struct vfdi_status; * @filter_sem: Filter table rw_semaphore, for freeing the table * @filter_lock: Filter table lock, for mere content changes * @filter_state: Architecture-dependent filter table state - * @rps_flow_id: Flow IDs of filters allocated for accelerated RFS, - * indexed by filter ID - * @rps_expire_index: Next index to check for expiry in @rps_flow_id + * @rps_expire_channel: Next channel to check for expiry + * @rps_expire_index: Next index to check for expiry in + * @rps_expire_channel's @rps_flow_id * @active_queues: Count of RX and TX queues that haven't been flushed and drained. * @rxq_flush_pending: Count of number of receive queues that need to be flushed. * Decremented when the efx_flush_rx_queue() is called. @@ -1035,7 +1039,7 @@ struct efx_nic { spinlock_t filter_lock; void *filter_state; #ifdef CONFIG_RFS_ACCEL - u32 *rps_flow_id; + unsigned int rps_expire_channel; unsigned int rps_expire_index; #endif diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 8956995b2fe7..02b0b5272c14 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -842,33 +842,18 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, struct efx_nic *efx = netdev_priv(net_dev); struct efx_channel *channel; struct efx_filter_spec spec; - const __be16 *ports; - __be16 ether_type; - int nhoff; + struct flow_keys fk; int rc; - /* The core RPS/RFS code has already parsed and validated - * VLAN, IP and transport headers. We assume they are in the - * header area. - */ - - if (skb->protocol == htons(ETH_P_8021Q)) { - const struct vlan_hdr *vh = - (const struct vlan_hdr *)skb->data; + if (flow_id == RPS_FLOW_ID_INVALID) + return -EINVAL; - /* We can't filter on the IP 5-tuple and the vlan - * together, so just strip the vlan header and filter - * on the IP part. - */ - EFX_BUG_ON_PARANOID(skb_headlen(skb) < sizeof(*vh)); - ether_type = vh->h_vlan_encapsulated_proto; - nhoff = sizeof(struct vlan_hdr); - } else { - ether_type = skb->protocol; - nhoff = 0; - } + if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) + return -EPROTONOSUPPORT; - if (ether_type != htons(ETH_P_IP) && ether_type != htons(ETH_P_IPV6)) + if (fk.basic.n_proto != htons(ETH_P_IP) && fk.basic.n_proto != htons(ETH_P_IPV6)) + return -EPROTONOSUPPORT; + if (fk.control.flags & FLOW_DIS_IS_FRAGMENT) return -EPROTONOSUPPORT; efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT, @@ -878,56 +863,41 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO | EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT | EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT; - spec.ether_type = ether_type; - - if (ether_type == htons(ETH_P_IP)) { - const struct iphdr *ip = - (const struct iphdr *)(skb->data + nhoff); - - EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip)); - if (ip_is_fragment(ip)) - return -EPROTONOSUPPORT; - spec.ip_proto = ip->protocol; - spec.rem_host[0] = ip->saddr; - spec.loc_host[0] = ip->daddr; - EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4); - ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl); + spec.ether_type = fk.basic.n_proto; + spec.ip_proto = fk.basic.ip_proto; + + if (fk.basic.n_proto == htons(ETH_P_IP)) { + spec.rem_host[0] = fk.addrs.v4addrs.src; + spec.loc_host[0] = fk.addrs.v4addrs.dst; } else { - const struct ipv6hdr *ip6 = - (const struct ipv6hdr *)(skb->data + nhoff); - - EFX_BUG_ON_PARANOID(skb_headlen(skb) < - nhoff + sizeof(*ip6) + 4); - spec.ip_proto = ip6->nexthdr; - memcpy(spec.rem_host, &ip6->saddr, sizeof(ip6->saddr)); - memcpy(spec.loc_host, &ip6->daddr, sizeof(ip6->daddr)); - ports = (const __be16 *)(ip6 + 1); + memcpy(spec.rem_host, &fk.addrs.v6addrs.src, sizeof(struct in6_addr)); + memcpy(spec.loc_host, &fk.addrs.v6addrs.dst, sizeof(struct in6_addr)); } - spec.rem_port = ports[0]; - spec.loc_port = ports[1]; + spec.rem_port = fk.ports.src; + spec.loc_port = fk.ports.dst; rc = efx->type->filter_rfs_insert(efx, &spec); if (rc < 0) return rc; /* Remember this so we can check whether to expire the filter later */ - efx->rps_flow_id[rc] = flow_id; - channel = efx_get_channel(efx, skb_get_rx_queue(skb)); + channel = efx_get_channel(efx, rxq_index); + channel->rps_flow_id[rc] = flow_id; ++channel->rfs_filters_added; - if (ether_type == htons(ETH_P_IP)) + if (spec.ether_type == htons(ETH_P_IP)) netif_info(efx, rx_status, efx->net_dev, "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n", (spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP", - spec.rem_host, ntohs(ports[0]), spec.loc_host, - ntohs(ports[1]), rxq_index, flow_id, rc); + spec.rem_host, ntohs(spec.rem_port), spec.loc_host, + ntohs(spec.loc_port), rxq_index, flow_id, rc); else netif_info(efx, rx_status, efx->net_dev, "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n", (spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP", - spec.rem_host, ntohs(ports[0]), spec.loc_host, - ntohs(ports[1]), rxq_index, flow_id, rc); + spec.rem_host, ntohs(spec.rem_port), spec.loc_host, + ntohs(spec.loc_port), rxq_index, flow_id, rc); return rc; } @@ -935,24 +905,34 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned int quota) { bool (*expire_one)(struct efx_nic *efx, u32 flow_id, unsigned int index); - unsigned int index, size; + unsigned int channel_idx, index, size; u32 flow_id; if (!spin_trylock_bh(&efx->filter_lock)) return false; expire_one = efx->type->filter_rfs_expire_one; + channel_idx = efx->rps_expire_channel; index = efx->rps_expire_index; size = efx->type->max_rx_ip_filters; while (quota--) { - flow_id = efx->rps_flow_id[index]; - if (expire_one(efx, flow_id, index)) + struct efx_channel *channel = efx_get_channel(efx, channel_idx); + flow_id = channel->rps_flow_id[index]; + + if (flow_id != RPS_FLOW_ID_INVALID && + expire_one(efx, flow_id, index)) { netif_info(efx, rx_status, efx->net_dev, - "expired filter %d [flow %u]\n", - index, flow_id); - if (++index == size) + "expired filter %d [queue %u flow %u]\n", + index, channel_idx, flow_id); + channel->rps_flow_id[index] = RPS_FLOW_ID_INVALID; + } + if (++index == size) { + if (++channel_idx == efx->n_channels) + channel_idx = 0; index = 0; + } } + efx->rps_expire_channel = channel_idx; efx->rps_expire_index = index; spin_unlock_bh(&efx->filter_lock); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 3f83c369f56c..ec295851812b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -297,7 +297,7 @@ int stmmac_mdio_register(struct net_device *ndev) return -ENOMEM; if (mdio_bus_data->irqs) - memcpy(new_bus->irq, mdio_bus_data, sizeof(new_bus->irq)); + memcpy(new_bus->irq, mdio_bus_data->irqs, sizeof(new_bus->irq)); #ifdef CONFIG_OF if (priv->device->of_node) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index a0f64cba86ba..2ace126533cd 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -990,7 +990,7 @@ static void team_port_disable(struct team *team, #define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_ALL_TSO) -static void __team_compute_features(struct team *team) +static void ___team_compute_features(struct team *team) { struct team_port *port; u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL; @@ -1021,15 +1021,20 @@ static void __team_compute_features(struct team *team) team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) team->dev->priv_flags |= IFF_XMIT_DST_RELEASE; +} +static void __team_compute_features(struct team *team) +{ + ___team_compute_features(team); netdev_change_features(team->dev); } static