diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics index 55db27815361b..53e508c6936a5 100644 --- a/Documentation/ABI/testing/sysfs-class-net-statistics +++ b/Documentation/ABI/testing/sysfs-class-net-statistics @@ -1,4 +1,4 @@ -What: /sys/class//statistics/collisions +What: /sys/class/net//statistics/collisions Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -6,7 +6,7 @@ Description: Indicates the number of collisions seen by this network device. This value might not be relevant with all MAC layers. -What: /sys/class//statistics/multicast +What: /sys/class/net//statistics/multicast Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -14,7 +14,7 @@ Description: Indicates the number of multicast packets received by this network device. -What: /sys/class//statistics/rx_bytes +What: /sys/class/net//statistics/rx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -23,7 +23,7 @@ Description: See the network driver for the exact meaning of when this value is incremented. -What: /sys/class//statistics/rx_compressed +What: /sys/class/net//statistics/rx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: network device. This value might only be relevant for interfaces that support packet compression (e.g: PPP). -What: /sys/class//statistics/rx_crc_errors +What: /sys/class/net//statistics/rx_crc_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -41,7 +41,7 @@ Description: by this network device. Note that the specific meaning might depend on the MAC layer used by the interface. -What: /sys/class//statistics/rx_dropped +What: /sys/class/net//statistics/rx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -51,7 +51,7 @@ Description: packet processing. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_errors +What: /sys/class/net//statistics/rx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -59,7 +59,7 @@ Description: Indicates the number of receive errors on this network device. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_fifo_errors +What: /sys/class/net//statistics/rx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -68,7 +68,7 @@ Description: network device. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_frame_errors +What: /sys/class/net//statistics/rx_frame_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -78,7 +78,7 @@ Description: on the MAC layer protocol used. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_length_errors +What: /sys/class/net//statistics/rx_length_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -87,7 +87,7 @@ Description: error, oversized or undersized. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_missed_errors +What: /sys/class/net//statistics/rx_missed_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -96,7 +96,7 @@ Description: due to lack of capacity in the receive side. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_nohandler +What: /sys/class/net//statistics/rx_nohandler Date: February 2016 KernelVersion: 4.6 Contact: netdev@vger.kernel.org @@ -104,7 +104,7 @@ Description: Indicates the number of received packets that were dropped on an inactive device by the network core. -What: /sys/class//statistics/rx_over_errors +What: /sys/class/net//statistics/rx_over_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -114,7 +114,7 @@ Description: (e.g: larger than MTU). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_packets +What: /sys/class/net//statistics/rx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -122,7 +122,7 @@ Description: Indicates the total number of good packets received by this network device. -What: /sys/class//statistics/tx_aborted_errors +What: /sys/class/net//statistics/tx_aborted_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -132,7 +132,7 @@ Description: a medium collision). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/tx_bytes +What: /sys/class/net//statistics/tx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -143,7 +143,7 @@ Description: transmitted packets or all packets that have been queued for transmission. -What: /sys/class//statistics/tx_carrier_errors +What: /sys/class/net//statistics/tx_carrier_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -152,7 +152,7 @@ Description: because of carrier errors (e.g: physical link down). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/tx_compressed +What: /sys/class/net//statistics/tx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -161,7 +161,7 @@ Description: this might only be relevant for devices that support compression (e.g: PPP). -What: /sys/class//statistics/tx_dropped +What: /sys/class/net//statistics/tx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -170,7 +170,7 @@ Description: See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_errors +What: /sys/class/net//statistics/tx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -179,7 +179,7 @@ Description: a network device. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_fifo_errors +What: /sys/class/net//statistics/tx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -188,7 +188,7 @@ Description: FIFO error. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_heartbeat_errors +What: /sys/class/net//statistics/tx_heartbeat_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -197,7 +197,7 @@ Description: reported as heartbeat errors. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_packets +What: /sys/class/net//statistics/tx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -206,7 +206,7 @@ Description: device. See the driver for whether this reports the number of all attempted or successful transmissions. -What: /sys/class//statistics/tx_window_errors +What: /sys/class/net//statistics/tx_window_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index 7acd64c61f50c..29fd5213eeb2b 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -235,3 +235,10 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ASR | ASR8601 | #8601001 | N/A | +----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2139208 | ARM64_ERRATUM_2139208 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2067961 | ARM64_ERRATUM_2067961 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2253138 | ARM64_ERRATUM_2253138 | ++----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/arch/ia64/features.rst b/Documentation/arch/ia64/features.rst index d7226fdcf5f8c..056838d2ab55c 100644 --- a/Documentation/arch/ia64/features.rst +++ b/Documentation/arch/ia64/features.rst @@ -1,3 +1,3 @@ .. SPDX-License-Identifier: GPL-2.0 -.. kernel-feat:: $srctree/Documentation/features ia64 +.. kernel-feat:: features ia64 diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index e33ad2401ad70..562f46b412744 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -126,7 +126,7 @@ Users may also set the RoCE capability of the function using `devlink port function set roce` command. Users may also set the function as migratable using -'devlink port function set migratable' command. +`devlink port function set migratable` command. Users may also set the IPsec crypto capability of the function using `devlink port function set ipsec_crypto` command. diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py index b9df61eb45013..03ace5f01b5c0 100644 --- a/Documentation/sphinx/kernel_feat.py +++ b/Documentation/sphinx/kernel_feat.py @@ -109,7 +109,7 @@ class KernelFeat(Directive): else: out_lines += line + "\n" - nodeList = self.nestedParse(out_lines, fname) + nodeList = self.nestedParse(out_lines, self.arguments[0]) return nodeList def nestedParse(self, lines, fname): diff --git a/Makefile b/Makefile index 3330c00c0a471..b7198af9e59b4 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 6 -SUBLEVEL = 17 +SUBLEVEL = 18 EXTRAVERSION = NAME = Hurr durr I'ma ninja sloth diff --git a/arch/Kconfig b/arch/Kconfig index 12d51495caec1..20c2c93d2c889 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -681,6 +681,7 @@ config SHADOW_CALL_STACK bool "Shadow Call Stack" depends on ARCH_SUPPORTS_SHADOW_CALL_STACK depends on DYNAMIC_FTRACE_WITH_ARGS || DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER + depends on MMU help This option enables the compiler's Shadow Call Stack, which uses a shadow stack to protect function return addresses from diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h index 9d96180797396..a339223d9e052 100644 --- a/arch/arc/include/asm/jump_label.h +++ b/arch/arc/include/asm/jump_label.h @@ -31,7 +31,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "nop \n" ".pushsection __jump_table, \"aw\" \n" @@ -47,7 +47,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "b %l[l_yes] \n" ".pushsection __jump_table, \"aw\" \n" diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h index e12d7d096fc03..e4eb54f6cd9fe 100644 --- a/arch/arm/include/asm/jump_label.h +++ b/arch/arm/include/asm/jump_label.h @@ -11,7 +11,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(nop) "\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -25,7 +25,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(b) " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 94b486192e1f1..a3652b6bb740d 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -229,7 +229,7 @@ alternative_has_cap_likely(const unsigned long cpucap) compiletime_assert(cpucap < ARM64_NCAPS, "cpucap must be < ARM64_NCAPS"); - asm_volatile_goto( + asm goto( ALTERNATIVE_CB("b %l[l_no]", %[cpucap], alt_cb_patch_nops) : : [cpucap] "i" (cpucap) @@ -247,7 +247,7 @@ alternative_has_cap_unlikely(const unsigned long cpucap) compiletime_assert(cpucap < ARM64_NCAPS, "cpucap must be < ARM64_NCAPS"); - asm_volatile_goto( + asm goto( ALTERNATIVE("nop", "b %l[l_yes]", %[cpucap]) : : [cpucap] "i" (cpucap) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 7c7493cb571f9..52f076afeb960 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -61,6 +61,7 @@ #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 #define ARM_CPU_IMP_AMPERE 0xC0 +#define ARM_CPU_IMP_MICROSOFT 0x6D #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -135,6 +136,8 @@ #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -193,6 +196,7 @@ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 48ddc0f45d228..6aafbb7899916 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -18,7 +18,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: nop \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" @@ -35,7 +35,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: b %l[l_yes] \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 87787a012bea8..7bba831f62c33 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -390,6 +390,7 @@ static const struct midr_range erratum_1463225[] = { static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2139208 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2119858 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -403,6 +404,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { static const struct midr_range tsb_flush_fail_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2067961 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2054223 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -415,6 +417,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = { static struct midr_range trbe_write_out_of_range_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2253138 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2224489 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index f9b3adebcb187..1e1e0511c0081 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1686,7 +1686,7 @@ void fpsimd_preserve_current_state(void) void fpsimd_signal_preserve_current_state(void) { fpsimd_preserve_current_state(); - if (test_thread_flag(TIF_SVE)) + if (current->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(current); } diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0e8beb3349ea2..425b1bc17a3f6 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -242,7 +242,7 @@ static int preserve_sve_context(struct sve_context __user *ctx) vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); flags |= SVE_SIG_FLAG_SM; - } else if (test_thread_flag(TIF_SVE)) { + } else if (current->thread.fp_type == FP_STATE_SVE) { vq = sve_vq_from_vl(vl); } @@ -878,7 +878,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0; - if (add_all || test_thread_flag(TIF_SVE) || + if (add_all || current->thread.fp_type == FP_STATE_SVE || thread_sm_enabled(¤t->thread)) { int vl = max(sve_max_vl(), sme_max_vl()); diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 6ff3ec18c9258..b2c8084cdb95d 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -101,6 +101,17 @@ void __init kvm_hyp_reserve(void) hyp_mem_base); } +static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm) +{ + if (host_kvm->arch.pkvm.handle) { + WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, + host_kvm->arch.pkvm.handle)); + } + + host_kvm->arch.pkvm.handle = 0; + free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); +} + /* * Allocates and donates memory for hypervisor VM structs at EL2. * @@ -181,7 +192,7 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm) return 0; destroy_vm: - pkvm_destroy_hyp_vm(host_kvm); + __pkvm_destroy_hyp_vm(host_kvm); return ret; free_vm: free_pages_exact(hyp_vm, hyp_vm_sz); @@ -194,23 +205,19 @@ int pkvm_create_hyp_vm(struct kvm *host_kvm) { int ret = 0; - mutex_lock(&host_kvm->lock); + mutex_lock(&host_kvm->arch.config_lock); if (!host_kvm->arch.pkvm.handle) ret = __pkvm_create_hyp_vm(host_kvm); - mutex_unlock(&host_kvm->lock); + mutex_unlock(&host_kvm->arch.config_lock); return ret; } void pkvm_destroy_hyp_vm(struct kvm *host_kvm) { - if (host_kvm->arch.pkvm.handle) { - WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, - host_kvm->arch.pkvm.handle)); - } - - host_kvm->arch.pkvm.handle = 0; - free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); + mutex_lock(&host_kvm->arch.config_lock); + __pkvm_destroy_hyp_vm(host_kvm); + mutex_unlock(&host_kvm->arch.config_lock); } int pkvm_init_host_vm(struct kvm *host_kvm) diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h index 98a3f4b168bd2..ef2e37a10a0fe 100644 --- a/arch/csky/include/asm/jump_label.h +++ b/arch/csky/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: nop32 \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" @@ -29,7 +29,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: bsr32 %l[label] \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h index 3cea299a5ef58..29acfe3de3faa 100644 --- a/arch/loongarch/include/asm/jump_label.h +++ b/arch/loongarch/include/asm/jump_label.h @@ -22,7 +22,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: nop \n\t" JUMP_TABLE_ENTRY : : "i"(&((char *)key)[branch]) : : l_yes); @@ -35,7 +35,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, co static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( "1: b %l[l_yes] \n\t" JUMP_TABLE_ENTRY : : "i"(&((char *)key)[branch]) : : l_yes); diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c index cc3e81fe0186f..c608adc998458 100644 --- a/arch/loongarch/mm/kasan_init.c +++ b/arch/loongarch/mm/kasan_init.c @@ -44,6 +44,9 @@ void *kasan_mem_to_shadow(const void *addr) unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff; unsigned long offset = 0; + if (maddr >= FIXADDR_START) + return (void *)(kasan_early_shadow_page); + maddr &= XRANGE_SHADOW_MASK; switch (xrange) { case XKPRANGE_CC_SEG: diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index 4044eaf989ac7..0921ddda11a4b 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " .set pop" : "=&r" (sum), "=&r" (tmp) : "r" (saddr), "r" (daddr), - "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)); + "0" (htonl(len)), "r" (htonl(proto)), "r" (sum) + : "memory"); return csum_fold(sum); } diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h index c5c6864e64bc4..405c85173f2c1 100644 --- a/arch/mips/include/asm/jump_label.h +++ b/arch/mips/include/asm/jump_label.h @@ -36,7 +36,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" B_INSN " 2f\n\t" + asm goto("1:\t" B_INSN " 2f\n\t" "2:\t.insn\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" @@ -50,7 +50,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t" + asm goto("1:\t" J_INSN " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" ".popsection\n\t" diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index daf3cf244ea97..701a233583c2c 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -154,6 +154,8 @@ static inline long regs_return_value(struct pt_regs *regs) } #define instruction_pointer(regs) ((regs)->cp0_epc) +extern unsigned long exception_ip(struct pt_regs *regs); +#define exception_ip(regs) exception_ip(regs) #define profile_pc(regs) instruction_pointer(regs) extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index d9df543f7e2c4..59288c13b581b 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -31,6 +31,7 @@ #include #include +#include #include #include #include @@ -48,6 +49,12 @@ #define CREATE_TRACE_POINTS #include +unsigned long exception_ip(struct pt_regs *regs) +{ + return exception_epc(regs); +} +EXPORT_SYMBOL(exception_ip); + /* * Called by kernel/ptrace.c when detaching.. * diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 8c45b98dfe0e4..4adeb73d5885c 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -24,7 +24,6 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select BUG - select BUILDTIME_TABLE_SORT select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_KERNEL_BZIP2 diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 74d17d7e759da..5937d5edaba1e 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -576,6 +576,7 @@ .section __ex_table,"aw" ! \ .align 4 ! \ .word (fault_addr - .), (except_addr - .) ! \ + or %r0,%r0,%r0 ! \ .previous diff --git a/arch/parisc/include/asm/extable.h b/arch/parisc/include/asm/extable.h new file mode 100644 index 0000000000000..4ea23e3d79dc9 --- /dev/null +++ b/arch/parisc/include/asm/extable.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PARISC_EXTABLE_H +#define __PARISC_EXTABLE_H + +#include +#include + +/* + * The exception table consists of three addresses: + * + * - A relative address to the instruction that is allowed to fault. + * - A relative address at which the program should continue (fixup routine) + * - An asm statement which specifies which CPU register will + * receive -EFAULT when an exception happens if the lowest bit in + * the fixup address is set. + * + * Note: The register specified in the err_opcode instruction will be + * modified at runtime if a fault happens. Register %r0 will be ignored. + * + * Since relative addresses are used, 32bit values are sufficient even on + * 64bit kernel. + */ + +struct pt_regs; +int fixup_exception(struct pt_regs *regs); + +#define ARCH_HAS_RELATIVE_EXTABLE +struct exception_table_entry { + int insn; /* relative address of insn that is allowed to fault. */ + int fixup; /* relative address of fixup routine */ + int err_opcode; /* sample opcode with register which holds error code */ +}; + +#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr, opcode )\ + ".section __ex_table,\"aw\"\n" \ + ".align 4\n" \ + ".word (" #fault_addr " - .), (" #except_addr " - .)\n" \ + opcode "\n" \ + ".previous\n" + +/* + * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry + * (with lowest bit set) for which the fault handler in fixup_exception() will + * load -EFAULT on fault into the register specified by the err_opcode instruction, + * and zeroes the target register in case of a read fault in get_user(). + */ +#define ASM_EXCEPTIONTABLE_VAR(__err_var) \ + int __err_var = 0 +#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr, register )\ + ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1, "or %%r0,%%r0," register) + +static inline void swap_ex_entry_fixup(struct exception_table_entry *a, + struct exception_table_entry *b, + struct exception_table_entry tmp, + int delta) +{ + a->fixup = b->fixup + delta; + b->fixup = tmp.fixup - delta; + a->err_opcode = b->err_opcode; + b->err_opcode = tmp.err_opcode; +} +#define swap_ex_entry_fixup swap_ex_entry_fixup + +#endif diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h index 94428798b6aa6..317ebc5edc9fe 100644 --- a/arch/parisc/include/asm/jump_label.h +++ b/arch/parisc/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align %1\n\t" @@ -29,7 +29,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b,n %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align %1\n\t" diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h index c822bd0c0e3c6..51f40eaf77806 100644 --- a/arch/parisc/include/asm/special_insns.h +++ b/arch/parisc/include/asm/special_insns.h @@ -8,7 +8,8 @@ "copy %%r0,%0\n" \ "8:\tlpa %%r0(%1),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY(8b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY(8b, 9b, \ + "or %%r0,%%r0,%%r0") \ : "=&r" (pa) \ : "r" (va) \ : "memory" \ @@ -22,7 +23,8 @@ "copy %%r0,%0\n" \ "8:\tlpa %%r0(%%sr3,%1),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY(8b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY(8b, 9b, \ + "or %%r0,%%r0,%%r0") \ : "=&r" (pa) \ : "r" (va) \ : "memory" \ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 4165079898d9e..88d0ae5769dde 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -7,6 +7,7 @@ */ #include #include +#include #include #include @@ -26,37 +27,6 @@ #define STD_USER(sr, x, ptr) __put_user_asm(sr, "std", x, ptr) #endif -/* - * The exception table contains two values: the first is the relative offset to - * the address of the instruction that is allowed to fault, and the second is - * the relative offset to the address of the fixup routine. Since relative - * addresses are used, 32bit values are sufficient even on 64bit kernel. - */ - -#define ARCH_HAS_RELATIVE_EXTABLE -struct exception_table_entry { - int insn; /* relative address of insn that is allowed to fault. */ - int fixup; /* relative address of fixup routine */ -}; - -#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\ - ".section __ex_table,\"aw\"\n" \ - ".align 4\n" \ - ".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \ - ".previous\n" - -/* - * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry - * (with lowest bit set) for which the fault handler in fixup_exception() will - * load -EFAULT into %r29 for a read or write fault, and zeroes the target - * register in case of a read fault in get_user(). - */ -#define ASM_EXCEPTIONTABLE_REG 29 -#define ASM_EXCEPTIONTABLE_VAR(__variable) \ - register long __variable __asm__ ("r29") = 0 -#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\ - ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1) - #define __get_user_internal(sr, val, ptr) \ ({ \ ASM_EXCEPTIONTABLE_VAR(__gu_err); \ @@ -83,7 +53,7 @@ struct exception_table_entry { \ __asm__("1: " ldx " 0(%%sr%2,%3),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1") \ : "=r"(__gu_val), "+r"(__gu_err) \ : "i"(sr), "r"(ptr)); \ \ @@ -115,8 +85,8 @@ struct exception_table_entry { "1: ldw 0(%%sr%2,%3),%0\n" \ "2: ldw 4(%%sr%2,%3),%R0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1") \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%1") \ : "=&r"(__gu_tmp.l), "+r"(__gu_err) \ : "i"(sr), "r"(ptr)); \ \ @@ -174,7 +144,7 @@ struct exception_table_entry { __asm__ __volatile__ ( \ "1: " stx " %1,0(%%sr%2,%3)\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0") \ : "+r"(__pu_err) \ : "r"(x), "i"(sr), "r"(ptr)) @@ -186,15 +156,14 @@ struct exception_table_entry { "1: stw %1,0(%%sr%2,%3)\n" \ "2: stw %R1,4(%%sr%2,%3)\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0") \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%0") \ : "+r"(__pu_err) \ : "r"(__val), "i"(sr), "r"(ptr)); \ } while (0) #endif /* !defined(CONFIG_64BIT) */ - /* * Complex access routines -- external declarations */ @@ -216,7 +185,4 @@ unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src, #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER -struct pt_regs; -int fixup_exception(struct pt_regs *regs); - #endif /* __PARISC_UACCESS_H */ diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 268d90a9325b4..393822f167270 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -58,7 +58,7 @@ int pa_serialize_tlb_flushes __ro_after_init; struct pdc_cache_info cache_info __ro_after_init; #ifndef CONFIG_PA20 -struct pdc_btlb_info btlb_info __ro_after_init; +struct pdc_btlb_info btlb_info; #endif DEFINE_STATIC_KEY_TRUE(parisc_has_cache); @@ -850,7 +850,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes, #endif " fic,m %3(%4,%0)\n" "2: sync\n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1") : "+r" (start), "+r" (error) : "r" (end), "r" (dcache_stride), "i" (SR_USER)); } @@ -865,7 +865,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes, #endif " fdc,m %3(%4,%0)\n" "2: sync\n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1") : "+r" (start), "+r" (error) : "r" (end), "r" (icache_stride), "i" (SR_USER)); } diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index ed8b759480614..8be4558ef33c0 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -1004,6 +1004,9 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) pr_info("\n"); + /* Prevent hung task messages when printing on serial console */ + cond_resched(); + pr_info("#define HPA_%08lx_DESCRIPTION \"%s\"\n", hpa, parisc_hardware_description(&dev->id)); diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index ce25acfe4889d..c520e551a1652 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -120,8 +120,8 @@ static int emulate_ldh(struct pt_regs *regs, int toreg) "2: ldbs 1(%%sr1,%3), %0\n" " depw %2, 23, 24, %0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "+r" (val), "+r" (ret), "=&r" (temp1) : "r" (saddr), "r" (regs->isr) ); @@ -152,8 +152,8 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop) " mtctl %2,11\n" " vshd %0,%3,%0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "+r" (val), "+r" (ret), "=&r" (temp1), "=&r" (temp2) : "r" (saddr), "r" (regs->isr) ); @@ -189,8 +189,8 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) " mtsar %%r19\n" " shrpd %0,%%r20,%%sar,%0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "=r" (val), "+r" (ret) : "0" (val), "r" (saddr), "r" (regs->isr) : "r19", "r20" ); @@ -209,9 +209,9 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) " vshd %0,%R0,%0\n" " vshd %R0,%4,%R0\n" "4: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1") : "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1) : "r" (regs->isr) ); } @@ -244,8 +244,8 @@ static int emulate_sth(struct pt_regs *regs, int frreg) "1: stb %1, 0(%%sr1, %3)\n" "2: stb %2, 1(%%sr1, %3)\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0") : "+r" (ret), "=&r" (temp1) : "r" (val), "r" (regs->ior), "r" (regs->isr) ); @@ -285,8 +285,8 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop) " stw %%r20,0(%%sr1,%2)\n" " stw %%r21,4(%%sr1,%2)\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1" ); @@ -329,10 +329,10 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) "3: std %%r20,0(%%sr1,%2)\n" "4: std %%r21,8(%%sr1,%2)\n" "5: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1" ); @@ -357,11 +357,11 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) "4: stw %%r1,4(%%sr1,%2)\n" "5: stw %R1,8(%%sr1,%2)\n" "6: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r1" ); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 2fe5b44986e09..c39de84e98b05 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -150,11 +150,16 @@ int fixup_exception(struct pt_regs *regs) * Fix up get_user() and put_user(). * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant * bit in the relative address of the fixup routine to indicate - * that gr[ASM_EXCEPTIONTABLE_REG] should be loaded with - * -EFAULT to report a userspace access error. + * that the register encoded in the "or %r0,%r0,register" + * opcode should be loaded with -EFAULT to report a userspace + * access error. */ if (fix->fixup & 1) { - regs->gr[ASM_EXCEPTIONTABLE_REG] = -EFAULT; + int fault_error_reg = fix->err_opcode & 0x1f; + if (!WARN_ON(!fault_error_reg)) + regs->gr[fault_error_reg] = -EFAULT; + pr_debug("Unalignment fixup of register %d at %pS\n", + fault_error_reg, (void*)regs->iaoq[0]); /* zero target register for get_user() */ if (parisc_acctyp(0, regs->iir) == VM_READ) { diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 93ce3ec253877..2f2a86ed2280a 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop # arch_static_branch\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" @@ -32,7 +32,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes] # arch_static_branch_jump\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 4ae4ab9090a2d..ade5f094dbd22 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -617,6 +617,8 @@ #endif #define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */ #define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */ +#define SPRN_HID2_G2_LE 0x3F3 /* G2_LE HID2 Register */ +#define HID2_G2_LE_HBE (1<<18) /* High BAT Enable (G2_LE) */ #define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */ #define SPRN_IABR2 0x3FA /* 83xx */ #define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */ diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index bf5dde1a41147..15c5691dd2184 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -14,7 +14,7 @@ #ifdef __KERNEL__ -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15 #define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1) #else #define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index fb725ec77926e..4c96de9cd1e99 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -74,7 +74,7 @@ __pu_failed: \ /* -mprefixed can generate offsets beyond range, fall back hack */ #ifdef CONFIG_PPC_KERNEL_PREFIXED #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op " %0,0(%1) # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -83,7 +83,7 @@ __pu_failed: \ : label) #else #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -97,7 +97,7 @@ __pu_failed: \ __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ @@ -146,7 +146,7 @@ do { \ /* -mprefixed can generate offsets beyond range, fall back hack */ #ifdef CONFIG_PPC_KERNEL_PREFIXED #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op" %0,0(%1) # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -155,7 +155,7 @@ do { \ : label) #else #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -169,7 +169,7 @@ do { \ __get_user_asm_goto(x, addr, label, "ld") #else /* __powerpc64__ */ #define __get_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: lwz%X1 %0, %1\n" \ "2: lwz%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index f29ce3dd6140f..bfd3f442e5eb9 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -26,6 +26,15 @@ BEGIN_FTR_SECTION bl __init_fpu_registers END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE) bl setup_common_caches + + /* + * This assumes that all cores using __setup_cpu_603 with + * MMU_FTR_USE_HIGH_BATS are G2_LE compatible + */ +BEGIN_MMU_FTR_SECTION + bl setup_g2_le_hid2 +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + mtlr r5 blr _GLOBAL(__setup_cpu_604) @@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0) blr SYM_FUNC_END(setup_604_hid0) +/* Enable high BATs for G2_LE and derivatives like e300cX */ +SYM_FUNC_START_LOCAL(setup_g2_le_hid2) + mfspr r11,SPRN_HID2_G2_LE + oris r11,r11,HID2_G2_LE_HBE@h + mtspr SPRN_HID2_G2_LE,r11 + sync + isync + blr +SYM_FUNC_END(setup_g2_le_hid2) + /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some * erratas we work around here. * Moto MPC710CE.pdf describes them, those are errata @@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup) mtcr r7 blr _ASM_NOKPROBE_SYMBOL(__restore_cpu_setup) - diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h index ceb06b109f831..2ae8e9a7b461c 100644 --- a/arch/powerpc/kernel/cpu_specs_e500mc.h +++ b/arch/powerpc/kernel/cpu_specs_e500mc.h @@ -8,7 +8,8 @@ #ifdef CONFIG_PPC64 #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ - PPC_FEATURE_HAS_FPU | PPC_FEATURE_64) + PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \ + PPC_FEATURE_BOOKE) #else #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index bd863702d8121..1ad059a9e2fef 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) - std r11,_NIP(r1) + std r11,_LINK(r1) + std r11,_NIP(r1) /* Saved LR is also the next instruction */ std r12,_MSR(r1) std r0,GPR0(r1) std r10,GPR1(r1) @@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) std r9,GPR13(r1) SAVE_NVGPRS(r1) std r11,_XER(r1) - std r11,_LINK(r1) std r11,_CTR(r1) li r11,\trapnr diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index 938e66829eae6..d5c48d1b0a31e 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -230,7 +230,7 @@ notrace __no_kcsan void arch_local_irq_restore(unsigned long mask) * This allows interrupts to be unmasked without hard disabling, and * also without new hard interrupts coming in ahead of pending ones. */ - asm_volatile_goto( + asm goto( "1: \n" " lbz 9,%0(13) \n" " cmpwi 9,0 \n" diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c index a70828a6d9357..aa9aa11927b2f 100644 --- a/arch/powerpc/mm/kasan/init_32.c +++ b/arch/powerpc/mm/kasan/init_32.c @@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size) if (ret) return ret; + k_start = k_start & PAGE_MASK; block = memblock_alloc(k_end - k_start, PAGE_SIZE); if (!block) return -ENOMEM; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index d4d6de0628b05..47d9a65324472 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -662,8 +662,12 @@ u64 pseries_paravirt_steal_clock(int cpu) { struct lppaca *lppaca = &lppaca_of(cpu); - return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + - be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)); + /* + * VPA steal time counters are reported at TB frequency. Hence do a + * conversion to ns before returning + */ + return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + + be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb))); } #endif diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index b7b58258f6c7c..f4157034efa9c 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -98,7 +98,7 @@ riscv_has_extension_likely(const unsigned long ext) "ext must be < RISCV_ISA_EXT_MAX"); if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { - asm_volatile_goto( + asm goto( ALTERNATIVE("j %l[l_no]", "nop", 0, %[ext], 1) : : [ext] "i" (ext) @@ -121,7 +121,7 @@ riscv_has_extension_unlikely(const unsigned long ext) "ext must be < RISCV_ISA_EXT_MAX"); if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { - asm_volatile_goto( + asm goto( ALTERNATIVE("nop", "j %l[l_yes]", 0, %[ext], 1) : : [ext] "i" (ext) diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h index 14a5ea8d8ef0f..4a35d787c0191 100644 --- a/arch/riscv/include/asm/jump_label.h +++ b/arch/riscv/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" @@ -39,7 +39,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 895f774bbcc55..bf78cf381dfcd 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -25,7 +25,7 @@ */ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 0,%l[label]\n" + asm goto("0: brcl 0,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" @@ -39,7 +39,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 15,%l[label]\n" + asm goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h index 94eb529dcb776..2718cbea826a7 100644 --- a/arch/sparc/include/asm/jump_label.h +++ b/arch/sparc/include/asm/jump_label.h @@ -10,7 +10,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" @@ -26,7 +26,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes]\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" diff --git a/arch/um/Makefile b/arch/um/Makefile index 82f05f2506348..34957dcb88b9c 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -115,7 +115,9 @@ archprepare: $(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static -LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie) +ifdef CONFIG_LD_SCRIPT_DYN +LINK-$(call gcc-min-version, 60100)$(CONFIG_CC_IS_CLANG) += -no-pie +endif LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h index 4b6d1b526bc12..66fe06db872f0 100644 --- a/arch/um/include/asm/cpufeature.h +++ b/arch/um/include/asm/cpufeature.h @@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" + asm goto("1: jmp 6f\n" "2:\n" ".skip -(((5f-4f) - (2b-1b)) > 0) * " "((5f-4f) - (2b-1b)),0x90\n" diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 00468adf180f1..87396575cfa77 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -375,7 +375,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index f33e45ed14376..3cece19b74732 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -89,7 +89,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index b22f34b8684a7..083ec6d7722a1 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -43,11 +43,13 @@ SECTIONS *(.rodata.