diff options
121 files changed, 2082 insertions, 1192 deletions
diff --git a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt index b7fa3b97986d..a339dbb15493 100644 --- a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt +++ b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt @@ -44,13 +44,19 @@ Hip05 Example (note that Hip06 is the same except compatible): }; HiSilicon Hip06/Hip07 PCIe host bridge DT (almost-ECAM) description. + +Some BIOSes place the host controller in a mode where it is ECAM +compliant for all devices other than the root complex. In such cases, +the host controller should be described as below. + The properties and their meanings are identical to those described in host-generic-pci.txt except as listed below. Properties of the host controller node that differ from host-generic-pci.txt: -- compatible : Must be "hisilicon,pcie-almost-ecam" +- compatible : Must be "hisilicon,hip06-pcie-ecam", or + "hisilicon,hip07-pcie-ecam" - reg : Two entries: First the ECAM configuration space for any other bus underneath the root bus. Second, the base @@ -59,7 +65,7 @@ host-generic-pci.txt: Example: pcie0: pcie@a0090000 { - compatible = "hisilicon,pcie-almost-ecam"; + compatible = "hisilicon,hip06-pcie-ecam"; reg = <0 0xb0000000 0 0x2000000>, /* ECAM configuration space */ <0 0xa0090000 0 0x10000>; /* host bridge registers */ bus-range = <0 31>; diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt index 723e1ad937da..940707d095cc 100644 --- a/Documentation/devicetree/bindings/power/power_domain.txt +++ b/Documentation/devicetree/bindings/power/power_domain.txt @@ -31,7 +31,9 @@ Optional properties: - domain-idle-states : A phandle of an idle-state that shall be soaked into a generic domain power state. The idle state definitions are - compatible with domain-idle-state specified in [1]. + compatible with domain-idle-state specified in [1]. phandles + that are not compatible with domain-idle-state will be + ignored. The domain-idle-state property reflects the idle state of this PM domain and not the idle states of the devices or sub-domains in the PM domain. Devices and sub-domains have their own idle-states independent of the parent diff --git a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt index d23dc002a87e..d3a5a93a65cd 100644 --- a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt +++ b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt @@ -33,6 +33,7 @@ Required properties: - compatible: should be one of: - "rockchip,rk3188-io-voltage-domain" for rk3188 - "rockchip,rk3288-io-voltage-domain" for rk3288 + - "rockchip,rk3328-io-voltage-domain" for rk3328 - "rockchip,rk3368-io-voltage-domain" for rk3368 - "rockchip,rk3368-pmu-io-voltage-domain" for rk3368 pmu-domains - "rockchip,rk3399-io-voltage-domain" for rk3399 diff --git a/MAINTAINERS b/MAINTAINERS index 676c139bc883..56a92ec7d3f7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2585,12 +2585,26 @@ F: include/uapi/linux/if_bonding.h BPF (Safe dynamic programs and tools) M: Alexei Starovoitov <ast@kernel.org> +M: Daniel Borkmann <daniel@iogearbox.net> L: netdev@vger.kernel.org L: linux-kernel@vger.kernel.org S: Supported +F: arch/x86/net/bpf_jit* +F: Documentation/networking/filter.txt +F: include/linux/bpf* +F: include/linux/filter.h +F: include/uapi/linux/bpf* +F: include/uapi/linux/filter.h F: kernel/bpf/ -F: tools/testing/selftests/bpf/ +F: kernel/trace/bpf_trace.c F: lib/test_bpf.c +F: net/bpf/ +F: net/core/filter.c +F: net/sched/act_bpf.c +F: net/sched/cls_bpf.c +F: samples/bpf/ +F: tools/net/bpf* +F: tools/testing/selftests/bpf/ BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> @@ -3449,6 +3463,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git T: git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates) B: https://bugzilla.kernel.org F: Documentation/cpu-freq/ +F: Documentation/devicetree/bindings/cpufreq/ F: drivers/cpufreq/ F: include/linux/cpufreq.h F: tools/testing/selftests/cpufreq/ @@ -8761,6 +8776,7 @@ W: http://www.linuxfoundation.org/en/Net 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 +B: mailto:netdev@vger.kernel.org S: Maintained F: net/ F: include/net/ @@ -12464,7 +12480,6 @@ F: drivers/clk/ti/ F: include/linux/clk/ti.h TI ETHERNET SWITCH DRIVER (CPSW) -M: Mugunthan V N <mugunthanvnm@ti.com> R: Grygorii Strashko <grygorii.strashko@ti.com> L: linux-omap@vger.kernel.org L: netdev@vger.kernel.org @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 11 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index 162e1eb5373d..6c5affe2d0f5 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -1189,11 +1189,6 @@ status = "disabled"; }; - cpufreq-cooling { - compatible = "stericsson,db8500-cpufreq-cooling"; - status = "disabled"; - }; - mcde@a0350000 { compatible = "stericsson,mcde"; reg = <0xa0350000 0x1000>, /* MCDE */ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 8442727f28d2..cbd4f4af8108 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -39,10 +39,10 @@ #define get_user __get_user #if !defined(CONFIG_64BIT) -#define LDD_USER(ptr) __get_user_asm64(ptr) +#define LDD_USER(val, ptr) __get_user_asm64(val, ptr) #define STD_USER(x, ptr) __put_user_asm64(x, ptr) #else -#define LDD_USER(ptr) __get_user_asm("ldd", ptr) +#define LDD_USER(val, ptr) __get_user_asm(val, "ldd", ptr) #define STD_USER(x, ptr) __put_user_asm("std", x, ptr) #endif @@ -97,63 +97,87 @@ struct exception_data { " mtsp %0,%%sr2\n\t" \ : : "r"(get_fs()) : ) -#define __get_user(x, ptr) \ -({ \ - register long __gu_err __asm__ ("r8") = 0; \ - register long __gu_val; \ - \ - load_sr2(); \ - switch (sizeof(*(ptr))) { \ - case 1: __get_user_asm("ldb", ptr); break; \ - case 2: __get_user_asm("ldh", ptr); break; \ - case 4: __get_user_asm("ldw", ptr); break; \ - case 8: LDD_USER(ptr); break; \ - default: BUILD_BUG(); break; \ - } \ - \ - (x) = (__force __typeof__(*(ptr))) __gu_val; \ - __gu_err; \ +#define __get_user_internal(val, ptr) \ +({ \ + register long __gu_err __asm__ ("r8") = 0; \ + \ + switch (sizeof(*(ptr))) { \ + case 1: __get_user_asm(val, "ldb", ptr); break; \ + case 2: __get_user_asm(val, "ldh", ptr); break; \ + case 4: __get_user_asm(val, "ldw", ptr); break; \ + case 8: LDD_USER(val, ptr); break; \ + default: BUILD_BUG(); \ + } \ + \ + __gu_err; \ }) -#define __get_user_asm(ldx, ptr) \ +#define __get_user(val, ptr) \ +({ \ + load_sr2(); \ + __get_user_internal(val, ptr); \ +}) + +#define __get_user_asm(val, ldx, ptr) \ +{ \ + register long __gu_val; \ + \ __asm__("1: " ldx " 0(%%sr2,%2),%0\n" \ "9:\n" \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ : "=r"(__gu_val), "=r"(__gu_err) \ - : "r"(ptr), "1"(__gu_err)); + : "r"(ptr), "1"(__gu_err)); \ + \ + (val) = (__force __typeof__(*(ptr))) __gu_val; \ +} #if !defined(CONFIG_64BIT) -#define __get_user_asm64(ptr) \ +#define __get_user_asm64(val, ptr) \ +{ \ + union { \ + unsigned long long l; \ + __typeof__(*(ptr)) t; \ + } __gu_tmp; \ + \ __asm__(" copy %%r0,%R0\n" \ "1: ldw 0(%%sr2,%2),%0\n" \ "2: ldw 4(%%sr2,%2),%R0\n" \ "9:\n" \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ - : "=r"(__gu_val), "=r"(__gu_err) \ - : "r"(ptr), "1"(__gu_err)); + : "=&r"(__gu_tmp.l), "=r"(__gu_err) \ + : "r"(ptr), "1"(__gu_err)); \ + \ + (val) = __gu_tmp.t; \ +} #endif /* !defined(CONFIG_64BIT) */ -#define __put_user(x, ptr) \ +#define __put_user_internal(x, ptr) \ ({ \ register long __pu_err __asm__ ("r8") = 0; \ __typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x); \ \ - load_sr2(); \ switch (sizeof(*(ptr))) { \ - case 1: __put_user_asm("stb", __x, ptr); break; \ - case 2: __put_user_asm("sth", __x, ptr); break; \ - case 4: __put_user_asm("stw", __x, ptr); break; \ - case 8: STD_USER(__x, ptr); break; \ - default: BUILD_BUG(); break; \ - } \ + case 1: __put_user_asm("stb", __x, ptr); break; \ + case 2: __put_user_asm("sth", __x, ptr); break; \ + case 4: __put_user_asm("stw", __x, ptr); break; \ + case 8: STD_USER(__x, ptr); break; \ + default: BUILD_BUG(); \ + } \ \ __pu_err; \ }) +#define __put_user(x, ptr) \ +({ \ + load_sr2(); \ + __put_user_internal(x, ptr); \ +}) + + /* * The "__put_user/kernel_asm()" macros tell gcc they read from memory * instead of writing. This is because they do not write to any memory diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 14752eee3d0c..ed3beadd2cc5 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -236,9 +236,9 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtctr reg; \ bctr -#define BRANCH_LINK_TO_FAR(reg, label) \ - __LOAD_FAR_HANDLER(reg, label); \ - mtctr reg; \ +#define BRANCH_LINK_TO_FAR(label) \ + __LOAD_FAR_HANDLER(r12, label); \ + mtctr r12; \ bctrl /* @@ -265,7 +265,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define BRANCH_TO_COMMON(reg, label) \ b label -#define BRANCH_LINK_TO_FAR(reg, label) \ +#define BRANCH_LINK_TO_FAR(label) \ bl label #define BRANCH_TO_KVM(reg, label) \ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 6432d4bf08c8..767ef6d68c9e 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -689,7 +689,7 @@ resume_kernel: addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ - lwz r3,GPR1(r1) + ld r3,GPR1(r1) subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */ mr r4,r1 /* src: current exception frame */ mr r1,r3 /* Reroute the trampoline frame to r1 */ @@ -703,8 +703,8 @@ resume_kernel: addi r6,r6,8 bdnz 2b - /* Do real store operation to complete stwu */ - lwz r5,GPR1(r1) + /* Do real store operation to complete stdu */ + ld r5,GPR1(r1) std r8,0(r5) /* Clear _TIF_EMULATE_STACK_STORE flag */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 857bf7c5b946..6353019966e6 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -982,7 +982,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early) EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) EXCEPTION_PROLOG_COMMON_3(0xe60) addi r3,r1,STACK_FRAME_OVERHEAD - BRANCH_LINK_TO_FAR(r4, hmi_exception_realmode) + BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */ /* Windup the stack. */ /* Move original HSRR0 and HSRR1 into the respective regs */ ld r9,_MSR(r1) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 93e37b12e882..ecec682bb516 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1051,6 +1051,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, { if (!MACHINE_HAS_NX) pte_val(entry) &= ~_PAGE_NOEXEC; + if (pte_present(entry)) + pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) ptep_set_pte_at(mm, addr, ptep, entry); else diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 68ac5c7cd982..a59deaef21e5 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -43,7 +43,7 @@ config SPARC select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select HAVE_ARCH_HARDENED_USERCOPY - select PROVE_LOCKING_SMALL if PROVE_LOCKING + select LOCKDEP_SMALL if LOCKDEP select ARCH_WANT_RELAX_ORDER config SPARC32 diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index ee5273ad918d..7c29d38e6b99 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -461,6 +461,22 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, pgd_t *pgd; unsigned long next; + addr &= PMD_MASK; + if (addr < floor) { + addr += PMD_SIZE; + if (!addr) + return; + } + if (ceiling) { + ceiling &= PMD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + end -= PMD_SIZE; + if (addr > end - 1) + return; + pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 1e5a50c11d3c..217cd4449bc9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -85,7 +85,7 @@ void mce_gen_pool_process(struct work_struct *__unused) head = llist_reverse_order(head); llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->mce; - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 903043e6a62b..19592ba1a320 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -13,7 +13,7 @@ enum severity_level { MCE_PANIC_SEVERITY, }; -extern struct atomic_notifier_head x86_mce_decoder_chain; +extern struct blocking_notifier_head x86_mce_decoder_chain; #define ATTR_LEN 16 #define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5accfbdee3f0..af44ebeb593f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -123,7 +123,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. */ -ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ void mce_setup(struct mce *m) @@ -220,7 +220,7 @@ void mce_register_decode_chain(struct notifier_block *nb) WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); - atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); @@ -228,7 +228,7 @@ void mce_unregister_decode_chain(struct notifier_block *nb) { atomic_dec(&num_notifiers); - atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); @@ -321,18 +321,7 @@ static void __print_mce(struct mce *m) static void print_mce(struct mce *m) { - int ret = 0; - __print_mce(m); - - /* - * Print out human-readable details about the MCE error, - * (if the CPU has an implementation for that) - */ - ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); - if (ret == NOTIFY_STOP) - return; - pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 572966f49596..c7836a1ded97 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2928,8 +2928,17 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie) hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; if (!blk_qc_t_is_internal(cookie)) rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie)); - else + else { rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie)); + /* + * With scheduling, if the request has completed, we'll + * get a NULL return here, as we clear the sched tag when + * that happens. The request still remains valid, like always, + * so we should be safe with just the NULL check. + */ + if (!rq) + return false; + } return __blk_mq_poll(hctx, rq); } diff --git a/block/elevator.c b/block/elevator.c index dbeecf7be719..4d9084a14c10 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -1098,12 +1098,20 @@ int elevator_change(struct request_queue *q, const char *name) } EXPORT_SYMBOL(elevator_change); +static inline bool elv_support_iosched(struct request_queue *q) +{ + if (q->mq_ops && q->tag_set && (q->tag_set->flags & + BLK_MQ_F_NO_SCHED)) + return false; + return true; +} + ssize_t elv_iosched_store(struct request_queue *q, const char *name, size_t count) { int ret; - if (!(q->mq_ops || q->request_fn)) + if (!(q->mq_ops || q->request_fn) || !elv_support_iosched(q)) return count; ret = __elevator_change(q, name); @@ -1135,7 +1143,7 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) len += sprintf(name+len, "[%s] ", elv->elevator_name); continue; } - if (__e->uses_mq && q->mq_ops) + if (__e->uses_mq && q->mq_ops && elv_support_iosched(q)) len += sprintf(name+len, "%s ", __e->elevator_name); else if (!__e->uses_mq && !q->mq_ops) len += sprintf(name+len, "%s ", __e->elevator_name); diff --git a/crypto/ahash.c b/crypto/ahash.c index e58c4970c22b..826cd7ab4d4a 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -32,6 +32,7 @@ struct ahash_request_priv { crypto_completion_t complete; void *data; u8 *result; + u32 flags; void *ubuf[] CRYPTO_MINALIGN_ATTR; }; @@ -253,6 +254,8 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt) priv->result = req->result; priv->complete = req->base.complete; priv->data = req->base.data; + priv->flags = req->base.flags; + /* * WARNING: We do not backup req->priv here! The req->priv * is for internal use of the Crypto API and the @@ -267,38 +270,44 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt) return 0; } -static void ahash_restore_req(struct ahash_request *req) +static void ahash_restore_req(struct ahash_request *req, int err) { struct ahash_request_priv *priv = req->priv; + if (!err) + memcpy(priv->result, req->result, + crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); + /* Restore the original crypto request. */ req->result = priv->result; - req->base.complete = priv->complete; - req->base.data = priv->data; + + ahash_request_set_callback(req, priv->flags, + priv->complete, priv->data); req->priv = NULL; /* Free the req->priv.priv from the ADJUSTED request. */ kzfree(priv); } -static void ahash_op_unaligned_finish(struct ahash_request *req, int err) +static void ahash_notify_einprogress(struct ahash_request *req) { struct ahash_request_priv *priv = req->priv; + struct crypto_async_request oreq; - if (err == -EINPROGRESS) - return; - - if (!err) - memcpy(priv->result, req->result, - crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); + oreq.data = priv->data; - ahash_restore_req(req); + priv->complete(&oreq, -EINPROGRESS); } static void ahash_op_unaligned_done(struct crypto_async_request *req, int err) { struct ahash_request *areq = req->data; + if (err == -EINPROGRESS) { + ahash_notify_einprogress(areq); + return; + } + /* * Restore the original request, see ahash_op_unaligned() for what * goes where. @@ -309,7 +318,7 @@ static void ahash_op_unaligned_done(struct crypto_async_request *req, int err) */ /* First copy req->result into req->priv.result */ - ahash_op_unaligned_finish(areq, err); + ahash_restore_req(areq, err); /* Complete the ORIGINAL request. */ areq->base.complete(&areq->base, err); @@ -325,7 +334,12 @@ static int ahash_op_unaligned(struct ahash_request *req, return err; err = op(req); - ahash_op_unaligned_finish(req, err); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; + + ahash_restore_req(req, err); return err; } @@ -360,25 +374,14 @@ int crypto_ahash_digest(struct ahash_request *req) } EXPORT_SYMBOL_GPL(crypto_ahash_digest); -static void ahash_def_finup_finish2(struct ahash_request *req, int err) +static void ahash_def_finup_done2(struct crypto_async_request *req, int err) { - struct ahash_request_priv *priv = req->priv; + struct ahash_request *areq = req->data; if (err == -EINPROGRESS) return; - if (!err) - memcpy(priv->result, req->result, - crypto_ahash_digestsize(crypto_ahash_reqtfm(req))); - - ahash_restore_req(req); -} - -static void ahash_def_finup_done2(struct crypto_async_request *req, int err) -{ - struct ahash_request *areq = req->data; - - ahash_def_finup_finish2(areq, err); + ahash_restore_req(areq, err); areq->base.complete(&areq->base, err); } @@ -389,11 +392,15 @@ static int ahash_def_finup_finish1(struct ahash_request *req, int err) goto out; req->base.complete = ahash_def_finup_done2; - req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + err = crypto_ahash_reqtfm(req)->final(req); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; out: - ahash_def_finup_finish2(req, err); + ahash_restore_req(req, err); return err; } @@ -401,7 +408,16 @@ static void ahash_def_finup_done1(struct crypto_async_request *req, int err) { struct ahash_request *areq = req->data; + if (err == -EINPROGRESS) { + ahash_notify_einprogress(areq); + return; + } + + areq->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + err = ahash_def_finup_finish1(areq, err); + if (areq->priv) + return; areq->base.complete(&areq->base, err); } @@ -416,6 +432,11 @@ static int ahash_def_finup(struct ahash_request *req) return err; err = tfm->update(req); + if (err == -EINPROGRESS || + (err == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) + return err; + return ahash_def_finup_finish1(req, err); } diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 5a8053758657..ef59d9926ee9 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -40,6 +40,7 @@ struct aead_async_req { struct aead_async_rsgl first_rsgl; struct list_head list; struct kiocb *iocb; + struct sock *sk; unsigned int tsgls; char iv[]; }; @@ -379,12 +380,10 @@ unlock: static void aead_async_cb(struct crypto_async_request *_req, int err) { - struct sock *sk = _req->data; - struct alg_sock *ask = alg_sk(sk); - struct aead_ctx *ctx = ask->private; - struct crypto_aead *tfm = crypto_aead_reqtfm(&ctx->aead_req); - struct aead_request *req = aead_request_cast(_req); + struct aead_request *req = _req->data; + struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aead_async_req *areq = GET_ASYM_REQ(req, tfm); + struct sock *sk = areq->sk; struct scatterlist *sg = areq->tsgl; struct aead_async_rsgl *rsgl; struct kiocb *iocb = areq->iocb; @@ -447,11 +446,12 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, memset(&areq->first_rsgl, '\0', sizeof(areq->first_rsgl)); INIT_LIST_HEAD(&areq->list); areq->iocb = msg->msg_iocb; + areq->sk = sk; memcpy(areq->iv, ctx->iv, crypto_aead_ivsize(tfm)); aead_request_set_tfm(req, tfm); aead_request_set_ad(req, ctx->aead_assoclen); aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - aead_async_cb, sk); + aead_async_cb, req); used -= ctx->aead_assoclen; /* take over all tx sgls from ctx */ diff --git a/crypto/lrw.c b/crypto/lrw.c index 3ea095adafd9..a8bfae4451bf 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -345,6 +345,13 @@ static void encrypt_done(struct crypto_async_request *areq, int err) struct rctx *rctx; rctx = skcipher_request_ctx(req); + + if (err == -EINPROGRESS) { + if (rctx->left != req->cryptlen) + return; + goto out; + } + subreq = &rctx->subreq; subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; @@ -352,6 +359,7 @@ static void encrypt_done(struct crypto_async_request *areq, int err) if (rctx->left) return; +out: skcipher_request_complete(req, err); } @@ -389,6 +397,13 @@ static void decrypt_done(struct crypto_async_request *areq, int err) struct rctx *rctx; rctx = skcipher_request_ctx(req); + + if (err == -EINPROGRESS) { + if (rctx->left != req->cryptlen) + return; + goto out; + } + subreq = &rctx->subreq; subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; @@ -396,6 +411,7 @@ static void decrypt_done(struct crypto_async_request *areq, int err) if (rctx->left) return; +out: skcipher_request_complete(req, err); } diff --git a/crypto/xts.c b/crypto/xts.c index c976bfac29da..89ace5ebc2da 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -286,6 +286,13 @@ static void encrypt_done(struct crypto_async_request *areq, int err) struct rctx *rctx; rctx = skcipher_request_ctx(req); + + if (err == -EINPROGRESS) { + if (rctx->left != req->cryptlen) + return; + goto out; + } + subreq = &rctx->subreq; subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; @@ -293,6 +300,7 @@ static void encrypt_done(struct crypto_async_request *areq, int err) if (rctx->left) return; +out: skcipher_request_complete(req, err); } @@ -330,6 +338,13 @@ static void decrypt_done(struct crypto_async_request *areq, int err) struct rctx *rctx; rctx = skcipher_request_ctx(req); + + if (err == -EINPROGRESS) { + if (rctx->left != req->cryptlen) + return; + goto out; + } + subreq = &rctx->subreq; subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; @@ -337,6 +352,7 @@ static void decrypt_done(struct crypto_async_request *areq, int err) if (rctx->left) return; +out: skcipher_request_complete(req, err); } diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index fcd4ce6f78d5..1c2b846c5776 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -200,6 +200,7 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) return -EINVAL; /* The state of the list is 'on' IFF all resources are 'on'. */ + cur_state = 0; list_for_each_entry(entry, list, node) { struct acpi_power_resource *resource = entry->resource; acpi_handle handle = resource->device.handle; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index e697dec9d25b..ad196427b4f2 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -121,7 +121,9 @@ static const struct genpd_lock_ops genpd_spin_ops = { #define genpd_lock_interruptible(p) p->lock_ops->lock_interruptible(p) #define genpd_unlock(p) p->lock_ops->unlock(p) +#define genpd_status_on(genpd) (genpd->status == GPD_STATE_ACTIVE) #define genpd_is_irq_safe(genpd) (genpd->flags & GENPD_FLAG_IRQ_SAFE) +#define genpd_is_always_on(genpd) (genpd->flags & GENPD_FLAG_ALWAYS_ON) static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, struct generic_pm_domain *genpd) @@ -130,8 +132,12 @@ static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd); - /* Warn once if IRQ safe dev in no sleep domain */ - if (ret) + /* + * Warn once if an IRQ safe device is attached to a no sleep domain, as + * to indicate a suboptimal configuration for PM. For an always on + * domain this isn't case, thus don't warn. + */ + if (ret && !genpd_is_always_on(genpd)) dev_warn_once(dev, "PM domain %s will not be powered off\n", genpd->name); @@ -296,11 +302,15 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, * (1) The domain is already in the "power off" state. * (2) System suspend is in progress. */ - if (genpd->status == GPD_STATE_POWER_OFF - || genpd->prepared_count > 0) + if (!genpd_status_on(genpd) || genpd->prepared_count > 0) return 0; - if (atomic_read(&genpd->sd_count) > 0) + /* + * Abort power off for the PM domain in the following situations: + * (1) The domain is configured as always on. + * (2) When the domain has a subdomain being powered on. + */ + if (genpd_is_always_on(genpd) || atomic_read(&genpd->sd_count) > 0) return -EBUSY; list_for_each_entry(pdd, &genpd->dev_list, list_node) { @@ -373,7 +383,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth) struct gpd_link *link; int ret = 0; - if (genpd->status == GPD_STATE_ACTIVE) + if (genpd_status_on(genpd)) return 0; /* @@ -752,7 +762,7 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock, { struct gpd_link *link; - if (genpd->status == GPD_STATE_POWER_OFF) + if (!genpd_status_on(genpd) || genpd_is_always_on(genpd)) return; if (genpd->suspended_count != genpd->device_count @@ -761,7 +771,8 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock, /* Choose the deepest state when suspending */ genpd->state_idx = genpd->state_count - 1; - _genpd_power_off(genpd, false); + if (_genpd_power_off(genpd, false)) + return; genpd->status = GPD_STATE_POWER_OFF; @@ -793,7 +804,7 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock, { struct gpd_link *link; - if (genpd->status == GPD_STATE_ACTIVE) + if (genpd_status_on(genpd)) return; list_for_each_entry(link, &genpd->slave_links, slave_node) { @@ -1329,8 +1340,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd, genpd_lock(subdomain); genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING); - if (genpd->status == GPD_STATE_POWER_OFF - && subdomain->status != GPD_STATE_POWER_OFF) { + if (!genpd_status_on(genpd) && genpd_status_on(subdomain)) { ret = -EINVAL; goto out; } @@ -1346,7 +1356,7 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd, list_add_tail(&link->master_node, &genpd->master_links); link->slave = subdomain; list_add_tail(&link->slave_node, &subdomain->slave_links); - if (subdomain->status != GPD_STATE_POWER_OFF) + if (genpd_status_on(subdomain)) genpd_sd_counter_inc(genpd); out: @@ -1406,7 +1416,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, list_del(&link->master_node); list_del(&link->slave_node); kfree(link); - if (subdomain->status != GPD_STATE_POWER_OFF) + if (genpd_status_on(subdomain)) genpd_sd_counter_dec(genpd); ret = 0; @@ -1492,6 +1502,10 @@ int pm_genpd_init(struct generic_pm_domain *genpd, genpd->dev_ops.start = pm_clk_resume; } + /* Always-on domains must be powered on at initialization. */ + if (genpd_is_always_on(genpd) && !genpd_status_on(genpd)) + return -EINVAL; + /* Use only one "off" state if there were no states declared */ if (genpd->state_count == 0) { ret = genpd_set_default_power_state(genpd); @@ -1700,12 +1714,12 @@ int of_genpd_add_provider_simple(struct device_node *np, mutex_lock(&gpd_list_lock); - if (pm_genpd_present(genpd)) + if (pm_genpd_present(genpd)) { ret = genpd_add_provider(np, genpd_xlate_simple, genpd); - - if (!ret) { - genpd->provider = &np->fwnode; - genpd->has_provider = true; + if (!ret) { + genpd->provider = &np->fwnode; + genpd->has_provider = true; + } } mutex_unlock(&gpd_list_lock); @@ -2079,11 +2093,6 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, int err; u32 residency; u32 entry_latency, exit_latency; - const struct of_device_id *match_id; - - match_id = of_match_node(idle_state_match, state_node); - if (!match_id) - return -EINVAL; err = of_property_read_u32(state_node, "entry-latency-us", &entry_latency); @@ -2132,6 +2141,7 @@ int of_genpd_parse_idle_states(struct device_node *dn, int err, ret; int count; struct of_phandle_iterator it; + const struct of_device_id *match_id; count = of_count_phandle_with_args(dn, "domain-idle-states", NULL); if (count <= 0) @@ -2144,6 +2154,9 @@ int of_genpd_parse_idle_states(struct device_node *dn, /* Loop over the phandles until all the requested entry is found */ of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) { np = it.node; + match_id = of_match_node(idle_state_match, np); + if (!match_id) + continue; ret = genpd_parse_state(&st[i++], np); if (ret) { pr_err @@ -2155,8 +2168,11 @@ int of_genpd_parse_idle_states(struct device_node *dn, } } - *n = count; - *states = st; + *n = i; + if (!i) + kfree(st); + else + *states = st; return 0; } @@ -2221,7 +2237,7 @@ static int pm_genpd_summary_one(struct seq_file *s, if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup))) goto exit; - if (genpd->status == GPD_STATE_POWER_OFF) + if (!genpd_status_on(genpd)) snprintf(state, sizeof(state), "%s-%u", status_lookup[genpd->status], genpd->state_idx); else diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index f96ab717534c..1d1dc11aa5fa 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3969,7 +3969,7 @@ static int mtip_block_initialize(struct driver_data *dd) dd->tags.reserved_tags = 1; dd->tags.cmd_size = sizeof(struct mtip_cmd); dd->tags.numa_node = dd->numa_node; - dd->tags.flags = BLK_MQ_F_SHOULD_MERGE; + dd->tags.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_NO_SCHED; dd->tags.driver_data = dd; dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS; diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c index ab609a76706f..cf9449b3dbd9 100644 --- a/drivers/clk/clk-stm32f4.c +++ b/drivers/clk/clk-stm32f4.c @@ -429,6 +429,13 @@ static const struct clk_div_table pll_divp_table[] = { { 0, 2 }, { 1, 4 }, { 2, 6 }, { 3, 8 }, { 0 } }; +static const struct clk_div_table pll_divq_table[] = { + { 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 }, + { 8, 8 }, { 9, 9 }, { 10, 10 }, { 11, 11 }, { 12, 12 }, { 13, 13 }, + { 14, 14 }, { 15, 15 }, + { 0 } +}; + static const struct clk_div_table pll_divr_table[] = { { 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 }, { 0 } }; @@ -496,9 +503,9 @@ struct stm32f4_div_data { #define MAX_PLL_DIV 3 static const struct stm32f4_div_data div_data[MAX_PLL_DIV] = { - { 16, 2, 0, pll_divp_table }, - { 24, 4, CLK_DIVIDER_ONE_BASED, NULL }, - { 28, 3, 0, pll_divr_table }, + { 16, 2, 0, pll_divp_table }, + { 24, 4, 0, pll_divq_table }, + { 28, 3, 0, pll_divr_table }, }; struct stm32f4_pll_data { diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig index 72109d2cf41b..1c2357301017 100644 --- a/drivers/clk/sunxi-ng/Kconfig +++ b/drivers/clk/sunxi-ng/Kconfig @@ -1,6 +1,7 @@ config SUNXI_CCU bool "Clock support for Allwinner SoCs" depends on ARCH_SUNXI || COMPILE_TEST + select RESET_CONTROLLER default ARCH_SUNXI if SUNXI_CCU @@ -135,6 +136,7 @@ config SUN8I_V3S_CCU config SUN9I_A80_CCU bool "Support for the Allwinner A80 CCU" select SUNXI_CCU_DIV + select SUNXI_CCU_MULT select SUNXI_CCU_GATE select SUNXI_CCU_NKMP select SUNXI_CCU_NM diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c index a7b3c08ed0e2..2c69b631967a 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c @@ -752,6 +752,13 @@ static const struct sunxi_ccu_desc sun8i_a33_ccu_desc = { .num_resets = ARRAY_SIZE(sun8i_a33_ccu_resets), }; +static struct ccu_pll_nb sun8i_a33_pll_cpu_nb = { + .common = &pll_cpux_clk.common, + /* copy from pll_cpux_clk */ + .enable = BIT(31), + .lock = BIT(28), +}; + static struct ccu_mux_nb sun8i_a33_cpu_nb = { .common = &cpux_clk.common, .cm = &cpux_clk.mux, @@ -783,6 +790,10 @@ static void __init sun8i_a33_ccu_setup(struct device_node *node) sunxi_ccu_probe(node, reg, &sun8i_a33_ccu_desc); + /* Gate then ungate PLL CPU after any rate changes */ + ccu_pll_notifier_register(&sun8i_a33_pll_cpu_nb); + + /* Reparent CPU during PLL CPU rate changes */ ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, &sun8i_a33_cpu_nb); } diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c index 8a47bafd7890..9d8724715a43 100644 --- a/drivers/clk/sunxi-ng/ccu_common.c +++ b/drivers/clk/sunxi-ng/ccu_common.c @@ -14,11 +14,13 @@ * GNU General Public License for more details. */ +#include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/iopoll.h> #include <linux/slab.h> #include "ccu_common.h" +#include "ccu_gate.h" #include "ccu_reset.h" static DEFINE_SPINLOCK(ccu_lock); @@ -39,6 +41,53 @@ void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock) WARN_ON(readl_relaxed_poll_timeout(addr, reg, reg & lock, 100, 70000)); } +/* + * This clock notifier is called when the frequency of a PLL clock is + * changed. In common PLL designs, changes to the dividers take effect + * almost immediately, while changes to the multipliers (implemented + * as dividers in the feedback loop) take a few cycles to work into + * the feedback loop for the PLL to stablize. + * + * Sometimes when the PLL clock rate is changed, the decrease in the + * divider is too much for the decrease in the multiplier to catch up. + * The PLL clock rate will spike, and in some cases, might lock up + * completely. + * + * This notifier callback will gate and then ungate the clock, + * effectively resetting it, so it proceeds to work. Care must be + * taken to reparent consumers to other temporary clocks during the + * rate change, and that this notifier callback must be the first + * to be registered. + */ +static int ccu_pll_notifier_cb(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct ccu_pll_nb *pll = to_ccu_pll_nb(nb); + int ret = 0; + + if (event != POST_RATE_CHANGE) + goto out; + + ccu_gate_helper_disable(pll->common, pll->enable); + + ret = ccu_gate_helper_enable(pll->common, pll->enable); + if (ret) + goto out; + + ccu_helper_wait_for_lock(pll->common, pll->lock); + +out: + return notifier_from_errno(ret); +} + +int ccu_pll_notifier_register(struct ccu_pll_nb *pll_nb) +{ + pll_nb->clk_nb.notifier_call = ccu_pll_notifier_cb; + + return clk_notifier_register(pll_nb->common->hw.clk, + &pll_nb->clk_nb); +} + int sunxi_ccu_probe(struct device_node *node, void __iomem *reg, const struct sunxi_ccu_desc *desc) { diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h index 73d81dc58fc5..d6fdd7a789aa 100644 --- a/drivers/clk/sunxi-ng/ccu_common.h +++ b/drivers/clk/sunxi-ng/ccu_common.h @@ -83,6 +83,18 @@ struct sunxi_ccu_desc { void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock); +struct ccu_pll_nb { + struct notifier_block clk_nb; + struct ccu_common *common; + + u32 enable; + u32 lock; +}; + +#define to_ccu_pll_nb(_nb) container_of(_nb, struct ccu_pll_nb, clk_nb) + +int ccu_pll_notifier_register(struct ccu_pll_nb *pll_nb); + int sunxi_ccu_probe(struct device_node *node, void __iomem *reg, const struct sunxi_ccu_desc *desc); diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 74fa5c5904d3..74ed7e9a7f27 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -247,6 +247,12 @@ config ARM_TEGRA124_CPUFREQ help This adds the CPUFreq driver support for Tegra124 SOCs. +config ARM_TEGRA186_CPUFREQ + tristate "Tegra186 CPUFreq support" + depends on ARCH_TEGRA && TEGRA_BPMP + help + This adds the CPUFreq driver support for Tegra186 SOCs. + config ARM_TI_CPUFREQ bool "Texas Instruments CPUFreq support" depends on ARCH_OMAP2PLUS diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 9f5a8045f36d..b7e78f063c4f 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_ARM_SPEAR_CPUFREQ) += spear-cpufreq.o obj-$(CONFIG_ARM_STI_CPUFREQ) += sti-cpufreq.o obj-$(CONFIG_ARM_TEGRA20_CPUFREQ) += tegra20-cpufreq.o obj-$(CONFIG_ARM_TEGRA124_CPUFREQ) += tegra124-cpufreq.o +obj-$(CONFIG_ARM_TEGRA186_CPUFREQ) += tegra186-cpufreq.o obj-$(CONFIG_ARM_TI_CPUFREQ) += ti-cpufreq.o obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ) += vexpress-spc-cpufreq.o obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c index 5c3ec1dd4921..3575b82210ba 100644 --- a/drivers/cpufreq/dbx500-cpufreq.c +++ b/drivers/cpufreq/dbx500-cpufreq.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/cpufreq.h> +#include <linux/cpu_cooling.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/platform_device.h> @@ -18,6 +19,7 @@ static struct cpufreq_frequency_table *freq_table; static struct clk *armss_clk; +static struct thermal_cooling_device *cdev; static int dbx500_cpufreq_target(struct cpufreq_policy *policy, unsigned int index) @@ -32,6 +34,22 @@ static int dbx500_cpufreq_init(struct cpufreq_policy *policy) return cpufreq_generic_init(policy, freq_table, 20 * 1000); } +static int dbx500_cpufreq_exit(struct cpufreq_policy *policy) +{ + if (!IS_ERR(cdev)) + cpufreq_cooling_unregister(cdev); + return 0; +} + +static void dbx500_cpufreq_ready(struct cpufreq_policy *policy) +{ + cdev = cpufreq_cooling_register(policy->cpus); + if (IS_ERR(cdev)) + pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev)); + else + pr_info("Cooling device registered: %s\n", cdev->type); +} + static struct cpufreq_driver dbx500_cpufreq_driver = { .flags = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_INITIAL_FREQ_CHECK, @@ -39,6 +57,8 @@ static struct cpufreq_driver dbx500_cpufreq_driver = { .target_index = dbx500_cpufreq_target, .get = cpufreq_generic_get, .init = dbx500_cpufreq_init, + .exit = dbx500_cpufreq_exit, + .ready = dbx500_cpufreq_ready, .name = "DBX500", .attr = cpufreq_generic_attr, }; diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 7719b02e04f5..9c13f097fd8c 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -161,8 +161,13 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index) static int imx6q_cpufreq_init(struct cpufreq_policy *policy) { + int ret; + policy->clk = arm_clk; - return cpufreq_generic_init(policy, freq_table, transition_latency); + ret = cpufreq_generic_init(policy, freq_table, transition_latency); + policy->suspend_freq = policy->max; + + return ret; } static struct cpufreq_driver imx6q_cpufreq_driver = { @@ -173,6 +178,7 @@ static struct cpufreq_driver imx6q_cpufreq_driver = { .init = imx6q_cpufreq_init, .name = "imx6q-cpufreq", .attr = cpufreq_generic_attr, + .suspend = cpufreq_generic_suspend, }; static int imx6q_cpufreq_probe(struct platform_device *pdev) @@ -222,6 +228,13 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev) arm_reg = regulator_get(cpu_dev, "arm"); pu_reg = regulator_get_optional(cpu_dev, "pu"); soc_reg = regulator_get(cpu_dev, "soc"); + if (PTR_ERR(arm_reg) == -EPROBE_DEFER || + PTR_ERR(soc_reg) == -EPROBE_DEFER || + PTR_ERR(pu_reg) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + dev_dbg(cpu_dev, "regulators not ready, defer\n"); + goto put_reg; + } if (IS_ERR(arm_reg) || IS_ERR(soc_reg)) { dev_err(cpu_dev, "failed to get regulators\n"); ret = -ENOENT; @@ -255,7 +268,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev) ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret); - goto put_reg; + goto out_free_opp; } /* Make imx6_soc_volt array's size same as arm opp number */ diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 283491f742d3..b7de5bd76a31 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -37,7 +37,11 @@ #include <asm/cpufeature.h> #include <asm/intel-family.h> +#define INTEL_PSTATE_DEFAULT_SAMPLING_INTERVAL (10 * NSEC_PER_MSEC) +#define INTEL_PSTATE_HWP_SAMPLING_INTERVAL (50 * NSEC_PER_MSEC) + #define INTEL_CPUFREQ_TRANSITION_LATENCY 20000 +#define INTEL_CPUFREQ_TRANSITION_DELAY 500 #ifdef CONFIG_ACPI #include <acpi/processor.h> @@ -74,6 +78,11 @@ static inline int ceiling_fp(int32_t x) return ret; } +static inline int32_t percent_fp(int percent) +{ + return div_fp(percent, 100); +} + static inline u64 mul_ext_fp(u64 x, u64 y) { return (x * y) >> EXT_FRAC_BITS; @@ -186,45 +195,22 @@ struct _pid { }; /** - * struct perf_limits - Store user and policy limits - * @no_turbo: User requested turbo state from intel_pstate sysfs - * @turbo_disabled: Platform turbo status either from msr - * MSR_IA32_MISC_ENABLE or when maximum available pstate - * matches the maximum turbo pstate - * @max_perf_pct: Effective maximum performance limit in percentage, this - * is minimum of either limits enforced by cpufreq policy - * or limits from user set limits via intel_pstate sysfs - * @min_perf_pct: Effective minimum performance limit in percentage, this - * is maximum of either limits enforced by cpufreq policy - * or limits from user set limits via intel_pstate sysfs - * @max_perf: This is a scaled value between 0 to 255 for max_perf_pct - * This value is used to limit max pstate - * @min_perf: This is a scaled value between 0 to 255 for min_perf_pct - * This value is used to limit min pstate - * @max_policy_pct: The maximum performance in percentage enforced by - * cpufreq setpolicy interface - * @max_sysfs_pct: The maximum performance in percentage enforced by - * intel pstate sysfs interface, unused when per cpu - * controls are enforced - * @min_policy_pct: The minimum performance in percentage enforced by - * cpufreq setpolicy interface - * @min_sysfs_pct: The minimum performance in percentage enforced by - * intel pstate sysfs interface, unused when per cpu - * controls are enforced - * - * Storage for user and policy defined limits. + * struct global_params - Global parameters, mostly tunable via sysfs. + * @no_turbo: Whether or not to use turbo P-states. + * @turbo_disabled: Whethet or not turbo P-states are available at all, + * based on the MSR_IA32_MISC_ENABLE value and whether or + * not the maximum reported turbo P-state is different from + * the maximum reported non-turbo one. + * @min_perf_pct: Minimum capacity limit in percent of the maximum turbo + * P-state capacity. + * @max_perf_pct: Maximum capacity limit in percent of the maximum turbo + * P-state capacity. */ -struct perf_limits { - int no_turbo; - int turbo_disabled; +struct global_params { + bool no_turbo; + bool turbo_disabled; int max_perf_pct; int min_perf_pct; - int32_t max_perf; - int32_t min_perf; - int max_policy_pct; - int max_sysfs_pct; - int min_policy_pct; - int min_sysfs_pct; }; /** @@ -245,9 +231,10 @@ struct perf_limits { * @prev_cummulative_iowait: IO Wait time difference from last and * current sample * @sample: Storage for storing last Sample data - * @perf_limits: Pointer to perf_limit unique to this CPU - * Not all field in the structure are applicable - * when per cpu controls are enforced + * @min_perf: Minimum capacity limit as a fraction of the maximum + * turbo P-state capacity. + * @max_perf: Maximum capacity limit as a fraction of the maximum + * turbo P-state capacity. * @acpi_perf_data: Stores ACPI perf information read from _PSS * @valid_pss_table: Set to true for valid ACPI _PSS entries found * @epp_powersave: Last saved HWP energy performance preference @@ -279,7 +266,8 @@ struct cpudata { u64 prev_tsc; u64 prev_cummulative_iowait; struct sample sample; - struct perf_limits *perf_limits; + int32_t min_perf; + int32_t max_perf; #ifdef CONFIG_ACPI struct acpi_processor_performance acpi_perf_data; bool valid_pss_table; @@ -324,7 +312,7 @@ struct pstate_adjust_policy { * @get_scaling: Callback to get frequency scaling factor * @get_val: Callback to convert P state to actual MSR write value * @get_vid: Callback to get VID data for Atom platforms - * @get_target_pstate: Callback to a function to calculate next P state to use + * @update_util: Active mode utilization update callback. * * Core and Atom CPU models have different way to get P State limits. This * structure is used to store those callbacks. @@ -337,43 +325,31 @@ struct pstate_funcs { int (*get_scaling)(void); u64 (*get_val)(struct cpudata*, int pstate); void (*get_vid)(struct cpudata *); - int32_t (*get_target_pstate)(struct cpudata *); + void (*update_util)(struct update_util_data *data, u64 time, + unsigned int flags); }; -/** - * struct cpu_defaults- Per CPU model default config data - * @pid_policy: PID config data - * @funcs: Callback function data - */ -struct cpu_defaults { - struct pstate_adjust_policy pid_policy; - struct pstate_funcs funcs; +static struct pstate_funcs pstate_funcs __read_mostly; +static struct pstate_adjust_policy pid_params __read_mostly = { + .sample_rate_ms = 10, + .sample_rate_ns = 10 * NSEC_PER_MSEC, + .deadband = 0, + .setpoint = 97, + .p_gain_pct = 20, + .d_gain_pct = 0, + .i_gain_pct = 0, }; -static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu); -static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu); - -static struct pstate_adjust_policy pid_params __read_mostly; -static struct pstate_funcs pstate_funcs __read_mostly; static int hwp_active __read_mostly; static bool per_cpu_limits __read_mostly; -static bool driver_registered __read_mostly; +static struct cpufreq_driver *intel_pstate_driver __read_mostly; #ifdef CONFIG_ACPI static bool acpi_ppc; #endif -static struct perf_limits global; - -static void intel_pstate_init_limits(struct perf_limits *limits) -{ - memset(limits, 0, sizeof(*limits)); - limits->max_perf_pct = 100; - limits->max_perf = int_ext_tofp(1); - limits->max_policy_pct = 100; - limits->max_sysfs_pct = 100; -} +static struct global_params global; static DEFINE_MUTEX(intel_pstate_driver_lock); static DEFINE_MUTEX(intel_pstate_limits_lock); @@ -530,29 +506,6 @@ static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) } #endif -static inline void pid_reset(struct _pid *pid, int setpoint, int busy, - int deadband, int integral) { - pid->setpoint = int_tofp(setpoint); - pid->deadband = int_tofp(deadband); - pid->integral = int_tofp(integral); - pid->last_err = int_tofp(setpoint) - int_tofp(busy); -} - -static inline void pid_p_gain_set(struct _pid *pid, int percent) -{ - pid->p_gain = div_fp(percent, 100); -} - -static inline void pid_i_gain_set(struct _pid *pid, int percent) -{ - pid->i_gain = div_fp(percent, 100); -} - -static inline void pid_d_gain_set(struct _pid *pid, int percent) -{ - pid->d_gain = div_fp(percent, 100); -} - static signed int pid_calc(struct _pid *pid, int32_t busy) { signed int result; @@ -590,23 +543,17 @@ static signed int pid_calc(struct _pid *pid, int32_t busy) return (signed int)fp_toint(result); } -static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu) -{ - pid_p_gain_set(&cpu->pid, pid_params.p_gain_pct); - pid_d_gain_set(&cpu->pid, pid_params.d_gain_pct); - pid_i_gain_set(&cpu->pid, pid_params.i_gain_pct); - - pid_reset(&cpu->pid, pid_params.setpoint, 100, pid_params.deadband, 0); -} - -static inline void intel_pstate_reset_all_pid(void) +static inline void intel_pstate_pid_reset(struct cpudata *cpu) { - unsigned int cpu; + struct _pid *pid = &cpu->pid; - for_each_online_cpu(cpu) { - if (all_cpu_data[cpu]) - intel_pstate_busy_pid_reset(all_cpu_data[cpu]); - } + pid->p_gain = percent_fp(pid_params.p_gain_pct); + pid->d_gain = percent_fp(pid_params.d_gain_pct); + pid->i_gain = percent_fp(pid_params.i_gain_pct); + pid->setpoint = int_tofp(pid_params.setpoint); + pid->last_err = pid->setpoint - int_tofp(100); + pid->deadband = int_tofp(pid_params.deadband); + pid->integral = 0; } static inline void update_turbo_state(void) @@ -621,6 +568,14 @@ static inline void update_turbo_state(void) cpu->pstate.max_pstate == cpu->pstate.turbo_pstate); } +static int min_perf_pct_min(void) +{ + struct cpudata *cpu = all_cpu_data[0]; + + return DIV_ROUND_UP(cpu->pstate.min_pstate * 100, + cpu->pstate.turbo_pstate); +} + static s16 intel_pstate_get_epb(struct cpudata *cpu_data) { u64 epb; @@ -838,96 +793,80 @@ static struct freq_attr *hwp_cpufreq_attrs[] = { NULL, }; -static void intel_pstate_hwp_set(struct cpufreq_policy *policy) +static void intel_pstate_hwp_set(unsigned int cpu) { - int min, hw_min, max, hw_max, cpu; - struct perf_limits *perf_limits = &global; + struct cpudata *cpu_data = all_cpu_data[cpu]; + int min, hw_min, max, hw_max; u64 value, cap; + s16 epp; - for_each_cpu(cpu, policy->cpus) { - struct cpudata *cpu_data = all_cpu_data[cpu]; - s16 epp; - - if (per_cpu_limits) - perf_limits = all_cpu_data[cpu]->perf_limits; - - rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); - hw_min = HWP_LOWEST_PERF(cap); - if (global.no_turbo) - hw_max = HWP_GUARANTEED_PERF(cap); - else - hw_max = HWP_HIGHEST_PERF(cap); - - max = fp_ext_toint(hw_max * perf_limits->max_perf); - if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) - min = max; - else - min = fp_ext_toint(hw_max * perf_limits->min_perf); + rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); + hw_min = HWP_LOWEST_PERF(cap); + if (global.no_turbo) + hw_max = HWP_GUARANTEED_PERF(cap); + else + hw_max = HWP_HIGHEST_PERF(cap); - rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value); + max = fp_ext_toint(hw_max * cpu_data->max_perf); + if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) + min = max; + else + min = fp_ext_toint(hw_max * cpu_data->min_perf); - value &= ~HWP_MIN_PERF(~0L); - value |= HWP_MIN_PERF(min); + rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value); - value &= ~HWP_MAX_PERF(~0L); - value |= HWP_MAX_PERF(max); + value &= ~HWP_MIN_PERF(~0L); + value |= HWP_MIN_PERF(min); - if (cpu_data->epp_policy == cpu_data->policy) - goto skip_epp; + value &= ~HWP_MAX_PERF(~0L); + value |= HWP_MAX_PERF(max); - cpu_data->epp_policy = cpu_data->policy; + if (cpu_data->epp_policy == cpu_data->policy) + goto skip_epp; - if (cpu_data->epp_saved >= 0) { - epp = cpu_data->epp_saved; - cpu_data->epp_saved = -EINVAL; - goto update_epp; - } + cpu_data->epp_policy = cpu_data->policy; - if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) { - epp = intel_pstate_get_epp(cpu_data, value); - cpu_data->epp_powersave = epp; - /* If EPP read was failed, then don't try to write */ - if (epp < 0) - goto skip_epp; + if (cpu_data->epp_saved >= 0) { + epp = cpu_data->epp_saved; + cpu_data->epp_saved = -EINVAL; + goto update_epp; + } + if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) { + epp = intel_pstate_get_epp(cpu_data, value); + cpu_data->epp_powersave = epp; + /* If EPP read was failed, then don't try to write */ + if (epp < 0) + goto skip_epp; - epp = 0; - } else { - /* skip setting EPP, when saved value is invalid */ - if (cpu_data->epp_powersave < 0) - goto skip_epp; + epp = 0; + } else { + /* skip setting EPP, when saved value is invalid */ + if (cpu_data->epp_powersave < 0) + goto skip_epp; - /* - * No need to restore EPP when it is not zero. This - * means: - * - Policy is not changed - * - user has manually changed - * - Error reading EPB - */ - epp = intel_pstate_get_epp(cpu_data, value); - if (epp) - goto skip_epp; + /* + * No need to restore EPP when it is not zero. This + * means: + * - Policy is not changed + * - user has manually changed + * - Error reading EPB + */ + epp = intel_pstate_get_epp(cpu_data, value); + if (epp) + goto skip_epp; - epp = cpu_data->epp_powersave; - } + epp = cpu_data->epp_powersave; + } update_epp: - if (static_cpu_has(X86_FEATURE_HWP_EPP)) { - value &= ~GENMASK_ULL(31, 24); - value |= (u64)epp << 24; - } else { - intel_pstate_set_epb(cpu, epp); - } -skip_epp: - wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + value &= ~GENMASK_ULL(31, 24); + value |= (u64)epp << 24; + } else { + intel_pstate_set_epb(cpu, epp); } -} - -static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy) -{ - if (hwp_active) - intel_pstate_hwp_set(policy); - - return 0; +skip_epp: + wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) @@ -944,20 +883,17 @@ static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) static int intel_pstate_resume(struct cpufreq_policy *policy) { - int ret; - if (!hwp_active) return 0; mutex_lock(&intel_pstate_limits_lock); all_cpu_data[policy->cpu]->epp_policy = 0; - - ret = intel_pstate_hwp_set_policy(policy); + intel_pstate_hwp_set(policy->cpu); mutex_unlock(&intel_pstate_limits_lock); - return ret; + return 0; } static void intel_pstate_update_policies(void) @@ -971,9 +907,14 @@ static void intel_pstate_update_policies(void) /************************** debugfs begin ************************/ static int pid_param_set(void *data, u64 val) { + unsigned int cpu; + *(u32 *)data = val; pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC; - intel_pstate_reset_all_pid(); + for_each_possible_cpu(cpu) + if (all_cpu_data[cpu]) + intel_pstate_pid_reset(all_cpu_data[cpu]); + return 0; } @@ -1084,7 +1025,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj, mutex_lock(&intel_pstate_driver_lock); - if (!driver_registered) { + if (!intel_pstate_driver) { mutex_unlock(&intel_pstate_driver_lock); return -EAGAIN; } @@ -1109,7 +1050,7 @@ static ssize_t show_num_pstates(struct kobject *kobj, mutex_lock(&intel_pstate_driver_lock); - if (!driver_registered) { + if (!intel_pstate_driver) { mutex_unlock(&intel_pstate_driver_lock); return -EAGAIN; } @@ -1129,7 +1070,7 @@ static ssize_t show_no_turbo(struct kobject *kobj, mutex_lock(&intel_pstate_driver_lock); - if (!driver_registered) { + if (!intel_pstate_driver) { mutex_unlock(&intel_pstate_driver_lock); return -EAGAIN; } @@ -1157,7 +1098,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, mutex_lock(&intel_pstate_driver_lock); - if (!driver_registered) { + if (!intel_pstate_driver) { mutex_unlock(&intel_pstate_driver_lock); return -EAGAIN; } @@ -1174,6 +1115,15 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, global.no_turbo = clamp_t(int, input, 0, 1); + if (global.no_turbo) { + struct cpudata *cpu = all_cpu_data[0]; + int pct = cpu->pstate.max_pstate * 100 / cpu->pstate.turbo_pstate; + + /* Squash the global minimum into the permitted range. */ + if (global.min_perf_pct > pct) + global.min_perf_pct = pct; + } + mutex_unlock(&intel_pstate_limits_lock); intel_pstate_update_policies(); @@ -1195,18 +1145,14 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, mutex_lock(&intel_pstate_driver_lock); - if (!driver_registered) { + if (!intel_pstate_driver) { mutex_unlock(&intel_pstate_driver_lock); return -EAGAIN; } mutex_lock(&intel_pstate_limits_lock); - global.max_sysfs_pct = clamp_t(int, input, 0 , 100); - global.max_perf_pct = min(global.max_policy_pct, global.max_sysfs_pct); - global.max_perf_pct = max(global.min_policy_pct, global.max_perf_pct); - global.max_perf_pct = max(global.min_perf_pct, global.max_perf_pct); - global.max_perf = percent_ext_fp(global.max_perf_pct); + global.max_perf_pct = clamp_t(int, input, global.min_perf_pct, 100); mutex_unlock(&intel_pstate_limits_lock); @@ -1229,18 +1175,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, mutex_lock(&intel_pstate_driver_lock); - if (!driver_registered) { + if (!intel_pstate_driver) { mutex_unlock(&intel_pstate_driver_lock); return -EAGAIN; } mutex_lock(&intel_pstate_limits_lock); - global.min_sysfs_pct = clamp_t(int, input, 0 , 100); - global.min_perf_pct = max(global.min_policy_pct, global.min_sysfs_pct); - global.min_perf_pct = min(global.max_policy_pct, global.min_perf_pct); - global.min_perf_pct = min(global.max_perf_pct, global.min_perf_pct); - global.min_perf = percent_ext_fp(global.min_perf_pct); + global.min_perf_pct = clamp_t(int, input, + min_perf_pct_min(), global.max_perf_pct); mutex_unlock(&intel_pstate_limits_lock); @@ -1554,132 +1497,10 @@ static int knl_get_turbo_pstate(void) return ret; } -static struct cpu_defaults core_params = { - .pid_policy = { - .sample_rate_ms = 10, - .deadband = 0, - .setpoint = 97, - .p_gain_pct = 20, - .d_gain_pct = 0, - .i_gain_pct = 0, - }, - .funcs = { - .get_max = core_get_max_pstate, - .get_max_physical = core_get_max_pstate_physical, - .get_min = core_get_min_pstate, - .get_turbo = core_get_turbo_pstate, - .get_scaling = core_get_scaling, - .get_val = core_get_val, - .get_target_pstate = get_target_pstate_use_performance, - }, -}; - -static const struct cpu_defaults silvermont_params = { - .pid_policy = { - .sample_rate_ms = 10, - .deadband = 0, - .setpoint = 60, - .p_gain_pct = 14, - .d_gain_pct = 0, - .i_gain_pct = 4, - }, - .funcs = { - .get_max = atom_get_max_pstate, - .get_max_physical = atom_get_max_pstate, - .get_min = atom_get_min_pstate, - .get_turbo = atom_get_turbo_pstate, - .get_val = atom_get_val, - .get_scaling = silvermont_get_scaling, - .get_vid = atom_get_vid, - .get_target_pstate = get_target_pstate_use_cpu_load, - }, -}; - -static const struct cpu_defaults airmont_params = { - .pid_policy = { - .sample_rate_ms = 10, - .deadband = 0, - .setpoint = 60, - .p_gain_pct = 14, - .d_gain_pct = 0, - .i_gain_pct = 4, - }, - .funcs = { - .get_max = atom_get_max_pstate, - .get_max_physical = atom_get_max_pstate, - .get_min = atom_get_min_pstate, - .get_turbo = atom_get_turbo_pstate, - .get_val = atom_get_val, - .get_scaling = airmont_get_scaling, - .get_vid = atom_get_vid, - .get_target_pstate = get_target_pstate_use_cpu_load, - }, -}; - -static const struct cpu_defaults knl_params = { - .pid_policy = { - .sample_rate_ms = 10, - .deadband = 0, - .setpoint = 97, - .p_gain_pct = 20, - .d_gain_pct = 0, - .i_gain_pct = 0, - }, - .funcs = { - .get_max = core_get_max_pstate, - .get_max_physical = core_get_max_pstate_physical, - .get_min = core_get_min_pstate, - .get_turbo = knl_get_turbo_pstate, - .get_scaling = core_get_scaling, - .get_val = core_get_val, - .get_target_pstate = get_target_pstate_use_performance, - }, -}; - -static const struct cpu_defaults bxt_params = { - .pid_policy = { - .sample_rate_ms = 10, - .deadband = 0, - .setpoint = 60, - .p_gain_pct = 14, - .d_gain_pct = 0, - .i_gain_pct = 4, - }, - .funcs = { - .get_max = core_get_max_pstate, - .get_max_physical = core_get_max_pstate_physical, - .get_min = core_get_min_pstate, - .get_turbo = core_get_turbo_pstate, - .get_scaling = core_get_scaling, - .get_val = core_get_val, - .get_target_pstate = get_target_pstate_use_cpu_load, - }, -}; - -static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) +static int intel_pstate_get_base_pstate(struct cpudata *cpu) { - int max_perf = cpu->pstate.turbo_pstate; - int max_perf_adj; - int min_perf; - struct perf_limits *perf_limits = &global; - - if (global.no_turbo || global.turbo_disabled) - max_perf = cpu->pstate.max_pstate; - - if (per_cpu_limits) - perf_limits = cpu->perf_limits; - - /* - * performance can be limited by user through sysfs, by cpufreq - * policy, or by cpu specific default values determined through - * experimentation. - */ - max_perf_adj = fp_ext_toint(max_perf * perf_limits->max_perf); - *max = clamp_t(int, max_perf_adj, - cpu->pstate.min_pstate, cpu->pstate.turbo_pstate); - - min_perf = fp_ext_toint(max_perf * perf_limits->min_perf); - *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf); + return global.no_turbo || global.turbo_disabled ? + cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; } static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) @@ -1702,11 +1523,13 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu) static void intel_pstate_max_within_limits(struct cpudata *cpu) { - int min_pstate, max_pstate; + int pstate; update_turbo_state(); - intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate); - intel_pstate_set_pstate(cpu, max_pstate); + pstate = intel_pstate_get_base_pstate(cpu); + pstate = max(cpu->pstate.min_pstate, + fp_ext_toint(pstate * cpu->max_perf)); + intel_pstate_set_pstate(cpu, pstate); } static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) @@ -1767,7 +1590,11 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time) * that sample.time will always be reset before setting the utilization * update hook and make the caller skip the sample then. */ - return !!cpu->last_sample_time; + if (cpu->last_sample_time) { + intel_pstate_calc_avg_perf(cpu); + return true; + } + return false; } static inline int32_t get_avg_frequency(struct cpudata *cpu) @@ -1788,6 +1615,9 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) int32_t busy_frac, boost; int target, avg_pstate; + if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) + return cpu->pstate.turbo_pstate; + busy_frac = div_fp(sample->mperf, sample->tsc); boost = cpu->iowait_boost; @@ -1824,6 +1654,9 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) int32_t perf_scaled, max_pstate, current_pstate, sample_ratio; u64 duration_ns; + if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) + return cpu->pstate.turbo_pstate; + /* * perf_scaled is the ratio of the average P-state during the last * sampling period to the P-state requested last time (in percent). @@ -1858,11 +1691,13 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate) { - int max_perf, min_perf; + int max_pstate = intel_pstate_get_base_pstate(cpu); + int min_pstate; - intel_pstate_get_min_max(cpu, &min_perf, &max_perf); - pstate = clamp_t(int, pstate, min_perf, max_perf); - return pstate; + min_pstate = max(cpu->pstate.min_pstate, + fp_ext_toint(max_pstate * cpu->min_perf)); + max_pstate = max(min_pstate, fp_ext_toint(max_pstate * cpu->max_perf)); + return clamp_t(int, pstate, min_pstate, max_pstate); } static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) @@ -1874,16 +1709,11 @@ static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate)); } -static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) +static void intel_pstate_adjust_pstate(struct cpudata *cpu, int target_pstate) { - int from, target_pstate; + int from = cpu->pstate.current_pstate; struct sample *sample; - from = cpu->pstate.current_pstate; - - target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ? - cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu); - update_turbo_state(); target_pstate = intel_pstate_prepare_request(cpu, target_pstate); @@ -1902,76 +1732,155 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) fp_toint(cpu->iowait_boost * 100)); } +static void intel_pstate_update_util_hwp(struct update_util_data *data, + u64 time, unsigned int flags) +{ + struct cpudata *cpu = container_of(data, struct cpudata, update_util); + u64 delta_ns = time - cpu->sample.time; + + if ((s64)delta_ns >= INTEL_PSTATE_HWP_SAMPLING_INTERVAL) + intel_pstate_sample(cpu, time); +} + +static void intel_pstate_update_util_pid(struct update_util_data *data, + u64 time, unsigned int flags) +{ + struct cpudata *cpu = container_of(data, struct cpudata, update_util); + u64 delta_ns = time - cpu->sample.time; + + if ((s64)delta_ns < pid_params.sample_rate_ns) + return; + + if (intel_pstate_sample(cpu, time)) { + int target_pstate; + + target_pstate = get_target_pstate_use_performance(cpu); + intel_pstate_adjust_pstate(cpu, target_pstate); + } +} + static void intel_pstate_update_util(struct update_util_data *data, u64 time, unsigned int flags) { struct cpudata *cpu = container_of(data, struct cpudata, update_util); u64 delta_ns; - if (pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) { - if (flags & SCHED_CPUFREQ_IOWAIT) { - cpu->iowait_boost = int_tofp(1); - } else if (cpu->iowait_boost) { - /* Clear iowait_boost if the CPU may have been idle. */ - delta_ns = time - cpu->last_update; - if (delta_ns > TICK_NSEC) - cpu->iowait_boost = 0; - } - cpu->last_update = time; + if (flags & SCHED_CPUFREQ_IOWAIT) { + cpu->iowait_boost = int_tofp(1); + } else if (cpu->iowait_boost) { + /* Clear iowait_boost if the CPU may have been idle. */ + delta_ns = time - cpu->last_update; + if (delta_ns > TICK_NSEC) + cpu->iowait_boost = 0; } - + cpu->last_update = time; delta_ns = time - cpu->sample.time; - if ((s64)delta_ns >= pid_params.sample_rate_ns) { - bool sample_taken = intel_pstate_sample(cpu, time); + if ((s64)delta_ns < INTEL_PSTATE_DEFAULT_SAMPLING_INTERVAL) + return; - if (sample_taken) { - intel_pstate_calc_avg_perf(cpu); - if (!hwp_active) - intel_pstate_adjust_busy_pstate(cpu); - } + if (intel_pstate_sample(cpu, time)) { + int target_pstate; + + target_pstate = get_target_pstate_use_cpu_load(cpu); + intel_pstate_adjust_pstate(cpu, target_pstate); } } +static struct pstate_funcs core_funcs = { + .get_max = core_get_max_pstate, + .get_max_physical = core_get_max_pstate_physical, + .get_min = core_get_min_pstate, + .get_turbo = core_get_turbo_pstate, + .get_scaling = core_get_scaling, + .get_val = core_get_val, + .update_util = intel_pstate_update_util_pid, +}; + +static const struct pstate_funcs silvermont_funcs = { + .get_max = atom_get_max_pstate, + .get_max_physical = atom_get_max_pstate, + .get_min = atom_get_min_pstate, + .get_turbo = atom_get_turbo_pstate, + .get_val = atom_get_val, + .get_scaling = silvermont_get_scaling, + .get_vid = atom_get_vid, + .update_util = intel_pstate_update_util, +}; + +static const struct pstate_funcs airmont_funcs = { + .get_max = atom_get_max_pstate, + .get_max_physical = atom_get_max_pstate, + .get_min = atom_get_min_pstate, + .get_turbo = atom_get_turbo_pstate, + .get_val = atom_get_val, + .get_scaling = airmont_get_scaling, + .get_vid = atom_get_vid, + .update_util = intel_pstate_update_util, +}; + +static const struct pstate_funcs knl_funcs = { + .get_max = core_get_max_pstate, + .get_max_physical = core_get_max_pstate_physical, + .get_min = core_get_min_pstate, + .get_turbo = knl_get_turbo_pstate, + .get_scaling = core_get_scaling, + .get_val = core_get_val, + .update_util = intel_pstate_update_util_pid, +}; + +static const struct pstate_funcs bxt_funcs = { + .get_max = core_get_max_pstate, + .get_max_physical = core_get_max_pstate_physical, + .get_min = core_get_min_pstate, + .get_turbo = core_get_turbo_pstate, + .get_scaling = core_get_scaling, + .get_val = core_get_val, + .update_util = intel_pstate_update_util, +}; + #define ICPU(model, policy) \ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\ (unsigned long)&policy } static const struct x86_cpu_id intel_pstate_cpu_ids[] = { - ICPU(INTEL_FAM6_SANDYBRIDGE, core_params), - ICPU(INTEL_FAM6_SANDYBRIDGE_X, core_params), - ICPU(INTEL_FAM6_ATOM_SILVERMONT1, silvermont_params), - ICPU(INTEL_FAM6_IVYBRIDGE, core_params), - ICPU(INTEL_FAM6_HASWELL_CORE, core_params), - ICPU(INTEL_FAM6_BROADWELL_CORE, core_params), - ICPU(INTEL_FAM6_IVYBRIDGE_X, core_params), - ICPU(INTEL_FAM6_HASWELL_X, core_params), - ICPU(INTEL_FAM6_HASWELL_ULT, core_params), - ICPU(INTEL_FAM6_HASWELL_GT3E, core_params), - ICPU(INTEL_FAM6_BROADWELL_GT3E, core_params), - ICPU(INTEL_FAM6_ATOM_AIRMONT, airmont_params), - ICPU(INTEL_FAM6_SKYLAKE_MOBILE, core_params), - ICPU(INTEL_FAM6_BROADWELL_X, core_params), - ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_params), - ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params), - ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_params), - ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_params), - ICPU(INTEL_FAM6_ATOM_GOLDMONT, bxt_params), + ICPU(INTEL_FAM6_SANDYBRIDGE, core_funcs), + ICPU(INTEL_FAM6_SANDYBRIDGE_X, core_funcs), + ICPU(INTEL_FAM6_ATOM_SILVERMONT1, silvermont_funcs), + ICPU(INTEL_FAM6_IVYBRIDGE, core_funcs), + ICPU(INTEL_FAM6_HASWELL_CORE, core_funcs), + ICPU(INTEL_FAM6_BROADWELL_CORE, core_funcs), + ICPU(INTEL_FAM6_IVYBRIDGE_X, core_funcs), + ICPU(INTEL_FAM6_HASWELL_X, core_funcs), + ICPU(INTEL_FAM6_HASWELL_ULT, core_funcs), + ICPU(INTEL_FAM6_HASWELL_GT3E, core_funcs), + ICPU(INTEL_FAM6_BROADWELL_GT3E, core_funcs), + ICPU(INTEL_FAM6_ATOM_AIRMONT, airmont_funcs), + ICPU(INTEL_FAM6_SKYLAKE_MOBILE, core_funcs), + ICPU(INTEL_FAM6_BROADWELL_X, core_funcs), + ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_funcs), + ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_funcs), + ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_funcs), + ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_funcs), + ICPU(INTEL_FAM6_ATOM_GOLDMONT, bxt_funcs), + ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, bxt_funcs), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { - ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params), - ICPU(INTEL_FAM6_BROADWELL_X, core_params), - ICPU(INTEL_FAM6_SKYLAKE_X, core_params), + ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_funcs), + ICPU(INTEL_FAM6_BROADWELL_X, core_funcs), + ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs), {} }; static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = { - ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params), + ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_funcs), {} }; +static bool pid_in_use(void); + static int intel_pstate_init_cpu(unsigned int cpunum) { struct cpudata *cpu; @@ -1979,18 +1888,11 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu = all_cpu_data[cpunum]; if (!cpu) { - unsigned int size = sizeof(struct cpudata); - - if (per_cpu_limits) - size += sizeof(struct perf_limits); - - cpu = kzalloc(size, GFP_KERNEL); + cpu = kzalloc(sizeof(*cpu), GFP_KERNEL); if (!cpu) return -ENOMEM; all_cpu_data[cpunum] = cpu; - if (per_cpu_limits) - cpu->perf_limits = (struct perf_limits *)(cpu + 1); cpu->epp_default = -EINVAL; cpu->epp_powersave = -EINVAL; @@ -2009,14 +1911,12 @@ static int intel_pstate_init_cpu(unsigned int cpunum) intel_pstate_disable_ee(cpunum); intel_pstate_hwp_enable(cpu); - pid_params.sample_rate_ms = 50; - pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC; + } else if (pid_in_use()) { + intel_pstate_pid_reset(cpu); } intel_pstate_get_cpu_pstates(cpu); - intel_pstate_busy_pid_reset(cpu); - pr_debug("controlling: cpu %d\n", cpunum); return 0; @@ -2039,7 +1939,7 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num) /* Prevent intel_pstate_update_util() from using stale data. */ cpu->sample.time = 0; cpufreq_add_update_util_hook(cpu_num, &cpu->update_util, - intel_pstate_update_util); + pstate_funcs.update_util); cpu->update_util_set = true; } @@ -2055,46 +1955,68 