void team_compute_features(struct team *team) { mutex_lock(&team->lock); - __team_compute_features(team); + ___team_compute_features(team); mutex_unlock(&team->lock); + netdev_change_features(team->dev); } static int team_port_enter(struct team *team, struct team_port *port) diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 36cd7f016a8d..9bbe0161a2f4 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -473,7 +473,7 @@ static void read_bulk_callback(struct urb *urb) goto goon; } - if (!count || count < 4) + if (count < 4) goto goon; rx_status = buf[count - 2]; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index d9d2806a47b1..dc989a8b5afb 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -61,6 +61,8 @@ #define SUSPEND_ALLMODES (SUSPEND_SUSPEND0 | SUSPEND_SUSPEND1 | \ SUSPEND_SUSPEND2 | SUSPEND_SUSPEND3) +#define CARRIER_CHECK_DELAY (2 * HZ) + struct smsc95xx_priv { u32 mac_cr; u32 hash_hi; @@ -69,6 +71,9 @@ struct smsc95xx_priv { spinlock_t mac_cr_lock; u8 features; u8 suspend_flags; + bool link_ok; + struct delayed_work carrier_check; + struct usbnet *dev; }; static bool turbo_mode = true; @@ -624,6 +629,44 @@ static void smsc95xx_status(struct usbnet *dev, struct urb *urb) intdata); } +static void set_carrier(struct usbnet *dev, bool link) +{ + struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + + if (pdata->link_ok == link) + return; + + pdata->link_ok = link; + + if (link) + usbnet_link_change(dev, 1, 0); + else + usbnet_link_change(dev, 0, 0); +} + +static void check_carrier(struct work_struct *work) +{ + struct smsc95xx_priv *pdata = container_of(work, struct smsc95xx_priv, + carrier_check.work); + struct usbnet *dev = pdata->dev; + int ret; + + if (pdata->suspend_flags != 0) + return; + + ret = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, MII_BMSR); + if (ret < 0) { + netdev_warn(dev->net, "Failed to read MII_BMSR\n"); + return; + } + if (ret & BMSR_LSTATUS) + set_carrier(dev, 1); + else + set_carrier(dev, 0); + + schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); +} + /* Enable or disable Tx & Rx checksum offload engines */ static int smsc95xx_set_features(struct net_device *netdev, netdev_features_t features) @@ -1165,13 +1208,20 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->flags |= IFF_MULTICAST; dev->net->hard_header_len += SMSC95XX_TX_OVERHEAD_CSUM; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + + pdata->dev = dev; + INIT_DELAYED_WORK(&pdata->carrier_check, check_carrier); + schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); + return 0; } static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) { struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + if (pdata) { + cancel_delayed_work(&pdata->carrier_check); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); pdata = NULL; @@ -1695,6 +1745,7 @@ static int smsc95xx_resume(struct usb_interface *intf) /* do this first to ensure it's cleared even in error case */ pdata->suspend_flags = 0; + schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); if (suspend_flags & SUSPEND_ALLMODES) { /* clear wake-up sources */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 49d84e540343..e0638e556fe7 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1925,24 +1925,11 @@ static int virtnet_probe(struct virtio_device *vdev) virtio_device_ready(vdev); - /* Last of all, set up some receive buffers. */ - for (i = 0; i < vi->curr_queue_pairs; i++) { - try_fill_recv(vi, &vi->rq[i], GFP_KERNEL); - - /* If we didn't even get one input buffer, we're useless. */ - if (vi->rq[i].vq->num_free == - virtqueue_get_vring_size(vi->rq[i].vq)) { - free_unused_bufs(vi); - err = -ENOMEM; - goto free_recv_bufs; - } - } - vi->nb.notifier_call = &virtnet_cpu_callback; err = register_hotcpu_notifier(&vi->nb); if (err) { pr_debug("virtio_net: registering cpu notifier failed\n"); - goto free_recv_bufs; + goto free_unregister_netdev; } /* Assume link up if device can't report link status, @@ -1960,10 +1947,9 @@ static int virtnet_probe(struct virtio_device *vdev) return 0; -free_recv_bufs: +free_unregister_netdev: vi->vdev->config->reset(vdev); - free_receive_bufs(vi); unregister_netdev(dev); free_vqs: cancel_delayed_work_sync(&vi->refill); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 8ff30c3bdfce..f999db2f97b4 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3086,6 +3086,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL; + if (tb[IFLA_MTU]) + conf.mtu = nla_get_u32(tb[IFLA_MTU]); + err = vxlan_dev_configure(src_net, dev, &conf); switch (err) { case -ENODEV: diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index f2d01d4d9364..1b8304e1efaa 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -950,17 +950,14 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) /* For SPIs, we need to track the affinity per IRQ */ if (using_spi) { - if (i >= pdev->num_resources) { - of_node_put(dn); + if (i >= pdev->num_resources) break; - } irqs[i] = cpu; } /* Keep track of the CPUs containing this PMU type */ cpumask_set_cpu(cpu, &pmu->supported_cpus); - of_node_put(dn); i++; } while (1); @@ -995,9 +992,6 @@ int arm_pmu_device_probe(struct platform_device *pdev, armpmu_init(pmu); - if (!__oprofile_cpu_pmu) - __oprofile_cpu_pmu = pmu; - pmu->plat_device = pdev; if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) { @@ -1033,6 +1027,9 @@ int arm_pmu_device_probe(struct platform_device *pdev, if (ret) goto out_destroy; + if (!__oprofile_cpu_pmu) + __oprofile_cpu_pmu = pmu; + pr_info("enabled with %s PMU driver, %d counters available\n", pmu->name, pmu->num_events); @@ -1043,6 +1040,7 @@ out_destroy: out_free: pr_info("%s: failed to register PMU devices!\n", of_node_full_name(node)); + kfree(pmu->irq_affinity); kfree(pmu); return ret; } diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c index 207b13b618cf..a607655d7830 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c @@ -1256,9 +1256,10 @@ static void mtk_eint_irq_handler(struct irq_desc *desc) const struct mtk_desc_pin *pin; chained_irq_enter(chip, desc); - for (eint_num = 0; eint_num < pctl->devdata->ap_num; eint_num += 32) { + for (eint_num = 0; + eint_num < pctl->devdata->ap_num; + eint_num += 32, reg += 4) { status = readl(reg); - reg += 4; while (status) { offset = __ffs(status); index = eint_num + offset; diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c index ccbfc325c778..38faceff2f08 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c @@ -854,7 +854,7 @@ static int nmk_gpio_get_dir(struct gpio_chip *chip, unsigned offset) clk_enable(nmk_chip->clk); - dir = !!(readl(nmk_chip->addr + NMK_GPIO_DIR) & BIT(offset)); + dir = !