*) _erodata = . ; } - .data : { + .data : ALIGN(0x1000) { _data = . ; *(.data) *(.data.*) - *(.bss.efistub) + + /* Add 4 bytes of extra space for a CRC-32 checksum */ + . = ALIGN(. + 4, 0x200); _edata = . ; } . = ALIGN(L1_CACHE_BYTES); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b04ca8e2b213c..a1bbedd989e42 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -36,66 +36,20 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ #define ROOT_RDONLY 1 #endif + .set salign, 0x1000 + .set falign, 0x200 + .code16 .section ".bstext", "ax" - - .global bootsect_start -bootsect_start: #ifdef CONFIG_EFI_STUB # "MZ", MS-DOS header .word MZ_MAGIC -#endif - - # Normalize the start address - ljmp $BOOTSEG, $start2 - -start2: - movw %cs, %ax - movw %ax, %ds - movw %ax, %es - movw %ax, %ss - xorw %sp, %sp - sti - cld - - movw $bugger_off_msg, %si - -msg_loop: - lodsb - andb %al, %al - jz bs_die - movb $0xe, %ah - movw $7, %bx - int $0x10 - jmp msg_loop - -bs_die: - # Allow the user to press a key, then reboot - xorw %ax, %ax - int $0x16 - int $0x19 - - # int 0x19 should never return. In case it does anyway, - # invoke the BIOS reset code... - ljmp $0xf000,$0xfff0 - -#ifdef CONFIG_EFI_STUB .org 0x38 # # Offset to the PE header. # .long LINUX_PE_MAGIC .long pe_header -#endif /* CONFIG_EFI_STUB */ - - .section ".bsdata", "a" -bugger_off_msg: - .ascii "Use a boot loader.\r\n" - .ascii "\n" - .ascii "Remove disk and press any key to reboot...\r\n" - .byte 0 - -#ifdef CONFIG_EFI_STUB pe_header: .long PE_MAGIC @@ -124,30 +78,26 @@ optional_header: .byte 0x02 # MajorLinkerVersion .byte 0x14 # MinorLinkerVersion - # Filled in by build.c - .long 0 # SizeOfCode + .long ZO__data # SizeOfCode - .long 0 # SizeOfInitializedData + .long ZO__end - ZO__data # SizeOfInitializedData .long 0 # SizeOfUninitializedData - # Filled in by build.c - .long 0x0000 # AddressOfEntryPoint + .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint - .long 0x0200 # BaseOfCode + .long setup_size # BaseOfCode #ifdef CONFIG_X86_32 .long 0 # data #endif extra_header_fields: - # PE specification requires ImageBase to be 64k aligned - .set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff #ifdef CONFIG_X86_32 - .long image_base # ImageBase + .long 0 # ImageBase #else - .quad image_base # ImageBase + .quad 0 # ImageBase #endif - .long 0x20 # SectionAlignment - .long 0x20 # FileAlignment + .long salign # SectionAlignment + .long falign # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion .word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion @@ -156,12 +106,9 @@ extra_header_fields: .word 0 # MinorSubsystemVersion .long 0 # Win32VersionValue - # - # The size of the bzImage is written in tools/build.c - # - .long 0 # SizeOfImage + .long setup_size + ZO__end # SizeOfImage - .long 0x200 # SizeOfHeaders + .long salign # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) #ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES @@ -192,87 +139,77 @@ extra_header_fields: # Section table section_table: - # - # The offset & size fields are filled in by build.c. - # .ascii ".setup" .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data - # on disk - .long 0x0 # startup_{32,64} - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers - .long IMAGE_SCN_CNT_CODE | \ - IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + .long pecompat_fstart - salign # VirtualSize + .long salign # VirtualAddress + .long pecompat_fstart - salign # SizeOfRawData + .long salign # PointerToRawData - # - # The EFI application loader requires a relocation section - # because EFI applications must be relocatable. The .reloc - # offset & size fields are filled in by build.c. - # - .ascii ".reloc" - .byte 0 - .byte 0 - .long 0 - .long 0 - .long 0 # SizeOfRawData - .long 0 # PointerToRawData - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics #ifdef CONFIG_EFI_MIXED - # - # The offset & size fields are filled in by build.c. - # .asciz ".compat" - .long 0 - .long 0x0 - .long 0 # Size of initialized data - # on disk - .long 0x0 - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + + .long pecompat_fsize # VirtualSize + .long pecompat_fstart # VirtualAddress + .long pecompat_fsize # SizeOfRawData + .long pecompat_fstart # PointerToRawData + + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics + + /* + * Put the IA-32 machine type and the associated entry point address in + * the .compat section, so loaders can figure out which other execution + * modes this image supports. + */ + .pushsection ".pecompat", "a", @progbits + .balign salign + .globl pecompat_fstart +pecompat_fstart: + .byte 0x1 # Version + .byte 8 # Size + .word IMAGE_FILE_MACHINE_I386 # PE machine type + .long setup_size + ZO_efi32_pe_entry # Entrypoint + .byte 0x0 # Sentinel + .popsection +#else + .set pecompat_fstart, setup_size #endif - - # - # The offset & size fields are filled in by build.c. - # .ascii ".text" .byte 0 .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data + .long ZO__data + .long setup_size + .long ZO__data # Size of initialized data # on disk - .long 0x0 # startup_{32,64} + .long setup_size .long 0 # PointerToRelocations .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations .word 0 # NumberOfLineNumbers .long IMAGE_SCN_CNT_CODE | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + IMAGE_SCN_MEM_EXECUTE # Characteristics + + .ascii ".data\0\0\0" + .long ZO__end - ZO__data # VirtualSize + .long setup_size + ZO__data # VirtualAddress + .long ZO__edata - ZO__data # SizeOfRawData + .long setup_size + ZO__data # PointerToRawData + + .long 0, 0, 0 + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_WRITE # Characteristics .set section_count, (. - section_table) / 40 #endif /* CONFIG_EFI_STUB */ @@ -286,12 +223,12 @@ sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */ .globl hdr hdr: -setup_sects: .byte 0 /* Filled in by build.c */ + .byte setup_sects - 1 root_flags: .word ROOT_RDONLY -syssize: .long 0 /* Filled in by build.c */ +syssize: .long ZO__edata / 16 ram_size: .word 0 /* Obsolete */ vid_mode: .word SVGA_MODE -root_dev: .word 0 /* Filled in by build.c */ +root_dev: .word 0 /* Default to major/minor 0/0 */ boot_flag: .word 0xAA55 # offset 512, entry point @@ -579,9 +516,25 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr # define INIT_SIZE VO_INIT_SIZE #endif + .macro __handover_offset +#ifndef CONFIG_EFI_HANDOVER_PROTOCOL + .long 0 +#elif !defined(CONFIG_X86_64) + .long ZO_efi32_stub_entry +#else + /* Yes, this is really how we defined it :( */ + .long ZO_efi64_stub_entry - 0x200 +#ifdef CONFIG_EFI_MIXED + .if ZO_efi32_stub_entry != ZO_efi64_stub_entry - 0x200 + .error "32-bit and 64-bit EFI entry points do not match" + .endif +#endif +#endif + .endm + init_size: .long INIT_SIZE # kernel initialization size -handover_offset: .long 0 # Filled in by build.c -kernel_info_offset: .long 0 # Filled in by build.c +handover_offset: __handover_offset +kernel_info_offset: .long ZO_kernel_info # End of setup header ##################################################### diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 49546c247ae25..3a2d1360abb01 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -10,10 +10,11 @@ ENTRY(_start) SECTIONS { . = 0; - .bstext : { *(.bstext) } - .bsdata : { *(.bsdata) } + .bstext : { + *(.bstext) + . = 495; + } =0xffffffff - . = 495; .header : { *(.header) } .entrytext : { *(.entrytext) } .inittext : { *(.inittext) } @@ -23,6 +24,9 @@ SECTIONS .text : { *(.text .text.*) } .text32 : { *(.text32) } + .pecompat : { *(.pecompat) } + PROVIDE(pecompat_fsize = setup_size - pecompat_fstart); + . = ALIGN(16); .rodata : { *(.rodata*) } @@ -38,8 +42,10 @@ SECTIONS .signature : { setup_sig = .; LONG(0x5a5aaa55) - } + setup_size = ALIGN(ABSOLUTE(.), 4096); + setup_sects = ABSOLUTE(setup_size / 512); + } . = ALIGN(16); .bss : diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index bd247692b7017..10311d77c67f8 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -40,10 +40,6 @@ typedef unsigned char u8; typedef unsigned short u16; typedef unsigned int u32; -#define DEFAULT_MAJOR_ROOT 0 -#define DEFAULT_MINOR_ROOT 0 -#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT) - /* Minimal number of setup sectors */ #define SETUP_SECT_MIN 5 #define SETUP_SECT_MAX 64 @@ -51,22 +47,7 @@ typedef unsigned int u32; /* This must be large enough to hold the entire setup */ u8 buf[SETUP_SECT_MAX*512]; -#define PECOFF_RELOC_RESERVE 0x20 - -#ifdef CONFIG_EFI_MIXED -#define PECOFF_COMPAT_RESERVE 0x20 -#else -#define PECOFF_COMPAT_RESERVE 0x0 -#endif - -static unsigned long efi32_stub_entry; -static unsigned long efi64_stub_entry; -static unsigned long efi_pe_entry; -static unsigned long efi32_pe_entry; -static unsigned long kernel_info; -static unsigned long startup_64; -static unsigned long _ehead; -static unsigned long _end; +static unsigned long _edata; /*----------------------------------------------------------------------*/ @@ -152,180 +133,6 @@ static void usage(void) die("Usage: build setup system zoffset.h image"); } -#ifdef CONFIG_EFI_STUB - -static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) -{ - unsigned int pe_header; - unsigned short num_sections; - u8 *section; - - pe_header = get_unaligned_le32(&buf[0x3c]); - num_sections = get_unaligned_le16(&buf[pe_header + 6]); - -#ifdef CONFIG_X86_32 - section = &buf[pe_header + 0xa8]; -#else - section = &buf[pe_header + 0xb8]; -#endif - - while (num_sections > 0) { - if (strncmp((char*)section, section_name, 8) == 0) { - /* section header size field */ - put_unaligned_le32(size, section + 0x8); - - /* section header vma field */ - put_unaligned_le32(vma, section + 0xc); - - /* section header 'size of initialised data' field */ - put_unaligned_le32(datasz, section + 0x10); - - /* section header 'file offset' field */ - put_unaligned_le32(offset, section + 0x14); - - break; - } - section += 0x28; - num_sections--; - } -} - -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) -{ - update_pecoff_section_header_fields(section_name, offset, size, size, offset); -} - -static void update_pecoff_setup_and_reloc(unsigned int size) -{ - u32 setup_offset = 0x200; - u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE; -#ifdef CONFIG_EFI_MIXED - u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE; -#endif - u32 setup_size = reloc_offset - setup_offset; - - update_pecoff_section_header(".setup", setup_offset, setup_size); - update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE); - - /* - * Modify .reloc section contents with a single entry. The - * relocation is applied to offset 10 of the relocation section. - */ - put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]); - put_unaligned_le32(10, &buf[reloc_offset + 4]); - -#ifdef CONFIG_EFI_MIXED - update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE); - - /* - * Put the IA-32 machine type (0x14c) and the associated entry point - * address in the .compat section, so loaders can figure out which other - * execution modes this image supports. - */ - buf[compat_offset] = 0x1; - buf[compat_offset + 1] = 0x8; - put_unaligned_le16(0x14c, &buf[compat_offset + 2]); - put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]); -#endif -} - -static void update_pecoff_text(unsigned int text_start, unsigned int file_sz, - unsigned int init_sz) -{ - unsigned int pe_header; - unsigned int text_sz = file_sz - text_start; - unsigned int bss_sz = init_sz - file_sz; - - pe_header = get_unaligned_le32(&buf[0x3c]); - - /* - * The PE/COFF loader may load the image at an address which is - * misaligned with respect to the kernel_alignment field in the setup - * header. - * - * In order to avoid relocating the kernel to correct the misalignment, - * add slack to allow the buffer to be aligned within the declared size - * of the image. - */ - bss_sz += CONFIG_PHYSICAL_ALIGN; - init_sz += CONFIG_PHYSICAL_ALIGN; - - /* - * Size of code: Subtract the size of the first sector (512 bytes) - * which includes the header. - */ - put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]); - - /* Size of image */ - put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); - - /* - * Address of entry point for PE/COFF executable - */ - put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]); - - update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz, - text_sz, text_start); -} - -static int reserve_pecoff_reloc_section(int c) -{ - /* Reserve 0x20 bytes for .reloc section */ - memset(buf+c, 0, PECOFF_RELOC_RESERVE); - return PECOFF_RELOC_RESERVE; -} - -static void efi_stub_defaults(void) -{ - /* Defaults for old kernel */ -#ifdef CONFIG_X86_32 - efi_pe_entry = 0x10; -#else - efi_pe_entry = 0x210; - startup_64 = 0x200; -#endif -} - -static void efi_stub_entry_update(void) -{ - unsigned long addr = efi32_stub_entry; - -#ifdef CONFIG_EFI_HANDOVER_PROTOCOL -#ifdef CONFIG_X86_64 - /* Yes, this is really how we defined it :( */ - addr = efi64_stub_entry - 0x200; -#endif - -#ifdef CONFIG_EFI_MIXED - if (efi32_stub_entry != addr) - die("32-bit and 64-bit EFI entry points do not match\n"); -#endif -#endif - put_unaligned_le32(addr, &buf[0x264]); -} - -#else - -static inline void update_pecoff_setup_and_reloc(unsigned int size) {} -static inline void update_pecoff_text(unsigned int text_start, - unsigned int file_sz, - unsigned int init_sz) {} -static inline void efi_stub_defaults(void) {} -static inline void efi_stub_entry_update(void) {} - -static inline int reserve_pecoff_reloc_section(int c) -{ - return 0; -} -#endif /* CONFIG_EFI_STUB */ - -static int reserve_pecoff_compat_section(int c) -{ - /* Reserve 0x20 bytes for .compat section */ - memset(buf+c, 0, PECOFF_COMPAT_RESERVE); - return PECOFF_COMPAT_RESERVE; -} - /* * Parse zoffset.h and find the entry points. We could just #include zoffset.h * but that would mean tools/build would have to be rebuilt every time. It's @@ -354,14 +161,7 @@ static void parse_zoffset(char *fname) p = (char *)buf; while (p && *p) { - PARSE_ZOFS(p, efi32_stub_entry); - PARSE_ZOFS(p, efi64_stub_entry); - PARSE_ZOFS(p, efi_pe_entry); - PARSE_ZOFS(p, efi32_pe_entry); - PARSE_ZOFS(p, kernel_info); - PARSE_ZOFS(p, startup_64); - PARSE_ZOFS(p, _ehead); - PARSE_ZOFS(p, _end); + PARSE_ZOFS(p, _edata); p = strchr(p, '\n'); while (p && (*p == '\r' || *p == '\n')) @@ -371,17 +171,14 @@ static void parse_zoffset(char *fname) int main(int argc, char ** argv) { - unsigned int i, sz, setup_sectors, init_sz; + unsigned int i, sz, setup_sectors; int c; - u32 sys_size; struct stat sb; FILE *file, *dest; int fd; void *kernel; u32 crc = 0xffffffffUL; - efi_stub_defaults(); - if (argc != 5) usage(); parse_zoffset(argv[3]); @@ -403,72 +200,27 @@ int main(int argc, char ** argv) die("Boot block hasn't got boot flag (0xAA55)"); fclose(file); - c += reserve_pecoff_compat_section(c); - c += reserve_pecoff_reloc_section(c); - /* Pad unused space with zeros */ - setup_sectors = (c + 511) / 512; + setup_sectors = (c + 4095) / 4096; + setup_sectors *= 8; if (setup_sectors < SETUP_SECT_MIN) setup_sectors = SETUP_SECT_MIN; i = setup_sectors*512; memset(buf+c, 0, i-c); - update_pecoff_setup_and_reloc(i); - - /* Set the default root device */ - put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]); - /* Open and stat the kernel file */ fd = open(argv[2], O_RDONLY); if (fd < 0) die("Unable to open `%s': %m", argv[2]); if (fstat(fd, &sb)) die("Unable to stat `%s': %m", argv[2]); - sz = sb.st_size; + if (_edata != sb.st_size) + die("Unexpected file size `%s': %u != %u", argv[2], _edata, + sb.st_size); + sz = _edata - 4; kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); if (kernel == MAP_FAILED) die("Unable to mmap '%s': %m", argv[2]); - /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ - sys_size = (sz + 15 + 4) / 16; -#ifdef CONFIG_EFI_STUB - /* - * COFF requires minimum 32-byte alignment of sections, and - * adding a signature is problematic without that alignment. - */ - sys_size = (sys_size + 1) & ~1; -#endif - - /* Patch the setup code with the appropriate size parameters */ - buf[0x1f1] = setup_sectors-1; - put_unaligned_le32(sys_size, &buf[0x1f4]); - - init_sz = get_unaligned_le32(&buf[0x260]); -#ifdef CONFIG_EFI_STUB - /* - * The decompression buffer will start at ImageBase. When relocating - * the compressed kernel to its end, we must ensure that the head - * section does not get overwritten. The head section occupies - * [i, i + _ehead), and the destination is [init_sz - _end, init_sz). - * - * At present these should never overlap, because 'i' is at most 32k - * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the - * calculation of INIT_SIZE in boot/header.S ensures that - * 'init_sz - _end' is at least 64k. - * - * For future-proofing, increase init_sz if necessary. - */ - - if (init_sz - _end < i + _ehead) { - init_sz = (i + _ehead + _end + 4095) & ~4095; - put_unaligned_le32(init_sz, &buf[0x260]); - } -#endif - update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz); - - efi_stub_entry_update(); - - /* Update kernel_info offset. */ - put_unaligned_le32(kernel_info, &buf[0x268]); crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) @@ -479,13 +231,6 @@ int main(int argc, char ** argv) if (fwrite(kernel, 1, sz, dest) != sz) die("Writing kernel failed"); - /* Add padding leaving 4 bytes for the checksum */ - while (sz++ < (sys_size*16) - 4) { - crc = partial_crc32_one('\0', crc); - if (fwrite("\0", 1, 1, dest) != 1) - die("Writing padding failed"); - } - /* Write the CRC */ put_unaligned_le32(crc, buf); if (fwrite(buf, 1, 4, dest) != 4) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 35389b2af88ee..0216f63a366b5 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -81,22 +81,4 @@ do { \ #include -/* - * Make previous memory operations globally visible before - * a WRMSR. - * - * MFENCE makes writes visible, but only affects load/store - * instructions. WRMSR is unfortunately not a load/store - * instruction and is unaffected by MFENCE. The LFENCE ensures - * that the WRMSR is not reordered. - * - * Most WRMSRs are full serializing instructions themselves and - * do not require this barrier. This is only required for the - * IA32_TSC_DEADLINE and X2APIC MSRs. - */ -static inline void weak_wrmsr_fence(void) -{ - asm volatile("mfence; lfence" : : : "memory"); -} - #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index a26bebbdff87e..a1273698fc430 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto( + asm goto( ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 58cb9495e40f4..0091f10083143 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -308,10 +308,10 @@ #define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ #define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ #define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ - #define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ #define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ #define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 071572e23d3a0..cbbef32517f00 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -24,7 +24,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes] # objtool NOPs this \n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (2 | branch) : : l_yes); @@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" ".byte " __stringify(BYTES_NOP5) "\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); @@ -52,7 +52,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, co static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a3669a7774edb..191f1d8f05061 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -734,4 +734,22 @@ bool arch_is_platform_page(u64 paddr); extern bool gds_ucode_mitigated(void); +/* + * Make previous memory operations globally visible before + * a WRMSR. + * + * MFENCE makes writes visible, but only affects load/store + * instructions. WRMSR is unfortunately not a load/store + * instruction and is unaffected by MFENCE. The LFENCE ensures + * that the WRMSR is not reordered. + * + * Most WRMSRs are full serializing instructions themselves and + * do not require this barrier. This is only required for the + * IA32_TSC_DEADLINE and X2APIC MSRs. + */ +static inline void weak_wrmsr_fence(void) +{ + alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE)); +} + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 4b081e0d3306b..363266cbcadaf 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -13,7 +13,7 @@ #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ ({ \ bool c = false; \ - asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \ + asm goto (fullop "; j" #cc " %l[cc_label]" \ : : [var] "m" (_var), ## __VA_ARGS__ \ : clobbers : cc_label); \ if (0) { \ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index d6cd9344f6c78..48f8dd47cf688 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p) #ifdef CONFIG_X86_USER_SHADOW_STACK static inline int write_user_shstk_64(u64 __user *addr, u64 val) { - asm_volatile_goto("1: wrussq %[val], (%[addr])\n" + asm goto("1: wrussq %[val], (%[addr])\n" _ASM_EXTABLE(1b, %l[fail]) :: [addr] "r" (addr), [val] "r" (val) :: fail); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 5c367c1290c35..237dc8cdd12b9 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -133,7 +133,7 @@ extern int __get_user_bad(void); #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ @@ -295,7 +295,7 @@ do { \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ @@ -375,7 +375,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -394,7 +394,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; }; * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 6e4f23f314ac5..bb3efc825bf4f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1157,6 +1157,9 @@ static void init_amd(struct cpuinfo_x86 *c) if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has_amd_erratum(c, amd_erratum_1485)) msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); + + /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ + clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4e5ffc8b0e469..d98d023ae497f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1858,6 +1858,13 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); #endif + + /* + * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and + * Hygon will clear it in ->c_init() below. + */ + set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); + /* * Vendor-specific initialization. In this section we * canonicalize the feature flags, meaning if there are diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index a7b3ef4c4de91..6e738759779e8 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -348,6 +348,9 @@ static void init_hygon(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); check_null_seg_clears_base(c); + + /* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ + clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); } static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 558076dbde5bf..247f2225aa9f3 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ -static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only, unsigned int size) +static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { struct fpu *fpu = ¤t->thread.fpu; int ret; + /* Restore enabled features only. */ + xrestore &= fpu->fpstate->user_xfeatures; retry: fpregs_lock(); /* Ensure that XFD is up to date */ @@ -309,7 +310,7 @@ static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, if (ret != X86_TRAP_PF) return false; - if (!fault_in_readable(buf, size)) + if (!fault_in_readable(buf, fpu->fpstate->user_size)) goto retry; return false; } @@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, struct user_i387_ia32_struct env; bool success, fx_only = false; union fpregs_state *fpregs; - unsigned int state_size; u64 user_xfeatures = 0; if (use_xsave()) { @@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, return false; fx_only = !fx_sw_user.magic1; - state_size = fx_sw_user.xstate_size; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; - state_size = fpu->fpstate->user_size; } if (likely(!ia32_fxstate)) { /* Restore the FPU registers directly from user memory. */ - return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, - state_size); + return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); } /* diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 36c8af87a707a..4e725854c63a1 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -8,7 +8,7 @@ #define svm_asm(insn, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) "\n\t" \ + asm goto("1: " __stringify(insn) "\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ ::: clobber : fault); \ return; \ @@ -18,7 +18,7 @@ fault: \ #define svm_asm1(insn, op1, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1 : clobber : fault); \ return; \ @@ -28,7 +28,7 @@ fault: \ #define svm_asm2(insn, op1, op2, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1, op2 : clobber : fault); \ return; \ diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 90c1f7f07e53b..1549461fa42b7 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -71,7 +71,7 @@ static int fixed_pmc_events[] = { static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { struct kvm_pmc *pmc; - u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl; + u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl; int i; pmu->fixed_ctr_ctrl = data; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9bba5352582c3..792245d7aa356 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -745,7 +745,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, */ static int kvm_cpu_vmxoff(void) { - asm_volatile_goto("1: vmxoff\n\t" + asm goto("1: vmxoff\n\t" _ASM_EXTABLE(1b, %l[fault]) ::: "cc", "memory" : fault); @@ -2789,7 +2789,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) cr4_set_bits(X86_CR4_VMXE); - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + asm goto("1: vmxon %[vmxon_pointer]\n\t" _ASM_EXTABLE(1b, %l[fault]) : : [vmxon_pointer] "m"(vmxon_pointer) : : fault); diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 33af7b4c6eb4a..6a0c6e81f7f3e 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT - asm_volatile_goto("1: vmread %[field], %[output]\n\t" + asm_goto_output("1: vmread %[field], %[output]\n\t" "jna %l[do_fail]\n\t" _ASM_EXTABLE(1b, %l[do_exception]) @@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) #define vmx_asm1(insn, op1, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ @@ -205,7 +205,7 @@ fault: \ #define vmx_asm2(insn, op1, op2, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e179db7c17dad..3d8472d00024c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5300,7 +5300,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { vcpu->arch.nmi_pending = 0; atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending); - kvm_make_request(KVM_REQ_NMI, vcpu); + if (events->nmi.pending) + kvm_make_request(KVM_REQ_NMI, vcpu); } static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 968d7005f4a72..f50cc210a9818 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; + bool use_gbpage; next = (addr & PUD_MASK) + PUD_SIZE; if (next > end) next = end; - if (info->direct_gbpages) { - pud_t pudval; + /* if this is already a gbpage, this portion is already mapped */ + if (pud_large(*pud)) + continue; + + /* Is using a gbpage allowed? */ + use_gbpage = info->direct_gbpages; - if (pud_present(*pud)) - continue; + /* Don't use gbpage if it maps more than the requested region. */ + /* at the begining: */ + use_gbpage &= ((addr & ~PUD_MASK) == 0); + /* ... or at the end: */ + use_gbpage &= ((next & ~PUD_MASK) == 0); + + /* Never overwrite existing mappings */ + use_gbpage &= !pud_present(*pud); + + if (use_gbpage) { + pud_t pudval; - addr &= PUD_MASK; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h index c812bf85021c0..46c8596259d2d 100644 --- a/arch/xtensa/include/asm/jump_label.h +++ b/arch/xtensa/include/asm/jump_label.h @@ -13,7 +13,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "_nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, * make it reachable and wrap both into a no-transform block * to avoid any assembler interference with this. */ - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" ".begin no-transform\n\t" "_j %l[l_yes]\n\t" "2:\n\t" diff --git a/block/blk-mq.c b/block/blk-mq.c index 257b0addd47e5..d8b47f534df93 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -767,11 +767,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio, /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. + * For such case, force the completed nbytes to be equal to + * the BIO size so that bio_advance() sets the BIO remaining + * size to 0 and we end up calling bio_endio() before returning. */ - if (bio->bi_iter.bi_size != nbytes) + if (bio->bi_iter.bi_size != nbytes) { bio->bi_status = BLK_STS_IOERR; - else + nbytes = bio->bi_iter.bi_size; + } else { bio->bi_iter.bi_sector = rq->__sector; + } } bio_advance(bio, nbytes); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 0bb613139becb..f8fda9cf583e1 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -165,9 +165,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) */ static bool wb_recent_wait(struct rq_wb *rwb) { - struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb; + struct backing_dev_info *bdi = rwb->rqos.disk->bdi; - return time_before(jiffies, wb->dirty_sleep + HZ); + return time_before(jiffies, bdi->last_bdp_sleep + HZ); } static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 82c44d4899b96..e24c829d7a015 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -91,13 +91,13 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, if (!(msg->msg_flags & MSG_MORE)) { err = hash_alloc_result(sk, ctx); if (err) - goto unlock_free; + goto unlock_free_result; ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0); err = crypto_wait_req(crypto_ahash_final(&ctx->req), &ctx->wait); if (err) - goto unlock_free; + goto unlock_free_result; } goto done_more; } @@ -170,6 +170,7 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, unlock_free: af_alg_free_sg(&ctx->sgl); +unlock_free_result: hash_free_result(sk, ctx); ctx->more = false; goto unlock; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 71a40a4c546f5..8460458ebe3d4 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -478,6 +478,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread, { WARN_ON(!list_empty(&thread->waiting_thread_node)); binder_enqueue_work_ilocked(work, &thread->todo); + + /* (e)poll-based threads require an explicit wakeup signal when + * queuing their own work; they rely on these events to consume + * messages without I/O block. Without it, threads risk waiting + * indefinitely without handling the work. + */ + if (thread->looper & BINDER_LOOPER_STATE_POLL && + thread->pid == current->pid && !thread->process_todo) + wake_up_interruptible_sync(&thread->wait); + thread->process_todo = true; } diff --git a/drivers/base/core.c b/drivers/base/core.c index 4d8b315c48a15..2cc0ab8541680 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -283,10 +283,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target) return false; } +#define DL_MARKER_FLAGS (DL_FLAG_INFERRED | \ + DL_FLAG_CYCLE | \ + DL_FLAG_MANAGED) static inline bool device_link_flag_is_sync_state_only(u32 flags) { - return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) == - (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED); + return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY; } /** @@ -2057,9 +2059,14 @@ static int fw_devlink_create_devlink(struct device *con, /* * SYNC_STATE_ONLY device links don't block probing and supports cycles. - * So cycle detection isn't necessary and shouldn't be done. + * So, one might expect that cycle detection isn't necessary for them. + * However, if the device link was marked as SYNC_STATE_ONLY because + * it's part of a cycle, then we still need to do cycle detection. This + * is because the consumer and supplier might be part of multiple cycles + * and we need to detect all those cycles. */ - if (!