diff options
185 files changed, 2289 insertions, 1175 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index f6befa9..61ab162 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3787,6 +3787,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. READ_CAPACITY_16 command); f = NO_REPORT_OPCODES (don't use report opcodes command, uas only); + g = MAX_SECTORS_240 (don't transfer more than + 240 sectors at a time, uas only); h = CAPACITY_HEURISTICS (decrease the reported device capacity by one sector if the number is odd); diff --git a/Documentation/module-signing.txt b/Documentation/module-signing.txt index 09c2382..c72702e 100644 --- a/Documentation/module-signing.txt +++ b/Documentation/module-signing.txt @@ -119,9 +119,9 @@ Most notably, in the x509.genkey file, the req_distinguished_name section should be altered from the default: [ req_distinguished_name ] - O = Magrathea - CN = Glacier signing key - emailAddress = slartibartfast@magrathea.h2g2 + #O = Unspecified company + CN = Build time autogenerated kernel key + #emailAddress = unspecified.user@unspecified.company The generated RSA key size can also be set with: diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt index 639ddf0..9ed15f8 100644 --- a/Documentation/networking/mpls-sysctl.txt +++ b/Documentation/networking/mpls-sysctl.txt @@ -18,3 +18,12 @@ platform_labels - INTEGER Possible values: 0 - 1048575 Default: 0 + +conf/<interface>/input - BOOL + Control whether packets can be input on this interface. + + If disabled, packets will be discarded without further + processing. + + 0 - disabled (default) + not 0 - enabled diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt index cbfac09..59f4db2 100644 --- a/Documentation/networking/scaling.txt +++ b/Documentation/networking/scaling.txt @@ -282,7 +282,7 @@ following is true: - The current CPU's queue head counter >= the recorded tail counter value in rps_dev_flow[i] -- The current CPU is unset (equal to RPS_NO_CPU) +- The current CPU is unset (>= nr_cpu_ids) - The current CPU is offline After this check, the packet is sent to the (possibly updated) current diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.txt index ba0a2a4..ded6979 100644 --- a/Documentation/powerpc/transactional_memory.txt +++ b/Documentation/powerpc/transactional_memory.txt @@ -74,23 +74,22 @@ Causes of transaction aborts Syscalls ======== -Syscalls made from within an active transaction will not be performed and the -transaction will be doomed by the kernel with the failure code TM_CAUSE_SYSCALL -| TM_CAUSE_PERSISTENT. +Performing syscalls from within transaction is not recommended, and can lead +to unpredictable results. -Syscalls made from within a suspended transaction are performed as normal and -the transaction is not explicitly doomed by the kernel. However, what the -kernel does to perform the syscall may result in the transaction being doomed -by the hardware. The syscall is performed in suspended mode so any side -effects will be persistent, independent of transaction success or failure. No -guarantees are provided by the kernel about which syscalls will affect -transaction success. +Syscalls do not by design abort transactions, but beware: The kernel code will +not be running in transactional state. The effect of syscalls will always +remain visible, but depending on the call they may abort your transaction as a +side-effect, read soon-to-be-aborted transactional data that should not remain +invisible, etc. If you constantly retry a transaction that constantly aborts +itself by calling a syscall, you'll have a livelock & make no progress. -Care must be taken when relying on syscalls to abort during active transactions -if the calls are made via a library. Libraries may cache values (which may -give the appearance of success) or perform operations that cause transaction -failure before entering the kernel (which may produce different failure codes). -Examples are glibc's getpid() and lazy symbol resolution. +Simple syscalls (e.g. sigprocmask()) "could" be OK. Even things like write() +from, say, printf() should be OK as long as the kernel does not access any +memory that was accessed transactionally. + +Consider any syscalls that happen to work as debug-only -- not recommended for +production use. Best to queue them up till after the transaction is over. Signals @@ -177,7 +176,8 @@ kernel aborted a transaction: TM_CAUSE_RESCHED Thread was rescheduled. TM_CAUSE_TLBI Software TLB invalid. TM_CAUSE_FAC_UNAV FP/VEC/VSX unavailable trap. - TM_CAUSE_SYSCALL Syscall from active transaction. + TM_CAUSE_SYSCALL Currently unused; future syscalls that must abort + transactions for consistency will use this. TM_CAUSE_SIGNAL Signal delivered. TM_CAUSE_MISC Currently unused. TM_CAUSE_ALIGNMENT Alignment fault. diff --git a/MAINTAINERS b/MAINTAINERS index 2e5bbc0..1622775 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10523,7 +10523,6 @@ F: include/linux/virtio_console.h F: include/uapi/linux/virtio_console.h VIRTIO CORE, NET AND BLOCK DRIVERS -M: Rusty Russell <rusty@rustcorp.com.au> M: "Michael S. Tsirkin" <mst@redhat.com> L: virtualization@lists.linux-foundation.org S: Maintained diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 4269dba..7796af4 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -31,6 +31,7 @@ config ARM64 select GENERIC_EARLY_IOREMAP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW + select GENERIC_IRQ_SHOW_LEVEL select GENERIC_PCI_IOMAP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index a5abb00..71f19c4 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -65,6 +65,14 @@ do { \ do { \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("stlrb %w1, %0" \ + : "=Q" (*p) : "r" (v) : "memory"); \ + break; \ + case 2: \ + asm volatile ("stlrh %w1, %0" \ + : "=Q" (*p) : "r" (v) : "memory"); \ + break; \ case 4: \ asm volatile ("stlr %w1, %0" \ : "=Q" (*p) : "r" (v) : "memory"); \ @@ -81,6 +89,14 @@ do { \ typeof(*p) ___p1; \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("ldarb %w0, %1" \ + : "=r" (___p1) : "Q" (*p) : "memory"); \ + break; \ + case 2: \ + asm volatile ("ldarh %w0, %1" \ + : "=r" (___p1) : "Q" (*p) : "memory"); \ + break; \ case 4: \ asm volatile ("ldar %w0, %1" \ : "=r" (___p1) : "Q" (*p) : "memory"); \ diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 195991d..23f25ac 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1310,7 +1310,7 @@ static const struct of_device_id armpmu_of_device_ids[] = { static int armpmu_device_probe(struct platform_device *pdev) { - int i, *irqs; + int i, irq, *irqs; if (!cpu_pmu) return -ENODEV; @@ -1319,6 +1319,11 @@ static int armpmu_device_probe(struct platform_device *pdev) if (!irqs) return -ENOMEM; + /* Don't bother with PPIs; they're already affine */ + irq = platform_get_irq(pdev, 0); + if (irq >= 0 && irq_is_percpu(irq)) + return 0; + for (i = 0; i < pdev->num_resources; ++i) { struct device_node *dn; int cpu; @@ -1327,7 +1332,7 @@ static int armpmu_device_probe(struct platform_device *pdev) i); if (!dn) { pr_warn("Failed to parse %s/interrupt-affinity[%d]\n", - of_node_full_name(dn), i); + of_node_full_name(pdev->dev.of_node), i); break; } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index ef7d112..b0bd4e5 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -67,8 +67,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) *ret_page = phys_to_page(phys); ptr = (void *)val; - if (flags & __GFP_ZERO) - memset(ptr, 0, size); + memset(ptr, 0, size); } return ptr; @@ -105,7 +104,6 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, struct page *page; void *addr; - size = PAGE_ALIGN(size); page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, get_order(size)); if (!page) @@ -113,8 +111,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, *dma_handle = phys_to_dma(dev, page_to_phys(page)); addr = page_address(page); - if (flags & __GFP_ZERO) - memset(addr, 0, size); + memset(addr, 0, size); return addr; } else { return swiotlb_alloc_coherent(dev, size, dma_handle, flags); @@ -195,6 +192,8 @@ static void __dma_free(struct device *dev, size_t size, { void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle)); + size = PAGE_ALIGN(size); + if (!is_device_dma_coherent(dev)) { if (__free_from_pool(vaddr, size)) return; diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h index 5047659..5d836b7 100644 --- a/arch/powerpc/include/uapi/asm/tm.h +++ b/arch/powerpc/include/uapi/asm/tm.h @@ -11,7 +11,7 @@ #define TM_CAUSE_RESCHED 0xde #define TM_CAUSE_TLBI 0xdc #define TM_CAUSE_FAC_UNAV 0xda -#define TM_CAUSE_SYSCALL 0xd8 +#define TM_CAUSE_SYSCALL 0xd8 /* future use */ #define TM_CAUSE_MISC 0xd6 /* future use */ #define TM_CAUSE_SIGNAL 0xd4 #define TM_CAUSE_ALIGNMENT 0xd2 diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 44b480e3..9ee61d1 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -749,21 +749,24 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat eeh_unfreeze_pe(pe, false); eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev); + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); break; case pcie_hot_reset: + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_HOT); break; case pcie_warm_reset: + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); break; default: - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, EEH_PE_ISOLATED | EEH_PE_CFG_BLOCKED); return -EINVAL; }; @@ -1058,6 +1061,9 @@ void eeh_add_device_early(struct pci_dn *pdn) if (!edev || !eeh_enabled()) return; + if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) + return; + /* USB Bus children of PCI devices will not have BUID's */ phb = edev->phb; if (NULL == phb || @@ -1112,6 +1118,9 @@ void eeh_add_device_late(struct pci_dev *dev) return; } + if (eeh_has_flag(EEH_PROBE_MODE_DEV)) + eeh_ops->probe(pdn, NULL); + /* * The EEH cache might not be removed correctly because of * unbalanced kref to the device during unplug time, which diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 8ca9434..afbc200 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -34,7 +34,6 @@ #include <asm/ftrace.h> #include <asm/hw_irq.h> #include <asm/context_tracking.h> -#include <asm/tm.h> /* * System calls. @@ -146,24 +145,6 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) andi. r11,r10,_TIF_SYSCALL_DOTRACE bne syscall_dotrace .Lsyscall_dotrace_cont: -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - b 1f -END_FTR_SECTION_IFCLR(CPU_FTR_TM) - extrdi. r11, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ - beq+ 1f - - /* Doom the transaction and don't perform the syscall: */ - mfmsr r11 - li r12, 1 - rldimi r11, r12, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r11, 0 - li r11, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R11) - - b .Lsyscall_exit -1: -#endif cmpldi 0,r0,NR_syscalls bge- syscall_enosys diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index eeaa0d5..ccde8f0 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -501,9 +501,11 @@ BEGIN_FTR_SECTION CHECK_HMI_INTERRUPT END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) ld r1,PACAR1(r13) + ld r6,_CCR(r1) ld r4,_MSR(r1) ld r5,_NIP(r1) addi r1,r1,INT_FRAME_SIZE + mtcr r6 mtspr SPRN_SRR1,r4 mtspr SPRN_SRR0,r5 rfid diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 8f3e6cc..c6ca7db 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -12,6 +12,7 @@ #include <linux/err.h> #include <linux/gfp.h> #include <linux/anon_inodes.h> +#include <linux/spinlock.h> #include <asm/uaccess.h> #include <asm/kvm_book3s.h> @@ -20,7 +21,6 @@ #include <asm/xics.h> #include <asm/debug.h> #include <asm/time.h> -#include <asm/spinlock.h> #include <linux/debugfs.h> #include <linux/seq_file.h> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 920c252..f8bc950 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2693,7 +2693,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, hose->last_busno = 0xff; } hose->private_data = phb; - hose->controller_ops = pnv_pci_controller_ops; phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = ioda_type; @@ -2812,6 +2811,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook; pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment; pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus; + hose->controller_ops = pnv_pci_controller_ops; #ifdef CONFIG_PCI_IOV ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources; diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index b4b1109..019d34a 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -412,6 +412,10 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count) if (rc) return -EINVAL; + rc = dlpar_acquire_drc(drc_index); + if (rc) + return -EINVAL; + parent = of_find_node_by_path("/cpus"); if (!parent) return -ENODEV; @@ -422,12 +426,6 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count) of_node_put(parent); - rc = dlpar_acquire_drc(drc_index); - if (rc) { - dlpar_free_cc_nodes(dn); - return -EINVAL; - } - rc = dlpar_attach_node(dn); if (rc) { dlpar_release_drc(drc_index); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8e58c61..b06dc38 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -115,7 +115,7 @@ config S390 select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE - select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z9_109_FEATURES + select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_DEBUG_KMEMLEAK diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h index ba3b2ae..d9c4c31 100644 --- a/arch/s390/crypto/crypt_s390.h +++ b/arch/s390/crypto/crypt_s390.h @@ -3,9 +3,10 @@ * * Support for s390 cryptographic instructions. * - * Copyright IBM Corp. 2003, 2007 + * Copyright IBM Corp. 2003, 2015 * Author(s): Thomas Spatzier * Jan Glauber (jan.glauber@de.ibm.com) + * Harald Freudenberger (freude@de.ibm.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 @@ -28,15 +29,17 @@ #define CRYPT_S390_MSA 0x1 #define CRYPT_S390_MSA3 0x2 #define CRYPT_S390_MSA4 0x4 +#define CRYPT_S390_MSA5 0x8 /* s390 cryptographic operations */ enum crypt_s390_operations { - CRYPT_S390_KM = 0x0100, - CRYPT_S390_KMC = 0x0200, - CRYPT_S390_KIMD = 0x0300, - CRYPT_S390_KLMD = 0x0400, - CRYPT_S390_KMAC = 0x0500, - CRYPT_S390_KMCTR = 0x0600 + CRYPT_S390_KM = 0x0100, + CRYPT_S390_KMC = 0x0200, + CRYPT_S390_KIMD = 0x0300, + CRYPT_S390_KLMD = 0x0400, + CRYPT_S390_KMAC = 0x0500, + CRYPT_S390_KMCTR = 0x0600, + CRYPT_S390_PPNO = 0x0700 }; /* @@ -138,6 +141,16 @@ enum crypt_s390_kmac_func { KMAC_TDEA_192 = CRYPT_S390_KMAC | 3 }; +/* + * function codes for PPNO (PERFORM PSEUDORANDOM NUMBER + * OPERATION) instruction + */ +enum crypt_s390_ppno_func { + PPNO_QUERY = CRYPT_S390_PPNO | 0, + PPNO_SHA512_DRNG_GEN = CRYPT_S390_PPNO | 3, + PPNO_SHA512_DRNG_SEED = CRYPT_S390_PPNO | 0x83 +}; + /** * crypt_s390_km: * @func: the function code passed to KM; see crypt_s390_km_func @@ -162,11 +175,11 @@ static inline int crypt_s390_km(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb92e0000,%3,%1 \n" /* KM opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb92e0000,%3,%1\n" /* KM opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -198,11 +211,11 @@ static inline int crypt_s390_kmc(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb92f0000,%3,%1 \n" /* KMC opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb92f0000,%3,%1\n" /* KMC opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -233,11 +246,11 @@ static inline int crypt_s390_kimd(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb93e0000,%1,%1 \n" /* KIMD opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb93e0000,%1,%1\n" /* KIMD opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -267,11 +280,11 @@ static inline int crypt_s390_klmd(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb93f0000,%1,%1 \n" /* KLMD opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb93f0000,%1,%1\n" /* KLMD opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -302,11 +315,11 @@ static inline int crypt_s390_kmac(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb91e0000,%1,%1 \n" /* KLAC opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb91e0000,%1,%1\n" /* KLAC opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -340,11 +353,11 @@ static inline int crypt_s390_kmctr(long func, void *param, u8 *dest, int ret = -1; asm volatile( - "0: .insn rrf,0xb92d0000,%3,%1,%4,0 \n" /* KMCTR opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rrf,0xb92d0000,%3,%1,%4,0\n" /* KMCTR opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "+d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest), "+a" (__ctr) : "d" (__func), "a" (__param) : "cc", "memory"); @@ -354,6 +367,47 @@ static inline int crypt_s390_kmctr(long func, void *param, u8 *dest, } /** + * crypt_s390_ppno: + * @func: the function code passed to PPNO; see crypt_s390_ppno_func + * @param: address of parameter block; see POP for details on each func + * @dest: address of destination memory area + * @dest_len: size of destination memory area in bytes + * @seed: address of seed data + * @seed_len: size of seed data in bytes + * + * Executes the PPNO (PERFORM PSEUDORANDOM NUMBER OPERATION) + * operation of the CPU. + * + * Returns -1 for failure, 0 for the query func, number of random + * bytes stored in dest buffer for generate function + */ +static inline int crypt_s390_ppno(long func, void *param, + u8 *dest, long dest_len, + const u8 *seed, long seed_len) +{ + register long __func asm("0") = func & CRYPT_S390_FUNC_MASK; + register void *__param asm("1") = param; /* param block (240 bytes) */ + register u8 *__dest asm("2") = dest; /* buf for recv random bytes */ + register long __dest_len asm("3") = dest_len; /* requested random bytes */ + register const u8 *__seed asm("4") = seed; /* buf with seed data */ + register long __seed_len asm("5") = seed_len; /* bytes in seed buf */ + int ret = -1; + + asm volatile ( + "0: .insn rre,0xb93c0000,%1,%5\n" /* PPNO opcode */ + "1: brc 1,0b\n" /* handle partial completion */ + " la %0,0\n" + "2:\n" + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) + : "+d" (ret), "+a"(__dest), "+d"(__dest_len) + : "d"(__func), "a"(__param), "a"(__seed), "d"(__seed_len) + : "cc", "memory"); + if (ret < 0) + return ret; + return (func & CRYPT_S390_FUNC_MASK) ? dest_len - __dest_len : 0; +} + +/** * crypt_s390_func_available: * @func: the function code of the specific function; 0 if op in general * @@ -373,6 +427,9 @@ static inline int crypt_s390_func_available(int func, return 0; if (facility_mask & CRYPT_S390_MSA4 && !test_facility(77)) return 0; + if (facility_mask & CRYPT_S390_MSA5 && !test_facility(57)) + return 0; + switch (func & CRYPT_S390_OP_MASK) { case CRYPT_S390_KM: ret = crypt_s390_km(KM_QUERY, &status, NULL, NULL, 0); @@ -390,8 +447,12 @@ static inline int crypt_s390_func_available(int func, ret = crypt_s390_kmac(KMAC_QUERY, &status, NULL, 0); break; case CRYPT_S390_KMCTR: - ret = crypt_s390_kmctr(KMCTR_QUERY, &status, NULL, NULL, 0, - NULL); + ret = crypt_s390_kmctr(KMCTR_QUERY, &status, + NULL, NULL, 0, NULL); + break; + case CRYPT_S390_PPNO: + ret = crypt_s390_ppno(PPNO_QUERY, &status, + NULL, 0, NULL, 0); break; default: return 0; @@ -419,15 +480,14 @@ static inline int crypt_s390_pcc(long func, void *param) int ret = -1; asm volatile( - "0: .insn rre,0xb92c0000,0,0 \n" /* PCC opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb92c0000,0,0\n" /* PCC opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "+d" (ret) : "d" (__func), "a" (__param) : "cc", "memory"); return ret; } - #endif /* _CRYPTO_ARCH_S390_CRYPT_S390_H */ diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index 94a35a4..1f374b3 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -1,106 +1,529 @@ /* - * Copyright IBM Corp. 2006, 2007 + * Copyright IBM Corp. 2006, 2015 * Author(s): Jan Glauber <jan.glauber@de.ibm.com> + * Harald Freudenberger <freude@de.ibm.com> * Driver for the s390 pseudo random number generator */ + +#define KMSG_COMPONENT "prng" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/fs.h> +#include <linux/fips.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/device.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/moduleparam.h> +#include <linux/mutex.h> #include <linux/random.h> #include <linux/slab.h> #include <asm/debug.h> #include <asm/uaccess.h> +#include <asm/timex.h> #include "crypt_s390.h" MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jan Glauber <jan.glauber@de.ibm.com>"); +MODULE_AUTHOR("IBM Corporation"); MODULE_DESCRIPTION("s390 PRNG interface"); -static int prng_chunk_size = 256; -module_param(prng_chunk_size, int, S_IRUSR | S_IRGRP | S_IROTH); + +#define PRNG_MODE_AUTO 0 +#define PRNG_MODE_TDES 1 +#define PRNG_MODE_SHA512 2 + +static unsigned int prng_mode = PRNG_MODE_AUTO; +module_param_named(mode, prng_mode, int, 0); +MODULE_PARM_DESC(prng_mode, "PRNG mode: 0 - auto, 1 - TDES, 2 - SHA512"); + + +#define PRNG_CHUNKSIZE_TDES_MIN 8 +#define PRNG_CHUNKSIZE_TDES_MAX (64*1024) +#define PRNG_CHUNKSIZE_SHA512_MIN 64 +#define PRNG_CHUNKSIZE_SHA512_MAX (64*1024) + +static unsigned int prng_chunk_size = 256; +module_param_named(chunksize, prng_chunk_size, int, 0); MODULE_PARM_DESC(prng_chunk_size, "PRNG read chunk size in bytes"); -static int prng_entropy_limit = 4096; -module_param(prng_entropy_limit, int, S_IRUSR | S_IRGRP | S_IROTH | S_IWUSR); -MODULE_PARM_DESC(prng_entropy_limit, - "PRNG add entropy after that much bytes were produced"); + +#define PRNG_RESEED_LIMIT_TDES 4096 +#define PRNG_RESEED_LIMIT_TDES_LOWER 4096 +#define PRNG_RESEED_LIMIT_SHA512 100000 +#define PRNG_RESEED_LIMIT_SHA512_LOWER 10000 + +static unsigned int prng_reseed_limit; +module_param_named(reseed_limit, prng_reseed_limit, int, 0); +MODULE_PARM_DESC(prng_reseed_limit, "PRNG reseed limit"); + /* * Any one who considers arithmetical methods of producing random digits is, * of course, in a state of sin. -- John von Neumann */ -struct s390_prng_data { - unsigned long count; /* how many bytes were produced */ - char *buf; +static int prng_errorflag; + +#define PRNG_GEN_ENTROPY_FAILED 1 +#define PRNG_SELFTEST_FAILED 2 +#define PRNG_INSTANTIATE_FAILED 3 +#define PRNG_SEED_FAILED 4 +#define PRNG_RESEED_FAILED 5 +#define PRNG_GEN_FAILED 6 + +struct prng_ws_s { + u8 parm_block[32]; + u32 reseed_counter; + u64 byte_counter; }; -static struct s390_prng_data *p; +struct ppno_ws_s { + u32 res; + u32 reseed_counter; + u64 stream_bytes; + u8 V[112]; + u8 C[112]; +}; -/* copied from libica, use a non-zero initial parameter block */ -static unsigned char parm_block[32] = { -0x0F,0x2B,0x8E,0x63,0x8C,0x8E,0xD2,0x52,0x64,0xB7,0xA0,0x7B,0x75,0x28,0xB8,0xF4, -0x75,0x5F,0xD2,0xA6,0x8D,0x97,0x11,0xFF,0x49,0xD8,0x23,0xF3,0x7E,0x21,0xEC,0xA0, +struct prng_data_s { + struct mutex mutex; + union { + struct prng_ws_s prngws; + struct ppno_ws_s ppnows; + }; + u8 *buf; + u32 rest; + u8 *prev; }; -static int prng_open(struct inode *inode, struct file *file) +static struct prng_data_s *prng_data; + +/* initial parameter block for tdes mode, copied from libica */ +static const u8 initial_parm_block[32] __initconst = { + 0x0F, 0x2B, 0x8E, 0x63, 0x8C, 0x8E, 0xD2, 0x52, + 0x64, 0xB7, 0xA0, 0x7B, 0x75, 0x28, 0xB8, 0xF4, + 0x75, 0x5F, 0xD2, 0xA6, 0x8D, 0x97, 0x11, 0xFF, + 0x49, 0xD8, 0x23, 0xF3, 0x7E, 0x21, 0xEC, 0xA0 }; + + +/*** helper functions ***/ + +static int generate_entropy(u8 *ebuf, size_t nbytes) { - return nonseekable_open(inode, file); + int n, ret = 0; + u8 *pg, *h, hash[32]; + + pg = (u8 *) __get_free_page(GFP_KERNEL); + if (!pg) { + prng_errorflag = PRNG_GEN_ENTROPY_FAILED; + return -ENOMEM; + } + + while (nbytes) { + /* fill page with urandom bytes */ + get_random_bytes(pg, PAGE_SIZE); + /* exor page with stckf values */ + for (n = 0; n < sizeof(PAGE_SIZE/sizeof(u64)); n++) { + u64 *p = ((u64 *)pg) + n; + *p ^= get_tod_clock_fast(); + } + n = (nbytes < sizeof(hash)) ? nbytes : sizeof(hash); + if (n < sizeof(hash)) + h = hash; + else + h = ebuf; + /* generate sha256 from this page */ + if (crypt_s390_kimd(KIMD_SHA_256, h, + pg, PAGE_SIZE) != PAGE_SIZE) { + prng_errorflag = PRNG_GEN_ENTROPY_FAILED; + ret = -EIO; + goto out; + } + if (n < sizeof(hash)) + memcpy(ebuf, hash, n); + ret += n; + ebuf += n; + nbytes -= n; + } + +out: + free_page((unsigned long)pg); + return ret; } -static void prng_add_entropy(void) + +/*** tdes functions ***/ + +static void prng_tdes_add_entropy(void) { __u64 entropy[4]; unsigned int i; int ret; for (i = 0; i < 16; i++) { - ret = crypt_s390_kmc(KMC_PRNG, parm_block, (char *)entropy, - (char *)entropy, sizeof(entropy)); + ret = crypt_s390_kmc(KMC_PRNG, prng_data->prngws.parm_block, + (char *)entropy, (char *)entropy, + sizeof(entropy)); BUG_ON(ret < 0 || ret != sizeof(entropy)); - memcpy(parm_block, entropy, sizeof(entropy)); + memcpy(prng_data->prngws.parm_block, entropy, sizeof(entropy)); } } -static void prng_seed(int nbytes) + +static void prng_tdes_seed(int nbytes) { char buf[16]; int i = 0; - BUG_ON(nbytes > 16); + BUG_ON(nbytes > sizeof(buf)); + get_random_bytes(buf, nbytes); /* Add the entropy */ while (nbytes >= 8) { - *((__u64 *)parm_block) ^= *((__u64 *)(buf+i)); - prng_add_entropy(); + *((__u64 *)prng_data->prngws.parm_block) ^= *((__u64 *)(buf+i)); + prng_tdes_add_entropy(); i += 8; nbytes -= 8; } - prng_add_entropy(); + prng_tdes_add_entropy(); + prng_data->prngws.reseed_counter = 0; +} + + +static int __init prng_tdes_instantiate(void) +{ + int datalen; + + pr_debug("prng runs in TDES mode with " + "chunksize=%d and reseed_limit=%u\n", + prng_chunk_size, prng_reseed_limit); + + /* memory allocation, prng_data struct init, mutex init */ + datalen = sizeof(struct prng_data_s) + prng_chunk_size; + prng_data = kzalloc(datalen, GFP_KERNEL); + if (!prng_data) { + prng_errorflag = PRNG_INSTANTIATE_FAILED; + return -ENOMEM; + } + mutex_init(&prng_data->mutex); + prng_data->buf = ((u8 *)prng_data) + sizeof(struct prng_data_s); + memcpy(prng_data->prngws.parm_block, initial_parm_block, 32); + + /* initialize the PRNG, add 128 bits of entropy */ + prng_tdes_seed(16); + + return 0; } -static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes, - loff_t *ppos) + +static void prng_tdes_deinstantiate(void) +{ + pr_debug("The prng module stopped " + "after running in triple DES mode\n"); + kzfree(prng_data); +} + + +/*** sha512 functions ***/ + +static int __init prng_sha512_selftest(void) { - int chunk, n; + /* NIST DRBG testvector for Hash Drbg, Sha-512, Count #0 */ + static const u8 seed[] __initconst = { + 0x6b, 0x50, 0xa7, 0xd8, 0xf8, 0xa5, 0x5d, 0x7a, + 0x3d, 0xf8, 0xbb, 0x40, 0xbc, 0xc3, 0xb7, 0x22, + 0xd8, 0x70, 0x8d, 0xe6, 0x7f, 0xda, 0x01, 0x0b, + 0x03, 0xc4, 0xc8, 0x4d, 0x72, 0x09, 0x6f, 0x8c, + 0x3e, 0xc6, 0x49, 0xcc, 0x62, 0x56, 0xd9, 0xfa, + 0x31, 0xdb, 0x7a, 0x29, 0x04, 0xaa, 0xf0, 0x25 }; + static const u8 V0[] __initconst = { + 0x00, 0xad, 0xe3, 0x6f, 0x9a, 0x01, 0xc7, 0x76, + 0x61, 0x34, 0x35, 0xf5, 0x4e, 0x24, 0x74, 0x22, + 0x21, 0x9a, 0x29, 0x89, 0xc7, 0x93, 0x2e, 0x60, + 0x1e, 0xe8, 0x14, 0x24, 0x8d, 0xd5, 0x03, 0xf1, + 0x65, 0x5d, 0x08, 0x22, 0x72, 0xd5, 0xad, 0x95, + 0xe1, 0x23, 0x1e, 0x8a, 0xa7, 0x13, 0xd9, 0x2b, + 0x5e, 0xbc, 0xbb, 0x80, 0xab, 0x8d, 0xe5, 0x79, + 0xab, 0x5b, 0x47, 0x4e, 0xdd, 0xee, 0x6b, 0x03, + 0x8f, 0x0f, 0x5c, 0x5e, 0xa9, 0x1a, 0x83, 0xdd, + 0xd3, 0x88, 0xb2, 0x75, 0x4b, 0xce, 0x83, 0x36, + 0x57, 0x4b, 0xf1, 0x5c, 0xca, 0x7e, 0x09, 0xc0, + 0xd3, 0x89, 0xc6, 0xe0, 0xda, 0xc4, 