(readl(nmk_chip->addr + NMK_GPIO_DIR) & BIT(offset)); clk_disable(nmk_chip->clk); diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 579fd65299a0..d637c933c8a9 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -208,14 +208,10 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) break; case PTP_SYS_OFFSET: - sysoff = kmalloc(sizeof(*sysoff), GFP_KERNEL); - if (!sysoff) { - err = -ENOMEM; - break; - } - if (copy_from_user(sysoff, (void __user *)arg, - sizeof(*sysoff))) { - err = -EFAULT; + sysoff = memdup_user((void __user *)arg, sizeof(*sysoff)); + if (IS_ERR(sysoff)) { + err = PTR_ERR(sysoff); + sysoff = NULL; break; } if (sysoff->n_samples > PTP_MAX_SAMPLES) { diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 8f90d9e77104..969c312de1be 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -621,6 +621,11 @@ struct aac_driver_ident #define AAC_QUIRK_SCSI_32 0x0020 /* + * SRC based adapters support the AifReqEvent functions + */ +#define AAC_QUIRK_SRC 0x0040 + +/* * The adapter interface specs all queues to be located in the same * physically contiguous block. The host structure that defines the * commuication queues will assume they are each a separate physically diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index a943bd230bc2..79871f3519ff 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -236,10 +236,10 @@ static struct aac_driver_ident aac_drivers[] = { { aac_rx_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec Catch All */ { aac_rkt_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec Rocket Catch All */ { aac_nark_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec NEMER/ARK Catch All */ - { aac_src_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 6 (Tupelo) */ - { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 7 (Denali) */ - { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 8 */ - { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 } /* Adaptec PMC Series 9 */ + { aac_src_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 6 (Tupelo) */ + { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 7 (Denali) */ + { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 8 */ + { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC } /* Adaptec PMC Series 9 */ }; /** @@ -1299,7 +1299,8 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) else shost->this_id = shost->max_id; - aac_intr_normal(aac, 0, 2, 0, NULL); + if (aac_drivers[index].quirks & AAC_QUIRK_SRC) + aac_intr_normal(aac, 0, 2, 0, NULL); /* * dmb - we may need to move the setting of these parms somewhere else once diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 6a4df5a315e9..6bff13e7afc7 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -7975,13 +7975,14 @@ mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index, ActiveCableEventData = (Mpi26EventDataActiveCableExcept_t *) mpi_reply->EventData; if (ActiveCableEventData->ReasonCode == - MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER) + MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER) { pr_info(MPT3SAS_FMT "Currently an active cable with ReceptacleID %d", ioc->name, ActiveCableEventData->ReceptacleID); pr_info("cannot be powered and devices connected to this active cable"); pr_info("will not be seen. This active cable"); pr_info("requires %d mW of power", ActiveCableEventData->ActiveCablePowerRequirement); + } break; default: /* ignore the rest */ diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b2e332af0f51..c71344aebdbb 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -821,9 +821,12 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) } /* - * If we finished all bytes in the request we are done now. + * special case: failed zero length commands always need to + * drop down into the retry code. Otherwise, if we finished + * all bytes in the request we are done now. */ - if (!scsi_end_request(req, error, good_bytes, 0)) + if (!(blk_rq_bytes(req) == 0 && error) && + !scsi_end_request(req, error, good_bytes, 0)) return; /* diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 428c03ef02b2..f459dff30512 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1398,11 +1398,15 @@ static int media_not_present(struct scsi_disk *sdkp, **/ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing) { - struct scsi_disk *sdkp = scsi_disk(disk); - struct scsi_device *sdp = sdkp->device; + struct scsi_disk *sdkp = scsi_disk_get(disk); + struct scsi_device *sdp; struct scsi_sense_hdr *sshdr = NULL; int retval; + if (!sdkp) + return 0; + + sdp = sdkp->device; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n")); /* @@ -1459,6 +1463,7 @@ out: kfree(sshdr); retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0; sdp->changed = 0; + scsi_disk_put(sdkp); return retval; } diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 3fe90d494edb..4551c6f2a6c4 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -112,19 +112,24 @@ struct dma_buf_ops { * @file: file pointer used for sharing buffers across, and for refcounting. * @attachments: list of dma_buf_attachment that denotes all devices attached. * @ops: dma_buf_ops associated with this buffer object. + * @lock: used internally to serialize list manipulation, attach/detach and vmap/unmap + * @vmapping_counter: used internally to refcnt the vmaps + * @vmap_ptr: the current vmap ptr if vmapping_counter > 0 * @exp_name: name of the exporter; useful for debugging. * @owner: pointer to exporter module; used for refcounting when exporter is a * kernel module. * @list_node: node for dma_buf accounting and debugging. * @priv: exporter specific private data for this buffer object. * @resv: reservation object linked to this dma-buf + * @poll: for userspace poll support + * @cb_excl: for userspace poll support + * @cb_shared: for userspace poll support */ struct dma_buf { size_t size; struct file *file; struct list_head attachments; const struct dma_buf_ops *ops; - /* mutex to serialize list manipulation, attach/detach and vmap/unmap */ struct mutex lock; unsigned vmapping_counter; void *vmap_ptr; @@ -188,9 +193,11 @@ struct dma_buf_export_info { /** * helper macro for exporters; zeros and fills in most common values + * + * @name: export-info name */ -#define DEFINE_DMA_BUF_EXPORT_INFO(a) \ - struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME, \ +#define DEFINE_DMA_BUF_EXPORT_INFO(name) \ + struct dma_buf_export_info name = { .exp_name = KBUILD_MODNAME, \ .owner = THIS_MODULE } /** diff --git a/include/linux/fence.h b/include/linux/fence.h index 2b17698b60b8..2056e9fd0138 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -49,6 +49,8 @@ struct fence_cb; * @timestamp: Timestamp when the fence was signaled. * @status: Optional, only valid if < 0, must be set before calling * fence_signal, indicates that the fence has completed with an error. + * @child_list: list of children fences + * @active_list: list of active fences * * the flags member must be manipulated and read using the appropriate * atomic ops (bit_*), so taking the spinlock will not be needed most diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 49d057655d62..b0f305e77b7f 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -49,12 +49,27 @@ extern struct ww_class reservation_ww_class; extern struct lock_class_key reservation_seqcount_class; extern const char reservation_seqcount_string[]; +/** + * struct reservation_object_list - a list of shared fences + * @rcu: for internal use + * @shared_count: table of shared fences + * @shared_max: for growing shared fence table + * @shared: shared fence table + */ struct reservation_object_list { struct rcu_head rcu; u32 shared_count, shared_max; struct fence __rcu *shared[]; }; +/** + * struct reservation_object - a reservation object manages fences for a buffer + * @lock: update side lock + * @seq: sequence count for managing RCU read-side synchronization + * @fence_excl: the exclusive fence, if there is one currently + * @fence: list of current shared fences + * @staged: staged copy of shared fences for RCU updates + */ struct reservation_object { struct ww_mutex lock; seqcount_t seq; @@ -68,6 +83,10 @@ struct reservation_object { #define