(flags & DL_FLAG_SYNC_STATE_ONLY)) { + if (!device_link_flag_is_sync_state_only(flags) || + flags & DL_FLAG_CYCLE) { device_links_write_lock(); if (__fw_devlink_relax_cycles(con, sup_handle)) { __fwnode_link_cycle(link); diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 5cb2023581d4d..84443b6bd8825 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1102,7 +1102,7 @@ static int __init genpd_power_off_unused(void) return 0; } -late_initcall(genpd_power_off_unused); +late_initcall_sync(genpd_power_off_unused); #ifdef CONFIG_PM_SLEEP diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 3d5e6d705fc6e..44b19e6961763 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -108,9 +108,8 @@ static inline void send_msg(struct cn_msg *msg) filter_data[1] = 0; } - if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, - cn_filter, (void *)filter_data) == -ESRCH) - atomic_set(&proc_event_num_listeners, 0); + cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, + cn_filter, (void *)filter_data); local_unlock(&local_event.lock); } diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index f97166fba9d93..17fb01853dbf4 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -520,10 +520,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init); static int __sev_platform_shutdown_locked(int *error) { - struct sev_device *sev = psp_master->sev_data; + struct psp_device *psp = psp_master; + struct sev_device *sev; int ret; - if (!sev || sev->state == SEV_STATE_UNINIT) + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (sev->state == SEV_STATE_UNINIT) return 0; ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 2828e9573e90b..da8a4c8f28768 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -100,10 +100,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size) * @buf: where to put the string * @size: size of @buf, in bytes * - * The string is taken from a minimal ASCII text descriptor leaf after - * the immediate entry with @key. The string is zero-terminated. - * An overlong string is silently truncated such that it and the - * zero byte fit into @size. + * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the + * @key. The string is zero-terminated. An overlong string is silently truncated such that it + * and the zero byte fit into @size. * * Returns strlen(buf) or a negative error code. */ diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index a1157c2a71704..ef4c12f0877ba 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -108,13 +108,6 @@ lib-y := $(patsubst %.o,%.stub.o,$(lib-y)) # https://bugs.llvm.org/show_bug.cgi?id=46480 STUBCOPY_FLAGS-y += --remove-section=.note.gnu.property -# -# For x86, bootloaders like systemd-boot or grub-efi do not zero-initialize the -# .bss section, so the .bss section of the EFI stub needs to be included in the -# .data section of the compressed kernel to ensure initialization. Rename the -# .bss section here so it's easy to pick out in the linker script. -# -STUBCOPY_FLAGS-$(CONFIG_X86) += --rename-section .bss=.bss.efistub,load,alloc STUBCOPY_RELOC-$(CONFIG_X86_32) := R_386_32 STUBCOPY_RELOC-$(CONFIG_X86_64) := R_X86_64_64 diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 4a11470bed5ea..7bcc5170043fc 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -458,9 +458,8 @@ void __noreturn efi_stub_entry(efi_handle_t handle, efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg) { - struct boot_params *boot_params; - struct setup_header *hdr; - void *image_base; + static struct boot_params boot_params __page_aligned_bss; + struct setup_header *hdr = &boot_params.hdr; efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; int options_size = 0; efi_status_t status; @@ -478,30 +477,9 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_exit(handle, status); } - image_base = efi_table_attr(image, image_base); - - status = efi_allocate_pages(sizeof(struct boot_params), - (unsigned long *)&boot_params, ULONG_MAX); - if (status != EFI_SUCCESS) { - efi_err("Failed to allocate lowmem for boot params\n"); - efi_exit(handle, status); - } - - memset(boot_params, 0x0, sizeof(struct boot_params)); - - hdr = &boot_params->hdr; - - /* Copy the setup header from the second sector to boot_params */ - memcpy(&hdr->jump, image_base + 512, - sizeof(struct setup_header) - offsetof(struct setup_header, jump)); - - /* - * Fill out some of the header fields ourselves because the - * EFI firmware loader doesn't load the first sector. - */ + /* Assign the setup_header fields that the kernel actually cares about */ hdr->root_flags = 1; hdr->vid_mode = 0xffff; - hdr->boot_flag = 0xAA55; hdr->type_of_loader = 0x21; @@ -510,25 +488,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, if (!cmdline_ptr) goto fail; - efi_set_u64_split((unsigned long)cmdline_ptr, - &hdr->cmd_line_ptr, &boot_params->ext_cmd_line_ptr); - - hdr->ramdisk_image = 0; - hdr->ramdisk_size = 0; - - /* - * Disregard any setup data that was provided by the bootloader: - * setup_data could be pointing anywhere, and we have no way of - * authenticating or validating the payload. - */ - hdr->setup_data = 0; + efi_set_u64_split((unsigned long)cmdline_ptr, &hdr->cmd_line_ptr, + &boot_params.ext_cmd_line_ptr); - efi_stub_entry(handle, sys_table_arg, boot_params); + efi_stub_entry(handle, sys_table_arg, &boot_params); /* not reached */ fail: - efi_free(sizeof(struct boot_params), (unsigned long)boot_params); - efi_exit(handle, status); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 7791367e7c024..79261bec26542 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4133,7 +4133,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); cancel_delayed_work_sync(&adev->delayed_init_work); - flush_delayed_work(&adev->gfx.gfx_off_delay_work); amdgpu_ras_suspend(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index ef4cb921781d7..053983e9f4aef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -702,8 +702,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state) { - schedule_delayed_work(&adev->gfx.gfx_off_delay_work, + /* If going to s2idle, no need to wait */ + if (adev->in_s0ix) { + if (!amdgpu_dpm_set_powergating_by_smu(adev, + AMD_IP_BLOCK_TYPE_GFX, true)) + adev->gfx.gfx_off_state = true; + } else { + schedule_delayed_work(&adev->gfx.gfx_off_delay_work, delay); + } } } else { if (adev->gfx.gfx_off_req_count == 0) { diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c index 6f7c031dd197a..f24e34dc33d1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c @@ -204,6 +204,12 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32(mmIH_RB_CNTL); tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; WREG32(mmIH_RB_CNTL, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; + WREG32(mmIH_RB_CNTL, tmp); } return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c index b8c47e0cf37ad..c19681492efa7 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c @@ -216,6 +216,11 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); out: return (wptr & ih->ptr_mask); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index c2b9dfc6451d5..495eb4cad0e1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4020,8 +4020,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) err = 0; adev->gfx.mec2_fw = NULL; } - amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2); - amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT); gfx_v10_0_check_fw_write_wait(adev); out: diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c index aecad530b10a6..2c02ae69883d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c @@ -215,6 +215,11 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); out: return (wptr & ih->ptr_mask); diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c index ec0c8f8b465ab..f432dc72df6a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c @@ -418,6 +418,12 @@ static u32 ih_v6_0_get_wptr(struct amdgpu_device *adev, tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c index 8fb05eae340ad..b8da0fc29378c 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c @@ -418,6 +418,13 @@ static u32 ih_v6_1_get_wptr(struct amdgpu_device *adev, tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c index b6a8478dabf43..737eff53f54f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c @@ -442,6 +442,12 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c index 9a24f17a57502..cada9f300a7f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c @@ -119,6 +119,12 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32(IH_RB_CNTL); tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; WREG32(IH_RB_CNTL, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; + WREG32(IH_RB_CNTL, tmp); } return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 8b2ff2b281b0a..5a77ab587b599 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -50,13 +50,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs; /* SOC21 */ static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, }; static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = { diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c index 917707bba7f36..450b6e8315091 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c @@ -219,6 +219,12 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index d364c6dd152c3..bf68e18e3824b 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -373,6 +373,12 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index dbc99536440f2..131e7b769519c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -421,6 +421,12 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 56a61ac2b3f5a..83c263e2d7171 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6072,7 +6072,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); drm_mode_copy(&saved_mode, &mode); + saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio; drm_mode_copy(&mode, freesync_mode); + mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio; } else { decide_crtc_timing_for_drm_display_mode( &mode, preferred_mode, scale); @@ -10358,11 +10360,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; } - ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); - if (ret) { - DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); - ret = -EINVAL; - goto fail; + if (dc_resource_is_dsc_encoding_supported(dc)) { + ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); + if (ret) { + DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); + ret = -EINVAL; + goto fail; + } } ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars); diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index c206812dc6897..0ba9a7997d561 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 5a0b045189569..16a62e0187122 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -517,6 +517,7 @@ enum link_training_result dp_check_link_loss_status( { enum link_training_result status = LINK_TRAINING_SUCCESS; union lane_status lane_status; + union lane_align_status_updated dpcd_lane_status_updated; uint8_t dpcd_buf[6] = {0}; uint32_t lane; @@ -532,10 +533,12 @@ enum link_training_result dp_check_link_loss_status( * check lanes status */ lane_status.raw = dp_get_nibble_at_index(&dpcd_buf[2], lane); + dpcd_lane_status_updated.raw = dpcd_buf[4]; if (!lane_status.bits.CHANNEL_EQ_DONE_0 || !lane_status.bits.CR_DONE_0 || - !lane_status.bits.SYMBOL_LOCKED_0) { + !lane_status.bits.SYMBOL_LOCKED_0 || + !dp_is_interlane_aligned(dpcd_lane_status_updated)) { /* if one of the channel equalization, clock * recovery or symbol lock is dropped * consider it as (link has been diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 834a5e28abbe5..7352bde299d54 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -820,7 +820,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, if (max_segment == 0) max_segment = UINT_MAX; err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0, - nr_pages << PAGE_SHIFT, + (unsigned long)nr_pages << PAGE_SHIFT, max_segment, GFP_KERNEL); if (err) { kfree(sg); diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index 5f68e31a3e4e1..0915f3b68752e 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -26,7 +26,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map) { void *vaddr; - vaddr = msm_gem_get_vaddr(obj); + vaddr = msm_gem_get_vaddr_locked(obj); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); iosys_map_set_vaddr(map, vaddr); @@ -36,7 +36,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map) void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map) { - msm_gem_put_vaddr(obj); + msm_gem_put_vaddr_locked(obj); } struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev, diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 7f64c66673002..5c10b559a5957 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -749,12 +749,14 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct msm_ringbuffer *ring = submit->ring; unsigned long flags; - pm_runtime_get_sync(&gpu->pdev->dev); + WARN_ON(!mutex_is_locked(&gpu->lock)); - mutex_lock(&gpu->lock); + pm_runtime_get_sync(&gpu->pdev->dev); msm_gpu_hw_init(gpu); + submit->seqno = submit->hw_fence->seqno; + update_sw_cntrs(gpu); /* @@ -779,11 +781,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) gpu->funcs->submit(gpu, submit); gpu->cur_ctx_seqno = submit->queue->ctx->seqno; - hangcheck_timer_reset(gpu); - - mutex_unlock(&gpu->lock); - pm_runtime_put(&gpu->pdev->dev); + hangcheck_timer_reset(gpu); } /* diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 5cc8d358cc975..d5512037c38bc 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -21,6 +21,8 @@ struct msm_iommu_pagetable { struct msm_mmu base; struct msm_mmu *parent; struct io_pgtable_ops *pgtbl_ops; + const struct iommu_flush_ops *tlb; + struct device *iommu_dev; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ phys_addr_t ttbr; u32 asid; @@ -201,11 +203,33 @@ static const struct msm_mmu_funcs pagetable_funcs = { static void msm_iommu_tlb_flush_all(void *cookie) { + struct msm_iommu_pagetable *pagetable = cookie; + struct adreno_smmu_priv *adreno_smmu; + + if (!pm_runtime_get_if_in_use(pagetable->iommu_dev)) + return; + + adreno_smmu = dev_get_drvdata(pagetable->parent->dev); + + pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie); + + pm_runtime_put_autosuspend(pagetable->iommu_dev); } static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule, void *cookie) { + struct msm_iommu_pagetable *pagetable = cookie; + struct adreno_smmu_priv *adreno_smmu; + + if (!pm_runtime_get_if_in_use(pagetable->iommu_dev)) + return; + + adreno_smmu = dev_get_drvdata(pagetable->parent->dev); + + pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie); + + pm_runtime_put_autosuspend(pagetable->iommu_dev); } static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, @@ -213,7 +237,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, { } -static const struct iommu_flush_ops null_tlb_ops = { +static const struct iommu_flush_ops tlb_ops = { .tlb_flush_all = msm_iommu_tlb_flush_all, .tlb_flush_walk = msm_iommu_tlb_flush_walk, .tlb_add_page = msm_iommu_tlb_add_page, @@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* The incoming cfg will have the TTBR1 quirk enabled */ ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1; - ttbr0_cfg.tlb = &null_tlb_ops; + ttbr0_cfg.tlb = &tlb_ops; pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1, - &ttbr0_cfg, iommu->domain); + &ttbr0_cfg, pagetable); if (!pagetable->pgtbl_ops) { kfree(pagetable); @@ -279,6 +303,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Needed later for TLB flush */ pagetable->parent = parent; + pagetable->tlb = ttbr1_cfg->tlb; + pagetable->iommu_dev = ttbr1_cfg->iommu_dev; pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap; pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr; diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 40c0bc35a44ce..7f5e0a961bba7 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -21,8 +21,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) msm_fence_init(submit->hw_fence, fctx); - submit->seqno = submit->hw_fence->seqno; - mutex_lock(&priv->lru.lock); for (i = 0; i < submit->nr_bos; i++) { @@ -34,8 +32,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) mutex_unlock(&priv->lru.lock); + /* TODO move submit path over to using a per-ring lock.. */ + mutex_lock(&gpu->lock); + msm_gpu_submit(gpu, submit); + mutex_unlock(&gpu->lock); + return dma_fence_get(submit->hw_fence); } diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index ca762ea554136..93f08f9479d89 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -103,6 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error) void nouveau_fence_context_del(struct nouveau_fence_chan *fctx) { + cancel_work_sync(&fctx->uevent_work); nouveau_fence_context_kill(fctx, 0); nvif_event_dtor(&fctx->event); fctx->dead = 1; @@ -145,12 +146,13 @@ nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fc return drop; } -static int -nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc) +static void +nouveau_fence_uevent_work(struct work_struct *work) { - struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event); + struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan, + uevent_work); unsigned long flags; - int ret = NVIF_EVENT_KEEP; + int drop = 0; spin_lock_irqsave(&fctx->lock, flags); if (!list_empty(&fctx->pending)) { @@ -160,11 +162,20 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc fence = list_entry(fctx->pending.next, typeof(*fence), head); chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock)); if (nouveau_fence_update(chan, fctx)) - ret = NVIF_EVENT_DROP; + drop = 1; } + if (drop) + nvif_event_block(&fctx->event); + spin_unlock_irqrestore(&fctx->lock, flags); +} - return ret; +static int +nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc) +{ + struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event); + schedule_work(&fctx->uevent_work); + return NVIF_EVENT_KEEP; } void @@ -178,6 +189,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha } args; int ret; + INIT_WORK(&fctx->uevent_work, nouveau_fence_uevent_work); INIT_LIST_HEAD(&fctx->flip); INIT_LIST_HEAD(&fctx->pending); spin_lock_init(&fctx->lock); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 64d33ae7f3561..8bc065acfe358 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -44,6 +44,7 @@ struct nouveau_fence_chan { u32 context; char name[32]; + struct work_struct uevent_work; struct nvif_event event; int notify_ref, dead, killed; }; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 186351ecf72fd..ec9f307370fa8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -1011,7 +1011,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id) if (ret) return ret; - buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL); + buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL); if (!buffer->fault) return -ENOMEM; diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 148f09aaf99a7..c5716fd0aed38 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -94,6 +94,7 @@ static int virtio_gpu_probe(struct virtio_device *vdev) goto err_free; } + dma_set_max_seg_size(dev->dev, dma_max_mapping_size(dev->dev) ?: UINT_MAX); ret = virtio_gpu_init(vdev, dev); if (ret) goto err_free; diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index d9ef45fcaeab1..7903c8638e817 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -241,6 +241,39 @@ int hid_bpf_reconnect(struct hid_device *hdev) return 0; } +static int do_hid_bpf_attach_prog(struct hid_device *hdev, int prog_fd, struct bpf_prog *prog, + __u32 flags) +{ + int fd, err, prog_type; + + prog_type = hid_bpf_get_prog_attach_type(prog); + if (prog_type < 0) + return prog_type; + + if (prog_type >= HID_BPF_PROG_TYPE_MAX) + return -EINVAL; + + if (prog_type == HID_BPF_PROG_TYPE_DEVICE_EVENT) { + err = hid_bpf_allocate_event_data(hdev); + if (err) + return err; + } + + fd = __hid_bpf_attach_prog(hdev, prog_type, prog_fd, prog, flags); + if (fd < 0) + return fd; + + if (prog_type == HID_BPF_PROG_TYPE_RDESC_FIXUP) { + err = hid_bpf_reconnect(hdev); + if (err) { + close_fd(fd); + return err; + } + } + + return fd; +} + /** * hid_bpf_attach_prog - Attach the given @prog_fd to the given HID device * @@ -257,18 +290,13 @@ noinline int hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags) { struct hid_device *hdev; + struct bpf_prog *prog; struct device *dev; - int fd, err, prog_type = hid_bpf_get_prog_attach_type(prog_fd); + int err, fd; if (!hid_bpf_ops) return -EINVAL; - if (prog_type < 0) - return prog_type; - - if (prog_type >= HID_BPF_PROG_TYPE_MAX) - return -EINVAL; - if ((flags & ~HID_BPF_FLAG_MASK)) return -EINVAL; @@ -278,25 +306,29 @@ hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags) hdev = to_hid_device(dev); - if (prog_type == HID_BPF_PROG_TYPE_DEVICE_EVENT) { - err = hid_bpf_allocate_event_data(hdev); - if (err) - return err; + /* + * take a ref on the prog itself, it will be released + * on errors or when it'll be detached + */ + prog = bpf_prog_get(prog_fd); + if (IS_ERR(prog)) { + err = PTR_ERR(prog); + goto out_dev_put; } - fd = __hid_bpf_attach_prog(hdev, prog_type, prog_fd, flags); - if (fd < 0) - return fd; - - if (prog_type == HID_BPF_PROG_TYPE_RDESC_FIXUP) { - err = hid_bpf_reconnect(hdev); - if (err) { - close_fd(fd); - return err; - } + fd = do_hid_bpf_attach_prog(hdev, prog_fd, prog, flags); + if (fd < 0) { + err = fd; + goto out_prog_put; } return fd; + + out_prog_put: + bpf_prog_put(prog); + out_dev_put: + put_device(dev); + return err; } /** @@ -323,8 +355,10 @@ hid_bpf_allocate_context(unsigned int hid_id) hdev = to_hid_device(dev); ctx_kern = kzalloc(sizeof(*ctx_kern), GFP_KERNEL); - if (!ctx_kern) + if (!ctx_kern) { + put_device(dev); return NULL; + } ctx_kern->ctx.hid = hdev; @@ -341,10 +375,15 @@ noinline void hid_bpf_release_context(struct hid_bpf_ctx *ctx) { struct hid_bpf_ctx_kern *ctx_kern; + struct hid_device *hid; ctx_kern = container_of(ctx, struct hid_bpf_ctx_kern, ctx); + hid = (struct hid_device *)ctx_kern->ctx.hid; /* ignore const */ kfree(ctx_kern); + + /* get_device() is called by bus_find_device() */ + put_device(&hid->dev); } /** diff --git a/drivers/hid/bpf/hid_bpf_dispatch.h b/drivers/hid/bpf/hid_bpf_dispatch.h index 63dfc8605cd21..fbe0639d09f26 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.h +++ b/drivers/hid/bpf/hid_bpf_dispatch.h @@ -12,9 +12,9 @@ struct hid_bpf_ctx_kern { int hid_bpf_preload_skel(void); void hid_bpf_free_links_and_skel(void); -int hid_bpf_get_prog_attach_type(int prog_fd); +int hid_bpf_get_prog_attach_type(struct bpf_prog *prog); int __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type, int prog_fd, - __u32 flags); + struct bpf_prog *prog, __u32 flags); void __hid_bpf_destroy_device(struct hid_device *hdev); int hid_bpf_prog_run(struct hid_device *hdev, enum hid_bpf_prog_type type, struct hid_bpf_ctx_kern *ctx_kern); diff --git a/drivers/hid/bpf/hid_bpf_jmp_table.c b/drivers/hid/bpf/hid_bpf_jmp_table.c index eca34b7372f95..aa8e1c79cdf55 100644 --- a/drivers/hid/bpf/hid_bpf_jmp_table.c +++ b/drivers/hid/bpf/hid_bpf_jmp_table.c @@ -196,6 +196,7 @@ static void __hid_bpf_do_release_prog(int map_fd, unsigned int idx) static void hid_bpf_release_progs(struct work_struct *work) { int i, j, n, map_fd = -1; + bool hdev_destroyed; if (!jmp_table.map) return; @@ -220,6 +221,12 @@ static void hid_bpf_release_progs(struct work_struct *work) if (entry->hdev) { hdev = entry->hdev; type = entry->type; + /* + * hdev is still valid, even if we are called after hid_destroy_device(): + * when hid_bpf_attach() gets called, it takes a ref on the dev through + * bus_find_device() + */ + hdev_destroyed = hdev->bpf.destroyed; hid_bpf_populate_hdev(hdev, type); @@ -232,12 +239,19 @@ static void hid_bpf_release_progs(struct work_struct *work) if (test_bit(next->idx, jmp_table.enabled)) continue; - if (next->hdev == hdev && next->type == type) + if (next->hdev == hdev && next->type == type) { + /* + * clear the hdev reference and decrement the device ref + * that was taken during bus_find_device() while calling + * hid_bpf_attach() + */ next->hdev = NULL; + put_device(&hdev->dev); + } } - /* if type was rdesc fixup, reconnect device */ - if (type == HID_BPF_PROG_TYPE_RDESC_FIXUP) + /* if type was rdesc fixup and the device is not gone, reconnect device */ + if (type == HID_BPF_PROG_TYPE_RDESC_FIXUP && !hdev_destroyed) hid_bpf_reconnect(hdev); } } @@ -333,15 +347,10 @@ static int hid_bpf_insert_prog(int prog_fd, struct bpf_prog *prog) return err; } -int hid_bpf_get_prog_attach_type(int prog_fd) +int hid_bpf_get_prog_attach_type(struct bpf_prog *prog) { - struct bpf_prog *prog = NULL; - int i; int prog_type = HID_BPF_PROG_TYPE_UNDEF; - - prog = bpf_prog_get(prog_fd); - if (IS_ERR(prog)) - return PTR_ERR(prog); + int i; for (i = 0; i < HID_BPF_PROG_TYPE_MAX; i++) { if (hid_bpf_btf_ids[i] == prog->aux->attach_btf_id) { @@ -350,8 +359,6 @@ int hid_bpf_get_prog_attach_type(int prog_fd) } } - bpf_prog_put(prog); - return prog_type; } @@ -388,19 +395,13 @@ static const struct bpf_link_ops hid_bpf_link_lops = { /* called from syscall */ noinline int __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type, - int prog_fd, __u32 flags) + int prog_fd, struct bpf_prog *prog, __u32 flags) { struct bpf_link_primer link_primer; struct hid_bpf_link *link; - struct bpf_prog *prog = NULL; struct hid_bpf_prog_entry *prog_entry; int cnt, err = -EINVAL, prog_table_idx = -1; - /* take a ref on the prog itself */ - prog = bpf_prog_get(prog_fd); - if (IS_ERR(prog)) - return PTR_ERR(prog); - mutex_lock(&hid_bpf_attach_lock); link = kzalloc(sizeof(*link), GFP_USER); @@ -467,7 +468,6 @@ __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type, err_unlock: mutex_unlock(&hid_bpf_attach_lock); - bpf_prog_put(prog); kfree(link); return err; diff --git a/drivers/hid/i2c-hid/i2c-hid-of.c b/drivers/hid/i2c-hid/i2c-hid-of.c index c4e1fa0273c84..8be4d576da773 100644 --- a/drivers/hid/i2c-hid/i2c-hid-of.c +++ b/drivers/hid/i2c-hid/i2c-hid-of.c @@ -87,6 +87,7 @@ static int i2c_hid_of_probe(struct i2c_client *client) if (!ihid_of) return -ENOMEM; + ihid_of->client = client; ihid_of->ops.power_up = i2c_hid_of_power_up; ihid_of->ops.power_down = i2c_hid_of_power_down; diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 3f704b8072e8a..7659c98d94292 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2080,7 +2080,7 @@ static int wacom_allocate_inputs(struct wacom *wacom) return 0; } -static int wacom_register_inputs(struct wacom *wacom) +static int wacom_setup_inputs(struct wacom *wacom) { struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; struct wacom_wac *wacom_wac = &(wacom->wacom_wac); @@ -2099,10 +2099,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pen_input_dev); wacom_wac->pen_input = NULL; pen_input_dev = NULL; - } else { - error = input_register_device(pen_input_dev); - if (error) - goto fail; } error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac); @@ -2111,10 +2107,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(touch_input_dev); wacom_wac->touch_input = NULL; touch_input_dev = NULL; - } else { - error = input_register_device(touch_input_dev); - if (error) - goto fail; } error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac); @@ -2123,7 +2115,34 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pad_input_dev); wacom_wac->pad_input = NULL; pad_input_dev = NULL; - } else { + } + + return 0; +} + +static int wacom_register_inputs(struct wacom *wacom) +{ + struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; + struct wacom_wac *wacom_wac = &(wacom->wacom_wac); + int error = 0; + + pen_input_dev = wacom_wac->pen_input; + touch_input_dev = wacom_wac->touch_input; + pad_input_dev = wacom_wac->pad_input; + + if (pen_input_dev) { + error = input_register_device(pen_input_dev); + if (error) + goto fail; + } + + if (touch_input_dev) { + error = input_register_device(touch_input_dev); + if (error) + goto fail; + } + + if (pad_input_dev) { error = input_register_device(pad_input_dev); if (error) goto fail; @@ -2376,6 +2395,20 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) if (error) goto fail; + error = wacom_setup_inputs(wacom); + if (error) + goto fail; + + if (features->type == HID_GENERIC) + connect_mask |= HID_CONNECT_DRIVER; + + /* Regular HID work starts now */ + error = hid_hw_start(hdev, connect_mask); + if (error) { + hid_err(hdev, "hw start failed\n"); + goto fail; + } + error = wacom_register_inputs(wacom); if (error) goto fail; @@ -2390,16 +2423,6 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail; } - if (features->type == HID_GENERIC) - connect_mask |= HID_CONNECT_DRIVER; - - /* Regular HID work starts now */ - error = hid_hw_start(hdev, connect_mask); - if (error) { - hid_err(hdev, "hw start failed\n"); - goto fail; - } - if (!wireless) { /* Note that if query fails it is not a hard failure */ wacom_query_tablet_data(wacom); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 8289ce7637044..002cbaa16bd16 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2574,7 +2574,14 @@ static void wacom_wac_pen_report(struct hid_device *hdev, wacom_wac->hid_data.tipswitch); input_report_key(input, wacom_wac->tool[0], sense); if (wacom_wac->serial[0]) { - input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]); + /* + * xf86-input-wacom does not accept a serial number + * of '0'. Report the low 32 bits if possible, but + * if they are zero, report the upper ones instead. + */ + __u32 serial_lo = wacom_wac->serial[0] & 0xFFFFFFFFu; + __u32 serial_hi = wacom_wac->serial[0] >> 32; + input_event(input, EV_MSC, MSC_SERIAL, (int)(serial_lo ? serial_lo : serial_hi)); input_report_abs(input, ABS_MISC, sense ? id : 0); } diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index af56fe2c75c09..9be9fdb07f3dc 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -90,10 +90,8 @@ obj-$(CONFIG_I2C_NPCM) += i2c-npcm7xx.o obj-$(CONFIG_I2C_OCORES) += i2c-ocores.o obj-$(CONFIG_I2C_OMAP) += i2c-omap.o obj-$(CONFIG_I2C_OWL) += i2c-owl.o -i2c-pasemi-objs := i2c-pasemi-core.o i2c-pasemi-pci.o -obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi.o -i2c-apple-objs := i2c-pasemi-core.o i2c-pasemi-platform.o -obj-$(CONFIG_I2C_APPLE) += i2c-apple.o +obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi-core.o i2c-pasemi-pci.o +obj-$(CONFIG_I2C_APPLE) += i2c-pasemi-core.o i2c-pasemi-platform.o obj-$(CONFIG_I2C_PCA_PLATFORM) += i2c-pca-platform.o obj-$(CONFIG_I2C_PNX) += i2c-pnx.o obj-$(CONFIG_I2C_PXA) += i2c-pxa.o diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index a87e3c15e5fc6..f1c82b2016f30 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -500,11 +500,10 @@ static int i801_block_transaction_by_block(struct i801_priv *priv, /* Set block buffer mode */ outb_p(inb_p(SMBAUXCTL(priv)) | SMBAUXCTL_E32B, SMBAUXCTL(priv)); - inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ - if (read_write == I2C_SMBUS_WRITE) { len = data->block[0]; outb_p(len, SMBHSTDAT0(priv)); + inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ for (i = 0; i < len; i++) outb_p(data->block[i+1], SMBBLKDAT(priv)); } @@ -522,6 +521,7 @@ static int i801_block_transaction_by_block(struct i801_priv *priv, } data->block[0] = len; + inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ for (i = 0; i < len; i++) data->block[i + 1] = inb_p(SMBBLKDAT(priv)); } diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 7d54a9f34c74b..bd8becbdeeb28 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -369,6 +369,7 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) return 0; } +EXPORT_SYMBOL_GPL(pasemi_i2c_common_probe); irqreturn_t pasemi_irq_handler(int irq, void *dev_id) { @@ -378,3 +379,8 @@ irqreturn_t pasemi_irq_handler(int irq, void *dev_id) complete(&smbus->irq_completion); return IRQ_HANDLED; } +EXPORT_SYMBOL_GPL(pasemi_irq_handler); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Olof Johansson "); +MODULE_DESCRIPTION("PA Semi PWRficient SMBus driver"); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 0a9d389df301b..5cc32a465f12e 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -613,20 +613,20 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i peripheral.addr = msgs[i].addr; + ret = geni_i2c_gpi(gi2c, &msgs[i], &config, + &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c); + if (ret) + goto err; + if (msgs[i].flags & I2C_M_RD) { ret = geni_i2c_gpi(gi2c, &msgs[i], &config, &rx_addr, &rx_buf, I2C_READ, gi2c->rx_c); if (ret) goto err; - } - - ret = geni_i2c_gpi(gi2c, &msgs[i], &config, - &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c); - if (ret) - goto err; - if (msgs[i].flags & I2C_M_RD) dma_async_issue_pending(gi2c->rx_c); + } + dma_async_issue_pending(gi2c->tx_c); timeout = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT); diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index b6b45d359f287..5c5876b4d3b62 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -219,10 +219,12 @@ config BMA400 config BMA400_I2C tristate + select REGMAP_I2C depends on BMA400 config BMA400_SPI tristate + select REGMAP_SPI depends on BMA400 config BMC150_ACCEL diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c index 5a5dd5e87ffc4..e650ebd167b03 100644 --- a/drivers/iio/adc/ad4130.c +++ b/drivers/iio/adc/ad4130.c @@ -1826,7 +1826,7 @@ static int ad4130_setup_int_clk(struct ad4130_state *st) { struct device *dev = &st->spi->dev; struct device_node *of_node = dev_of_node(dev); - struct clk_init_data init; + struct clk_init_data init = {}; const char *clk_name; struct clk *clk; int ret; @@ -1900,10 +1900,14 @@ static int ad4130_setup(struct iio_dev *indio_dev) return ret; /* - * Configure all GPIOs for output. If configured, the interrupt function - * of P2 takes priority over the GPIO out function. + * Configure unused GPIOs for output. If configured, the interrupt + * function of P2 takes priority over the GPIO out function. */ - val = AD4130_IO_CONTROL_GPIO_CTRL_MASK; + val = 0; + for (i = 0; i < AD4130_MAX_GPIOS; i++) + if (st->pins_fn[i + AD4130_AIN2_P1] == AD4130_PIN_FN_NONE) + val |= FIELD_PREP(AD4130_IO_CONTROL_GPIO_CTRL_MASK, BIT(i)); + val |= FIELD_PREP(AD4130_IO_CONTROL_INT_PIN_SEL_MASK, st->int_pin_sel); ret = regmap_write(st->regmap, AD4130_IO_CONTROL_REG, val); diff --git a/drivers/iio/imu/bno055/Kconfig b/drivers/iio/imu/bno055/Kconfig index 83e53acfbe880..c7f5866a177d9 100644 --- a/drivers/iio/imu/bno055/Kconfig +++ b/drivers/iio/imu/bno055/Kconfig @@ -8,6 +8,7 @@ config BOSCH_BNO055 config BOSCH_BNO055_SERIAL tristate "Bosch BNO055 attached via UART" depends on SERIAL_DEV_BUS + select REGMAP select BOSCH_BNO055 help Enable this to support Bosch BNO055 IMUs attached via UART. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index d752e9c0499b9..feec93adb0651 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1577,10 +1577,13 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev) ret = iio_device_register_sysfs_group(indio_dev, &iio_dev_opaque->chan_attr_group); if (ret) - goto error_clear_attrs; + goto error_free_chan_attrs; return 0; +error_free_chan_attrs: + kfree(iio_dev_opaque->chan_attr_group.attrs); + iio_dev_opaque->chan_attr_group.attrs = NULL; error_clear_attrs: iio_free_chan_devattr_list(&iio_dev_opaque->channel_attr_list); diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c index eb1aedad7edcc..3c8b9aab5da7c 100644 --- a/drivers/iio/light/hid-sensor-als.c +++ b/drivers/iio/light/hid-sensor-als.c @@ -226,6 +226,7 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev, case HID_USAGE_SENSOR_TIME_TIMESTAMP: als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes, *(s64 *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c index 69938204456f8..42b70cd42b393 100644 --- a/drivers/iio/magnetometer/rm3100-core.c +++ b/drivers/iio/magnetometer/rm3100-core.c @@ -530,6 +530,7 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq) struct rm3100_data *data; unsigned int tmp; int ret; + int samp_rate_index; indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); if (!indio_dev) @@ -586,9 +587,14 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq) ret = regmap_read(regmap, RM3100_REG_TMRC, &tmp); if (ret < 0) return ret; + + samp_rate_index = tmp - RM3100_TMRC_OFFSET; + if (samp_rate_index < 0 || samp_rate_index >= RM3100_SAMP_NUM) { + dev_err(dev, "The value read from RM3100_REG_TMRC is invalid!\n"); + return -EINVAL; + } /* Initializing max wait time, which is double conversion time. */ - data->conversion_time = rm3100_samp_rates[tmp - RM3100_TMRC_OFFSET][2] - * 2; + data->conversion_time = rm3100_samp_rates[samp_rate_index][2] * 2; /* Cycle count values may not be what we want. */ if ((tmp - RM3100_TMRC_OFFSET) == 0) diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c index 1dff9bb7c4e90..967de99c1bb97 100644 --- a/drivers/iio/pressure/bmp280-spi.c +++ b/drivers/iio/pressure/bmp280-spi.c @@ -91,6 +91,7 @@ static const struct of_device_id bmp280_of_spi_match[] = { MODULE_DEVICE_TABLE(of, bmp280_of_spi_match); static const struct spi_device_id bmp280_spi_id[] = { + { "bmp085", (kernel_ulong_t)&bmp180_chip_info }, { "bmp180", (kernel_ulong_t)&bmp180_chip_info }, { "bmp181", (kernel_ulong_t)&bmp180_chip_info }, { "bmp280", (kernel_ulong_t)&bmp280_chip_info }, diff --git a/drivers/interconnect/qcom/sc8180x.c b/drivers/interconnect/qcom/sc8180x.c index bdd3471d4ac89..a741badaa966e 100644 --- a/drivers/interconnect/qcom/sc8180x.c +++ b/drivers/interconnect/qcom/sc8180x.c @@ -1372,6 +1372,7 @@ static struct qcom_icc_bcm bcm_mm0 = { static struct qcom_icc_bcm bcm_co0 = { .name = "CO0", + .keepalive = true, .num_nodes = 1, .nodes = { &slv_qns_cdsp_mem_noc } }; diff --git a/drivers/interconnect/qcom/sm8550.c b/drivers/interconnect/qcom/sm8550.c index a10c8b6549ee6..16b2dfd794b40 100644 --- a/drivers/interconnect/qcom/sm8550.c +++ b/drivers/interconnect/qcom/sm8550.c @@ -2223,6 +2223,7 @@ static struct platform_driver qnoc_driver = { .driver = { .name = "qnoc-sm8550", .of_match_table = qnoc_of_match, + .sync_state = icc_sync_state, }, }; diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index 5559c943f03f9..2b0b3175cea06 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -2,7 +2,7 @@ /* * Generic Broadcom Set Top Box Level 2 Interrupt controller driver * - * Copyright (C) 2014-2017 Broadcom + * Copyright (C) 2014-2024 Broadcom */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -112,6 +112,9 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc) generic_handle_domain_irq(b->domain, irq); } while (status); out: + /* Don't ack parent before all device writes are done */ + wmb(); + chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 9a7a74239eabb..3632c92cd183c 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -207,6 +207,11 @@ static bool require_its_list_vmovp(struct its_vm *vm, struct its_node *its) return (gic_rdists->has_rvpeid || vm->vlpi_count[its->list_nr]); } +static bool rdists_support_shareable(void) +{ + return !(gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE); +} + static u16 get_its_list(struct its_vm *vm) { struct its_node *its; @@ -2710,10 +2715,12 @@ static u64 inherit_vpe_l1_table_from_its(void) break; } val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12); - val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK, - FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser)); - val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK, - FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser)); + if (rdists_support_shareable()) { + val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK, + FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser)); + val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK, + FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser)); + } val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1); return val; @@ -2936,8 +2943,10 @@ static int allocate_vpe_l1_table(void) WARN_ON(!IS_ALIGNED(pa, psz)); val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12); - val |= GICR_VPROPBASER_RaWb; - val |= GICR_VPROPBASER_InnerShareable; + if (rdists_support_shareable()) { + val |= GICR_VPROPBASER_RaWb; + val |= GICR_VPROPBASER_InnerShareable; + } val |= GICR_VPROPBASER_4_1_Z; val |= GICR_VPROPBASER_4_1_VALID; @@ -3126,7 +3135,7 @@ static void its_cpu_init_lpis(void) gicr_write_propbaser(val, rbase + GICR_PROPBASER); tmp = gicr_read_propbaser(rbase + GICR_PROPBASER); - if (gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE) + if (!rdists_support_shareable()) tmp &= ~GICR_PROPBASER_SHAREABILITY_MASK; if ((tmp ^ val) & GICR_PROPBASER_SHAREABILITY_MASK) { @@ -3153,7 +3162,7 @@ static void its_cpu_init_lpis(void) gicr_write_pendbaser(val, rbase + GICR_PENDBASER); tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER); - if (gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE) + if (!rdists_support_shareable()) tmp &= ~GICR_PENDBASER_SHAREABILITY_MASK; if (!