0x81, 0x7e, + 0x5b, 0xf9, 0xe1, 0x01, 0xc1, 0x92, 0x05, 0xea, + 0xf5, 0x2f, 0xc6, 0xc6, 0xc7, 0x8f, 0xbc, 0xf4 }; + static const u8 C0[] __initconst = { + 0x00, 0xf4, 0xa3, 0xe5, 0xa0, 0x72, 0x63, 0x95, + 0xc6, 0x4f, 0x48, 0xd0, 0x8b, 0x5b, 0x5f, 0x8e, + 0x6b, 0x96, 0x1f, 0x16, 0xed, 0xbc, 0x66, 0x94, + 0x45, 0x31, 0xd7, 0x47, 0x73, 0x22, 0xa5, 0x86, + 0xce, 0xc0, 0x4c, 0xac, 0x63, 0xb8, 0x39, 0x50, + 0xbf, 0xe6, 0x59, 0x6c, 0x38, 0x58, 0x99, 0x1f, + 0x27, 0xa7, 0x9d, 0x71, 0x2a, 0xb3, 0x7b, 0xf9, + 0xfb, 0x17, 0x86, 0xaa, 0x99, 0x81, 0xaa, 0x43, + 0xe4, 0x37, 0xd3, 0x1e, 0x6e, 0xe5, 0xe6, 0xee, + 0xc2, 0xed, 0x95, 0x4f, 0x53, 0x0e, 0x46, 0x8a, + 0xcc, 0x45, 0xa5, 0xdb, 0x69, 0x0d, 0x81, 0xc9, + 0x32, 0x92, 0xbc, 0x8f, 0x33, 0xe6, 0xf6, 0x09, + 0x7c, 0x8e, 0x05, 0x19, 0x0d, 0xf1, 0xb6, 0xcc, + 0xf3, 0x02, 0x21, 0x90, 0x25, 0xec, 0xed, 0x0e }; + static const u8 random[] __initconst = { + 0x95, 0xb7, 0xf1, 0x7e, 0x98, 0x02, 0xd3, 0x57, + 0x73, 0x92, 0xc6, 0xa9, 0xc0, 0x80, 0x83, 0xb6, + 0x7d, 0xd1, 0x29, 0x22, 0x65, 0xb5, 0xf4, 0x2d, + 0x23, 0x7f, 0x1c, 0x55, 0xbb, 0x9b, 0x10, 0xbf, + 0xcf, 0xd8, 0x2c, 0x77, 0xa3, 0x78, 0xb8, 0x26, + 0x6a, 0x00, 0x99, 0x14, 0x3b, 0x3c, 0x2d, 0x64, + 0x61, 0x1e, 0xee, 0xb6, 0x9a, 0xcd, 0xc0, 0x55, + 0x95, 0x7c, 0x13, 0x9e, 0x8b, 0x19, 0x0c, 0x7a, + 0x06, 0x95, 0x5f, 0x2c, 0x79, 0x7c, 0x27, 0x78, + 0xde, 0x94, 0x03, 0x96, 0xa5, 0x01, 0xf4, 0x0e, + 0x91, 0x39, 0x6a, 0xcf, 0x8d, 0x7e, 0x45, 0xeb, + 0xdb, 0xb5, 0x3b, 0xbf, 0x8c, 0x97, 0x52, 0x30, + 0xd2, 0xf0, 0xff, 0x91, 0x06, 0xc7, 0x61, 0x19, + 0xae, 0x49, 0x8e, 0x7f, 0xbc, 0x03, 0xd9, 0x0f, + 0x8e, 0x4c, 0x51, 0x62, 0x7a, 0xed, 0x5c, 0x8d, + 0x42, 0x63, 0xd5, 0xd2, 0xb9, 0x78, 0x87, 0x3a, + 0x0d, 0xe5, 0x96, 0xee, 0x6d, 0xc7, 0xf7, 0xc2, + 0x9e, 0x37, 0xee, 0xe8, 0xb3, 0x4c, 0x90, 0xdd, + 0x1c, 0xf6, 0xa9, 0xdd, 0xb2, 0x2b, 0x4c, 0xbd, + 0x08, 0x6b, 0x14, 0xb3, 0x5d, 0xe9, 0x3d, 0xa2, + 0xd5, 0xcb, 0x18, 0x06, 0x69, 0x8c, 0xbd, 0x7b, + 0xbb, 0x67, 0xbf, 0xe3, 0xd3, 0x1f, 0xd2, 0xd1, + 0xdb, 0xd2, 0xa1, 0xe0, 0x58, 0xa3, 0xeb, 0x99, + 0xd7, 0xe5, 0x1f, 0x1a, 0x93, 0x8e, 0xed, 0x5e, + 0x1c, 0x1d, 0xe2, 0x3a, 0x6b, 0x43, 0x45, 0xd3, + 0x19, 0x14, 0x09, 0xf9, 0x2f, 0x39, 0xb3, 0x67, + 0x0d, 0x8d, 0xbf, 0xb6, 0x35, 0xd8, 0xe6, 0xa3, + 0x69, 0x32, 0xd8, 0x10, 0x33, 0xd1, 0x44, 0x8d, + 0x63, 0xb4, 0x03, 0xdd, 0xf8, 0x8e, 0x12, 0x1b, + 0x6e, 0x81, 0x9a, 0xc3, 0x81, 0x22, 0x6c, 0x13, + 0x21, 0xe4, 0xb0, 0x86, 0x44, 0xf6, 0x72, 0x7c, + 0x36, 0x8c, 0x5a, 0x9f, 0x7a, 0x4b, 0x3e, 0xe2 }; + int ret = 0; - int tmp; + u8 buf[sizeof(random)]; + struct ppno_ws_s ws; + + memset(&ws, 0, sizeof(ws)); + + /* initial seed */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED, + &ws, NULL, 0, + seed, sizeof(seed)); + if (ret < 0) { + pr_err("The prng self test seed operation for the " + "SHA-512 mode failed with rc=%d\n", ret); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + + /* check working states V and C */ + if (memcmp(ws.V, V0, sizeof(V0)) != 0 + || memcmp(ws.C, C0, sizeof(C0)) != 0) { + pr_err("The prng self test state test " + "for the SHA-512 mode failed\n"); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + + /* generate random bytes */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN, + &ws, buf, sizeof(buf), + NULL, 0); + if (ret < 0) { + pr_err("The prng self test generate operation for " + "the SHA-512 mode failed with rc=%d\n", ret); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN, + &ws, buf, sizeof(buf), + NULL, 0); + if (ret < 0) { + pr_err("The prng self test generate operation for " + "the SHA-512 mode failed with rc=%d\n", ret); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + + /* check against expected data */ + if (memcmp(buf, random, sizeof(random)) != 0) { + pr_err("The prng self test data test " + "for the SHA-512 mode failed\n"); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + + return 0; +} + + +static int __init prng_sha512_instantiate(void) +{ + int ret, datalen; + u8 seed[64]; + + pr_debug("prng runs in SHA-512 mode " + "with chunksize=%d and reseed_limit=%u\n", + prng_chunk_size, prng_reseed_limit); + + /* memory allocation, prng_data struct init, mutex init */ + datalen = sizeof(struct prng_data_s) + prng_chunk_size; + if (fips_enabled) + datalen += prng_chunk_size; + prng_data = kzalloc(datalen, GFP_KERNEL); + if (!prng_data) { + prng_errorflag = PRNG_INSTANTIATE_FAILED; + return -ENOMEM; + } + mutex_init(&prng_data->mutex); + prng_data->buf = ((u8 *)prng_data) + sizeof(struct prng_data_s); + + /* selftest */ + ret = prng_sha512_selftest(); + if (ret) + goto outfree; + + /* generate initial seed bytestring, first 48 bytes of entropy */ + ret = generate_entropy(seed, 48); + if (ret != 48) + goto outfree; + /* followed by 16 bytes of unique nonce */ + get_tod_clock_ext(seed + 48); + + /* initial seed of the ppno drng */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED, + &prng_data->ppnows, NULL, 0, + seed, sizeof(seed)); + if (ret < 0) { + prng_errorflag = PRNG_SEED_FAILED; + ret = -EIO; + goto outfree; + } + + /* if fips mode is enabled, generate a first block of random + bytes for the FIPS 140-2 Conditional Self Test */ + if (fips_enabled) { + prng_data->prev = prng_data->buf + prng_chunk_size; + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN, + &prng_data->ppnows, + prng_data->prev, + prng_chunk_size, + NULL, 0); + if (ret < 0 || ret != prng_chunk_size) { + prng_errorflag = PRNG_GEN_FAILED; + ret = -EIO; + goto outfree; + } + } + + return 0; + +outfree: + kfree(prng_data); + return ret; +} + + +static void prng_sha512_deinstantiate(void) +{ + pr_debug("The prng module stopped after running in SHA-512 mode\n"); + kzfree(prng_data); +} + + +static int prng_sha512_reseed(void) +{ + int ret; + u8 seed[32]; + + /* generate 32 bytes of fresh entropy */ + ret = generate_entropy(seed, sizeof(seed)); + if (ret != sizeof(seed)) + return ret; + + /* do a reseed of the ppno drng with this bytestring */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED, + &prng_data->ppnows, NULL, 0, + seed, sizeof(seed)); + if (ret) { + prng_errorflag = PRNG_RESEED_FAILED; + return -EIO; + } + + return 0; +} + + +static int prng_sha512_generate(u8 *buf, size_t nbytes) +{ + int ret; + + /* reseed needed ? */ + if (prng_data->ppnows.reseed_counter > prng_reseed_limit) { + ret = prng_sha512_reseed(); + if (ret) + return ret; + } + + /* PPNO generate */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN, + &prng_data->ppnows, buf, nbytes, + NULL, 0); + if (ret < 0 || ret != nbytes) { + prng_errorflag = PRNG_GEN_FAILED; + return -EIO; + } + + /* FIPS 140-2 Conditional Self Test */ + if (fips_enabled) { + if (!memcmp(prng_data->prev, buf, nbytes)) { + prng_errorflag = PRNG_GEN_FAILED; + return -EILSEQ; + } + memcpy(prng_data->prev, buf, nbytes); + } + + return ret; +} + + +/*** file io functions ***/ + +static int prng_open(struct inode *inode, struct file *file) +{ + return nonseekable_open(inode, file); +} + + +static ssize_t prng_tdes_read(struct file *file, char __user *ubuf, + size_t nbytes, loff_t *ppos) +{ + int chunk, n, tmp, ret = 0; + + /* lock prng_data struct */ + if (mutex_lock_interruptible(&prng_data->mutex)) + return -ERESTARTSYS; - /* nbytes can be arbitrary length, we split it into chunks */ while (nbytes) { - /* same as in extract_entropy_user in random.c */ if (need_resched()) { if (signal_pending(current)) { if (ret == 0) ret = -ERESTARTSYS; break; } + /* give mutex free before calling schedule() */ + mutex_unlock(&prng_data->mutex); schedule(); + /* occopy mutex again */ + if (mutex_lock_interruptible(&prng_data->mutex)) { + if (ret == 0) + ret = -ERESTARTSYS; + return ret; + } } /* @@ -112,12 +535,11 @@ static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes, /* PRNG only likes multiples of 8 bytes */ n = (chunk + 7) & -8; - if (p->count > prng_entropy_limit) - prng_seed(8); + if (prng_data->prngws.reseed_counter > prng_reseed_limit) + prng_tdes_seed(8); /* if the CPU supports PRNG stckf is present too */ - asm volatile(".insn s,0xb27c0000,%0" - : "=m" (*((unsigned long long *)p->buf)) : : "cc"); + *((unsigned long long *)prng_data->buf) = get_tod_clock_fast(); /* * Beside the STCKF the input for the TDES-EDE is the output @@ -132,35 +554,259 @@ static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes, * Note: you can still get strict X9.17 conformity by setting * prng_chunk_size to 8 bytes. */ - tmp = crypt_s390_kmc(KMC_PRNG, parm_block, p->buf, p->buf, n); - BUG_ON((tmp < 0) || (tmp != n)); + tmp = crypt_s390_kmc(KMC_PRNG, prng_data->prngws.parm_block, + prng_data->buf, prng_data->buf, n); + if (tmp < 0 || tmp != n) { + ret = -EIO; + break; + } - p->count += n; + prng_data->prngws.byte_counter += n; + prng_data->prngws.reseed_counter += n; - if (copy_to_user(ubuf, p->buf, chunk)) + if (copy_to_user(ubuf, prng_data->buf, chunk)) return -EFAULT; nbytes -= chunk; ret += chunk; ubuf += chunk; } + + /* unlock prng_data struct */ + mutex_unlock(&prng_data->mutex); + return ret; } -static const struct file_operations prng_fops = { + +static ssize_t prng_sha512_read(struct file *file, char __user *ubuf, + size_t nbytes, loff_t *ppos) +{ + int n, ret = 0; + u8 *p; + + /* if errorflag is set do nothing and return 'broken pipe' */ + if (prng_errorflag) + return -EPIPE; + + /* lock prng_data struct */ + if (mutex_lock_interruptible(&prng_data->mutex)) + return -ERESTARTSYS; + + while (nbytes) { + if (need_resched()) { + if (signal_pending(current)) { + if (ret == 0) + ret = -ERESTARTSYS; + break; + } + /* give mutex free before calling schedule() */ + mutex_unlock(&prng_data->mutex); + schedule(); + /* occopy mutex again */ + if (mutex_lock_interruptible(&prng_data->mutex)) { + if (ret == 0) + ret = -ERESTARTSYS; + return ret; + } + } + if (prng_data->rest) { + /* push left over random bytes from the previous read */ + p = prng_data->buf + prng_chunk_size - prng_data->rest; + n = (nbytes < prng_data->rest) ? + nbytes : prng_data->rest; + prng_data->rest -= n; + } else { + /* generate one chunk of random bytes into read buf */ + p = prng_data->buf; + n = prng_sha512_generate(p, prng_chunk_size); + if (n < 0) { + ret = n; + break; + } + if (nbytes < prng_chunk_size) { + n = nbytes; + prng_data->rest = prng_chunk_size - n; + } else { + n = prng_chunk_size; + prng_data->rest = 0; + } + } + if (copy_to_user(ubuf, p, n)) { + ret = -EFAULT; + break; + } + ubuf += n; + nbytes -= n; + ret += n; + } + + /* unlock prng_data struct */ + mutex_unlock(&prng_data->mutex); + + return ret; +} + + +/*** sysfs stuff ***/ + +static const struct file_operations prng_sha512_fops = { + .owner = THIS_MODULE, + .open = &prng_open, + .release = NULL, + .read = &prng_sha512_read, + .llseek = noop_llseek, +}; +static const struct file_operations prng_tdes_fops = { .owner = THIS_MODULE, .open = &prng_open, .release = NULL, - .read = &prng_read, + .read = &prng_tdes_read, .llseek = noop_llseek, }; -static struct miscdevice prng_dev = { +static struct miscdevice prng_sha512_dev = { + .name = "prandom", + .minor = MISC_DYNAMIC_MINOR, + .fops = &prng_sha512_fops, +}; +static struct miscdevice prng_tdes_dev = { .name = "prandom", .minor = MISC_DYNAMIC_MINOR, - .fops = &prng_fops, + .fops = &prng_tdes_fops, }; + +/* chunksize attribute (ro) */ +static ssize_t prng_chunksize_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size); +} +static DEVICE_ATTR(chunksize, 0444, prng_chunksize_show, NULL); + +/* counter attribute (ro) */ +static ssize_t prng_counter_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + u64 counter; + + if (mutex_lock_interruptible(&prng_data->mutex)) + return -ERESTARTSYS; + if (prng_mode == PRNG_MODE_SHA512) + counter = prng_data->ppnows.stream_bytes; + else + counter = prng_data->prngws.byte_counter; + mutex_unlock(&prng_data->mutex); + + return snprintf(buf, PAGE_SIZE, "%llu\n", counter); +} +static DEVICE_ATTR(byte_counter, 0444, prng_counter_show, NULL); + +/* errorflag attribute (ro) */ +static ssize_t prng_errorflag_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag); +} +static DEVICE_ATTR(errorflag, 0444, prng_errorflag_show, NULL); + +/* mode attribute (ro) */ +static ssize_t prng_mode_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (prng_mode == PRNG_MODE_TDES) + return snprintf(buf, PAGE_SIZE, "TDES\n"); + else + return snprintf(buf, PAGE_SIZE, "SHA512\n"); +} +static DEVICE_ATTR(mode, 0444, prng_mode_show, NULL); + +/* reseed attribute (w) */ +static ssize_t prng_reseed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + if (mutex_lock_interruptible(&prng_data->mutex)) + return -ERESTARTSYS; + prng_sha512_reseed(); + mutex_unlock(&prng_data->mutex); + + return count; +} +static DEVICE_ATTR(reseed, 0200, NULL, prng_reseed_store); + +/* reseed limit attribute (rw) */ +static ssize_t prng_reseed_limit_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit); +} +static ssize_t prng_reseed_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned limit; + + if (sscanf(buf, "%u\n", &limit) != 1) + return -EINVAL; + + if (prng_mode == PRNG_MODE_SHA512) { + if (limit < PRNG_RESEED_LIMIT_SHA512_LOWER) + return -EINVAL; + } else { + if (limit < PRNG_RESEED_LIMIT_TDES_LOWER) + return -EINVAL; + } + + prng_reseed_limit = limit; + + return count; +} +static DEVICE_ATTR(reseed_limit, 0644, + prng_reseed_limit_show, prng_reseed_limit_store); + +/* strength attribute (ro) */ +static ssize_t prng_strength_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "256\n"); +} +static DEVICE_ATTR(strength, 0444, prng_strength_show, NULL); + +static struct attribute *prng_sha512_dev_attrs[] = { + &dev_attr_errorflag.attr, + &dev_attr_chunksize.attr, + &dev_attr_byte_counter.attr, + &dev_attr_mode.attr, + &dev_attr_reseed.attr, + &dev_attr_reseed_limit.attr, + &dev_attr_strength.attr, + NULL +}; +static struct attribute *prng_tdes_dev_attrs[] = { + &dev_attr_chunksize.attr, + &dev_attr_byte_counter.attr, + &dev_attr_mode.attr, + NULL +}; + +static struct attribute_group prng_sha512_dev_attr_group = { + .attrs = prng_sha512_dev_attrs +}; +static struct attribute_group prng_tdes_dev_attr_group = { + .attrs = prng_tdes_dev_attrs +}; + + +/*** module init and exit ***/ + static int __init prng_init(void) { int ret; @@ -169,43 +815,105 @@ static int __init prng_init(void) if (!crypt_s390_func_available(KMC_PRNG, CRYPT_S390_MSA)) return -EOPNOTSUPP; - if (prng_chunk_size < 8) - return -EINVAL; + /* choose prng mode */ + if (prng_mode != PRNG_MODE_TDES) { + /* check for MSA5 support for PPNO operations */ + if (!crypt_s390_func_available(PPNO_SHA512_DRNG_GEN, + CRYPT_S390_MSA5)) { + if (prng_mode == PRNG_MODE_SHA512) { + pr_err("The prng module cannot " + "start in SHA-512 mode\n"); + return -EOPNOTSUPP; + } + prng_mode = PRNG_MODE_TDES; + } else + prng_mode = PRNG_MODE_SHA512; + } - p = kmalloc(sizeof(struct s390_prng_data), GFP_KERNEL); - if (!p) - return -ENOMEM; - p->count = 0; + if (prng_mode == PRNG_MODE_SHA512) { - p->buf = kmalloc(prng_chunk_size, GFP_KERNEL); - if (!p->buf) { - ret = -ENOMEM; - goto out_free; - } + /* SHA512 mode */ - /* initialize the PRNG, add 128 bits of entropy */ - prng_seed(16); + if (prng_chunk_size < PRNG_CHUNKSIZE_SHA512_MIN + || prng_chunk_size > PRNG_CHUNKSIZE_SHA512_MAX) + return -EINVAL; + prng_chunk_size = (prng_chunk_size + 0x3f) & ~0x3f; - ret = misc_register(&prng_dev); - if (ret) - goto out_buf; - return 0; + if (prng_reseed_limit == 0) + prng_reseed_limit = PRNG_RESEED_LIMIT_SHA512; + else if (prng_reseed_limit < PRNG_RESEED_LIMIT_SHA512_LOWER) + return -EINVAL; + + ret = prng_sha512_instantiate(); + if (ret) + goto out; + + ret = misc_register(&prng_sha512_dev); + if (ret) { + prng_sha512_deinstantiate(); + goto out; + } + ret = sysfs_create_group(&prng_sha512_dev.this_device->kobj, + &prng_sha512_dev_attr_group); + if (ret) { + misc_deregister(&prng_sha512_dev); + prng_sha512_deinstantiate(); + goto out; + } -out_buf: - kfree(p->buf); -out_free: - kfree(p); + } else { + + /* TDES mode */ + + if (prng_chunk_size < PRNG_CHUNKSIZE_TDES_MIN + || prng_chunk_size > PRNG_CHUNKSIZE_TDES_MAX) + return -EINVAL; + prng_chunk_size = (prng_chunk_size + 0x07) & ~0x07; + + if (prng_reseed_limit == 0) + prng_reseed_limit = PRNG_RESEED_LIMIT_TDES; + else if (prng_reseed_limit < PRNG_RESEED_LIMIT_TDES_LOWER) + return -EINVAL; + + ret = prng_tdes_instantiate(); + if (ret) + goto out; + + ret = misc_register(&prng_tdes_dev); + if (ret) { + prng_tdes_deinstantiate(); + goto out; + } + ret = sysfs_create_group(&prng_tdes_dev.this_device->kobj, + &prng_tdes_dev_attr_group); + if (ret) { + misc_deregister(&prng_tdes_dev); + prng_tdes_deinstantiate(); + goto out; + } + + } + +out: return ret; } + static void __exit prng_exit(void) { - /* wipe me */ - kzfree(p->buf); - kfree(p); - - misc_deregister(&prng_dev); + if (prng_mode == PRNG_MODE_SHA512) { + sysfs_remove_group(&prng_sha512_dev.this_device->kobj, + &prng_sha512_dev_attr_group); + misc_deregister(&prng_sha512_dev); + prng_sha512_deinstantiate(); + } else { + sysfs_remove_group(&prng_tdes_dev.this_device->kobj, + &prng_tdes_dev_attr_group); + misc_deregister(&prng_tdes_dev); + prng_tdes_deinstantiate(); + } } + module_init(prng_init); module_exit(prng_exit); diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index 694bcd6..2f924bc 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -26,6 +26,9 @@ /* Not more than 2GB */ #define KEXEC_CONTROL_MEMORY_LIMIT (1UL<<31) +/* Allocate control page with GFP_DMA */ +#define KEXEC_CONTROL_MEMORY_GFP GFP_DMA + /* Maximum address we can use for the crash control pages */ #define KEXEC_CRASH_CONTROL_MEMORY_LIMIT (-1UL) diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index a5e6562..d29ad95 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -14,7 +14,9 @@ typedef struct { unsigned long asce_bits; unsigned long asce_limit; unsigned long vdso_base; - /* The mmu context has extended page tables. */ + /* The mmu context allocates 4K page tables. */ + unsigned int alloc_pgste:1; + /* The mmu context uses extended page tables. */ unsigned int has_pgste:1; /* The mmu context uses storage keys. */ unsigned int use_skey:1; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index d25d9ff..fb1b93e 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -20,8 +20,11 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.flush_mm = 0; mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; mm->context.asce_bits |= _ASCE_TYPE_REGION3; +#ifdef CONFIG_PGSTE + mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; +#endif mm->context.asce_limit = STACK_TOP_MAX; crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 51e7fb6..7b7858f 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -21,6 +21,7 @@ void crst_table_free(struct mm_struct *, unsigned long *); unsigned long *page_table_alloc(struct mm_struct *); void page_table_free(struct mm_struct *, unsigned long *); void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long); +extern int page_table_allocate_pgste; int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, unsigned long key, bool nq); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 989cfae..fc64239 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -12,12 +12,9 @@ #define _ASM_S390_PGTABLE_H /* - * The Linux memory management assumes a three-level page table setup. For - * s390 31 bit we "fold" the mid level into the top-level page table, so - * that we physically have the same two-level page table as the s390 mmu - * expects in 31 bit mode. For s390 64 bit we use three of the five levels - * the hardware provides (region first and region second tables are not - * used). + * The Linux memory management assumes a three-level page table setup. + * For s390 64 bit we use up to four of the five levels the hardware + * provides (region first tables are not used). * * The "pgd_xxx()" functions are trivial for a folded two-level * setup: the pgd is never bad, and a pmd always exists (as it's folded @@ -101,8 +98,8 @@ extern unsigned long zero_page_mask; #ifndef __ASSEMBLY__ /* - * The vmalloc and module area will always be on the topmost area of the kernel - * mapping. We reserve 96MB (31bit) / 128GB (64bit) for vmalloc and modules. + * The vmalloc and module area will always be on the topmost area of the + * kernel mapping. We reserve 128GB (64bit) for vmalloc and modules. * On 64 bit kernels we have a 2GB area at the top of the vmalloc area where * modules will reside. That makes sure that inter module branches always * happen without trampolines and in addition the placement within a 2GB frame @@ -131,38 +128,6 @@ static inline int is_module_addr(void *addr) } /* - * A 31 bit pagetable entry of S390 has following format: - * | PFRA | | OS | - * 0 0IP0 - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * I Page-Invalid Bit: Page is not available for address-translation - * P Page-Protection Bit: Store access not possible for page - * - * A 31 bit segmenttable entry of S390 has following format: - * | P-table origin | |PTL - * 0 IC - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * I Segment-Invalid Bit: Segment is not available for address-translation - * C Common-Segment Bit: Segment is not private (PoP 3-30) - * PTL Page-Table-Length: Page-table length (PTL+1*16 entries -> up to 256) - * - * The 31 bit segmenttable origin of S390 has following format: - * - * |S-table origin | | STL | - * X **GPS - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * X Space-Switch event: - * G Segment-Invalid Bit: * - * P Private-Space Bit: Segment is not private (PoP 3-30) - * S Storage-Alteration: - * STL Segment-Table-Length: Segment-table length (STL+1*16 entries -> up to 2048) - * * A 64 bit pagetable entry of S390 has following format: * | PFRA |0IPC| OS | * 0000000000111111111122222222223333333333444444444455555555556666 @@ -220,7 +185,6 @@ static inline int is_module_addr(void *addr) /* Software bits in the page table entry */ #define _PAGE_PRESENT 0x001 /* SW pte present bit */ -#define _PAGE_TYPE 0x002 /* SW pte type bit */ #define _PAGE_YOUNG 0x004 /* SW pte young bit */ #define _PAGE_DIRTY 0x008 /* SW pte dirty bit */ #define _PAGE_READ 0x010 /* SW pte read bit */ @@ -240,31 +204,34 @@ static inline int is_module_addr(void *addr) * table lock held. * * The following table gives the different possible bit combinations for - * the pte hardware and software bits in the last 12 bits of a pte: + * the pte hardware and software bits in the last 12 bits of a pte + * (. unassigned bit, x don't care, t swap type): * * 842100000000 * 000084210000 * 000000008421 - * .IR...wrdytp - * empty .10...000000 - * swap .10...xxxx10 - * file .11...xxxxx0 - * prot-none, clean, old .11...000001 - * prot-none, clean, young .11...000101 - * prot-none, dirty, old .10...001001 - * prot-none, dirty, young .10...001101 - * read-only, clean, old .11...010001 - * read-only, clean, young .01...010101 - * read-only, dirty, old .11...011001 - * read-only, dirty, young .01...011101 - * read-write, clean, old .11...110001 - * read-write, clean, young .01...110101 - * read-write, dirty, old .10...111001 - * read-write, dirty, young .00...111101 + * .IR.uswrdy.p + * empty .10.00000000 + * swap .11..ttttt.0 + * prot-none, clean, old .11.xx0000.1 + * prot-none, clean, young .11.xx0001.1 + * prot-none, dirty, old .10.xx0010.1 + * prot-none, dirty, young .10.xx0011.1 + * read-only, clean, old .11.xx0100.1 + * read-only, clean, young .01.xx0101.1 + * read-only, dirty, old .11.xx0110.1 + * read-only, dirty, young .01.xx0111.1 + * read-write, clean, old .11.xx1100.1 + * read-write, clean, young .01.xx1101.1 + * read-write, dirty, old .10.xx1110.1 + * read-write, dirty, young .00.xx1111.1 + * HW-bits: R read-only, I invalid + * SW-bits: p present, y young, d dirty, r read, w write, s special, + * u unused, l large * - * pte_present is true for the bit pattern .xx...xxxxx1, (pte & 0x001) == 0x001 - * pte_none is true for the bit pattern .10...xxxx00, (pte & 0x603) == 0x400 - * pte_swap is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402 + * pte_none is true for the bit pattern .10.00000000, pte == 0x400 + * pte_swap is true for the bit pattern .11..ooooo.0, (pte & 0x201) == 0x200 + * pte_present is true for the bit pattern .xx.xxxxxx.1, (pte & 0x001) == 0x001 */ /* Bits in the segment/region table address-space-control-element */ @@ -335,6 +302,8 @@ static inline int is_module_addr(void *addr) * read-write, dirty, young 11..0...0...11 * The segment table origin is used to distinguish empty (origin==0) from * read-write, old segment table entries (origin!