reservation_object_assert_held(obj) \ lockdep_assert_held(&(obj)->lock.base) +/** + * reservation_object_init - initialize a reservation object + * @obj: the reservation object + */ static inline void reservation_object_init(struct reservation_object *obj) { @@ -79,6 +98,10 @@ reservation_object_init(struct reservation_object *obj) obj->staged = NULL; } +/** + * reservation_object_fini - destroys a reservation object + * @obj: the reservation object + */ static inline void reservation_object_fini(struct reservation_object *obj) { @@ -106,6 +129,14 @@ reservation_object_fini(struct reservation_object *obj) ww_mutex_destroy(&obj->lock); } +/** + * reservation_object_get_list - get the reservation object's + * shared fence list, with update-side lock held + * @obj: the reservation object + * + * Returns the shared fence list. Does NOT take references to + * the fence. The obj->lock must be held. + */ static inline struct reservation_object_list * reservation_object_get_list(struct reservation_object *obj) { @@ -113,6 +144,17 @@ reservation_object_get_list(struct reservation_object *obj) reservation_object_held(obj)); } +/** + * reservation_object_get_excl - get the reservation object's + * exclusive fence, with update-side lock held + * @obj: the reservation object + * + * Returns the exclusive fence (if any). Does NOT take a + * reference. The obj->lock must be held. + * + * RETURNS + * The exclusive fence or NULL + */ static inline struct fence * reservation_object_get_excl(struct reservation_object *obj) { @@ -120,6 +162,17 @@ reservation_object_get_excl(struct reservation_object *obj) reservation_object_held(obj)); } +/** + * reservation_object_get_excl_rcu - get the reservation object's + * exclusive fence, without lock held. + * @obj: the reservation object + * + * If there is an exclusive fence, this atomically increments it's + * reference count and returns it. + * + * RETURNS + * The exclusive fence or NULL if none + */ static inline struct fence * reservation_object_get_excl_rcu(struct reservation_object *obj) { diff --git a/include/linux/sctp.h b/include/linux/sctp.h index dacb5e711994..de1f64318fc4 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -765,6 +765,8 @@ struct sctp_info { __u8 sctpi_s_disable_fragments; __u8 sctpi_s_v4mapped; __u8 sctpi_s_frag_interleave; + __u32 sctpi_s_type; + __u32 __reserved3; }; struct sctp_infox { diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 37dbacf84849..816b7543f81b 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -21,6 +21,9 @@ static inline int do_sys_settimeofday(const struct timespec *tv, struct timespec64 ts64; if (!tv) + return do_sys_settimeofday64(NULL, tz); + + if (!timespec_valid(tv)) return -EINVAL; ts64 = timespec_to_timespec64(*tv); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index d325c81332e3..43a5a0e4524c 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -63,6 +63,8 @@ struct ip6_tnl_encap_ops { u8 *protocol, struct flowi6 *fl6); }; +#ifdef CONFIG_INET + extern const struct ip6_tnl_encap_ops __rcu * ip6tun_encaps[MAX_IPTUN_ENCAP_OPS]; @@ -138,7 +140,6 @@ struct net *ip6_tnl_get_link_net(const struct net_device *dev); int ip6_tnl_get_iflink(const struct net_device *dev); int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu); -#ifdef CONFIG_INET static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, struct net_device *dev) { diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 401038d2f9b8..fea53f4d92ca 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -61,6 +61,7 @@ psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound) } struct qdisc_watchdog { + u64 last_expires; struct hrtimer timer; struct Qdisc *qdisc; }; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 9222db8ccccc..5f030b46cff4 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1353,6 +1353,15 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT = 28, ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT = 29, ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT = 30, + ETHTOOL_LINK_MODE_25000baseCR_Full_BIT = 31, + ETHTOOL_LINK_MODE_25000baseKR_Full_BIT = 32, + ETHTOOL_LINK_MODE_25000baseSR_Full_BIT = 33, + ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT = 34, + ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT = 35, + ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT = 36, + ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT = 37, + ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT = 38, + ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT = 39, /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* @@ -1361,7 +1370,7 @@ enum ethtool_link_mode_bit_indices { */ __ETHTOOL_LINK_MODE_LAST - = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT, + = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, }; #define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index eba5914ba5d1..f4297c8a42fe 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -145,6 +145,8 @@ enum { TCA_POLICE_PEAKRATE, TCA_POLICE_AVRATE, TCA_POLICE_RESULT, + TCA_POLICE_TM, + TCA_POLICE_PAD, __TCA_POLICE_MAX #define TCA_POLICE_RESULT TCA_POLICE_RESULT }; @@ -173,7 +175,7 @@ enum { TCA_U32_DIVISOR, TCA_U32_SEL, TCA_U32_POLICE, - TCA_U32_ACT, + TCA_U32_ACT, TCA_U32_INDEV, TCA_U32_PCNT, TCA_U32_MARK, diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 04be7021f848..318858edb1cd 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -365,7 +365,6 @@ static struct file_system_type bpf_fs_type = { .name = "bpf", .mount = bpf_mount, .kill_sb = kill_litter_super, - .fs_flags = FS_USERNS_MOUNT, }; MODULE_ALIAS_FS("bpf"); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 8c7392c4fdbd..e99df0ff1d42 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -425,6 +425,7 @@ void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } +EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 77d7d034bac3..b9cfdbfae9aa 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1841,6 +1841,9 @@ config TEST_BITMAP If unsure, say N. +config TEST_UUID + tristate "Test functions located in the uuid module at runtime" + config TEST_RHASHTABLE tristate "Perform selftest on resizable hash table" default n diff --git a/lib/Makefile b/lib/Makefile index 499fb354d627..ff6a7a6c6395 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -58,6 +58,7 @@ obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o obj-$(CONFIG_TEST_PRINTF) += test_printf.o obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o +obj-$(CONFIG_TEST_UUID) += test_uuid.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG diff --git a/lib/test_uuid.c b/lib/test_uuid.c new file mode 100644 index 000000000000..547d3127a3cf --- /dev/null +++ b/lib/test_uuid.c @@ -0,0 +1,133 @@ +/* + * Test cases for lib/uuid.c module. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/string.h> +#include <linux/uuid.h> + +struct test_uuid_data { + const char *uuid; + uuid_le le; + uuid_be be; +}; + +static const struct test_uuid_data test_uuid_test_data[] = { + { + .uuid = "c33f4995-3701-450e-9fbf-206a2e98e576", + .le = UUID_LE(0xc33f4995, 0x3701, 0x450e, 0x9f, 0xbf, 0x20, 0x6a, 0x2e, 0x98, 0xe5, 0x76), + .be = UUID_BE(0xc33f4995, 0x3701, 0x450e, 0x9f, 0xbf, 0x20, 0x6a, 0x2e, 0x98, 0xe5, 0x76), + }, + { + .uuid = "64b4371c-77c1-48f9-8221-29f054fc023b", + .le = UUID_LE(0x64b4371c, 0x77c1, 0x48f9, 0x82, 0x21, 0x29, 0xf0, 0x54, 0xfc, 0x02, 0x3b), + .be = UUID_BE(0x64b4371c, 0x77c1, 0x48f9, 0x82, 0x21, 0x29, 0xf0, 0x54, 0xfc, 0x02, 0x3b), + }, + { + .uuid = "0cb4ddff-a545-4401-9d06-688af53e7f84", + .le = UUID_LE(0x0cb4ddff, 0xa545, 0x4401, 0x9d, 0x06, 0x68, 0x8a, 0xf5, 0x3e, 0x7f, 0x84), + .be = UUID_BE(0x0cb4ddff, 0xa545, 0x4401, 0x9d, 0x06, 0x68, 0x8a, 0xf5, 0x3e, 0x7f, 0x84), + }, +}; + +static const char * const test_uuid_wrong_data[] = { + "c33f4995-3701-450e-9fbf206a2e98e576 ", /* no hyphen(s) */ + "64b4371c-77c1-48f9-8221-29f054XX023b", /* invalid character(s) */ + "0cb4ddff-a545-4401-9d06-688af53e", /* not enough data */ +}; + +static unsigned total_tests __initdata; +static unsigned failed_tests __initdata; + +static void __init test_uuid_failed(const char *prefix, bool wrong, bool be, + const char *data, const char *actual) +{ + pr_err("%s test #%u %s %s data: '%s'\n", + prefix, + total_tests, + wrong ? "passed on wrong" : "failed on", + be ? "BE" : "LE", + data); + if (actual && *actual) + pr_err("%s test #%u actual data: '%s'\n", + prefix, + total_tests, + actual); + failed_tests++; +} + +static void __init test_uuid_test(const struct test_uuid_data *data) +{ + uuid_le le; + uuid_be be; + char buf[48]; + + /* LE */ + total_tests++; + if (uuid_le_to_bin(data->uuid, &le)) + test_uuid_failed("conversion", false, false, data->uuid, NULL); + + total_tests++; + if (uuid_le_cmp(data->le, le)) { + sprintf(buf, "%pUl", &le); + test_uuid_failed("cmp", false, false, data->uuid, buf); + } + + /* BE */ + total_tests++; + if (uuid_be_to_bin(data->uuid, &be)) + test_uuid_failed("conversion", false, true, data->uuid, NULL); + + total_tests++; + if (uuid_be_cmp(data->be, be)) { + sprintf(buf, "%pUb", &be); + test_uuid_failed("cmp", false, true, data->uuid, buf); + } +} + +static void __init test_uuid_wrong(const char *data) +{ + uuid_le le; + uuid_be be; + + /* LE */ + total_tests++; + if (!uuid_le_to_bin(data, &le)) + test_uuid_failed("negative", true, false, data, NULL); + + /* BE */ + total_tests++; + if (!uuid_be_to_bin(data, &be)) + test_uuid_failed("negative", true, true, data, NULL); +} + +static int __init test_uuid_init(void) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(test_uuid_test_data); i++) + test_uuid_test(&test_uuid_test_data[i]); + + for (i = 0; i < ARRAY_SIZE(test_uuid_wrong_data); i++) + test_uuid_wrong(test_uuid_wrong_data[i]); + + if (failed_tests == 0) + pr_info("all %u tests passed\n", total_tests); + else + pr_err("failed %u out of %u tests\n", failed_tests, total_tests); + + return failed_tests ? -EINVAL : 0; +} +module_init(test_uuid_init); + +static void __exit test_uuid_exit(void) +{ + /* do nothing */ +} +module_exit(test_uuid_exit); + +MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/uuid.c b/lib/uuid.c index e116ae5fa00f..37687af77ff8 100644 --- a/lib/uuid.c +++ b/lib/uuid.c @@ -106,8 +106,8 @@ static int __uuid_to_bin(const char *uuid, __u8 b[16], const u8 ei[16]) return -EINVAL; for (i = 0; i < 16; i++) { - int hi = hex_to_bin(uuid[si[i]] + 0); - int lo = hex_to_bin(uuid[si[i]] + 1); + int hi = hex_to_bin(uuid[si[i] + 0]); + int lo = hex_to_bin(uuid[si[i] + 1]); b[ei[i]] = (hi << 4) | lo; } diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a1e273af6fc8..82a116ba590e 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -290,6 +290,10 @@ static void vlan_sync_address(struct net_device *dev, if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr)) return; + /* vlan continues to inherit address of lower device */ + if (vlan_dev_inherit_address(vlandev, dev)) + goto out; + /* vlan address was different from the old address and is equal to * the new address */ if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && @@ -302,6 +306,7 @@ static void vlan_sync_address(struct net_device *dev, !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); +out: ether_addr_copy(vlan->real_dev_addr, dev->dev_addr); } diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 9d010a09ab98..cc1557978066 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -109,6 +109,8 @@ int vlan_check_real_dev(struct net_device *real_dev, void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); +bool vlan_dev_inherit_address(struct net_device *dev, + struct net_device *real_dev); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e7e62570bdb8..86ae75b77390 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -245,6 +245,17 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result) strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23); } +bool vlan_dev_inherit_address(struct net_device *dev, + struct net_device *real_dev) +{ + if (dev->addr_assign_type != NET_ADDR_STOLEN) + return false; + + ether_addr_copy(dev->dev_addr, real_dev->dev_addr); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return true; +} + static int vlan_dev_open(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); @@ -255,7 +266,8 @@ static int vlan_dev_open(struct net_device *dev) !(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) return -ENETDOWN; - if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) { + if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr) && + !vlan_dev_inherit_address(dev, real_dev)) { err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) goto out; @@ -560,8 +572,10 @@ static int vlan_dev_init(struct net_device *dev) /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; - if (is_zero_ether_addr(dev->dev_addr)) - eth_hw_addr_inherit(dev, real_dev); + if (is_zero_ether_addr(dev->dev_addr)) { + ether_addr_copy(dev->dev_addr, real_dev->dev_addr); + dev->addr_assign_type = NET_ADDR_STOLEN; + } if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 4fd6af47383a..adb6e3d21b1e 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -124,7 +124,7 @@ as_indicate_complete: break; case as_addparty: case as_dropparty: - sk->sk_err_soft = msg->reply; + sk->sk_err_soft = -msg->reply; /* < 0 failure, otherwise ep_ref */ clear_bit(ATM_VF_WAITING, &vcc->flags); break; diff --git a/net/atm/svc.c b/net/atm/svc.c index 3fa0a9ee98d1..878563a8354d 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -546,7 +546,7 @@ static int svc_addparty(struct socket *sock, struct sockaddr *sockaddr, schedule(); } finish_wait(sk_sleep(sk), &wait); - error = xchg(&sk->sk_err_soft, 0); + error = -xchg(&sk->sk_err_soft, 0); out: release_sock(sk); return error; @@ -573,7 +573,7 @@ static int svc_dropparty(struct socket *sock, int ep_ref) error = -EUNATCH; goto out; } - error = xchg(&sk->sk_err_soft, 0); + error = -xchg(&sk->sk_err_soft, 0); out: release_sock(sk); return error; diff --git a/net/core/hwbm.c b/net/core/hwbm.c index 941c28486896..2cab489ae62e 100644 --- a/net/core/hwbm.c +++ b/net/core/hwbm.c @@ -55,18 +55,21 @@ int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp) spin_lock_irqsave(&bm_pool->lock, flags); if (bm_pool->buf_num == bm_pool->size) { pr_warn("pool already filled\n"); + spin_unlock_irqrestore(&bm_pool->lock, flags); return bm_pool->buf_num; } if (buf_num + bm_pool->buf_num > bm_pool->size) { pr_warn("cannot allocate %d buffers for pool\n", buf_num); + spin_unlock_irqrestore(&bm_pool->lock, flags); return 0; } if ((buf_num + bm_pool->buf_num) < bm_pool->buf_num) { pr_warn("Adding %d buffers to the %d current buffers will overflow\n", buf_num, bm_pool->buf_num); + spin_unlock_irqrestore(&bm_pool->lock, flags); return 0; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 