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu) synchronize_sched(); } +static int intel_pstate_get_max_freq(struct cpudata *cpu) +{ + return global.turbo_disabled || global.no_turbo ? + cpu->pstate.max_freq : cpu->pstate.turbo_freq; +} + static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy, - struct perf_limits *limits) + struct cpudata *cpu) { + int max_freq = intel_pstate_get_max_freq(cpu); int32_t max_policy_perf, min_policy_perf; - max_policy_perf = div_ext_fp(policy->max, policy->cpuinfo.max_freq); + max_policy_perf = div_ext_fp(policy->max, max_freq); max_policy_perf = clamp_t(int32_t, max_policy_perf, 0, int_ext_tofp(1)); if (policy->max == policy->min) { min_policy_perf = max_policy_perf; } else { - min_policy_perf = div_ext_fp(policy->min, - policy->cpuinfo.max_freq); + min_policy_perf = div_ext_fp(policy->min, max_freq); min_policy_perf = clamp_t(int32_t, min_policy_perf, 0, max_policy_perf); } /* Normalize user input to [min_perf, max_perf] */ - limits->min_perf = max(min_policy_perf, - percent_ext_fp(limits->min_sysfs_pct)); - limits->min_perf = min(limits->min_perf, max_policy_perf); - limits->max_perf = min(max_policy_perf, - percent_ext_fp(limits->max_sysfs_pct)); - limits->max_perf = max(min_policy_perf, limits->max_perf); + if (per_cpu_limits) { + cpu->min_perf = min_policy_perf; + cpu->max_perf = max_policy_perf; + } else { + int32_t global_min, global_max; + + /* Global limits are in percent of the maximum turbo P-state. */ + global_max = percent_ext_fp(global.max_perf_pct); + global_min = percent_ext_fp(global.min_perf_pct); + if (max_freq != cpu->pstate.turbo_freq) { + int32_t turbo_factor; + + turbo_factor = div_ext_fp(cpu->pstate.turbo_pstate, + cpu->pstate.max_pstate); + global_min = mul_ext_fp(global_min, turbo_factor); + global_max = mul_ext_fp(global_max, turbo_factor); + } + global_min = clamp_t(int32_t, global_min, 0, global_max); + + cpu->min_perf = max(min_policy_perf, global_min); + cpu->min_perf = min(cpu->min_perf, max_policy_perf); + cpu->max_perf = min(max_policy_perf, global_max); + cpu->max_perf = max(min_policy_perf, cpu->max_perf); - /* Make sure min_perf <= max_perf */ - limits->min_perf = min(limits->min_perf, limits->max_perf); + /* Make sure min_perf <= max_perf */ + cpu->min_perf = min(cpu->min_perf, cpu->max_perf); + } - limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS); - limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS); - limits->max_perf_pct = fp_ext_toint(limits->max_perf * 100); - limits->min_perf_pct = fp_ext_toint(limits->min_perf * 100); + cpu->max_perf = round_up(cpu->max_perf, EXT_FRAC_BITS); + cpu->min_perf = round_up(cpu->min_perf, EXT_FRAC_BITS); pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu, - limits->max_perf_pct, limits->min_perf_pct); + fp_ext_toint(cpu->max_perf * 100), + fp_ext_toint(cpu->min_perf * 100)); } static int intel_pstate_set_policy(struct cpufreq_policy *policy) { struct cpudata *cpu; - struct perf_limits *perf_limits = &global; if (!policy->cpuinfo.max_freq) return -ENODEV; @@ -2105,19 +2027,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) cpu = all_cpu_data[policy->cpu]; cpu->policy = policy->policy; - if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate && - policy->max < policy->cpuinfo.max_freq && - policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) { - pr_debug("policy->max > max non turbo frequency\n"); - policy->max = policy->cpuinfo.max_freq; - } - - if (per_cpu_limits) - perf_limits = cpu->perf_limits; - mutex_lock(&intel_pstate_limits_lock); - intel_pstate_update_perf_limits(policy, perf_limits); + intel_pstate_update_perf_limits(policy, cpu); if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { /* @@ -2130,38 +2042,38 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) intel_pstate_set_update_util_hook(policy->cpu); - intel_pstate_hwp_set_policy(policy); + if (hwp_active) + intel_pstate_hwp_set(policy->cpu); mutex_unlock(&intel_pstate_limits_lock); return 0; } +static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy, + struct cpudata *cpu) +{ + if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate && + policy->max < policy->cpuinfo.max_freq && + policy->max > cpu->pstate.max_freq) { + pr_debug("policy->max > max non turbo frequency\n"); + policy->max = policy->cpuinfo.max_freq; + } +} + static int intel_pstate_verify_policy(struct cpufreq_policy *policy) { struct cpudata *cpu = all_cpu_data[policy->cpu]; update_turbo_state(); - policy->cpuinfo.max_freq = global.turbo_disabled || global.no_turbo ? - cpu->pstate.max_freq : - cpu->pstate.turbo_freq; - - cpufreq_verify_within_cpu_limits(policy); + cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, + intel_pstate_get_max_freq(cpu)); if (policy->policy != CPUFREQ_POLICY_POWERSAVE && policy->policy != CPUFREQ_POLICY_PERFORMANCE) return -EINVAL; - /* When per-CPU limits are used, sysfs limits are not used */ - if (!per_cpu_limits) { - unsigned int max_freq, min_freq; - - max_freq = policy->cpuinfo.max_freq * - global.max_sysfs_pct / 100; - min_freq = policy->cpuinfo.max_freq * - global.min_sysfs_pct / 100; - cpufreq_verify_within_limits(policy, min_freq, max_freq); - } + intel_pstate_adjust_policy_max(policy, cpu); return 0; } @@ -2202,8 +2114,8 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) cpu = all_cpu_data[policy->cpu]; - if (per_cpu_limits) - intel_pstate_init_limits(cpu->perf_limits); + cpu->max_perf = int_ext_tofp(1); + cpu->min_perf = 0; policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling; policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling; @@ -2257,10 +2169,12 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy) struct cpudata *cpu = all_cpu_data[policy->cpu]; update_turbo_state(); - policy->cpuinfo.max_freq = global.no_turbo || global.turbo_disabled ? - cpu->pstate.max_freq : cpu->pstate.turbo_freq; + cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, + intel_pstate_get_max_freq(cpu)); - cpufreq_verify_within_cpu_limits(policy); + intel_pstate_adjust_policy_max(policy, cpu); + + intel_pstate_update_perf_limits(policy, cpu); return 0; } @@ -2324,6 +2238,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) return ret; policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY; + policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY; /* This reflects the intel_pstate_get_cpu_pstates() setting. */ policy->cur = policy->cpuinfo.min_freq; @@ -2341,7 +2256,13 @@ static struct cpufreq_driver intel_cpufreq = { .name = "intel_cpufreq", }; -static struct cpufreq_driver *intel_pstate_driver = &intel_pstate; +static struct cpufreq_driver *default_driver = &intel_pstate; + +static bool pid_in_use(void) +{ + return intel_pstate_driver == &intel_pstate && + pstate_funcs.update_util == intel_pstate_update_util_pid; +} static void intel_pstate_driver_cleanup(void) { @@ -2358,26 +2279,26 @@ static void intel_pstate_driver_cleanup(void) } } put_online_cpus(); + intel_pstate_driver = NULL; } -static int intel_pstate_register_driver(void) +static int intel_pstate_register_driver(struct cpufreq_driver *driver) { int ret; - intel_pstate_init_limits(&global); + memset(&global, 0, sizeof(global)); + global.max_perf_pct = 100; + intel_pstate_driver = driver; ret = cpufreq_register_driver(intel_pstate_driver); if (ret) { intel_pstate_driver_cleanup(); return ret; } - mutex_lock(&intel_pstate_limits_lock); - driver_registered = true; - mutex_unlock(&intel_pstate_limits_lock); + global.min_perf_pct = min_perf_pct_min(); - if (intel_pstate_driver == &intel_pstate && !hwp_active && - pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load) + if (pid_in_use()) intel_pstate_debug_expose_params(); return 0; @@ -2388,14 +2309,9 @@ static int intel_pstate_unregister_driver(void) if (hwp_active) return -EBUSY; - if (intel_pstate_driver == &intel_pstate && !hwp_active && - pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load) + if (pid_in_use()) intel_pstate_debug_hide_params(); - mutex_lock(&intel_pstate_limits_lock); - driver_registered = false; - mutex_unlock(&intel_pstate_limits_lock); - cpufreq_unregister_driver(intel_pstate_driver); intel_pstate_driver_cleanup(); @@ -2404,7 +2320,7 @@ static int intel_pstate_unregister_driver(void) static ssize_t intel_pstate_show_status(char *buf) { - if (!driver_registered) + if (!intel_pstate_driver) return sprintf(buf, "off\n"); return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ? @@ -2416,11 +2332,11 @@ static int intel_pstate_update_status(const char *buf, size_t size) int ret; if (size == 3 && !strncmp(buf, "off", size)) - return driver_registered ? + return intel_pstate_driver ? intel_pstate_unregister_driver() : -EINVAL; if (size == 6 && !strncmp(buf, "active", size)) { - if (driver_registered) { + if (intel_pstate_driver) { if (intel_pstate_driver == &intel_pstate) return 0; @@ -2429,13 +2345,12 @@ static int intel_pstate_update_status(const char *buf, size_t size) return ret; } - intel_pstate_driver = &intel_pstate; - return intel_pstate_register_driver(); + return intel_pstate_register_driver(&intel_pstate); } if (size == 7 && !strncmp(buf, "passive", size)) { - if (driver_registered) { - if (intel_pstate_driver != &intel_pstate) + if (intel_pstate_driver) { + if (intel_pstate_driver == &intel_cpufreq) return 0; ret = intel_pstate_unregister_driver(); @@ -2443,8 +2358,7 @@ static int intel_pstate_update_status(const char *buf, size_t size) return ret; } - intel_pstate_driver = &intel_cpufreq; - return intel_pstate_register_driver(); + return intel_pstate_register_driver(&intel_cpufreq); } return -EINVAL; @@ -2465,23 +2379,17 @@ static int __init intel_pstate_msrs_not_valid(void) return 0; } -static void __init copy_pid_params(struct pstate_adjust_policy *policy) -{ - pid_params.sample_rate_ms = policy->sample_rate_ms; - pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC; - pid_params.p_gain_pct = policy->p_gain_pct; - pid_params.i_gain_pct = policy->i_gain_pct; - pid_params.d_gain_pct = policy->d_gain_pct; - pid_params.deadband = policy->deadband; - pid_params.setpoint = policy->setpoint; -} - #ifdef CONFIG_ACPI static void intel_pstate_use_acpi_profile(void) { - if (acpi_gbl_FADT.preferred_profile == PM_MOBILE) - pstate_funcs.get_target_pstate = - get_target_pstate_use_cpu_load; + switch (acpi_gbl_FADT.preferred_profile) { + case PM_MOBILE: + case PM_TABLET: + case PM_APPLIANCE_PC: + case PM_DESKTOP: + case PM_WORKSTATION: + pstate_funcs.update_util = intel_pstate_update_util; + } } #else static void intel_pstate_use_acpi_profile(void) @@ -2498,7 +2406,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_scaling = funcs->get_scaling; pstate_funcs.get_val = funcs->get_val; pstate_funcs.get_vid = funcs->get_vid; - pstate_funcs.get_target_pstate = funcs->get_target_pstate; + pstate_funcs.update_util = funcs->update_util; intel_pstate_use_acpi_profile(); } @@ -2637,28 +2545,30 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = { static int __init intel_pstate_init(void) { - const struct x86_cpu_id *id; - struct cpu_defaults *cpu_def; - int rc = 0; + int rc; if (no_load) return -ENODEV; - if (x86_match_cpu(hwp_support_ids) && !no_hwp) { - copy_cpu_funcs(&core_params.funcs); - hwp_active++; - intel_pstate.attr = hwp_cpufreq_attrs; - goto hwp_cpu_matched; - } - - id = x86_match_cpu(intel_pstate_cpu_ids); - if (!id) - return -ENODEV; + if (x86_match_cpu(hwp_support_ids)) { + copy_cpu_funcs(&core_funcs); + if (no_hwp) { + pstate_funcs.update_util = intel_pstate_update_util; + } else { + hwp_active++; + intel_pstate.attr = hwp_cpufreq_attrs; + pstate_funcs.update_util = intel_pstate_update_util_hwp; + goto hwp_cpu_matched; + } + } else { + const struct x86_cpu_id *id; - cpu_def = (struct cpu_defaults *)id->driver_data; + id = x86_match_cpu(intel_pstate_cpu_ids); + if (!id) + return -ENODEV; - copy_pid_params(&cpu_def->pid_policy); - copy_cpu_funcs(&cpu_def->funcs); + copy_cpu_funcs((struct pstate_funcs *)id->driver_data); + } if (intel_pstate_msrs_not_valid()) return -ENODEV; @@ -2685,7 +2595,7 @@ hwp_cpu_matched: intel_pstate_sysfs_expose_params(); mutex_lock(&intel_pstate_driver_lock); - rc = intel_pstate_register_driver(); + rc = intel_pstate_register_driver(default_driver); mutex_unlock(&intel_pstate_driver_lock); if (rc) return rc; @@ -2706,7 +2616,7 @@ static int __init intel_pstate_setup(char *str) no_load = 1; } else if (!strcmp(str, "passive")) { pr_info("Passive mode enabled\n"); - intel_pstate_driver = &intel_cpufreq; + default_driver = &intel_cpufreq; no_hwp = 1; } if (!strcmp(str, "no_hwp")) { diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c index ab25b1235a5e..fd1886faf33a 100644 --- a/drivers/cpufreq/mt8173-cpufreq.c +++ b/drivers/cpufreq/mt8173-cpufreq.c @@ -573,14 +573,33 @@ static struct platform_driver mt8173_cpufreq_platdrv = { .probe = mt8173_cpufreq_probe, }; -static int mt8173_cpufreq_driver_init(void) +/* List of machines supported by this driver */ +static const struct of_device_id mt8173_cpufreq_machines[] __initconst = { + { .compatible = "mediatek,mt817x", }, + { .compatible = "mediatek,mt8173", }, + { .compatible = "mediatek,mt8176", }, + + { } +}; + +static int __init mt8173_cpufreq_driver_init(void) { + struct device_node *np; + const struct of_device_id *match; struct platform_device *pdev; int err; - if (!of_machine_is_compatible("mediatek,mt8173")) + np = of_find_node_by_path("/"); + if (!np) return -ENODEV; + match = of_match_node(mt8173_cpufreq_machines, np); + of_node_put(np); + if (!match) { + pr_warn("Machine is not compatible with mt8173-cpufreq\n"); + return -ENODEV; + } + err = platform_driver_register(&mt8173_cpufreq_platdrv); if (err) return err; diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index bfec1bcd3835..e2ea433a5f9c 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -52,17 +52,27 @@ static u32 get_bus_freq(void) { struct device_node *soc; u32 sysfreq; + struct clk *pltclk; + int ret; + /* get platform freq by searching bus-frequency property */ soc = of_find_node_by_type(NULL, "soc"); - if (!soc) - return 0; - - if (of_property_read_u32(soc, "bus-frequency", &sysfreq)) - sysfreq = 0; + if (soc) { + ret = of_property_read_u32(soc, "bus-frequency", &sysfreq); + of_node_put(soc); + if (!ret) + return sysfreq; + } - of_node_put(soc); + /* get platform freq by its clock name */ + pltclk = clk_get(NULL, "cg-pll0-div1"); + if (IS_ERR(pltclk)) { + pr_err("%s: can't get bus frequency %ld\n", + __func__, PTR_ERR(pltclk)); + return PTR_ERR(pltclk); + } - return sysfreq; + return clk_get_rate(pltclk); } static struct clk *cpu_to_clk(int cpu) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c new file mode 100644 index 000000000000..fe7875311d62 --- /dev/null +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -0,0 +1,275 @@ +/* + * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/cpufreq.h> +#include <linux/dma-mapping.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> + +#include <soc/tegra/bpmp.h> +#include <soc/tegra/bpmp-abi.h> + +#define EDVD_CORE_VOLT_FREQ(core) (0x20 + (core) * 0x4) +#define EDVD_CORE_VOLT_FREQ_F_SHIFT 0 +#define EDVD_CORE_VOLT_FREQ_V_SHIFT 16 + +struct tegra186_cpufreq_cluster_info { + unsigned long offset; + int cpus[4]; + unsigned int bpmp_cluster_id; +}; + +#define NO_CPU -1 +static const struct tegra186_cpufreq_cluster_info tegra186_clusters[] = { + /* Denver cluster */ + { + .offset = SZ_64K * 7, + .cpus = { 1, 2, NO_CPU, NO_CPU }, + .bpmp_cluster_id = 0, + }, + /* A57 cluster */ + { + .offset = SZ_64K * 6, + .cpus = { 0, 3, 4, 5 }, + .bpmp_cluster_id = 1, + }, +}; + +struct tegra186_cpufreq_cluster { + const struct tegra186_cpufreq_cluster_info *info; + struct cpufreq_frequency_table *table; +}; + +struct tegra186_cpufreq_data { + void __iomem *regs; + + size_t num_clusters; + struct tegra186_cpufreq_cluster *clusters; +}; + +static int tegra186_cpufreq_init(struct cpufreq_policy *policy) +{ + struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); + unsigned int i; + + for (i = 0; i < data->num_clusters; i++) { + struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; + const struct tegra186_cpufreq_cluster_info *info = + cluster->info; + int core; + + for (core = 0; core < ARRAY_SIZE(info->cpus); core++) { + if (info->cpus[core] == policy->cpu) + break; + } + if (core == ARRAY_SIZE(info->cpus)) + continue; + + policy->driver_data = + data->regs + info->offset + EDVD_CORE_VOLT_FREQ(core); + cpufreq_table_validate_and_show(policy, cluster->table); + } + + policy->cpuinfo.transition_latency = 300 * 1000; + + return 0; +} + +static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy, + unsigned int index) +{ + struct cpufreq_frequency_table *tbl = policy->freq_table + index; + void __iomem *edvd_reg = policy->driver_data; + u32 edvd_val = tbl->driver_data; + + writel(edvd_val, edvd_reg); + + return 0; +} + +static struct cpufreq_driver tegra186_cpufreq_driver = { + .name = "tegra186", + .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY, + .verify = cpufreq_generic_frequency_table_verify, + .target_index = tegra186_cpufreq_set_target, + .init = tegra186_cpufreq_init, + .attr = cpufreq_generic_attr, +}; + +static struct cpufreq_frequency_table *init_vhint_table( + struct platform_device *pdev, struct tegra_bpmp *bpmp, + unsigned int cluster_id) +{ + struct cpufreq_frequency_table *table; + struct mrq_cpu_vhint_request req; + struct tegra_bpmp_message msg; + struct cpu_vhint_data *data; + int err, i, j, num_rates = 0; + dma_addr_t phys; + void *virt; + + virt = dma_alloc_coherent(bpmp->dev, sizeof(*data), &phys, + GFP_KERNEL | GFP_DMA32); + if (!virt) + return ERR_PTR(-ENOMEM); + + data = (struct cpu_vhint_data *)virt; + + memset(&req, 0, sizeof(req)); + req.addr = phys; + req.cluster_id = cluster_id; + + memset(&msg, 0, sizeof(msg)); + msg.mrq = MRQ_CPU_VHINT; + msg.tx.data = &req; + msg.tx.size = sizeof(req); + + err = tegra_bpmp_transfer(bpmp, &msg); + if (err) { + table = ERR_PTR(err); + goto free; + } + + for (i = data->vfloor; i <= data->vceil; i++) { + u16 ndiv = data->ndiv[i]; + + if (ndiv < data->ndiv_min || ndiv > data->ndiv_max) + continue; + + /* Only store lowest voltage index for each rate */ + if (i > 0 && ndiv == data->ndiv[i - 1]) + continue; + + num_rates++; + } + + table = devm_kcalloc(&pdev->dev, num_rates + 1, sizeof(*table), + GFP_KERNEL); + if (!table) { + table = ERR_PTR(-ENOMEM); + goto free; + } + + for (i = data->vfloor, j = 0; i <= data->vceil; i++) { + struct cpufreq_frequency_table *point; + u16 ndiv = data->ndiv[i]; + u32 edvd_val = 0; + + if (ndiv < data->ndiv_min || ndiv > data->ndiv_max) + continue; + + /* Only store lowest voltage index for each rate */ + if (i > 0 && ndiv == data->ndiv[i - 1]) + continue; + + edvd_val |= i << EDVD_CORE_VOLT_FREQ_V_SHIFT; + edvd_val |= ndiv << EDVD_CORE_VOLT_FREQ_F_SHIFT; + + point = &table[j++]; + point->driver_data = edvd_val; + point->frequency = data->ref_clk_hz * ndiv / data->pdiv / + data->mdiv / 1000; + } + + table[j].frequency = CPUFREQ_TABLE_END; + +free: + dma_free_coherent(bpmp->dev, sizeof(*data), virt, phys); + + return table; +} + +static int tegra186_cpufreq_probe(struct platform_device *pdev) +{ + struct tegra186_cpufreq_data *data; + struct tegra_bpmp *bpmp; + struct resource *res; + unsigned int i = 0, err; + + data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->clusters = devm_kcalloc(&pdev->dev, ARRAY_SIZE(tegra186_clusters), + sizeof(*data->clusters), GFP_KERNEL); + if (!data->clusters) + return -ENOMEM; + + data->num_clusters = ARRAY_SIZE(tegra186_clusters); + + bpmp = tegra_bpmp_get(&pdev->dev); + if (IS_ERR(bpmp)) + return PTR_ERR(bpmp); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + data->regs = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(data->regs)) { + err = PTR_ERR(data->regs); + goto put_bpmp; + } + + for (i = 0; i < data->num_clusters; i++) { + struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; + + cluster->info = &tegra186_clusters[i]; + cluster->table = init_vhint_table( + pdev, bpmp, cluster->info->bpmp_cluster_id); + if (IS_ERR(cluster->table)) { + err = PTR_ERR(cluster->table); + goto put_bpmp; + } + } + + tegra_bpmp_put(bpmp); + + tegra186_cpufreq_driver.driver_data = data; + + err = cpufreq_register_driver(&tegra186_cpufreq_driver); + if (err) + return err; + + return 0; + +put_bpmp: + tegra_bpmp_put(bpmp); + + return err; +} + +static int tegra186_cpufreq_remove(struct platform_device *pdev) +{ + cpufreq_unregister_driver(&tegra186_cpufreq_driver); + + return 0; +} + +static const struct of_device_id tegra186_cpufreq_of_match[] = { + { .compatible = "nvidia,tegra186-ccplex-cluster", }, + { } +}; +MODULE_DEVICE_TABLE(of, tegra186_cpufreq_of_match); + +static struct platform_driver tegra186_cpufreq_platform_driver = { + .driver = { + .name = "tegra186-cpufreq", + .of_match_table = tegra186_cpufreq_of_match, + }, + .probe = tegra186_cpufreq_probe, + .remove = tegra186_cpufreq_remove, +}; +module_platform_driver(tegra186_cpufreq_platform_driver); + +MODULE_AUTHOR("Mikko Perttunen <mperttunen@nvidia.com>"); +MODULE_DESCRIPTION("NVIDIA Tegra186 cpufreq driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/cpuidle/cpuidle-cps.c b/drivers/cpuidle/cpuidle-cps.c index 926ba9871c62..12b9145913de 100644 --- a/drivers/cpuidle/cpuidle-cps.c +++ b/drivers/cpuidle/cpuidle-cps.c @@ -118,7 +118,7 @@ static void __init cps_cpuidle_unregister(void) static int __init cps_cpuidle_init(void) { - int err, cpu, core, i; + int err, cpu, i; struct cpuidle_device *device; /* Detect supported states */ @@ -160,7 +160,6 @@ static int __init cps_cpuidle_init(void) } for_each_possible_cpu(cpu) { - core = cpu_data[cpu].core; device = &per_cpu(cpuidle_dev, cpu); device->cpu = cpu; #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index cda8f62d555b..12409a519cc5 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -56,10 +56,9 @@ static int snooze_loop(struct cpuidle_device *dev, snooze_exit_time = get_tb() + snooze_timeout; ppc64_runlatch_off(); + HMT_very_low(); while (!need_resched()) { - HMT_low(); - HMT_very_low(); - if (snooze_timeout_en && get_tb() > snooze_exit_time) + if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) break; } @@ -215,11 +214,25 @@ static inline void add_powernv_state(int index, const char *name, stop_psscr_table[index].mask = psscr_mask; } +/* + * Returns 0 if prop1_len == prop2_len. Else returns -1 + */ +static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len, + const char *prop2, int prop2_len) +{ + if (prop1_len == prop2_len) + return 0; + + pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n", + prop1, prop2); + return -1; +} + static int powernv_add_idle_states(void) { struct device_node *power_mgt; int nr_idle_states = 1; /* Snooze */ - int dt_idle_states; + int dt_idle_states, count; u32 latency_ns[CPUIDLE_STATE_MAX]; u32 residency_ns[CPUIDLE_STATE_MAX]; u32 flags[CPUIDLE_STATE_MAX]; @@ -244,6 +257,21 @@ static int powernv_add_idle_states(void) goto out; } + count = of_property_count_u32_elems(power_mgt, + "ibm,cpu-idle-state-latencies-ns"); + + if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states, + "ibm,cpu-idle-state-latencies-ns", + count) != 