=0) + * HW-bits: R read-only, I invalid + * SW-bits: y young, d dirty, r read, w write */ #define _SEGMENT_ENTRY_SPLIT_BIT 11 /* THP splitting bit number */ @@ -423,6 +392,15 @@ static inline int mm_has_pgste(struct mm_struct *mm) return 0; } +static inline int mm_alloc_pgste(struct mm_struct *mm) +{ +#ifdef CONFIG_PGSTE + if (unlikely(mm->context.alloc_pgste)) + return 1; +#endif + return 0; +} + /* * In the case that a guest uses storage keys * faults should no longer be backed by zero pages @@ -582,10 +560,9 @@ static inline int pte_none(pte_t pte) static inline int pte_swap(pte_t pte) { - /* Bit pattern: (pte & 0x603) == 0x402 */ - return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT | - _PAGE_TYPE | _PAGE_PRESENT)) - == (_PAGE_INVALID | _PAGE_TYPE); + /* Bit pattern: (pte & 0x201) == 0x200 */ + return (pte_val(pte) & (_PAGE_PROTECT | _PAGE_PRESENT)) + == _PAGE_PROTECT; } static inline int pte_special(pte_t pte) @@ -1586,51 +1563,51 @@ static inline int has_transparent_hugepage(void) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * 31 bit swap entry format: - * A page-table entry has some bits we have to treat in a special way. - * Bits 0, 20 and bit 23 have to be zero, otherwise an specification - * exception will occur instead of a page translation exception. The - * specifiation exception has the bad habit not to store necessary - * information in the lowcore. - * Bits 21, 22, 30 and 31 are used to indicate the page type. - * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402 - * This leaves the bits 1-19 and bits 24-29 to store type and offset. - * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19 - * plus 24 for the offset. - * 0| offset |0110|o|type |00| - * 0 0000000001111111111 2222 2 22222 33 - * 0 1234567890123456789 0123 4 56789 01 - * * 64 bit swap entry format: * A page-table entry has some bits we have to treat in a special way. * Bits 52 and bit 55 have to be zero, otherwise an specification * exception will occur instead of a page translation exception. The * specifiation exception has the bad habit not to store necessary * information in the lowcore. - * Bits 53, 54, 62 and 63 are used to indicate the page type. - * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402 - * This leaves the bits 0-51 and bits 56-61 to store type and offset. - * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51 - * plus 56 for the offset. - * | offset |0110|o|type |00| - * 0000000000111111111122222222223333333333444444444455 5555 5 55566 66 - * 0123456789012345678901234567890123456789012345678901 2345 6 78901 23 + * Bits 54 and 63 are used to indicate the page type. + * A swap pte is indicated by bit pattern (pte & 0x201) == 0x200 + * This leaves the bits 0-51 and bits 56-62 to store type and offset. + * We use the 5 bits from 57-61 for the type and the 52 bits from 0-51 + * for the offset. + * | offset |01100|type |00| + * |0000000000111111111122222222223333333333444444444455|55555|55566|66| + * |0123456789012345678901234567890123456789012345678901|23456|78901|23| */ -#define __SWP_OFFSET_MASK (~0UL >> 11) +#define __SWP_OFFSET_MASK ((1UL << 52) - 1) +#define __SWP_OFFSET_SHIFT 12 +#define __SWP_TYPE_MASK ((1UL << 5) - 1) +#define __SWP_TYPE_SHIFT 2 static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) { pte_t pte; - offset &= __SWP_OFFSET_MASK; - pte_val(pte) = _PAGE_INVALID | _PAGE_TYPE | ((type & 0x1f) << 2) | - ((offset & 1UL) << 7) | ((offset & ~1UL) << 11); + + pte_val(pte) = _PAGE_INVALID | _PAGE_PROTECT; + pte_val(pte) |= (offset & __SWP_OFFSET_MASK) << __SWP_OFFSET_SHIFT; + pte_val(pte) |= (type & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT; return pte; } -#define __swp_type(entry) (((entry).val >> 2) & 0x1f) -#define __swp_offset(entry) (((entry).val >> 11) | (((entry).val >> 7) & 1)) -#define __swp_entry(type,offset) ((swp_entry_t) { pte_val(mk_swap_pte((type),(offset))) }) +static inline unsigned long __swp_type(swp_entry_t entry) +{ + return (entry.val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK; +} + +static inline unsigned long __swp_offset(swp_entry_t entry) +{ + return (entry.val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK; +} + +static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset) +{ + return (swp_entry_t) { pte_val(mk_swap_pte(type, offset)) }; +} #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 210ffed..e617e74 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -14,20 +14,23 @@ static inline pmd_t __pte_to_pmd(pte_t pte) /* * Convert encoding pte bits pmd bits - * .IR...wrdytp dy..R...I...wr - * empty .10...000000 -> 00..0...1...00 - * prot-none, clean, old .11...000001 -> 00..1...1...00 - * prot-none, clean, young .11...000101 -> 01..1...1...00 - * prot-none, dirty, old .10...001001 -> 10..1...1...00 - * prot-none, dirty, young .10...001101 -> 11..1...1...00 - * read-only, clean, old .11...010001 -> 00..1...1...01 - * read-only, clean, young .01...010101 -> 01..1...0...01 - * read-only, dirty, old .11...011001 -> 10..1...1...01 - * read-only, dirty, young .01...011101 -> 11..1...0...01 - * read-write, clean, old .11...110001 -> 00..0...1...11 - * read-write, clean, young .01...110101 -> 01..0...0...11 - * read-write, dirty, old .10...111001 -> 10..0...1...11 - * read-write, dirty, young .00...111101 -> 11..0...0...11 + * lIR.uswrdy.p dy..R...I...wr + * empty 010.000000.0 -> 00..0...1...00 + * prot-none, clean, old 111.000000.1 -> 00..1...1...00 + * prot-none, clean, young 111.000001.1 -> 01..1...1...00 + * prot-none, dirty, old 111.000010.1 -> 10..1...1...00 + * prot-none, dirty, young 111.000011.1 -> 11..1...1...00 + * read-only, clean, old 111.000100.1 -> 00..1...1...01 + * read-only, clean, young 101.000101.1 -> 01..1...0...01 + * read-only, dirty, old 111.000110.1 -> 10..1...1...01 + * read-only, dirty, young 101.000111.1 -> 11..1...0...01 + * read-write, clean, old 111.001100.1 -> 00..1...1...11 + * read-write, clean, young 101.001101.1 -> 01..1...0...11 + * read-write, dirty, old 110.001110.1 -> 10..0...1...11 + * read-write, dirty, young 100.001111.1 -> 11..0...0...11 + * HW-bits: R read-only, I invalid + * SW-bits: p present, y young, d dirty, r read, w write, s special, + * u unused, l large */ if (pte_present(pte)) { pmd_val(pmd) = pte_val(pte) & PAGE_MASK; @@ -48,20 +51,23 @@ static inline pte_t __pmd_to_pte(pmd_t pmd) /* * Convert encoding pmd bits pte bits - * dy..R...I...wr .IR...wrdytp - * empty 00..0...1...00 -> .10...001100 - * prot-none, clean, old 00..0...1...00 -> .10...000001 - * prot-none, clean, young 01..0...1...00 -> .10...000101 - * prot-none, dirty, old 10..0...1...00 -> .10...001001 - * prot-none, dirty, young 11..0...1...00 -> .10...001101 - * read-only, clean, old 00..1...1...01 -> .11...010001 - * read-only, clean, young 01..1...1...01 -> .11...010101 - * read-only, dirty, old 10..1...1...01 -> .11...011001 - * read-only, dirty, young 11..1...1...01 -> .11...011101 - * read-write, clean, old 00..0...1...11 -> .10...110001 - * read-write, clean, young 01..0...1...11 -> .10...110101 - * read-write, dirty, old 10..0...1...11 -> .10...111001 - * read-write, dirty, young 11..0...1...11 -> .10...111101 + * dy..R...I...wr lIR.uswrdy.p + * empty 00..0...1...00 -> 010.000000.0 + * prot-none, clean, old 00..1...1...00 -> 111.000000.1 + * prot-none, clean, young 01..1...1...00 -> 111.000001.1 + * prot-none, dirty, old 10..1...1...00 -> 111.000010.1 + * prot-none, dirty, young 11..1...1...00 -> 111.000011.1 + * read-only, clean, old 00..1...1...01 -> 111.000100.1 + * read-only, clean, young 01..1...0...01 -> 101.000101.1 + * read-only, dirty, old 10..1...1...01 -> 111.000110.1 + * read-only, dirty, young 11..1...0...01 -> 101.000111.1 + * read-write, clean, old 00..1...1...11 -> 111.001100.1 + * read-write, clean, young 01..1...0...11 -> 101.001101.1 + * read-write, dirty, old 10..0...1...11 -> 110.001110.1 + * read-write, dirty, young 11..0...0...11 -> 100.001111.1 + * HW-bits: R read-only, I invalid + * SW-bits: p present, y young, d dirty, r read, w write, s special, + * u unused, l large */ if (pmd_present(pmd)) { pte_val(pte) = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN_LARGE; @@ -70,8 +76,8 @@ static inline pte_t __pmd_to_pte(pmd_t pmd) pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) << 4; pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) << 5; pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT); - pmd_val(pmd) |= (pte_val(pte) & _PAGE_DIRTY) << 10; - pmd_val(pmd) |= (pte_val(pte) & _PAGE_YOUNG) << 10; + pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) >> 10; + pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) >> 10; } else pte_val(pte) = _PAGE_INVALID; return pte; diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 33f5894..b33f661 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -18,6 +18,7 @@ #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/swapops.h> +#include <linux/sysctl.h> #include <linux/ksm.h> #include <linux/mman.h> @@ -920,6 +921,40 @@ unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr) } EXPORT_SYMBOL(get_guest_storage_key); +static int page_table_allocate_pgste_min = 0; +static int page_table_allocate_pgste_max = 1; +int page_table_allocate_pgste = 0; +EXPORT_SYMBOL(page_table_allocate_pgste); + +static struct ctl_table page_table_sysctl[] = { + { + .procname = "allocate_pgste", + .data = &page_table_allocate_pgste, + .maxlen = sizeof(int), + .mode = S_IRUGO | S_IWUSR, + .proc_handler = proc_dointvec, + .extra1 = &page_table_allocate_pgste_min, + .extra2 = &page_table_allocate_pgste_max, + }, + { } +}; + +static struct ctl_table page_table_sysctl_dir[] = { + { + .procname = "vm", + .maxlen = 0, + .mode = 0555, + .child = page_table_sysctl, + }, + { } +}; + +static int __init page_table_register_sysctl(void) +{ + return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM; +} +__initcall(page_table_register_sysctl); + #else /* CONFIG_PGSTE */ static inline int page_table_with_pgste(struct page *page) @@ -963,7 +998,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) struct page *uninitialized_var(page); unsigned int mask, bit; - if (mm_has_pgste(mm)) + if (mm_alloc_pgste(mm)) return page_table_alloc_pgste(mm); /* Allocate fragments of a 4K page as 1K/2K page table */ spin_lock_bh(&mm->context.list_lock); @@ -1165,116 +1200,25 @@ static inline void thp_split_mm(struct mm_struct *mm) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb, - struct mm_struct *mm, pud_t *pud, - unsigned long addr, unsigned long end) -{ - unsigned long next, *table, *new; - struct page *page; - spinlock_t *ptl; - pmd_t *pmd; - - pmd = pmd_offset(pud, addr); - do { - next = pmd_addr_end(addr, end); -again: - if (pmd_none_or_clear_bad(pmd)) - continue; - table = (unsigned long *) pmd_deref(*pmd); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); - if (page_table_with_pgste(page)) - continue; - /* Allocate new page table with pgstes */ - new = page_table_alloc_pgste(mm); - if (!new) - return -ENOMEM; - - ptl = pmd_lock(mm, pmd); - if (likely((unsigned long *) pmd_deref(*pmd) == table)) { - /* Nuke pmd entry pointing to the "short" page table */ - pmdp_flush_lazy(mm, addr, pmd); - pmd_clear(pmd); - /* Copy ptes from old table to new table */ - memcpy(new, table, PAGE_SIZE/2); - clear_table(table, _PAGE_INVALID, PAGE_SIZE/2); - /* Establish new table */ - pmd_populate(mm, pmd, (pte_t *) new); - /* Free old table with rcu, there might be a walker! */ - page_table_free_rcu(tlb, table, addr); - new = NULL; - } - spin_unlock(ptl); - if (new) { - page_table_free_pgste(new); - goto again; - } - } while (pmd++, addr = next, addr != end); - - return addr; -} - -static unsigned long page_table_realloc_pud(struct mmu_gather *tlb, - struct mm_struct *mm, pgd_t *pgd, - unsigned long addr, unsigned long end) -{ - unsigned long next; - pud_t *pud; - - pud = pud_offset(pgd, addr); - do { - next = pud_addr_end(addr, end); - if (pud_none_or_clear_bad(pud)) - continue; - next = page_table_realloc_pmd(tlb, mm, pud, addr, next); - if (unlikely(IS_ERR_VALUE(next))) - return next; - } while (pud++, addr = next, addr != end); - - return addr; -} - -static unsigned long page_table_realloc(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long addr, unsigned long end) -{ - unsigned long next; - pgd_t *pgd; - - pgd = pgd_offset(mm, addr); - do { - next = pgd_addr_end(addr, end); - if (pgd_none_or_clear_bad(pgd)) - continue; - next = page_table_realloc_pud(tlb, mm, pgd, addr, next); - if (unlikely(IS_ERR_VALUE(next))) - return next; - } while (pgd++, addr = next, addr != end); - - return 0; -} - /* * switch on pgstes for its userspace process (for kvm) */ int s390_enable_sie(void) { - struct task_struct *tsk = current; - struct mm_struct *mm = tsk->mm; - struct mmu_gather tlb; + struct mm_struct *mm = current->mm; /* Do we have pgstes? if yes, we are done */ - if (mm_has_pgste(tsk->mm)) + if (mm_has_pgste(mm)) return 0; - + /* Fail if the page tables are 2K */ + if (!mm_alloc_pgste(mm)) + return -EINVAL; down_write(&mm->mmap_sem); + mm->context.has_pgste = 1; /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - /* Reallocate the page tables with pgstes */ - tlb_gather_mmu(&tlb, mm, 0, TASK_SIZE); - if (!page_table_realloc(&tlb, mm, 0, TASK_SIZE)) - mm->context.has_pgste = 1; - tlb_finish_mmu(&tlb, 0, TASK_SIZE); up_write(&mm->mmap_sem); - return mm->context.has_pgste ? 0 : -ENOMEM; + return 0; } EXPORT_SYMBOL_GPL(s390_enable_sie); diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index 6873f00..d366675 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -774,7 +774,7 @@ static void __init zone_sizes_init(void) * though, there'll be no lowmem, so we just alloc_bootmem * the memmap. There will be no percpu memory either. */ - if (i != 0 && cpumask_test_cpu(i, &isolnodes)) { + if (i != 0 && node_isset(i, isolnodes)) { node_memmap_pfn[i] = alloc_bootmem_pfn(0, memmap_size, 0); BUG_ON(node_percpu[i] != 0); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 25b1cc0..d6b078e 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,7 +95,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; - u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index e5ecd20..2f355d2 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,46 +141,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } -static struct pvclock_vsyscall_time_info *pvclock_vdso_info; - -static struct pvclock_vsyscall_time_info * -pvclock_get_vsyscall_user_time_info(int cpu) -{ - if (!pvclock_vdso_info) { - BUG(); - return NULL; - } - - return &pvclock_vdso_info[cpu]; -} - -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) -{ - return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; -} - #ifdef CONFIG_X86_64 -static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, - void *v) -{ - struct task_migration_notifier *mn = v; - struct pvclock_vsyscall_time_info *pvti; - - pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); - - /* this is NULL when pvclock vsyscall is not initialized */ - if (unlikely(pvti == NULL)) - return NOTIFY_DONE; - - pvti->migrate_count++; - - return NOTIFY_DONE; -} - -static struct notifier_block pvclock_migrate = { - .notifier_call = pvclock_task_migrate, -}; - /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -194,17 +155,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - pvclock_vdso_info = i; - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } - - register_task_migration_notifier(&pvclock_migrate); - return 0; } #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ed31c31..c73efcd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1669,12 +1669,28 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) &guest_hv_clock, sizeof(guest_hv_clock)))) return 0; - /* - * The interface expects us to write an even number signaling that the - * update is finished. Since the guest won't see the intermediate - * state, we just increase by 2 at the end. + /* This VCPU is paused, but it's legal for a guest to read another + * VCPU's kvmclock, so we really have to follow the specification where + * it says that version is odd if data is being modified, and even after + * it is consistent. + * + * Version field updates must be kept separate. This is because + * kvm_write_guest_cached might use a "rep movs" instruction, and + * writes within a string instruction are weakly ordered. So there + * are three writes overall. + * + * As a small optimization, only write the version field in the first + * and third write. The vcpu->pv_time cache is still valid, because the + * version field is the first in the struct. */ - vcpu->hv_clock.version = guest_hv_clock.version + 2; + BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); + + vcpu->hv_clock.version = guest_hv_clock.version + 1; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); + + smp_wmb(); /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); @@ -1695,6 +1711,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) kvm_write_guest_cached(v->kvm, &vcpu->pv_time, &vcpu->hv_clock, sizeof(vcpu->hv_clock)); + + smp_wmb(); + + vcpu->hv_clock.version++; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); return 0; } diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 40d2473..9793322 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,15 +82,18 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; - u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * When looping to get a consistent (time-info, tsc) pair, we - * also need to deal with the possibility we can switch vcpus, - * so make sure we always re-fetch time-info for the current vcpu. + * Note: hypervisor must guarantee that: + * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. + * 2. that per-CPU pvclock time info is updated if the + * underlying CPU changes. + * 3. that version is increased whenever underlying CPU + * changes. + * */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -99,27 +102,20 @@ static notrace cycle_t vread_pvclock(int *mode) * __getcpu() calls (Gleb). */ - /* Make sure migrate_count will change if we leave the VCPU. */ - do { - pvti = get_pvti(cpu); - migrate_count = pvti->migrate_count; - - cpu1 = cpu; - cpu = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1)); + pvti = get_pvti(cpu); version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* * Test we're still on the cpu as well as the version. - * - We must read TSC of pvti's VCPU. - * - KVM doesn't follow the versioning protocol, so data could - * change before version if we left the VCPU. + * We could have been migrated just after the first + * vgetcpu but before fetching the version, so we + * wouldn't notice a version change. */ - smp_rmb(); - } while (unlikely((pvti->pvti.version & 1) || - pvti->pvti.version != version || - pvti->migrate_count != migrate_count)); + cpu1 = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1 || + (pvti->pvti.version & 1) || + pvti->pvti.version != version)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index cd82762..01504c8 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -684,7 +684,7 @@ static int acpi_sbs_add(struct acpi_device *device) if (!sbs_manager_broken) { result = acpi_manager_get_info(sbs); if (!result) { - sbs->manager_present = 0; + sbs->manager_present = 1; for (id = 0; id < MAX_SBS_BAT; ++id) if ((sbs->batteries_supported & (1 << id))) acpi_battery_add(sbs, id); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 8125233..ec6c5c6 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -2264,6 +2264,11 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request) result, xferred); if (!img_request->result) img_request->result = result; + /* + * Need to end I/O on the entire obj_request worth of + * bytes in case of error. + */ + xferred = obj_request->length; } /* Image object requests don't own their page array */ diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 7a73a27..61c417b 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -158,9 +158,18 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, int entered_state; struct cpuidle_state *target_state = &drv->states[index]; + bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); ktime_t time_start, time_end; s64 diff; + /* + * Tell the time framework to switch to a broadcast timer because our + * local timer will be shut down. If a local timer is used from another + * CPU as a broadcast timer, this call may fail if it is not available. + */ + if (broadcast && tick_broadcast_enter()) + return -EBUSY; + trace_cpu_idle_rcuidle(index, dev->cpu); time_start = ktime_get(); @@ -169,6 +178,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, time_end = ktime_get(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + if (broadcast) { + if (WARN_ON_ONCE(!irqs_disabled())) + local_irq_disable(); + + tick_broadcast_exit(); + } + if (!cpuidle_state_is_coupled(dev, drv, entered_state)) local_irq_enable(); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index c8a18e4..720ceeb 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1298,21 +1298,22 @@ static int table_load(struct dm_ioctl *param, size_t param_size) goto err_unlock_md_type; } - if (dm_get_md_type(md) == DM_TYPE_NONE) + if (dm_get_md_type(md) == DM_TYPE_NONE) { /* Initial table load: acquire type of table. */ dm_set_md_type(md, dm_table_get_type(t)); - else if (dm_get_md_type(md) != dm_table_get_type(t)) { + + /* setup md->queue to reflect md's type (may block) */ + r = dm_setup_md_queue(md); + if (r) { + DMWARN("unable to set up device queue for new table."); + goto err_unlock_md_type; + } + } else if (dm_get_md_type(md) != dm_table_get_type(t)) { DMWARN("can't change device type after initial table load."); r = -EINVAL; goto err_unlock_md_type; } - /* setup md->queue to reflect md's type (may block) */ - r = dm_setup_md_queue(md); - if (r) { - DMWARN("unable to set up device queue for new table."); - goto err_unlock_md_type; - } dm_unlock_md_type(md); /* stage inactive table */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f8c7ca3..a930b72 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1082,18 +1082,26 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) dm_put(md); } -static void free_rq_clone(struct request *clone) +static void free_rq_clone(struct request *clone, bool must_be_mapped) { struct dm_rq_target_io *tio = clone->end_io_data; struct mapped_device *md = tio->md; + WARN_ON_ONCE(must_be_mapped && !clone->q); + blk_rq_unprep_clone(clone); - if (clone->q->mq_ops) + if (md->type == DM_TYPE_MQ_REQUEST_BASED) + /* stacked on blk-mq queue(s) */ tio->ti->type->release_clone_rq(clone); else if (!md->queue->mq_ops) /* request_fn queue stacked on request_fn queue(s) */ free_clone_request(md, clone); + /* + * NOTE: for the blk-mq queue stacked on request_fn queue(s) case: + * no need to call free_clone_request() because we leverage blk-mq by + * allocating the clone at the end of the blk-mq pdu (see: clone_rq) + */ if (!md->queue->mq_ops) free_rq_tio(tio); @@ -1124,7 +1132,7 @@ static void dm_end_request(struct request *clone, int error) rq->sense_len = clone->sense_len; } - free_rq_clone(clone); + free_rq_clone(clone, true); if (!rq->q->mq_ops) blk_end_request_all(rq, error); else @@ -1143,7 +1151,7 @@ static void dm_unprep_request(struct request *rq) } if (clone) - free_rq_clone(clone); + free_rq_clone(clone, false); } /* @@ -2662,9 +2670,6 @@ static int dm_init_request_based_queue(struct mapped_device *md) { struct request_queue *q = NULL; - if (md->queue->elevator) - return 0; - /* Fully initialize the queue */ q = blk_init_allocated_queue(md->queue, dm_request_fn, NULL); if (!q) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 78dde56..d5fe5d5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -82,6 +82,8 @@ #include <net/bond_3ad.h> #include <net/bond_alb.h> +#include "bonding_priv.h" + /*---------------------------- Module parameters ----------------------------*/ /* monitor all links that often (in milliseconds). <=0 disables monitoring */ @@ -4542,6 +4544,8 @@ unsigned int bond_get_num_tx_queues(void) int bond_create(struct net *net, const char *name) { struct net_device *bond_dev; + struct bonding *bond; + struct alb_bond_info *bond_info; int res; rtnl_lock(); @@ -4555,6 +4559,14 @@ int bond_create(struct net *net, const char *name) return -ENOMEM; } + /* + * Initialize rx_hashtbl_used_head to RLB_NULL_INDEX. + * It is set to 0 by default which is wrong. + */ + bond = netdev_priv(bond_dev); + bond_info = &(BOND_ALB_INFO(bond)); + bond_info->rx_hashtbl_used_head = RLB_NULL_INDEX; + dev_net_set(bond_dev, net); bond_dev->rtnl_link_ops = &bond_link_ops; diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 62694cf..b20b35ac 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -4,6 +4,7 @@ #include <net/netns/generic.h> #include <net/bonding.h> +#include "bonding_priv.h" static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) diff --git a/drivers/net/bonding/bonding_priv.h b/drivers/net/bonding/bonding_priv.h new file mode 100644 index 0000000..5a4d81a --- /dev/null +++ b/drivers/net/bonding/bonding_priv.h @@ -0,0 +1,25 @@ +/* + * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. + * + * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes + * NCM: Network and Communications Management, Inc. + * + * BUT, I'm the one who modified it for ethernet, so: + * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov + * + * This software may be used and distributed according to the terms + * of the GNU Public License, incorporated herein by reference. + * + */ + +#ifndef _BONDING_PRIV_H +#define _BONDING_PRIV_H + +#define DRV_VERSION "3.7.1" +#define DRV_RELDATE "April 27, 2011" +#define DRV_NAME "bonding" +#define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" + +#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" + +#endif diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 58808f6..e8c96b8 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -112,7 +112,7 @@ config PCH_CAN config CAN_GRCAN tristate "Aeroflex Gaisler GRCAN and GRHCAN CAN devices" - depends on OF + depends on OF && HAS_DMA ---help--- Say Y here if you want to use Aeroflex Gaisler GRCAN or GRHCAN. Note that the driver supports little endian, even though little diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 4643914..8b17a90 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -1102,7 +1102,7 @@ static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv, if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | MSG_FLAG_NERR)) { - netdev_err(priv->netdev, "Unknow error (flags: 0x%02x)\n", + netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n", msg->u.rx_can_header.flag); stats->rx_errors++; diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c index b36ee9e..d686b9c 100644 --- a/drivers/net/ethernet/8390/etherh.c +++ b/drivers/net/ethernet/8390/etherh.c @@ -523,7 +523,7 @@ static int etherh_addr(char *addr, struct expansion_card *ec) char *s; if (!ecard_readchunk(&cd, ec, 0xf5, 0)) { - printk(KERN_ERR "%s: unable to read podule description string\n", + printk(KERN_ERR "%s: unable to read module description string\n", dev_name(&ec->dev)); goto no_addr; } diff --git a/drivers/net/ethernet/altera/altera_msgdmahw.h b/drivers/net/ethernet/altera/altera_msgdmahw.h index eba070f..89cd11d 100644 --- a/drivers/net/ethernet/altera/altera_msgdmahw.h +++ b/drivers/net/ethernet/altera/altera_msgdmahw.h @@ -58,15 +58,12 @@ struct msgdma_extended_desc { /* Tx buffer control flags */ #define MSGDMA_DESC_CTL_TX_FIRST (MSGDMA_DESC_CTL_GEN_SOP | \ - MSGDMA_DESC_CTL_TR_ERR_IRQ | \ MSGDMA_DESC_CTL_GO) -#define MSGDMA_DESC_CTL_TX_MIDDLE (MSGDMA_DESC_CTL_TR_ERR_IRQ | \ - MSGDMA_DESC_CTL_GO) +#define MSGDMA_DESC_CTL_TX_MIDDLE (MSGDMA_DESC_CTL_GO) #define MSGDMA_DESC_CTL_TX_LAST (MSGDMA_DESC_CTL_GEN_EOP | \ MSGDMA_DESC_CTL_TR_COMP_IRQ | \ - MSGDMA_DESC_CTL_TR_ERR_IRQ | \ MSGDMA_DESC_CTL_GO) #define MSGDMA_DESC_CTL_TX_SINGLE (MSGDMA_DESC_CTL_GEN_SOP | \ diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 90a7630..da48e66 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -391,6 +391,12 @@ static int tse_rx(struct altera_tse_private *priv, int limit) "RCV pktstatus %08X pktlength %08X\n", pktstatus, pktlength); + /* DMA trasfer from TSE starts with 2 aditional bytes for + * IP payload alignment. Status returned by get_rx_status() + * contains DMA transfer length. Packet is 2 bytes shorter. + */ + pktlength -= 2; + count++; next_entry = (++priv->rx_cons) % priv->rx_ring_size; @@ -777,6 +783,8 @@ static int init_phy(struct net_device *dev) struct altera_tse_private *priv = netdev_priv(dev); struct phy_device *phydev; struct device_node *phynode; + bool fixed_link = false; + int rc = 0; /* Avoid init phy in case of no phy present */ if (!priv->phy_iface) @@ -789,13 +797,32 @@ static int init_phy(struct net_device *dev) phynode = of_parse_phandle(priv->device->of_node, "phy-handle", 0); if (!phynode) { - netdev_dbg(dev, "no phy-handle found\n"); - if (!priv->mdio) { - netdev_err(dev, - "No phy-handle nor local mdio specified\n"); - return -ENODEV; + /* check if a fixed-link is defined in device-tree */ + if (of_phy_is_fixed_link(priv->device->of_node)) { + rc = of_phy_register_fixed_link(priv->device->of_node); + if (rc < 0) { + netdev_err(dev, "cannot register fixed PHY\n"); + return rc; + } + + /* In the case of a fixed PHY, the DT node associated + * to the PHY is the Ethernet MAC DT node. + */ + phynode = of_node_get(priv->device->of_node); + fixed_link = true; + + netdev_dbg(dev, "fixed-link detected\n"); + phydev = of_phy_connect(dev, phynode, + &altera_tse_adjust_link, + 0, priv->phy_iface); + } else { + netdev_dbg(dev, "no phy-handle found\n"); + if (!priv->mdio) { + netdev_err(dev, "No phy-handle nor local mdio specified\n"); + return -ENODEV; + } + phydev = connect_local_phy(dev); } - phydev = connect_local_phy(dev); } else { netdev_dbg(dev, "phy-handle found\n"); phydev = of_phy_connect(dev, phynode, @@ -819,10 +846,10 @@ static int init_phy(struct net_device *dev) /* Broken HW is sometimes missing the pull-up resistor on the * MDIO line, which results in reads to non-existent devices returning * 0 rather than 0xffff. Catch this here and treat 0 as a