(tmp & GICR_PENDBASER_SHAREABILITY_MASK)) { @@ -3817,8 +3826,9 @@ static int its_vpe_set_affinity(struct irq_data *d, bool force) { struct its_vpe *vpe = irq_data_get_irq_chip_data(d); - int from, cpu = cpumask_first(mask_val); + struct cpumask common, *table_mask; unsigned long flags; + int from, cpu; /* * Changing affinity is mega expensive, so let's be as lazy as @@ -3834,19 +3844,22 @@ static int its_vpe_set_affinity(struct irq_data *d, * taken on any vLPI handling path that evaluates vpe->col_idx. */ from = vpe_to_cpuid_lock(vpe, &flags); - if (from == cpu) - goto out; - - vpe->col_idx = cpu; + table_mask = gic_data_rdist_cpu(from)->vpe_table_mask; /* - * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD - * is sharing its VPE table with the current one. + * If we are offered another CPU in the same GICv4.1 ITS + * affinity, pick this one. Otherwise, any CPU will do. */ - if (gic_data_rdist_cpu(cpu)->vpe_table_mask && - cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask)) + if (table_mask && cpumask_and(&common, mask_val, table_mask)) + cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common); + else + cpu = cpumask_first(mask_val); + + if (from == cpu) goto out; + vpe->col_idx = cpu; + its_send_vmovp(vpe); its_vpe_db_proxy_move(vpe, from, cpu); @@ -3880,14 +3893,18 @@ static void its_vpe_schedule(struct its_vpe *vpe) val = virt_to_phys(page_address(vpe->its_vm->vprop_page)) & GENMASK_ULL(51, 12); val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; - val |= GICR_VPROPBASER_RaWb; - val |= GICR_VPROPBASER_InnerShareable; + if (rdists_support_shareable()) { + val |= GICR_VPROPBASER_RaWb; + val |= GICR_VPROPBASER_InnerShareable; + } gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); val = virt_to_phys(page_address(vpe->vpt_page)) & GENMASK_ULL(51, 16); - val |= GICR_VPENDBASER_RaWaWb; - val |= GICR_VPENDBASER_InnerShareable; + if (rdists_support_shareable()) { + val |= GICR_VPENDBASER_RaWaWb; + val |= GICR_VPENDBASER_InnerShareable; + } /* * There is no good way of finding out if the pending table is * empty as we can race against the doorbell interrupt very @@ -5078,6 +5095,8 @@ static int __init its_probe_one(struct its_node *its) u32 ctlr; int err; + its_enable_quirks(its); + if (is_v4(its)) { if (!(its->typer & GITS_TYPER_VMOVP)) { err = its_compute_its_list_map(its); @@ -5429,7 +5448,6 @@ static int __init its_of_probe(struct device_node *node) if (!its) return -ENOMEM; - its_enable_quirks(its); err = its_probe_one(its); if (err) { its_node_destroy(its); diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index 1623cd7791752..b3736bdd4b9f2 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -241,7 +241,7 @@ static int eiointc_domain_alloc(struct irq_domain *domain, unsigned int virq, int ret; unsigned int i, type; unsigned long hwirq = 0; - struct eiointc *priv = domain->host_data; + struct eiointc_priv *priv = domain->host_data; ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type); if (ret) diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 095b9b49aa825..e6757a30dccad 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -22,6 +22,8 @@ #include "dm-ima.h" #define DM_RESERVED_MAX_IOS 1024 +#define DM_MAX_TARGETS 1048576 +#define DM_MAX_TARGET_PARAMS 1024 struct dm_io; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 17ffbf7fbe73e..1a539ec81bacc 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -73,10 +73,8 @@ struct dm_crypt_io { struct bio *base_bio; u8 *integrity_metadata; bool integrity_metadata_from_pool:1; - bool in_tasklet:1; struct work_struct work; - struct tasklet_struct tasklet; struct convert_context ctx; @@ -1768,7 +1766,6 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc, io->ctx.r.req = NULL; io->integrity_metadata = NULL; io->integrity_metadata_from_pool = false; - io->in_tasklet = false; atomic_set(&io->io_pending, 0); } @@ -1777,13 +1774,6 @@ static void crypt_inc_pending(struct dm_crypt_io *io) atomic_inc(&io->io_pending); } -static void kcryptd_io_bio_endio(struct work_struct *work) -{ - struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); - - bio_endio(io->base_bio); -} - /* * One of the bios was finished. Check for completion of * the whole request and correctly clean up the buffer. @@ -1807,20 +1797,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io) base_bio->bi_status = error; - /* - * If we are running this function from our tasklet, - * we can't call bio_endio() here, because it will call - * clone_endio() from dm.c, which in turn will - * free the current struct dm_crypt_io structure with - * our tasklet. In this case we need to delay bio_endio() - * execution to after the tasklet is done and dequeued. - */ - if (io->in_tasklet) { - INIT_WORK(&io->work, kcryptd_io_bio_endio); - queue_work(cc->io_queue, &io->work); - return; - } - bio_endio(base_bio); } @@ -2252,11 +2228,6 @@ static void kcryptd_crypt(struct work_struct *work) kcryptd_crypt_write_convert(io); } -static void kcryptd_crypt_tasklet(unsigned long work) -{ - kcryptd_crypt((struct work_struct *)work); -} - static void kcryptd_queue_crypt(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; @@ -2268,15 +2239,10 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io) * irqs_disabled(): the kernel may run some IO completion from the idle thread, but * it is being executed with irqs disabled. */ - if (in_hardirq() || irqs_disabled()) { - io->in_tasklet = true; - tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work); - tasklet_schedule(&io->tasklet); + if (!(in_hardirq() || irqs_disabled())) { + kcryptd_crypt(&io->work); return; } - - kcryptd_crypt(&io->work); - return; } INIT_WORK(&io->work, kcryptd_crypt); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 21ebb6c39394b..3b8b2e886cf67 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1941,7 +1941,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern minimum_data_size - sizeof(param_kernel->version))) return -EFAULT; - if (param_kernel->data_size < minimum_data_size) { + if (unlikely(param_kernel->data_size < minimum_data_size) || + unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) { DMERR("Invalid data size in the ioctl structure: %u", param_kernel->data_size); return -EINVAL; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 37b48f63ae6a5..fd84e06670e8d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -129,7 +129,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num) int dm_table_create(struct dm_table **result, blk_mode_t mode, unsigned int num_targets, struct mapped_device *md) { - struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); + struct dm_table *t; + + if (num_targets > DM_MAX_TARGETS) + return -EOVERFLOW; + + t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) return -ENOMEM; @@ -144,7 +149,7 @@ int dm_table_create(struct dm_table **result, blk_mode_t mode, if (!num_targets) { kfree(t); - return -ENOMEM; + return -EOVERFLOW; } if (alloc_targets(t, num_targets)) { diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 14e58ae705218..82662f5769c4a 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -645,23 +645,6 @@ static void verity_work(struct work_struct *w) verity_finish_io(io, errno_to_blk_status(verity_verify_io(io))); } -static void verity_tasklet(unsigned long data) -{ - struct dm_verity_io *io = (struct dm_verity_io *)data; - int err; - - io->in_tasklet = true; - err = verity_verify_io(io); - if (err == -EAGAIN || err == -ENOMEM) { - /* fallback to retrying with work-queue */ - INIT_WORK(&io->work, verity_work); - queue_work(io->v->verify_wq, &io->work); - return; - } - - verity_finish_io(io, errno_to_blk_status(err)); -} - static void verity_end_io(struct bio *bio) { struct dm_verity_io *io = bio->bi_private; @@ -674,13 +657,8 @@ static void verity_end_io(struct bio *bio) return; } - if (static_branch_unlikely(&use_tasklet_enabled) && io->v->use_tasklet) { - tasklet_init(&io->tasklet, verity_tasklet, (unsigned long)io); - tasklet_schedule(&io->tasklet); - } else { - INIT_WORK(&io->work, verity_work); - queue_work(io->v->verify_wq, &io->work); - } + INIT_WORK(&io->work, verity_work); + queue_work(io->v->verify_wq, &io->work); } /* diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index f9d522c870e61..f3f6070084196 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -83,7 +83,6 @@ struct dm_verity_io { struct bvec_iter iter; struct work_struct work; - struct tasklet_struct tasklet; /* * Three variably-size fields follow this struct: diff --git a/drivers/md/md.c b/drivers/md/md.c index dccf270aa1b4b..108590041db64 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -940,9 +940,10 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, return; bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev, - 1, - REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA, - GFP_NOIO, &mddev->sync_set); + 1, + REQ_OP_WRITE | REQ_SYNC | REQ_IDLE | REQ_META + | REQ_PREFLUSH | REQ_FUA, + GFP_NOIO, &mddev->sync_set); atomic_inc(&rdev->nr_pending); diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c index f96f821a7b50d..acc559652d6eb 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c @@ -559,7 +559,7 @@ static int rkisp1_probe(struct platform_device *pdev) rkisp1->irqs[il] = irq; } - ret = devm_request_irq(dev, irq, info->isrs[i].isr, 0, + ret = devm_request_irq(dev, irq, info->isrs[i].isr, IRQF_SHARED, dev_driver_string(dev), dev); if (ret) { dev_err(dev, "request irq failed: %d\n", ret); diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fe17c7f98e810..52d82cbe7685f 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -253,7 +253,7 @@ int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) if (attr->attach_flags) return -EINVAL; - rcdev = rc_dev_get_from_fd(attr->target_fd); + rcdev = rc_dev_get_from_fd(attr->target_fd, true); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); @@ -278,7 +278,7 @@ int lirc_prog_detach(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - rcdev = rc_dev_get_from_fd(attr->target_fd); + rcdev = rc_dev_get_from_fd(attr->target_fd, true); if (IS_ERR(rcdev)) { bpf_prog_put(prog); return PTR_ERR(rcdev); @@ -303,7 +303,7 @@ int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->query.query_flags) return -EINVAL; - rcdev = rc_dev_get_from_fd(attr->query.target_fd); + rcdev = rc_dev_get_from_fd(attr->query.target_fd, false); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c index 1968067092594..69e630d85262f 100644 --- a/drivers/media/rc/ir_toy.c +++ b/drivers/media/rc/ir_toy.c @@ -332,6 +332,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) sizeof(COMMAND_SMODE_EXIT), STATE_COMMAND_NO_RESP); if (err) { dev_err(irtoy->dev, "exit sample mode: %d\n", err); + kfree(buf); return err; } @@ -339,6 +340,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND); if (err) { dev_err(irtoy->dev, "enter sample mode: %d\n", err); + kfree(buf); return err; } diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index a537734832c50..caad59f76793f 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -814,7 +814,7 @@ void __exit lirc_dev_exit(void) unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX); } -struct rc_dev *rc_dev_get_from_fd(int fd) +struct rc_dev *rc_dev_get_from_fd(int fd, bool write) { struct fd f = fdget(fd); struct lirc_fh *fh; @@ -828,6 +828,9 @@ struct rc_dev *rc_dev_get_from_fd(int fd) return ERR_PTR(-EINVAL); } + if (write && !(f.file->f_mode & FMODE_WRITE)) + return ERR_PTR(-EPERM); + fh = f.file->private_data; dev = fh->rc; diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h index ef1e95e1af7fc..7df949fc65e2b 100644 --- a/drivers/media/rc/rc-core-priv.h +++ b/drivers/media/rc/rc-core-priv.h @@ -325,7 +325,7 @@ void lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev); void lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc); int lirc_register(struct rc_dev *dev); void lirc_unregister(struct rc_dev *dev); -struct rc_dev *rc_dev_get_from_fd(int fd); +struct rc_dev *rc_dev_get_from_fd(int fd, bool write); #else static inline int lirc_dev_init(void) { return 0; } static inline void lirc_dev_exit(void) {} diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 1c6c62a7f7f55..03319a1fa97fd 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -2191,7 +2191,7 @@ static int fastrpc_cb_remove(struct platform_device *pdev) int i; spin_lock_irqsave(&cctx->lock, flags); - for (i = 1; i < FASTRPC_MAX_SESSIONS; i++) { + for (i = 0; i < FASTRPC_MAX_SESSIONS; i++) { if (cctx->session[i].sid == sess->sid) { cctx->session[i].valid = false; cctx->sesscount--; diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 2a2d949a9344e..39f45c2b6de8a 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -75,11 +75,15 @@ EXPORT_SYMBOL(mmc_gpio_set_cd_irq); int mmc_gpio_get_ro(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; + int cansleep; if (!ctx || !ctx->ro_gpio) return -ENOSYS; - return gpiod_get_value_cansleep(ctx->ro_gpio); + cansleep = gpiod_cansleep(ctx->ro_gpio); + return cansleep ? + gpiod_get_value_cansleep(ctx->ro_gpio) : + gpiod_get_value(ctx->ro_gpio); } EXPORT_SYMBOL(mmc_gpio_get_ro); diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c index 7bfee28116af1..d4a02184784a3 100644 --- a/drivers/mmc/host/sdhci-pci-o2micro.c +++ b/drivers/mmc/host/sdhci-pci-o2micro.c @@ -693,6 +693,35 @@ static int sdhci_pci_o2_init_sd_express(struct mmc_host *mmc, struct mmc_ios *io return 0; } +static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode, unsigned short vdd) +{ + struct sdhci_pci_chip *chip; + struct sdhci_pci_slot *slot = sdhci_priv(host); + u32 scratch_32 = 0; + u8 scratch_8 = 0; + + chip = slot->chip; + + if (mode == MMC_POWER_OFF) { + /* UnLock WP */ + pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); + scratch_8 &= 0x7f; + pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); + + /* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */ + pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32); + scratch_32 &= ~(O2_SD_SEL_DLL); + pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32); + + /* Lock WP */ + pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); + scratch_8 |= 0x80; + pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); + } + + sdhci_set_power(host, mode, vdd); +} + static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot) { struct sdhci_pci_chip *chip; @@ -1051,6 +1080,7 @@ static const struct sdhci_ops sdhci_pci_o2_ops = { .set_bus_width = sdhci_set_bus_width, .reset = sdhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_power = sdhci_pci_o2_set_power, }; const struct sdhci_pci_fixes sdhci_o2 = { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8e6cc0e133b7f..6cf7f364704e8 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1819,6 +1819,8 @@ void bond_xdp_set_features(struct net_device *bond_dev) bond_for_each_slave(bond, slave, iter) val &= slave->dev->xdp_features; + val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY; + xdp_set_features_flag(bond_dev, val); } @@ -5934,9 +5936,6 @@ void bond_setup(struct net_device *bond_dev) if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_dev->features |= BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ - - if (bond_xdp_check(bond)) - bond_dev->xdp_features = NETDEV_XDP_ACT_MASK; } /* Destroy a bonding device. diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 036d85ef07f5b..dfdc039d92a6c 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -346,7 +346,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], /* Neither of TDC parameters nor TDC flags are * provided: do calculation */ - can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, + can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt, &priv->ctrlmode, priv->ctrlmode_supported); } /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly * turned off. TDC is disabled: do nothing diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index dc7f9b99f409f..5ad51271a5349 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3545,7 +3545,7 @@ static int mv88e6xxx_mdio_read_c45(struct mii_bus *bus, int phy, int devad, int err; if (!chip->info->ops->phy_read_c45) - return -EOPNOTSUPP; + return 0xffff; mv88e6xxx_reg_lock(chip); err = chip->info->ops->phy_read_c45(chip, bus, phy, devad, reg, &val); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index aad39ebff4aba..9d37c0374c75e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5351,7 +5351,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) { int v, ret = 0; - for (v = 0; v < pf->hw.func_caps.num_vsis; v++) { + for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v]) { ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]); if (ret) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index cc4c53470db2c..082c099209995 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2848,6 +2848,24 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg) (u8 *)&stats, sizeof(stats)); } +/** + * i40e_can_vf_change_mac + * @vf: pointer to the VF info + * + * Return true if the VF is allowed to change its MAC filters, false otherwise + */ +static bool i40e_can_vf_change_mac(struct i40e_vf *vf) +{ + /* If the VF MAC address has been set administratively (via the + * ndo_set_vf_mac command), then deny permission to the VF to + * add/delete unicast MAC addresses, unless the VF is trusted + */ + if (vf->pf_set_mac && !vf->trusted) + return false; + + return true; +} + #define I40E_MAX_MACVLAN_PER_HW 3072 #define I40E_MAX_MACVLAN_PER_PF(num_ports) (I40E_MAX_MACVLAN_PER_HW / \ (num_ports)) @@ -2907,8 +2925,8 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, * The VF may request to set the MAC address filter already * assigned to it so do not return an error in that case. */ - if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) && - !is_multicast_ether_addr(addr) && vf->pf_set_mac && + if (!i40e_can_vf_change_mac(vf) && + !is_multicast_ether_addr(addr) && !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); @@ -3114,19 +3132,29 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) ret = -EINVAL; goto error_param; } - if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr)) - was_unimac_deleted = true; } vsi = pf->vsi[vf->lan_vsi_idx]; spin_lock_bh(&vsi->mac_filter_hash_lock); /* delete addresses from the list */ - for (i = 0; i < al->num_elements; i++) + for (i = 0; i < al->num_elements; i++) { + const u8 *addr = al->list[i].addr; + + /* Allow to delete VF primary MAC only if it was not set + * administratively by PF or if VF is trusted. + */ + if (ether_addr_equal(addr, vf->default_lan_addr.addr) && + i40e_can_vf_change_mac(vf)) + was_unimac_deleted = true; + else + continue; + if (i40e_del_mac_filter(vsi, al->list[i].addr)) { ret = -EINVAL; spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } + } spin_unlock_bh(&vsi->mac_filter_hash_lock); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c index 41fa2523d91d3..5f2cd9a8cf8fb 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c @@ -37,19 +37,24 @@ static void lan966x_lag_set_aggr_pgids(struct lan966x *lan966x) /* Now, set PGIDs for each active LAG */ for (lag = 0; lag < lan966x->num_phys_ports; ++lag) { - struct net_device *bond = lan966x->ports[lag]->bond; + struct lan966x_port *port = lan966x->ports[lag]; int num_active_ports = 0; + struct net_device *bond; unsigned long bond_mask; u8 aggr_idx[16]; - if (!bond || (visited & BIT(lag))) + if (!port || !port->bond || (visited & BIT(lag))) continue; + bond = port->bond; bond_mask = lan966x_lag_get_mask(lan966x, bond); for_each_set_bit(p, &bond_mask, lan966x->num_phys_ports) { struct lan966x_port *port = lan966x->ports[p]; + if (!port) + continue; + lan_wr(ANA_PGID_PGID_SET(bond_mask), lan966x, ANA_PGID(p)); if (port->lag_tx_active) diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index 2967bab725056..15180538b80a1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1424,10 +1424,30 @@ static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_ mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask); return; + /* Both struct tcphdr and struct udphdr start with + * __be16 source; + * __be16 dest; + * so we can use the same code for both. + */ case FLOW_ACT_MANGLE_HDR_TYPE_TCP: case FLOW_ACT_MANGLE_HDR_TYPE_UDP: - mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val); - mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask); + if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) { + mangle_action->mangle.val = + (__force u32)cpu_to_be32(mangle_action->mangle.val << 16); + /* The mask of mangle action is inverse mask, + * so clear the dest tp port with 0xFFFF to + * instead of rotate-left operation. + */ + mangle_action->mangle.mask = + (__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF); + } + if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) { + mangle_action->mangle.offset = 0; + mangle_action->mangle.val = + (__force u32)cpu_to_be32(mangle_action->mangle.val); + mangle_action->mangle.mask = + (__force u32)cpu_to_be32(mangle_action->mangle.mask); + } return; default: @@ -1864,10 +1884,30 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv, { struct flow_rule *rule = flow_cls_offload_flow_rule(flow); struct nfp_fl_ct_flow_entry *ct_entry; + struct flow_action_entry *ct_goto; struct nfp_fl_ct_zone_entry *zt; + struct flow_action_entry *act; bool wildcarded = false; struct flow_match_ct ct; - struct flow_action_entry *ct_goto; + int i; + + flow_action_for_each(i, act, &rule->action) { + switch (act->id) { + case FLOW_ACTION_REDIRECT: + case FLOW_ACTION_REDIRECT_INGRESS: + case FLOW_ACTION_MIRRED: + case FLOW_ACTION_MIRRED_INGRESS: + if (act->dev->rtnl_link_ops && + !strcmp(act->dev->rtnl_link_ops->kind, "openvswitch")) { + NL_SET_ERR_MSG_MOD(extack, + "unsupported offload: out port is openvswitch internal port"); + return -EOPNOTSUPP; + } + break; + default: + break; + } + } flow_rule_match_ct(rule, &ct); if (!ct.mask->ct_zone) { diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index e522845c7c211..0d7d138d6e0d7 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -1084,7 +1084,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, u16 nfp_mac_idx = 0; entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); - if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { + if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) { if (entry->bridge_count || !nfp_flower_is_supported_bridge(netdev)) { nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index de0a5d5ded305..f2085340a1cfe 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2588,6 +2588,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn) case NFP_NFD_VER_NFD3: netdev->netdev_ops = &nfp_nfd3_netdev_ops; netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; + netdev->xdp_features |= NETDEV_XDP_ACT_REDIRECT; break; case NFP_NFD_VER_NFDK: netdev->netdev_ops = &nfp_nfdk_netdev_ops; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index 33b4c28563162..3f10c5365c80e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -537,11 +537,13 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface) const u32 barcfg_msix_general = NFP_PCIE_BAR_PCIE2CPP_MapType( NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) | - NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT; + NFP_PCIE_BAR_PCIE2CPP_LengthSelect( + NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT); const u32 barcfg_msix_xpb = NFP_PCIE_BAR_PCIE2CPP_MapType( NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) | - NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT | + NFP_PCIE_BAR_PCIE2CPP_LengthSelect( + NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) | NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress( NFP_CPP_TARGET_ISLAND_XPB); const u32 barcfg_explicit[4] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 3d4f34e178a88..b0dd8adce3560 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -59,28 +59,51 @@ #undef FRAME_FILTER_DEBUG /* #define FRAME_FILTER_DEBUG */ +struct stmmac_q_tx_stats { + u64_stats_t tx_bytes; + u64_stats_t tx_set_ic_bit; + u64_stats_t tx_tso_frames; + u64_stats_t tx_tso_nfrags; +}; + +struct stmmac_napi_tx_stats { + u64_stats_t tx_packets; + u64_stats_t tx_pkt_n; + u64_stats_t poll; + u64_stats_t tx_clean; + u64_stats_t tx_set_ic_bit; +}; + struct stmmac_txq_stats { - u64 tx_bytes; - u64 tx_packets; - u64 tx_pkt_n; - u64 tx_normal_irq_n; - u64 napi_poll; - u64 tx_clean; - u64 tx_set_ic_bit; - u64 tx_tso_frames; - u64 tx_tso_nfrags; - struct u64_stats_sync syncp; + /* Updates protected by tx queue lock. */ + struct u64_stats_sync q_syncp; + struct stmmac_q_tx_stats q; + + /* Updates protected by NAPI poll logic. */ + struct u64_stats_sync napi_syncp; + struct stmmac_napi_tx_stats napi; } ____cacheline_aligned_in_smp; +struct stmmac_napi_rx_stats { + u64_stats_t rx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_pkt_n; + u64_stats_t poll; +}; + struct stmmac_rxq_stats { - u64 rx_bytes; - u64 rx_packets; - u64 rx_pkt_n; - u64 rx_normal_irq_n; - u64 napi_poll; - struct u64_stats_sync syncp; + /* Updates protected by NAPI poll logic. */ + struct u64_stats_sync napi_syncp; + struct stmmac_napi_rx_stats napi; } ____cacheline_aligned_in_smp; +/* Updates on each CPU protected by not allowing nested irqs. */ +struct stmmac_pcpu_stats { + struct u64_stats_sync syncp; + u64_stats_t rx_normal_irq_n[MTL_MAX_TX_QUEUES]; + u64_stats_t tx_normal_irq_n[MTL_MAX_RX_QUEUES]; +}; + /* Extra statistic and debug information exposed by ethtool */ struct stmmac_extra_stats { /* Transmit errors */ @@ -205,6 +228,7 @@ struct stmmac_extra_stats { /* per queue statistics */ struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES]; struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES]; + struct stmmac_pcpu_stats __percpu *pcpu_stats; unsigned long rx_dropped; unsigned long rx_errors; unsigned long tx_dropped; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 465ff1fd47855..51f121f867457 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -441,8 +441,7 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; - struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); int ret = 0; u32 v; @@ -455,9 +454,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, if (v & EMAC_TX_INT) { ret |= handle_tx; - u64_stats_update_begin(&txq_stats->syncp); - txq_stats->tx_normal_irq_n++; - u64_stats_update_end(&txq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); } if (v & EMAC_TX_DMA_STOP_INT) @@ -479,9 +478,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, if (v & EMAC_RX_INT) { ret |= handle_rx; - u64_stats_update_begin(&rxq_stats->syncp); - rxq_stats->rx_normal_irq_n++; - u64_stats_update_end(&rxq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); } if (v & EMAC_RX_BUF_UA_INT) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 9470d3fd2dede..0d185e54eb7e2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -171,8 +171,7 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs; u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan)); u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); - struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; - struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); int ret = 0; if (dir == DMA_DIR_RX) @@ -201,15 +200,15 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, } /* TX/RX NORMAL interrupts */ if (likely(intr_status & DMA_CHAN_STATUS_RI)) { - u64_stats_update_begin(&rxq_stats->syncp); - rxq_stats->rx_normal_irq_n++; - u64_stats_update_end(&rxq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_rx; } if (likely(intr_status & DMA_CHAN_STATUS_TI)) { - u64_stats_update_begin(&txq_stats->syncp); - txq_stats->tx_normal_irq_n++; - u64_stats_update_end(&txq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_tx; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index 7907d62d34375..85e18f9a22f92 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -162,8 +162,7 @@ static void show_rx_process_state(unsigned int status) int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; - struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); int ret = 0; /* read the status register (CSR5) */ u32 intr_status = readl(ioaddr + DMA_STATUS); @@ -215,16 +214,16 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, u32 value = readl(ioaddr + DMA_INTR_ENA); /* to schedule NAPI on real RIE event. */ if (likely(value & DMA_INTR_ENA_RIE)) { - u64_stats_update_begin(&rxq_stats->syncp); - rxq_stats->rx_normal_irq_n++; - u64_stats_update_end(&rxq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_rx; } } if (likely(intr_status & DMA_STATUS_TI)) { - u64_stats_update_begin(&txq_stats->syncp); - txq_stats->tx_normal_irq_n++; - u64_stats_update_end(&txq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_tx; } if (unlikely(intr_status & DMA_STATUS_ERI)) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 3cde695fec91b..dd2ab6185c40e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -337,8 +337,7 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; - struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan)); u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan)); int ret = 0; @@ -367,15 +366,15 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv, /* TX/RX NORMAL interrupts */ if (likely(intr_status & XGMAC_NIS)) { if (likely(intr_status & XGMAC_RI)) { - u64_stats_update_begin(&rxq_stats->syncp); - rxq_stats->rx_normal_irq_n++; - u64_stats_update_end(&rxq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_rx; } if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) { - u64_stats_update_begin(&txq_stats->syncp); - txq_stats->tx_normal_irq_n++; - u64_stats_update_end(&txq_stats->syncp); + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); ret |= handle_tx; } } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 69c8c25285243..521b1b5ffebb4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -539,44 +539,79 @@ stmmac_set_pauseparam(struct net_device *netdev, } } +static u64 stmmac_get_rx_normal_irq_n(struct stmmac_priv *priv, int q) +{ + u64 total; + int cpu; + + total = 0; + for_each_possible_cpu(cpu) { + struct stmmac_pcpu_stats *pcpu; + unsigned int start; + u64 irq_n; + + pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu); + do { + start = u64_stats_fetch_begin(&pcpu->syncp); + irq_n = u64_stats_read(&pcpu->rx_normal_irq_n[q]); + } while (u64_stats_fetch_retry(&pcpu->syncp, start)); + total += irq_n; + } + return total; +} + +static u64 stmmac_get_tx_normal_irq_n(struct stmmac_priv *priv, int q) +{ + u64 total; + int cpu; + + total = 0; + for_each_possible_cpu(cpu) { + struct stmmac_pcpu_stats *pcpu; + unsigned int start; + u64 irq_n; + + pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu); + do { + start = u64_stats_fetch_begin(&pcpu->syncp); + irq_n = u64_stats_read(&pcpu->tx_normal_irq_n[q]); + } while (u64_stats_fetch_retry(&pcpu->syncp, start)); + total += irq_n; + } + return total; +} + static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data) { u32 tx_cnt = priv->plat->tx_queues_to_use; u32 rx_cnt = priv->plat->rx_queues_to_use; unsigned int start; - int q, stat; - char *p; + int q; for (q = 0; q < tx_cnt; q++) { struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q]; - struct stmmac_txq_stats snapshot; + u64 pkt_n; do { - start = u64_stats_fetch_begin(&txq_stats->syncp); - snapshot = *txq_stats; - } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); + start = u64_stats_fetch_begin(&txq_stats->napi_syncp); + pkt_n = u64_stats_read(&txq_stats->napi.tx_pkt_n); + } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start)); - p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n); - for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) { - *data++ = (*(u64 *)p); - p += sizeof(u64); - } + *data++ = pkt_n; + *data++ = stmmac_get_tx_normal_irq_n(priv, q); } for (q = 0; q < rx_cnt; q++) { struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q]; - struct stmmac_rxq_stats snapshot; + u64 pkt_n; do { - start = u64_stats_fetch_begin(&rxq_stats->syncp); - snapshot = *rxq_stats; - } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); + start = u64_stats_fetch_begin(&rxq_stats->napi_syncp); + pkt_n = u64_stats_read(&rxq_stats->napi.rx_pkt_n); + } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start)); - p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n); - for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) { - *data++ = (*(u64 *)p); - p += sizeof(u64); - } + *data++ = pkt_n; + *data++ = stmmac_get_rx_normal_irq_n(priv, q); } } @@ -635,39 +670,49 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, pos = j; for (i = 0; i < rx_queues_count; i++) { struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[i]; - struct stmmac_rxq_stats snapshot; + struct stmmac_napi_rx_stats snapshot; + u64 n_irq; j = pos; do { - start = u64_stats_fetch_begin(&rxq_stats->syncp); - snapshot = *rxq_stats; - } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); - - data[j++] += snapshot.rx_pkt_n; - data[j++] += snapshot.rx_normal_irq_n; - normal_irq_n += snapshot.rx_normal_irq_n; - napi_poll += snapshot.napi_poll; + start = u64_stats_fetch_begin(&rxq_stats->napi_syncp); + snapshot = rxq_stats->napi; + } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start)); + + data[j++] += u64_stats_read(&snapshot.rx_pkt_n); + n_irq = stmmac_get_rx_normal_irq_n(priv, i); + data[j++] += n_irq; + normal_irq_n += n_irq; + napi_poll += u64_stats_read(&snapshot.poll); } pos = j; for (i = 0; i < tx_queues_count; i++) { struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[i]; - struct stmmac_txq_stats snapshot; + struct stmmac_napi_tx_stats napi_snapshot; + struct stmmac_q_tx_stats q_snapshot; + u64 n_irq; j = pos; do { - start = u64_stats_fetch_begin(&txq_stats->syncp); - snapshot = *txq_stats; - } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); - - data[j++] += snapshot.tx_pkt_n; - data[j++] += snapshot.tx_normal_irq_n; - normal_irq_n += snapshot.tx_normal_irq_n; - data[j++] += snapshot.tx_clean; - data[j++] += snapshot.tx_set_ic_bit; - data[j++] += snapshot.tx_tso_frames; - data[j++] += snapshot.tx_tso_nfrags; - napi_poll += snapshot.napi_poll; + start = u64_stats_fetch_begin(&txq_stats->q_syncp); + q_snapshot = txq_stats->q; + } while (u64_stats_fetch_retry(&txq_stats->q_syncp, start)); + do { + start = u64_stats_fetch_begin(&txq_stats->napi_syncp); + napi_snapshot = txq_stats->napi; + } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start)); + + data[j++] += u64_stats_read(&napi_snapshot.tx_pkt_n); + n_irq = stmmac_get_tx_normal_irq_n(priv, i); + data[j++] += n_irq; + normal_irq_n += n_irq; + data[j++] += u64_stats_read(&napi_snapshot.tx_clean); + data[j++] += u64_stats_read(&q_snapshot.tx_set_ic_bit) + + u64_stats_read(&napi_snapshot.tx_set_ic_bit); + data[j++] += u64_stats_read(&q_snapshot.tx_tso_frames); + data[j++] += u64_stats_read(&q_snapshot.tx_tso_nfrags); + napi_poll += u64_stats_read(&napi_snapshot.poll); } normal_irq_n += priv->xstats.rx_early_irq; data[j++] = normal_irq_n; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 292857c0e601f..f1614ad2daaa7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2442,7 +2442,6 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) struct xdp_desc xdp_desc; bool work_done = true; u32 tx_set_ic_bit = 0; - unsigned long flags; /* Avoids TX time-out as we are sharing with slow path */ txq_trans_cond_update(nq); @@ -2515,9 +2514,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size); entry = tx_q->cur_tx; } - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_set_ic_bit += tx_set_ic_bit; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->napi_syncp); + u64_stats_add(&txq_stats->napi.tx_set_ic_bit, tx_set_ic_bit); + u64_stats_update_end(&txq_stats->napi_syncp); if (tx_desc) { stmmac_flush_tx_descriptors(priv, queue); @@ -2561,7 +2560,6 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) unsigned int bytes_compl = 0, pkts_compl = 0; unsigned int entry, xmits = 0, count = 0; u32 tx_packets = 0, tx_errors = 0; - unsigned long flags; __netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue)); @@ -2717,11 +2715,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) if (tx_q->dirty_tx != tx_q->cur_tx) stmmac_tx_timer_arm(priv, queue); - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_packets += tx_packets; - txq_stats->tx_pkt_n += tx_packets; - txq_stats->tx_clean++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->napi_syncp); + u64_stats_add(&txq_stats->napi.tx_packets, tx_packets); + u64_stats_add(&txq_stats->napi.tx_pkt_n, tx_packets); + u64_stats_inc(&txq_stats->napi.tx_clean); + u64_stats_update_end(&txq_stats->napi_syncp); priv->xstats.tx_errors += tx_errors; @@ -3853,6 +3851,9 @@ static int __stmmac_open(struct net_device *dev, priv->rx_copybreak = STMMAC_RX_COPYBREAK; buf_sz = dma_conf->dma_buf_sz; + for (int i = 0; i < MTL_MAX_TX_QUEUES; i++) + if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN) + dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs; memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf)); stmmac_reset_queues_param(priv); @@ -4131,7 +4132,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_tx_queue *tx_q; bool has_vlan, set_ic; u8 proto_hdr_len, hdr; - unsigned long flags; u32 pay_len, mss; dma_addr_t des; int i; @@ -4296,13 +4296,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); } - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_bytes += skb->len; - txq_stats->tx_tso_frames++; - txq_stats->tx_tso_nfrags += nfrags; + u64_stats_update_begin(&txq_stats->q_syncp); + u64_stats_add(&txq_stats->q.tx_bytes, skb->len); + u64_stats_inc(&txq_stats->q.tx_tso_frames); + u64_stats_add(&txq_stats->q.tx_tso_nfrags, nfrags); if (set_ic) - txq_stats->tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_inc(&txq_stats->q.tx_set_ic_bit); + u64_stats_update_end(&txq_stats->q_syncp); if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -4401,7 +4401,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_tx_queue *tx_q; bool has_vlan, set_ic; int entry, first_tx; - unsigned long flags; dma_addr_t des; tx_q = &priv->dma_conf.tx_queue[queue]; @@ -4571,11 +4570,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); } - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_bytes += skb->len; + u64_stats_update_begin(&txq_stats->q_syncp); + u64_stats_add(&txq_stats->q.tx_bytes, skb->len); if (set_ic) - txq_stats->tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_inc(&txq_stats->q.tx_set_ic_bit); + u64_stats_update_end(&txq_stats->q_syncp); if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -4839,12 +4838,11 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue, set_ic = false; if (set_ic) { - unsigned long flags; tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, tx_desc); - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->q_syncp); + u64_stats_inc(&txq_stats->q.tx_set_ic_bit); + u64_stats_update_end(&txq_stats->q_syncp); } stmmac_enable_dma_transmission(priv, priv->ioaddr); @@ -4994,7 +4992,6 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue, unsigned int len = xdp->data_end - xdp->data; enum pkt_hash_types hash_type; int coe = priv->hw->rx_csum; - unsigned long flags; struct sk_buff *skb; u32 hash; @@ -5019,10 +5016,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue, skb_record_rx_queue(skb, queue); napi_gro_receive(&ch->rxtx_napi, skb); - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->rx_pkt_n++; - rxq_stats->rx_bytes += len; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_inc(&rxq_stats->napi.rx_pkt_n); + u64_stats_add(&rxq_stats->napi.rx_bytes, len); + u64_stats_update_end(&rxq_stats->napi_syncp); } static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget) @@ -5104,7 +5101,6 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue) unsigned int desc_size; struct bpf_prog *prog; bool failure = false; - unsigned long flags; int xdp_status = 0; int status = 0; @@ -5259,9 +5255,9 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue) stmmac_finalize_xdp_rx(priv, xdp_status); - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->rx_pkt_n += count; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_add(&rxq_stats->napi.rx_pkt_n, count); + u64_stats_update_end(&rxq_stats->napi_syncp); priv->xstats.rx_dropped += rx_dropped; priv->xstats.rx_errors += rx_errors; @@ -5299,7 +5295,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) unsigned int desc_size; struct sk_buff *skb = NULL; struct stmmac_xdp_buff ctx; - unsigned long flags; int xdp_status = 0; int buf_sz; @@ -5552,11 +5547,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) stmmac_rx_refill(priv, queue); - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->rx_packets += rx_packets; - rxq_stats->rx_bytes += rx_bytes; - rxq_stats->rx_pkt_n += count; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_add(&rxq_stats->napi.rx_packets, rx_packets); + u64_stats_add(&rxq_stats->napi.rx_bytes, rx_bytes); + u64_stats_add(&rxq_stats->napi.rx_pkt_n, count); + u64_stats_update_end(&rxq_stats->napi_syncp); priv->xstats.rx_dropped += rx_dropped; priv->xstats.rx_errors += rx_errors; @@ -5571,13 +5566,12 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget) struct stmmac_priv *priv = ch->priv_data; struct stmmac_rxq_stats *rxq_stats; u32 chan = ch->index; - unsigned long flags; int work_done; rxq_stats = &priv->xstats.rxq_stats[chan]; - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->napi_poll++; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_inc(&rxq_stats->napi.poll); + u64_stats_update_end(&rxq_stats->napi_syncp); work_done = stmmac_rx(priv, budget, chan); if (work_done < budget && napi_complete_done(napi, work_done)) { @@ -5598,13 +5592,12 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget) struct stmmac_priv *priv = ch->priv_data; struct stmmac_txq_stats *txq_stats; u32 chan = ch->index; - unsigned long flags; int work_done; txq_stats = &priv->xstats.txq_stats[chan]; - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->napi_poll++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->napi_syncp); + u64_stats_inc(&txq_stats->napi.poll); + u64_stats_update_end(&txq_stats->napi_syncp); work_done = stmmac_tx_clean(priv, budget, chan); work_done = min(work_done, budget); @@ -5629,17 +5622,16 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget) struct stmmac_rxq_stats *rxq_stats; struct stmmac_txq_stats *txq_stats; u32 chan = ch->index; - unsigned long flags; rxq_stats = &priv->xstats.rxq_stats[chan]; - flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); - rxq_stats->napi_poll++; - u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); + u64_stats_update_begin(&rxq_stats->napi_syncp); + u64_stats_inc(&rxq_stats->napi.poll); + u64_stats_update_end(&rxq_stats->napi_syncp); txq_stats = &priv->xstats.txq_stats[chan]; - flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); - txq_stats->napi_poll++; - u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); + u64_stats_update_begin(&txq_stats->napi_syncp); + u64_stats_inc(&txq_stats->napi.poll); + u64_stats_update_end(&txq_stats->napi_syncp); tx_done = stmmac_tx_clean(priv, budget, chan); tx_done = min(tx_done, budget); @@ -6961,10 +6953,13 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64 u64 tx_bytes; do { - start = u64_stats_fetch_begin(&txq_stats->syncp); - tx_packets = txq_stats->tx_packets; - tx_bytes = txq_stats->tx_bytes; - } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); + start = u64_stats_fetch_begin(&txq_stats->q_syncp); + tx_bytes = u64_stats_read(&txq_stats->q.tx_bytes); + } while (u64_stats_fetch_retry(&txq_stats->q_syncp, start)); + do { + start = u64_stats_fetch_begin(&txq_stats->napi_syncp); + tx_packets = u64_stats_read(&txq_stats->napi.tx_packets); + } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start)); stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; @@ -6976,10 +6971,10 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64 u64 rx_bytes; do { - start = u64_stats_fetch_begin(&rxq_stats->syncp); - rx_packets = rxq_stats->rx_packets; - rx_bytes = rxq_stats->rx_bytes; - } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); + start = u64_stats_fetch_begin(&rxq_stats->napi_syncp); + rx_packets = u64_stats_read(&rxq_stats->napi.rx_packets); + rx_bytes = u64_stats_read(&rxq_stats->napi.rx_bytes); + } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; @@ -7373,9 +7368,16 @@ int stmmac_dvr_probe(struct device *device, priv->dev = ndev; for (i = 0; i < MTL_MAX_RX_QUEUES; i++) - u64_stats_init(&priv->xstats.rxq_stats[i].syncp); - for (i = 0; i < MTL_MAX_TX_QUEUES; i++) - u64_stats_init(&priv->xstats.txq_stats[i].syncp); + u64_stats_init(&priv->xstats.rxq_stats[i].napi_syncp); + for (i = 0; i < MTL_MAX_TX_QUEUES; i++) { + u64_stats_init(&priv->xstats.txq_stats[i].q_syncp); + u64_stats_init(&priv->xstats.txq_stats[i].napi_syncp); + } + + priv->xstats.pcpu_stats = + devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats); + if (!priv->xstats.pcpu_stats) + return -ENOMEM; stmmac_set_ethtool_ops(ndev); priv->pause = pause; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index ca4d4548f85e3..2ed165dcdbdcf 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -631,6 +631,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) } } + phy->mac_managed_pm = true; + slave->phy = phy; phy_attached_info(slave->phy); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 0e4f526b17532..9061dca97fcbf 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -773,6 +773,9 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) slave->slave_num); return; } + + phy->mac_managed_pm = true; + slave->phy = phy; phy_attached_info(slave->phy); diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 82e9796c8f5e5..4f9658a741024 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -708,7 +708,10 @@ void netvsc_device_remove(struct hv_device *device) /* Disable NAPI and disassociate its context from the device. */ for (i = 0; i < net_device->num_chn; i++) { /* See also vmbus_reset_channel_cb(). */ - napi_disable(&net_device->chan_table[i].napi); + /* only disable enabled NAPI channel */ + if (i < ndev->real_num_rx_queues) + napi_disable(&net_device->chan_table[i].napi); + netif_napi_del(&net_device->chan_table[i].napi); } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index cd15d7b380ab5..9d2d66a4aafd5 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -42,6 +42,10 @@ #define LINKCHANGE_INT (2 * HZ) #define VF_TAKEOVER_INT (HZ / 10) +/* Macros to define the context of vf registration */ +#define VF_REG_IN_PROBE 1 +#define VF_REG_IN_NOTIFIER 2 + static unsigned int ring_size __ro_after_init = 128; module_param(ring_size, uint, 0444); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)"); @@ -2183,7 +2187,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb) } static int netvsc_vf_join(struct net_device *vf_netdev, - struct net_device *ndev) + struct net_device *ndev, int context) { struct net_device_context *ndev_ctx = netdev_priv(ndev); int ret; @@ -2206,7 +2210,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto upper_link_failed; } - schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); + /* If this registration is called from probe context vf_takeover + * is taken care of later in probe itself. + */ + if (context == VF_REG_IN_NOTIFIER) + schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); @@ -2344,7 +2352,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev) return NOTIFY_DONE; } -static int netvsc_register_vf(struct net_device *vf_netdev) +static int netvsc_register_vf(struct net_device *vf_netdev, int context) { struct net_device_context *net_device_ctx; struct netvsc_device *netvsc_dev; @@ -2384,7 +2392,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev) netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); - if (netvsc_vf_join(vf_netdev, ndev) != 0) + if (netvsc_vf_join(vf_netdev, ndev, context) != 0) return NOTIFY_DONE; dev_hold(vf_netdev); @@ -2482,10 +2490,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) return NOTIFY_OK; } +static int check_dev_is_matching_vf(struct net_device *event_ndev) +{ + /* Skip NetVSC interfaces */ + if (event_ndev->netdev_ops == &device_ops) + return -ENODEV; + + /* Avoid non-Ethernet type devices */ + if (event_ndev->type != ARPHRD_ETHER) + return -ENODEV; + + /* Avoid Vlan dev with same MAC registering as VF */ + if (is_vlan_dev(event_ndev)) + return -ENODEV; + + /* Avoid Bonding master dev with same MAC registering as VF */ + if (netif_is_bond_master(event_ndev)) + return -ENODEV; + + return 0; +} + static int netvsc_probe(struct hv_device *dev, const struct hv_vmbus_device_id *dev_id) { - struct net_device *net = NULL; + struct net_device *net = NULL, *vf_netdev; struct net_device_context *net_device_ctx; struct netvsc_device_info *device_info = NULL; struct netvsc_device *nvdev; @@ -2597,6 +2626,30 @@ static int netvsc_probe(struct hv_device *dev, } list_add(&net_device_ctx->list, &netvsc_dev_list); + + /* When the hv_netvsc driver is unloaded and reloaded, the + * NET_DEVICE_REGISTER for the vf device is replayed before probe + * is complete. This is because register_netdevice_notifier() gets + * registered before vmbus_driver_register() so that callback func + * is set before probe and we don't miss events like NETDEV_POST_INIT + * So, in this section we try to register the matching vf device that + * is present as a netdevice, knowing that its register call is not + * processed in the netvsc_netdev_notifier(as probing is progress and + * get_netvsc_byslot fails). + */ + for_each_netdev(dev_net(net), vf_netdev) { + ret = check_dev_is_matching_vf(vf_netdev); + if (ret != 0) + continue; + + if (net != get_netvsc_byslot(vf_netdev)) + continue; + + netvsc_prepare_bonding(vf_netdev); + netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE); + __netvsc_vf_setup(net, vf_netdev); + break; + } rtnl_unlock(); netvsc_devinfo_put(device_info); @@ -2752,28 +2805,17 @@ static int netvsc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + int ret = 0; - /* Skip our own events */ - if (event_dev->netdev_ops == &device_ops) - return NOTIFY_DONE; - - /* Avoid non-Ethernet type devices */ - if (event_dev->type != ARPHRD_ETHER) - return NOTIFY_DONE; - - /* Avoid Vlan dev with same MAC registering as VF */ - if (is_vlan_dev(event_dev)) - return NOTIFY_DONE; - - /* Avoid Bonding master dev with same MAC registering as VF */ - if (netif_is_bond_master(event_dev)) + ret = check_dev_is_matching_vf(event_dev); + if (ret != 0) return NOTIFY_DONE; switch (event) { case NETDEV_POST_INIT: return netvsc_prepare_bonding(event_dev); case NETDEV_REGISTER: - return netvsc_register_vf(event_dev); + return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER); case NETDEV_UNREGISTER: return netvsc_unregister_vf(event_dev); case NETDEV_UP: diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index b26f90e522564..359397a617153 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -618,7 +618,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 2) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -634,7 +634,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 1) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -650,7 +650,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 0) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -707,7 +707,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 2) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -723,7 +723,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 1) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -739,7 +739,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 0) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -1088,6 +1088,9 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt) goto read_table; } + ret = PTR_ERR(wifi_pkg); + goto out_free; + read_table: fwrt->ppag_ver = tbl_rev; flags = &wifi_pkg->package.elements[1]; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index fb5e254757e71..8faf4e7872bb9 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -128,6 +128,7 @@ static void iwl_dealloc_ucode(struct iwl_drv *drv) kfree(drv->fw.ucode_capa.cmd_versions); kfree(drv->fw.phy_integration_ver); kfree(drv->trans->dbg.pc_data); + drv->trans->dbg.pc_data = NULL; for (i = 0; i < IWL_UCODE_TYPE_MAX; i++) iwl_free_fw_img(drv, drv->fw.img + i); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index a25ea638229b0..0aeca64725da6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3666,6 +3666,9 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, NL80211_TDLS_SETUP); } + if (ret) + return ret; + for_each_sta_active_link(vif, sta, link_sta, i) link_sta->agg.max_rc_amsdu_len = 1; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 8d1e44fd9de73..82b4d4d01097a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -503,6 +503,10 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue, return false; mvm_sta = iwl_mvm_sta_from_mac80211(sta); + + if (WARN_ON_ONCE(!mvm_sta->dup_data)) + return false; + dup_data = &mvm_sta->dup_data[queue]; /* diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index d7503aef599f0..fab361a250d60 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -104,13 +104,12 @@ bool provides_xdp_headroom = true; module_param(provides_xdp_headroom, bool, 0644); static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status); + s8 status); static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st); -static void push_tx_responses(struct xenvif_queue *queue); + s8 status); static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); @@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue, unsigned int extra_count, RING_IDX end) { RING_IDX cons = queue->tx.req_cons; - unsigned long flags; do { - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, flags); if (cons == end) break; RING_COPY_REQUEST(&queue->tx, cons++, txp); @@ -465,12 +460,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue, for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; nr_slots--) { if (unlikely(!txp->size)) { - unsigned long flags; - - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, flags); ++txp; continue; } @@ -496,14 +486,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) { if (unlikely(!txp->size)) { - unsigned long flags; - - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, - flags); continue; } @@ -995,7 +979,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, (ret == 0) ? XEN_NETIF_RSP_OKAY : XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); continue; } @@ -1007,7 +990,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, make_tx_response(queue, &txreq, extra_count, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); continue; } @@ -1433,8 +1415,35 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget) return work_done; } +static void _make_tx_response(struct xenvif_queue *queue, + const struct xen_netif_tx_request *txp, + unsigned int extra_count, + s8 status) +{ + RING_IDX i = queue->tx.rsp_prod_pvt; + struct xen_netif_tx_response *resp; + + resp = RING_GET_RESPONSE(&queue->tx, i); + resp->id = txp->id; + resp->status = status; + + while (extra_count-- != 0) + RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + + queue->tx.rsp_prod_pvt = ++i; +} + +static void push_tx_responses(struct xenvif_queue *queue) +{ + int notify; + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + if (notify) + notify_remote_via_irq(queue->tx_irq); +} + static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status) + s8 status) { struct pending_tx_info *pending_tx_info; pending_ring_idx_t index; @@ -1444,8 +1453,8 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_lock_irqsave(&queue->response_lock, flags); - make_tx_response(queue, &pending_tx_info->req, - pending_tx_info->extra_count, status); + _make_tx_response(queue, &pending_tx_info->req, + pending_tx_info->extra_count, status); /* Release the pending index before pusing the Tx response so * its available before a new Tx request is pushed by the @@ -1459,32 +1468,19 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_unlock_irqrestore(&queue->response_lock, flags); } - static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st) + s8 status) { - RING_IDX i = queue->tx.rsp_prod_pvt; - struct xen_netif_tx_response *resp; - - resp = RING_GET_RESPONSE(&queue->tx, i); - resp->id = txp->id; - resp->status = st; - - while (extra_count-- != 0) - RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + unsigned long flags; - queue->tx.rsp_prod_pvt = ++i; -} + spin_lock_irqsave(&queue->response_lock, flags); -static void push_tx_responses(struct xenvif_queue *queue) -{ - int notify; + _make_tx_response(queue, txp, extra_count, status); + push_tx_responses(queue); - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); - if (notify) - notify_remote_via_irq(queue->tx_irq); + spin_unlock_irqrestore(&queue->response_lock, flags); } static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) diff --git a/drivers/of/property.c b/drivers/of/property.c index cf8dacf3e3b84..e1a2cb5ef401c 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -762,7 +762,9 @@ struct device_node *of_graph_get_port_parent(struct device_node *node) /* Walk 3 levels up only if there is 'ports' node. */ for (depth = 3; depth && node; depth--) { node = of_get_next_parent(node); - if (depth == 2 && !of_node_name_eq(node, "ports")) + if (depth == 2 && !of_node_name_eq(node, "ports") && + !of_node_name_eq(node, "in-ports") && + !of_node_name_eq(node, "out-ports")) break; } return node; @@ -1062,36 +1064,6 @@ of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, return of_device_get_match_data(dev); } -static struct device_node *of_get_compat_node(struct device_node *np) -{ - of_node_get(np); - - while (np) { - if (!of_device_is_available(np)) { - of_node_put(np); - np = NULL; - } - - if (of_property_present(np, "compatible")) - break; - - np = of_get_next_parent(np); - } - - return np; -} - -static struct device_node *of_get_compat_node_parent(struct device_node *np) -{ - struct device_node *parent, *node; - - parent = of_get_parent(np); - node = of_get_compat_node(parent); - of_node_put(parent); - - return node; -} - static void of_link_to_phandle(struct device_node *con_np, struct device_node *sup_np) { @@ -1221,10 +1193,10 @@ static struct device_node *parse_##fname(struct device_node *np, \ * @parse_prop.prop_name: Name of property holding a phandle value * @parse_prop.index: For properties holding a list of phandles, this is the * index into the list + * @get_con_dev: If the consumer node containing the property is never converted + * to a struct device, implement this ops so fw_devlink can use it + * to find the true consumer. * @optional: Describes whether a supplier is mandatory or not - * @node_not_dev: The consumer node containing the property is never converted - * to a struct device. Instead, parse ancestor nodes for the - * compatible property to find a node corresponding to a device. * * Returns: * parse_prop() return values are @@ -1235,15 +1207,15 @@ static struct device_node *parse_##fname(struct device_node *np, \ struct supplier_bindings { struct device_node *(*parse_prop)(struct device_node *np, const char *prop_name, int index); + struct device_node *(*get_con_dev)(struct device_node *np); bool optional; - bool node_not_dev; }; DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells") DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells") DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") -DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells") +DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") @@ -1261,7 +1233,6 @@ DEFINE_SIMPLE_PROP(pinctrl5, "pinctrl-5", NULL) DEFINE_SIMPLE_PROP(pinctrl6, "pinctrl-6", NULL) DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL) DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL) -DEFINE_SIMPLE_PROP(remote_endpoint, "remote-endpoint", NULL) DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells") DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells") DEFINE_SIMPLE_PROP(leds, "leds", NULL) @@ -1326,6 +1297,17 @@ static struct device_node *parse_interrupts(struct device_node *np, return of_irq_parse_one(np, index, &sup_args) ? NULL : sup_args.np; } +static struct device_node *parse_remote_endpoint(struct device_node *np, + const char *prop_name, + int index) +{ + /* Return NULL for index > 0 to signify end of remote-endpoints. */ + if (!index || strcmp(prop_name, "remote-endpoint")) + return NULL; + + return of_graph_get_remote_port_parent(np); +} + static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_clocks, }, { .parse_prop = parse_interconnects, }, @@ -1350,7 +1332,10 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_pinctrl6, }, { .parse_prop = parse_pinctrl7, }, { .parse_prop = parse_pinctrl8, }, - { .parse_prop = parse_remote_endpoint, .node_not_dev = true, }, + { + .parse_prop = parse_remote_endpoint, + .get_con_dev = of_graph_get_port_parent, + }, { .parse_prop = parse_pwms, }, { .parse_prop = parse_resets, }, { .parse_prop = parse_leds, }, @@ -1400,8 +1385,8 @@ static int of_link_property(struct device_node *con_np, const char *prop_name) while ((phandle = s->parse_prop(con_np, prop_name, i))) { struct device_node *con_dev_np; - con_dev_np = s->node_not_dev - ? of_get_compat_node_parent(con_np) + con_dev_np = s->get_con_dev + ? s->get_con_dev(con_np) : of_node_get(con_np); matched = true; i++; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index f278def7ef038..4f58345b5c683 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -50,6 +50,12 @@ static struct unittest_results { failed; \ }) +#ifdef CONFIG_OF_KOBJ +#define OF_KREF_READ(NODE) kref_read(&(NODE)->kobj.kref) +#else +#define OF_KREF_READ(NODE) 1 +#endif + /* * Expected message may have a message level other than KERN_INFO. * Print the expected message only if the current loglevel will allow @@ -570,7 +576,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void) pr_err("missing testcase data\n"); return; } - prefs[i] = kref_read(&p[i]->kobj.kref); + prefs[i] = OF_KREF_READ(p[i]); } rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells"); @@ -693,9 +699,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void) unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); for (i = 0; i < ARRAY_SIZE(p); ++i) { - unittest(prefs[i] == kref_read(&p[i]->kobj.kref), + unittest(prefs[i] == OF_KREF_READ(p[i]), "provider%d: expected:%d got:%d\n", - i, prefs[i], kref_read(&p[i]->kobj.kref)); + i, prefs[i], OF_KREF_READ(p[i])); of_node_put(p[i]); } } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 59d6cb1a3a9d5..06fc6f532d6c4 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2434,29 +2434,36 @@ static void pci_pme_list_scan(struct work_struct *work) if (pdev->pme_poll) { struct pci_dev *bridge = pdev->bus->self; struct device *dev = &pdev->dev; - int pm_status; + struct device *bdev = bridge ? &bridge->dev : NULL; + int bref = 0; /* - * If bridge is in low power state, the - * configuration space of subordinate devices - * may be not accessible + * If we have a bridge, it should be in an active/D0 + * state or the configuration space of subordinate + * devices may not be accessible or stable over the + * course of the call. */ - if (bridge && bridge->current_state != PCI_D0) - continue; + if (bdev) { + bref = pm_runtime_get_if_active(bdev, true); + if (!bref) + continue; + + if (bridge->current_state != PCI_D0) + goto put_bridge; + } /* - * If the device is in a low power state it - * should not be polled either. + * The device itself should be suspended but config + * space must be accessible, therefore it cannot be in + * D3cold. */ - pm_status = pm_runtime_get_if_active(dev, true); - if (!pm_status) - continue; - - if (pdev->current_state != PCI_D3cold) + if (pm_runtime_suspended(dev) && + pdev->current_state != PCI_D3cold) pci_pme_wakeup(pdev, NULL); - if (pm_status > 0) - pm_runtime_put(dev); +put_bridge: + if (bref > 0) + pm_runtime_put(bdev); } else { list_del(&pme_dev->list); kfree(pme_dev); diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c index 365d964b0f6a6..bc0d414a6aff9 100644 --- a/drivers/perf/cxl_pmu.c +++ b/drivers/perf/cxl_pmu.c @@ -419,7 +419,7 @@ static struct attribute *cxl_pmu_event_attrs[] = { CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmp, CXL_PMU_GID_S2M_NDR, BIT(0)), CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmps, CXL_PMU_GID_S2M_NDR, BIT(1)), CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmpe, CXL_PMU_GID_S2M_NDR, BIT(2)), - CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack, CXL_PMU_GID_S2M_NDR, BIT(3)), + CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack, CXL_PMU_GID_S2M_NDR, BIT(4)), /* CXL rev 3.0 Table 3-46 S2M DRS opcodes */ CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdata, CXL_PMU_GID_S2M_DRS, BIT(0)), CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdatanxm, CXL_PMU_GID_S2M_DRS, BIT(1)), diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c index ee962804b8303..edded392950ce 100644 --- a/drivers/pmdomain/mediatek/mtk-pm-domains.c +++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c @@ -508,6 +508,11 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren goto err_put_node; } + /* recursive call to add all subdomains */ + ret = scpsys_add_subdomain(scpsys, child); + if (ret) + goto err_put_node; + ret = pm_genpd_add_subdomain(parent_pd, child_pd); if (ret) { dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n", @@ -517,11 +522,6 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name, child_pd->name); } - - /* recursive call to add all subdomains */ - ret = scpsys_add_subdomain(scpsys, child); - if (ret) - goto err_put_node; } return 0; @@ -535,9 +535,6 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) { int ret; - if (scpsys_domain_is_on(pd)) - scpsys_power_off(&pd->genpd); - /* * We're in the error cleanup already, so we only complain, * but won't emit another error on top of the original one. @@ -547,6 +544,8 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) dev_err(pd->scpsys->dev, "failed to remove domain '%s' : %d - state may be inconsistent\n", pd->genpd.name, ret); + if (scpsys_domain_is_on(pd)) + scpsys_power_off(&pd->genpd); clk_bulk_put(pd->num_clks, pd->clks); clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks); diff --git a/drivers/pmdomain/renesas/r8a77980-sysc.c b/drivers/pmdomain/renesas/r8a77980-sysc.c index 39ca84a67daad..621e411fc9991 100644 --- a/drivers/pmdomain/renesas/r8a77980-sysc.c +++ b/drivers/pmdomain/renesas/r8a77980-sysc.c @@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = { PD_CPU_NOCR }, { "ca53-cpu3", 0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU, PD_CPU_NOCR }, - { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON }, + { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON, + PD_CPU_NOCR }, { "a3ir", 0x180, 0, R8A77980_PD_A3IR, R8A77980_PD_ALWAYS_ON }, { "a2ir0", 0x400, 0, R8A77980_PD_A2IR0, R8A77980_PD_A3IR }, { "a2ir1", 0x400, 1, R8A77980_PD_A2IR1, R8A77980_PD_A3IR }, diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index b92a32b4b1141..04c64ce0a1ca1 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -255,9 +255,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) if (!recover) { hash_del(&addr->hnode); kfree(addr); - continue; + } else { + /* prepare for recovery */ + addr->disp_flag = QETH_DISP_ADDR_ADD; } - addr->disp_flag = QETH_DISP_ADDR_ADD; } mutex_unlock(&card->ip_lock); @@ -278,9 +279,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card) if (addr->disp_flag == QETH_DISP_ADDR_ADD) { rc = qeth_l3_register_addr_entry(card, addr); - if (!rc) { + if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) { + /* keep it in the records */ addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; } else { + /* bad address */ hash_del(&addr->hnode); kfree(addr); } diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 19eee108db021..5c8d1ba3f8f3c 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -319,17 +319,16 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip) { struct fcoe_fcf *sel; struct fcoe_fcf *fcf; - unsigned long flags; mutex_lock(&fip->ctlr_mutex); - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); kfree_skb(fip->flogi_req); fip->flogi_req = NULL; list_for_each_entry(fcf, &fip->fcfs, list) fcf->flogi_sent = 0; - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); sel = fip->sel_fcf; if (sel && ether_addr_equal(sel->fcf_mac, fip->dest_addr)) @@ -700,7 +699,6 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, { struct fc_frame *fp; struct fc_frame_header *fh; - unsigned long flags; u16 old_xid; u8 op; u8 mac[ETH_ALEN]; @@ -734,11 +732,11 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, op = FIP_DT_FLOGI; if (fip->mode == FIP_MODE_VN2VN) break; - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); kfree_skb(fip->flogi_req); fip->flogi_req = skb; fip->flogi_req_send = 1; - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); schedule_work(&fip->timer_work); return -EINPROGRESS; case ELS_FDISC: @@ -1707,11 +1705,10 @@ static int fcoe_ctlr_flogi_send_locked(struct fcoe_ctlr *fip) static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; - unsigned long flags; int error; mutex_lock(&fip->ctlr_mutex); - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); LIBFCOE_FIP_DBG(fip, "re-sending FLOGI - reselect\n"); fcf = fcoe_ctlr_select(fip); if (!fcf || fcf->flogi_sent) { @@ -1722,7 +1719,7 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) fcoe_ctlr_solicit(fip, NULL); error = fcoe_ctlr_flogi_send_locked(fip); } - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); mutex_unlock(&fip->ctlr_mutex); return error; } @@ -1739,9 +1736,8 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; - unsigned long flags; - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); fcf = fip->sel_fcf; if (!fcf || !fip->flogi_req_send) goto unlock; @@ -1768,7 +1764,7 @@ static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) } else /* XXX */ LIBFCOE_FIP_DBG(fip, "No FCF selected - defer send\n"); unlock: - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); } /** diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index a95936b18f695..7ceb982040a5d 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -330,6 +330,7 @@ enum storvsc_request_type { */ static int storvsc_ringbuffer_size = (128 * 1024); +static int aligned_ringbuffer_size; static u32 max_outstanding_req_per_channel; static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth); @@ -687,8 +688,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc) new_sc->next_request_id_callback = storvsc_next_request_id; ret = vmbus_open(new_sc, - storvsc_ringbuffer_size, - storvsc_ringbuffer_size, + aligned_ringbuffer_size, + aligned_ringbuffer_size, (void *)&props, sizeof(struct vmstorage_channel_properties), storvsc_on_channel_callback, new_sc); @@ -1973,7 +1974,7 @@ static int storvsc_probe(struct hv_device *device, dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1); stor_device->port_number = host->host_no; - ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc); + ret = storvsc_connect_to_vsp(device, aligned_ringbuffer_size, is_fc); if (ret) goto err_out1; @@ -2164,7 +2165,7 @@ static int storvsc_resume(struct hv_device *hv_dev) { int ret; - ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size, + ret = storvsc_connect_to_vsp(hv_dev, aligned_ringbuffer_size, hv_dev_is_fc(hv_dev)); return ret; } @@ -2198,8 +2199,9 @@ static int __init storvsc_drv_init(void) * the ring buffer indices) by the max request size (which is * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64) */ + aligned_ringbuffer_size = VMBUS_RING_SIZE(storvsc_ringbuffer_size); max_outstanding_req_per_channel = - ((storvsc_ringbuffer_size - PAGE_SIZE) / + ((aligned_ringbuffer_size - PAGE_SIZE) / ALIGN(MAX_MULTIPAGE_BUFFER_PACKET + sizeof(struct vstor_packet) + sizeof(u64), sizeof(u64))); diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 272bc871a848b..e2d3e3ec13789 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -2,6 +2,7 @@ // Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved. // Copyright (C) 2008 Juergen Beisert +#include #include #include #include @@ -660,15 +661,15 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, << MX51_ECSPI_CTRL_BL_OFFSET; else { if (spi_imx->usedma) { - ctrl |= (spi_imx->bits_per_word * - spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1) + ctrl |= (spi_imx->bits_per_word - 1) << MX51_ECSPI_CTRL_BL_OFFSET; } else { if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST) - ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1) + ctrl |= (MX51_ECSPI_CTRL_MAX_BURST * BITS_PER_BYTE - 1) << MX51_ECSPI_CTRL_BL_OFFSET; else - ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1) + ctrl |= spi_imx->count / DIV_ROUND_UP(spi_imx->bits_per_word, + BITS_PER_BYTE) * spi_imx->bits_per_word << MX51_ECSPI_CTRL_BL_OFFSET; } } diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c index 03aab661be9d3..e982d3189fdce 100644 --- a/drivers/spi/spi-ppc4xx.c +++ b/drivers/spi/spi-ppc4xx.c @@ -166,10 +166,8 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) int scr; u8 cdm = 0; u32 speed; - u8 bits_per_word; /* Start with the generic configuration for this device. */ - bits_per_word = spi->bits_per_word; speed = spi->max_speed_hz; /* @@ -177,9 +175,6 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) * the transfer to overwrite the generic configuration with zeros. */ if (t) { - if (t->bits_per_word) - bits_per_word = t->bits_per_word; - if (t->speed_hz) speed = min(t->speed_hz, spi->max_speed_hz); } diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 46db6d91542a4..2d0883a640827 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -608,7 +608,7 @@ static void ad5933_work(struct work_struct *work) struct ad5933_state, work.work); struct iio_dev *indio_dev = i2c_get_clientdata(st->client); __be16 buf[2]; - int val[2]; + u16 val[2]; unsigned char status; int ret; diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index cf9f2370878a8..580277dc91152 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -203,7 +203,7 @@ struct tb_regs_switch_header { #define ROUTER_CS_5_WOP BIT(1) #define ROUTER_CS_5_WOU BIT(2) #define ROUTER_CS_5_WOD BIT(3) -#define ROUTER_CS_5_C3S BIT(23) +#define ROUTER_CS_5_CNS BIT(23) #define ROUTER_CS_5_PTO BIT(24) #define ROUTER_CS_5_UTO BIT(25) #define ROUTER_CS_5_HCO BIT(26) diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 05ddb224c4649..13c779e23011b 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -290,7 +290,7 @@ int usb4_switch_setup(struct tb_switch *sw) } /* TBT3 supported by the CM */ - val |= ROUTER_CS_5_C3S; + val &= ~ROUTER_CS_5_CNS; return tb_sw_write(sw, &val, TB_CFG_SWITCH, ROUTER_CS_5, 1); } diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index db3204d2a3053..3865c7f6dba8a 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -237,6 +237,14 @@ #define MAX310x_REV_MASK (0xf8) #define MAX310X_WRITE_BIT 0x80 +/* Port startup definitions */ +#define MAX310X_PORT_STARTUP_WAIT_RETRIES 20 /* Number of retries */ +#define MAX310X_PORT_STARTUP_WAIT_DELAY_MS 10 /* Delay between retries */ + +/* Crystal-related definitions */ +#define MAX310X_XTAL_WAIT_RETRIES 20 /* Number of retries */ +#define MAX310X_XTAL_WAIT_DELAY_MS 10 /* Delay between retries */ + /* MAX3107 specific */ #define MAX3107_REV_ID (0xa0) @@ -583,7 +591,7 @@ static int max310x_update_best_err(unsigned long f, long *besterr) return 1; } -static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, +static s32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, unsigned long freq, bool xtal) { unsigned int div, clksrc, pllcfg = 0; @@ -641,12 +649,20 @@ static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, /* Wait for crystal */ if (xtal) { - unsigned int val; - msleep(10); - regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val); - if (!