0) + goto out; + + count = of_property_count_strings(power_mgt, + "ibm,cpu-idle-state-names"); + if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states, + "ibm,cpu-idle-state-names", + count) != 0) + goto out; + /* * Since snooze is used as first idle state, max idle states allowed is * CPUIDLE_STATE_MAX -1 @@ -278,6 +306,22 @@ static int powernv_add_idle_states(void) has_stop_states = (flags[0] & (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP)); if (has_stop_states) { + count = of_property_count_u64_elems(power_mgt, + "ibm,cpu-idle-state-psscr"); + if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", + dt_idle_states, + "ibm,cpu-idle-state-psscr", + count) != 0) + goto out; + + count = of_property_count_u64_elems(power_mgt, + "ibm,cpu-idle-state-psscr-mask"); + if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", + dt_idle_states, + "ibm,cpu-idle-state-psscr-mask", + count) != 0) + goto out; + if (of_property_read_u64_array(power_mgt, "ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) { pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n"); @@ -292,8 +336,21 @@ static int powernv_add_idle_states(void) } } - rc = of_property_read_u32_array(power_mgt, - "ibm,cpu-idle-state-residency-ns", residency_ns, dt_idle_states); + count = of_property_count_u32_elems(power_mgt, + "ibm,cpu-idle-state-residency-ns"); + + if (count < 0) { + rc = count; + } else if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", + dt_idle_states, + "ibm,cpu-idle-state-residency-ns", + count) != 0) { + goto out; + } else { + rc = of_property_read_u32_array(power_mgt, + "ibm,cpu-idle-state-residency-ns", + residency_ns, dt_idle_states); + } for (i = 0; i < dt_idle_states; i++) { unsigned int exit_latency, target_residency; diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h index 71576b8bdfef..a4f2fa1091e4 100644 --- a/drivers/devfreq/governor.h +++ b/drivers/devfreq/governor.h @@ -25,6 +25,35 @@ #define DEVFREQ_GOV_SUSPEND 0x4 #define DEVFREQ_GOV_RESUME 0x5 +/** + * struct devfreq_governor - Devfreq policy governor + * @node: list node - contains registered devfreq governors + * @name: Governor's name + * @immutable: Immutable flag for governor. If the value is 1, + * this govenror is never changeable to other governor. + * @get_target_freq: Returns desired operating frequency for the device. + * Basically, get_target_freq will run + * devfreq_dev_profile.get_dev_status() to get the + * status of the device (load = busy_time / total_time). + * If no_central_polling is set, this callback is called + * only with update_devfreq() notified by OPP. + * @event_handler: Callback for devfreq core framework to notify events + * to governors. Events include per device governor + * init and exit, opp changes out of devfreq, suspend + * and resume of per device devfreq during device idle. + * + * Note that the callbacks are called with devfreq->lock locked by devfreq. + */ +struct devfreq_governor { + struct list_head node; + + const char name[DEVFREQ_NAME_LEN]; + const unsigned int immutable; + int (*get_target_freq)(struct devfreq *this, unsigned long *freq); + int (*event_handler)(struct devfreq *devfreq, + unsigned int event, void *data); +}; + /* Caution: devfreq->lock must be locked before calling update_devfreq */ extern int update_devfreq(struct devfreq *devfreq); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 94250c293be2..c68ac65db7ff 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2006,7 +2006,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field return; case HID_DG_TOOLSERIALNUMBER: wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); - wacom_wac->serial[0] |= value; + wacom_wac->serial[0] |= (__u32)value; return; case WACOM_HID_WD_SENSE: wacom_wac->hid_data.sense_state = value; @@ -2176,6 +2176,16 @@ static void wacom_wac_finger_usage_mapping(struct hid_device *hdev, wacom_wac->hid_data.cc_index = field->index; wacom_wac->hid_data.cc_value_index = usage->usage_index; break; + case HID_DG_CONTACTID: + if ((field->logical_maximum - field->logical_minimum) < touch_max) { + /* + * The HID descriptor for G11 sensors leaves logical + * maximum set to '1' despite it being a multitouch + * device. Override to a sensible number. + */ + field->logical_maximum = 255; + } + break; } } diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index efc8ec342351..e73d968023f7 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1118,6 +1118,7 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad * Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons + * Fujitsu LIFEBOOK E547 0x470f00 50, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons * Fujitsu T725 0x470f01 05, 12, 09 2 hw buttons * Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**) @@ -1524,6 +1525,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = { }, }, { + /* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E547"), + }, + }, + { /* Fujitsu LIFEBOOK E554 does not work with crc_enabled == 0 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index e992a7f8a16f..2b32b88949ba 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -267,7 +267,7 @@ static void sdio_release_func(struct device *dev) sdio_free_func_cis(func); kfree(func->info); - + kfree(func->tmpbuf); kfree(func); } @@ -282,6 +282,16 @@ struct sdio_func *sdio_alloc_func(struct mmc_card *card) if (!func) return ERR_PTR(-ENOMEM); + /* + * allocate buffer separately to make sure it's properly aligned for + * DMA usage (incl. 64 bit DMA) + */ + func->tmpbuf = kmalloc(4, GFP_KERNEL); + if (!func->tmpbuf) { + kfree(func); + return ERR_PTR(-ENOMEM); + } + func->card = card; device_initialize(&func->dev); diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index a9ac0b457313..8718432751c5 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -22,6 +22,7 @@ #include <linux/ioport.h> #include <linux/module.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/stat.h> @@ -1621,10 +1622,16 @@ static void dw_mci_init_card(struct mmc_host *mmc, struct mmc_card *card) if (card->type == MMC_TYPE_SDIO || card->type == MMC_TYPE_SD_COMBO) { - set_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags); + if (!test_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags)) { + pm_runtime_get_noresume(mmc->parent); + set_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags); + } clk_en_a = clk_en_a_old & ~clken_low_pwr; } else { - clear_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags); + if (test_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags)) { + pm_runtime_put_noidle(mmc->parent); + clear_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags); + } clk_en_a = clk_en_a_old | clken_low_pwr; } diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 7123ef96ed18..445fc47dc3e7 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -830,6 +830,7 @@ static int esdhc_change_pinstate(struct sdhci_host *host, switch (uhs) { case MMC_TIMING_UHS_SDR50: + case MMC_TIMING_UHS_DDR50: pinctrl = imx_data->pins_100mhz; break; case MMC_TIMING_UHS_SDR104: diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index 0134ba32a057..39712560b4c1 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -148,11 +148,11 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, return err; } - if (bytes == 0) { - err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL); - if (err) - return err; + err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL); + if (err) + return err; + if (bytes == 0) { err = clear_update_marker(ubi, vol, 0); if (err) return err; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 64a1095e4d14..a0ca68ce3fbb 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -134,6 +134,7 @@ static void set_max_bgx_per_node(struct pci_dev *pdev) pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid); switch (sdevid) { case PCI_SUBSYS_DEVID_81XX_BGX: + case PCI_SUBSYS_DEVID_81XX_RGX: max_bgx_per_node = MAX_BGX_PER_CN81XX; break; case PCI_SUBSYS_DEVID_83XX_BGX: diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index c5080f2cead5..6b7fe6fdd13b 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -16,6 +16,7 @@ /* Subsystem device IDs */ #define PCI_SUBSYS_DEVID_88XX_BGX 0xA126 #define PCI_SUBSYS_DEVID_81XX_BGX 0xA226 +#define PCI_SUBSYS_DEVID_81XX_RGX 0xA254 #define PCI_SUBSYS_DEVID_83XX_BGX 0xA326 #define MAX_BGX_THUNDER 8 /* Max 2 nodes, 4 per node */ diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 9e757684816d..93949139e62c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -613,7 +613,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; struct mtk_tx_dma *itxd, *txd; - struct mtk_tx_buf *tx_buf; + struct mtk_tx_buf *itx_buf, *tx_buf; dma_addr_t mapped_addr; unsigned int nr_frags; int i, n_desc = 1; @@ -627,8 +627,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, fport = (mac->id + 1) << TX_DMA_FPORT_SHIFT; txd4 |= fport; - tx_buf = mtk_desc_to_tx_buf(ring, itxd); - memset(tx_buf, 0, sizeof(*tx_buf)); + itx_buf = mtk_desc_to_tx_buf(ring, itxd); + memset(itx_buf, 0, sizeof(*itx_buf)); if (gso) txd4 |= TX_DMA_TSO; @@ -647,9 +647,11 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, return -ENOMEM; WRITE_ONCE(itxd->txd1, mapped_addr); - tx_buf->flags |= MTK_TX_FLAGS_SINGLE0; - dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb)); + itx_buf->flags |= MTK_TX_FLAGS_SINGLE0; + itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : + MTK_TX_FLAGS_FPORT1; + dma_unmap_addr_set(itx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(itx_buf, dma_len0, skb_headlen(skb)); /* TX SG offload */ txd = itxd; @@ -685,11 +687,13 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, last_frag * TX_DMA_LS0)); WRITE_ONCE(txd->txd4, fport); - tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; tx_buf = mtk_desc_to_tx_buf(ring, txd); memset(tx_buf, 0, sizeof(*tx_buf)); - + tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; tx_buf->flags |= MTK_TX_FLAGS_PAGE0; + tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : + MTK_TX_FLAGS_FPORT1; + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); dma_unmap_len_set(tx_buf, dma_len0, frag_map_size); frag_size -= frag_map_size; @@ -698,7 +702,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, } /* store skb to cleanup */ - tx_buf->skb = skb; + itx_buf->skb = skb; WRITE_ONCE(itxd->txd4, txd4); WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) | @@ -1012,17 +1016,16 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) while ((cpu != dma) && budget) { u32 next_cpu = desc->txd2; - int mac; + int mac = 0; desc = mtk_qdma_phys_to_virt(ring, desc->txd2); if ((desc->txd3 & TX_DMA_OWNER_CPU) == 0) break; - mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) & - TX_DMA_FPORT_MASK; - mac--; - tx_buf = mtk_desc_to_tx_buf(ring, desc); + if (tx_buf->flags & MTK_TX_FLAGS_FPORT1) + mac = 1; + skb = tx_buf->skb; if (!skb) { condition = 1; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 99b1c8e9f16f..08285a96ff70 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -406,12 +406,18 @@ struct mtk_hw_stats { struct u64_stats_sync syncp; }; -/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how - * memory was allocated so that it can be freed properly - */ enum mtk_tx_flags { + /* PDMA descriptor can point at 1-2 segments. This enum allows us to + * track how memory was allocated so that it can be freed properly. + */ MTK_TX_FLAGS_SINGLE0 = 0x01, MTK_TX_FLAGS_PAGE0 = 0x02, + + /* MTK_TX_FLAGS_FPORTx allows tracking which port the transmitted + * SKB out instead of looking up through hardware TX descriptor. + */ + MTK_TX_FLAGS_FPORT0 = 0x04, + MTK_TX_FLAGS_FPORT1 = 0x08, }; /* This enum allows us to identify how the clock is defined on the array of the diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 5bd36a4a8fcd..a6e2bbe629bd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -583,6 +583,13 @@ qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn, p_params->ets_cbs, p_ets->pri_tc_tbl[0], p_params->max_ets_tc); + if (p_params->ets_enabled && !p_params->max_ets_tc) { + p_params->max_ets_tc = QED_MAX_PFC_PRIORITIES; + DP_VERBOSE(p_hwfn, QED_MSG_DCB, + "ETS params: max_ets_tc is forced to %d\n", + p_params->max_ets_tc); + } + /* 8 bit tsa and bw data corresponding to each of the 8 TC's are * encoded in a type u32 array of size 2. */ @@ -1001,6 +1008,8 @@ qed_dcbx_set_pfc_data(struct qed_hwfn *p_hwfn, u8 pfc_map = 0; int i; + *pfc &= ~DCBX_PFC_ERROR_MASK; + if (p_params->pfc.willing) *pfc |= DCBX_PFC_WILLING_MASK; else @@ -1255,7 +1264,7 @@ static struct qed_dcbx_get *qed_dcbnl_get_dcbx(struct qed_hwfn *hwfn, { struct qed_dcbx_get *dcbx_info; - dcbx_info = kzalloc(sizeof(*dcbx_info), GFP_KERNEL); + dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_ATOMIC); if (!dcbx_info) return NULL; @@ -2073,6 +2082,8 @@ static int qed_dcbnl_ieee_setpfc(struct qed_dev *cdev, struct ieee_pfc *pfc) for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) dcbx_set.config.params.pfc.prio[i] = !!(pfc->pfc_en & BIT(i)); + dcbx_set.config.params.pfc.max_tc = pfc->pfc_cap; + ptt = qed_ptt_acquire(hwfn); if (!ptt) return -EINVAL; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 54248775f227..f68c4db656ed 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1127,12 +1127,70 @@ static struct mdiobb_ops bb_ops = { .get_mdio_data = sh_get_mdio, }; +/* free Tx skb function */ +static int sh_eth_tx_free(struct net_device *ndev, bool sent_only) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + struct sh_eth_txdesc *txdesc; + int free_num = 0; + int entry; + bool sent; + + for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) { + entry = mdp->dirty_tx % mdp->num_tx_ring; + txdesc = &mdp->tx_ring[entry]; + sent = !(txdesc->status & cpu_to_le32(TD_TACT)); + if (sent_only && !sent) + break; + /* TACT bit must be checked before all the following reads */ + dma_rmb(); + netif_info(mdp, tx_done, ndev, + "tx entry %d status 0x%08x\n", + entry, le32_to_cpu(txdesc->status)); + /* Free the original skb. */ + if (mdp->tx_skbuff[entry]) { + dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr), + le32_to_cpu(txdesc->len) >> 16, + DMA_TO_DEVICE); + dev_kfree_skb_irq(mdp->tx_skbuff[entry]); + mdp->tx_skbuff[entry] = NULL; + free_num++; + } + txdesc->status = cpu_to_le32(TD_TFP); + if (entry >= mdp->num_tx_ring - 1) + txdesc->status |= cpu_to_le32(TD_TDLE); + + if (sent) { + ndev->stats.tx_packets++; + ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16; + } + } + return free_num; +} + /* free skb and descriptor buffer */ static void sh_eth_ring_free(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); int ringsize, i; + if (mdp->rx_ring) { + for (i = 0; i < mdp->num_rx_ring; i++) { + if (mdp->rx_skbuff[i]) { + struct sh_eth_rxdesc *rxdesc = &mdp->rx_ring[i]; + + dma_unmap_single(&ndev->dev, + le32_to_cpu(rxdesc->addr), + ALIGN(mdp->rx_buf_sz, 32), + DMA_FROM_DEVICE); + } + } + ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring; + dma_free_coherent(NULL, ringsize, mdp->rx_ring, + mdp->rx_desc_dma); + mdp->rx_ring = NULL; + } + /* Free Rx skb ringbuffer */ if (mdp->rx_skbuff) { for (i = 0; i < mdp->num_rx_ring; i++) @@ -1141,27 +1199,18 @@ static void sh_eth_ring_free(struct net_device *ndev) kfree(mdp->rx_skbuff); mdp->rx_skbuff = NULL; - /* Free Tx skb ringbuffer */ - if (mdp->tx_skbuff) { - for (i = 0; i < mdp->num_tx_ring; i++) - dev_kfree_skb(mdp->tx_skbuff[i]); - } - kfree(mdp->tx_skbuff); - mdp->tx_skbuff = NULL; - - if (mdp->rx_ring) { - ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring; - dma_free_coherent(NULL, ringsize, mdp->rx_ring, - mdp->rx_desc_dma); - mdp->rx_ring = NULL; - } - if (mdp->tx_ring) { + sh_eth_tx_free(ndev, false); + ringsize = sizeof(struct sh_eth_txdesc) * mdp->num_tx_ring; dma_free_coherent(NULL, ringsize, mdp->tx_ring, mdp->tx_desc_dma); mdp->tx_ring = NULL; } + + /* Free Tx skb ringbuffer */ + kfree(mdp->tx_skbuff); + mdp->tx_skbuff = NULL; } /* format skb and descriptor buffer */ @@ -1409,43 +1458,6 @@ static void sh_eth_dev_exit(struct net_device *ndev) update_mac_address(ndev); } -/* free Tx skb function */ -static int sh_eth_txfree(struct net_device *ndev) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - struct sh_eth_txdesc *txdesc; - int free_num = 0; - int entry; - - for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) { - entry = mdp->dirty_tx % mdp->num_tx_ring; - txdesc = &mdp->tx_ring[entry]; - if (txdesc->status & cpu_to_le32(TD_TACT)) - break; - /* TACT bit must be checked before all the following reads */ - dma_rmb(); - netif_info(mdp, tx_done, ndev, - "tx entry %d status 0x%08x\n", - entry, le32_to_cpu(txdesc->status)); - /* Free the original skb. */ - if (mdp->tx_skbuff[entry]) { - dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr), - le32_to_cpu(txdesc->len) >> 16, - DMA_TO_DEVICE); - dev_kfree_skb_irq(mdp->tx_skbuff[entry]); - mdp->tx_skbuff[entry] = NULL; - free_num++; - } - txdesc->status = cpu_to_le32(TD_TFP); - if (entry >= mdp->num_tx_ring - 1) - txdesc->status |= cpu_to_le32(TD_TDLE); - - ndev->stats.tx_packets++; - ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16; - } - return free_num; -} - /* Packet receive function */ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) { @@ -1690,7 +1702,7 @@ static void sh_eth_error(struct net_device *ndev, u32 intr_status) intr_status, mdp->cur_tx, mdp->dirty_tx, (u32)ndev->state, edtrr); /* dirty buffer free */ - sh_eth_txfree(ndev); + sh_eth_tx_free(ndev, true); /* SH7712 BUG */ if (edtrr ^ sh_eth_get_edtrr_trns(mdp)) { @@ -1751,7 +1763,7 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev) /* Clear Tx interrupts */ sh_eth_write(ndev, intr_status & cd->tx_check, EESR); - sh_eth_txfree(ndev); + sh_eth_tx_free(ndev, true); netif_wake_queue(ndev); } @@ -2412,7 +2424,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) spin_lock_irqsave(&mdp->lock, flags); if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) { - if (!sh_eth_txfree(ndev)) { + if (!sh_eth_tx_free(ndev, true)) { netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n"); netif_stop_queue(ndev); spin_unlock_irqrestore(&mdp->lock, flags); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 50d28261b6b9..b9cb697b2818 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1371,6 +1371,13 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx) free_cpumask_var(thread_mask); } + if (count > EFX_MAX_RX_QUEUES) { + netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn, + "Reducing number of rx queues from %u to %u.\n", + count, EFX_MAX_RX_QUEUES); + count = EFX_MAX_RX_QUEUES; + } + /* If RSS is requested for the PF *and* VFs then we can't write RSS * table entries that are inaccessible to VFs */ diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index f5e5cd1659a1..29614da91cbf 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -1354,6 +1354,13 @@ static unsigned int ef4_wanted_parallelism(struct ef4_nic *efx) free_cpumask_var(thread_mask); } + if (count > EF4_MAX_RX_QUEUES) { + netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn, + "Reducing number of rx queues from %u to %u.\n", + count, EF4_MAX_RX_QUEUES); + count = EF4_MAX_RX_QUEUES; + } + return count; } diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index e2460a57e4b1..ed0d10f54f26 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1438,8 +1438,6 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT; skb_queue_tail(&dp83640->rx_queue, skb); schedule_delayed_work(&dp83640->ts_work, SKB_TIMESTAMP_TIMEOUT); - } else { - netif_rx_ni(skb); } return true; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 6742070ca676..1326d99771c1 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -798,9 +798,6 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -940,9 +937,6 @@ static struct phy_driver ksphy_driver[] = { .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -952,6 +946,7 @@ static struct phy_driver ksphy_driver[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, .driver_data = &ksz9021_type, + .probe = kszphy_probe, .config_init = ksz9021_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, @@ -971,6 +966,7 @@ static struct phy_driver ksphy_driver[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, .driver_data = &ksz9021_type, + .probe = kszphy_probe, .config_init = ksz9031_config_init, .config_aneg = genphy_config_aneg, .read_status = ksz9031_read_status, @@ -989,9 +985,6 @@ static struct phy_driver ksphy_driver[] = { .config_init = kszphy_config_init, .config_aneg = ksz8873mll_config_aneg, .read_status = ksz8873mll_read_status, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -1003,9 +996,6 @@ static struct phy_driver ksphy_driver[] = { .config_init = kszphy_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -1017,9 +1007,6 @@ static struct phy_driver ksphy_driver[] = { .config_init = kszphy_config_init, .config_aneg = ksz8873mll_config_aneg, .read_status = ksz8873mll_read_status, - .get_sset_count = kszphy_get_sset_count, - .get_strings = kszphy_get_strings, - .