non-existent - * device as well. + * device as well. If a fixed-link is used the phy_id is always 0. * Note: phydev->phy_id is the result of reading the UID PHY registers. */ - if (phydev->phy_id == 0) { + if ((phydev->phy_id == 0) && !fixed_link) { netdev_err(dev, "Bad PHY UID 0x%08x\n", phydev->phy_id); phy_disconnect(phydev); return -ENODEV; diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index c638c85..089c269 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -179,7 +179,7 @@ config SUNLANCE config AMD_XGBE tristate "AMD 10GbE Ethernet driver" - depends on (OF_NET || ACPI) && HAS_IOMEM + depends on (OF_NET || ACPI) && HAS_IOMEM && HAS_DMA select PHYLIB select AMD_XGBE_PHY select BITREVERSE diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig index 8e262e2..dea29ee 100644 --- a/drivers/net/ethernet/arc/Kconfig +++ b/drivers/net/ethernet/arc/Kconfig @@ -25,8 +25,7 @@ config ARC_EMAC_CORE config ARC_EMAC tristate "ARC EMAC support" select ARC_EMAC_CORE - depends on OF_IRQ - depends on OF_NET + depends on OF_IRQ && OF_NET && HAS_DMA ---help--- On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x non-standard on-chip ethernet device ARC EMAC 10/100 is used. @@ -35,7 +34,7 @@ config ARC_EMAC config EMAC_ROCKCHIP tristate "Rockchip EMAC support" select ARC_EMAC_CORE - depends on OF_IRQ && OF_NET && REGULATOR + depends on OF_IRQ && OF_NET && REGULATOR && HAS_DMA ---help--- Support for Rockchip RK3066/RK3188 EMAC ethernet controllers. This selects Rockchip SoC glue layer support for the diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_hw.h b/drivers/net/ethernet/atheros/atl1e/atl1e_hw.h index 74df16a..88a6271 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_hw.h +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_hw.h @@ -129,7 +129,7 @@ s32 atl1e_restart_autoneg(struct atl1e_hw *hw); #define TWSI_CTRL_LD_SLV_ADDR_SHIFT 8 #define TWSI_CTRL_SW_LDSTART 0x800 #define TWSI_CTRL_HW_LDSTART 0x1000 -#define TWSI_CTRL_SMB_SLV_ADDR_MASK 0x0x7F +#define TWSI_CTRL_SMB_SLV_ADDR_MASK 0x7F #define TWSI_CTRL_SMB_SLV_ADDR_SHIFT 15 #define TWSI_CTRL_LD_EXIST 0x400000 #define TWSI_CTRL_READ_FREQ_SEL_MASK 0x3 diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 7e3d87a..e2c043e 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -543,7 +543,7 @@ struct bcm_sysport_tx_counters { u32 jbr; /* RO # of xmited jabber count*/ u32 bytes; /* RO # of xmited byte count */ u32 pok; /* RO # of xmited good pkt */ - u32 uc; /* RO (0x0x4f0)# of xmited unitcast pkt */ + u32 uc; /* RO (0x4f0) # of xmited unicast pkt */ }; struct bcm_sysport_mib { diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index de77d3a..21e3c38 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1260,7 +1260,7 @@ static int bgmac_poll(struct napi_struct *napi, int weight) /* Poll again if more events arrived in the meantime */ if (bgmac_read(bgmac, BGMAC_INT_STATUS) & (BGMAC_IS_TX0 | BGMAC_IS_RX)) - return handled; + return weight; if (handled < weight) { napi_complete(napi); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 355d5fe..a3b0f7a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -521,6 +521,7 @@ struct bnx2x_fp_txdata { }; enum bnx2x_tpa_mode_t { + TPA_MODE_DISABLED, TPA_MODE_LRO, TPA_MODE_GRO }; @@ -589,7 +590,6 @@ struct bnx2x_fastpath { /* TPA related */ struct bnx2x_agg_info *tpa_info; - u8 disable_tpa; #ifdef BNX2X_STOP_ON_ERROR u64 tpa_queue_used; #endif @@ -1545,9 +1545,7 @@ struct bnx2x { #define USING_MSIX_FLAG (1 << 5) #define USING_MSI_FLAG (1 << 6) #define DISABLE_MSI_FLAG (1 << 7) -#define TPA_ENABLE_FLAG (1 << 8) #define NO_MCP_FLAG (1 << 9) -#define GRO_ENABLE_FLAG (1 << 10) #define MF_FUNC_DIS (1 << 11) #define OWN_CNIC_IRQ (1 << 12) #define NO_ISCSI_OOO_FLAG (1 << 13) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 2f63467..a8bb8f6 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -947,10 +947,10 @@ static int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget) u16 frag_size, pages; #ifdef BNX2X_STOP_ON_ERROR /* sanity check */ - if (fp->disable_tpa && + if (fp->mode == TPA_MODE_DISABLED && (CQE_TYPE_START(cqe_fp_type) || CQE_TYPE_STOP(cqe_fp_type))) - BNX2X_ERR("START/STOP packet while disable_tpa type %x\n", + BNX2X_ERR("START/STOP packet while TPA disabled, type %x\n", CQE_TYPE(cqe_fp_type)); #endif @@ -1396,7 +1396,7 @@ void bnx2x_init_rx_rings(struct bnx2x *bp) DP(NETIF_MSG_IFUP, "mtu %d rx_buf_size %d\n", bp->dev->mtu, fp->rx_buf_size); - if (!fp->disable_tpa) { + if (fp->mode != TPA_MODE_DISABLED) { /* Fill the per-aggregation pool */ for (i = 0; i < MAX_AGG_QS(bp); i++) { struct bnx2x_agg_info *tpa_info = @@ -1410,7 +1410,7 @@ void bnx2x_init_rx_rings(struct bnx2x *bp) BNX2X_ERR("Failed to allocate TPA skb pool for queue[%d] - disabling TPA on this queue!\n", j); bnx2x_free_tpa_pool(bp, fp, i); - fp->disable_tpa = 1; + fp->mode = TPA_MODE_DISABLED; break; } dma_unmap_addr_set(first_buf, mapping, 0); @@ -1438,7 +1438,7 @@ void bnx2x_init_rx_rings(struct bnx2x *bp) ring_prod); bnx2x_free_tpa_pool(bp, fp, MAX_AGG_QS(bp)); - fp->disable_tpa = 1; + fp->mode = TPA_MODE_DISABLED; ring_prod = 0; break; } @@ -1560,7 +1560,7 @@ static void bnx2x_free_rx_skbs(struct bnx2x *bp) bnx2x_free_rx_bds(fp); - if (!fp->disable_tpa) + if (fp->mode != TPA_MODE_DISABLED) bnx2x_free_tpa_pool(bp, fp, MAX_AGG_QS(bp)); } } @@ -2477,17 +2477,19 @@ static void bnx2x_bz_fp(struct bnx2x *bp, int index) /* set the tpa flag for each queue. The tpa flag determines the queue * minimal size so it must be set prior to queue memory allocation */ - fp->disable_tpa = !(bp->flags & TPA_ENABLE_FLAG || - (bp->flags & GRO_ENABLE_FLAG && - bnx2x_mtu_allows_gro(bp->dev->mtu))); - if (bp->flags & TPA_ENABLE_FLAG) + if (bp->dev->features & NETIF_F_LRO) fp->mode = TPA_MODE_LRO; - else if (bp->flags & GRO_ENABLE_FLAG) + else if (bp->dev->features & NETIF_F_GRO && + bnx2x_mtu_allows_gro(bp->dev->mtu)) fp->mode = TPA_MODE_GRO; + else + fp->mode = TPA_MODE_DISABLED; - /* We don't want TPA on an FCoE L2 ring */ - if (IS_FCOE_FP(fp)) - fp->disable_tpa = 1; + /* We don't want TPA if it's disabled in bp + * or if this is an FCoE L2 ring. + */ + if (bp->disable_tpa || IS_FCOE_FP(fp)) + fp->mode = TPA_MODE_DISABLED; } int bnx2x_load_cnic(struct bnx2x *bp) @@ -2608,7 +2610,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) /* * Zero fastpath structures preserving invariants like napi, which are * allocated only once, fp index, max_cos, bp pointer. - * Also set fp->disable_tpa and txdata_ptr. + * Also set fp->mode and txdata_ptr. */ DP(NETIF_MSG_IFUP, "num queues: %d", bp->num_queues); for_each_queue(bp, i) @@ -3247,7 +3249,7 @@ int bnx2x_low_latency_recv(struct napi_struct *napi) if ((bp->state == BNX2X_STATE_CLOSED) || (bp->state == BNX2X_STATE_ERROR) || - (bp->flags & (TPA_ENABLE_FLAG | GRO_ENABLE_FLAG))) + (bp->dev->features & (NETIF_F_LRO | NETIF_F_GRO))) return LL_FLUSH_FAILED; if (!bnx2x_fp_lock_poll(fp)) @@ -4543,7 +4545,7 @@ alloc_mem_err: * In these cases we disable the queue * Min size is different for OOO, TPA and non-TPA queues */ - if (ring_size < (fp->disable_tpa ? + if (ring_size < (fp->mode == TPA_MODE_DISABLED ? MIN_RX_SIZE_NONTPA : MIN_RX_SIZE_TPA)) { /* release memory allocated for this queue */ bnx2x_free_fp_mem_at(bp, index); @@ -4809,66 +4811,71 @@ netdev_features_t bnx2x_fix_features(struct net_device *dev, { struct bnx2x *bp = netdev_priv(dev); + if (pci_num_vf(bp->pdev)) { + netdev_features_t changed = dev->features ^ features; + + /* Revert the requested changes in features if they + * would require internal reload of PF in bnx2x_set_features(). + */ + if (!(features & NETIF_F_RXCSUM) && !bp->disable_tpa) { + features &= ~NETIF_F_RXCSUM; + features |= dev->features & NETIF_F_RXCSUM; + } + + if (changed & NETIF_F_LOOPBACK) { + features &= ~NETIF_F_LOOPBACK; + features |= dev->features & NETIF_F_LOOPBACK; + } + } + /* TPA requires Rx CSUM offloading */ if (!(features & NETIF_F_RXCSUM)) { features &= ~NETIF_F_LRO; features &= ~NETIF_F_GRO; } - /* Note: do not disable SW GRO in kernel when HW GRO is off */ - if (bp->disable_tpa) - features &= ~NETIF_F_LRO; - return features; } int bnx2x_set_features(struct net_device *dev, netdev_features_t features) { struct bnx2x *bp = netdev_priv(dev); - u32 flags = bp->flags; - u32 changes; + netdev_features_t changes = features ^ dev->features; bool bnx2x_reload = false; + int rc; - if (features & NETIF_F_LRO) - flags |= TPA_ENABLE_FLAG; - else - flags &= ~TPA_ENABLE_FLAG; - - if (features & NETIF_F_GRO) - flags |= GRO_ENABLE_FLAG; - else - flags &= ~GRO_ENABLE_FLAG; - - if (features & NETIF_F_LOOPBACK) { - if (bp->link_params.loopback_mode != LOOPBACK_BMAC) { - bp->link_params.loopback_mode = LOOPBACK_BMAC; - bnx2x_reload = true; - } - } else { - if (bp->link_params.loopback_mode != LOOPBACK_NONE) { - bp->link_params.loopback_mode = LOOPBACK_NONE; - bnx2x_reload = true; + /* VFs or non SRIOV PFs should be able to change loopback feature */ + if (!pci_num_vf(bp->pdev)) { + if (features & NETIF_F_LOOPBACK) { + if (bp->link_params.loopback_mode != LOOPBACK_BMAC) { + bp->link_params.loopback_mode = LOOPBACK_BMAC; + bnx2x_reload = true; + } + } else { + if (bp->link_params.loopback_mode != LOOPBACK_NONE) { + bp->link_params.loopback_mode = LOOPBACK_NONE; + bnx2x_reload = true; + } } } - changes = flags ^ bp->flags; - /* if GRO is changed while LRO is enabled, don't force a reload */ - if ((changes & GRO_ENABLE_FLAG) && (flags & TPA_ENABLE_FLAG)) - changes &= ~GRO_ENABLE_FLAG; + if ((changes & NETIF_F_GRO) && (features & NETIF_F_LRO)) + changes &= ~NETIF_F_GRO; /* if GRO is changed while HW TPA is off, don't force a reload */ - if ((changes & GRO_ENABLE_FLAG) && bp->disable_tpa) - changes &= ~GRO_ENABLE_FLAG; + if ((changes & NETIF_F_GRO) && bp->disable_tpa) + changes &= ~NETIF_F_GRO; if (changes) bnx2x_reload = true; - bp->flags = flags; - if (bnx2x_reload) { - if (bp->recovery_state == BNX2X_RECOVERY_DONE) - return bnx2x_reload_if_running(dev); + if (bp->recovery_state == BNX2X_RECOVERY_DONE) { + dev->features = features; + rc = bnx2x_reload_if_running(dev); + return rc ? rc : 1; + } /* else: bnx2x_nic_load() will be called at end of recovery */ } @@ -4931,6 +4938,11 @@ int bnx2x_resume(struct pci_dev *pdev) } bp = netdev_priv(dev); + if (pci_num_vf(bp->pdev)) { + DP(BNX2X_MSG_IOV, "VFs are enabled, can not change MTU\n"); + return -EPERM; + } + if (bp->recovery_state != BNX2X_RECOVERY_DONE) { BNX2X_ERR("Handling parity error recovery. Try again later\n"); return -EAGAIN; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index adcacda..d7a7175 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -969,7 +969,7 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, { int i; - if (fp->disable_tpa) + if (fp->mode == TPA_MODE_DISABLED) return; for (i = 0; i < last; i++) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index e3d853c..48ed005 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1843,6 +1843,12 @@ static int bnx2x_set_ringparam(struct net_device *dev, "set ring params command parameters: rx_pending = %d, tx_pending = %d\n", ering->rx_pending, ering->tx_pending); + if (pci_num_vf(bp->pdev)) { + DP(BNX2X_MSG_IOV, + "VFs are enabled, can not change ring parameters\n"); + return -EPERM; + } + if (bp->recovery_state != BNX2X_RECOVERY_DONE) { DP(BNX2X_MSG_ETHTOOL, "Handling parity error recovery. Try again later\n"); @@ -2899,6 +2905,12 @@ static void bnx2x_self_test(struct net_device *dev, u8 is_serdes, link_up; int rc, cnt = 0; + if (pci_num_vf(bp->pdev)) { + DP(BNX2X_MSG_IOV, + "VFs are enabled, can not perform self test\n"); + return; + } + if (bp->recovery_state != BNX2X_RECOVERY_DONE) { netdev_err(bp->dev, "Handling parity error recovery. Try again later\n"); @@ -3468,6 +3480,11 @@ static int bnx2x_set_channels(struct net_device *dev, channels->rx_count, channels->tx_count, channels->other_count, channels->combined_count); + if (pci_num_vf(bp->pdev)) { + DP(BNX2X_MSG_IOV, "VFs are enabled, can not set channels\n"); + return -EPERM; + } + /* We don't support separate rx / tx channels. * We don't allow setting 'other' channels. */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index b9f85fcc..556dcc1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -3128,7 +3128,7 @@ static unsigned long bnx2x_get_q_flags(struct bnx2x *bp, __set_bit(BNX2X_Q_FLG_FORCE_DEFAULT_PRI, &flags); } - if (!fp->disable_tpa) { + if (fp->mode != TPA_MODE_DISABLED) { __set_bit(BNX2X_Q_FLG_TPA, &flags); __set_bit(BNX2X_Q_FLG_TPA_IPV6, &flags); if (fp->mode == TPA_MODE_GRO) @@ -3176,7 +3176,7 @@ static void bnx2x_pf_rx_q_prep(struct bnx2x *bp, u16 sge_sz = 0; u16 tpa_agg_size = 0; - if (!fp->disable_tpa) { + if (fp->mode != TPA_MODE_DISABLED) { pause->sge_th_lo = SGE_TH_LO(bp); pause->sge_th_hi = SGE_TH_HI(bp); @@ -3304,7 +3304,7 @@ static void bnx2x_pf_init(struct bnx2x *bp) /* This flag is relevant for E1x only. * E2 doesn't have a TPA configuration in a function level. */ - flags |= (bp->flags & TPA_ENABLE_FLAG) ? FUNC_FLG_TPA : 0; + flags |= (bp->dev->features & NETIF_F_LRO) ? FUNC_FLG_TPA : 0; func_init.func_flgs = flags; func_init.pf_id = BP_FUNC(bp); @@ -12107,11 +12107,8 @@ static int bnx2x_init_bp(struct bnx2x *bp) /* Set TPA flags */ if (bp->disable_tpa) { - bp->flags &= ~(TPA_ENABLE_FLAG | GRO_ENABLE_FLAG); + bp->dev->hw_features &= ~NETIF_F_LRO; bp->dev->features &= ~NETIF_F_LRO; - } else { - bp->flags |= (TPA_ENABLE_FLAG | GRO_ENABLE_FLAG); - bp->dev->features |= NETIF_F_LRO; } if (CHIP_IS_E1(bp)) @@ -13371,6 +13368,12 @@ static int bnx2x_init_one(struct pci_dev *pdev, bool is_vf; int cnic_cnt; + /* Management FW 'remembers' living interfaces. Allow it some time + * to forget previously living interfaces, allowing a proper re-load. + */ + if (is_kdump_kernel()) + msleep(5000); + /* An estimated maximum supported CoS number according to the chip * version. * We will try to roughly estimate the maximum number of CoSes this chip diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 15b2d16..06b8c0d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -594,7 +594,7 @@ int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, bnx2x_vfpf_prep(bp, &req->first_tlv, CHANNEL_TLV_SETUP_Q, sizeof(*req)); /* select tpa mode to request */ - if (!fp->disable_tpa) { + if (fp->mode != TPA_MODE_DISABLED) { flags |= VFPF_QUEUE_FLG_TPA; flags |= VFPF_QUEUE_FLG_TPA_IPV6; if (fp->mode == TPA_MODE_GRO) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 1270b18..069952f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -18129,7 +18129,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, rtnl_lock(); - tp->pcierr_recovery = true; + /* We needn't recover from permanent error */ + if (state == pci_channel_io_frozen) + tp->pcierr_recovery = true; /* We probably don't have netdev yet */ if (!netdev || !netif_running(netdev)) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 9f53872..4104d49 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -707,6 +707,9 @@ static void gem_rx_refill(struct macb *bp) /* properly align Ethernet header */ skb_reserve(skb, NET_IP_ALIGN); + } else { + bp->rx_ring[entry].addr &= ~MACB_BIT(RX_USED); + bp->rx_ring[entry].ctrl = 0; } } @@ -1473,9 +1476,9 @@ static void macb_init_rings(struct macb *bp) for (i = 0; i < TX_RING_SIZE; i++) { bp->queues[0].tx_ring[i].addr = 0; bp->queues[0].tx_ring[i].ctrl = MACB_BIT(TX_USED); - bp->queues[0].tx_head = 0; - bp->queues[0].tx_tail = 0; } + bp->queues[0].tx_head = 0; + bp->queues[0].tx_tail = 0; bp->queues[0].tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP); bp->rx_tail = 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 5959e3a..e8578a7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -492,7 +492,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, memoffset = (mtype * (edc_size * 1024 * 1024)); else { mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap, - MA_EXT_MEMORY1_BAR_A)); + MA_EXT_MEMORY0_BAR_A)); memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024; } diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index fb0bc3c..a6dcbf8 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4846,7 +4846,8 @@ err: } static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u32 filter_mask) + struct net_device *dev, u32 filter_mask, + int nlflags) { struct be_adapter *adapter = netdev_priv(dev); int status = 0; @@ -4868,7 +4869,7 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, return ndo_dflt_bridge_getlink(skb, pid, seq, dev, hsw_mode == PORT_FWD_TYPE_VEPA ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB, - 0, 0); + 0, 0, nlflags); } #ifdef CONFIG_BE2NET_VXLAN diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f6a3a7a..66d47e4 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -988,7 +988,10 @@ fec_restart(struct net_device *ndev) rcntl |= 0x40000000 | 0x00000020; /* RGMII, RMII or MII */ - if (fep->phy_interface == PHY_INTERFACE_MODE_RGMII) + if (fep->phy_interface == PHY_INTERFACE_MODE_RGMII || + fep->phy_interface == PHY_INTERFACE_MODE_RGMII_ID || + fep->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID || + fep->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) rcntl |= (1 << 6); else if (fep->phy_interface == PHY_INTERFACE_MODE_RMII) rcntl |= (1 << 8); diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 291c870..2a0dc12 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3347,7 +3347,7 @@ static int ehea_register_memory_hooks(void) { int ret = 0; - if (atomic_inc_and_test(&ehea_memory_hooks_registered)) + if (atomic_inc_return(&ehea_memory_hooks_registered) > 1) return 0; ret = ehea_create_busmap(); @@ -3381,12 +3381,14 @@ out3: out2: unregister_reboot_notifier(&ehea_reboot_nb); out: + atomic_dec(&ehea_memory_hooks_registered); return ret; } static void ehea_unregister_memory_hooks(void) { - if (atomic_read(&ehea_memory_hooks_registered)) + /* Only remove the hooks if we've registered them */ + if (atomic_read(&ehea_memory_hooks_registered) == 0) return; unregister_reboot_notifier(&ehea_reboot_nb); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index cd7675a..1813476 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1238,7 +1238,7 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) - if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size) + if (new_mtu_oh <= adapter->rx_buff_pool[i].buff_size) break; if (i == IBMVETH_NUM_BUFF_POOLS) @@ -1257,7 +1257,7 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { adapter->rx_buff_pool[i].active = 1; - if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size) { + if (new_mtu_oh <= adapter->rx_buff_pool[i].buff_size) { dev->mtu = new_mtu; vio_cmo_set_dev_desired(viodev, ibmveth_get_desired_dma diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 24481cd..a54c144 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8053,10 +8053,10 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, #ifdef HAVE_BRIDGE_FILTER static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 __always_unused filter_mask) + u32 __always_unused filter_mask, int nlflags) #else static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev) + struct net_device *dev, int nlflags) #endif /* HAVE_BRIDGE_FILTER */ { struct i40e_netdev_priv *np = netdev_priv(dev); @@ -8078,7 +8078,8 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, if (!veb) return 0; - return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode); + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode, + nlflags); } #endif /* HAVE_BRIDGE_ATTRIBS */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d3f4b0c..5be12a0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8044,7 +8044,7 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask) + u32 filter_mask, int nlflags) { struct ixgbe_adapter *adapter = netdev_priv(dev); @@ -8052,7 +8052,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, return 0; return ndo_dflt_bridge_getlink(skb, pid, seq, dev, - adapter->bridge_mode, 0, 0); + adapter->bridge_mode, 0, 0, nlflags); } static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index af829c5..7ace07d 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1508,7 +1508,8 @@ static int pxa168_eth_probe(struct platform_device *pdev) np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); if (!np) { dev_err(&pdev->dev, "missing phy-handle\n"); - return -EINVAL; + err = -EINVAL; + goto err_netdev; } of_property_read_u32(np, "reg", &pep->phy_addr); pep->phy_intf = of_get_phy_mode(pdev->dev.of_node); @@ -1526,7 +1527,7 @@ static int pxa168_eth_probe(struct platform_device *pdev) pep->smi_bus = mdiobus_alloc(); if (pep->smi_bus == NULL) { err = -ENOMEM; - goto err_base; + goto err_netdev; } pep->smi_bus->priv = pep; pep->smi_bus->name = "pxa168_eth smi"; @@ -1551,13 +1552,10 @@ err_mdiobus: mdiobus_unregister(pep->smi_bus); err_free_mdio: mdiobus_free(pep->smi_bus); -err_base: - iounmap(pep->base); err_netdev: free_netdev(dev); err_clk: - clk_disable(clk); - clk_put(clk); + clk_disable_unprepare(clk); return err; } @@ -1574,13 +1572,9 @@ static int pxa168_eth_remove(struct platform_device *pdev) if (pep->phy) phy_disconnect(pep->phy); if (pep->clk) { - clk_disable(pep->clk); - clk_put(pep->clk); - pep->clk = NULL; + clk_disable_unprepare(pep->clk); } - iounmap(pep->base); - pep->base = NULL; mdiobus_unregister(pep->smi_bus); mdiobus_free(pep->smi_bus); unregister_netdev(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 3f44e2b..a2ddf3d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1102,20 +1102,21 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc) struct mlx4_en_priv *priv = netdev_priv(dev); /* check if requested function is supported by the device */ - if ((hfunc == ETH_RSS_HASH_TOP && - !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) || - (hfunc == ETH_RSS_HASH_XOR && - !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR))) - return -EINVAL; + if (hfunc == ETH_RSS_HASH_TOP) { + if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) + return -EINVAL; + if (!(dev->features & NETIF_F_RXHASH)) + en_warn(priv, "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n"); + return 0; + } else if (hfunc == ETH_RSS_HASH_XOR) { + if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR)) + return -EINVAL; + if (dev->features & NETIF_F_RXHASH) + en_warn(priv, "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n"); + return 0; + } - priv->rss_hash_fn = hfunc; - if (hfunc == ETH_RSS_HASH_TOP && !(dev->features & NETIF_F_RXHASH)) - en_warn(priv, - "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n"); - if (hfunc == ETH_RSS_HASH_XOR && (dev->features & NETIF_F_RXHASH)) - en_warn(priv, - "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n"); - return 0; + return -EINVAL; } static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key, @@ -1189,6 +1190,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index, priv->prof->rss_rings = rss_rings; if (key) memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE); + if (hfunc != ETH_RSS_HASH_NO_CHANGE) + priv->rss_hash_fn = hfunc; if (port_up) { err = mlx4_en_start_port(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 0f1afc0..32f5ec7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1467,6 +1467,7 @@ static void mlx4_en_service_task(struct work_struct *work) if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) mlx4_en_ptp_overflow_check(mdev); + mlx4_en_recover_from_oom(priv); queue_delayed_work(mdev->workqueue, &priv->service_task, SERVICE_TASK_DELAY); } @@ -1721,7 +1722,7 @@ mac_err: cq_err: while (rx_index--) { mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]); - mlx4_en_free_affinity_hint(priv, i); + mlx4_en_free_affinity_hint(priv, rx_index); } for (i = 0; i < priv->rx_ring_num; i++) mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 4fdd3c3..2a77a6b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -244,6 +244,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp); } +static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring) +{ + BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size); + return ring->prod == ring->cons; +} + static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring) { *ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff); @@ -315,8 +321,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv, ring->cons, ring->prod); /* Unmap and free Rx buffers */ - BUG_ON((u32) (ring->prod - ring->cons) > ring->actual_size); - while (ring->cons != ring->prod) { + while (!mlx4_en_is_ring_empty(ring)) { index = ring->cons & ring->size_mask; en_dbg(DRV, priv, "Processing descriptor:%d\n", index); mlx4_en_free_rx_desc(priv, ring, index); @@ -491,6 +496,23 @@ err_allocator: return err; } +/* We recover from out of memory by scheduling our napi poll + * function (mlx4_en_process_cq), which tries to allocate + * all missing RX buffers (call to mlx4_en_refill_rx_buffers). + */ +void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv) +{ + int ring; + + if (!priv->port_up) + return; + + for (ring = 0; ring < priv->rx_ring_num; ring++) { + if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) + napi_reschedule(&priv->rx_cq[ring]->napi); + } +} + void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring **pring, u32 size, u16 stride) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 1783705..f7bf312 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -143,8 +143,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type; ring->queue_index = queue_index; - if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index)) - cpumask_set_cpu(queue_index, &ring->affinity_mask); + if (queue_index < priv->num_tx_rings_p_up) + cpumask_set_cpu_local_first(queue_index, + priv->mdev->dev->numa_node, + &ring->affinity_mask); *pring = ring; return 0; @@ -213,7 +215,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context, &ring->qp, &ring->qp_state); - if (!user_prio && cpu_online(ring->queue_index)) + if (!cpumask_empty(&ring->affinity_mask)) netif_set_xps_queue(priv->dev, &ring->affinity_mask, ring->queue_index); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index a407981..e30bf57 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -56,11 +56,13 @@ MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: on)"); #define MLX4_GET(dest, source, offset) \ do { \ void *__p = (char *) (source) + (offset); \ + u64 val; \ switch (sizeof (dest)) { \ case 1: (dest) = *(u8 *) __p; break; \ case 2: (dest) = be16_to_cpup(__p); break; \ case 4: (dest) = be32_to_cpup(__p); break; \ - case 8: (dest) = be64_to_cpup(__p); break; \ + case 8: val = get_unaligned((u64 *)__p); \ + (dest) = be64_to_cpu(val); break; \ default: __buggy_use_of_MLX4_GET(); \ } \ } while (0) @@ -1605,9 +1607,17 @@ static void get_board_id(void *vsd, char *board_id) * swaps each 4-byte word before passing it back to * us. Therefore we need to swab it before printing. */ - for (i = 0; i < 4; ++i) - ((u32 *) board_id)[i] = - swab32(*(u32 *) (vsd + VSD_OFFSET_MLX_BOARD_ID + i * 4)); + u32 *bid_u32 = (u32 *)board_id; + + for (i = 0; i < 4; ++i) { + u32 *addr; + u32 val; + + addr = (u32 *) (vsd + VSD_OFFSET_MLX_BOARD_ID + i * 4); + val = get_unaligned(addr); + val = swab32(val); + put_unaligned(val, &bid_u32[i]); + } } } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 9de3021..d021f07 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -774,6 +774,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring); void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev); +void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv); int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring **pring, u32 size, u16 stride, int node); diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 1412f5a..2bae502 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -69,11 +69,7 @@ #include <net/ip.h> #include <net/tcp.h> #include <asm/byteorder.h> -#include <asm/io.h> #include <asm/processor.h> -#ifdef CONFIG_MTRR -#include <asm/mtrr.h> -#endif #include <net/busy_poll.h> #include "myri10ge_mcp.h" @@ -242,8 +238,7 @@ struct myri10ge_priv { unsigned int rdma_tags_available; int intr_coal_delay; __be32 __iomem *intr_coal_delay_ptr; - int mtrr; - int wc_enabled; + int wc_cookie; int down_cnt; wait_queue_head_t down_wq; struct work_struct watchdog_work; @@ -1905,7 +1900,7 @@ static const char myri10ge_gstrings_main_stats[][ETH_GSTRING_LEN] = { "tx_aborted_errors", "tx_carrier_errors", "tx_fifo_errors", "tx_heartbeat_errors", "tx_window_errors", /* device-specific stats */ - "tx_boundary", "WC", "irq", "MSI", "MSIX", + "tx_boundary", "irq", "MSI", "MSIX", "read_dma_bw_MBs", "write_dma_bw_MBs", "read_write_dma_bw_MBs", "serial_number", "watchdog_resets", #ifdef CONFIG_MYRI10GE_DCA @@ -1984,7 +1979,6 @@ myri10ge_get_ethtool_stats(struct net_device *netdev, data[i] = ((u64 *)&link_stats)[i]; data[i++] = (unsigned int)mgp->tx_boundary; - data[i++] = (unsigned int)mgp->wc_enabled; data[i++] = (unsigned int)mgp->pdev->irq; data[i++] = (unsigned int)mgp->msi_enabled; data[i++] = (unsigned int)mgp->msix_enabled; @@ -4040,14 +4034,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mgp->board_span = pci_resource_len(pdev, 0); mgp->iomem_base = pci_resource_start(pdev, 0); - mgp->mtrr = -1; - mgp->wc_enabled = 0; -#ifdef CONFIG_MTRR - mgp->mtrr = mtrr_add(mgp->iomem_base, mgp->board_span, - MTRR_TYPE_WRCOMB, 1); - if (mgp->mtrr >= 0) - mgp->wc_enabled = 1; -#endif + mgp->wc_cookie = arch_phys_wc_add(mgp->iomem_base, mgp->board_span); mgp->sram = ioremap_wc(mgp->iomem_base, mgp->board_span); if (mgp->sram == NULL) { dev_err(&pdev->dev, "ioremap failed for %ld bytes at 0x%lx\n", @@ -4146,14 +4133,14 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto abort_with_state; } if (mgp->msix_enabled) - dev_info(dev, "%d MSI-X IRQs, tx bndry %d, fw %s, WC %s\n", + dev_info(dev, "%d MSI-X IRQs, tx bndry %d, fw %s, MTRR %s, WC Enabled\n", mgp->num_slices, mgp->tx_boundary, mgp->fw_name, - (mgp->wc_enabled ? "Enabled" : "Disabled")); + (mgp->wc_cookie > 0 ? "Enabled" : "Disabled")); else - dev_info(dev, "%s IRQ %d, tx bndry %d, fw %s, WC %s\n", + dev_info(dev, "%s IRQ %d, tx bndry %d, fw %s, MTRR %s, WC Enabled\n", mgp->msi_enabled ? "MSI" : "xPIC", pdev->irq, mgp->tx_boundary, mgp->fw_name, - (mgp->wc_enabled ? "Enabled" : "Disabled")); + (mgp->wc_cookie > 0 ? "Enabled" : "Disabled")); board_number++; return 0; @@ -4175,10 +4162,7 @@ abort_with_ioremap: iounmap(mgp->sram); abort_with_mtrr: -#ifdef CONFIG_MTRR - if (mgp->mtrr >= 0) - mtrr_del(mgp->mtrr, mgp->iomem_base, mgp->board_span); -#endif + arch_phys_wc_del(mgp->wc_cookie); dma_free_coherent(&pdev->dev, sizeof(*mgp->cmd), mgp->cmd, mgp->cmd_bus); @@ -4220,11 +4204,7 @@ static void myri10ge_remove(struct pci_dev *pdev) pci_restore_state(pdev); iounmap(mgp->sram); - -#ifdef CONFIG_MTRR - if (mgp->mtrr >= 0) - mtrr_del(mgp->mtrr, mgp->iomem_base, mgp->board_span); -#endif + arch_phys_wc_del(mgp->wc_cookie); myri10ge_free_slices(mgp); kfree(mgp->msix_vectors); dma_free_coherent(&pdev->dev, sizeof(*mgp->cmd), diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c index 5c40683..8da7c3f 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c @@ -135,7 +135,7 @@ void netxen_release_tx_buffers(struct netxen_adapter *adapter) int i, j; struct nx_host_tx_ring *tx_ring = adapter->tx_ring; - spin_lock(&adapter->tx_clean_lock); + spin_lock_bh(&adapter->tx_clean_lock); cmd_buf = tx_ring->cmd_buf_arr; for (i = 0; i < tx_ring->num_desc; i++) { buffrag = cmd_buf->frag_array; @@ -159,7 +159,7 @@ void netxen_release_tx_buffers(struct netxen_adapter *adapter) } cmd_buf++; } - spin_unlock(&adapter->tx_clean_lock); + spin_unlock_bh(&adapter->tx_clean_lock); } void netxen_free_sw_resources(struct netxen_adapter *adapter) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index a570a60..ec25153 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4176,14 +4176,15 @@ static int rocker_port_bridge_setlink(struct net_device *dev, static int rocker_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask) + u32 filter_mask, int nlflags) { struct rocker_port *rocker_port = netdev_priv(dev); u16 mode = BRIDGE_MODE_UNDEF; u32 mask = BR_LEARNING | BR_LEARNING_SYNC; return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, - rocker_port->brport_flags, mask); + rocker_port->brport_flags, mask, + nlflags); } static int rocker_port_get_phys_port_name(struct net_device *dev, diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 2bef655..9b7e0a3 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -1765,7 +1765,9 @@ static void netcp_ethss_link_state_action(struct gbe_priv *gbe_dev, ALE_PORT_STATE, ALE_PORT_STATE_FORWARD); - if (ndev && slave->open) + if (ndev && slave->open && + slave->link_interface != SGMII_LINK_MAC_PHY && + slave->link_interface != XGMII_LINK_MAC_PHY) netif_carrier_on(ndev); } else { writel(mac_control, GBE_REG_ADDR(slave, emac_regs, @@ -1773,7 +1775,9 @@ static void netcp_ethss_link_state_action(struct gbe_priv *gbe_dev, cpsw_ale_control_set(gbe_dev->ale, slave->port_num, ALE_PORT_STATE, ALE_PORT_STATE_DISABLE); - if (ndev) + if (ndev && + slave->link_interface != SGMII_LINK_MAC_PHY && + slave->link_interface != XGMII_LINK_MAC_PHY) netif_carrier_off(ndev); } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index a10b316..41071d3 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -128,7 +128,6 @@ struct ndis_tcp_ip_checksum_info; struct hv_netvsc_packet { /* Bookkeeping stuff */ u32 status; - bool part_of_skb; bool is_data_pkt; bool xmit_more; /* from skb */ @@ -612,6 +611,15 @@ struct multi_send_data { u32 count; /* counter of batched packets */ }; +/* The context of the netvsc device */ +struct net_device_context { + /* point back to our device context */ + struct hv_device *device_ctx; + struct delayed_work dwork; + struct work_struct work; + u32 msg_enable; /* debug level */ +}; + /* Per netvsc device */ struct netvsc_device { struct hv_device *dev; @@ -667,6 +675,9 @@ struct netvsc_device { struct multi_send_data msd[NR_CPUS]; u32 max_pkt; /* max number of pkt in one send, e.g. 8 */ u32 pkt_align; /* alignment bytes, e.g. 8 */ + + /* The net device context */ + struct net_device_context *nd_ctx; }; /* NdisInitialize message */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 2e8ad06..2d9ef53 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -889,11 +889,6 @@ int netvsc_send(struct hv_device *device, } else { packet->page_buf_cnt = 0; packet->total_data_buflen += msd_len; - if (!packet->part_of_skb) { - skb = (struct sk_buff *)(unsigned long)packet-> - send_completion_tid; - packet->send_completion_tid = 0; - } } if (msdp->pkt) @@ -1197,6 +1192,9 @@ int netvsc_device_add(struct hv_device *device, void *additional_info) */ ndev = net_device->ndev; + /* Add netvsc_device context to netvsc_device */ + net_device->nd_ctx = netdev_priv(ndev); + /* Initialize the NetVSC channel extension */ init_completion(&net_device->channel_init_wait); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index a3a9d38..5993c7e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -40,18 +40,21 @@ #include "hyperv_net.h" -struct net_device_context { - /* point back to our device context */ - struct hv_device *device_ctx; - struct delayed_work dwork; - struct work_struct work; -}; #define RING_SIZE_MIN 64 static int ring_size = 128; module_param(ring_size, int, S_IRUGO); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)"); +static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE | + NETIF_MSG_LINK | NETIF_MSG_IFUP | + NETIF_MSG_IFDOWN | NETIF_MSG_RX_ERR | + NETIF_MSG_TX_ERR; + +static int debug = -1; +module_param(debug, int, S_IRUGO); +MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); + static void do_set_multicast(struct work_struct *w) { struct net_device_context *ndevctx = @@ -235,9 +238,6 @@ void netvsc_xmit_completion(void *context) struct sk_buff *skb = (struct sk_buff *) (unsigned long)packet->send_completion_tid; - if (!packet->part_of_skb) - kfree(packet); - if (skb) dev_kfree_skb_any(skb); } @@ -389,7 +389,6 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) u32 net_trans_info; u32 hash; u32 skb_length; - u32 head_room; u32 pkt_sz; struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT]; @@ -402,7 +401,6 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) check_size: skb_length = skb->len; - head_room = skb_headroom(skb); num_data_pgs = netvsc_get_slots(skb) + 2; if (num_data_pgs > MAX_PAGE_BUFFER_COUNT && linear) { net_alert_ratelimited("packet too big: %u pages (%u bytes)\n", @@ -421,20 +419,14 @@ check_size: pkt_sz = sizeof(struct hv_netvsc_packet) + RNDIS_AND_PPI_SIZE; - if (head_room < pkt_sz) { - packet = kmalloc(pkt_sz, GFP_ATOMIC); - if (!packet) { - /* out of memory, drop packet */ - netdev_err(net, "unable to alloc hv_netvsc_packet\n"); - ret = -ENOMEM; - goto drop; - } - packet->part_of_skb = false; - } else { - /* Use the headroom for building up the packet */ - packet = (struct hv_netvsc_packet *)skb->head; - packet->part_of_skb = true; + ret = skb_cow_head(skb, pkt_sz); + if (ret) { + netdev_err(net, "unable to alloc hv_netvsc_packet\n"); + ret = -ENOMEM; + goto drop; } + /* Use the headroom for building up the packet */ + packet = (struct hv_netvsc_packet *)skb->head; packet->status = 0; packet->xmit_more = skb->xmit_more; @@ -591,8 +583,6 @@ drop: net->stats.tx_bytes += skb_length; net->stats.tx_packets++; } else { - if (packet && !packet->part_of_skb) - kfree(packet); if (ret != -EAGAIN) { dev_kfree_skb_any(skb); net->stats.tx_dropped++; @@ -888,6 +878,11 @@ static int netvsc_probe(struct hv_device *dev, net_device_ctx = netdev_priv(net); net_device_ctx->device_ctx = dev; + net_device_ctx->msg_enable = netif_msg_init(debug, default_msg); + if (netif_msg_probe(net_device_ctx)) + netdev_dbg(net, "netvsc msg_enable: %d\n", + net_device_ctx->msg_enable); + hv_set_drvdata(dev, net); INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change); INIT_WORK(&net_device_ctx->work, do_set_multicast); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 0d92efe..9118cea 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -429,7 +429,8 @@ int rndis_filter_receive(struct hv_device *dev, rndis_msg = pkt->data; - dump_rndis_message(dev, rndis_msg); + if (netif_msg_rx_err(net_dev->nd_ctx)) + dump_rndis_message(dev, rndis_msg); switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c index 49ce7ec..c9cb486c 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/phy/mdio-gpio.c @@ -80,7 +80,8 @@ static void mdio_dir(struct mdiobb_ctrl *ctrl, int dir) * assume the pin serves as pull-up. If direction is * output, the default value is high. */ - gpio_set_value(bitbang->mdo, 1 ^ bitbang->mdo_active_low); + gpio_set_value_cansleep(bitbang->mdo, + 1 ^ bitbang->mdo_active_low); return; } @@ -96,7 +97,8 @@ static int mdio_get(struct mdiobb_ctrl *ctrl) struct mdio_gpio_info *bitbang = container_of(ctrl, struct mdio_gpio_info, ctrl); - return gpio_get_value(bitbang->mdio) ^ bitbang->mdio_active_low; + return gpio_get_value_cansleep(bitbang->mdio) ^ + bitbang->mdio_active_low; } static void mdio_set(struct mdiobb_ctrl *ctrl, int what) @@ -105,9 +107,11 @@ static void mdio_set(struct mdiobb_ctrl *ctrl, int what) container_of(ctrl, struct mdio_gpio_info, ctrl); if (bitbang->mdo) - gpio_set_value(bitbang->mdo, what ^ bitbang->mdo_active_low); + gpio_set_value_cansleep(bitbang->mdo, + what ^ bitbang->mdo_active_low); else - gpio_set_value(bitbang->mdio, what ^ bitbang->mdio_active_low); + gpio_set_value_cansleep(bitbang->mdio, + what ^ bitbang->mdio_active_low); } static void mdc_set(struct mdiobb_ctrl *ctrl, int what) @@ -115,7 +119,7 @@ static void mdc_set(struct mdiobb_ctrl *ctrl, int what) struct mdio_gpio_info *bitbang = container_of(ctrl, struct mdio_gpio_info, ctrl); - gpio_set_value(bitbang->mdc, what ^ bitbang->mdc_active_low); + gpio_set_value_cansleep(bitbang->mdc, what ^ bitbang->mdc_active_low); } static struct mdiobb_ops mdio_gpio_ops = { diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c index 1a87a58..66edd99 100644 --- a/drivers/net/phy/mdio-mux-gpio.c +++ b/drivers/net/phy/mdio-mux-gpio.c @@ -12,33 +12,30 @@ #include <linux/module.h> #include <linux/phy.h> #include <linux/mdio-mux.h> -#include <linux/of_gpio.h> +#include <linux/gpio/consumer.h> #define DRV_VERSION "1.1" #define DRV_DESCRIPTION "GPIO controlled MDIO bus multiplexer driver" -#define MDIO_MUX_GPIO_MAX_BITS 8 - struct mdio_mux_gpio_state { - struct gpio_desc *gpio[MDIO_MUX_GPIO_MAX_BITS]; - unsigned int num_gpios; + struct gpio_descs *gpios; void *mux_handle; }; static int mdio_mux_gpio_switch_fn(int current_child, int desired_child, void *data) { - int values[MDIO_MUX_GPIO_MAX_BITS]; - unsigned int n; struct mdio_mux_gpio_state *s = data; + int values[s->gpios->ndescs]; + unsigned int n; if (current_child == desired_child) return 0; - for (n = 0; n < s->num_gpios; n++) { + for (n = 0; n < s->gpios->ndescs; n++) values[n] = (desired_child >> n) & 1; - } - gpiod_set_array_cansleep(s->num_gpios, s->gpio, values); + + gpiod_set_array_cansleep(s->gpios->ndescs, s->gpios->desc, values); return 0; } @@ -46,56 +43,33 @@ static int mdio_mux_gpio_switch_fn(int current_child, int desired_child, static int mdio_mux_gpio_probe(struct platform_device *pdev) { struct mdio_mux_gpio_state *s; - int num_gpios; - unsigned int n; int r; - if (!pdev->dev.of_node) - return -ENODEV; - - num_gpios = of_gpio_count(pdev->dev.of_node); - if (num_gpios <= 0 || num_gpios > MDIO_MUX_GPIO_MAX_BITS) - return -ENODEV; - s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; - s->num_gpios = num_gpios; - - for (n = 0; n < num_gpios; ) { - struct gpio_desc *gpio = gpiod_get_index(&pdev->dev, NULL, n, - GPIOD_OUT_LOW); - if (IS_ERR(gpio)) { - r = PTR_ERR(gpio); - goto err; - } - s->gpio[n] = gpio; - n++; - } + s->gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW); + if (IS_ERR(s->gpios)) + return PTR_ERR(s->gpios); r = mdio_mux_init(&pdev->dev, mdio_mux_gpio_switch_fn, &s->mux_handle, s); - if (r == 0) { - pdev->dev.platform_data = s; - return 0; - } -err: - while (n) { - n--; - gpiod_put(s->gpio[n]); + if (r != 0) { + gpiod_put_array(s->gpios); + return r; } - return r; + + pdev->dev.platform_data = s; + return 0; } static int mdio_mux_gpio_remove(struct platform_device *pdev) { - unsigned int n; struct mdio_mux_gpio_state *s = dev_get_platdata(&pdev->dev); mdio_mux_uninit(s->mux_handle); - for (n = 0; n < s->num_gpios; n++) - gpiod_put(s->gpio[n]); + gpiod_put_array(s->gpios); return 0; } diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c index 911b216..05005c6 100644 --- a/drivers/net/ppp/ppp_mppe.c +++ b/drivers/net/ppp/ppp_mppe.c @@ -478,7 +478,6 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, struct blkcipher_desc desc = { .tfm = state->arc4 }; unsigned ccount; int flushed = MPPE_BITS(ibuf) & MPPE_BIT_FLUSHED; - int sanity = 0; struct scatterlist sg_in[1], sg_out[1]; if (isize <= PPP_HDRLEN + MPPE_OVHD) { @@ -514,31 +513,19 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, "mppe_decompress[%d]: ENCRYPTED bit not set!\n", state->unit); state->sanity_errors += 100; - sanity = 1; + goto sanity_error; } if (!state->stateful && !flushed) { printk(KERN_DEBUG "mppe_decompress[%d]: FLUSHED bit not set in " "stateless mode!\n", state->unit); state->sanity_errors += 100; - sanity = 1; + goto sanity_error; } if (state->stateful && ((ccount & 0xff) == 0xff) && !flushed) { printk(KERN_DEBUG "mppe_decompress[%d]: FLUSHED bit not set on " "flag packet!\n", state->unit); state->sanity_errors += 100; - sanity = 1; - } - - if (sanity) { - if (state->sanity_errors < SANITY_MAX) - return DECOMP_ERROR; - else - /* - * Take LCP down if the peer is sending too many bogons. - * We don't want to do this for a single or just a few - * instances since it could just be due to packet corruption. - */ - return DECOMP_FATALERROR; + goto sanity_error; } /* @@ -546,6 +533,13 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, */ if (!state->stateful) { + /* Discard late packet */ + if ((ccount - state->ccount) % MPPE_CCOUNT_SPACE + > MPPE_CCOUNT_SPACE / 2) { + state->sanity_errors++; + goto sanity_error; + } + /* RFC 3078, sec 8.1. Rekey for every packet. */ while (state->ccount != ccount) { mppe_rekey(state, 0); @@ -649,6 +643,16 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, state->sanity_errors >>= 1; return osize; + +sanity_error: + if (state->sanity_errors < SANITY_MAX) + return DECOMP_ERROR; + else + /* Take LCP down if the peer is sending too many bogons. + * We don't want to do this for a single or just a few + * instances since it could just be due to packet corruption. + */ + return DECOMP_FATALERROR; } /* diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 154116a..27a5f95 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -730,12 +730,8 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, /* Only change unicasts */ if (!(is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { - int rc = vxlan_fdb_replace(f, ip, port, vni, + notify |= vxlan_fdb_replace(f, ip, port, vni, ifindex); - - if (rc < 0) - return rc; - notify |= rc; } else return -EOPNOTSUPP; } diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index c43aca6..0fc3fe5 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -667,6 +667,8 @@ static struct raw3215_info *raw3215_alloc_info(void) info->buffer = kzalloc(RAW3215_BUFFER_SIZE, GFP_KERNEL | GFP_DMA); info->inbuf = kzalloc(RAW3215_INBUF_SIZE, GFP_KERNEL | GFP_DMA); if (!info->buffer || !info->inbuf) { + kfree(info->inbuf); + kfree(info->buffer); kfree(info); return NULL; } diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c index cd4c293..fe8875f 100644 --- a/drivers/sh/pm_runtime.c +++ b/drivers/sh/pm_runtime.c @@ -80,9 +80,10 @@ static int __init sh_pm_runtime_init(void) if (IS_ENABLED(CONFIG_ARCH_SHMOBILE_MULTI)) { if (!of_machine_is_compatible("renesas,emev2") && !of_machine_is_compatible("renesas,r7s72100") && - !of_machine_is_compatible("renesas,r8a73a4") && #ifndef CONFIG_PM_GENERIC_DOMAINS_OF + !of_machine_is_compatible("renesas,r8a73a4") && !of_machine_is_compatible("renesas,r8a7740") && + !of_machine_is_compatible("renesas,sh73a0") && #endif !of_machine_is_compatible("renesas,r8a7778") && !of_machine_is_compatible("renesas,r8a7779") && @@ -90,9 +91,7 @@ static int __init sh_pm_runtime_init(void) !of_machine_is_compatible("renesas,r8a7791") && !of_machine_is_compatible("renesas,r8a7792") && !of_machine_is_compatible("renesas,r8a7793") && - !of_machine_is_compatible("renesas,r8a7794") && - !of_machine_is_compatible("renesas,sh7372") && - !of_machine_is_compatible("renesas,sh73a0")) + !of_machine_is_compatible("renesas,r8a7794")) return 0; } diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 08da4d3..46bcebb 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1998,6 +1998,8 @@ pci_wch_ch38x_setup(struct serial_private *priv, #define PCIE_DEVICE_ID_WCH_CH382_2S1P 0x3250 #define PCIE_DEVICE_ID_WCH_CH384_4S 0x3470 +#define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 + /* Unknown vendors/cards - this should not be in linux/pci_ids.h */ #define PCI_SUBDEVICE_ID_UNKNOWN_0x1584 0x1584 #define PCI_SUBDEVICE_ID_UNKNOWN_0x1588 0x1588 @@ -2520,6 +2522,13 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = pci_xr17v35x_setup, }, + { + .vendor = PCI_VENDOR_ID_EXAR, + .device = PCI_DEVICE_ID_EXAR_XR17V8358, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_xr17v35x_setup, + }, /* * Xircom cards */ @@ -2999,6 +3008,7 @@ enum pci_board_num_t { pbn_exar_XR17V352, pbn_exar_XR17V354, pbn_exar_XR17V358, + pbn_exar_XR17V8358, pbn_exar_ibm_saturn, pbn_pasemi_1682M, pbn_ni8430_2, @@ -3685,6 +3695,14 @@ static struct pciserial_board pci_boards[] = { .reg_shift = 0, .first_offset = 0, }, + [pbn_exar_XR17V8358] = { + .flags = FL_BASE0, + .num_ports = 16, + .base_baud = 7812500, + .uart_offset = 0x400, + .reg_shift = 0, + .first_offset = 0, + }, [pbn_exar_ibm_saturn] = { .flags = FL_BASE0, .num_ports = 1, @@ -5080,7 +5098,7 @@ static struct pci_device_id serial_pci_tbl[] = { 0, 0, pbn_exar_XR17C158 }, /* - * Exar Corp. XR17V35[248] Dual/Quad/Octal PCIe UARTs + * Exar Corp. XR17V[48]35[248] Dual/Quad/Octal/Hexa PCIe UARTs */ { PCI_VENDOR_ID_EXAR, PCI_DEVICE_ID_EXAR_XR17V352, PCI_ANY_ID, PCI_ANY_ID, @@ -5094,7 +5112,10 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_exar_XR17V358 }, - + { PCI_VENDOR_ID_EXAR, PCI_DEVICE_ID_EXAR_XR17V8358, + PCI_ANY_ID, PCI_ANY_ID, + 0, + 0, pbn_exar_XR17V8358 }, /* * Topic TP560 Data/Fax/Voice 56k modem (reported by Evan Clarke) */ diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index d58fe47..27dade2 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -880,6 +880,7 @@ static int atmel_prepare_tx_dma(struct uart_port *port) config.direction = DMA_MEM_TO_DEV; config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; config.dst_addr = port->mapbase + ATMEL_US_THR; + config.dst_maxburst = 1; ret = dmaengine_slave_config(atmel_port->chan_tx, &config); @@ -1059,6 +1060,7 @@ static int atmel_prepare_rx_dma(struct uart_port *port) config.direction = DMA_DEV_TO_MEM; config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; config.src_addr = port->mapbase + ATMEL_US_RHR; + config.src_maxburst = 1; ret = dmaengine_slave_config(atmel_port->chan_rx, &config); diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c index 5b73afb..137381e 100644 --- a/drivers/tty/serial/of_serial.c +++ b/drivers/tty/serial/of_serial.c @@ -346,7 +346,6 @@ static const struct of_device_id of_platform_serial_table[] = { { .compatible = "ibm,qpace-nwp-serial", .data = (void *)PORT_NWPSERIAL, }, #endif - { .type = "serial", .data = (void *)PORT_UNKNOWN, }, { /* end of list */ }, }; diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c index cf08876..a0ae942 100644 --- a/drivers/tty/serial/samsung.c +++ b/drivers/tty/serial/samsung.c @@ -1068,8 +1068,9 @@ static int s3c64xx_serial_startup(struct uart_port *port) spin_lock_irqsave(&port->lock, flags); ufcon = rd_regl(port, S3C2410_UFCON); - ufcon |= S3C2410_UFCON_RESETRX | S3C2410_UFCON_RESETTX | - S5PV210_UFCON_RXTRIG8; + ufcon |= S3C2410_UFCON_RESETRX | S5PV210_UFCON_RXTRIG8; + if (!uart_console(port)) + ufcon |= S3C2410_UFCON_RESETTX; wr_regl(port, S3C2410_UFCON, ufcon); enable_rx_pio(ourport); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index eb5b03b..0b7bb12 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1770,7 +1770,7 @@ static const struct file_operations uart_proc_fops = { * @port: the port to write the message * @s: array of characters * @count: number of characters in string to write - * @write: function to write character to port + * @putchar: function to write character to port */ void uart_console_write(struct uart_port *port, const char *s, unsigned int count, diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c index 708eead..b1c6bd3 100644 --- a/drivers/tty/serial/uartlite.c +++ b/drivers/tty/serial/uartlite.c @@ -632,7 +632,8 @@ MODULE_DEVICE_TABLE(of, ulite_of_match); static int ulite_probe(struct platform_device *pdev) { - struct resource *res, *res2; + struct resource *res; + int irq; int id = pdev->id; #ifdef CONFIG_OF const __be32 *prop; @@ -646,11 +647,11 @@ static int ulite_probe(struct platform_device *pdev) if (!res) return -ENODEV; - res2 = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res2) - return -ENODEV; + irq = platform_get_irq(pdev, 0); + if (irq <= 0) + return -ENXIO; - return ulite_assign(&pdev->dev, id, res->start, res2->start); + return ulite_assign(&pdev->dev, id, res->start, irq); } static int ulite_remove(struct platform_device *pdev) diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index f218ec6..3ddbac7 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1331,9 +1331,9 @@ static SIMPLE_DEV_PM_OPS(cdns_uart_dev_pm_ops, cdns_uart_suspend, */ static int cdns_uart_probe(struct platform_device *pdev) { - int rc, id; + int rc, id, irq; struct uart_port *port; - struct resource *res, *res2; + struct resource *res; struct cdns_uart *cdns_uart_data; cdns_uart_data = devm_kzalloc(&pdev->dev, sizeof(*cdns_uart_data), @@ -1380,9 +1380,9 @@ static int cdns_uart_probe(struct platform_device *pdev) goto err_out_clk_disable; } - res2 = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res2) { - rc = -ENODEV; + irq = platform_get_irq(pdev, 0); + if (irq <= 0) { + rc = -ENXIO; goto err_out_clk_disable; } @@ -1411,7 +1411,7 @@ static int cdns_uart_probe(struct platform_device *pdev) * and triggers invocation of the config_port() entry point. */ port->mapbase = res->start; - port->irq = res2->start; + port->irq = irq; port->dev = &pdev->dev; port->uartclk = clk_get_rate(cdns_uart_data->uartclk); port->private_data = cdns_uart_data; diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 632fc81..8e53fe4 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -536,7 +536,7 @@ EXPORT_SYMBOL(tty_termios_hw_change); * Locking: termios_rwsem */ -static int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) +int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) { struct ktermios old_termios; struct tty_ldisc *ld; @@ -569,6 +569,7 @@ static int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) up_write(&tty->termios_rwsem); return 0; } +EXPORT_SYMBOL_GPL(tty_set_termios); /** * set_termios - set termios values for a tty diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c index 083acf4..19d655a 100644 --- a/drivers/usb/chipidea/otg_fsm.c +++ b/drivers/usb/chipidea/otg_fsm.c @@ -520,7 +520,6 @@ static int ci_otg_start_host(struct otg_fsm *fsm, int on) { struct ci_hdrc *ci = container_of(fsm, struct ci_hdrc, fsm); - mutex_unlock(&fsm->lock); if (on) { ci_role_stop(ci); ci_role_start(ci, CI_ROLE_HOST); @@ -529,7 +528,6 @@ static int ci_otg_start_host(struct otg_fsm *fsm, int on) hw_device_reset(ci); ci_role_start(ci, CI_ROLE_GADGET); } - mutex_lock(&fsm->lock); return 0; } @@ -537,12 +535,10 @@ static int ci_otg_start_gadget(struct otg_fsm *fsm, int on) { struct ci_hdrc *ci = container_of(fsm, struct ci_hdrc, fsm); - mutex_unlock(&fsm->lock); if (on) usb_gadget_vbus_connect(&ci->gadget); else usb_gadget_vbus_disconnect(&ci->gadget); - mutex_lock(&fsm->lock); return 0; } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 3e15add..5c8f581 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1142,11 +1142,16 @@ static int acm_probe(struct usb_interface *intf, } while (buflen > 0) { + elength = buffer[0]; + if (!elength) { + dev_err(&intf->dev, "skipping garbage byte\n"); + elength = 1; + goto next_desc; + } if (buffer[1] != USB_DT_CS_INTERFACE) { dev_err(&intf->dev, "skipping garbage\n"); goto next_desc; } - elength = buffer[0]; switch (buffer[2]) { case USB_CDC_UNION_TYPE: /* we've found it */ diff --git a/drivers/usb/host/ehci-msm.c b/drivers/usb/host/ehci-msm.c index 9db74ca..275c92e 100644 --- a/drivers/usb/host/ehci-msm.c +++ b/drivers/usb/host/ehci-msm.c @@ -88,13 +88,20 @@ static int ehci_msm_probe(struct platform_device *pdev) } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hcd->regs = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(hcd->regs)) { - ret = PTR_ERR(hcd->regs); + if (!res) { + dev_err(&pdev->dev, "Unable to get memory resource\n"); + ret = -ENODEV; goto put_hcd; } + hcd->rsrc_start = res->start; hcd->rsrc_len = resource_size(res); + hcd->regs = devm_ioremap(&pdev->dev, hcd->rsrc_start, hcd->rsrc_len); + if (!hcd->regs) { + dev_err(&pdev->dev, "ioremap failed\n"); + ret = -ENOMEM; + goto put_hcd; + } /* * OTG driver takes care of PHY initialization, clock management, diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h index 9893d69..f58caa9 100644 --- a/drivers/usb/storage/uas-detect.h +++ b/drivers/usb/storage/uas-detect.h @@ -51,7 +51,8 @@ static int uas_find_endpoints(struct usb_host_interface *alt, } static int uas_use_uas_driver(struct usb_interface *intf, - const struct usb_device_id *id) + const struct usb_device_id *id, + unsigned long *flags_ret) { struct usb_host_endpoint *eps[4] = { }; struct usb_device *udev = interface_to_usbdev(intf); @@ -73,7 +74,7 @@ static int uas_use_uas_driver(struct usb_interface *intf, * this writing the following versions exist: * ASM1051 - no uas support version * ASM1051 - with broken (*) uas support - * ASM1053 - with working uas support + * ASM1053 - with working uas support, but problems with large xfers * ASM1153 - with working uas support * * Devices with these chips re-use a number of device-ids over the @@ -103,6 +104,9 @@ static int uas_use_uas_driver(struct usb_interface *intf, } else if (usb_ss_max_streams(&eps[1]->ss_ep_comp) == 32) { /* Possibly an ASM1051, disable uas */ flags |= US_FL_IGNORE_UAS; + } else { + /* ASM1053, these have issues with large transfers */ + flags |= US_FL_MAX_SECTORS_240; } } @@ -132,5 +136,8 @@ static int uas_use_uas_driver(struct usb_interface *intf, return 0; } + if (flags_ret) + *flags_ret = flags; + return 1; } diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 6cdabdc..6d3122a 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -759,7 +759,10 @@ static int uas_eh_bus_reset_handler(struct scsi_cmnd *cmnd) static int uas_slave_alloc(struct scsi_device *sdev) { - sdev->hostdata = (void *)sdev->host->hostdata; + struct uas_dev_info *devinfo = + (struct uas_dev_info *)sdev->host->hostdata; + + sdev->hostdata = devinfo; /* USB has unusual DMA-alignment requirements: Although the * starting address of each scatter-gather element doesn't matter, @@ -778,6 +781,11 @@ static int uas_slave_alloc(struct scsi_device *sdev) */ blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1)); + if (devinfo->flags & US_FL_MAX_SECTORS_64) + blk_queue_max_hw_sectors(sdev->request_queue, 64); + else if (devinfo->flags & US_FL_MAX_SECTORS_240) + blk_queue_max_hw_sectors(sdev->request_queue, 240); + return 0; } @@ -887,8 +895,9 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) struct Scsi_Host *shost = NULL; struct uas_dev_info *devinfo; struct usb_device *udev = interface_to_usbdev(intf); + unsigned long dev_flags; - if (!uas_use_uas_driver(intf, id)) + if (!uas_use_uas_driver(intf, id, &dev_flags)) return -ENODEV; if (uas_switch_interface(udev, intf)) @@ -910,8 +919,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) devinfo->udev = udev; devinfo->resetting = 0; devinfo->shutdown = 0; - devinfo->flags = id->driver_info; - usb_stor_adjust_quirks(udev, &devinfo->flags); + devinfo->flags = dev_flags; init_usb_anchor(&devinfo->cmd_urbs); init_usb_anchor(&devinfo->sense_urbs); init_usb_anchor(&devinfo->data_urbs); diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index 5600c33..6c10c88 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -479,7 +479,8 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags) US_FL_SINGLE_LUN | US_FL_NO_WP_DETECT | US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 | US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE | - US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES); + US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES | + US_FL_MAX_SECTORS_240); p = quirks; while (*p) { @@ -520,6 +521,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags) case 'f': f |= US_FL_NO_REPORT_OPCODES; break; + case 'g': + f |= US_FL_MAX_SECTORS_240; + break; case 'h': f |= US_FL_CAPACITY_HEURISTICS; break; @@ -1080,7 +1084,7 @@ static int storage_probe(struct usb_interface *intf, /* If uas is enabled and this device can do uas then ignore it. */ #if IS_ENABLED(CONFIG_USB_UAS) - if (uas_use_uas_driver(intf, id)) + if (uas_use_uas_driver(intf, id, NULL)) return -ENXIO; #endif diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index cde698a..a2ae427 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1802,6 +1802,8 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev) set_nlink(inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item)); BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item); + BTRFS_I(inode)->last_trans = btrfs_stack_inode_transid(inode_item); + inode->i_version = btrfs_stack_inode_sequence(inode_item); inode->i_rdev = 0; *rdev = btrfs_stack_inode_rdev(inode_item); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1eef4ee..0ec8e22 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3178,8 +3178,8 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans, bi = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item)); btrfs_mark_buffer_dirty(leaf); - btrfs_release_path(path); fail: + btrfs_release_path(path); if (ret) btrfs_abort_transaction(trans, root, ret); return ret; @@ -3305,8 +3305,7 @@ again: spin_lock(&block_group->lock); if (block_group->cached != BTRFS_CACHE_FINISHED || - !btrfs_test_opt(root, SPACE_CACHE) || - block_group->delalloc_bytes) { + !btrfs_test_opt(root, SPACE_CACHE)) { /* * don't bother trying to write stuff out _if_ * a) we're not cached, @@ -3408,17 +3407,14 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans, int loops = 0; spin_lock(&cur_trans->dirty_bgs_lock); - if (!list_empty(&cur_trans->dirty_bgs)) { - list_splice_init(&cur_trans->dirty_bgs, &dirty); + if (list_empty(&cur_trans->dirty_bgs)) { + spin_unlock(&cur_trans->dirty_bgs_lock); + return 0; } + list_splice_init(&cur_trans->dirty_bgs, &dirty); spin_unlock(&cur_trans->dirty_bgs_lock); again: - if (list_empty(&dirty)) { - btrfs_free_path(path); - return 0; - } - /* * make sure all the block groups on our dirty list actually * exist @@ -3431,18 +3427,16 @@ again: return -ENOMEM; } + /* + * cache_write_mutex is here only to save us from balance or automatic + * removal of empty block groups deleting this block group while we are + * writing out the cache + */ + mutex_lock(&trans->transaction->cache_write_mutex); while (!list_empty(&dirty)) { cache = list_first_entry(&dirty, struct btrfs_block_group_cache, dirty_list); - - /* - * cache_write_mutex is here only to save us from balance - * deleting this block group while we are writing out the - * cache - */ - mutex_lock(&trans->transaction->cache_write_mutex); - /* * this can happen if something re-dirties a block * group that is already under IO. Just wait for it to @@ -3495,7 +3489,6 @@ again: } if (!ret) ret = write_one_cache_group(trans, root, path, cache); - mutex_unlock(&trans->transaction->cache_write_mutex); /* if its not on the io list, we need to put the block group */ if (should_put) @@ -3503,7 +3496,16 @@ again: if (ret) break; + + /* + * Avoid blocking other tasks for too long. It might even save + * us from writing caches for block groups that are going to be + * removed. + */ + mutex_unlock(&trans->transaction->cache_write_mutex); + mutex_lock(&trans->transaction->cache_write_mutex); } + mutex_unlock(&trans->transaction->cache_write_mutex); /* * go through delayed refs for all the stuff we've just kicked off @@ -3514,8 +3516,15 @@ again: loops++; spin_lock(&cur_trans->dirty_bgs_lock); list_splice_init(&cur_trans->dirty_bgs, &dirty); + /* + * dirty_bgs_lock protects us from concurrent block group + * deletes too (not just cache_write_mutex). + */ + if (!list_empty(&dirty)) { + spin_unlock(&cur_trans->dirty_bgs_lock); + goto again; + } spin_unlock(&cur_trans->dirty_bgs_lock); - goto again; } btrfs_free_path(path); @@ -7537,7 +7546,7 @@ static void unuse_block_rsv(struct btrfs_fs_info *fs_info, * returns the key for the extent through ins, and a tree buffer for * the first block of the extent through buf. * - * returns the tree buffer or NULL. + * returns the tree buffer or an ERR_PTR on error. */ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -7548,6 +7557,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_key ins; struct btrfs_block_rsv *block_rsv; struct extent_buffer *buf; + struct btrfs_delayed_extent_op *extent_op; u64 flags = 0; int ret; u32 blocksize = root->nodesize; @@ -7568,13 +7578,14 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, ret = btrfs_reserve_extent(root, blocksize, blocksize, empty_size, hint, &ins, 0, 0); - if (ret) { - unuse_block_rsv(root->fs_info, block_rsv, blocksize); - return ERR_PTR(ret); - } + if (ret) + goto out_unuse; buf = btrfs_init_new_buffer(trans, root, ins.objectid, level); - BUG_ON(IS_ERR(buf)); /* -ENOMEM */ + if (IS_ERR(buf)) { + ret = PTR_ERR(buf); + goto out_free_reserved; + } if (root_objectid == BTRFS_TREE_RELOC_OBJECTID) { if (parent == 0) @@ -7584,9 +7595,11 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, BUG_ON(parent > 0); if (root_objectid != BTRFS_TREE_LOG_OBJECTID) { - struct btrfs_delayed_extent_op *extent_op; extent_op = btrfs_alloc_delayed_extent_op(); - BUG_ON(!extent_op); /* -ENOMEM */ + if (!extent_op) { + ret = -ENOMEM; + goto out_free_buf; + } if (key) memcpy(&extent_op->key, key, sizeof(extent_op->key)); else @@ -7601,13 +7614,24 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, extent_op->level = level; ret = btrfs_add_delayed_tree_ref(root->fs_info, trans, - ins.objectid, - ins.offset, parent, root_objectid, - level, BTRFS_ADD_DELAYED_EXTENT, - extent_op, 0); - BUG_ON(ret); /* -ENOMEM */ + ins.objectid, ins.offset, + parent, root_objectid, level, + BTRFS_ADD_DELAYED_EXTENT, + extent_op, 0); + if (ret) + goto out_free_delayed; } return buf; + +out_free_delayed: + btrfs_free_delayed_extent_op(extent_op); +out_free_buf: + free_extent_buffer(buf); +out_free_reserved: + btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 0); +out_unuse: + unuse_block_rsv(root->fs_info, block_rsv, blocksize); + return ERR_PTR(ret); } struct walk_control { diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 782f3bc..43af5a6 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4560,36 +4560,37 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb) do { index--; page = eb->pages[index]; - if (page && mapped) { + if (!page) + continue; + if (mapped) spin_lock(&page->mapping->private_lock); + /* + * We do this since we'll remove the pages after we've + * removed the eb from the radix tree, so we could race + * and have this page now attached to the new eb. So + * only clear page_private if it's still connected to + * this eb. + */ + if (PagePrivate(page) && + page->private == (unsigned long)eb) { + BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + BUG_ON(PageDirty(page)); + BUG_ON(PageWriteback(page)); /* - * We do this since we'll remove the pages after we've - * removed the eb from the radix tree, so we could race - * and have this page now attached to the new eb. So - * only clear page_private if it's still connected to - * this eb. + * We need to make sure we haven't be attached + * to a new eb. */ - if (PagePrivate(page) && - page->private == (unsigned long)eb) { - BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); - BUG_ON(PageDirty(page)); - BUG_ON(PageWriteback(page)); - /* - * We need to make sure we haven't be attached - * to a new eb. - */ - ClearPagePrivate(page); - set_page_private(page, 0); - /* One for the page private */ - page_cache_release(page); - } - spin_unlock(&page->mapping->private_lock); - - } - if (page) { - /* One for when we alloced the page */ + ClearPagePrivate(page); + set_page_private(page, 0); + /* One for the page private */ page_cache_release(page); } + + if (mapped) + spin_unlock(&page->mapping->private_lock); + + /* One for when we alloced the page */ + page_cache_release(page); } while (index != 0); } @@ -4870,6 +4871,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, mark_extent_buffer_accessed(exists, p); goto free_eb; } + exists = NULL; /* * Do this so attach doesn't complain and we need to @@ -4933,12 +4935,12 @@ again: return eb; free_eb: + WARN_ON(!atomic_dec_and_test(&eb->refs)); for (i = 0; i < num_pages; i++) { if (eb->pages[i]) unlock_page(eb->pages[i]); } - WARN_ON(!atomic_dec_and_test(&eb->refs)); btrfs_release_extent_buffer(eb); return exists; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 81fa75a..41c510b 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1218,7 +1218,7 @@ out: * * This function writes out a free space cache struct to disk for quick recovery * on mount. This will return 0 if it was successfull in writing the cache out, - * and -1 if it was not. + * or an errno if it was not. */ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, struct btrfs_free_space_ctl *ctl, @@ -1235,12 +1235,12 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, int must_iput = 0; if (!i_size_read(inode)) - return -1; + return -EIO; WARN_ON(io_ctl->pages); ret = io_ctl_init(io_ctl, inode, root, 1); if (ret) - return -1; + return ret; if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) { down_write(&block_group->data_rwsem); @@ -1258,7 +1258,9 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, } /* Lock all pages first so we can lock the extent safely. */ - io_ctl_prepare_pages(io_ctl, inode, 0); + ret = io_ctl_prepare_pages(io_ctl, inode, 0); + if (ret) + goto out; lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, 0, &cached_state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ada4d24..8bb01367 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3632,25 +3632,28 @@ static void btrfs_read_locked_inode(struct inode *inode) BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item); BTRFS_I(inode)->last_trans = btrfs_inode_transid(leaf, inode_item); + inode->i_version = btrfs_inode_sequence(leaf, inode_item); + inode->i_generation = BTRFS_I(inode)->generation; + inode->i_rdev = 0; + rdev = btrfs_inode_rdev(leaf, inode_item); + + BTRFS_I(inode)->index_cnt = (u64)-1; + BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item); + +cache_index: /* * If we were modified in the current generation and evicted from memory * and then re-read we need to do a full sync since we don't have any * idea about which extents were modified before we were evicted from * cache. + * + * This is required for both inode re-read from disk and delayed inode + * in delayed_nodes_tree. */ if (BTRFS_I(inode)->last_trans == root->fs_info->generation) set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags); - inode->i_version = btrfs_inode_sequence(leaf, inode_item); - inode->i_generation = BTRFS_I(inode)->generation; - inode->i_rdev = 0; - rdev = btrfs_inode_rdev(leaf, inode_item); - - BTRFS_I(inode)->index_cnt = (u64)-1; - BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item); - -cache_index: path->slots[0]++; if (inode->i_nlink != 1 || path->slots[0] >= btrfs_header_nritems(leaf)) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b05653f..1c22c65 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2410,7 +2410,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, "Attempt to delete subvolume %llu during send", dest->root_key.objectid); err = -EPERM; - goto out_dput; + goto out_unlock_inode; } d_invalidate(dentry); @@ -2505,6 +2505,7 @@ out_up_write: root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); } +out_unlock_inode: mutex_unlock(&inode->i_mutex); if (!err) { shrink_dcache_sb(root->fs_info->sb); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 8bcd2a0..96aebf3 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1058,6 +1058,7 @@ static int contains_pending_extent(struct btrfs_trans_handle *trans, struct extent_map *em; struct list_head *search_list = &trans->transaction->pending_chunks; int ret = 0; + u64 physical_start = *start; again: list_for_each_entry(em, search_list, list) { @@ -1068,9 +1069,9 @@ again: for (i = 0; i < map->num_stripes; i++) { if (map->stripes[i].dev != device) continue; - if (map->stripes[i].physical >= *start + len || + if (map->stripes[i].physical >= physical_start + len || map->stripes[i].physical + em->orig_block_len <= - *start) + physical_start) continue; *start = map->stripes[i].physical + em->orig_block_len; @@ -1193,8 +1194,14 @@ again: */ if (contains_pending_extent(trans, device, &search_start, - hole_size)) - hole_size = 0; + hole_size)) { + if (key.offset >= search_start) { + hole_size = key.offset - search_start; + } else { + WARN_ON_ONCE(1); + hole_size = 0; + } + } if (hole_size > max_hole_size) { max_hole_start = search_start; diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index f5ca0e9..1c3002e 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -124,7 +124,6 @@ #ifndef ACPI_USE_SYSTEM_INTTYPES typedef unsigned char u8; -typedef unsigned char u8; typedef unsigned short u16; typedef short s16; typedef COMPILER_DEPENDENT_UINT64 u64; diff --git a/include/linux/kexec.h b/include/linux/kexec.h index e60a745..e804306 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -40,6 +40,10 @@ #error KEXEC_CONTROL_MEMORY_LIMIT not defined #endif +#ifndef KEXEC_CONTROL_MEMORY_GFP +#define KEXEC_CONTROL_MEMORY_GFP GFP_KERNEL +#endif + #ifndef KEXEC_CONTROL_PAGE_SIZE #error KEXEC_CONTROL_PAGE_SIZE not defined #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bcbde79..1899c74 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -60,6 +60,7 @@ struct phy_device; struct wireless_dev; /* 802.15.4 specific */ struct wpan_dev; +struct mpls_dev; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -976,7 +977,8 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, - * struct net_device *dev, u32 filter_mask) + * struct net_device *dev, u32 filter_mask, + * int nlflags) * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags); * @@ -1172,7 +1174,8 @@ struct net_device_ops { int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask); + u32 filter_mask, + int nlflags); int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); @@ -1627,6 +1630,9 @@ struct net_device { void *ax25_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; +#if IS_ENABLED(CONFIG_MPLS_ROUTING) + struct mpls_dev __rcu *mpls_ptr; +#endif /* * Cache lines mostly used on receive path (including eth_type_trans()) @@ -2021,10 +2027,10 @@ struct pcpu_sw_netstats { ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ if (pcpu_stats) { \ - int i; \ - for_each_possible_cpu(i) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ - stat = per_cpu_ptr(pcpu_stats, i); \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index ab8f76d..f2fdb5a 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -39,12 +39,24 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb) static inline int nf_bridge_get_physinif(const struct sk_buff *skb) { - return skb->nf_bridge ? skb->nf_bridge->physindev->ifindex : 0; + struct nf_bridge_info *nf_bridge; + + if (skb->nf_bridge == NULL) + return 0; + + nf_bridge = skb->nf_bridge; + return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0; } static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) { - return skb->nf_bridge ? skb->nf_bridge->physoutdev->ifindex : 0; + struct nf_bridge_info *nf_bridge; + + if (skb->nf_bridge == NULL) + return 0; + + nf_bridge = skb->nf_bridge; + return nf_bridge->physoutdev ? nf_bridge->physoutdev->ifindex : 0; } static inline struct net_device * diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index e23d242..dbcbcc5 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -282,7 +282,8 @@ static inline bool rht_shrink_below_30(const struct rhashtable *ht, static inline bool rht_grow_above_100(const struct rhashtable *ht, const struct bucket_table *tbl) { - return atomic_read(&ht->nelems) > tbl->size; + return atomic_read(&ht->nelems) > tbl->size && + (!ht->p.max_size || tbl->size < ht->p.max_size); } /* The bucket lock is selected based on the hash and protects mutations diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 2da5d10..7b8e260 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -122,5 +122,5 @@ extern int ndo_dflt_fdb_del(struct ndmsg *ndm, extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode, - u32 flags, u32 mask); + u32 flags, u32 mask, int nlflags); #endif /* __LINUX_RTNETLINK_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 8222ae4..26a2e61 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -175,14 +175,6 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); extern void update_cpu_load_nohz(void); -/* Notifier for when a task gets migrated to a new CPU */ -struct task_migration_notifier { - struct task_struct *task; - int from_cpu; - int to_cpu; -}; -extern void register_task_migration_notifier(struct notifier_block *n); - extern unsigned long get_parent_ip(unsigned long addr); extern void dump_cpu_task(int cpu); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 06793b5..66e374d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -773,6 +773,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); +struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) diff --git a/include/linux/tty.h b/include/linux/tty.h index 358a337..fe5623c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -491,6 +491,7 @@ static inline speed_t tty_get_baud_rate(struct tty_struct *tty) extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b); +extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); extern void tty_ldisc_deref(struct tty_ldisc *); diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index a7f2604..7f5f78b 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -77,6 +77,8 @@ /* Cannot handle ATA_12 or ATA_16 CDBs */ \ US_FLAG(NO_REPORT_OPCODES, 0x04000000) \ /* Cannot handle MI_REPORT_SUPPORTED_OPERATION_CODES */ \ + US_FLAG(MAX_SECTORS_240, 0x08000000) \ + /* Sets max_sectors to 240 */ \ #define US_FLAG(name, value) US_FL_##name = value , enum { US_DO_ALL_FLAGS }; diff --git a/include/net/bonding.h b/include/net/bonding.h index fda6fee..78ed135 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -30,13 +30,6 @@ #include <net/bond_alb.h> #include <net/bond_options.h> -#define DRV_VERSION "3.7.1" -#define DRV_RELDATE "April 27, 2011" -#define DRV_NAME "bonding" -#define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" - -#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" - #define BOND_MAX_ARP_TARGETS 16 #define BOND_DEFAULT_MIIMON 100 diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 7b5887c..48a81582 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -279,12 +279,6 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk, void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); -static inline void inet_csk_reqsk_queue_removed(struct sock *sk, - struct request_sock *req) -{ - reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); -} - static inline void inet_csk_reqsk_queue_added(struct sock *sk, const unsigned long timeout) { @@ -306,19 +300,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue); } -static inline void inet_csk_reqsk_queue_unlink(struct sock *sk, - struct request_sock *req) -{ - reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req); -} - -static inline void inet_csk_reqsk_queue_drop(struct sock *sk, - struct request_sock *req) -{ - inet_csk_reqsk_queue_unlink(sk, req); - inet_csk_reqsk_queue_removed(sk, req); - reqsk_put(req); -} +void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index fe41f3c..9f4265c 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -212,24 +212,6 @@ static inline int reqsk_queue_empty(struct request_sock_queue *queue) return queue->rskq_accept_head == NULL; } -static inline void reqsk_queue_unlink(struct request_sock_queue *queue, - struct request_sock *req) -{ - struct listen_sock *lopt = queue->listen_opt; - struct request_sock **prev; - - spin_lock(&queue->syn_wait_lock); - - prev = &lopt->syn_table[req->rsk_hash]; - while (*prev != req) - prev = &(*prev)->dl_next; - *prev = req->dl_next; - - spin_unlock(&queue->syn_wait_lock); - if (del_timer(&req->rsk_timer)) - reqsk_put(req); -} - static inline void reqsk_queue_add(struct request_sock_queue *queue, struct request_sock *req, struct sock *parent, diff --git a/include/sound/designware_i2s.h b/include/sound/designware_i2s.h index 26f406e..3a8fca9 100644 --- a/include/sound/designware_i2s.h +++ b/include/sound/designware_i2s.h @@ -1,5 +1,5 @@ /* - * Copyright (ST) 2012 Rajeev Kumar (rajeev-dlh.kumar@st.com) + * Copyright (ST) 2012 Rajeev Kumar (rajeevkumar.linux@gmail.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 diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h index 0de95cc..5bd1346 100644 --- a/include/sound/emu10k1.h +++ b/include/sound/emu10k1.h @@ -41,7 +41,8 @@ #define EMUPAGESIZE 4096 #define MAXREQVOICES 8 -#define MAXPAGES 8192 +#define MAXPAGES0 4096 /* 32 bit mode */ +#define MAXPAGES1 8192 /* 31 bit mode */ #define RESERVED 0 #define NUM_MIDI 16 #define NUM_G 64 /* use all channels */ @@ -50,8 +51,7 @@ /* FIXME? - according to the OSS driver the EMU10K1 needs a 29 bit DMA mask */ #define EMU10K1_DMA_MASK 0x7fffffffUL /* 31bit */ -#define AUDIGY_DMA_MASK 0x7fffffffUL /* 31bit FIXME - 32 should work? */ - /* See ALSA bug #1276 - rlrevell */ +#define AUDIGY_DMA_MASK 0xffffffffUL /* 32bit mode */ #define TMEMSIZE 256*1024 #define TMEMSIZEREG 4 @@ -466,8 +466,11 @@ #define MAPB 0x0d /* Cache map B */ -#define MAP_PTE_MASK 0xffffe000 /* The 19 MSBs of the PTE indexed by the PTI */ -#define MAP_PTI_MASK 0x00001fff /* The 13 bit index to one of the 8192 PTE dwords */ +#define MAP_PTE_MASK0 0xfffff000 /* The 20 MSBs of the PTE indexed by the PTI */ +#define MAP_PTI_MASK0 0x00000fff /* The 12 bit index to one of the 4096 PTE dwords */ + +#define MAP_PTE_MASK1 0xffffe000 /* The 19 MSBs of the PTE indexed by the PTI */ +#define MAP_PTI_MASK1 0x00001fff /* The 13 bit index to one of the 8192 PTE dwords */ /* 0x0e, 0x0f: Not used */ @@ -1704,6 +1707,7 @@ struct snd_emu10k1 { unsigned short model; /* subsystem id */ unsigned int card_type; /* EMU10K1_CARD_* */ unsigned int ecard_ctrl; /* ecard control bits */ + unsigned int address_mode; /* address mode */ unsigned long dma_mask; /* PCI DMA mask */ unsigned int delay_pcm_irq; /* in samples */ int max_cache_pages; /* max memory size / PAGE_SIZE */ diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 0bc8364..1065095 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -287,7 +287,7 @@ struct device; .