(val & MAX310X_STS_CLKREADY_BIT)) { - dev_warn(dev, "clock is not stable yet\n"); - } + bool stable = false; + unsigned int try = 0, val = 0; + + do { + msleep(MAX310X_XTAL_WAIT_DELAY_MS); + regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val); + + if (val & MAX310X_STS_CLKREADY_BIT) + stable = true; + } while (!stable && (++try < MAX310X_XTAL_WAIT_RETRIES)); + + if (!stable) + return dev_err_probe(dev, -EAGAIN, + "clock is not stable\n"); } return bestfreq; @@ -1271,7 +1287,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty { int i, ret, fmin, fmax, freq; struct max310x_port *s; - u32 uartclk = 0; + s32 uartclk = 0; bool xtal; for (i = 0; i < devtype->nr; i++) @@ -1334,6 +1350,9 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty goto out_clk; for (i = 0; i < devtype->nr; i++) { + bool started = false; + unsigned int try = 0, val = 0; + /* Reset port */ regmap_write(regmaps[i], MAX310X_MODE2_REG, MAX310X_MODE2_RST_BIT); @@ -1342,13 +1361,27 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty /* Wait for port startup */ do { - regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &ret); - } while (ret != 0x01); + msleep(MAX310X_PORT_STARTUP_WAIT_DELAY_MS); + regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &val); + + if (val == 0x01) + started = true; + } while (!started && (++try < MAX310X_PORT_STARTUP_WAIT_RETRIES)); + + if (!started) { + ret = dev_err_probe(dev, -EAGAIN, "port reset failed\n"); + goto out_uart; + } regmap_write(regmaps[i], MAX310X_MODE1_REG, devtype->mode1); } uartclk = max310x_set_ref_clk(dev, s, freq, xtal); + if (uartclk < 0) { + ret = uartclk; + goto out_uart; + } + dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk); for (i = 0; i < devtype->nr; i++) { diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index 8eeecf8ad3596..380a8b0590e34 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -605,13 +605,16 @@ static void mxs_auart_tx_chars(struct mxs_auart_port *s) return; } - pending = uart_port_tx(&s->port, ch, + pending = uart_port_tx_flags(&s->port, ch, UART_TX_NOSTOP, !(mxs_read(s, REG_STAT) & AUART_STAT_TXFF), mxs_write(ch, s, REG_DATA)); if (pending) mxs_set(AUART_INTR_TXIEN, s, REG_INTR); else mxs_clr(AUART_INTR_TXIEN, s, REG_INTR); + + if (uart_tx_stopped(&s->port)) + mxs_auart_stop_tx(&s->port); } static void mxs_auart_rx_char(struct mxs_auart_port *s) diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h index d9bb3d3f026e6..2a38e1eb65466 100644 --- a/drivers/usb/chipidea/ci.h +++ b/drivers/usb/chipidea/ci.h @@ -176,6 +176,7 @@ struct hw_bank { * @enabled_otg_timer_bits: bits of enabled otg timers * @next_otg_timer: next nearest enabled timer to be expired * @work: work for role changing + * @power_lost_work: work for power lost handling * @wq: workqueue thread * @qh_pool: allocation pool for queue heads * @td_pool: allocation pool for transfer descriptors @@ -226,6 +227,7 @@ struct ci_hdrc { enum otg_fsm_timer next_otg_timer; struct usb_role_switch *role_switch; struct work_struct work; + struct work_struct power_lost_work; struct workqueue_struct *wq; struct dma_pool *qh_pool; diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 85e9c3ab66e94..ca71df4f32e4c 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -856,6 +856,27 @@ static int ci_extcon_register(struct ci_hdrc *ci) return 0; } +static void ci_power_lost_work(struct work_struct *work) +{ + struct ci_hdrc *ci = container_of(work, struct ci_hdrc, power_lost_work); + enum ci_role role; + + disable_irq_nosync(ci->irq); + pm_runtime_get_sync(ci->dev); + if (!ci_otg_is_fsm_mode(ci)) { + role = ci_get_role(ci); + + if (ci->role != role) { + ci_handle_id_switch(ci); + } else if (role == CI_ROLE_GADGET) { + if (ci->is_otg && hw_read_otgsc(ci, OTGSC_BSV)) + usb_gadget_vbus_connect(&ci->gadget); + } + } + pm_runtime_put_sync(ci->dev); + enable_irq(ci->irq); +} + static DEFINE_IDA(ci_ida); struct platform_device *ci_hdrc_add_device(struct device *dev, @@ -1045,6 +1066,8 @@ static int ci_hdrc_probe(struct platform_device *pdev) spin_lock_init(&ci->lock); mutex_init(&ci->mutex); + INIT_WORK(&ci->power_lost_work, ci_power_lost_work); + ci->dev = dev; ci->platdata = dev_get_platdata(dev); ci->imx28_write_fix = !!(ci->platdata->flags & @@ -1396,25 +1419,6 @@ static int ci_suspend(struct device *dev) return 0; } -static void ci_handle_power_lost(struct ci_hdrc *ci) -{ - enum ci_role role; - - disable_irq_nosync(ci->irq); - if (!ci_otg_is_fsm_mode(ci)) { - role = ci_get_role(ci); - - if (ci->role != role) { - ci_handle_id_switch(ci); - } else if (role == CI_ROLE_GADGET) { - if (ci->is_otg && hw_read_otgsc(ci, OTGSC_BSV)) - usb_gadget_vbus_connect(&ci->gadget); - } - } - - enable_irq(ci->irq); -} - static int ci_resume(struct device *dev) { struct ci_hdrc *ci = dev_get_drvdata(dev); @@ -1446,7 +1450,7 @@ static int ci_resume(struct device *dev) ci_role(ci)->resume(ci, power_lost); if (power_lost) - ci_handle_power_lost(ci); + queue_work(system_freezable_wq, &ci->power_lost_work); if (ci->supports_runtime_pm) { pm_runtime_disable(dev); diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 84d91b1c1eed5..0886b19d2e1c8 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -301,7 +301,7 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi) return ret; } - root = debugfs_create_dir(dev_name(dev), ulpi_root); + root = debugfs_create_dir(dev_name(&ulpi->dev), ulpi_root); debugfs_create_file("regs", 0444, root, ulpi, &ulpi_regs_fops); dev_dbg(&ulpi->dev, "registered ULPI PHY: vendor %04x, product %04x\n", diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index bd27741327dfb..71635dfa741d2 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2047,9 +2047,19 @@ static void update_port_device_state(struct usb_device *udev) if (udev->parent) { hub = usb_hub_to_struct_hub(udev->parent); - port_dev = hub->ports[udev->portnum - 1]; - WRITE_ONCE(port_dev->state, udev->state); - sysfs_notify_dirent(port_dev->state_kn); + + /* + * The Link Layer Validation System Driver (lvstest) + * has a test step to unbind the hub before running the + * rest of the procedure. This triggers hub_disconnect + * which will set the hub's maxchild to 0, further + * resulting in usb_hub_to_struct_hub returning NULL. + */ + if (hub) { + port_dev = hub->ports[udev->portnum - 1]; + WRITE_ONCE(port_dev->state, udev->state); + sysfs_notify_dirent(port_dev->state_kn); + } } } @@ -2380,17 +2390,25 @@ static int usb_enumerate_device_otg(struct usb_device *udev) } } else if (desc->bLength == sizeof (struct usb_otg_descriptor)) { - /* Set a_alt_hnp_support for legacy otg device */ - err = usb_control_msg(udev, - usb_sndctrlpipe(udev, 0), - USB_REQ_SET_FEATURE, 0, - USB_DEVICE_A_ALT_HNP_SUPPORT, - 0, NULL, 0, - USB_CTRL_SET_TIMEOUT); - if (err < 0) - dev_err(&udev->dev, - "set a_alt_hnp_support failed: %d\n", - err); + /* + * We are operating on a legacy OTP device + * These should be told that they are operating + * on the wrong port if we have another port that does + * support HNP + */ + if (bus->otg_port != 0) { + /* Set a_alt_hnp_support for legacy otg device */ + err = usb_control_msg(udev, + usb_sndctrlpipe(udev, 0), + USB_REQ_SET_FEATURE, 0, + USB_DEVICE_A_ALT_HNP_SUPPORT, + 0, NULL, 0, + USB_CTRL_SET_TIMEOUT); + if (err < 0) + dev_err(&udev->dev, + "set a_alt_hnp_support failed: %d\n", + err); + } } } #endif diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 89de363ecf8bb..4c8dd67246788 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4703,15 +4703,13 @@ int dwc3_gadget_suspend(struct dwc3 *dwc) unsigned long flags; int ret; - if (!dwc->gadget_driver) - return 0; - ret = dwc3_gadget_soft_disconnect(dwc); if (ret) goto err; spin_lock_irqsave(&dwc->lock, flags); - dwc3_disconnect_gadget(dwc); + if (dwc->gadget_driver) + dwc3_disconnect_gadget(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 722a3ab2b3379..c265a1f62fc14 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -545,21 +545,37 @@ static int start_transfer(struct fsg_dev *fsg, struct usb_ep *ep, static bool start_in_transfer(struct fsg_common *common, struct fsg_buffhd *bh) { + int rc; + if (!fsg_is_set(common)) return false; bh->state = BUF_STATE_SENDING; - if (start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq)) + rc = start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq); + if (rc) { bh->state = BUF_STATE_EMPTY; + if (rc == -ESHUTDOWN) { + common->running = 0; + return false; + } + } return true; } static bool start_out_transfer(struct fsg_common *common, struct fsg_buffhd *bh) { + int rc; + if (!fsg_is_set(common)) return false; bh->state = BUF_STATE_RECEIVING; - if (start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq)) + rc = start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq); + if (rc) { bh->state = BUF_STATE_FULL; + if (rc == -ESHUTDOWN) { + common->running = 0; + return false; + } + } return true; } diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 47ae2d520fda5..6d455ca76125e 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4862,7 +4862,8 @@ static void run_state_machine(struct tcpm_port *port) break; case PORT_RESET: tcpm_reset_port(port); - tcpm_set_cc(port, TYPEC_CC_OPEN); + tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ? + TYPEC_CC_RD : tcpm_rp_cc(port)); tcpm_set_state(port, PORT_RESET_WAIT_OFF, PD_T_ERROR_RECOVERY); break; diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 61b64558f96c5..8f9dff993b3da 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -935,7 +935,9 @@ static void ucsi_handle_connector_change(struct work_struct *work) clear_bit(EVENT_PENDING, &con->ucsi->flags); + mutex_lock(&ucsi->ppm_lock); ret = ucsi_acknowledge_connector_change(ucsi); + mutex_unlock(&ucsi->ppm_lock); if (ret) dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret); diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c index 6bbf490ac4010..fa222080887d5 100644 --- a/drivers/usb/typec/ucsi/ucsi_acpi.c +++ b/drivers/usb/typec/ucsi/ucsi_acpi.c @@ -73,9 +73,13 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, const void *val, size_t val_len) { struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); + bool ack = UCSI_COMMAND(*(u64 *)val) == UCSI_ACK_CC_CI; int ret; - set_bit(COMMAND_PENDING, &ua->flags); + if (ack) + set_bit(ACK_PENDING, &ua->flags); + else + set_bit(COMMAND_PENDING, &ua->flags); ret = ucsi_acpi_async_write(ucsi, offset, val, val_len); if (ret) @@ -85,7 +89,10 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, ret = -ETIMEDOUT; out_clear_bit: - clear_bit(COMMAND_PENDING, &ua->flags); + if (ack) + clear_bit(ACK_PENDING, &ua->flags); + else + clear_bit(COMMAND_PENDING, &ua->flags); return ret; } @@ -142,8 +149,10 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data) if (UCSI_CCI_CONNECTOR(cci)) ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci)); - if (test_bit(COMMAND_PENDING, &ua->flags) && - cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE)) + if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags)) + complete(&ua->complete); + if (cci & UCSI_CCI_COMMAND_COMPLETE && + test_bit(COMMAND_PENDING, &ua->flags)) complete(&ua->complete); } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 5a97db9888107..3afd435dc2c7a 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1467,6 +1467,7 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans, */ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) { + LIST_HEAD(retry_list); struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; @@ -1488,6 +1489,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { + u64 used; int trimming; block_group = list_first_entry(&fs_info->unused_bgs, @@ -1523,9 +1525,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) goto next; } + spin_lock(&space_info->lock); spin_lock(&block_group->lock); - if (block_group->reserved || block_group->pinned || - block_group->used || block_group->ro || + if (btrfs_is_block_group_used(block_group) || block_group->ro || list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have @@ -1535,10 +1537,49 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) */ trace_btrfs_skip_unused_block_group(block_group); spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + up_write(&space_info->groups_sem); + goto next; + } + + /* + * The block group may be unused but there may be space reserved + * accounting with the existence of that block group, that is, + * space_info->bytes_may_use was incremented by a task but no + * space was yet allocated from the block group by the task. + * That space may or may not be allocated, as we are generally + * pessimistic about space reservation for metadata as well as + * for data when using compression (as we reserve space based on + * the worst case, when data can't be compressed, and before + * actually attempting compression, before starting writeback). + * + * So check if the total space of the space_info minus the size + * of this block group is less than the used space of the + * space_info - if that's the case, then it means we have tasks + * that might be relying on the block group in order to allocate + * extents, and add back the block group to the unused list when + * we finish, so that we retry later in case no tasks ended up + * needing to allocate extents from the block group. + */ + used = btrfs_space_info_used(space_info, true); + if (space_info->total_bytes - block_group->length < used) { + /* + * Add a reference for the list, compensate for the ref + * drop under the "next" label for the + * fs_info->unused_bgs list. + */ + btrfs_get_block_group(block_group); + list_add_tail(&block_group->bg_list, &retry_list); + + trace_btrfs_skip_unused_block_group(block_group); + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); /* We don't want to force the issue, only flip if it's ok. */ ret = inc_block_group_ro(block_group, 0); @@ -1662,12 +1703,16 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } + list_splice_tail(&retry_list, &fs_info->unused_bgs); spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); return; flip_async: btrfs_end_transaction(trans); + spin_lock(&fs_info->unused_bgs_lock); + list_splice_tail(&retry_list, &fs_info->unused_bgs); + spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); btrfs_put_block_group(block_group); btrfs_discard_punt_unused_bgs_list(fs_info); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 2bdbcb834f954..089979981e4aa 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -255,6 +255,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) return (block_group->start + block_group->length); } +static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg) +{ + lockdep_assert_held(&bg->lock); + + return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0); +} + static inline bool btrfs_is_block_group_data_only( struct btrfs_block_group *block_group) { diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index eef341bbcc60e..4a7aefa5f9cf9 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -245,7 +245,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv = &inode->block_rsv; u64 reserve_size = 0; u64 qgroup_rsv_size = 0; - u64 csum_leaves; unsigned outstanding_extents; lockdep_assert_held(&inode->lock); @@ -260,10 +259,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, outstanding_extents); reserve_size += btrfs_calc_metadata_size(fs_info, 1); } - csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, - inode->csum_bytes); - reserve_size += btrfs_calc_insert_metadata_size(fs_info, - csum_leaves); + if (!(inode->flags & BTRFS_INODE_NODATASUM)) { + u64 csum_leaves; + + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes); + reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves); + } /* * For qgroup rsv, the calculation is very simple: * account one nodesize for each outstanding extent @@ -278,14 +279,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, spin_unlock(&block_rsv->lock); } -static void calc_inode_reservations(struct btrfs_fs_info *fs_info, +static void calc_inode_reservations(struct btrfs_inode *inode, u64 num_bytes, u64 disk_num_bytes, u64 *meta_reserve, u64 *qgroup_reserve) { + struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 nr_extents = count_max_extents(fs_info, num_bytes); - u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + u64 csum_leaves; u64 inode_update = btrfs_calc_metadata_size(fs_info, 1); + if (inode->flags & BTRFS_INODE_NODATASUM) + csum_leaves = 0; + else + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + *meta_reserve = btrfs_calc_insert_metadata_size(fs_info, nr_extents + csum_leaves); @@ -337,7 +344,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, * everything out and try again, which is bad. This way we just * over-reserve slightly, and clean up the mess when we are done. */ - calc_inode_reservations(fs_info, num_bytes, disk_num_bytes, + calc_inode_reservations(inode, num_bytes, disk_num_bytes, &meta_reserve, &qgroup_reserve); ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true, noflush); @@ -358,7 +365,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, nr_extents = count_max_extents(fs_info, num_bytes); spin_lock(&inode->lock); btrfs_mod_outstanding_extents(inode, nr_extents); - inode->csum_bytes += disk_num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes += disk_num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); @@ -392,7 +400,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, num_bytes = ALIGN(num_bytes, fs_info->sectorsize); spin_lock(&inode->lock); - inode->csum_bytes -= num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes -= num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b79781df70714..ffb9ae303f2a3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1311,8 +1311,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { - /* Shouldn't get preallocated anon_dev for cached roots */ - ASSERT(!anon_dev); + /* + * Some other caller may have read out the newly inserted + * subvolume already (for things like backref walk etc). Not + * that common but still possible. In that case, we just need + * to free the anon_dev. + */ + if (unlikely(anon_dev)) { + free_anon_bdev(anon_dev); + anon_dev = 0; + } + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f250e2083c7eb..ca79c2b8adc46 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3168,8 +3168,23 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent) unwritten_start += logical_len; clear_extent_uptodate(io_tree, unwritten_start, end, NULL); - /* Drop extent maps for the part of the extent we didn't write. */ - btrfs_drop_extent_map_range(inode, unwritten_start, end, false); + /* + * Drop extent maps for the part of the extent we didn't write. + * + * We have an exception here for the free_space_inode, this is + * because when we do btrfs_get_extent() on the free space inode + * we will search the commit root. If this is a new block group + * we won't find anything, and we will trip over the assert in + * writepage where we do ASSERT(em->block_start != + * EXTENT_MAP_HOLE). + * + * Theoretically we could also skip this for any NOCOW extent as + * we don't mess with the extent map tree in the NOCOW case, but + * for now simply skip this if we are the free space inode. + */ + if (!btrfs_is_free_space_inode(inode)) + btrfs_drop_extent_map_range(inode, unwritten_start, + end, false); /* * If the ordered extent had an IOERR or something else went @@ -10223,6 +10238,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE) return -EINVAL; + /* + * Compressed extents should always have checksums, so error out if we + * have a NOCOW file or inode was created while mounted with NODATASUM. + */ + if (inode->flags & BTRFS_INODE_NODATASUM) + return -EINVAL; + orig_count = iov_iter_count(from); /* The extent size must be sane. */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 908215928d6a6..a26a909a5ad16 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3810,6 +3810,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } + if (sa->create && is_fstree(sa->qgroupid)) { + ret = -EINVAL; + goto out; + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a006f5160e6b4..9acdd0f91a5ae 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1659,6 +1659,15 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) return ret; } +static bool qgroup_has_usage(struct btrfs_qgroup *qgroup) +{ + return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 || + qgroup->excl > 0 || qgroup->excl_cmpr > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0); +} + int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1678,6 +1687,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) goto out; } + if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) { + ret = -EBUSY; + goto out; + } + /* Check if there are no children of this qgroup */ if (!list_empty(&qgroup->members)) { ret = -EBUSY; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index db94eefda27e2..994c0be8055c6 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -8111,7 +8111,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) } if (arg->flags & ~BTRFS_SEND_FLAG_MASK) { - ret = -EINVAL; + ret = -EOPNOTSUPP; goto out; } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 7f7e5f5d643c6..fc9f8f1a9036d 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1415,7 +1415,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, if (flushing & CEPH_CAP_XATTR_EXCL) { arg->old_xattr_buf = __ceph_build_xattrs_blob(ci); arg->xattr_version = ci->i_xattrs.version; - arg->xattr_buf = ci->i_xattrs.blob; + arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob); } else { arg->xattr_buf = NULL; arg->old_xattr_buf = NULL; @@ -1513,6 +1513,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci) encode_cap_msg(msg, arg); ceph_con_send(&arg->session->s_con, msg); ceph_buffer_put(arg->old_xattr_buf); + ceph_buffer_put(arg->xattr_buf); if (arg->wake) wake_up_all(&ci->i_cap_wq); } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 529ca47da0353..7a2d42a84807a 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1909,11 +1909,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); - this_cpu_inc(discard_pa_seq); - e4b->bd_info->bb_free += count; - if (first < e4b->bd_info->bb_first_free) - e4b->bd_info->bb_first_free = first; - /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ @@ -1927,23 +1922,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; + /* + * Fastcommit replay can free already freed blocks which + * corrupts allocation info. Regenerate it. + */ + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + mb_regenerate_buddy(e4b); + goto check; + } + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); - if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block (bit %u); block bitmap corrupt.", - block); - ext4_mark_group_bitmap_corrupted( - sb, e4b->bd_group, + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, blocknr, + "freeing already freed block (bit %u); block bitmap corrupt.", + block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); - } else { - mb_regenerate_buddy(e4b); - } - goto done; + return; } + this_cpu_inc(discard_pa_seq); + e4b->bd_info->bb_free += count; + if (first < e4b->bd_info->bb_first_free) + e4b->bd_info->bb_first_free = first; + /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; @@ -1968,9 +1971,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); -done: mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); +check: mb_check_buddy(e4b); } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 18a9e7c479754..e6976716e85d4 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -619,6 +619,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, goto out; o_end = o_start + len; + *moved_len = 0; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; @@ -673,7 +674,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ - move_extent_per_page(o_filp, donor_inode, + *moved_len += move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); @@ -683,9 +684,6 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, o_start += cur_len; d_start += cur_len; } - *moved_len = o_start - orig_blk; - if (*moved_len > len) - *moved_len = len; out: if (*moved_len) { diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 60fce26ff9378..ac519515ef6c0 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -123,6 +123,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); + vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has @@ -164,10 +165,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; + + vm_flags = vma->vm_flags; + /* + * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip + * reserving here. Note: only for SHM hugetlbfs file, the inode + * flag S_PRIVATE is set. + */ + if (inode->i_flags & S_PRIVATE) + vm_flags |= VM_NORESERVE; + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, - vma->vm_flags)) + vm_flags)) goto out; ret = 0; @@ -1390,6 +1401,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; + struct hstate *h; char *rest; unsigned long ps; int opt; @@ -1434,11 +1446,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_pagesize: ps = memparse(param->string, &rest); - ctx->hstate = size_to_hstate(ps); - if (!ctx->hstate) { + h = size_to_hstate(ps); + if (!h) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } + ctx->hstate = h; return 0; case Opt_min_size: diff --git a/fs/namespace.c b/fs/namespace.c index bfc5cff0e196f..e6c61d4997ccf 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4470,10 +4470,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. - * If this is a detached mount make sure it has an anonymous mount - * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE. + * + * If this mount doesn't have a parent it's most often simply a + * detached mount with an anonymous mount namespace. IOW, something + * that's simply not attached yet. But there are apparently also users + * that do change mount properties on the rootfs itself. That obviously + * neither has a parent nor is it a detached mount so we cannot + * unconditionally check for detached mounts. */ - if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns))) + if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f4cccbf664ceb..522596060252f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4944,10 +4944,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); return false; } @@ -5556,12 +5554,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (status) goto out_unlock; + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 740ce26d1e765..0505feef79f4a 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -105,7 +105,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - wait_for_stable_page(page); + /* + * Since checksumming including data blocks is performed to determine + * the validity of the log to be written and used for recovery, it is + * necessary to wait for writeback to finish here, regardless of the + * stable write requirement of the backing device. + */ + wait_on_page_writeback(page); out: sb_end_pagefault(inode->i_sb); return vmf_fs_error(ret); diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 0955b657938ff..a9b8d77c8c1d5 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, struct nilfs_recovery_block *rb, - struct page *page) + loff_t pos, struct page *page) { struct buffer_head *bh_org; + size_t from = pos & ~PAGE_MASK; void *kaddr; bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize); @@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, return -EIO; kaddr = kmap_atomic(page); - memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size); + memcpy(kaddr + from, bh_org->b_data, bh_org->b_size); kunmap_atomic(kaddr); brelse(bh_org); return 0; @@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - err = nilfs_recovery_copy_block(nilfs, rb, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, page); if (unlikely(err)) goto failed_page; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 7ec16879756e8..a03e37207f487 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1704,7 +1704,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); @@ -1715,6 +1714,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } break; } + set_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_begin_page_io(fs_page); fs_page = bh->b_page; @@ -1800,7 +1800,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { @@ -1809,6 +1808,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) } break; } + clear_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, err); fs_page = bh->b_page; @@ -1896,8 +1896,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) BIT(BH_Delay) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Redirected)); - set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh == segbuf->sb_super_root) { + set_buffer_uptodate(bh); + clear_buffer_dirty(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; @@ -1905,6 +1906,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) update_sr = true; break; } + set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, 0); fs_page = bh->b_page; diff --git a/fs/proc/array.c b/fs/proc/array.c index 2c2efbe685d87..37b8061d84bb7 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -511,7 +511,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = 0; + cutime = cstime = 0; cgtime = gtime = 0; if (lock_task_sighand(task, &flags)) { @@ -545,7 +545,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, min_flt += sig->min_flt; maj_flt += sig->maj_flt; - thread_group_cputime_adjusted(task, &utime, &stime); gtime += sig->gtime; if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) @@ -561,10 +560,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (permitted && (!whole || num_threads < 2)) wchan = !task_is_running(task); - if (!whole) { + + if (whole) { + thread_group_cputime_adjusted(task, &utime, &stime); + } else { + task_cputime_adjusted(task, &utime, &stime); min_flt = task->min_flt; maj_flt = task->maj_flt; - task_cputime_adjusted(task, &utime, &stime); gtime = task_gtime(task); } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 0ed6eb915c6ab..19440255944b0 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -3426,8 +3426,18 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx) * the user on mount */ if ((cifs_sb->ctx->wsize == 0) || - (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx))) - cifs_sb->ctx->wsize = server->ops->negotiate_wsize(tcon, ctx); + (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx))) { + cifs_sb->ctx->wsize = + round_down(server->ops->negotiate_wsize(tcon, ctx), PAGE_SIZE); + /* + * in the very unlikely event that the server sent a max write size under PAGE_SIZE, + * (which would get rounded down to 0) then reset wsize to absolute minimum eg 4096 + */ + if (cifs_sb->ctx->wsize == 0) { + cifs_sb->ctx->wsize = PAGE_SIZE; + cifs_dbg(VFS, "wsize too small, reset to minimum ie PAGE_SIZE, usually 4096\n"); + } + } if ((cifs_sb->ctx->rsize == 0) || (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx))) cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx); diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index a3493da12ad1e..75f2c8734ff56 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1107,6 +1107,17 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, case Opt_wsize: ctx->wsize = result.uint_32; ctx->got_wsize = true; + if (ctx->wsize % PAGE_SIZE != 0) { + ctx->wsize = round_down(ctx->wsize, PAGE_SIZE); + if (ctx->wsize == 0) { + ctx->wsize = PAGE_SIZE; + cifs_dbg(VFS, "wsize too small, reset to minimum %ld\n", PAGE_SIZE); + } else { + cifs_dbg(VFS, + "wsize rounded down to %d to multiple of PAGE_SIZE %ld\n", + ctx->wsize, PAGE_SIZE); + } + } break; case Opt_acregmax: ctx->acregmax = HZ * result.uint_32; diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c index a6968573b775e..4a517b280f2b7 100644 --- a/fs/smb/client/namespace.c +++ b/fs/smb/client/namespace.c @@ -168,6 +168,21 @@ static char *automount_fullpath(struct dentry *dentry, void *page) return s; } +static void fs_context_set_ids(struct smb3_fs_context *ctx) +{ + kuid_t uid = current_fsuid(); + kgid_t gid = current_fsgid(); + + if (ctx->multiuser) { + if (!ctx->uid_specified) + ctx->linux_uid = uid; + if (!ctx->gid_specified) + ctx->linux_gid = gid; + } + if (!ctx->cruid_specified) + ctx->cred_uid = uid; +} + /* * Create a vfsmount that we can automount */ @@ -205,6 +220,7 @@ static struct vfsmount *cifs_do_automount(struct path *path) tmp.leaf_fullpath = NULL; tmp.UNC = tmp.prepath = NULL; tmp.dfs_root_ses = NULL; + fs_context_set_ids(&tmp); rc = smb3_fs_context_dup(ctx, &tmp); if (rc) { diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index e33ed0fbc318e..5850f861e7e13 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -619,7 +619,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, goto out; } - while (bytes_left >= sizeof(*p)) { + while (bytes_left >= (ssize_t)sizeof(*p)) { memset(&tmp_iface, 0, sizeof(tmp_iface)); tmp_iface.speed = le64_to_cpu(p->LinkSpeed); tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 6ddfe3fef55f3..3e885cdc5ffc7 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -6173,8 +6173,10 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); - if (err) + if (err) { + kvfree(aux_payload_buf); goto out; + } kvfree(rpc_resp); } else { err = ksmbd_iov_pin_rsp(work, (void *)rsp, @@ -6384,8 +6386,10 @@ int smb2_read(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); - if (err) + if (err) { + kvfree(aux_payload_buf); goto out; + } ksmbd_fd_put(work, fp); return 0; diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index efbdc47c74dcf..110e8a2721890 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -2,8 +2,9 @@ /* * event_inode.c - part of tracefs, a pseudo file system for activating tracing * - * Copyright (C) 2020-23 VMware Inc, author: Steven Rostedt (VMware) + * Copyright (C) 2020-23 VMware Inc, author: Steven Rostedt * Copyright (C) 2020-23 VMware Inc, author: Ajay Kaher + * Copyright (C) 2023 Google, author: Steven Rostedt * * eventfs is used to dynamically create inodes and dentries based on the * meta data provided by the tracing system. @@ -23,51 +24,32 @@ #include #include "internal.h" -struct eventfs_inode { - struct list_head e_top_files; -}; - /* - * struct eventfs_file - hold the properties of the eventfs files and - * directories. - * @name: the name of the file or directory to create - * @d_parent: holds parent's dentry - * @dentry: once accessed holds dentry - * @list: file or directory to be added to parent directory - * @ei: list of files and directories within directory - * @fop: file_operations for file or directory - * @iop: inode_operations for file or directory - * @data: something that the caller will want to get to later on - * @is_freed: Flag set if the eventfs is on its way to be freed - * @mode: the permission that the file or directory should have - * @uid: saved uid if changed - * @gid: saved gid if changed + * eventfs_mutex protects the eventfs_inode (ei) dentry. Any access + * to the ei->dentry must be done under this mutex and after checking + * if ei->is_freed is not set. When ei->is_freed is set, the dentry + * is on its way to being freed after the last dput() is made on it. */ -struct eventfs_file { - const char *name; - struct dentry *d_parent; - struct dentry *dentry; - struct list_head list; - struct eventfs_inode *ei; - const struct file_operations *fop; - const struct inode_operations *iop; - /* - * Union - used for deletion - * @llist: for calling dput() if needed after RCU - * @rcu: eventfs_file to delete in RCU - */ - union { - struct llist_node llist; - struct rcu_head rcu; - }; - void *data; - unsigned int is_freed:1; - unsigned int mode:31; - kuid_t uid; - kgid_t gid; -}; - static DEFINE_MUTEX(eventfs_mutex); + +/* Choose something "unique" ;-) */ +#define EVENTFS_FILE_INODE_INO 0x12c4e37 + +/* Just try to make something consistent and unique */ +static int eventfs_dir_ino(struct eventfs_inode *ei) +{ + if (!ei->ino) + ei->ino = get_next_ino(); + + return ei->ino; +} + +/* + * The eventfs_inode (ei) itself is protected by SRCU. It is released from + * its parent's list and will have is_freed set (under eventfs_mutex). + * After the SRCU grace period is over and the last dput() is called + * the ei is freed. + */ DEFINE_STATIC_SRCU(eventfs_srcu); /* Mode is unsigned short, use the upper bits for flags */ @@ -75,60 +57,202 @@ enum { EVENTFS_SAVE_MODE = BIT(16), EVENTFS_SAVE_UID = BIT(17), EVENTFS_SAVE_GID = BIT(18), + EVENTFS_TOPLEVEL = BIT(19), }; #define EVENTFS_MODE_MASK (EVENTFS_SAVE_MODE - 1) +/* + * eventfs_inode reference count management. + * + * NOTE! We count only references from dentries, in the + * form 'dentry->d_fsdata'. There are also references from + * directory inodes ('ti->private'), but the dentry reference + * count is always a superset of the inode reference count. + */ +static void release_ei(struct kref *ref) +{ + struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref); + + WARN_ON_ONCE(!ei->is_freed); + + kfree(ei->entry_attrs); + kfree_const(ei->name); + kfree_rcu(ei, rcu); +} + +static inline void put_ei(struct eventfs_inode *ei) +{ + if (ei) + kref_put(&ei->kref, release_ei); +} + +static inline void free_ei(struct eventfs_inode *ei) +{ + if (ei) { + ei->is_freed = 1; + put_ei(ei); + } +} + +static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei) +{ + if (ei) + kref_get(&ei->kref); + return ei; +} + static struct dentry *eventfs_root_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); -static int dcache_dir_open_wrapper(struct inode *inode, struct file *file); -static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx); -static int eventfs_release(struct inode *inode, struct file *file); +static int eventfs_iterate(struct file *file, struct dir_context *ctx); -static void update_attr(struct eventfs_file *ef, struct iattr *iattr) +static void update_attr(struct eventfs_attr *attr, struct iattr *iattr) { unsigned int ia_valid = iattr->ia_valid; if (ia_valid & ATTR_MODE) { - ef->mode = (ef->mode & ~EVENTFS_MODE_MASK) | + attr->mode = (attr->mode & ~EVENTFS_MODE_MASK) | (iattr->ia_mode & EVENTFS_MODE_MASK) | EVENTFS_SAVE_MODE; } if (ia_valid & ATTR_UID) { - ef->mode |= EVENTFS_SAVE_UID; - ef->uid = iattr->ia_uid; + attr->mode |= EVENTFS_SAVE_UID; + attr->uid = iattr->ia_uid; } if (ia_valid & ATTR_GID) { - ef->mode |= EVENTFS_SAVE_GID; - ef->gid = iattr->ia_gid; + attr->mode |= EVENTFS_SAVE_GID; + attr->gid = iattr->ia_gid; } } static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, - struct iattr *iattr) + struct iattr *iattr) { - struct eventfs_file *ef; + const struct eventfs_entry *entry; + struct eventfs_inode *ei; + const char *name; int ret; mutex_lock(&eventfs_mutex); - ef = dentry->d_fsdata; - if (ef && ef->is_freed) { + ei = dentry->d_fsdata; + if (ei->is_freed) { /* Do not allow changes if the event is about to be removed. */ mutex_unlock(&eventfs_mutex); return -ENODEV; } + /* Preallocate the children mode array if necessary */ + if (!