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, } }; diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c index 8a40202c0a17..c4f1c363e24b 100644 --- a/drivers/net/usb/ch9200.c +++ b/drivers/net/usb/ch9200.c @@ -254,14 +254,9 @@ static struct sk_buff *ch9200_tx_fixup(struct usbnet *dev, struct sk_buff *skb, tx_overhead = 0x40; len = skb->len; - if (skb_headroom(skb) < tx_overhead) { - struct sk_buff *skb2; - - skb2 = skb_copy_expand(skb, tx_overhead, 0, flags); + if (skb_cow_head(skb, tx_overhead)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } __skb_push(skb, tx_overhead); diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index e221bfcee76b..947bea81d924 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -293,12 +293,9 @@ static struct sk_buff *cx82310_tx_fixup(struct usbnet *dev, struct sk_buff *skb, { int len = skb->len; - if (skb_headroom(skb) < 2) { - struct sk_buff *skb2 = skb_copy_expand(skb, 2, 0, flags); + if (skb_cow_head(skb, 2)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } skb_push(skb, 2); diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index 876f02f4945e..2a2c3edb6bad 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -803,18 +803,12 @@ static netdev_tx_t kaweth_start_xmit(struct sk_buff *skb, } /* We now decide whether we can put our special header into the sk_buff */ - if (skb_cloned(skb) || skb_headroom(skb) < 2) { - /* no such luck - we make our own */ - struct sk_buff *copied_skb; - copied_skb = skb_copy_expand(skb, 2, 0, GFP_ATOMIC); - dev_kfree_skb_irq(skb); - skb = copied_skb; - if (!copied_skb) { - kaweth->stats.tx_errors++; - netif_start_queue(net); - spin_unlock_irq(&kaweth->device_lock); - return NETDEV_TX_OK; - } + if (skb_cow_head(skb, 2)) { + kaweth->stats.tx_errors++; + netif_start_queue(net); + spin_unlock_irq(&kaweth->device_lock); + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; } private_header = (__le16 *)__skb_push(skb, 2); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 9889a70ff4f6..636f48f19d1e 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2607,14 +2607,9 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev, { u32 tx_cmd_a, tx_cmd_b; - if (skb_headroom(skb) < TX_OVERHEAD) { - struct sk_buff *skb2; - - skb2 = skb_copy_expand(skb, TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } if (lan78xx_linearize(skb) < 0) diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 0b17b40d7a4f..190de9a90f73 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2203,13 +2203,9 @@ static struct sk_buff *smsc75xx_tx_fixup(struct usbnet *dev, { u32 tx_cmd_a, tx_cmd_b; - if (skb_headroom(skb) < SMSC75XX_TX_OVERHEAD) { - struct sk_buff *skb2 = - skb_copy_expand(skb, SMSC75XX_TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, SMSC75XX_TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN) | TX_CMD_A_FCS; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 831aa33d078a..5f19fb0f025d 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -2001,13 +2001,13 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev, /* We do not advertise SG, so skbs should be already linearized */ BUG_ON(skb_shinfo(skb)->nr_frags); - if (skb_headroom(skb) < overhead) { - struct sk_buff *skb2 = skb_copy_expand(skb, - overhead, 0, flags); + /* Make writable and expand header space by overhead if required */ + if (skb_cow_head(skb, overhead)) { + /* Must deallocate here as returning NULL to indicate error + * means the skb won't be deallocated in the caller. + */ dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } if (csum) { diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 4a1e9c489f1f..aadfe1d1c37e 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -456,14 +456,9 @@ static struct sk_buff *sr9700_tx_fixup(struct usbnet *dev, struct sk_buff *skb, len = skb->len; - if (skb_headroom(skb) < SR_TX_OVERHEAD) { - struct sk_buff *skb2; - - skb2 = skb_copy_expand(skb, SR_TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, SR_TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } __skb_push(skb, SR_TX_OVERHEAD); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index d6988db1930d..7d909c8183e9 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1128,7 +1128,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) goto nla_put_failure; /* rule only needs to appear once */ - nlh->nlmsg_flags &= NLM_F_EXCL; + nlh->nlmsg_flags |= NLM_F_EXCL; frh = nlmsg_data(nlh); memset(frh, 0, sizeof(*frh)); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 9583a5f58a1d..eeb409c287b8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1316,6 +1316,14 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) table->entries[state] = target; /* + * Don't allow transitions to the deepest state + * if it's quirked off. + */ + if (state == ctrl->npss && + (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) + continue; + + /* * Is this state a useful non-operational state for * higher-power states to autonomously transition to? */ @@ -1387,16 +1395,15 @@ struct nvme_core_quirk_entry { }; static const struct nvme_core_quirk_entry core_quirks[] = { - /* - * Seen on a Samsung "SM951 NVMe SAMSUNG 256GB": using APST causes - * the controller to go out to lunch. It dies when the watchdog - * timer reads CSTS and gets 0xffffffff. - */ { - .vid = 0x144d, - .fr = "BXW75D0Q", + /* + * This Toshiba device seems to die using any APST states. See: + * https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1678184/comments/11 + */ + .vid = 0x1179, + .mn = "THNSF5256GPUK TOSHIBA", .quirks = NVME_QUIRK_NO_APST, - }, + } }; /* match is null-terminated but idstr is space-padded. */ diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 2aa20e3e5675..ab2d6ec7eb5c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -83,6 +83,11 @@ enum nvme_quirks { * APST should not be used. */ NVME_QUIRK_NO_APST = (1 << 4), + + /* + * The deepest sleep state should not be used. + */ + NVME_QUIRK_NO_DEEPEST_PS = (1 << 5), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 26a5fd05fe88..5d309535abbd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -19,6 +19,7 @@ #include <linux/blk-mq-pci.h> #include <linux/cpu.h> #include <linux/delay.h> +#include <linux/dmi.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/genhd.h> @@ -1943,10 +1944,31 @@ static int nvme_dev_map(struct nvme_dev *dev) return -ENODEV; } +static unsigned long check_dell_samsung_bug(struct pci_dev *pdev) +{ + if (pdev->vendor == 0x144d && pdev->device == 0xa802) { + /* + * Several Samsung devices seem to drop off the PCIe bus + * randomly when APST is on and uses the deepest sleep state. + * This has been observed on a Samsung "SM951 NVMe SAMSUNG + * 256GB", a "PM951 NVMe SAMSUNG 512GB", and a "Samsung SSD + * 950 PRO 256GB", but it seems to be restricted to two Dell + * laptops. + */ + if (dmi_match(DMI_SYS_VENDOR, "Dell Inc.") && + (dmi_match(DMI_PRODUCT_NAME, "XPS 15 9550") || + dmi_match(DMI_PRODUCT_NAME, "Precision 5510"))) + return NVME_QUIRK_NO_DEEPEST_PS; + } + + return 0; +} + static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int node, result = -ENOMEM; struct nvme_dev *dev; + unsigned long quirks = id->driver_data; node = dev_to_node(&pdev->dev); if (node == NUMA_NO_NODE) @@ -1978,8 +2000,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (result) goto put_pci; + quirks |= check_dell_samsung_bug(pdev); + result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, - id->driver_data); + quirks); if (result) goto release_pools; diff --git a/drivers/pci/dwc/pcie-hisi.c b/drivers/pci/dwc/pcie-hisi.c index fd66a3199db7..cf9d6a9d9fd4 100644 --- a/drivers/pci/dwc/pcie-hisi.c +++ b/drivers/pci/dwc/pcie-hisi.c @@ -380,9 +380,13 @@ struct pci_ecam_ops hisi_pcie_platform_ops = { static const struct of_device_id hisi_pcie_almost_ecam_of_match[] = { { - .compatible = "hisilicon,pcie-almost-ecam", + .compatible = "hisilicon,hip06-pcie-ecam", .data = (void *) &hisi_pcie_platform_ops, }, + { + .compatible = "hisilicon,hip07-pcie-ecam", + .data = (void *) &hisi_pcie_platform_ops, + }, {}, }; diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c index 56bce1908be2..85812521b6ba 100644 --- a/drivers/power/avs/rockchip-io-domain.c +++ b/drivers/power/avs/rockchip-io-domain.c @@ -43,6 +43,10 @@ #define RK3288_SOC_CON2_FLASH0 BIT(7) #define RK3288_SOC_FLASH_SUPPLY_NUM 2 +#define RK3328_SOC_CON4 0x410 +#define RK3328_SOC_CON4_VCCIO2 BIT(7) +#define RK3328_SOC_VCCIO2_SUPPLY_NUM 1 + #define RK3368_SOC_CON15 0x43c #define RK3368_SOC_CON15_FLASH0 BIT(14) #define RK3368_SOC_FLASH_SUPPLY_NUM 2 @@ -166,6 +170,25 @@ static void rk3288_iodomain_init(struct rockchip_iodomain *iod) dev_warn(iod->dev, "couldn't update flash0 ctrl\n"); } +static void rk3328_iodomain_init(struct rockchip_iodomain *iod) +{ + int ret; + u32 val; + + /* if no vccio2 supply we should leave things alone */ + if (!iod->supplies[RK3328_SOC_VCCIO2_SUPPLY_NUM].reg) + return; + + /* + * set vccio2 iodomain to also use this framework + * instead of a special gpio. + */ + val = RK3328_SOC_CON4_VCCIO2 | (RK3328_SOC_CON4_VCCIO2 << 16); + ret = regmap_write(iod->grf, RK3328_SOC_CON4, val); + if (ret < 0) + dev_warn(iod->dev, "couldn't update vccio2 vsel ctrl\n"); +} + static void rk3368_iodomain_init(struct rockchip_iodomain *iod) { int ret; @@ -247,6 +270,20 @@ static const struct rockchip_iodomain_soc_data soc_data_rk3288 = { .init = rk3288_iodomain_init, }; +static const struct rockchip_iodomain_soc_data soc_data_rk3328 = { + .grf_offset = 0x410, + .supply_names = { + "vccio1", + "vccio2", + "vccio3", + "vccio4", + "vccio5", + "vccio6", + "pmuio", + }, + .init = rk3328_iodomain_init, +}; + static const struct rockchip_iodomain_soc_data soc_data_rk3368 = { .grf_offset = 0x900, .supply_names = { @@ -312,6 +349,10 @@ static const struct of_device_id rockchip_iodomain_match[] = { .data = (void *)&soc_data_rk3288 }, { + .compatible = "rockchip,rk3328-io-voltage-domain", + .data = (void *)&soc_data_rk3328 + }, + { .compatible = "rockchip,rk3368-io-voltage-domain", .data = (void *)&soc_data_rk3368 }, diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index 776b34396144..0a16cf4bed39 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -291,18 +291,6 @@ config ARMADA_THERMAL Enable this option if you want to have support for thermal management controller present in Armada 370 and Armada XP SoC. -config DB8500_CPUFREQ_COOLING - tristate "DB8500 cpufreq cooling" - depends on ARCH_U8500 || COMPILE_TEST - depends on HAS_IOMEM - depends on CPU_THERMAL - default y - help - Adds DB8500 cpufreq cooling devices, and these cooling devices can be - bound to thermal zone trip points. When a trip point reached, the - bound cpufreq cooling device turns active to set CPU frequency low to - cool down the CPU. - config INTEL_POWERCLAMP tristate "Intel PowerClamp idle injection driver" depends on THERMAL diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile index 7adae2029355..c2372f10dae5 100644 --- a/drivers/thermal/Makefile +++ b/drivers/thermal/Makefile @@ -41,7 +41,6 @@ obj-$(CONFIG_TANGO_THERMAL) += tango_thermal.o obj-$(CONFIG_IMX_THERMAL) += imx_thermal.o obj-$(CONFIG_MAX77620_THERMAL) += max77620_thermal.o obj-$(CONFIG_QORIQ_THERMAL) += qoriq_thermal.o -obj-$(CONFIG_DB8500_CPUFREQ_COOLING) += db8500_cpufreq_cooling.o obj-$(CONFIG_INTEL_POWERCLAMP) += intel_powerclamp.o obj-$(CONFIG_X86_PKG_TEMP_THERMAL) += x86_pkg_temp_thermal.o obj-$(CONFIG_INTEL_SOC_DTS_IOSF_CORE) += intel_soc_dts_iosf.o diff --git a/drivers/thermal/db8500_cpufreq_cooling.c b/drivers/thermal/db8500_cpufreq_cooling.c deleted file mode 100644 index e58bd0b658b5..000000000000 --- a/drivers/thermal/db8500_cpufreq_cooling.c +++ /dev/null @@ -1,105 +0,0 @@ -/* - * db8500_cpufreq_cooling.c - DB8500 cpufreq works as cooling device. - * - * Copyright (C) 2012 ST-Ericsson - * Copyright (C) 2012 Linaro Ltd. - * - * Author: Hongbo Zhang <hongbo.zhang@linaro.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#include <linux/cpu_cooling.h> -#include <linux/err.h> -#include <linux/module.h> -#include <linux/of.h> -#include <linux/platform_device.h> -#include <linux/slab.h> - -static int db8500_cpufreq_cooling_probe(struct platform_device *pdev) -{ - struct thermal_cooling_device *cdev; - - cdev = cpufreq_cooling_register(cpu_present_mask); - if (IS_ERR(cdev)) { - int ret = PTR_ERR(cdev); - - if (ret != -EPROBE_DEFER) - dev_err(&pdev->dev, - "Failed to register cooling device %d\n", - ret); - - return ret; - } - - platform_set_drvdata(pdev, cdev); - - dev_info(&pdev->dev, "Cooling device registered: %s\n", cdev->type); - - return 0; -} - -static int db8500_cpufreq_cooling_remove(struct platform_device *pdev) -{ - struct thermal_cooling_device *cdev = platform_get_drvdata(pdev); - - cpufreq_cooling_unregister(cdev); - - return 0; -} - -static int db8500_cpufreq_cooling_suspend(struct platform_device *pdev, - pm_message_t state) -{ - return -ENOSYS; -} - -static int db8500_cpufreq_cooling_resume(struct platform_device *pdev) -{ - return -ENOSYS; -} - -#ifdef CONFIG_OF -static const struct of_device_id db8500_cpufreq_cooling_match[] = { - { .compatible = "stericsson,db8500-cpufreq-cooling" }, - {}, -}; -MODULE_DEVICE_TABLE(of, db8500_cpufreq_cooling_match); -#endif - -static struct platform_driver db8500_cpufreq_cooling_driver = { - .driver = { - .name = "db8500-cpufreq-cooling", - .of_match_table = of_match_ptr(db8500_cpufreq_cooling_match), - }, - .probe = db8500_cpufreq_cooling_probe, - .suspend = db8500_cpufreq_cooling_suspend, - .resume = db8500_cpufreq_cooling_resume, - .remove = db8500_cpufreq_cooling_remove, -}; - -static int __init db8500_cpufreq_cooling_init(void) -{ - return platform_driver_register(&db8500_cpufreq_cooling_driver); -} - -static void __exit db8500_cpufreq_cooling_exit(void) -{ - platform_driver_unregister(&db8500_cpufreq_cooling_driver); -} - -/* Should be later than db8500_cpufreq_register */ -late_initcall(db8500_cpufreq_cooling_init); -module_exit(db8500_cpufreq_cooling_exit); - -MODULE_AUTHOR("Hongbo Zhang <hongbo.zhang@stericsson.com>"); -MODULE_DESCRIPTION("DB8500 cpufreq cooling driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index d7efcb632f7d..002f1ce22bd0 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -297,14 +297,15 @@ static int pwm_backlight_probe(struct platform_device *pdev) } /* - * If the GPIO is configured as input, change the direction to output - * and set the GPIO as active. + * If the GPIO is not known to be already configured as output, that + * is, if gpiod_get_direction returns either GPIOF_DIR_IN or -EINVAL, + * change the direction to output and set the GPIO as active. * Do not force the GPIO to active when it was already output as it * could cause backlight flickering or we would enable the backlight too * early. Leave the decision of the initial backlight state for later. */ if (pb->enable_gpio && - gpiod_get_direction(pb->enable_gpio) == GPIOF_DIR_IN) + gpiod_get_direction(pb->enable_gpio) != GPIOF_DIR_OUT) gpiod_direction_output(pb->enable_gpio, 1); pb->power_supply = devm_regulator_get(&pdev->dev, "power"); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index cc93ba4da9b5..27bc360c7ffd 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -1015,6 +1015,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile) return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; } +static bool +cifs_can_echo(struct TCP_Server_Info *server) +{ + if (server->tcpStatus == CifsGood) + return true; + + return false; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1049,6 +1058,7 @@ struct smb_version_operations smb1_operations = { .get_dfs_refer = CIFSGetDFSRefer, .qfs_tcon = cifs_qfs_tcon, .is_path_accessible = cifs_is_path_accessible, + .can_echo = cifs_can_echo, .query_path_info = cifs_query_path_info, .query_file_info = cifs_query_file_info, .get_srv_inum = cifs_get_srv_inum, diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index cbeeda1e94a2..d86031b6ad79 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2489,7 +2489,7 @@ bool nfsd4_spo_must_allow(struct svc_rqst *rqstp) int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op) { - if (op->opnum == OP_ILLEGAL) + if (op->opnum == OP_ILLEGAL || op->status == nfserr_notsupp) return op_encode_hdr_size * sizeof(__be32); BUG_ON(OPDESC(op)->op_rsize_bop == NULL); diff --git a/fs/nsfs.c b/fs/nsfs.c index 1656843e87d2..323f492e0822 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -91,6 +91,7 @@ slow: return ERR_PTR(-ENOMEM); } d_instantiate(dentry, inode); + dentry->d_flags |= DCACHE_RCUACCESS; dentry->d_fsdata = (void *)ns->ops; d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry); if (d) { diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 1e712a364680..718b749fa11a 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -32,6 +32,7 @@ #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/random.h> +#include <linux/ctype.h> #include "ubifs.h" static DEFINE_SPINLOCK(dbg_lock); @@ -286,8 +287,10 @@ void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode) break; } - pr_err("\t%d: %s (%s)\n", - count++, dent->name, get_dent_type(dent->type)); + pr_err("\t%d: inode %llu, type %s, len %d\n", + count++, (unsigned long long) le64_to_cpu(dent->inum), + get_dent_type(dent->type), + le16_to_cpu(dent->nlen)); fname_name(&nm) = dent->name; fname_len(&nm) = le16_to_cpu(dent->nlen); @@ -464,7 +467,8 @@ void ubifs_dump_node(const struct ubifs_info *c, const void *node) pr_err("(bad name length, not printing, bad or corrupted node)"); else { for (i = 0; i < nlen && dent->name[i]; i++) - pr_cont("%c", dent->name[i]); + pr_cont("%c", isprint(dent->name[i]) ? + dent->name[i] : '?'); } pr_cont("\n"); diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 30825d882aa9..b777bddaa1dd 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -606,8 +606,8 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) } while (1) { - dbg_gen("feed '%s', ino %llu, new f_pos %#x", - dent->name, (unsigned long long)le64_to_cpu(dent->inum), + dbg_gen("ino %llu, new f_pos %#x", + (unsigned long long)le64_to_cpu(dent->inum), key_hash_flash(c, &dent->key)); ubifs_assert(le64_to_cpu(dent->ch.sqnum) > ubifs_inode(dir)->creat_sqnum); @@ -748,6 +748,11 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, goto out_fname; lock_2_inodes(dir, inode); + + /* Handle O_TMPFILE corner case, it is allowed to link a O_TMPFILE. */ + if (inode->i_nlink == 0) + ubifs_delete_orphan(c, inode->i_ino); + inc_nlink(inode); ihold(inode); inode->i_ctime = ubifs_current_time(inode); @@ -768,6 +773,8 @@ out_cancel: dir->i_size -= sz_change; dir_ui->ui_size = dir->i_size; drop_nlink(inode); + if (inode->i_nlink == 0) + ubifs_add_orphan(c, inode->i_ino); unlock_2_inodes(dir, inode); ubifs_release_budget(c, &req); iput(inode); @@ -1068,8 +1075,10 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, } err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); - if (err) + if (err) { + kfree(dev); goto out_budg; + } sz_change = CALC_DENT_SIZE(fname_len(&nm)); @@ -1316,9 +1325,6 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, unsigned int uninitialized_var(saved_nlink); struct fscrypt_name old_nm, new_nm; - if (flags & ~RENAME_NOREPLACE) - return -EINVAL; - /* * Budget request settings: deletion direntry, new direntry, removing * the old inode, and changing old and new parent directory inodes. diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index 1d4f365d8f03..f6d9af3efa45 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -166,6 +166,16 @@ static inline struct ahash_instance *ahash_alloc_instance( return crypto_alloc_instance2(name, alg, ahash_instance_headroom()); } +static inline void ahash_request_complete(struct ahash_request *req, int err) +{ + req->base.complete(&req->base, err); +} + +static inline u32 ahash_request_flags(struct ahash_request *req) +{ + return req->base.flags; +} + static inline struct crypto_ahash *crypto_spawn_ahash( struct crypto_ahash_spawn *spawn) { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 87165f06a307..a5ce0bbeadb5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -120,6 +120,13 @@ struct cpufreq_policy { bool fast_switch_possible; bool fast_switch_enabled; + /* + * Preferred average time interval between consecutive invocations of + * the driver to set the frequency for this policy. To be set by the + * scaling driver (0, which is the default, means no preference). + */ + unsigned int transition_delay_us; + /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ unsigned int cached_target_freq; int cached_resolved_idx; diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index e0acb0e5243b..6c220e4ebb6b 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -27,6 +27,7 @@ #define DEVFREQ_POSTCHANGE (1) struct devfreq; +struct devfreq_governor; /** * struct devfreq_dev_status - Data given from devfreq user device to @@ -101,35 +102,6 @@ struct devfreq_dev_profile { }; /** - * struct devfreq_governor - Devfreq policy governor - * @node: list node - contains registered devfreq governors - * @name: Governor's name - * @immutable: Immutable flag for governor. If the value is 1, - * this govenror is never changeable to other governor. - * @get_target_freq: Returns desired operating frequency for the device. - * Basically, get_target_freq will run - * devfreq_dev_profile.get_dev_status() to get the - * status of the device (load = busy_time / total_time). - * If no_central_polling is set, this callback is called - * only with update_devfreq() notified by OPP. - * @event_handler: Callback for devfreq core framework to notify events - * to governors. Events include per device governor - * init and exit, opp changes out of devfreq, suspend - * and resume of per device devfreq during device idle. - * - * Note that the callbacks are called with devfreq->lock locked by devfreq. - */ -struct devfreq_governor { - struct list_head node; - - const char name[DEVFREQ_NAME_LEN]; - const unsigned int immutable; - int (*get_target_freq)(struct devfreq *this, unsigned long *freq); - int (*event_handler)(struct devfreq *devfreq, - unsigned int event, void *data); -}; - -/** * struct devfreq - Device devfreq structure * @node: list node - contains the devices with devfreq that have been * registered. diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index aab032a6ae61..97ca105347a6 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -53,7 +53,7 @@ struct sdio_func { unsigned int state; /* function state */ #define SDIO_STATE_PRESENT (1<<0) /* present in sysfs */ - u8 tmpbuf[4]; /* DMA:able scratch buffer */ + u8 *tmpbuf; /* DMA:able scratch buffer */ unsigned num_info; /* number of info strings */ const char **info; /* info strings */ diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 5339ed5bd6f9..9b6abe632587 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -20,6 +20,7 @@ /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ #define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ +#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ diff --git a/include/linux/tick.h b/include/linux/tick.h index a04fea19676f..fe01e68bf520 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -117,6 +117,7 @@ extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern ktime_t tick_nohz_get_sleep_length(void); +extern unsigned long tick_nohz_get_idle_calls(void); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); #else /* !CONFIG_NO_HZ_COMMON */ diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index 85bbb1799df3..d496c02e14bc 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -35,7 +35,7 @@ #define RTF_PREF(pref) ((pref) << 27) #define RTF_PREF_MASK 0x18000000 -#define RTF_PCPU 0x40000000 +#define RTF_PCPU 0x40000000 /* read-only: can not be set by user */ #define RTF_LOCAL 0x80000000 diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7af0dcc5d755..821f9e807de5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -617,6 +617,14 @@ static void fixup_bpf_calls(struct bpf_prog *prog) if (insn->imm == BPF_FUNC_xdp_adjust_head) prog->xdp_adjust_head = 1; if (insn->imm == BPF_FUNC_tail_call) { + /* If we tail call into other programs, we + * cannot make any assumptions since they + * can be replaced dynamically during runtime + * in the program array. + */ + prog->cb_access = 1; + prog->xdp_adjust_head = 1; + /* mark bpf_tail_call as different opcode * to avoid conditional branch in * interpeter for every normal call diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index d052947fe785..e2d356dd7581 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -98,7 +98,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) int ncpus, v, vecs_to_assign, vecs_per_node; /* Spread the vectors per node */ - vecs_per_node = (affv - curvec) / nodes; + vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes; /* Get the cpus on this node which are in the mask */ cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n)); diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index c2b88490d857..c08fbd2f5ba9 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -46,13 +46,13 @@ enum { (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) /* - * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text, + * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text, * .data and .bss to fit in