8604ae245960..8b02df0d354d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2245,10 +2245,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) hrtimer_set_expires(&t.timer, spin_until); remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer)); - if (remaining <= 0) { - pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); - return; - } + if (remaining <= 0) + goto out; start_time = ktime_get(); if (remaining < 100000) { @@ -2273,7 +2271,9 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) } pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time)); +out: pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); + destroy_hrtimer_on_stack(&t.timer); } static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index ca207dbf673b..116187b5c267 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -1289,8 +1289,8 @@ ieee802154_llsec_parse_dev_addr(struct nlattr *nla, nl802154_dev_addr_policy)) return -EINVAL; - if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] && - !attrs[NL802154_DEV_ADDR_ATTR_MODE] && + if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || + !attrs[NL802154_DEV_ADDR_ATTR_MODE] || !(attrs[NL802154_DEV_ADDR_ATTR_SHORT] || attrs[NL802154_DEV_ADDR_ATTR_EXTENDED])) return -EINVAL; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 377424ea17a4..d39e9e47a26e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1681,6 +1681,14 @@ static __net_init int inet_init_net(struct net *net) */ net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1); net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0); + + /* Default values for sysctl-controlled parameters. + * We set them here, in case sysctl is not compiled. + */ + net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; + net->ipv4.sysctl_ip_dynaddr = 0; + net->ipv4.sysctl_ip_early_demux = 1; + return 0; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index bb0419582b8d..1cb67de106fe 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -999,10 +999,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!net->ipv4.sysctl_local_reserved_ports) goto err_ports; - net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; - net->ipv4.sysctl_ip_dynaddr = 0; - net->ipv4.sysctl_ip_early_demux = 1; - return 0; err_ports: diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 3f8411328de5..2343e4f2e0bf 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -232,6 +232,15 @@ config IPV6_GRE Saying M here will produce a module called ip6_gre. If unsure, say N. +config IPV6_FOU + tristate + default NET_FOU && IPV6 + +config IPV6_FOU_TUNNEL + tristate + default NET_FOU_IP_TUNNELS && IPV6_FOU + select IPV6_TUNNEL + config IPV6_MULTIPLE_TABLES bool "IPv6: Multiple Routing Tables" select FIB_RULES diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 7ec3129c9ace..6d8ea099213e 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -42,7 +42,7 @@ obj-$(CONFIG_IPV6_VTI) += ip6_vti.o obj-$(CONFIG_IPV6_SIT) += sit.o obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-$(CONFIG_IPV6_GRE) += ip6_gre.o -obj-$(CONFIG_NET_FOU) += fou6.o +obj-$(CONFIG_IPV6_FOU) += fou6.o obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload) diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index c972d0b52579..9ea249b9451e 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -69,7 +69,7 @@ int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, } EXPORT_SYMBOL(gue6_build_header); -#ifdef CONFIG_NET_FOU_IP_TUNNELS +#if IS_ENABLED(CONFIG_IPV6_FOU_TUNNEL) static const struct ip6_tnl_encap_ops fou_ip6tun_ops = { .encap_hlen = fou_encap_hlen, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index af503f518278..f4ac2842d4d9 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -712,6 +712,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) fl6->daddr = p->raddr; fl6->flowi6_oif = p->link; fl6->flowlabel = 0; + fl6->flowi6_proto = IPPROTO_GRE; if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; @@ -1027,6 +1028,8 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; + if (dev->type == ARPHRD_ETHER) + dev->mtu -= ETH_HLEN; if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index c6f5df1bed12..6c54e03fe9c1 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -128,6 +128,7 @@ static inline struct sock *l2tp_ip6_bind_lookup(struct net *net, */ static int l2tp_ip6_recv(struct sk_buff *skb) { + struct net *net = dev_net(skb->dev); struct sock *sk; u32 session_id; u32 tunnel_id; @@ -154,7 +155,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_find(&init_net, NULL, session_id); + session = l2tp_session_find(net, NULL, session_id); if (session == NULL) goto discard; @@ -188,14 +189,14 @@ pass_up: goto discard; tunnel_id = ntohl(*(__be32 *) &skb->data[4]); - tunnel = l2tp_tunnel_find(&init_net, tunnel_id); + tunnel = l2tp_tunnel_find(net, tunnel_id); if (tunnel != NULL) sk = tunnel->sock; else { struct ipv6hdr *iph = ipv6_hdr(skb); read_lock_bh(&l2tp_ip6_lock); - sk = __l2tp_ip6_bind_lookup(&init_net, &iph->daddr, + sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, 0, tunnel_id); read_unlock_bh(&l2tp_ip6_lock); } @@ -263,6 +264,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr; + struct net *net = sock_net(sk); __be32 v4addr = 0; int addr_type; int err; @@ -286,7 +288,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) err = -EADDRINUSE; read_lock_bh(&l2tp_ip6_lock); - if (__l2tp_ip6_bind_lookup(&init_net, &addr->l2tp_addr, + if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, sk->sk_bound_dev_if, addr->l2tp_conn_id)) goto out_in_use; read_unlock_bh(&l2tp_ip6_lock); @@ -456,7 +458,7 @@ static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb) return 0; drop: - IP_INC_STATS(&init_net, IPSTATS_MIB_INDISCARDS); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); return -1; } diff --git a/net/lapb/lapb_in.c b/net/lapb/lapb_in.c index 5dba899131b3..182470847fcf 100644 --- a/net/lapb/lapb_in.c +++ b/net/lapb/lapb_in.c @@ -444,10 +444,9 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, break; case LAPB_FRMR: - lapb_dbg(1, "(%p) S3 RX FRMR(%d) %02X %02X %02X %02X %02X\n", + lapb_dbg(1, "(%p) S3 RX FRMR(%d) %5ph\n", lapb->dev, frame->pf, - skb->data[0], skb->data[1], skb->data[2], - skb->data[3], skb->data[4]); + skb->data); lapb_establish_data_link(lapb); lapb_dbg(0, "(%p) S3 -> S1\n", lapb->dev); lapb_requeue_frames(lapb); diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c index ba4d015bd1a6..482c94d9d958 100644 --- a/net/lapb/lapb_out.c +++ b/net/lapb/lapb_out.c @@ -148,9 +148,7 @@ void lapb_transmit_buffer(struct lapb_cb *lapb, struct sk_buff *skb, int type) } } - lapb_dbg(2, "(%p) S%d TX %02X %02X %02X\n", - lapb->dev, lapb->state, - skb->data[0], skb->data[1], skb->data[2]); + lapb_dbg(2, "(%p) S%d TX %3ph\n", lapb->dev, lapb->state, skb->data); if (!lapb_data_transmit(lapb, skb)) kfree_skb(skb); diff --git a/net/lapb/lapb_subr.c b/net/lapb/lapb_subr.c index 9d0a426eccbb..3c1914df641f 100644 --- a/net/lapb/lapb_subr.c +++ b/net/lapb/lapb_subr.c @@ -113,9 +113,7 @@ int lapb_decode(struct lapb_cb *lapb, struct sk_buff *skb, { frame->type = LAPB_ILLEGAL; - lapb_dbg(2, "(%p) S%d RX %02X %02X %02X\n", - lapb->dev, lapb->state, - skb->data[0], skb->data[1], skb->data[2]); + lapb_dbg(2, "(%p) S%d RX %3ph\n", lapb->dev, lapb->state, skb->data); /* We always need to look at 2 bytes, sometimes we need * to look at 3 and those cases are handled below. @@ -284,10 +282,9 @@ void lapb_transmit_frmr(struct