(dentry->d_inode->i_mode & S_IFDIR)) { + if (!ei->entry_attrs) { + ei->entry_attrs = kcalloc(ei->nr_entries, sizeof(*ei->entry_attrs), + GFP_NOFS); + if (!ei->entry_attrs) { + ret = -ENOMEM; + goto out; + } + } + } + ret = simple_setattr(idmap, dentry, iattr); - if (!ret && ef) - update_attr(ef, iattr); + if (ret < 0) + goto out; + + /* + * If this is a dir, then update the ei cache, only the file + * mode is saved in the ei->m_children, and the ownership is + * determined by the parent directory. + */ + if (dentry->d_inode->i_mode & S_IFDIR) { + /* + * The events directory dentry is never freed, unless its + * part of an instance that is deleted. It's attr is the + * default for its child files and directories. + * Do not update it. It's not used for its own mode or ownership. + */ + if (ei->is_events) { + /* But it still needs to know if it was modified */ + if (iattr->ia_valid & ATTR_UID) + ei->attr.mode |= EVENTFS_SAVE_UID; + if (iattr->ia_valid & ATTR_GID) + ei->attr.mode |= EVENTFS_SAVE_GID; + } else { + update_attr(&ei->attr, iattr); + } + + } else { + name = dentry->d_name.name; + + for (int i = 0; i < ei->nr_entries; i++) { + entry = &ei->entries[i]; + if (strcmp(name, entry->name) == 0) { + update_attr(&ei->entry_attrs[i], iattr); + break; + } + } + } + out: mutex_unlock(&eventfs_mutex); return ret; } +static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb) +{ + struct inode *root; + + /* Only update if the "events" was on the top level */ + if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL)) + return; + + /* Get the tracefs root inode. */ + root = d_inode(sb->s_root); + ei->attr.uid = root->i_uid; + ei->attr.gid = root->i_gid; +} + +static void set_top_events_ownership(struct inode *inode) +{ + struct tracefs_inode *ti = get_tracefs(inode); + struct eventfs_inode *ei = ti->private; + + /* The top events directory doesn't get automatically updated */ + if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL)) + return; + + update_top_events_attr(ei, inode->i_sb); + + if (!(ei->attr.mode & EVENTFS_SAVE_UID)) + inode->i_uid = ei->attr.uid; + + if (!(ei->attr.mode & EVENTFS_SAVE_GID)) + inode->i_gid = ei->attr.gid; +} + +static int eventfs_get_attr(struct mnt_idmap *idmap, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + struct dentry *dentry = path->dentry; + struct inode *inode = d_backing_inode(dentry); + + set_top_events_ownership(inode); + + generic_fillattr(idmap, request_mask, inode, stat); + return 0; +} + +static int eventfs_permission(struct mnt_idmap *idmap, + struct inode *inode, int mask) +{ + set_top_events_ownership(inode); + return generic_permission(idmap, inode, mask); +} + static const struct inode_operations eventfs_root_dir_inode_operations = { .lookup = eventfs_root_lookup, .setattr = eventfs_set_attr, + .getattr = eventfs_get_attr, + .permission = eventfs_permission, }; static const struct inode_operations eventfs_file_inode_operations = { @@ -136,764 +260,548 @@ static const struct inode_operations eventfs_file_inode_operations = { }; static const struct file_operations eventfs_file_operations = { - .open = dcache_dir_open_wrapper, .read = generic_read_dir, - .iterate_shared = dcache_readdir_wrapper, + .iterate_shared = eventfs_iterate, .llseek = generic_file_llseek, - .release = eventfs_release, }; -static void update_inode_attr(struct inode *inode, struct eventfs_file *ef) +/* Return the evenfs_inode of the "events" directory */ +static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) +{ + struct eventfs_inode *ei; + + do { + // The parent is stable because we do not do renames + dentry = dentry->d_parent; + // ... and directories always have d_fsdata + ei = dentry->d_fsdata; + + /* + * If the ei is being freed, the ownership of the children + * doesn't matter. + */ + if (ei->is_freed) { + ei = NULL; + break; + } + // Walk upwards until you find the events inode + } while (!ei->is_events); + + update_top_events_attr(ei, dentry->d_sb); + + return ei; +} + +static void update_inode_attr(struct dentry *dentry, struct inode *inode, + struct eventfs_attr *attr, umode_t mode) { - inode->i_mode = ef->mode & EVENTFS_MODE_MASK; + struct eventfs_inode *events_ei = eventfs_find_events(dentry); + + if (!events_ei) + return; + + inode->i_mode = mode; + inode->i_uid = events_ei->attr.uid; + inode->i_gid = events_ei->attr.gid; + + if (!attr) + return; + + if (attr->mode & EVENTFS_SAVE_MODE) + inode->i_mode = attr->mode & EVENTFS_MODE_MASK; - if (ef->mode & EVENTFS_SAVE_UID) - inode->i_uid = ef->uid; + if (attr->mode & EVENTFS_SAVE_UID) + inode->i_uid = attr->uid; - if (ef->mode & EVENTFS_SAVE_GID) - inode->i_gid = ef->gid; + if (attr->mode & EVENTFS_SAVE_GID) + inode->i_gid = attr->gid; } /** - * create_file - create a file in the tracefs filesystem - * @ef: the eventfs_file - * @parent: parent dentry for this file. + * lookup_file - look up a file in the tracefs filesystem + * @dentry: the dentry to look up + * @mode: the permission that the file should have. + * @attr: saved attributes changed by user * @data: something that the caller will want to get to later on. * @fop: struct file_operations that should be used for this file. * - * This is the basic "create a file" function for tracefs. It allows for a - * wide range of flexibility in creating a file. - * - * This function will return a pointer to a dentry if it succeeds. This - * pointer must be passed to the tracefs_remove() function when the file is - * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. - * - * If tracefs is not enabled in the kernel, the value -%ENODEV will be - * returned. + * This function creates a dentry that represents a file in the eventsfs_inode + * directory. The inode.i_private pointer will point to @data in the open() + * call. */ -static struct dentry *create_file(struct eventfs_file *ef, - struct dentry *parent, void *data, +static struct dentry *lookup_file(struct eventfs_inode *parent_ei, + struct dentry *dentry, + umode_t mode, + struct eventfs_attr *attr, + void *data, const struct file_operations *fop) { struct tracefs_inode *ti; - struct dentry *dentry; struct inode *inode; - if (!(ef->mode & S_IFMT)) - ef->mode |= S_IFREG; - - if (WARN_ON_ONCE(!S_ISREG(ef->mode))) - return NULL; - - dentry = eventfs_start_creating(ef->name, parent); + if (!(mode & S_IFMT)) + mode |= S_IFREG; - if (IS_ERR(dentry)) - return dentry; + if (WARN_ON_ONCE(!S_ISREG(mode))) + return ERR_PTR(-EIO); inode = tracefs_get_inode(dentry->d_sb); if (unlikely(!inode)) - return eventfs_failed_creating(dentry); + return ERR_PTR(-ENOMEM); /* If the user updated the directory's attributes, use them */ - update_inode_attr(inode, ef); + update_inode_attr(dentry, inode, attr, mode); inode->i_op = &eventfs_file_inode_operations; inode->i_fop = fop; inode->i_private = data; + /* All files will have the same inode number */ + inode->i_ino = EVENTFS_FILE_INODE_INO; + ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; - d_instantiate(dentry, inode); - fsnotify_create(dentry->d_parent->d_inode, dentry); - return eventfs_end_creating(dentry); + + // Files have their parent's ei as their fsdata + dentry->d_fsdata = get_ei(parent_ei); + + d_add(dentry, inode); + return NULL; }; /** - * create_dir - create a dir in the tracefs filesystem + * lookup_dir_entry - look up a dir in the tracefs filesystem + * @dentry: the directory to look up * @ei: the eventfs_inode that represents the directory to create - * @parent: parent dentry for this file. - * @data: something that the caller will want to get to later on. * - * This is the basic "create a dir" function for eventfs. It allows for a - * wide range of flexibility in creating a dir. - * - * This function will return a pointer to a dentry if it succeeds. This - * pointer must be passed to the tracefs_remove() function when the file is - * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. - * - * If tracefs is not enabled in the kernel, the value -%ENODEV will be - * returned. + * This function will look up a dentry for a directory represented by + * a eventfs_inode. */ -static struct dentry *create_dir(struct eventfs_file *ef, - struct dentry *parent, void *data) +static struct dentry *lookup_dir_entry(struct dentry *dentry, + struct eventfs_inode *pei, struct eventfs_inode *ei) { struct tracefs_inode *ti; - struct dentry *dentry; struct inode *inode; - dentry = eventfs_start_creating(ef->name, parent); - if (IS_ERR(dentry)) - return dentry; - inode = tracefs_get_inode(dentry->d_sb); if (unlikely(!inode)) - return eventfs_failed_creating(dentry); + return ERR_PTR(-ENOMEM); - update_inode_attr(inode, ef); + /* If the user updated the directory's attributes, use them */ + update_inode_attr(dentry, inode, &ei->attr, + S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO); inode->i_op = &eventfs_root_dir_inode_operations; inode->i_fop = &eventfs_file_operations; - inode->i_private = data; + + /* All directories will have the same inode number */ + inode->i_ino = eventfs_dir_ino(ei); ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; + /* Only directories have ti->private set to an ei, not files */ + ti->private = ei; - inc_nlink(inode); - d_instantiate(dentry, inode); - inc_nlink(dentry->d_parent->d_inode); - fsnotify_mkdir(dentry->d_parent->d_inode, dentry); - return eventfs_end_creating(dentry); -} + dentry->d_fsdata = get_ei(ei); -static void free_ef(struct eventfs_file *ef) -{ - kfree(ef->name); - kfree(ef->ei); - kfree(ef); + d_add(dentry, inode); + return NULL; } -/** - * eventfs_set_ef_status_free - set the ef->status to free - * @ti: the tracefs_inode of the dentry - * @dentry: dentry who's status to be freed - * - * eventfs_set_ef_status_free will be called if no more - * references remain - */ -void eventfs_set_ef_status_free(struct tracefs_inode *ti, struct dentry *dentry) +static inline struct eventfs_inode *alloc_ei(const char *name) { - struct eventfs_inode *ei; - struct eventfs_file *ef; + struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL); - /* The top level events directory may be freed by this */ - if (unlikely(ti->flags & TRACEFS_EVENT_TOP_INODE)) { - mutex_lock(&eventfs_mutex); - ei = ti->private; - - /* Nothing should access this, but just in case! */ - ti->private = NULL; - mutex_unlock(&eventfs_mutex); - - ef = dentry->d_fsdata; - if (ef) - free_ef(ef); - return; - } - - mutex_lock(&eventfs_mutex); - - ef = dentry->d_fsdata; - if (!ef) - goto out; + if (!ei) + return NULL; - if (ef->is_freed) { - free_ef(ef); - } else { - ef->dentry = NULL; + ei->name = kstrdup_const(name, GFP_KERNEL); + if (!ei->name) { + kfree(ei); + return NULL; } - - dentry->d_fsdata = NULL; -out: - mutex_unlock(&eventfs_mutex); + kref_init(&ei->kref); + return ei; } /** - * eventfs_post_create_dir - post create dir routine - * @ef: eventfs_file of recently created dir + * eventfs_d_release - dentry is going away + * @dentry: dentry which has the reference to remove. * - * Map the meta-data of files within an eventfs dir to their parent dentry + * Remove the association between a dentry from an eventfs_inode. */ -static void eventfs_post_create_dir(struct eventfs_file *ef) +void eventfs_d_release(struct dentry *dentry) { - struct eventfs_file *ef_child; - struct tracefs_inode *ti; - - /* srcu lock already held */ - /* fill parent-child relation */ - list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list, - srcu_read_lock_held(&eventfs_srcu)) { - ef_child->d_parent = ef->dentry; - } - - ti = get_tracefs(ef->dentry->d_inode); - ti->private = ef->ei; + put_ei(dentry->d_fsdata); } /** - * create_dentry - helper function to create dentry - * @ef: eventfs_file of file or directory to create - * @parent: parent dentry - * @lookup: true if called from lookup routine + * lookup_file_dentry - create a dentry for a file of an eventfs_inode + * @ei: the eventfs_inode that the file will be created under + * @idx: the index into the entry_attrs[] of the @ei + * @parent: The parent dentry of the created file. + * @name: The name of the file to create + * @mode: The mode of the file. + * @data: The data to use to set the inode of the file with on open() + * @fops: The fops of the file to be created. * - * Used to create a dentry for file/dir, executes post dentry creation routine + * Create a dentry for a file of an eventfs_inode @ei and place it into the + * address located at @e_dentry. */ static struct dentry * -create_dentry(struct eventfs_file *ef, struct dentry *parent, bool lookup) +lookup_file_dentry(struct dentry *dentry, + struct eventfs_inode *ei, int idx, + umode_t mode, void *data, + const struct file_operations *fops) { - bool invalidate = false; - struct dentry *dentry; + struct eventfs_attr *attr = NULL; - mutex_lock(&eventfs_mutex); - if (ef->is_freed) { - mutex_unlock(&eventfs_mutex); - return NULL; - } - if (ef->dentry) { - dentry = ef->dentry; - /* On dir open, up the ref count */ - if (!lookup) - dget(dentry); - mutex_unlock(&eventfs_mutex); - return dentry; - } - mutex_unlock(&eventfs_mutex); - - if (!lookup) - inode_lock(parent->d_inode); - - if (ef->ei) - dentry = create_dir(ef, parent, ef->data); - else - dentry = create_file(ef, parent, ef->data, ef->fop); + if (ei->entry_attrs) + attr = &ei->entry_attrs[idx]; - if (!lookup) - inode_unlock(parent->d_inode); - - mutex_lock(&eventfs_mutex); - if (IS_ERR_OR_NULL(dentry)) { - /* If the ef was already updated get it */ - dentry = ef->dentry; - if (dentry && !lookup) - dget(dentry); - mutex_unlock(&eventfs_mutex); - return dentry; - } - - if (!ef->dentry && !ef->is_freed) { - ef->dentry = dentry; - if (ef->ei) - eventfs_post_create_dir(ef); - dentry->d_fsdata = ef; - } else { - /* A race here, should try again (unless freed) */ - invalidate = true; - - /* - * Should never happen unless we get here due to being freed. - * Otherwise it means two dentries exist with the same name. - */ - WARN_ON_ONCE(!ef->is_freed); - } - mutex_unlock(&eventfs_mutex); - if (invalidate) - d_invalidate(dentry); - - if (lookup || invalidate) - dput(dentry); - - return invalidate ? NULL : dentry; -} - -static bool match_event_file(struct eventfs_file *ef, const char *name) -{ - bool ret; - - mutex_lock(&eventfs_mutex); - ret = !ef->is_freed && strcmp(ef->name, name) == 0; - mutex_unlock(&eventfs_mutex); - - return ret; + return lookup_file(ei, dentry, mode, attr, data, fops); } /** * eventfs_root_lookup - lookup routine to create file/dir * @dir: in which a lookup is being done * @dentry: file/dir dentry - * @flags: to pass as flags parameter to simple lookup + * @flags: Just passed to simple_lookup() * - * Used to create a dynamic file/dir within @dir. Use the eventfs_inode - * list of meta data to find the information needed to create the file/dir. + * Used to create dynamic file/dir with-in @dir, search with-in @ei + * list, if @dentry found go ahead and create the file/dir */ + static struct dentry *eventfs_root_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { + struct eventfs_inode *ei_child; struct tracefs_inode *ti; struct eventfs_inode *ei; - struct eventfs_file *ef; - struct dentry *ret = NULL; - int idx; + const char *name = dentry->d_name.name; + struct dentry *result = NULL; ti = get_tracefs(dir); if (!(ti->flags & TRACEFS_EVENT_INODE)) - return NULL; + return ERR_PTR(-EIO); + + mutex_lock(&eventfs_mutex); ei = ti->private; - idx = srcu_read_lock(&eventfs_srcu); - list_for_each_entry_srcu(ef, &ei->e_top_files, list, - srcu_read_lock_held(&eventfs_srcu)) { - if (!match_event_file(ef, dentry->d_name.name)) + if (!ei || ei->is_freed) + goto out; + + list_for_each_entry(ei_child, &ei->children, list) { + if (strcmp(ei_child->name, name) != 0) continue; - ret = simple_lookup(dir, dentry, flags); - create_dentry(ef, ef->d_parent, true); - break; + if (ei_child->is_freed) + goto out; + result = lookup_dir_entry(dentry, ei, ei_child); + goto out; } - srcu_read_unlock(&eventfs_srcu, idx); - return ret; -} -struct dentry_list { - void *cursor; - struct dentry **dentries; -}; - -/** - * eventfs_release - called to release eventfs file/dir - * @inode: inode to be released - * @file: file to be released (not used) - */ -static int eventfs_release(struct inode *inode, struct file *file) -{ - struct tracefs_inode *ti; - struct dentry_list *dlist = file->private_data; - void *cursor; - int i; + for (int i = 0; i < ei->nr_entries; i++) { + void *data; + umode_t mode; + const struct file_operations *fops; + const struct eventfs_entry *entry = &ei->entries[i]; - ti = get_tracefs(inode); - if (!(ti->flags & TRACEFS_EVENT_INODE)) - return -EINVAL; + if (strcmp(name, entry->name) != 0) + continue; - if (WARN_ON_ONCE(!dlist)) - return -EINVAL; + data = ei->data; + if (entry->callback(name, &mode, &data, &fops) <= 0) + goto out; - for (i = 0; dlist->dentries && dlist->dentries[i]; i++) { - dput(dlist->dentries[i]); + result = lookup_file_dentry(dentry, ei, i, mode, data, fops); + goto out; } - - cursor = dlist->cursor; - kfree(dlist->dentries); - kfree(dlist); - file->private_data = cursor; - return dcache_dir_close(inode, file); + out: + mutex_unlock(&eventfs_mutex); + return result; } -/** - * dcache_dir_open_wrapper - eventfs open wrapper - * @inode: not used - * @file: dir to be opened (to create its child) - * - * Used to dynamically create the file/dir within @file. @file is really a - * directory and all the files/dirs of the children within @file will be - * created. If any of the files/dirs have already been created, their - * reference count will be incremented. +/* + * Walk the children of a eventfs_inode to fill in getdents(). */ -static int dcache_dir_open_wrapper(struct inode *inode, struct file *file) +static int eventfs_iterate(struct file *file, struct dir_context *ctx) { + const struct file_operations *fops; + struct inode *f_inode = file_inode(file); + const struct eventfs_entry *entry; + struct eventfs_inode *ei_child; struct tracefs_inode *ti; struct eventfs_inode *ei; - struct eventfs_file *ef; - struct dentry_list *dlist; - struct dentry **dentries = NULL; - struct dentry *dentry = file_dentry(file); - struct dentry *d; - struct inode *f_inode = file_inode(file); - int cnt = 0; + const char *name; + umode_t mode; int idx; - int ret; + int ret = -EINVAL; + int ino; + int i, r, c; + + if (!dir_emit_dots(file, ctx)) + return 0; ti = get_tracefs(f_inode); if (!(ti->flags & TRACEFS_EVENT_INODE)) return -EINVAL; - if (WARN_ON_ONCE(file->private_data)) - return -EINVAL; - - dlist = kmalloc(sizeof(*dlist), GFP_KERNEL); - if (!dlist) - return -ENOMEM; + c = ctx->pos - 2; - ei = ti->private; idx = srcu_read_lock(&eventfs_srcu); - list_for_each_entry_srcu(ef, &ei->e_top_files, list, - srcu_read_lock_held(&eventfs_srcu)) { - d = create_dentry(ef, dentry, false); - if (d) { - struct dentry **tmp; + mutex_lock(&eventfs_mutex); + ei = READ_ONCE(ti->private); + if (ei && ei->is_freed) + ei = NULL; + mutex_unlock(&eventfs_mutex); - tmp = krealloc(dentries, sizeof(d) * (cnt + 2), GFP_KERNEL); - if (!tmp) - break; - tmp[cnt] = d; - tmp[cnt + 1] = NULL; - cnt++; - dentries = tmp; - } - } - srcu_read_unlock(&eventfs_srcu, idx); - ret = dcache_dir_open(inode, file); + if (!ei) + goto out; /* - * dcache_dir_open() sets file->private_data to a dentry cursor. - * Need to save that but also save all the dentries that were - * opened by this function. + * Need to create the dentries and inodes to have a consistent + * inode number. */ - dlist->cursor = file->private_data; - dlist->dentries = dentries; - file->private_data = dlist; - return ret; -} + ret = 0; -/* - * This just sets the file->private_data back to the cursor and back. - */ -static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx) -{ - struct dentry_list *dlist = file->private_data; - int ret; + /* Start at 'c' to jump over already read entries */ + for (i = c; i < ei->nr_entries; i++, ctx->pos++) { + void *cdata = ei->data; - file->private_data = dlist->cursor; - ret = dcache_readdir(file, ctx); - dlist->cursor = file->private_data; - file->private_data = dlist; - return ret; -} + entry = &ei->entries[i]; + name = entry->name; -/** - * eventfs_prepare_ef - helper function to prepare eventfs_file - * @name: the name of the file/directory to create. - * @mode: the permission that the file should have. - * @fop: struct file_operations that should be used for this file/directory. - * @iop: struct inode_operations that should be used for this file/directory. - * @data: something that the caller will want to get to later on. The - * inode.i_private pointer will point to this value on the open() call. - * - * This function allocates and fills the eventfs_file structure. - */ -static struct eventfs_file *eventfs_prepare_ef(const char *name, umode_t mode, - const struct file_operations *fop, - const struct inode_operations *iop, - void *data) -{ - struct eventfs_file *ef; + mutex_lock(&eventfs_mutex); + /* If ei->is_freed then just bail here, nothing more to do */ + if (ei->is_freed) { + mutex_unlock(&eventfs_mutex); + goto out; + } + r = entry->callback(name, &mode, &cdata, &fops); + mutex_unlock(&eventfs_mutex); + if (r <= 0) + continue; - ef = kzalloc(sizeof(*ef), GFP_KERNEL); - if (!ef) - return ERR_PTR(-ENOMEM); + ino = EVENTFS_FILE_INODE_INO; - ef->name = kstrdup(name, GFP_KERNEL); - if (!ef->name) { - kfree(ef); - return ERR_PTR(-ENOMEM); + if (!dir_emit(ctx, name, strlen(name), ino, DT_REG)) + goto out; } - if (S_ISDIR(mode)) { - ef->ei = kzalloc(sizeof(*ef->ei), GFP_KERNEL); - if (!ef->ei) { - kfree(ef->name); - kfree(ef); - return ERR_PTR(-ENOMEM); - } - INIT_LIST_HEAD(&ef->ei->e_top_files); - ef->mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; - } else { - ef->ei = NULL; - ef->mode = mode; - } + /* Subtract the skipped entries above */ + c -= min((unsigned int)c, (unsigned int)ei->nr_entries); - ef->iop = iop; - ef->fop = fop; - ef->data = data; - return ef; -} + list_for_each_entry_srcu(ei_child, &ei->children, list, + srcu_read_lock_held(&eventfs_srcu)) { -/** - * eventfs_create_events_dir - create the trace event structure - * @name: the name of the directory to create. - * @parent: parent dentry for this file. This should be a directory dentry - * if set. If this parameter is NULL, then the directory will be - * created in the root of the tracefs filesystem. - * - * This function creates the top of the trace event directory. - */ -struct dentry *eventfs_create_events_dir(const char *name, - struct dentry *parent) -{ - struct dentry *dentry = tracefs_start_creating(name, parent); - struct eventfs_inode *ei; - struct tracefs_inode *ti; - struct inode *inode; + if (c > 0) { + c--; + continue; + } - if (security_locked_down(LOCKDOWN_TRACEFS)) - return NULL; + ctx->pos++; - if (IS_ERR(dentry)) - return dentry; + if (ei_child->is_freed) + continue; - ei = kzalloc(sizeof(*ei), GFP_KERNEL); - if (!ei) - return ERR_PTR(-ENOMEM); - inode = tracefs_get_inode(dentry->d_sb); - if (unlikely(!inode)) { - kfree(ei); - tracefs_failed_creating(dentry); - return ERR_PTR(-ENOMEM); - } + name = ei_child->name; - INIT_LIST_HEAD(&ei->e_top_files); + ino = eventfs_dir_ino(ei_child); - ti = get_tracefs(inode); - ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE; - ti->private = ei; + if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR)) + goto out_dec; + } + ret = 1; + out: + srcu_read_unlock(&eventfs_srcu, idx); - inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; - inode->i_op = &eventfs_root_dir_inode_operations; - inode->i_fop = &eventfs_file_operations; + return ret; - /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inc_nlink(inode); - d_instantiate(dentry, inode); - inc_nlink(dentry->d_parent->d_inode); - fsnotify_mkdir(dentry->d_parent->d_inode, dentry); - return tracefs_end_creating(dentry); + out_dec: + /* Incremented ctx->pos without adding something, reset it */ + ctx->pos--; + goto out; } /** - * eventfs_add_subsystem_dir - add eventfs subsystem_dir to list to create later - * @name: the name of the file to create. - * @parent: parent dentry for this dir. + * eventfs_create_dir - Create the eventfs_inode for this directory + * @name: The name of the directory to create. + * @parent: The eventfs_inode of the parent directory. + * @entries: A list of entries that represent the files under this directory + * @size: The number of @entries + * @data: The default data to pass to the files (an entry may override it). + * + * This function creates the descriptor to represent a directory in the + * eventfs. This descriptor is an eventfs_inode, and it is returned to be + * used to create other children underneath. + * + * The @entries is an array of eventfs_entry structures which has: + * const char *name + * eventfs_callback callback; + * + * The name is the name of the file, and the callback is a pointer to a function + * that will be called when the file is reference (either by lookup or by + * reading a directory). The callback is of the prototype: + * + * int callback(const char *name, umode_t *mode, void **data, + * const struct file_operations **fops); + * + * When a file needs to be created, this callback will be called with + * name = the name of the file being created (so that the same callback + * may be used for multiple files). + * mode = a place to set the file's mode + * data = A pointer to @data, and the callback may replace it, which will + * cause the file created to pass the new data to the open() call. + * fops = the fops to use for the created file. * - * This function adds eventfs subsystem dir to list. - * And all these dirs are created on the fly when they are looked up, - * and the dentry and inodes will be removed when they are done. + * NB. @callback is called while holding internal locks of the eventfs + * system. The callback must not call any code that might also call into + * the tracefs or eventfs system or it will risk creating a deadlock. */ -struct eventfs_file *eventfs_add_subsystem_dir(const char *name, - struct dentry *parent) +struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, + const struct eventfs_entry *entries, + int size, void *data) { - struct tracefs_inode *ti_parent; - struct eventfs_inode *ei_parent; - struct eventfs_file *ef; - - if (security_locked_down(LOCKDOWN_TRACEFS)) - return NULL; + struct eventfs_inode *ei; if (!parent) return ERR_PTR(-EINVAL); - ti_parent = get_tracefs(parent->d_inode); - ei_parent = ti_parent->private; + ei = alloc_ei(name); + if (!ei) + return ERR_PTR(-ENOMEM); - ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL); - if (IS_ERR(ef)) - return ef; + ei->entries = entries; + ei->nr_entries = size; + ei->data = data; + INIT_LIST_HEAD(&ei->children); + INIT_LIST_HEAD(&ei->list); mutex_lock(&eventfs_mutex); - list_add_tail(&ef->list, &ei_parent->e_top_files); - ef->d_parent = parent; + if (!parent->is_freed) + list_add_tail(&ei->list, &parent->children); mutex_unlock(&eventfs_mutex); - return ef; -} - -/** - * eventfs_add_dir - add eventfs dir to list to create later - * @name: the name of the file to create. - * @ef_parent: parent eventfs_file for this dir. - * - * This function adds eventfs dir to list. - * And all these dirs are created on the fly when they are looked up, - * and the dentry and inodes will be removed when they are done. - */ -struct eventfs_file *eventfs_add_dir(const char *name, - struct eventfs_file *ef_parent) -{ - struct eventfs_file *ef; - - if (security_locked_down(LOCKDOWN_TRACEFS)) - return NULL; - - if (!ef_parent) - return ERR_PTR(-EINVAL); - - ef = eventfs_prepare_ef(name, S_IFDIR, NULL, NULL, NULL); - if (IS_ERR(ef)) - return ef; - mutex_lock(&eventfs_mutex); - list_add_tail(&ef->list, &ef_parent->ei->e_top_files); - ef->d_parent = ef_parent->dentry; - mutex_unlock(&eventfs_mutex); - return ef; + /* Was the parent freed? */ + if (list_empty(&ei->list)) { + free_ei(ei); + ei = NULL; + } + return ei; } /** - * eventfs_add_events_file - add the data needed to create a file for later reference - * @name: the name of the file to create. - * @mode: the permission that the file should have. - * @parent: parent dentry for this file. - * @data: something that the caller will want to get to later on. - * @fop: struct file_operations that should be used for this file. + * eventfs_create_events_dir - create the top level events directory + * @name: The name of the top level directory to create. + * @parent: Parent dentry for this file in the tracefs directory. + * @entries: A list of entries that represent the files under this directory + * @size: The number of @entries + * @data: The default data to pass to the files (an entry may override it). * - * This function is used to add the information needed to create a - * dentry/inode within the top level events directory. The file created - * will have the @mode permissions. The @data will be used to fill the - * inode.i_private when the open() call is done. The dentry and inodes are - * all created when they are referenced, and removed when they are no - * longer referenced. + * This function creates the top of the trace event directory. + * + * See eventfs_create_dir() for use of @entries. */ -int eventfs_add_events_file(const char *name, umode_t mode, - struct dentry *parent, void *data, - const struct file_operations *fop) +struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, + const struct eventfs_entry *entries, + int size, void *data) { - struct tracefs_inode *ti; + struct dentry *dentry = tracefs_start_creating(name, parent); struct eventfs_inode *ei; - struct eventfs_file *ef; + struct tracefs_inode *ti; + struct inode *inode; + kuid_t uid; + kgid_t gid; if (security_locked_down(LOCKDOWN_TRACEFS)) - return -ENODEV; - - if (!parent) - return -EINVAL; - - if (!(mode & S_IFMT)) - mode |= S_IFREG; - - if (!parent->d_inode) - return -EINVAL; - - ti = get_tracefs(parent->d_inode); - if (!(ti->flags & TRACEFS_EVENT_INODE)) - return -EINVAL; - - ei = ti->private; - ef = eventfs_prepare_ef(name, mode, fop, NULL, data); - - if (IS_ERR(ef)) - return -ENOMEM; - - mutex_lock(&eventfs_mutex); - list_add_tail(&ef->list, &ei->e_top_files); - ef->d_parent = parent; - mutex_unlock(&eventfs_mutex); - return 0; -} - -/** - * eventfs_add_file - add eventfs file to list to create later - * @name: the name of the file to create. - * @mode: the permission that the file should have. - * @ef_parent: parent eventfs_file for this file. - * @data: something that the caller will want to get to later on. - * @fop: struct file_operations that should be used for this file. - * - * This function is used to add the information needed to create a - * file within a subdirectory of the events directory. The file created - * will have the @mode permissions. The @data will be used to fill the - * inode.i_private when the open() call is done. The dentry and inodes are - * all created when they are referenced, and removed when they are no - * longer referenced. - */ -int eventfs_add_file(const char *name, umode_t mode, - struct eventfs_file *ef_parent, - void *data, - const struct file_operations *fop) -{ - struct eventfs_file *ef; + return NULL; - if (security_locked_down(LOCKDOWN_TRACEFS)) - return -ENODEV; + if (IS_ERR(dentry)) + return ERR_CAST(dentry); - if (!ef_parent) - return -EINVAL; + ei = alloc_ei(name); + if (!ei) + goto fail; - if (!