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | SNDRV_CTL_ELEM_ACCESS_READWRITE,\ .tlv.p = (tlv_array), \ .get = snd_soc_dapm_get_volsw, .put = snd_soc_dapm_put_volsw, \ - .private_value = SOC_SINGLE_VALUE(reg, shift, max, invert, 0) } + .private_value = SOC_SINGLE_VALUE(reg, shift, max, invert, 1) } #define SOC_DAPM_SINGLE_TLV_VIRT(xname, max, tlv_array) \ SOC_DAPM_SINGLE(xname, SND_SOC_NOPM, 0, max, 0, tlv_array) #define SOC_DAPM_ENUM(xname, xenum) \ diff --git a/include/sound/soc.h b/include/sound/soc.h index fcb312b..f6226914 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -387,8 +387,20 @@ int snd_soc_codec_set_pll(struct snd_soc_codec *codec, int pll_id, int source, int snd_soc_register_card(struct snd_soc_card *card); int snd_soc_unregister_card(struct snd_soc_card *card); int devm_snd_soc_register_card(struct device *dev, struct snd_soc_card *card); +#ifdef CONFIG_PM_SLEEP int snd_soc_suspend(struct device *dev); int snd_soc_resume(struct device *dev); +#else +static inline int snd_soc_suspend(struct device *dev) +{ + return 0; +} + +static inline int snd_soc_resume(struct device *dev) +{ + return 0; +} +#endif int snd_soc_poweroff(struct device *dev); int snd_soc_register_platform(struct device *dev, const struct snd_soc_platform_driver *platform_drv); diff --git a/include/sound/spear_dma.h b/include/sound/spear_dma.h index 65aca51..e290de4 100644 --- a/include/sound/spear_dma.h +++ b/include/sound/spear_dma.h @@ -1,7 +1,7 @@ /* * linux/spear_dma.h * -* Copyright (ST) 2012 Rajeev Kumar (rajeev-dlh.kumar@st.com) +* Copyright (ST) 2012 Rajeev Kumar (rajeevkumar.linux@gmail.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 diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index a3318f3..915980a 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -155,7 +155,7 @@ static inline unsigned vring_size(unsigned int num, unsigned long align) } /* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */ -/* Assuming a given event_idx value from the other size, if +/* Assuming a given event_idx value from the other side, if * we have just incremented index from old to new_idx, * should we trigger an event? */ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old) diff --git a/kernel/Makefile b/kernel/Makefile index 0f8f8b0..60c302c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -197,9 +197,9 @@ x509.genkey: @echo >>x509.genkey "x509_extensions = myexts" @echo >>x509.genkey @echo >>x509.genkey "[ req_distinguished_name ]" - @echo >>x509.genkey "O = Magrathea" - @echo >>x509.genkey "CN = Glacier signing key" - @echo >>x509.genkey "emailAddress = slartibartfast@magrathea.h2g2" + @echo >>x509.genkey "#O = Unspecified company" + @echo >>x509.genkey "CN = Build time autogenerated kernel key" + @echo >>x509.genkey "#emailAddress = unspecified.user@unspecified.company" @echo >>x509.genkey @echo >>x509.genkey "[ myexts ]" @echo >>x509.genkey "basicConstraints=critical,CA:FALSE" diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4139a0f..54f0e7f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -357,8 +357,8 @@ select_insn: ALU64_MOD_X: if (unlikely(SRC == 0)) return 0; - tmp = DST; - DST = do_div(tmp, SRC); + div64_u64_rem(DST, SRC, &tmp); + DST = tmp; CONT; ALU_MOD_X: if (unlikely(SRC == 0)) @@ -367,8 +367,8 @@ select_insn: DST = do_div(tmp, (u32) SRC); CONT; ALU64_MOD_K: - tmp = DST; - DST = do_div(tmp, IMM); + div64_u64_rem(DST, IMM, &tmp); + DST = tmp; CONT; ALU_MOD_K: tmp = (u32) DST; @@ -377,7 +377,7 @@ select_insn: ALU64_DIV_X: if (unlikely(SRC == 0)) return 0; - do_div(DST, SRC); + DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: if (unlikely(SRC == 0)) @@ -387,7 +387,7 @@ select_insn: DST = (u32) tmp; CONT; ALU64_DIV_K: - do_div(DST, IMM); + DST = div64_u64(DST, IMM); CONT; ALU_DIV_K: tmp = (u32) DST; diff --git a/kernel/kexec.c b/kernel/kexec.c index 38c25b1..7a36fdc 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -707,7 +707,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, do { unsigned long pfn, epfn, addr, eaddr; - pages = kimage_alloc_pages(GFP_KERNEL, order); + pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order); if (!pages) break; pfn = page_to_pfn(pages); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f9123a8..fe22f75 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1016,13 +1016,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) rq_clock_skip_update(rq, true); } -static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); - -void register_task_migration_notifier(struct notifier_block *n) -{ - atomic_notifier_chain_register(&task_migration_notifier, n); -} - #ifdef CONFIG_SMP void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { @@ -1053,18 +1046,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { - struct task_migration_notifier tmn; - if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); - - tmn.task = p; - tmn.from_cpu = task_cpu(p); - tmn.to_cpu = new_cpu; - - atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn); } __set_task_cpu(p, new_cpu); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index deef1ca..fefcb1f 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -81,7 +81,6 @@ static void cpuidle_idle_call(void) struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; - unsigned int broadcast; bool reflect; /* @@ -150,17 +149,6 @@ static void cpuidle_idle_call(void) goto exit_idle; } - broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP; - - /* - * Tell the time framework to switch to a broadcast timer - * because our local timer will be shutdown. If a local timer - * is used from another cpu as a broadcast timer, this call may - * fail if it is not available - */ - if (broadcast && tick_broadcast_enter()) - goto use_default; - /* Take note of the planned idle state. */ idle_set_state(this_rq(), &drv->states[next_state]); @@ -174,8 +162,8 @@ static void cpuidle_idle_call(void) /* The cpu is no longer idle or about to enter idle. */ idle_set_state(this_rq(), NULL); - if (broadcast) - tick_broadcast_exit(); + if (entered_state == -EBUSY) + goto use_default; /* * Give the governor an opportunity to reflect on the outcome diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 4898442..b28df40 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -405,13 +405,18 @@ int rhashtable_insert_rehash(struct rhashtable *ht) if (rht_grow_above_75(ht, tbl)) size *= 2; - /* More than two rehashes (not resizes) detected. */ - else if (WARN_ON(old_tbl != tbl && old_tbl->size == size)) + /* Do not schedule more than one rehash */ + else if (old_tbl != tbl) return -EBUSY; new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC); - if (new_tbl == NULL) + if (new_tbl == NULL) { + /* Schedule async resize/rehash to try allocation + * non-atomic context. + */ + schedule_work(&ht->run_work); return -ENOMEM; + } err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 4096089..e29ad70 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -170,7 +170,7 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb, struct br_port_msg *bpm; struct nlattr *nest, *nest2; - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 0e4ddb8..4b5c236 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -394,7 +394,7 @@ errout: * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u32 filter_mask) + struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); @@ -402,7 +402,7 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; - return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI, + return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 6ca0251..3362c29 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -828,7 +828,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port); int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask); + u32 filter_mask, int nlflags); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ diff --git a/net/core/dev.c b/net/core/dev.c index 1796cef5..c7ba038 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3079,7 +3079,7 @@ static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { - if (next_cpu != RPS_NO_CPU) { + if (next_cpu < nr_cpu_ids) { #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; @@ -3184,7 +3184,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * If the desired CPU (where last recvmsg was done) is * different from current CPU (one in the rx-queue flow * table entry), switch if one of the following holds: - * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is unset (>= nr_cpu_ids). * - Current CPU is offline. * - The current CPU's queue tail has advanced beyond the * last packet that was enqueued using this table entry. @@ -3192,14 +3192,14 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * have been dequeued, thus preserving in order delivery. */ if (unlikely(tcpu != next_cpu) && - (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } - if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; goto done; @@ -3240,14 +3240,14 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, struct rps_dev_flow_table *flow_table; struct rps_dev_flow *rflow; bool expire = true; - int cpu; + unsigned int cpu; rcu_read_lock(); flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; cpu = ACCESS_ONCE(rflow->cpu); - if (rflow->filter == filter_id && cpu != RPS_NO_CPU && + if (rflow->filter == filter_id && cpu < nr_cpu_ids && ((int)(per_cpu(softnet_data, cpu).input_queue_head - rflow->last_qtail) < (int)(10 * flow_table->mask))) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 358d52a..666e092 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2854,7 +2854,7 @@ static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask, int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode, - u32 flags, u32 mask) + u32 flags, u32 mask, int nlflags) { struct nlmsghdr *nlh; struct ifinfomsg *ifm; @@ -2863,7 +2863,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct net_device *br_dev = netdev_master_upper_dev_get(dev); - nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), nlflags); if (nlh == NULL) return -EMSGSIZE; @@ -2969,7 +2969,8 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && br_dev->netdev_ops->ndo_bridge_getlink( - skb, portid, seq, dev, filter_mask) < 0) + skb, portid, seq, dev, filter_mask, + NLM_F_MULTI) < 0) break; idx++; } @@ -2977,7 +2978,8 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) if (ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && ops->ndo_bridge_getlink(skb, portid, seq, dev, - filter_mask) < 0) + filter_mask, + NLM_F_MULTI) < 0) break; idx++; } @@ -3018,7 +3020,7 @@ static int rtnl_bridge_notify(struct net_device *dev) goto errout; } - err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0, 0); if (err < 0) goto errout; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d1967da..3cfff2a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -280,13 +280,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -311,7 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -328,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } + +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb = __build_skb(data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; + } + return skb; +} EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { @@ -348,7 +365,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc, gfp_t gfp = gfp_mask; if (order) { - gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; + gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC; page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); nc->frag.size = PAGE_SIZE << (page ? order : 0); } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 2b4f21d..ccf4c56 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -453,7 +453,8 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) iph->saddr, iph->daddr); if (req) { nsk = dccp_check_req(sk, skb, req); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9d05510..5165571 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -301,7 +301,8 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) &iph->daddr, inet6_iif(skb)); if (req) { nsk = dccp_check_req(sk, skb, req); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo, diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 5f56666..30addee 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -186,8 +186,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, if (child == NULL) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req); - inet_csk_reqsk_queue_removed(sk, req); + inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); out: return child; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 079a224..e6f6cc3 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -633,7 +633,7 @@ static int dsa_of_probe(struct device *dev) if (cd->sw_addr > PHY_MAX_ADDR) continue; - if (!of_property_read_u32(np, "eeprom-length", &eeprom_len)) + if (!of_property_read_u32(child, "eeprom-length", &eeprom_len)) cd->eeprom_len = eeprom_len; for_each_available_child_of_node(child, port) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5c3dd62..8976ca4 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -564,6 +564,40 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); +/* return true if req was found in the syn_table[] */ +static bool reqsk_queue_unlink(struct request_sock_queue *queue, + struct request_sock *req) +{ + struct listen_sock *lopt = queue->listen_opt; + struct request_sock **prev; + bool found = false; + + spin_lock(&queue->syn_wait_lock); + + for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL; + prev = &(*prev)->dl_next) { + if (*prev == req) { + *prev = req->dl_next; + found = true; + break; + } + } + + spin_unlock(&queue->syn_wait_lock); + if (del_timer(&req->rsk_timer)) + reqsk_put(req); + return found; +} + +void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +{ + if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) { + reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); + reqsk_put(req); + } +} +EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); + static void reqsk_timer_handler(unsigned long data) { struct request_sock *req = (struct request_sock *)data; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index a93f260..05ff44b 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk) if (sk_hashed(sk)) { write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); + sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a78540f..bff62fc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -962,10 +962,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (dst_metric_locked(dst, RTAX_MTU)) return; - if (dst->dev->mtu < mtu) - return; - - if (rt->rt_pmtu && rt->rt_pmtu < mtu) + if (ipv4_mtu(dst) < mtu) return; if (mtu < ip_rt_min_pmtu) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3571f2b..fc1c658 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1348,7 +1348,8 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr); if (req) { nsk = tcp_check_req(sk, skb, req, false); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 63d6311..e5d7649 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -755,10 +755,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req); - inet_csk_reqsk_queue_removed(sk, req); - + inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); + /* Warning: caller must not call reqsk_put(req); + * child stole last reference on it. + */ return child; listen_overflow: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8c8d7e0..a369e8a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2812,39 +2812,65 @@ begin_fwd: } } -/* Send a fin. The caller locks the socket for us. This cannot be - * allowed to fail queueing a FIN frame under any circumstances. +/* We allow to exceed memory limits for FIN packets to expedite + * connection tear down and (memory) recovery. + * Otherwise tcp_send_fin() could be tempted to either delay FIN + * or even be forced to close flow without any FIN. + */ +static void sk_forced_wmem_schedule(struct sock *sk, int size) +{ + int amt, status; + + if (size <= sk->sk_forward_alloc) + return; + amt = sk_mem_pages(size); + sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; + sk_memory_allocated_add(sk, amt, &status); +} + +/* Send a FIN. The caller locks the socket for us. + * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { + struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = tcp_write_queue_tail(sk); - int mss_now; - /* Optimization, tack on the FIN if we have a queue of - * unsent frames. But be careful about outgoing SACKS - * and IP options. + /* Optimization, tack on the FIN if we have one skb in write queue and + * this skb was not yet sent, or we are under memory pressure. + * Note: in the latter case, FIN packet will be sent after a timeout, + * as TCP stack thinks it has already been transmitted. */ - mss_now = tcp_current_mss(sk); - - if (tcp_send_head(sk)) { - TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; - TCP_SKB_CB(skb)->end_seq++; + if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) { +coalesce: + TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; + TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; + if (!tcp_send_head(sk)) { + /* This means tskb was already sent. + * Pretend we included the FIN on previous transmit. + * We need to set tp->snd_nxt to the value it would have + * if FIN had been sent. This is because retransmit path + * does not change tp->snd_nxt. + */ + tp->snd_nxt++; + return; + } } else { - /* Socket is locked, keep trying until memory is available. */ - for (;;) { - skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); - if (skb) - break; - yield(); + skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + if (unlikely(!skb)) { + if (tskb) + goto coalesce; + return; } + skb_reserve(skb, MAX_TCP_HEADER); + sk_forced_wmem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } - __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); + __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index b5e6cc1..a38d3ac 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1246,7 +1246,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev) static int ip6gre_tunnel_init(struct net_device *dev) { struct ip6_tnl *tunnel; - int i; tunnel = netdev_priv(dev); @@ -1260,16 +1259,10 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (ipv6_addr_any(&tunnel->parms.raddr)) dev->header_ops = &ip6gre_header_ops; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6gre_tunnel_stats; - ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6gre_tunnel_stats->syncp); - } - return 0; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ad51df8..b6575d6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -946,7 +946,8 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); if (req) { nsk = tcp_check_req(sk, skb, req, false); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index db8a2ea..954810c 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -53,6 +53,11 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) return rt; } +static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->mpls_ptr); +} + static bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); @@ -136,6 +141,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, struct mpls_route *rt; struct mpls_entry_decoded dec; struct net_device *out_dev; + struct mpls_dev *mdev; unsigned int hh_len; unsigned int new_header_size; unsigned int mtu; @@ -143,6 +149,10 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, /* Careful this entire function runs inside of an rcu critical section */ + mdev = mpls_dev_get(dev); + if (!mdev || !mdev->input_enabled) + goto drop; + if (skb->pkt_type != PACKET_HOST) goto drop; @@ -352,9 +362,9 @@ static int mpls_route_add(struct mpls_route_config *cfg) if (!dev) goto errout; - /* For now just support ethernet devices */ + /* Ensure this is a supported device */ err = -EINVAL; - if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) + if (!mpls_dev_get(dev)) goto errout; err = -EINVAL; @@ -428,10 +438,89 @@ errout: return err; } +#define MPLS_PERDEV_SYSCTL_OFFSET(field) \ + (&((struct mpls_dev *)0)->field) + +static const struct ctl_table mpls_dev_table[] = { + { + .procname = "input", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled), + }, + { } +}; + +static int mpls_dev_sysctl_register(struct net_device *dev, + struct mpls_dev *mdev) +{ + char path[sizeof("net/mpls/conf/") + IFNAMSIZ]; + struct ctl_table *table; + int i; + + table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL); + if (!table) + goto out; + + /* Table data contains only offsets relative to the base of + * the mdev at this point, so make them absolute. + */ + for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++) + table[i].data = (char *)mdev + (uintptr_t)table[i].data; + + snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); + + mdev->sysctl = register_net_sysctl(dev_net(dev), path, table); + if (!mdev->sysctl) + goto free; + + return 0; + +free: + kfree(table); +out: + return -ENOBUFS; +} + +static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev) +{ + struct ctl_table *table; + + table = mdev->sysctl->ctl_table_arg; + unregister_net_sysctl_table(mdev->sysctl); + kfree(table); +} + +static struct mpls_dev *mpls_add_dev(struct net_device *dev) +{ + struct mpls_dev *mdev; + int err = -ENOMEM; + + ASSERT_RTNL(); + + mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); + if (!mdev) + return ERR_PTR(err); + + err = mpls_dev_sysctl_register(dev, mdev); + if (err) + goto free; + + rcu_assign_pointer(dev->mpls_ptr, mdev); + + return mdev; + +free: + kfree(mdev); + return ERR_PTR(err); +} + static void mpls_ifdown(struct net_device *dev) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); + struct mpls_dev *mdev; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); @@ -443,14 +532,35 @@ static void mpls_ifdown(struct net_device *dev) continue; rt->rt_dev = NULL; } + + mdev = mpls_dev_get(dev); + if (!mdev) + return; + + mpls_dev_sysctl_unregister(mdev); + + RCU_INIT_POINTER(dev->mpls_ptr, NULL); + + kfree(mdev); } static int mpls_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct mpls_dev *mdev; switch(event) { + case NETDEV_REGISTER: + /* For now just support ethernet devices */ + if ((dev->type == ARPHRD_ETHER) || + (dev->type == ARPHRD_LOOPBACK)) { + mdev = mpls_add_dev(dev); + if (IS_ERR(mdev)) + return notifier_from_errno(PTR_ERR(mdev)); + } + break; + case NETDEV_UNREGISTER: mpls_ifdown(dev); break; @@ -536,6 +646,15 @@ int nla_get_labels(const struct nlattr *nla, if ((dec.bos != bos) || dec.ttl || dec.tc) return -EINVAL; + switch (dec.label) { + case LABEL_IMPLICIT_NULL: + /* RFC3032: This is a label that an LSR may + * assign and distribute, but which never + * actually appears in the encapsulation. + */ + return -EINVAL; + } + label[i] = dec.label; } *labels = nla_labels; @@ -912,7 +1031,7 @@ static int mpls_platform_labels(struct ctl_table *table, int write, return ret; } -static struct ctl_table mpls_table[] = { +static const struct ctl_table mpls_table[] = { { .procname = "platform_labels", .data = NULL, diff --git a/net/mpls/internal.h b/net/mpls/internal.h index fb6de920..693877d 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -22,6 +22,12 @@ struct mpls_entry_decoded { u8 bos; }; +struct mpls_dev { + int input_enabled; + + struct ctl_table_header *sysctl; +}; + struct sk_buff; static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 78af83b..ad9d11f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4340,7 +4340,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: - desc->len = sizeof(data->verdict); break; case NFT_JUMP: case NFT_GOTO: @@ -4355,10 +4354,10 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, chain->use++; data->verdict.chain = chain; - desc->len = sizeof(data); break; } + desc->len = sizeof(data->verdict); desc->type = NFT_DATA_VERDICT; return 0; } diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 57d3e1a..0522fc9 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -63,6 +63,8 @@ int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; + default: + break; } return 0; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 62cabee..635dbba 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -108,6 +108,8 @@ static int nft_reject_inet_dump(struct sk_buff *skb, if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; + default: + break; } return 0; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 19909d0..ec4adbd 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1629,13 +1629,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, if (data == NULL) return NULL; - skb = build_skb(data, size); + skb = __build_skb(data, size); if (skb == NULL) vfree(data); - else { - skb->head_frag = 0; + else skb->destructor = netlink_skb_destructor; - } return skb; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 8e47251..295d14b 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -63,7 +63,6 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, skb->mark = c->mark; /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; - nf_ct_put(c); goto out; } @@ -82,7 +81,6 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, nf_ct_put(c); out: - skb->nfct = NULL; spin_unlock(&ca->tcf_lock); return ca->tcf_action; } diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 3613e72..70e3dac 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -591,14 +591,14 @@ void tipc_bearer_stop(struct net *net) /* Caller should hold rtnl_lock to protect the bearer */ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, - struct tipc_bearer *bearer) + struct tipc_bearer *bearer, int nlflags) { void *hdr; struct nlattr *attrs; struct nlattr *prop; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, - NLM_F_MULTI, TIPC_NL_BEARER_GET); + nlflags, TIPC_NL_BEARER_GET); if (!hdr) return -EMSGSIZE; @@ -657,7 +657,7 @@ int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!bearer) continue; - err = __tipc_nl_add_bearer(&msg, bearer); + err = __tipc_nl_add_bearer(&msg, bearer, NLM_F_MULTI); if (err) break; } @@ -705,7 +705,7 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) goto err_out; } - err = __tipc_nl_add_bearer(&msg, bearer); + err = __tipc_nl_add_bearer(&msg, bearer, 0); if (err) goto err_out; rtnl_unlock(); @@ -857,14 +857,14 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) } static int __tipc_nl_add_media(struct tipc_nl_msg *msg, - struct tipc_media *media) + struct tipc_media *media, int nlflags) { void *hdr; struct nlattr *attrs; struct nlattr *prop; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, - NLM_F_MULTI, TIPC_NL_MEDIA_GET); + nlflags, TIPC_NL_MEDIA_GET); if (!hdr) return -EMSGSIZE; @@ -916,7 +916,8 @@ int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); for (; media_info_array[i] != NULL; i++) { - err = __tipc_nl_add_media(&msg, media_info_array[i]); + err = __tipc_nl_add_media(&msg, media_info_array[i], + NLM_F_MULTI); if (err) break; } @@ -963,7 +964,7 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) goto err_out; } - err = __tipc_nl_add_media(&msg, media); + err = __tipc_nl_add_media(&msg, media, 0); if (err) goto err_out; rtnl_unlock(); diff --git a/net/tipc/link.c b/net/tipc/link.c index a6b30df..43a515d 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1145,11 +1145,8 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) } /* Synchronize with parallel link if applicable */ if (unlikely((l_ptr->flags & LINK_SYNCHING) && !msg_dup(msg))) { - link_handle_out_of_seq_msg(l_ptr, skb); - if (link_synch(l_ptr)) - link_retrieve_defq(l_ptr, &head); - skb = NULL; - goto unlock; + if (!link_synch(l_ptr)) + goto unlock; } l_ptr->next_in_no++; if (unlikely(!skb_queue_empty(&l_ptr->deferdq))) @@ -2013,7 +2010,7 @@ msg_full: /* Caller should hold appropriate locks to protect the link */ static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, - struct