lapb_cb *lapb) dptr++; *dptr++ = lapb->frmr_type; - lapb_dbg(1, "(%p) S%d TX FRMR %02X %02X %02X %02X %02X\n", + lapb_dbg(1, "(%p) S%d TX FRMR %5ph\n", lapb->dev, lapb->state, - skb->data[1], skb->data[2], skb->data[3], - skb->data[4], skb->data[5]); + &skb->data[1]); } else { dptr = skb_put(skb, 4); *dptr++ = LAPB_FRMR; @@ -299,9 +296,8 @@ void lapb_transmit_frmr(struct lapb_cb *lapb) dptr++; *dptr++ = lapb->frmr_type; - lapb_dbg(1, "(%p) S%d TX FRMR %02X %02X %02X\n", - lapb->dev, lapb->state, skb->data[1], - skb->data[2], skb->data[3]); + lapb_dbg(1, "(%p) S%d TX FRMR %3ph\n", + lapb->dev, lapb->state, &skb->data[1]); } lapb_transmit_buffer(lapb, skb, LAPB_RESPONSE); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 879185fe183f..9a3eb7a0ebf4 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -137,11 +137,23 @@ static bool is_flow_key_valid(const struct sw_flow_key *key) return !!key->eth.type; } +static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr, + __be16 ethertype) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) { + __be16 diff[] = { ~(hdr->h_proto), ethertype }; + + skb->csum = ~csum_partial((char *)diff, sizeof(diff), + ~skb->csum); + } + + hdr->h_proto = ethertype; +} + static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_action_push_mpls *mpls) { __be32 *new_mpls_lse; - struct ethhdr *hdr; /* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */ if (skb->encapsulation) @@ -160,9 +172,7 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN); - hdr = eth_hdr(skb); - hdr->h_proto = mpls->mpls_ethertype; - + update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype); if (!skb->inner_protocol) skb_set_inner_protocol(skb, skb->protocol); skb->protocol = mpls->mpls_ethertype; @@ -193,7 +203,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, * field correctly in the presence of VLAN tags. */ hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN); - hdr->h_proto = ethertype; + update_ethertype(skb, hdr, ethertype); if (eth_p_mpls(skb->protocol)) skb->protocol = ethertype; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 330f14e302e8..b884dae692a1 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -239,6 +239,8 @@ override: police->tcfp_t_c = ktime_get_ns(); police->tcf_index = parm->index ? parm->index : tcf_hash_new_index(tn); + police->tcf_tm.install = jiffies; + police->tcf_tm.lastuse = jiffies; h = tcf_hash(police->tcf_index, POL_TAB_MASK); spin_lock_bh(&hinfo->lock); hlist_add_head(&police->tcf_head, &hinfo->htab[h]); @@ -268,6 +270,7 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, spin_lock(&police->tcf_lock); bstats_update(&police->tcf_bstats, skb); + tcf_lastuse_update(&police->tcf_tm); if (police->tcfp_ewma_rate && police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { @@ -327,6 +330,7 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) .refcnt = police->tcf_refcnt - ref, .bindcnt = police->tcf_bindcnt - bind, }; + struct tcf_t t; if (police->rate_present) psched_ratecfg_getrate(&opt.rate, &police->rate); @@ -340,6 +344,13 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) if (police->tcfp_ewma_rate && nla_put_u32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate)) goto nla_put_failure; + + t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(police->tcf_tm.expires); + if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD)) + goto nla_put_failure; + return skb->len; nla_put_failure: diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 64f71a2155f3..ddf047df5361 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -607,6 +607,10 @@ void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool thr if (throttle) qdisc_throttled(wd->qdisc); + if (wd->last_expires == expires) + return; + + wd->last_expires = expires; hrtimer_start(&wd->timer, ns_to_ktime(expires), HRTIMER_MODE_ABS_PINNED); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index f6bf5818ed4d..d4b4218af6b1 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -928,17 +928,10 @@ ok: } } qdisc_qstats_overlimit(sch); - if (likely(next_event > q->now)) { - if (!test_bit(__QDISC_STATE_DEACTIVATED, - &qdisc_root_sleeping(q->watchdog.qdisc)->state)) { - ktime_t time = ns_to_ktime(next_event); - qdisc_throttled(q->watchdog.qdisc); - hrtimer_start(&q->watchdog.timer, time, - HRTIMER_MODE_ABS_PINNED); - } - } else { + if (likely(next_event > q->now)) + qdisc_watchdog_schedule_ns(&q->watchdog, next_event, true); + else schedule_work(&q->work); - } fin: return skb; } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index 8e3e769dc9ea..1ce724b87618 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -356,6 +356,9 @@ static int sctp_ep_dump(struct sctp_endpoint *ep, void *p) if (cb->args[4] < cb->args[1]) goto next; + if ((r->idiag_states & ~TCPF_LISTEN) && !list_empty(&ep->asocs)) + goto next; + if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 777d0324594a..67154b848aa9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4220,6 +4220,7 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, info->sctpi_s_disable_fragments = sp->disable_fragments; info->sctpi_s_v4mapped = sp->v4mapped; info->sctpi_s_frag_interleave = sp->frag_interleave; + info->sctpi_s_type = sp->type; return 0; } diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 4dfc5c14f8c3..f795b1dd0ccd 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -346,9 +346,15 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg, struct nlattr **attrs) { struct nlattr *bearer[TIPC_NLA_BEARER_MAX + 1]; + int err; + + if (!attrs[TIPC_NLA_BEARER]) + return -EINVAL; - nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX, attrs[TIPC_NLA_BEARER], - NULL); + err = nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX, + attrs[TIPC_NLA_BEARER], NULL); + if (err) + return err; return tipc_add_tlv(msg->rep, TIPC_TLV_BEARER_NAME, nla_data(bearer[TIPC_NLA_BEARER_NAME]), @@ -460,14 +466,31 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, struct nlattr *link[TIPC_NLA_LINK_MAX + 1]; struct nlattr *prop[TIPC_NLA_PROP_MAX + 1]; struct nlattr *stats[TIPC_NLA_STATS_MAX + 1]; + int err; - nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL); + if (!attrs[TIPC_NLA_LINK]) + return -EINVAL; - nla_parse_nested(prop, TIPC_NLA_PROP_MAX, link[TIPC_NLA_LINK_PROP], - NULL); + err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], + NULL); + if (err) + return err; + + if (!link[TIPC_NLA_LINK_PROP]) + return -EINVAL; - nla_parse_nested(stats, TIPC_NLA_STATS_MAX, link[TIPC_NLA_LINK_STATS], - NULL); + err = nla_parse_nested(prop, TIPC_NLA_PROP_MAX, + link[TIPC_NLA_LINK_PROP], NULL); + if (err) + return err; + + if (!link[TIPC_NLA_LINK_STATS]) + return -EINVAL; + + err = nla_parse_nested(stats, TIPC_NLA_STATS_MAX, + link[TIPC_NLA_LINK_STATS], NULL); + if (err) + return err; name = (char *)TLV_DATA(msg->req); if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0) @@ -569,8 +592,15 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg, { struct nlattr *link[TIPC_NLA_LINK_MAX + 1]; struct tipc_link_info link_info; + int err; - nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL); + if (!attrs[TIPC_NLA_LINK]) + return -EINVAL; + + err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], + NULL); + if (err) + return err; link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]); link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP])); @@ -758,12 +788,23 