required 32MB limit for the kernel. With - * PROVE_LOCKING we could go over this limit and cause system boot-up problems. + * CONFIG_LOCKDEP we could go over this limit and cause system boot-up problems. * So, reduce the static allocations for lockdeps related structures so that * everything fits in current required size limit. */ -#ifdef CONFIG_PROVE_LOCKING_SMALL +#ifdef CONFIG_LOCKDEP_SMALL /* * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies * we track. diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 54c577578da6..76877a62b5fa 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -61,6 +61,11 @@ struct sugov_cpu { unsigned long util; unsigned long max; unsigned int flags; + + /* The field below is for single-CPU policies only. */ +#ifdef CONFIG_NO_HZ_COMMON + unsigned long saved_idle_calls; +#endif }; static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu); @@ -93,22 +98,23 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, { struct cpufreq_policy *policy = sg_policy->policy; + if (sg_policy->next_freq == next_freq) + return; + + if (sg_policy->next_freq > next_freq) + next_freq = (sg_policy->next_freq + next_freq) >> 1; + + sg_policy->next_freq = next_freq; sg_policy->last_freq_update_time = time; if (policy->fast_switch_enabled) { - if (sg_policy->next_freq == next_freq) { - trace_cpu_frequency(policy->cur, smp_processor_id()); - return; - } - sg_policy->next_freq = next_freq; next_freq = cpufreq_driver_fast_switch(policy, next_freq); if (next_freq == CPUFREQ_ENTRY_INVALID) return; policy->cur = next_freq; trace_cpu_frequency(next_freq, smp_processor_id()); - } else if (sg_policy->next_freq != next_freq) { - sg_policy->next_freq = next_freq; + } else { sg_policy->work_in_progress = true; irq_work_queue(&sg_policy->irq_work); } @@ -192,6 +198,19 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util, sg_cpu->iowait_boost >>= 1; } +#ifdef CONFIG_NO_HZ_COMMON +static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) +{ + unsigned long idle_calls = tick_nohz_get_idle_calls(); + bool ret = idle_calls == sg_cpu->saved_idle_calls; + + sg_cpu->saved_idle_calls = idle_calls; + return ret; +} +#else +static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } +#endif /* CONFIG_NO_HZ_COMMON */ + static void sugov_update_single(struct update_util_data *hook, u64 time, unsigned int flags) { @@ -200,6 +219,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, struct cpufreq_policy *policy = sg_policy->policy; unsigned long util, max; unsigned int next_f; + bool busy; sugov_set_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; @@ -207,40 +227,37 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, if (!sugov_should_update_freq(sg_policy, time)) return; + busy = sugov_cpu_is_busy(sg_cpu); + if (flags & SCHED_CPUFREQ_RT_DL) { next_f = policy->cpuinfo.max_freq; } else { sugov_get_util(&util, &max); sugov_iowait_boost(sg_cpu, &util, &max); next_f = get_next_freq(sg_policy, util, max); + /* + * Do not reduce the frequency if the CPU has not been idle + * recently, as the reduction is likely to be premature then. + */ + if (busy && next_f < sg_policy->next_freq) + next_f = sg_policy->next_freq; } sugov_update_commit(sg_policy, time, next_f); } -static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, - unsigned long util, unsigned long max, - unsigned int flags) +static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; - unsigned int max_f = policy->cpuinfo.max_freq; u64 last_freq_update_time = sg_policy->last_freq_update_time; + unsigned long util = 0, max = 1; unsigned int j; - if (flags & SCHED_CPUFREQ_RT_DL) - return max_f; - - sugov_iowait_boost(sg_cpu, &util, &max); - for_each_cpu(j, policy->cpus) { - struct sugov_cpu *j_sg_cpu; + struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); unsigned long j_util, j_max; s64 delta_ns; - if (j == smp_processor_id()) - continue; - - j_sg_cpu = &per_cpu(sugov_cpu, j); /* * If the CPU utilization was last updated before the previous * frequency update and the time elapsed between the last update @@ -254,7 +271,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, continue; } if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL) - return max_f; + return policy->cpuinfo.max_freq; j_util = j_sg_cpu->util; j_max = j_sg_cpu->max; @@ -289,7 +306,11 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, sg_cpu->last_update = time; if (sugov_should_update_freq(sg_policy, time)) { - next_f = sugov_next_freq_shared(sg_cpu, util, max, flags); + if (flags & SCHED_CPUFREQ_RT_DL) + next_f = sg_policy->policy->cpuinfo.max_freq; + else + next_f = sugov_next_freq_shared(sg_cpu); + sugov_update_commit(sg_policy, time, next_f); } @@ -473,7 +494,6 @@ static int sugov_init(struct cpufreq_policy *policy) { struct sugov_policy *sg_policy; struct sugov_tunables *tunables; - unsigned int lat; int ret = 0; /* State should be equivalent to EXIT */ @@ -512,10 +532,16 @@ static int sugov_init(struct cpufreq_policy *policy) goto stop_kthread; } - tunables->rate_limit_us = LATENCY_MULTIPLIER; - lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC; - if (lat) - tunables->rate_limit_us *= lat; + if (policy->transition_delay_us) { + tunables->rate_limit_us = policy->transition_delay_us; + } else { + unsigned int lat; + + tunables->rate_limit_us = LATENCY_MULTIPLIER; + lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC; + if (lat) + tunables->rate_limit_us *= lat; + } policy->governor_data = sg_policy; sg_policy->tunables = tunables; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 7fe53be86077..64c97fc130c4 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -993,6 +993,18 @@ ktime_t tick_nohz_get_sleep_length(void) return ts->sleep_length; } +/** + * tick_nohz_get_idle_calls - return the current idle calls counter value + * + * Called from the schedutil frequency scaling governor in scheduler context. + */ +unsigned long tick_nohz_get_idle_calls(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + return ts->idle_calls; +} + static void tick_nohz_account_idle_ticks(struct tick_sched *ts) { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 27bb2e61276e..dd3e91d68dc7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5566,6 +5566,15 @@ static void clear_ftrace_pids(struct trace_array *tr) trace_free_pid_list(pid_list); } +void ftrace_clear_pids(struct trace_array *tr) +{ + mutex_lock(&ftrace_lock); + + clear_ftrace_pids(tr); + + mutex_unlock(&ftrace_lock); +} + static void ftrace_pid_reset(struct trace_array *tr) { mutex_lock(&ftrace_lock); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 54e7a90db848..ca47a4fa2986 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3405,11 +3405,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); int ring_buffer_iter_empty(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + struct buffer_page *head_page; + struct buffer_page *commit_page; + unsigned commit; cpu_buffer = iter->cpu_buffer; - return iter->head_page == cpu_buffer->commit_page && - iter->head == rb_commit_index(cpu_buffer); + /* Remember, trace recording is off when iterator is in use */ + reader = cpu_buffer->reader_page; + head_page = cpu_buffer->head_page; + commit_page = cpu_buffer->commit_page; + commit = rb_page_commit(commit_page); + + return ((iter->head_page == commit_page && iter->head == commit) || + (iter->head_page == reader && commit_page == head_page && + head_page->read == commit && + iter->head == rb_page_commit(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f35109514a01..0ad75e9698f6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6733,11 +6733,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash, return ret; out_reg: - ret = register_ftrace_function_probe(glob, ops, count); + ret = alloc_snapshot(&global_trace); + if (ret < 0) + goto out; - if (ret >= 0) - alloc_snapshot(&global_trace); + ret = register_ftrace_function_probe(glob, ops, count); + out: return ret < 0 ? ret : 0; } @@ -7402,6 +7404,7 @@ static int instance_rmdir(const char *name) tracing_set_nop(tr); event_trace_del_tracer(tr); + ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); tracefs_remove_recursive(tr->dir); free_trace_buffers(tr); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ae1cce91fead..d19d52d600d6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -896,6 +896,7 @@ int using_ftrace_ops_list_func(void); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d_tracer); +void ftrace_clear_pids(struct trace_array *tr); #else static inline int ftrace_trace_task(struct trace_array *tr) { @@ -914,6 +915,7 @@ ftrace_init_global_array_ops(struct trace_array *tr) { } static inline void ftrace_reset_array_ops(struct trace_array *tr) { } static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { } static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { } +static inline void ftrace_clear_pids(struct trace_array *tr) { } /* ftace_func_t type is not defined, use macro instead of static inline */ #define ftrace_init_array_ops(tr, func) do { } while (0) #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 97d62c2da6c2..fa16c0f82d6e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1103,9 +1103,6 @@ config PROVE_LOCKING For more details, see Documentation/locking/lockdep-design.txt. -config PROVE_LOCKING_SMALL - bool - config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT @@ -1114,6 +1111,9 @@ config LOCKDEP select KALLSYMS select KALLSYMS_ALL +config LOCKDEP_SMALL + bool + config LOCK_STAT bool "Lock usage statistics" depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT diff --git a/mm/migrate.c b/mm/migrate.c index ed97c2c14fa8..738f1d5f8350 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -184,9 +184,9 @@ void putback_movable_pages(struct list_head *l) unlock_page(page); put_page(page); } else { - putback_lru_page(page); dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); + putback_lru_page(page); } } } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f3d603cef2c0..07efbc3a8656 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1090,10 +1090,10 @@ static void free_pcppages_bulk(struct zone *zone, int count, { int migratetype = 0; int batch_free = 0; - unsigned long nr_scanned, flags; + unsigned long nr_scanned; bool isolated_pageblocks; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) @@ -1142,7 +1142,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, trace_mm_page_pcpu_drain(page, 0, mt); } while (--count && --batch_free && !list_empty(list)); } - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static void free_one_page(struct zone *zone, @@ -1150,9 +1150,8 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype) { - unsigned long nr_scanned, flags; - spin_lock_irqsave(&zone->lock, flags); - __count_vm_events(PGFREE, 1 << order); + unsigned long nr_scanned; + spin_lock(&zone->lock); nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED); if (nr_scanned) __mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned); @@ -1162,7 +1161,7 @@ static void free_one_page(struct zone *zone, migratetype = get_pfnblock_migratetype(page, pfn); } __free_one_page(page, pfn, zone, order, migratetype); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); } static void __meminit __init_single_page(struct page *page, unsigned long pfn, @@ -1240,6 +1239,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) static void __free_pages_ok(struct page *page, unsigned int order) { + unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); @@ -1247,7 +1247,10 @@ static void __free_pages_ok(struct page *page, unsigned int order) return; migratetype = get_pfnblock_migratetype(page, pfn); + local_irq_save(flags); + __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, pfn, order, migratetype); + local_irq_restore(flags); } static void __init __free_pages_boot_core(struct page *page, unsigned int order) @@ -2219,9 +2222,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, int migratetype, bool cold) { int i, alloced = 0; - unsigned long flags; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype); if (unlikely(page == NULL)) @@ -2257,7 +2259,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * pages added to the pcp list. */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); return alloced; } @@ -2485,20 +2487,17 @@ void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; + unsigned long flags; unsigned long pfn = page_to_pfn(page); int migratetype; - if (in_interrupt()) { - __free_pages_ok(page, 0); - return; - } - if (!free_pcp_prepare(page)) return; migratetype = get_pfnblock_migratetype(page, pfn); set_pcppage_migratetype(page, migratetype); - preempt_disable(); + local_irq_save(flags); + __count_vm_event(PGFREE); /* * We only track unmovable, reclaimable and movable on pcp lists. @@ -2515,7 +2514,6 @@ void free_hot_cold_page(struct page *page, bool cold) migratetype = MIGRATE_MOVABLE; } - __count_vm_event(PGFREE); pcp = &this_cpu_ptr(zone->pageset)->pcp; if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); @@ -2529,7 +2527,7 @@ void free_hot_cold_page(struct page *page, bool cold) } out: - preempt_enable(); + local_irq_restore(flags); } /* @@ -2654,8 +2652,6 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, { struct page *page; - VM_BUG_ON(in_interrupt()); - do { if (list_empty(list)) { pcp->count += rmqueue_bulk(zone, 0, @@ -2686,8 +2682,9 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct list_head *list; bool cold = ((gfp_flags & __GFP_COLD) != 0); struct page *page; + unsigned long flags; - preempt_disable(); + local_irq_save(flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; page = __rmqueue_pcplist(zone, migratetype, cold, pcp, list); @@ -2695,7 +2692,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone); } - preempt_enable(); + local_irq_restore(flags); return page; } @@ -2711,7 +2708,7 @@ struct page *rmqueue(struct zone *preferred_zone, unsigned long flags; struct page *page; - if (likely(order == 0) && !in_interrupt()) { + if (likely(order == 0)) { page = rmqueue_pcplist(preferred_zone, zone, order, gfp_flags, migratetype); goto out; diff --git a/mm/vmstat.c b/mm/vmstat.c index 809025ed97ea..5a4f5c5a31e8 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1768,8 +1768,7 @@ void __init init_mm_internals(void) { int ret __maybe_unused; - mm_percpu_wq = alloc_workqueue("mm_percpu_wq", - WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0); #ifdef CONFIG_SMP ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead", diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 9424673009c1..29be2466970c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -105,15 +105,21 @@ static void queue_process(struct work_struct *work) while ((skb = skb_dequeue(&npinfo->txq))) { struct net_device *dev = skb->dev; struct netdev_queue *txq; + unsigned int q_index; if (!netif_device_present(dev) || !netif_running(dev)) { kfree_skb(skb); continue; } - txq = skb_get_tx_queue(dev, skb); - local_irq_save(flags); + /* check if skb->queue_mapping is still valid */ + q_index = skb_get_queue_mapping(skb); + if (unlikely(q_index >= dev->real_num_tx_queues)) { + q_index = q_index % dev->real_num_tx_queues; + skb_set_queue_mapping(skb, q_index); + } + txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9f781092fda9..f86bf69cfb8d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3082,22 +3082,32 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, if (sg && csum && (mss != GSO_BY_FRAGS)) { if (!(features & NETIF_F_GSO_PARTIAL)) { struct sk_buff *iter; + unsigned int frag_len; if (!list_skb || !net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) goto normal; - /* Split the buffer at the frag_list pointer. - * This is based on the assumption that all - * buffers in the chain excluding the last - * containing the same amount of data. + /* If we get here then all the required + * GSO features except frag_list are supported. + * Try to split the SKB to multiple GSO SKBs + * with no frag_list. + * Currently we can do that only when the buffers don't + * have a linear part and all the buffers except + * the last are of the same length. */ + frag_len = list_skb->len; skb_walk_frags(head_skb, iter) { + if (frag_len != iter->len && iter->next) + goto normal; if (skb_headlen(iter)) goto normal; len -= iter->len; } + + if (len != frag_len) + goto normal; } /* GSO partial only requires that we trim off any excess that @@ -3807,6 +3817,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; + serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk->sk_protocol == IPPROTO_TCP && diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ebd953bc5607..1d46d05efb0f 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -488,16 +488,15 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk, return false; /* Support IP_PKTINFO on tstamp packets if requested, to correlate - * timestamp with egress dev. Not possible for packets without dev + * timestamp with egress dev. Not possible for packets without iif * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). */ - if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) || - (!skb->dev)) + info = PKTINFO_SKB_CB(skb); + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) || + !info->ipi_ifindex) return false; - info = PKTINFO_SKB_CB(skb); info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr; - info->ipi_ifindex = skb->dev->ifindex; return true; } @@ -591,6 +590,7 @@ static bool setsockopt_needs_rtnl(int optname) case MCAST_LEAVE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_UNBLOCK_SOURCE: + case IP_ROUTER_ALERT: return true; } return false; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c0317c940bcd..b036e85e093b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1278,7 +1278,7 @@ static void mrtsock_destruct(struct sock *sk) struct net *net = sock_net(sk); struct mr_table *mrt; - rtnl_lock(); + ASSERT_RTNL(); ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; @@ -1289,7 +1289,6 @@ static void mrtsock_destruct(struct sock *sk) mroute_clean_tables(mrt, false); } } - rtnl_unlock(); } /* Socket options and virtual interface manipulation. The whole @@ -1353,13 +1352,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, if (sk != rcu_access_pointer(mrt->mroute_sk)) { ret = -EACCES; } else { - /* We need to unlock here because mrtsock_destruct takes - * care of rtnl itself and we can't change that due to - * the IP_ROUTER_ALERT setsockopt which runs without it. - */ - rtnl_unlock(); ret = ip_ra_control(sk, 0, NULL); - goto out; + goto out_unlock; } break; case MRT_ADD_VIF: @@ -1470,7 +1464,6 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, } out_unlock: rtnl_unlock(); -out: return ret; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8119e1f66e03..9d943974de2b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -682,7 +682,9 @@ static void raw_close(struct sock *sk, long timeout) /* * Raw sockets may have direct kernel references. Kill them. */ + rtnl_lock(); ip_ra_control(sk, 0, NULL); + rtnl_unlock(); sk_common_release(sk); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index eec27f87efac..e011122ebd43 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -405,9 +405,6 @@ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr) * At one point, excluding local errors was a quick test to identify icmp/icmp6 * errors. This is no longer true, but the test remained, so the v6 stack, * unlike v4, also honors cmsg requests on all wifi and timestamp errors. - * - * Timestamp code paths do not initialize the fields expected by cmsg: - * the PKTINFO fields in skb->cb[]. Fill those in here. */ static bool ip6_datagram_support_cmsg(struct sk_buff *skb, struct sock_exterr_skb *serr) @@ -419,14 +416,9 @@ static bool ip6_datagram_support_cmsg(struct sk_buff *skb, if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) return false; - if (!skb->dev) + if (!IP6CB(skb)->iif) return false; - if (skb->protocol == htons(ETH_P_IPV6)) - IP6CB(skb)->iif = skb->dev->ifindex; - else - PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex; - return true; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 275cac628a95..25192a3b0cd7 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -388,7 +388,6 @@ looped_back: icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); - kfree_skb(skb); return -1; } diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index aacfb4bce153..c45b12b4431c 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -122,11 +122,14 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs)); /* * RFC4291 2.5.3 + * The loopback address must not be used as the source address in IPv6 + * packets that are sent outside of a single node. [..] * A packet received on an interface with a destination address * of loopback must be dropped. */ - if (!(dev->flags & IFF_LOOPBACK) && - ipv6_addr_loopback(&hdr->daddr)) + if ((ipv6_addr_loopback(&hdr->saddr) || + ipv6_addr_loopback(&hdr->daddr)) && + !