tipc_link *link) + struct tipc_link *link, int nlflags) { int err; void *hdr; @@ -2022,7 +2019,7 @@ static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, struct tipc_net *tn = net_generic(net, tipc_net_id); hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, - NLM_F_MULTI, TIPC_NL_LINK_GET); + nlflags, TIPC_NL_LINK_GET); if (!hdr) return -EMSGSIZE; @@ -2095,7 +2092,7 @@ static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg, if (!node->links[i]) continue; - err = __tipc_nl_add_link(net, msg, node->links[i]); + err = __tipc_nl_add_link(net, msg, node->links[i], NLM_F_MULTI); if (err) return err; } @@ -2143,7 +2140,6 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) err = __tipc_nl_add_node_links(net, &msg, node, &prev_link); tipc_node_unlock(node); - tipc_node_put(node); if (err) goto out; @@ -2210,7 +2206,7 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) goto err_out; } - err = __tipc_nl_add_link(net, &msg, link); + err = __tipc_nl_add_link(net, &msg, link, 0); if (err) goto err_out; diff --git a/net/tipc/server.c b/net/tipc/server.c index ab6183c..77ff03e 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -102,7 +102,7 @@ static void tipc_conn_kref_release(struct kref *kref) } saddr->scope = -TIPC_NODE_SCOPE; kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); - sk_release_kernel(sk); + sock_release(sock); con->sock = NULL; } @@ -321,12 +321,9 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) struct socket *sock = NULL; int ret; - ret = sock_create_kern(AF_TIPC, SOCK_SEQPACKET, 0, &sock); + ret = __sock_create(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock, 1); if (ret < 0) return NULL; - - sk_change_net(sock->sk, s->net); - ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE, (char *)&s->imp, sizeof(s->imp)); if (ret < 0) @@ -376,7 +373,7 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) create_err: kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sock->sk); + sock_release(sock); return NULL; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ee90d74..9074b5c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1764,13 +1764,14 @@ static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) { u32 dnode, dport = 0; - int err = -TIPC_ERR_NO_PORT; + int err; struct sk_buff *skb; struct tipc_sock *tsk; struct tipc_net *tn; struct sock *sk; while (skb_queue_len(inputq)) { + err = -TIPC_ERR_NO_PORT; skb = NULL; dport = tipc_skb_peek_port(inputq, dport); tsk = tipc_sk_lookup(net, dport); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 99f7012..a73a226 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -95,39 +95,36 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); unsigned int unix_tot_inflight; - struct sock *unix_get_socket(struct file *filp) { struct sock *u_sock = NULL; struct inode *inode = file_inode(filp); - /* - * Socket ? - */ + /* Socket ? */ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { struct socket *sock = SOCKET_I(inode); struct sock *s = sock->sk; - /* - * PF_UNIX ? - */ + /* PF_UNIX ? */ if (s && sock->ops && sock->ops->family == PF_UNIX) u_sock = s; } return u_sock; } -/* - * Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. +/* Keep the number of times in flight count for the file + * descriptor if it is for an AF_UNIX socket. */ void unix_inflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + if (s) { struct unix_sock *u = unix_sk(s); + spin_lock(&unix_gc_lock); + if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); @@ -142,10 +139,13 @@ void unix_inflight(struct file *fp) void unix_notinflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + if (s) { struct unix_sock *u = unix_sk(s); + spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); + if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; @@ -161,32 +161,27 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), spin_lock(&x->sk_receive_queue.lock); skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - /* - * Do we have file descriptors ? - */ + /* Do we have file descriptors ? */ if (UNIXCB(skb).fp) { bool hit = false; - /* - * Process the descriptors of this socket - */ + /* Process the descriptors of this socket */ int nfd = UNIXCB(skb).fp->count; struct file **fp = UNIXCB(skb).fp->fp; + while (nfd--) { - /* - * Get the socket the fd matches - * if it indeed does so - */ + /* Get the socket the fd matches if it indeed does so */ struct sock *sk = unix_get_socket(*fp++); + if (sk) { struct unix_sock *u = unix_sk(sk); - /* - * Ignore non-candidates, they could + /* Ignore non-candidates, they could * have been added to the queues after * starting the garbage collection */ if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { hit = true; + func(u); } } @@ -203,24 +198,22 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), static void scan_children(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { - if (x->sk_state != TCP_LISTEN) + if (x->sk_state != TCP_LISTEN) { scan_inflight(x, func, hitlist); - else { + } else { struct sk_buff *skb; struct sk_buff *next; struct unix_sock *u; LIST_HEAD(embryos); - /* - * For a listening socket collect the queued embryos + /* For a listening socket collect the queued embryos * and perform a scan on them as well. */ spin_lock(&x->sk_receive_queue.lock); skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { u = unix_sk(skb->sk); - /* - * An embryo cannot be in-flight, so it's safe + /* An embryo cannot be in-flight, so it's safe * to use the list link. */ BUG_ON(!list_empty(&u->link)); @@ -249,8 +242,7 @@ static void inc_inflight(struct unix_sock *usk) static void inc_inflight_move_tail(struct unix_sock *u) { atomic_long_inc(&u->inflight); - /* - * If this still might be part of a cycle, move it to the end + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over */ @@ -263,8 +255,7 @@ static bool gc_in_progress; void wait_for_unix_gc(void) { - /* - * If number of inflight sockets is insane, + /* If number of inflight sockets is insane, * force a garbage collect right now. */ if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress) @@ -288,8 +279,7 @@ void unix_gc(void) goto out; gc_in_progress = true; - /* - * First, select candidates for garbage collection. Only + /* First, select candidates for garbage collection. Only * in-flight sockets are considered, and from those only ones * which don't have any external reference. * @@ -320,15 +310,13 @@ void unix_gc(void) } } - /* - * Now remove all internal in-flight reference to children of + /* Now remove all internal in-flight reference to children of * the candidates. */ list_for_each_entry(u, &gc_candidates, link) scan_children(&u->sk, dec_inflight, NULL); - /* - * Restore the references for children of all candidates, + /* Restore the references for children of all candidates, * which have remaining references. Do this recursively, so * only those remain, which form cyclic references. * @@ -350,8 +338,7 @@ void unix_gc(void) } list_del(&cursor); - /* - * not_cycle_list contains those sockets which do not make up a + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ while (!list_empty(¬_cycle_list)) { @@ -360,8 +347,7 @@ void unix_gc(void) list_move_tail(&u->link, &gc_inflight_list); } - /* - * Now gc_candidates contains only garbage. Restore original + /* Now gc_candidates contains only garbage. Restore original * inflight counters for these as well, and remove the skbuffs * which are creating the cycle(s). */ diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c index 37d0220..db7a2e5 100644 --- a/sound/pci/emu10k1/emu10k1.c +++ b/sound/pci/emu10k1/emu10k1.c @@ -183,8 +183,10 @@ static int snd_card_emu10k1_probe(struct pci_dev *pci, } #endif - strcpy(card->driver, emu->card_capabilities->driver); - strcpy(card->shortname, emu->card_capabilities->name); + strlcpy(card->driver, emu->card_capabilities->driver, + sizeof(card->driver)); + strlcpy(card->shortname, emu->card_capabilities->name, + sizeof(card->shortname)); snprintf(card->longname, sizeof(card->longname), "%s (rev.%d, serial:0x%x) at 0x%lx, irq %i", card->shortname, emu->revision, emu->serial, emu->port, emu->irq); diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c index 874cd76..d2c7ea3 100644 --- a/sound/pci/emu10k1/emu10k1_callback.c +++ b/sound/pci/emu10k1/emu10k1_callback.c @@ -415,7 +415,7 @@ start_voice(struct snd_emux_voice *vp) snd_emu10k1_ptr_write(hw, Z2, ch, 0); /* invalidate maps */ - temp = (hw->silent_page.addr << 1) | MAP_PTI_MASK; + temp = (hw->silent_page.addr << hw->address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); snd_emu10k1_ptr_write(hw, MAPA, ch, temp); snd_emu10k1_ptr_write(hw, MAPB, ch, temp); #if 0 @@ -436,7 +436,7 @@ start_voice(struct snd_emux_voice *vp) snd_emu10k1_ptr_write(hw, CDF, ch, sample); /* invalidate maps */ - temp = ((unsigned int)hw->silent_page.addr << 1) | MAP_PTI_MASK; + temp = ((unsigned int)hw->silent_page.addr << hw_address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); snd_emu10k1_ptr_write(hw, MAPA, ch, temp); snd_emu10k1_ptr_write(hw, MAPB, ch, temp); diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index 54079f5..a454814 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -282,7 +282,7 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir, int resume) snd_emu10k1_ptr_write(emu, TCB, 0, 0); /* taken from original driver */ snd_emu10k1_ptr_write(emu, TCBS, 0, 4); /* taken from original driver */ - silent_page = (emu->silent_page.addr << 1) | MAP_PTI_MASK; + silent_page = (emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); for (ch = 0; ch < NUM_G; ch++) { snd_emu10k1_ptr_write(emu, MAPA, ch, silent_page); snd_emu10k1_ptr_write(emu, MAPB, ch, silent_page); @@ -348,6 +348,11 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir, int resume) outl(reg | A_IOCFG_GPOUT0, emu->port + A_IOCFG); } + if (emu->address_mode == 0) { + /* use 16M in 4G */ + outl(inl(emu->port + HCFG) | HCFG_EXPANDED_MEM, emu->port + HCFG); + } + return 0; } @@ -1446,7 +1451,7 @@ static struct snd_emu_chip_details emu_chip_details[] = { * */ {.vendor = 0x1102, .device = 0x0008, .subsystem = 0x20011102, - .driver = "Audigy2", .name = "SB Audigy 2 ZS Notebook [SB0530]", + .driver = "Audigy2", .name = "Audigy 2 ZS Notebook [SB0530]", .id = "Audigy2", .emu10k2_chip = 1, .ca0108_chip = 1, @@ -1596,7 +1601,7 @@ static struct snd_emu_chip_details emu_chip_details[] = { .adc_1361t = 1, /* 24 bit capture instead of 16bit */ .ac97_chip = 1} , {.vendor = 0x1102, .device = 0x0004, .subsystem = 0x10051102, - .driver = "Audigy2", .name = "SB Audigy 2 Platinum EX [SB0280]", + .driver = "Audigy2", .name = "Audigy 2 Platinum EX [SB0280]", .id = "Audigy2", .emu10k2_chip = 1, .ca0102_chip = 1, @@ -1902,8 +1907,10 @@ int snd_emu10k1_create(struct snd_card *card, is_audigy = emu->audigy = c->emu10k2_chip; + /* set addressing mode */ + emu->address_mode = is_audigy ? 0 : 1; /* set the DMA transfer mask */ - emu->dma_mask = is_audigy ? AUDIGY_DMA_MASK : EMU10K1_DMA_MASK; + emu->dma_mask = emu->address_mode ? EMU10K1_DMA_MASK : AUDIGY_DMA_MASK; if (pci_set_dma_mask(pci, emu->dma_mask) < 0 || pci_set_consistent_dma_mask(pci, emu->dma_mask) < 0) { dev_err(card->dev, @@ -1928,7 +1935,7 @@ int snd_emu10k1_create(struct snd_card *card, emu->max_cache_pages = max_cache_bytes >> PAGE_SHIFT; if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci), - 32 * 1024, &emu->ptb_pages) < 0) { + (emu->address_mode ? 32 : 16) * 1024, &emu->ptb_pages) < 0) { err = -ENOMEM; goto error; } @@ -2027,8 +2034,8 @@ int snd_emu10k1_create(struct snd_card *card, /* Clear silent pages and set up pointers */ memset(emu->silent_page.area, 0, PAGE_SIZE); - silent_page = emu->silent_page.addr << 1; - for (idx = 0; idx < MAXPAGES; idx++) + silent_page = emu->silent_page.addr << emu->address_mode; + for (idx = 0; idx < (emu->address_mode ? MAXPAGES1 : MAXPAGES0); idx++) ((u32 *)emu->ptb_pages.area)[idx] = cpu_to_le32(silent_page | idx); /* set up voice indices */ diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 0dc0738..14a305b 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -380,7 +380,7 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu, snd_emu10k1_ptr_write(emu, Z1, voice, 0); snd_emu10k1_ptr_write(emu, Z2, voice, 0); /* invalidate maps */ - silent_page = ((unsigned int)emu->silent_page.addr << 1) | MAP_PTI_MASK; + silent_page = ((unsigned int)emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); snd_emu10k1_ptr_write(emu, MAPA, voice, silent_page); snd_emu10k1_ptr_write(emu, MAPB, voice, silent_page); /* modulation envelope */ diff --git a/sound/pci/emu10k1/memory.c b/sound/pci/emu10k1/memory.c index c68e6dd..4f1f69b 100644 --- a/sound/pci/emu10k1/memory.c +++ b/sound/pci/emu10k1/memory.c @@ -34,10 +34,11 @@ * aligned pages in others */ #define __set_ptb_entry(emu,page,addr) \ - (((u32 *)(emu)->ptb_pages.area)[page] = cpu_to_le32(((addr) << 1) | (page))) + (((u32 *)(emu)->ptb_pages.area)[page] = cpu_to_le32(((addr) << (emu->address_mode)) | (page))) #define UNIT_PAGES (PAGE_SIZE / EMUPAGESIZE) -#define MAX_ALIGN_PAGES (MAXPAGES / UNIT_PAGES) +#define MAX_ALIGN_PAGES0 (MAXPAGES0 / UNIT_PAGES) +#define MAX_ALIGN_PAGES1 (MAXPAGES1 / UNIT_PAGES) /* get aligned page from offset address */ #define get_aligned_page(offset) ((offset) >> PAGE_SHIFT) /* get offset address from aligned page */ @@ -124,7 +125,7 @@ static int search_empty_map_area(struct snd_emu10k1 *emu, int npages, struct lis } page = blk->mapped_page + blk->pages; } - size = MAX_ALIGN_PAGES - page; + size = (emu->address_mode ? MAX_ALIGN_PAGES1 : MAX_ALIGN_PAGES0) - page; if (size >= max_size) { *nextp = pos; return page; @@ -181,7 +182,7 @@ static int unmap_memblk(struct snd_emu10k1 *emu, struct snd_emu10k1_memblk *blk) q = get_emu10k1_memblk(p, mapped_link); end_page = q->mapped_page; } else - end_page = MAX_ALIGN_PAGES; + end_page = (emu->address_mode ? MAX_ALIGN_PAGES1 : MAX_ALIGN_PAGES0); /* remove links */ list_del(&blk->mapped_link); @@ -307,7 +308,7 @@ snd_emu10k1_alloc_pages(struct snd_emu10k1 *emu, struct snd_pcm_substream *subst if (snd_BUG_ON(!emu)) return NULL; if (snd_BUG_ON(runtime->dma_bytes <= 0 || - runtime->dma_bytes >= MAXPAGES * EMUPAGESIZE)) + runtime->dma_bytes >= (emu->address_mode ? MAXPAGES1 : MAXPAGES0) * EMUPAGESIZE)) return NULL; hdr = emu->memhdr; if (snd_BUG_ON(!hdr)) diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 873ed1b..b49feff 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -873,14 +873,15 @@ struct hda_pcm *snd_hda_codec_pcm_new(struct hda_codec *codec, struct hda_pcm *pcm; va_list args; - va_start(args, fmt); pcm = kzalloc(sizeof(*pcm), GFP_KERNEL); if (!pcm) return NULL; pcm->codec = codec; kref_init(&pcm->kref); + va_start(args, fmt); pcm->name = kvasprintf(GFP_KERNEL, fmt, args); + va_end(args); if (!pcm->name) { kfree(pcm); return NULL; @@ -2082,6 +2083,16 @@ static struct snd_kcontrol_new vmaster_mute_mode = { .put = vmaster_mute_mode_put, }; +/* meta hook to call each driver's vmaster hook */ +static void vmaster_hook(void *private_data, int enabled) +{ + struct hda_vmaster_mute_hook *hook = private_data; + + if (hook->mute_mode != HDA_VMUTE_FOLLOW_MASTER) + enabled = hook->mute_mode; + hook->hook(hook->codec, enabled); +} + /** * snd_hda_add_vmaster_hook - Add a vmaster hook for mute-LED * @codec: the HDA codec @@ -2100,9 +2111,9 @@ int snd_hda_add_vmaster_hook(struct hda_codec *codec, if (!hook->hook || !hook->sw_kctl) return 0; - snd_ctl_add_vmaster_hook(hook->sw_kctl, hook->hook, codec); hook->codec = codec; hook->mute_mode = HDA_VMUTE_FOLLOW_MASTER; + snd_ctl_add_vmaster_hook(hook->sw_kctl, vmaster_hook, hook); if (!expose_enum_ctl) return 0; kctl = snd_ctl_new1(&vmaster_mute_mode, hook); @@ -2128,14 +2139,7 @@ void snd_hda_sync_vmaster_hook(struct hda_vmaster_mute_hook *hook) */ if (hook->codec->bus->shutdown) return; - switch (hook->mute_mode) { - case HDA_VMUTE_FOLLOW_MASTER: - snd_ctl_sync_vmaster_hook(hook->sw_kctl); - break; - default: - hook->hook(hook->codec, hook->mute_mode); - break; - } + snd_ctl_sync_vmaster_hook(hook->sw_kctl); } EXPORT_SYMBOL_GPL(snd_hda_sync_vmaster_hook); diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 3d2597b..788f969 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3259,7 +3259,8 @@ static int create_input_ctls(struct hda_codec *codec) val = PIN_IN; if (cfg->inputs[i].type == AUTO_PIN_MIC) val |= snd_hda_get_default_vref(codec, pin); - if (pin != spec->hp_mic_pin) + if (pin != spec->hp_mic_pin && + !snd_hda_codec_get_pin_target(codec, pin)) set_pin_target(codec, pin, val, false); if (mixer) { diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 06199e4..e2afd53 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4190,11 +4190,18 @@ static void alc_shutup_dell_xps13(struct hda_codec *codec) static void alc_fixup_dell_xps13(struct hda_codec *codec, const struct hda_fixup *fix, int action) { - if (action == HDA_FIXUP_ACT_PROBE) { - struct alc_spec *spec = codec->spec; - struct hda_input_mux *imux = &spec->gen.input_mux; - int i; + struct alc_spec *spec = codec->spec; + struct hda_input_mux *imux = &spec->gen.input_mux; + int i; + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + /* mic pin 0x19 must be initialized with Vref Hi-Z, otherwise + * it causes a click noise at start up + */ + snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ); + break; + case HDA_FIXUP_ACT_PROBE: spec->shutup = alc_shutup_dell_xps13; /* Make the internal mic the default input source. */ @@ -4204,6 +4211,7 @@ static void alc_fixup_dell_xps13(struct hda_codec *codec, break; } } + break; } } diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c index 0a4ad5f..d51703e 100644 --- a/sound/pci/hda/thinkpad_helper.c +++ b/sound/pci/hda/thinkpad_helper.c @@ -72,6 +72,7 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec, if (led_set_func(TPACPI_LED_MUTE, false) >= 0) { old_vmaster_hook = spec->vmaster_mute.hook; spec->vmaster_mute.hook = update_tpacpi_mute_led; + spec->vmaster_mute_enum = 1; removefunc = false; } if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) { diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 69528ae..be4d741 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -18,6 +18,7 @@ #include <linux/platform_device.h> #include <linux/spi/spi.h> #include <linux/gpio.h> +#include <linux/acpi.h> #include <sound/core.h> #include <sound/pcm.h> #include <sound/pcm_params.h> @@ -2656,6 +2657,15 @@ static const struct i2c_device_id rt5645_i2c_id[] = { }; MODULE_DEVICE_TABLE(i2c, rt5645_i2c_id); +#ifdef CONFIG_ACPI +static struct acpi_device_id rt5645_acpi_match[] = { + { "10EC5645", 0 }, + { "10EC5650", 0 }, + {}, +}; +MODULE_DEVICE_TABLE(acpi, rt5645_acpi_match); +#endif + static int rt5645_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { @@ -2770,7 +2780,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c, case RT5645_DMIC_DATA_GPIO12: regmap_update_bits(rt5645->regmap, RT5645_DMIC_CTRL1, - RT5645_DMIC_1_DP_MASK, RT5645_DMIC_2_DP_GPIO12); + RT5645_DMIC_2_DP_MASK, RT5645_DMIC_2_DP_GPIO12); regmap_update_bits(rt5645->regmap, RT5645_GPIO_CTRL1, RT5645_GP12_PIN_MASK, RT5645_GP12_PIN_DMIC2_SDA); @@ -2872,6 +2882,7 @@ static struct i2c_driver rt5645_i2c_driver = { .driver = { .name = "rt5645", .owner = THIS_MODULE, + .acpi_match_table = ACPI_PTR(rt5645_acpi_match), }, .probe = rt5645_i2c_probe, .remove = rt5645_i2c_remove, diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c index af18258..169aa47 100644 --- a/sound/soc/codecs/rt5677.c +++ b/sound/soc/codecs/rt5677.c @@ -62,6 +62,9 @@ static const struct reg_default init_list[] = { {RT5677_PR_BASE + 0x1e, 0x0000}, {RT5677_PR_BASE + 0x12, 0x0eaa}, {RT5677_PR_BASE + 0x14, 0x018a}, + {RT5677_PR_BASE + 0x15, 0x0490}, + {RT5677_PR_BASE + 0x38, 0x0f71}, + {RT5677_PR_BASE + 0x39, 0x0f71}, }; #define RT5677_INIT_REG_LEN ARRAY_SIZE(init_list) @@ -914,7 +917,7 @@ static int set_dmic_clk(struct snd_soc_dapm_widget *w, { struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm); struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec); - int idx = rl6231_calc_dmic_clk(rt5677->sysclk); + int idx = rl6231_calc_dmic_clk(rt5677->lrck[RT5677_AIF1] << 8); if (idx < 0) dev_err(codec->dev, "Failed to set DMIC clock\n"); diff --git a/sound/soc/codecs/tfa9879.c b/sound/soc/codecs/tfa9879.c index 16f1b71..aab0af6 100644 --- a/sound/soc/codecs/tfa9879.c +++ b/sound/soc/codecs/tfa9879.c @@ -280,8 +280,8 @@ static int tfa9879_i2c_probe(struct i2c_client *i2c, int i; tfa9879 = devm_kzalloc(&i2c->dev, sizeof(*tfa9879), GFP_KERNEL); - if (IS_ERR(tfa9879)) - return PTR_ERR(tfa9879); + if (!tfa9879) + return -ENOMEM; i2c_set_clientdata(i2c, tfa9879); diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index e8bb8ee..0d48804 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -1357,7 +1357,7 @@ static int fsl_ssi_probe(struct platform_device *pdev) } ssi_private->irq = platform_get_irq(pdev, 0); - if (!ssi_private->irq) { + if (ssi_private->irq < 0) { dev_err(&pdev->dev, "no irq for node %s\n", pdev->name); return ssi_private->irq; } diff --git a/sound/soc/intel/Makefile b/sound/soc/intel/Makefile index cd9aee9..3853ec2 100644 --- a/sound/soc/intel/Makefile +++ b/sound/soc/intel/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_SND_SOC_INTEL_SST) += common/ # Platform Support obj-$(CONFIG_SND_SOC_INTEL_HASWELL) += haswell/ obj-$(CONFIG_SND_SOC_INTEL_BAYTRAIL) += baytrail/ -obj-$(CONFIG_SND_SOC_INTEL_BAYTRAIL) += atom/ +obj-$(CONFIG_SND_SST_MFLD_PLATFORM) += atom/ # Machine support obj-$(CONFIG_SND_SOC_INTEL_SST) += boards/ diff --git a/sound/soc/intel/baytrail/sst-baytrail-ipc.c b/sound/soc/intel/baytrail/sst-baytrail-ipc.c index 1efb33b..a839dbf 100644 --- a/sound/soc/intel/baytrail/sst-baytrail-ipc.c +++ b/sound/soc/intel/baytrail/sst-baytrail-ipc.c @@ -759,7 +759,6 @@ fw_err: dsp_new_err: sst_ipc_fini(ipc); ipc_init_err: - kfree(byt); return err; } diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.c b/sound/soc/intel/haswell/sst-haswell-ipc.c index 344a1e9..324eceb 100644 --- a/sound/soc/intel/haswell/sst-haswell-ipc.c +++ b/sound/soc/intel/haswell/sst-haswell-ipc.c @@ -2201,7 +2201,6 @@ dma_err: dsp_new_err: sst_ipc_fini(ipc); ipc_init_err: - kfree(hsw); return ret; } EXPORT_SYMBOL_GPL(sst_hsw_dsp_init); diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 6698d05..dc790ab 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -194,7 +194,7 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); - int ret; + int ret = -EINVAL; switch (cmd) { case SNDRV_PCM_TRIGGER_START: diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c index 326d3c3..5bf7236 100644 --- a/sound/soc/samsung/s3c24xx-i2s.c +++ b/sound/soc/samsung/s3c24xx-i2s.c @@ -461,8 +461,8 @@ static int s3c24xx_iis_dev_probe(struct platform_device *pdev) return -ENOENT; } s3c24xx_i2s.regs = devm_ioremap_resource(&pdev->dev, res); - if (s3c24xx_i2s.regs == NULL) - return -ENXIO; + if (IS_ERR(s3c24xx_i2s.regs)) + return PTR_ERR(s3c24xx_i2s.regs); s3c24xx_i2s_pcm_stereo_out.dma_addr = res->start + S3C2410_IISFIFO; s3c24xx_i2s_pcm_stereo_in.dma_addr = res->start + S3C2410_IISFIFO; diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c index ac3756f..144308f 100644 --- a/sound/soc/sh/rcar/dma.c +++ b/sound/soc/sh/rcar/dma.c @@ -156,6 +156,7 @@ static int rsnd_dmaen_init(struct rsnd_priv *priv, struct rsnd_dma *dma, int id, (void *)id); } if (IS_ERR_OR_NULL(dmaen->chan)) { + dmaen->chan = NULL; dev_err(dev, "can't get dma channel\n"); goto rsnd_dma_channel_err; } diff --git a/sound/synth/emux/emux_oss.c b/sound/synth/emux/emux_oss.c index ab37add..82e350e 100644 --- a/sound/synth/emux/emux_oss.c +++ b/sound/synth/emux/emux_oss.c @@ -118,12 +118,8 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) if (snd_BUG_ON(!arg || !emu)) return -ENXIO; - mutex_lock(&emu->register_mutex); - - if (!snd_emux_inc_count(emu)) { - mutex_unlock(&emu->register_mutex); + if (!snd_emux_inc_count(emu)) return -EFAULT; - } memset(&callback, 0, sizeof(callback)); callback.owner = THIS_MODULE; @@ -135,7 +131,6 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) if (p == NULL) { snd_printk(KERN_ERR "can't create port\n"); snd_emux_dec_count(emu); - mutex_unlock(&emu->register_mutex); return -ENOMEM; } @@ -148,8 +143,6 @@ snd_emux_open_seq_oss(struct snd_seq_oss_arg *arg, void *closure) reset_port_mode(p, arg->seq_mode); snd_emux_reset_port(p); - - mutex_unlock(&emu->register_mutex); return 0; } @@ -195,13 +188,11 @@ snd_emux_close_seq_oss(struct snd_seq_oss_arg *arg) if (snd_BUG_ON(!emu)) return -ENXIO; - mutex_lock(&emu->register_mutex); snd_emux_sounds_off_all(p); snd_soundfont_close_check(emu->sflist, SF_CLIENT_NO(p->chset.port)); snd_seq_event_port_detach(p->chset.client, p->chset.port); snd_emux_dec_count(emu); - mutex_unlock(&emu->register_mutex); return 0; } diff --git a/sound/synth/emux/emux_seq.c b/sound/synth/emux/emux_seq.c index 7778b8e..a020920 100644 --- a/sound/synth/emux/emux_seq.c +++ b/sound/synth/emux/emux_seq.c @@ -124,12 +124,10 @@ snd_emux_detach_seq(struct snd_emux *emu) if (emu->voices) snd_emux_terminate_all(emu); - mutex_lock(&emu->register_mutex); if (emu->client >= 0) { snd_seq_delete_kernel_client(emu->client); emu->client = -1; } - mutex_unlock(&emu->register_mutex); } @@ -269,8 +267,8 @@ snd_emux_event_input(struct snd_seq_event *ev, int direct, void *private_data, /* * increment usage count */ -int -snd_emux_inc_count(struct snd_emux *emu) +static int +__snd_emux_inc_count(struct snd_emux *emu) { emu->used++; if (!try_module_get(emu->ops.owner)) @@ -284,12 +282,21 @@ snd_emux_inc_count(struct snd_emux *emu) return 1; } +int snd_emux_inc_count(struct snd_emux *emu) +{ + int ret; + + mutex_lock(&emu->register_mutex); + ret = __snd_emux_inc_count(emu); + mutex_unlock(&emu->register_mutex); + return ret; +} /* * decrease usage count */ -void -snd_emux_dec_count(struct snd_emux *emu) +static void +__snd_emux_dec_count(struct snd_emux *emu) { module_put(emu->card->module); emu->used--; @@ -298,6 +305,12 @@ snd_emux_dec_count(struct snd_emux *emu) module_put(emu->ops.owner); } +void snd_emux_dec_count(struct snd_emux *emu) +{ + mutex_lock(&emu->register_mutex); + __snd_emux_dec_count(emu); + mutex_unlock(&emu->register_mutex); +} /* * Routine that is called upon a first use of a particular port @@ -317,7 +330,7 @@ snd_emux_use(void *private_data, struct snd_seq_port_subscribe *info) mutex_lock(&emu->register_mutex); snd_emux_init_port(p); - snd_emux_inc_count(emu); + __snd_emux_inc_count(emu); mutex_unlock(&emu->register_mutex); return 0; } @@ -340,7 +353,7 @@ snd_emux_unuse(void *private_data, struct snd_seq_port_subscribe *info) mutex_lock(&emu->register_mutex); snd_emux_sounds_off_all(p); - snd_emux_dec_count(emu); + __snd_emux_dec_count(emu); mutex_unlock(&emu->register_mutex); return 0; } diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index 5a16117..a9099d9 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -26,7 +26,7 @@ override define EMIT_TESTS $(MAKE) -s -C ebb emit_tests endef -DEFAULT_INSTALL := $(INSTALL_RULE) +DEFAULT_INSTALL_RULE := $(INSTALL_RULE) override define INSTALL_RULE $(DEFAULT_INSTALL_RULE) $(MAKE) -C ebb install diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 1b616fa..6bff955 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -1,4 +1,4 @@ -TEST_PROGS := tm-resched-dscr tm-syscall +TEST_PROGS := tm-resched-dscr all: $(TEST_PROGS) |