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg, u32 node, depth, type, lowbound, upbound; static const char * const scope_str[] = {"", " zone", " cluster", " node"}; + int err; - nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX, - attrs[TIPC_NLA_NAME_TABLE], NULL); + if (!attrs[TIPC_NLA_NAME_TABLE]) + return -EINVAL; - nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, nt[TIPC_NLA_NAME_TABLE_PUBL], - NULL); + err = nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX, + attrs[TIPC_NLA_NAME_TABLE], NULL); + if (err) + return err; + + if (!nt[TIPC_NLA_NAME_TABLE_PUBL]) + return -EINVAL; + + err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, + nt[TIPC_NLA_NAME_TABLE_PUBL], NULL); + if (err) + return err; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); @@ -815,8 +856,15 @@ static int __tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, { u32 type, lower, upper; struct nlattr *publ[TIPC_NLA_PUBL_MAX + 1]; + int err; - nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL], NULL); + if (!attrs[TIPC_NLA_PUBL]) + return -EINVAL; + + err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL], + NULL); + if (err) + return err; type = nla_get_u32(publ[TIPC_NLA_PUBL_TYPE]); lower = nla_get_u32(publ[TIPC_NLA_PUBL_LOWER]); @@ -876,7 +924,13 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg, u32 sock_ref; struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1]; - nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK], NULL); + if (!attrs[TIPC_NLA_SOCK]) + return -EINVAL; + + err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK], + NULL); + if (err) + return err; sock_ref = nla_get_u32(sock[TIPC_NLA_SOCK_REF]); tipc_tlv_sprintf(msg->rep, "%u:", sock_ref); @@ -917,9 +971,15 @@ static int tipc_nl_compat_media_dump(struct tipc_nl_compat_msg *msg, struct nlattr **attrs) { struct nlattr *media[TIPC_NLA_MEDIA_MAX + 1]; + int err; + + if (!attrs[TIPC_NLA_MEDIA]) + return -EINVAL; - nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, attrs[TIPC_NLA_MEDIA], - NULL); + err = nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, attrs[TIPC_NLA_MEDIA], + NULL); + if (err) + return err; return tipc_add_tlv(msg->rep, TIPC_TLV_MEDIA_NAME, nla_data(media[TIPC_NLA_MEDIA_NAME]), @@ -931,8 +991,15 @@ static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg, { struct tipc_node_info node_info; struct nlattr *node[TIPC_NLA_NODE_MAX + 1]; + int err; - nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE], NULL); + if (!attrs[TIPC_NLA_NODE]) + return -EINVAL; + + err = nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE], + NULL); + if (err) + return err; node_info.addr = htonl(nla_get_u32(node[TIPC_NLA_NODE_ADDR])); node_info.up = htonl(nla_get_flag(node[TIPC_NLA_NODE_UP])); @@ -971,8 +1038,16 @@ static int tipc_nl_compat_net_dump(struct tipc_nl_compat_msg *msg, { __be32 id; struct nlattr *net[TIPC_NLA_NET_MAX + 1]; + int err; + + if (!attrs[TIPC_NLA_NET]) + return -EINVAL; + + err = nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET], + NULL); + if (err) + return err; - nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET], NULL); id = htonl(nla_get_u32(net[TIPC_NLA_NET_ID])); return tipc_add_tlv(msg->rep, TIPC_TLV_UNSIGNED, &id, sizeof(id)); diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c index a3f12b3b277b..3a3a699b7489 100644 --- a/virt/kvm/arm/hyp/vgic-v2-sr.c +++ b/virt/kvm/arm/hyp/vgic-v2-sr.c @@ -100,12 +100,11 @@ static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base) if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i))) continue; - if (cpu_if->vgic_elrsr & (1UL << i)) { + if (cpu_if->vgic_elrsr & (1UL << i)) cpu_if->vgic_lr[i] &= ~GICH_LR_STATE; - continue; - } + else + cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4)); - cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4)); writel_relaxed(0, base + GICH_LR0 + (i * 4)); } } diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 059595ec3da0..9f6fab74dce7 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -191,10 +191,8 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, * other thread sync back the IRQ. */ while (irq->vcpu && /* IRQ may have state in an LR somewhere */ - irq->vcpu->cpu != -1) { /* VCPU thread is running */ - BUG_ON(irq->intid < VGIC_NR_PRIVATE_IRQS); + irq->vcpu->cpu != -1) /* VCPU thread is running */ cond_resched_lock(&irq->irq_lock); - } irq->active = new_active_state; if (new_active_state) diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 8ad42c217770..e31405ee5515 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -112,11 +112,15 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) } } - /* Clear soft pending state when level IRQs have been acked */ - if (irq->config == VGIC_CONFIG_LEVEL && - !(val & GICH_LR_PENDING_BIT)) { - irq->soft_pending = false; - irq->pending = irq->line_level; + /* + * Clear soft pending state when level irqs have been acked. + * Always regenerate the pending state. + */ + if (irq->config == VGIC_CONFIG_LEVEL) { + if (!(val & GICH_LR_PENDING_BIT)) + irq->soft_pending = false; + + irq->pending = irq->line_level || irq->soft_pending; } spin_unlock(&irq->irq_lock); diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 336a46115937..346b4ad12b49 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -101,11 +101,15 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) } } - /* Clear soft pending state when level irqs have been acked */ - if (irq->config == VGIC_CONFIG_LEVEL && - !(val & ICH_LR_PENDING_BIT)) { - irq->soft_pending = false; - irq->pending = irq->line_level; + /* + * Clear soft pending state when level irqs have been acked. + * Always regenerate the pending state. + */ + if (irq->config == VGIC_CONFIG_LEVEL) { + if (!(val & ICH_LR_PENDING_BIT)) + irq->soft_pending = false; + + irq->pending = irq->line_level || irq->soft_pending; } spin_unlock(&irq->irq_lock); diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index fe84e1a95dd5..8db197bb6c7a 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -40,7 +40,7 @@ int kvm_irq_map_gsi(struct kvm *kvm, irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu, lockdep_is_held(&kvm->irq_lock)); - if (gsi < irq_rt->nr_rt_entries) { + if (irq_rt && gsi < irq_rt->nr_rt_entries) { hlist_for_each_entry(e, &irq_rt->map[gsi], link) { entries[n] = *e; ++n; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 37af23052470..02e98f3131bd 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2935,7 +2935,7 @@ static long kvm_vm_ioctl(struct file *filp, case KVM_SET_GSI_ROUTING: { struct kvm_irq_routing routing; struct kvm_irq_routing __user *urouting; - struct kvm_irq_routing_entry *entries; + struct kvm_irq_routing_entry *entries = NULL; r = -EFAULT; if (copy_from_user(&routing, argp, sizeof(routing))) @@ -2945,15 +2945,17 @@ static long kvm_vm_ioctl(struct file *filp, goto out; if (routing.flags) goto out; - r = -ENOMEM; - entries = vmalloc(routing.nr * sizeof(*entries)); - if (!entries) - goto out; - r = -EFAULT; - urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; + if (routing.nr) { + r = -ENOMEM; + entries = vmalloc(routing.nr * sizeof(*entries)); + if (!entries) + goto out; + r = -EFAULT; + urouting = argp; + if (copy_from_user(entries, urouting->entries, + routing.nr * sizeof(*entries))) + goto out_free_irq_routing; + } r = kvm_set_irq_routing(kvm, entries, routing.nr, routing.flags); out_free_irq_routing: |