(dev->flags & IFF_LOOPBACK)) goto err; /* RFC4291 Errata ID: 3480 diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 6ba6c900ebcf..bf34d0950752 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -774,7 +774,8 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) +static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, + struct list_head *head) { struct mif_device *v; struct net_device *dev; @@ -820,7 +821,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) dev->ifindex, &in6_dev->cnf); } - if (v->flags & MIFF_REGISTER) + if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); dev_put(dev); @@ -1331,7 +1332,6 @@ static int ip6mr_device_event(struct notifier_block *this, struct mr6_table *mrt; struct mif_device *v; int ct; - LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; @@ -1340,10 +1340,9 @@ static int ip6mr_device_event(struct notifier_block *this, v = &mrt->vif6_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(mrt, ct, &list); + mif6_delete(mrt, ct, 1, NULL); } } - unregister_netdevice_many(&list); return NOTIFY_DONE; } @@ -1552,7 +1551,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all) for (i = 0; i < mrt->maxvif; i++) { if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC)) continue; - mif6_delete(mrt, i, &list); + mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); @@ -1707,7 +1706,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(mrt, mifi, NULL); + ret = mif6_delete(mrt, mifi, 0, NULL); rtnl_unlock(); return ret; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9db1418993f2..fb174b590fd3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1854,6 +1854,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) int addr_type; int err = -EINVAL; + /* RTF_PCPU is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_PCPU) + goto out; + if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) goto out; #ifndef CONFIG_IPV6_SUBTREES diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index a855eb325b03..5f44ffed2576 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -53,6 +53,9 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) struct sr6_tlv *tlv; unsigned int tlv_len; + if (trailing < sizeof(*tlv)) + return false; + tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset); tlv_len = sizeof(*tlv) + tlv->len; diff --git a/net/key/af_key.c b/net/key/af_key.c index c6252ed42c1d..be8cecc65002 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -63,8 +63,13 @@ struct pfkey_sock { } u; struct sk_buff *skb; } dump; + struct mutex dump_lock; }; +static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, + xfrm_address_t *saddr, xfrm_address_t *daddr, + u16 *family); + static inline struct pfkey_sock *pfkey_sk(struct sock *sk) { return (struct pfkey_sock *)sk; @@ -139,6 +144,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; + struct pfkey_sock *pfk; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) @@ -153,6 +159,9 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, if (sk == NULL) goto out; + pfk = pfkey_sk(sk); + mutex_init(&pfk->dump_lock); + sock->ops = &pfkey_ops; sock_init_data(sock, sk); @@ -281,13 +290,23 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) struct sadb_msg *hdr; int rc; + mutex_lock(&pfk->dump_lock); + if (!pfk->dump.dump) { + rc = 0; + goto out; + } + rc = pfk->dump.dump(pfk); - if (rc == -ENOBUFS) - return 0; + if (rc == -ENOBUFS) { + rc = 0; + goto out; + } if (pfk->dump.skb) { - if (!pfkey_can_dump(&pfk->sk)) - return 0; + if (!pfkey_can_dump(&pfk->sk)) { + rc = 0; + goto out; + } hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; @@ -298,6 +317,9 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) } pfkey_terminate_dump(pfk); + +out: + mutex_unlock(&pfk->dump_lock); return rc; } @@ -1793,19 +1815,26 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms struct xfrm_address_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); - if (pfk->dump.dump != NULL) + mutex_lock(&pfk->dump_lock); + if (pfk->dump.dump != NULL) { + mutex_unlock(&pfk->dump_lock); return -EBUSY; + } proto = pfkey_satype2proto(hdr->sadb_msg_satype); - if (proto == 0) + if (proto == 0) { + mutex_unlock(&pfk->dump_lock); return -EINVAL; + } if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; filter = kmalloc(sizeof(*filter), GFP_KERNEL); - if (filter == NULL) + if (filter == NULL) { + mutex_unlock(&pfk->dump_lock); return -ENOMEM; + } memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, sizeof(xfrm_address_t)); @@ -1821,6 +1850,7 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); + mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } @@ -1913,19 +1943,14 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) /* addresses present only in tunnel mode */ if (t->mode == XFRM_MODE_TUNNEL) { - u8 *sa = (u8 *) (rq + 1); - int family, socklen; + int err; - family = pfkey_sockaddr_extract((struct sockaddr *)sa, - &t->saddr); - if (!family) - return -EINVAL; - - socklen = pfkey_sockaddr_len(family); - if (pfkey_sockaddr_extract((struct sockaddr *)(sa + socklen), - &t->id.daddr) != family) - return -EINVAL; - t->encap_family = family; + err = parse_sockaddr_pair( + (struct sockaddr *)(rq + 1), + rq->sadb_x_ipsecrequest_len - sizeof(*rq), + &t->saddr, &t->id.daddr, &t->encap_family); + if (err) + return err; } else t->encap_family = xp->family; @@ -1945,7 +1970,11 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy)) return -EINVAL; - while (len >= sizeof(struct sadb_x_ipsecrequest)) { + while (len >= sizeof(*rq)) { + if (len < rq->sadb_x_ipsecrequest_len || + rq->sadb_x_ipsecrequest_len < sizeof(*rq)) + return -EINVAL; + if ((err = parse_ipsecrequest(xp, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; @@ -2408,7 +2437,6 @@ out: return err; } -#ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_sockaddr_pair_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2); @@ -2420,7 +2448,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, { int af, socklen; - if (ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) + if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) return -EINVAL; af = pfkey_sockaddr_extract(sa, saddr); @@ -2436,6 +2464,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, return 0; } +#ifdef CONFIG_NET_KEY_MIGRATE static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct xfrm_migrate *m) { @@ -2443,13 +2472,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct sadb_x_ipsecrequest *rq2; int mode; - if (len <= sizeof(struct sadb_x_ipsecrequest) || - len < rq1->sadb_x_ipsecrequest_len) + if (len < sizeof(*rq1) || + len < rq1->sadb_x_ipsecrequest_len || + rq1->sadb_x_ipsecrequest_len < sizeof(*rq1)) return -EINVAL; /* old endoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1), - rq1->sadb_x_ipsecrequest_len, + rq1->sadb_x_ipsecrequest_len - sizeof(*rq1), &m->old_saddr, &m->old_daddr, &m->old_family); if (err) @@ -2458,13 +2488,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len); len -= rq1->sadb_x_ipsecrequest_len; - if (len <= sizeof(struct sadb_x_ipsecrequest) || - len < rq2->sadb_x_ipsecrequest_len) + if (len <= sizeof(*rq2) || + len < rq2->sadb_x_ipsecrequest_len || + rq2->sadb_x_ipsecrequest_len < sizeof(*rq2)) return -EINVAL; /* new endpoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1), - rq2->sadb_x_ipsecrequest_len, + rq2->sadb_x_ipsecrequest_len - sizeof(*rq2), &m->new_saddr, &m->new_daddr, &m->new_family); if (err) @@ -2679,14 +2710,18 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb { struct pfkey_sock *pfk = pfkey_sk(sk); - if (pfk->dump.dump != NULL) + mutex_lock(&pfk->dump_lock); + if (pfk->dump.dump != NULL) { + mutex_unlock(&pfk->dump_lock); return -EBUSY; + } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sp; pfk->dump.done = pfkey_dump_sp_done; xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN); + mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index e48724a6725e..4d7543d1a62c 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -208,6 +208,51 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, return len; } +static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + int rtap_vendor_space) +{ + struct { + struct ieee80211_hdr_3addr hdr; + u8 category; + u8 action_code; + } __packed action; + + if (!sdata) + return; + + BUILD_BUG_ON(sizeof(action) != IEEE80211_MIN_ACTION_SIZE + 1); + + if (skb->len < rtap_vendor_space + sizeof(action) + + VHT_MUMIMO_GROUPS_DATA_LEN) + return; + + if (!is_valid_ether_addr(sdata->u.mntr.mu_follow_addr)) + return; + + skb_copy_bits(skb, rtap_vendor_space, &action, sizeof(action)); + + if (!ieee80211_is_action(action.hdr.frame_control)) + return; + + if (action.category != WLAN_CATEGORY_VHT) + return; + + if (action.action_code != WLAN_VHT_ACTION_GROUPID_MGMT) + return; + + if (!ether_addr_equal(action.hdr.addr1, sdata->u.mntr.mu_follow_addr)) + return; + + skb = skb_copy(skb, GFP_ATOMIC); + if (!skb) + return; + + skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; + skb_queue_tail(&sdata->skb_queue, skb); + ieee80211_queue_work(&sdata->local->hw, &sdata->work); +} + /* * ieee80211_add_rx_radiotap_header - add radiotap header * @@ -515,7 +560,6 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, struct net_device *prev_dev = NULL; int present_fcs_len = 0; unsigned int rtap_vendor_space = 0; - struct ieee80211_mgmt *mgmt; struct ieee80211_sub_if_data *monitor_sdata = rcu_dereference(local->monitor_sdata); @@ -553,6 +597,8 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, return remove_monitor_info(local, origskb, rtap_vendor_space); } + ieee80211_handle_mu_mimo_mon(monitor_sdata, origskb, rtap_vendor_space); + /* room for the radiotap header based on driver features */ rt_hdrlen = ieee80211_rx_radiotap_hdrlen(local, status, origskb); needed_headroom = rt_hdrlen - rtap_vendor_space; @@ -618,23 +664,6 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, ieee80211_rx_stats(sdata->dev, skb->len); } - mgmt = (void *)skb->data; - if (monitor_sdata && - skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + VHT_MUMIMO_GROUPS_DATA_LEN && - ieee80211_is_action(mgmt->frame_control) && - mgmt->u.action.category == WLAN_CATEGORY_VHT && - mgmt->u.action.u.vht_group_notif.action_code == WLAN_VHT_ACTION_GROUPID_MGMT && - is_valid_ether_addr(monitor_sdata->u.mntr.mu_follow_addr) && - ether_addr_equal(mgmt->da, monitor_sdata->u.mntr.mu_follow_addr)) { - struct sk_buff *mu_skb = skb_copy(skb, GFP_ATOMIC); - - if (mu_skb) { - mu_skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; - skb_queue_tail(&monitor_sdata->skb_queue, mu_skb); - ieee80211_queue_work(&local->hw, &monitor_sdata->work); - } - } - if (prev_dev) { skb->dev = prev_dev; netif_receive_skb(skb); @@ -3610,6 +3639,27 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) !ether_addr_equal(bssid, hdr->addr1)) return false; } + + /* + * 802.11-2016 Table 9-26 says that for data frames, A1 must be + * the BSSID - we've checked that already but may have accepted + * the wildcard (ff:ff:ff:ff:ff:ff). + * + * It also says: + * The BSSID of the Data frame is determined as follows: + * a) If the STA is contained within an AP or is associated + * with an AP, the BSSID is the address currently in use + * by the STA contained in the AP. + * + * So we should not accept data frames with an address that's + * multicast. + * + * Accepting it also opens a security problem because stations + * could encrypt it with the GTK and inject traffic that way. + */ + if (ieee80211_is_data(hdr->frame_control) && multicast) + return false; + return true; case NL80211_IFTYPE_WDS: if (bssid || !ieee80211_is_data(hdr->frame_control)) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index ae5ac175b2be..9da7368b0140 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -658,7 +658,9 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } if (plen != len) { - skb_pad(skb, plen - len); + rc = skb_pad(skb, plen - len); + if (rc) + goto out_node; skb_put(skb, plen - len); } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b70aa57319ea..e05b924618a0 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -529,20 +529,20 @@ errout: return err; } -static int nla_memdup_cookie(struct tc_action *a, struct nlattr **tb) +static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) { - a->act_cookie = kzalloc(sizeof(*a->act_cookie), GFP_KERNEL); - if (!a->act_cookie) - return -ENOMEM; + struct tc_cookie *c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return NULL; - a->act_cookie->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL); - if (!a->act_cookie->data) { - kfree(a->act_cookie); - return -ENOMEM; + c->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL); + if (!c->data) { + kfree(c); + return NULL; } - a->act_cookie->len = nla_len(tb[TCA_ACT_COOKIE]); + c->len = nla_len(tb[TCA_ACT_COOKIE]); - return 0; + return c; } struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, @@ -551,6 +551,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, { struct tc_action *a; struct tc_action_ops *a_o; + struct tc_cookie *cookie = NULL; char act_name[IFNAMSIZ]; struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; @@ -566,6 +567,18 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, goto err_out; if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) goto err_out; + if (tb[TCA_ACT_COOKIE]) { + int cklen = nla_len(tb[TCA_ACT_COOKIE]); + + if (cklen > TC_COOKIE_MAX_SIZE) + goto err_out; + + cookie = nla_memdup_cookie(tb); + if (!cookie) { + err = -ENOMEM; + goto err_out; + } + } } else { err = -EINVAL; if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) @@ -604,20 +617,12 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, if (err < 0) goto err_mod; - if (tb[TCA_ACT_COOKIE]) { - int cklen = nla_len(tb[TCA_ACT_COOKIE]); - - if (cklen > TC_COOKIE_MAX_SIZE) { - err = -EINVAL; - tcf_hash_release(a, bind); - goto err_mod; - } - - if (nla_memdup_cookie(a, tb) < 0) { - err = -ENOMEM; - tcf_hash_release(a, bind); - goto err_mod; + if (name == NULL && tb[TCA_ACT_COOKIE]) { + if (a->act_cookie) { + kfree(a->act_cookie->data); + kfree(a->act_cookie); } + a->act_cookie = cookie; } /* module count goes up only when brand new policy is created @@ -632,6 +637,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, err_mod: module_put(a_o->owner); err_out: + if (cookie) { + kfree(cookie->data); + kfree(cookie); + } return ERR_PTR(err); } diff --git a/security/keys/gc.c b/security/keys/gc.c index addf060399e0..9cb4fe4478a1 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -46,7 +46,7 @@ static unsigned long key_gc_flags; * immediately unlinked. */ struct key_type key_type_dead = { - .name = "dead", + .name = ".dead", }; /* diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 52c34532c785..4ad3212adebe 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -273,7 +273,8 @@ error: * Create and join an anonymous session keyring or join a named session * keyring, creating it if necessary. A named session keyring must have Search * permission for it to be joined. Session keyrings without this permit will - * be skipped over. + * be skipped over. It is not permitted for userspace to create or join + * keyrings whose name begin with a dot. * * If successful, the ID of the joined session keyring will be returned. */ @@ -290,12 +291,16 @@ long keyctl_join_session_keyring(const char __user *_name) ret = PTR_ERR(name); goto error; } + + ret = -EPERM; + if (name[0] == '.') + goto error_name; } /* join the session */ ret = join_session_keyring(name); +error_name: kfree(name); - error: return ret; } @@ -1253,8 +1258,8 @@ error: * Read or set the default keyring in which request_key() will cache keys and * return the old setting. * - * If a process keyring is specified then this will be created if it doesn't - * yet exist. The old setting will be returned if successful. + * If a thread or process keyring is specified then it will be created if it + * doesn't yet exist. The old setting will be returned if successful. */ long keyctl_set_reqkey_keyring(int reqkey_defl) { @@ -1279,11 +1284,8 @@ long keyctl_set_reqkey_keyring(int reqkey_defl) case KEY_REQKEY_DEFL_PROCESS_KEYRING: ret = install_process_keyring_to_cred(new); - if (ret < 0) { - if (ret != -EEXIST) - goto error; - ret = 0; - } + if (ret < 0) + goto error; goto set; case KEY_REQKEY_DEFL_DEFAULT: diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index b6fdd22205b1..9139b18fc863 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -128,13 +128,18 @@ error: } /* - * Install a fresh thread keyring directly to new credentials. This keyring is - * allowed to overrun the quota. + * Install a thread keyring to the given credentials struct if it didn't have + * one already. This is allowed to overrun the quota. + * + * Return: 0 if a thread keyring is now present; -errno on failure. */ int install_thread_keyring_to_cred(struct cred *new) { struct key *keyring; + if (new->thread_keyring) + return 0; + keyring = keyring_alloc("_tid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, KEY_ALLOC_QUOTA_OVERRUN, @@ -147,7 +152,9 @@ int install_thread_keyring_to_cred(struct cred *new) } /* - * Install a fresh thread keyring, discarding the old one. + * Install a thread keyring to the current task if it didn't have one already. + * + * Return: 0 if a thread keyring is now present; -errno on failure. */ static int install_thread_keyring(void) { @@ -158,8 +165,6 @@ static int install_thread_keyring(void) if (!new) return -ENOMEM; - BUG_ON(new->thread_keyring); - ret = install_thread_keyring_to_cred(new); if (ret < 0) { abort_creds(new); @@ -170,17 +175,17 @@ static int install_thread_keyring(void) } /* - * Install a process keyring directly to a credentials struct. + * Install a process keyring to the given credentials struct if it didn't have + * one already. This is allowed to overrun the quota. * - * Returns -EEXIST if there was already a process keyring, 0 if one installed, - * and other value on any other error + * Return: 0 if a process keyring is now present; -errno on failure. */ int install_process_keyring_to_cred(struct cred *new) { struct key *keyring; if (new->process_keyring) - return -EEXIST; + return 0; keyring = keyring_alloc("_pid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, @@ -194,11 +199,9 @@ int install_process_keyring_to_cred(struct cred *new) } /* - * Make sure a process keyring is installed for the current process. The - * existing process keyring is not replaced. + * Install a process keyring to the current task if it didn't have one already. * - * Returns 0 if there is a process keyring by the end of this function, some - * error otherwise. + * Return: 0 if a process keyring is now present; -errno on failure. */ static int install_process_keyring(void) { @@ -212,14 +215,18 @@ static int install_process_keyring(void) ret = install_process_keyring_to_cred(new); if (ret < 0) { abort_creds(new); - return ret != -EEXIST ? ret : 0; + return ret; } return commit_creds(new); } /* - * Install a session keyring directly to a credentials struct. + * Install the given keyring as the session keyring of the given credentials + * struct, replacing the existing one if any. If the given keyring is NULL, + * then install a new anonymous session keyring. + * + * Return: 0 on success; -errno on failure. */ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) { @@ -254,8 +261,11 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) } /* - * Install a session keyring, discarding the old one. If a keyring is not - * supplied, an empty one is invented. + * Install the given keyring as the session keyring of the current task, + * replacing the existing one if any. If the given keyring is NULL, then + * install a new anonymous session keyring. + * + * Return: 0 on success; -errno on failure. */ static int install_session_keyring(struct key *keyring) { diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index a0aa2009b0e0..20f1871874df 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -282,7 +282,7 @@ static void test_arraymap_percpu(int task, void *data) { unsigned int nr_cpus = bpf_num_possible_cpus(); int key, next_key, fd, i; - long values[nr_cpus]; + long long values[nr_cpus]; fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), sizeof(values[0]), 2, 0); @@ -340,7 +340,7 @@ static void test_arraymap_percpu_many_keys(void) * allocator more than anything else */ unsigned int nr_keys = 2000; - long values[nr_cpus]; + long long values[nr_cpus]; int key, fd, i; fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc new file mode 100644 index 000000000000..bab5ff7c607e --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -0,0 +1,117 @@ +#!/bin/sh +# description: ftrace - function pid filters + +# Make sure that function pid matching filter works. +# Also test it on an instance directory + +if ! grep -q function available_tracers; then + echo "no function tracer configured" + exit_unsupported +fi + +if [ ! -f set_ftrace_pid ]; then + echo "set_ftrace_pid not found? Is function tracer not set?" + exit_unsupported +fi + +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is function tracer not set?" + exit_unsupported +fi + +do_function_fork=1 + +if [ ! -f options/function-fork ]; then + do_function_fork=0 + echo "no option for function-fork found. Option will not be tested." +fi + +read PID _ < /proc/self/stat + +if [ $do_function_fork -eq 1 ]; then + # default value of function-fork option + orig_value=`grep function-fork trace_options` +fi + +do_reset() { + reset_tracer + clear_trace + enable_tracing + echo > set_ftrace_filter + echo > set_ftrace_pid + + if [ $do_function_fork -eq 0 ]; then + return + fi + + echo $orig_value > trace_options +} + +fail() { # msg + do_reset + echo $1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 +} + +do_test() { + disable_tracing + + echo do_execve* > set_ftrace_filter + echo *do_fork >> set_ftrace_filter + + echo $PID > set_ftrace_pid + echo function > current_tracer + + if [ $do_function_fork -eq 1 ]; then + # don't allow children to be traced + echo nofunction-fork > trace_options + fi + + enable_tracing + yield + + count_pid=`cat trace | grep -v ^# | grep $PID | wc -l` + count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l` + + # count_other should be 0 + if [ $count_pid -eq 0 -o $count_other -ne 0 ]; then + fail "PID filtering not working?" + fi + + disable_tracing + clear_trace + + if [ $do_function_fork -eq 0 ]; then + return + fi + + # allow children to be traced + echo function-fork > trace_options + + enable_tracing + yield + + count_pid=`cat trace | grep -v ^# | grep $PID | wc -l` + count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l` + + # count_other should NOT be 0 + if [ $count_pid -eq 0 -o $count_other -eq 0 ]; then + fail "PID filtering not following fork?" + fi +} + +do_test + +mkdir instances/foo +cd instances/foo +do_test +cd ../../ +rmdir instances/foo + +do_reset + +exit 0 diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 412459369686..e62bb354820c 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -75,7 +75,7 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets) { int fd, val; - fd = socket(PF_PACKET, SOCK_DGRAM, htons(ETH_P_IP)); + fd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP)); if (fd < 0) { perror("socket packet"); exit(1); @@ -95,6 +95,24 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets) return fd; } +static void sock_fanout_set_cbpf(int fd) +{ + struct sock_filter bpf_filter[] = { + BPF_STMT(BPF_LD+BPF_B+BPF_ABS, 80), /* ldb [80] */ + BPF_STMT(BPF_RET+BPF_A, 0), /* ret A */ + }; + struct sock_fprog bpf_prog; + + bpf_prog.filter = bpf_filter; + bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); + + if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &bpf_prog, + sizeof(bpf_prog))) { + perror("fanout data cbpf"); + exit(1); + } +} + static void sock_fanout_set_ebpf(int fd) { const int len_off = __builtin_offsetof(struct __sk_buff, len); @@ -270,7 +288,7 @@ static int test_datapath(uint16_t typeflags, int port_off, exit(1); } if (type == PACKET_FANOUT_CBPF) - sock_setfilter(fds[0], SOL_PACKET, PACKET_FANOUT_DATA); + sock_fanout_set_cbpf(fds[0]); else if (type == PACKET_FANOUT_EBPF) sock_fanout_set_ebpf(fds[0]); diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h index a77da88bf946..7d990d6c861b 100644 --- a/tools/testing/selftests/net/psock_lib.h +++ b/tools/testing/selftests/net/psock_lib.h @@ -38,7 +38,7 @@ # define __maybe_unused __attribute__ ((__unused__)) #endif -static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum) +static __maybe_unused void pair_udp_setfilter(int fd) { /* the filter below checks for all of the following conditions that * are based on the contents of create_payload() @@ -76,23 +76,16 @@ static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum) }; struct sock_fprog bpf_prog; - if (lvl == SOL_PACKET && optnum == PACKET_FANOUT_DATA) - bpf_filter[5].code = 0x16; /* RET A */ - bpf_prog.filter = bpf_filter; bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); - if (setsockopt(fd, lvl, optnum, &bpf_prog, + + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog, sizeof(bpf_prog))) { perror("setsockopt SO_ATTACH_FILTER"); exit(1); } } -static __maybe_unused void pair_udp_setfilter(int fd) -{ - sock_setfilter(fd, SOL_SOCKET, SO_ATTACH_FILTER); -} - static __maybe_unused void pair_udp_open(int fds[], uint16_t port) { struct sockaddr_in saddr, daddr; |