(mode & S_IFMT)) - mode |= S_IFREG; + inode = tracefs_get_inode(dentry->d_sb); + if (unlikely(!inode)) + goto fail; - ef = eventfs_prepare_ef(name, mode, fop, NULL, data); - if (IS_ERR(ef)) - return -ENOMEM; + // Note: we have a ref to the dentry from tracefs_start_creating() + ei->events_dir = dentry; + ei->entries = entries; + ei->nr_entries = size; + ei->is_events = 1; + ei->data = data; - mutex_lock(&eventfs_mutex); - list_add_tail(&ef->list, &ef_parent->ei->e_top_files); - ef->d_parent = ef_parent->dentry; - mutex_unlock(&eventfs_mutex); - return 0; -} + /* Save the ownership of this directory */ + uid = d_inode(dentry->d_parent)->i_uid; + gid = d_inode(dentry->d_parent)->i_gid; -static LLIST_HEAD(free_list); + /* + * If the events directory is of the top instance, then parent + * is NULL. Set the attr.mode to reflect this and its permissions will + * default to the tracefs root dentry. + */ + if (!parent) + ei->attr.mode = EVENTFS_TOPLEVEL; -static void eventfs_workfn(struct work_struct *work) -{ - struct eventfs_file *ef, *tmp; - struct llist_node *llnode; - - llnode = llist_del_all(&free_list); - llist_for_each_entry_safe(ef, tmp, llnode, llist) { - /* This should only get here if it had a dentry */ - if (!WARN_ON_ONCE(!ef->dentry)) - dput(ef->dentry); - } -} + /* This is used as the default ownership of the files and directories */ + ei->attr.uid = uid; + ei->attr.gid = gid; -static DECLARE_WORK(eventfs_work, eventfs_workfn); + INIT_LIST_HEAD(&ei->children); + INIT_LIST_HEAD(&ei->list); -static void free_rcu_ef(struct rcu_head *head) -{ - struct eventfs_file *ef = container_of(head, struct eventfs_file, rcu); + ti = get_tracefs(inode); + ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE; + ti->private = ei; - if (ef->dentry) { - /* Do not free the ef until all references of dentry are gone */ - if (llist_add(&ef->llist, &free_list)) - queue_work(system_unbound_wq, &eventfs_work); - return; - } + inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + inode->i_uid = uid; + inode->i_gid = gid; + inode->i_op = &eventfs_root_dir_inode_operations; + inode->i_fop = &eventfs_file_operations; - free_ef(ef); -} + dentry->d_fsdata = get_ei(ei); -static void unhook_dentry(struct dentry *dentry) -{ - if (!dentry) - return; /* - * Need to add a reference to the dentry that is expected by - * simple_recursive_removal(), which will include a dput(). + * Keep all eventfs directories with i_nlink == 1. + * Due to the dynamic nature of the dentry creations and not + * wanting to add a pointer to the parent eventfs_inode in the + * eventfs_inode structure, keeping the i_nlink in sync with the + * number of directories would cause too much complexity for + * something not worth much. Keeping directory links at 1 + * tells userspace not to trust the link number. */ - dget(dentry); + d_instantiate(dentry, inode); + /* The dentry of the "events" parent does keep track though */ + inc_nlink(dentry->d_parent->d_inode); + fsnotify_mkdir(dentry->d_parent->d_inode, dentry); + tracefs_end_creating(dentry); - /* - * Also add a reference for the dput() in eventfs_workfn(). - * That is required as that dput() will free the ei after - * the SRCU grace period is over. - */ - dget(dentry); + return ei; + + fail: + free_ei(ei); + tracefs_failed_creating(dentry); + return ERR_PTR(-ENOMEM); } /** * eventfs_remove_rec - remove eventfs dir or file from list - * @ef: eventfs_file to be removed. - * @level: to check recursion depth + * @ei: eventfs_inode to be removed. + * @level: prevent recursion from going more than 3 levels deep. * - * The helper function eventfs_remove_rec() is used to clean up and free the - * associated data from eventfs for both of the added functions. + * This function recursively removes eventfs_inodes which + * contains info of files and/or directories. */ -static void eventfs_remove_rec(struct eventfs_file *ef, int level) +static void eventfs_remove_rec(struct eventfs_inode *ei, int level) { - struct eventfs_file *ef_child; + struct eventfs_inode *ei_child; - if (!ef) - return; /* * Check recursion depth. It should never be greater than 3: * 0 - events/ @@ -904,72 +812,54 @@ static void eventfs_remove_rec(struct eventfs_file *ef, int level) if (WARN_ON_ONCE(level > 3)) return; - if (ef->ei) { - /* search for nested folders or files */ - list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list, - lockdep_is_held(&eventfs_mutex)) { - eventfs_remove_rec(ef_child, level + 1); - } - } - - ef->is_freed = 1; + /* search for nested folders or files */ + list_for_each_entry(ei_child, &ei->children, list) + eventfs_remove_rec(ei_child, level + 1); - unhook_dentry(ef->dentry); - - list_del_rcu(&ef->list); - call_srcu(&eventfs_srcu, &ef->rcu, free_rcu_ef); + list_del(&ei->list); + free_ei(ei); } /** - * eventfs_remove - remove eventfs dir or file from list - * @ef: eventfs_file to be removed. + * eventfs_remove_dir - remove eventfs dir or file from list + * @ei: eventfs_inode to be removed. * * This function acquire the eventfs_mutex lock and call eventfs_remove_rec() */ -void eventfs_remove(struct eventfs_file *ef) +void eventfs_remove_dir(struct eventfs_inode *ei) { - struct dentry *dentry; - - if (!ef) + if (!ei) return; mutex_lock(&eventfs_mutex); - dentry = ef->dentry; - eventfs_remove_rec(ef, 0); + eventfs_remove_rec(ei, 0); mutex_unlock(&eventfs_mutex); - - /* - * If any of the ei children has a dentry, then the ei itself - * must have a dentry. - */ - if (dentry) - simple_recursive_removal(dentry, NULL); } /** - * eventfs_remove_events_dir - remove eventfs dir or file from list - * @dentry: events's dentry to be removed. + * eventfs_remove_events_dir - remove the top level eventfs directory + * @ei: the event_inode returned by eventfs_create_events_dir(). * - * This function remove events main directory + * This function removes the events main directory */ -void eventfs_remove_events_dir(struct dentry *dentry) +void eventfs_remove_events_dir(struct eventfs_inode *ei) { - struct eventfs_file *ef_child; - struct eventfs_inode *ei; - struct tracefs_inode *ti; + struct dentry *dentry; - if (!dentry || !dentry->d_inode) + dentry = ei->events_dir; + if (!dentry) return; - ti = get_tracefs(dentry->d_inode); - if (!ti || !(ti->flags & TRACEFS_EVENT_INODE)) - return; + ei->events_dir = NULL; + eventfs_remove_dir(ei); - mutex_lock(&eventfs_mutex); - ei = ti->private; - list_for_each_entry_srcu(ef_child, &ei->e_top_files, list, - lockdep_is_held(&eventfs_mutex)) { - eventfs_remove_rec(ef_child, 0); - } - mutex_unlock(&eventfs_mutex); + /* + * Matches the dget() done by tracefs_start_creating() + * in eventfs_create_events_dir() when it the dentry was + * created. In other words, it's a normal dentry that + * sticks around while the other ei->dentry are created + * and destroyed dynamically. + */ + d_invalidate(dentry); + dput(dentry); } diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 0292c6a2bed9f..99caf1c3d0c41 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -38,8 +38,6 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb) if (!ti) return NULL; - ti->flags = 0; - return &ti->vfs_inode; } @@ -91,6 +89,7 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap, struct inode *inode, struct dentry *dentry, umode_t mode) { + struct tracefs_inode *ti; char *name; int ret; @@ -98,6 +97,15 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap, if (!name) return -ENOMEM; + /* + * This is a new directory that does not take the default of + * the rootfs. It becomes the default permissions for all the + * files and directories underneath it. + */ + ti = get_tracefs(inode); + ti->flags |= TRACEFS_INSTANCE_INODE; + ti->private = inode; + /* * The mkdir call can call the generic functions that create * the files within the tracefs system. It is up to the individual @@ -141,10 +149,76 @@ static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry) return ret; } -static const struct inode_operations tracefs_dir_inode_operations = { +static void set_tracefs_inode_owner(struct inode *inode) +{ + struct tracefs_inode *ti = get_tracefs(inode); + struct inode *root_inode = ti->private; + + /* + * If this inode has never been referenced, then update + * the permissions to the superblock. + */ + if (!(ti->flags & TRACEFS_UID_PERM_SET)) + inode->i_uid = root_inode->i_uid; + + if (!(ti->flags & TRACEFS_GID_PERM_SET)) + inode->i_gid = root_inode->i_gid; +} + +static int tracefs_permission(struct mnt_idmap *idmap, + struct inode *inode, int mask) +{ + set_tracefs_inode_owner(inode); + return generic_permission(idmap, inode, mask); +} + +static int tracefs_getattr(struct mnt_idmap *idmap, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + struct inode *inode = d_backing_inode(path->dentry); + + set_tracefs_inode_owner(inode); + generic_fillattr(idmap, request_mask, inode, stat); + return 0; +} + +static int tracefs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) +{ + unsigned int ia_valid = attr->ia_valid; + struct inode *inode = d_inode(dentry); + struct tracefs_inode *ti = get_tracefs(inode); + + if (ia_valid & ATTR_UID) + ti->flags |= TRACEFS_UID_PERM_SET; + + if (ia_valid & ATTR_GID) + ti->flags |= TRACEFS_GID_PERM_SET; + + return simple_setattr(idmap, dentry, attr); +} + +static const struct inode_operations tracefs_instance_dir_inode_operations = { .lookup = simple_lookup, .mkdir = tracefs_syscall_mkdir, .rmdir = tracefs_syscall_rmdir, + .permission = tracefs_permission, + .getattr = tracefs_getattr, + .setattr = tracefs_setattr, +}; + +static const struct inode_operations tracefs_dir_inode_operations = { + .lookup = simple_lookup, + .permission = tracefs_permission, + .getattr = tracefs_getattr, + .setattr = tracefs_setattr, +}; + +static const struct inode_operations tracefs_file_inode_operations = { + .permission = tracefs_permission, + .getattr = tracefs_getattr, + .setattr = tracefs_setattr, }; struct inode *tracefs_get_inode(struct super_block *sb) @@ -183,77 +257,6 @@ struct tracefs_fs_info { struct tracefs_mount_opts mount_opts; }; -static void change_gid(struct dentry *dentry, kgid_t gid) -{ - if (!dentry->d_inode) - return; - dentry->d_inode->i_gid = gid; -} - -/* - * Taken from d_walk, but without he need for handling renames. - * Nothing can be renamed while walking the list, as tracefs - * does not support renames. This is only called when mounting - * or remounting the file system, to set all the files to - * the given gid. - */ -static void set_gid(struct dentry *parent, kgid_t gid) -{ - struct dentry *this_parent; - struct list_head *next; - - this_parent = parent; - spin_lock(&this_parent->d_lock); - - change_gid(this_parent, gid); -repeat: - next = this_parent->d_subdirs.next; -resume: - while (next != &this_parent->d_subdirs) { - struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_child); - next = tmp->next; - - spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - - change_gid(dentry, gid); - - if (!list_empty(&dentry->d_subdirs)) { - spin_unlock(&this_parent->d_lock); - spin_release(&dentry->d_lock.dep_map, _RET_IP_); - this_parent = dentry; - spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); - goto repeat; - } - spin_unlock(&dentry->d_lock); - } - /* - * All done at this level ... ascend and resume the search. - */ - rcu_read_lock(); -ascend: - if (this_parent != parent) { - struct dentry *child = this_parent; - this_parent = child->d_parent; - - spin_unlock(&child->d_lock); - spin_lock(&this_parent->d_lock); - - /* go into the first sibling still alive */ - do { - next = child->d_child.next; - if (next == &this_parent->d_subdirs) - goto ascend; - child = list_entry(next, struct dentry, d_child); - } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); - rcu_read_unlock(); - goto resume; - } - rcu_read_unlock(); - spin_unlock(&this_parent->d_lock); - return; -} - static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) { substring_t args[MAX_OPT_ARGS]; @@ -326,10 +329,8 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) if (!remount || opts->opts & BIT(Opt_uid)) inode->i_uid = opts->uid; - if (!remount || opts->opts & BIT(Opt_gid)) { - /* Set all the group ids to the mount option */ - set_gid(sb->s_root, opts->gid); - } + if (!remount || opts->opts & BIT(Opt_gid)) + inode->i_gid = opts->gid; return 0; } @@ -376,21 +377,30 @@ static const struct super_operations tracefs_super_operations = { .show_options = tracefs_show_options, }; -static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode) +/* + * It would be cleaner if eventfs had its own dentry ops. + * + * Note that d_revalidate is called potentially under RCU, + * so it can't take the eventfs mutex etc. It's fine - if + * we open a file just as it's marked dead, things will + * still work just fine, and just see the old stale case. + */ +static void tracefs_d_release(struct dentry *dentry) { - struct tracefs_inode *ti; + if (dentry->d_fsdata) + eventfs_d_release(dentry); +} - if (!dentry || !inode) - return; +static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct eventfs_inode *ei = dentry->d_fsdata; - ti = get_tracefs(inode); - if (ti && ti->flags & TRACEFS_EVENT_INODE) - eventfs_set_ef_status_free(ti, dentry); - iput(inode); + return !(ei && ei->is_freed); } static const struct dentry_operations tracefs_dentry_operations = { - .d_iput = tracefs_dentry_iput, + .d_revalidate = tracefs_d_revalidate, + .d_release = tracefs_d_release, }; static int trace_fill_super(struct super_block *sb, void *data, int silent) @@ -494,73 +504,24 @@ struct dentry *tracefs_end_creating(struct dentry *dentry) return dentry; } -/** - * eventfs_start_creating - start the process of creating a dentry - * @name: Name of the file created for the dentry - * @parent: The parent dentry where this dentry will be created - * - * This is a simple helper function for the dynamically created eventfs - * files. When the directory of the eventfs files are accessed, their - * dentries are created on the fly. This function is used to start that - * process. - */ -struct dentry *eventfs_start_creating(const char *name, struct dentry *parent) +/* Find the inode that this will use for default */ +static struct inode *instance_inode(struct dentry *parent, struct inode *inode) { - struct dentry *dentry; - int error; - - /* Must always have a parent. */ - if (WARN_ON_ONCE(!parent)) - return ERR_PTR(-EINVAL); - - error = simple_pin_fs(&trace_fs_type, &tracefs_mount, - &tracefs_mount_count); - if (error) - return ERR_PTR(error); + struct tracefs_inode *ti; - if (unlikely(IS_DEADDIR(parent->d_inode))) - dentry = ERR_PTR(-ENOENT); - else - dentry = lookup_one_len(name, parent, strlen(name)); + /* If parent is NULL then use root inode */ + if (!parent) + return d_inode(inode->i_sb->s_root); - if (!IS_ERR(dentry) && dentry->d_inode) { - dput(dentry); - dentry = ERR_PTR(-EEXIST); + /* Find the inode that is flagged as an instance or the root inode */ + while (!IS_ROOT(parent)) { + ti = get_tracefs(d_inode(parent)); + if (ti->flags & TRACEFS_INSTANCE_INODE) + break; + parent = parent->d_parent; } - if (IS_ERR(dentry)) - simple_release_fs(&tracefs_mount, &tracefs_mount_count); - - return dentry; -} - -/** - * eventfs_failed_creating - clean up a failed eventfs dentry creation - * @dentry: The dentry to clean up - * - * If after calling eventfs_start_creating(), a failure is detected, the - * resources created by eventfs_start_creating() needs to be cleaned up. In - * that case, this function should be called to perform that clean up. - */ -struct dentry *eventfs_failed_creating(struct dentry *dentry) -{ - dput(dentry); - simple_release_fs(&tracefs_mount, &tracefs_mount_count); - return NULL; -} - -/** - * eventfs_end_creating - Finish the process of creating a eventfs dentry - * @dentry: The dentry that has successfully been created. - * - * This function is currently just a place holder to match - * eventfs_start_creating(). In case any synchronization needs to be added, - * this function will be used to implement that without having to modify - * the callers of eventfs_start_creating(). - */ -struct dentry *eventfs_end_creating(struct dentry *dentry) -{ - return dentry; + return d_inode(parent); } /** @@ -593,6 +554,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { + struct tracefs_inode *ti; struct dentry *dentry; struct inode *inode; @@ -611,7 +573,11 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, if (unlikely(!inode)) return tracefs_failed_creating(dentry); + ti = get_tracefs(inode); + ti->private = instance_inode(parent, inode); + inode->i_mode = mode; + inode->i_op = &tracefs_file_inode_operations; inode->i_fop = fops ? fops : &tracefs_file_operations; inode->i_private = data; inode->i_uid = d_inode(dentry->d_parent)->i_uid; @@ -624,6 +590,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, static struct dentry *__create_dir(const char *name, struct dentry *parent, const struct inode_operations *ops) { + struct tracefs_inode *ti; struct dentry *dentry = tracefs_start_creating(name, parent); struct inode *inode; @@ -641,6 +608,9 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent, inode->i_uid = d_inode(dentry->d_parent)->i_uid; inode->i_gid = d_inode(dentry->d_parent)->i_gid; + ti = get_tracefs(inode); + ti->private = instance_inode(parent, inode); + /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); @@ -671,7 +641,7 @@ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent) if (security_locked_down(LOCKDOWN_TRACEFS)) return NULL; - return __create_dir(name, parent, &simple_dir_inode_operations); + return __create_dir(name, parent, &tracefs_dir_inode_operations); } /** @@ -702,7 +672,7 @@ __init struct dentry *tracefs_create_instance_dir(const char *name, if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir)) return NULL; - dentry = __create_dir(name, parent, &tracefs_dir_inode_operations); + dentry = __create_dir(name, parent, &tracefs_instance_dir_inode_operations); if (!dentry) return NULL; @@ -747,7 +717,11 @@ static void init_once(void *foo) { struct tracefs_inode *ti = (struct tracefs_inode *) foo; + /* inode_init_once() calls memset() on the vfs_inode portion */ inode_init_once(&ti->vfs_inode); + + /* Zero out the rest */ + memset_after(ti, 0, vfs_inode); } static int __init tracefs_init(void) diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 4f2e49e2197b1..beb3dcd0e4342 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -5,12 +5,64 @@ enum { TRACEFS_EVENT_INODE = BIT(1), TRACEFS_EVENT_TOP_INODE = BIT(2), + TRACEFS_GID_PERM_SET = BIT(3), + TRACEFS_UID_PERM_SET = BIT(4), + TRACEFS_INSTANCE_INODE = BIT(5), }; struct tracefs_inode { + struct inode vfs_inode; + /* The below gets initialized with memset_after(ti, 0, vfs_inode) */ unsigned long flags; void *private; - struct inode vfs_inode; +}; + +/* + * struct eventfs_attr - cache the mode and ownership of a eventfs entry + * @mode: saved mode plus flags of what is saved + * @uid: saved uid if changed + * @gid: saved gid if changed + */ +struct eventfs_attr { + int mode; + kuid_t uid; + kgid_t gid; +}; + +/* + * struct eventfs_inode - hold the properties of the eventfs directories. + * @list: link list into the parent directory + * @rcu: Union with @list for freeing + * @children: link list into the child eventfs_inode + * @entries: the array of entries representing the files in the directory + * @name: the name of the directory to create + * @events_dir: the dentry of the events directory + * @entry_attrs: Saved mode and ownership of the @d_children + * @data: The private data to pass to the callbacks + * @attr: Saved mode and ownership of eventfs_inode itself + * @is_freed: Flag set if the eventfs is on its way to be freed + * Note if is_freed is set, then dentry is corrupted. + * @is_events: Flag set for only the top level "events" directory + * @nr_entries: The number of items in @entries + * @ino: The saved inode number + */ +struct eventfs_inode { + union { + struct list_head list; + struct rcu_head rcu; + }; + struct list_head children; + const struct eventfs_entry *entries; + const char *name; + struct dentry *events_dir; + struct eventfs_attr *entry_attrs; + void *data; + struct eventfs_attr attr; + struct kref kref; + unsigned int is_freed:1; + unsigned int is_events:1; + unsigned int nr_entries:30; + unsigned int ino; }; static inline struct tracefs_inode *get_tracefs(const struct inode *inode) @@ -22,9 +74,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent); struct dentry *tracefs_end_creating(struct dentry *dentry); struct dentry *tracefs_failed_creating(struct dentry *dentry); struct inode *tracefs_get_inode(struct super_block *sb); -struct dentry *eventfs_start_creating(const char *name, struct dentry *parent); -struct dentry *eventfs_failed_creating(struct dentry *dentry); -struct dentry *eventfs_end_creating(struct dentry *dentry); -void eventfs_set_ef_status_free(struct tracefs_inode *ti, struct dentry *dentry); + +void eventfs_d_release(struct dentry *dentry); #endif /* _TRACEFS_INTERNAL_H */ diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index b2c9b35df8f76..897b12ec61e29 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -348,7 +348,12 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, struct zonefs_inode_info *zi = ZONEFS_I(inode); if (error) { - zonefs_io_error(inode, true); + /* + * For Sync IOs, error recovery is called from + * zonefs_file_dio_write(). + */ + if (!is_sync_kiocb(iocb)) + zonefs_io_error(inode, true); return error; } @@ -491,6 +496,14 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = -EINVAL; goto inode_unlock; } + /* + * Advance the zone write pointer offset. This assumes that the + * IO will succeed, which is OK to do because we do not allow + * partial writes (IOMAP_DIO_PARTIAL is not set) and if the IO + * fails, the error path will correct the write pointer offset. + */ + z->z_wpoffset += count; + zonefs_inode_account_active(inode); mutex_unlock(&zi->i_truncate_mutex); } @@ -504,20 +517,19 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) if (ret == -ENOTBLK) ret = -EBUSY; - if (zonefs_zone_is_seq(z) && - (ret > 0 || ret == -EIOCBQUEUED)) { - if (ret > 0) - count = ret; - - /* - * Update the zone write pointer offset assuming the write - * operation succeeded. If it did not, the error recovery path - * will correct it. Also do active seq file accounting. - */ - mutex_lock(&zi->i_truncate_mutex); - z->z_wpoffset += count; - zonefs_inode_account_active(inode); - mutex_unlock(&zi->i_truncate_mutex); + /* + * For a failed IO or partial completion, trigger error recovery + * to update the zone write pointer offset to a correct value. + * For asynchronous IOs, zonefs_file_write_dio_end_io() may already + * have executed error recovery if the IO already completed when we + * reach here. However, we cannot know that and execute error recovery + * again (that will not change anything). + */ + if (zonefs_zone_is_seq(z)) { + if (ret > 0 && ret != count) + ret = -EIO; + if (ret < 0 && ret != -EIOCBQUEUED) + zonefs_io_error(inode, true); } inode_unlock: diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 9d1a9808fbbba..cc364669d723d 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -246,16 +246,18 @@ static void zonefs_inode_update_mode(struct inode *inode) z->z_mode = inode->i_mode; } -struct zonefs_ioerr_data { - struct inode *inode; - bool write; -}; - static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, void *data) { - struct zonefs_ioerr_data *err = data; - struct inode *inode = err->inode; + struct blk_zone *z = data; + + *z = *zone; + return 0; +} + +static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone, + bool write) +{ struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); @@ -270,8 +272,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, data_size = zonefs_check_zone_condition(sb, z, zone); isize = i_size_read(inode); if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) && - !err->write && isize == data_size) - return 0; + !write && isize == data_size) + return; /* * At this point, we detected either a bad zone or an inconsistency @@ -292,7 +294,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, * In all cases, warn about inode size inconsistency and handle the * IO error according to the zone condition and to the mount options. */ - if (zonefs_zone_is_seq(z) && isize != data_size) + if (isize != data_size) zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n", inode->i_ino, isize, data_size); @@ -352,8 +354,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, zonefs_i_size_write(inode, data_size); z->z_wpoffset = data_size; zonefs_inode_account_active(inode); - - return 0; } /* @@ -367,23 +367,25 @@ void __zonefs_io_error(struct inode *inode, bool write) { struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; - struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; - unsigned int nr_zones = 1; - struct zonefs_ioerr_data err = { - .inode = inode, - .write = write, - }; + struct blk_zone zone; int ret; /* - * The only files that have more than one zone are conventional zone - * files with aggregated conventional zones, for which the inode zone - * size is always larger than the device zone size. + * Conventional zone have no write pointer and cannot become read-only + * or offline. So simply fake a report for a single or aggregated zone + * and let zonefs_handle_io_error() correct the zone inode information + * according to the mount options. */ - if (z->z_size > bdev_zone_sectors(sb->s_bdev)) - nr_zones = z->z_size >> - (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + if (!zonefs_zone_is_seq(z)) { + zone.start = z->z_sector; + zone.len = z->z_size >> SECTOR_SHIFT; + zone.wp = zone.start + zone.len; + zone.type = BLK_ZONE_TYPE_CONVENTIONAL; + zone.cond = BLK_ZONE_COND_NOT_WP; + zone.capacity = zone.len; + goto handle_io_error; + } /* * Memory allocations in blkdev_report_zones() can trigger a memory @@ -394,12 +396,20 @@ void __zonefs_io_error(struct inode *inode, bool write) * the GFP_NOIO context avoids both problems. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones, - zonefs_io_error_cb, &err); - if (ret != nr_zones) + ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1, + zonefs_io_error_cb, &zone); + memalloc_noio_restore(noio_flag); + + if (ret != 1) { zonefs_err(sb, "Get inode %lu zone information failed %d\n", inode->i_ino, ret); - memalloc_noio_restore(noio_flag); + zonefs_warn(sb, "remounting filesystem read-only\n"); + sb->s_flags |= SB_RDONLY; + return; + } + +handle_io_error: + zonefs_handle_io_error(inode, &zone, write); } static struct kmem_cache *zonefs_inode_cachep; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 67d8dd2f1bdec..bae0fe4d499bc 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -356,7 +356,6 @@ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data*) \ - MEM_KEEP(exit.data*) \ *(.data.unlikely) \ __start_once = .; \ *(.data.once) \ @@ -521,7 +520,6 @@ __init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) { \ *(.ref.rodata) \ MEM_KEEP(init.rodata) \ - MEM_KEEP(exit.rodata) \ } \ \ /* Built-in module parameters. */ \ @@ -574,7 +572,6 @@ *(.ref.text) \ *(.text.asan.* .text.tsan.*) \ MEM_KEEP(init.text*) \ - MEM_KEEP(exit.text*) \ /* sched.text is aling to function alignment to secure we have same @@ -714,13 +711,10 @@ *(.exit.data .exit.data.*) \ *(.fini_array .fini_array.*) \ *(.dtors .dtors.*) \ - MEM_DISCARD(exit.data*) \ - MEM_DISCARD(exit.rodata*) #define EXIT_TEXT \ *(.exit.text) \ *(.text.exit) \ - MEM_DISCARD(exit.text) #define EXIT_CALL \ *(.exitcall.exit) diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index ae12696ec492c..2ad261082bba5 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -141,8 +141,6 @@ struct bdi_writeback { struct delayed_work dwork; /* work item used for writeback */ struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ - unsigned long dirty_sleep; /* last wait */ - struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK @@ -179,6 +177,11 @@ struct backing_dev_info { * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; + /* + * Jiffies when last process was dirty throttled on this bdi. Used by + * blk-wbt. + */ + unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 7af9e34ec261b..8c9a095c17571 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,6 +66,26 @@ __builtin_unreachable(); \ } while (0) +/* + * GCC 'asm goto' with outputs miscompiles certain code sequences: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 + * + * Work around it via the same compiler barrier quirk that we used + * to use for the old 'asm goto' workaround. + * + * Also, always mark such 'asm goto' statements as volatile: all + * asm goto statements are supposed to be volatile as per the + * documentation, but some versions of gcc didn't actually do + * that for asms with outputs: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 + */ +#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND +#define asm_goto_output(x...) \ + do { asm volatile goto(x); asm (""); } while (0) +#endif + #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index c523c6683789d..b2f9e2c409cf2 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -352,8 +352,15 @@ struct ftrace_likely_data { # define __realloc_size(x, ...) #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +/* + * Some versions of gcc do not mark 'asm goto' volatile: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 + * + * We do it here by hand, because it doesn't hurt. + */ +#ifndef asm_goto_output +#define asm_goto_output(x...) asm volatile goto(x) #endif #ifdef CONFIG_CC_HAS_ASM_INLINE diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 7852f6c9a714c..719cf9cc6e1ac 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -8,6 +8,8 @@ #ifndef __AD_SIGMA_DELTA_H__ #define __AD_SIGMA_DELTA_H__ +#include + enum ad_sigma_delta_mode { AD_SD_MODE_CONTINUOUS = 0, AD_SD_MODE_SINGLE = 1, @@ -99,7 +101,7 @@ struct ad_sigma_delta { * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp, * rounded to 16 bytes to take into account padding. */ - uint8_t tx_buf[4] ____cacheline_aligned; + uint8_t tx_buf[4] __aligned(IIO_DMA_MINALIGN); uint8_t rx_buf[16] __aligned(8); }; diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 607c3a89a6471..f9ae5cdd884f5 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -258,9 +258,9 @@ struct st_sensor_data { bool hw_irq_trigger; s64 hw_timestamp; - char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned; - struct mutex odr_lock; + + char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN); }; #ifdef CONFIG_IIO_BUFFER diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index dc9ea299e0885..8898966bc0f08 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -11,6 +11,7 @@ #include #include +#include #include #define ADIS_WRITE_REG(reg) ((0x80 | (reg))) @@ -131,7 +132,7 @@ struct adis { unsigned long irq_flag; void *buffer; - u8 tx[10] ____cacheline_aligned; + u8 tx[10] __aligned(IIO_DMA_MINALIGN); u8 rx[4]; }; diff --git a/include/linux/init.h b/include/linux/init.h index 266c3e1640d47..01b52c9c75268 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -89,9 +89,6 @@ __latent_entropy #define __meminitdata __section(".meminit.data") #define __meminitconst __section(".meminit.rodata") -#define __memexit __section(".memexit.text") __exitused __cold notrace -#define __memexitdata __section(".memexit.data") -#define __memexitconst __section(".memexit.rodata") /* For assembly routines */ #define __HEAD .section ".head.text","ax" diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 74c60f9446f84..489362b0cd857 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -311,9 +311,9 @@ LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how) LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb) -LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock, +LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) -LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock, +LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock, struct sk_buff *skb, u32 *secid) LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e8c350a3ade15..e9f4f845d760a 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -186,6 +186,8 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Cancel ongoing garbage collectors before destroying the set*/ + void (*cancel_gc)(struct ip_set *set); /* Region-locking is used */ bool region_lock; }; @@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { + /* For call_cru in destroy */ + struct rcu_head rcu; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index eaaef3ffec221..90507d4afcd6d 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -393,6 +393,10 @@ static inline void user_single_step_report(struct pt_regs *regs) #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif +#ifndef exception_ip +#define exception_ip(x) instruction_pointer(x) +#endif + extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index bbbafc0feb5b0..27a26092493ad 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -748,8 +748,17 @@ struct uart_driver { void uart_write_wakeup(struct uart_port *port); -#define __uart_port_tx(uport, ch, tx_ready, put_char, tx_done, for_test, \ - for_post) \ +/** + * enum UART_TX_FLAGS -- flags for uart_port_tx_flags() + * + * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer + */ +enum UART_TX_FLAGS { + UART_TX_NOSTOP = BIT(0), +}; + +#define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done, \ + for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ struct circ_buf *xmit = &__port->state->xmit; \ @@ -777,7 +786,7 @@ void uart_write_wakeup(struct uart_port *port); if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ - if (pending == 0) \ + if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ @@ -812,7 +821,7 @@ void uart_write_wakeup(struct uart_port *port); */ #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ - __uart_port_tx(port, ch, tx_ready, put_char, tx_done, __count, \ + __uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count, \ __count--); \ }) @@ -826,8 +835,21 @@ void uart_write_wakeup(struct uart_port *port); * See uart_port_tx_limited() for more details. */ #define uart_port_tx(port, ch, tx_ready, put_char) \ - __uart_port_tx(port, ch, tx_ready, put_char, ({}), true, ({})) + __uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({})) + +/** + * uart_port_tx_flags -- transmit helper for uart_port with flags + * @port: uart port + * @ch: variable to store a character to be written to the HW + * @flags: %UART_TX_NOSTOP or similar + * @tx_ready: can HW accept more data function + * @put_char: function to write a character + * + * See uart_port_tx_limited() for more details. + */ +#define uart_port_tx_flags(port, ch, flags, tx_ready, put_char) \ + __uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({})) /* * Baud rate helpers. */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index cf9f0c61796e1..696f8dc4aa53c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -652,7 +652,7 @@ struct trace_event_file { struct list_head list; struct trace_event_call *event_call; struct event_filter __rcu *filter; - struct eventfs_file *ef; + struct eventfs_inode *ei; struct trace_array *tr; struct trace_subsystem_dir *system; struct list_head triggers; diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 009072792fa36..7a5fe17b6bf9c 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -23,26 +23,69 @@ struct file_operations; struct eventfs_file; -struct dentry *eventfs_create_events_dir(const char *name, - struct dentry *parent); - -struct eventfs_file *eventfs_add_subsystem_dir(const char *name, - struct dentry *parent); +/** + * eventfs_callback - A callback function to create dynamic files in eventfs + * @name: The name of the file that is to be created + * @mode: return the file mode for the file (RW access, etc) + * @data: data to pass to the created file ops + * @fops: the file operations of the created file + * + * The evetnfs files are dynamically created. The struct eventfs_entry array + * is passed to eventfs_create_dir() or eventfs_create_events_dir() that will + * be used to create the files within those directories. When a lookup + * or access to a file within the directory is made, the struct eventfs_entry + * array is used to find a callback() with the matching name that is being + * referenced (for lookups, the entire array is iterated and each callback + * will be called). + * + * The callback will be called with @name for the name of the file to create. + * The callback can return less than 1 to indicate that no file should be + * created. + * + * If a file is to be created, then @mode should be populated with the file + * mode (permissions) for which the file is created for. This would be + * used to set the created inode i_mode field. + * + * The @data should be set to the data passed to the other file operations + * (read, write, etc). Note, @data will also point to the data passed in + * to eventfs_create_dir() or eventfs_create_events_dir(), but the callback + * can replace the data if it chooses to. Otherwise, the original data + * will be used for the file operation functions. + * + * The @fops should be set to the file operations that will be used to create + * the inode. + * + * NB. This callback is called while holding internal locks of the eventfs + * system. The callback must not call any code that might also call into + * the tracefs or eventfs system or it will risk creating a deadlock. + */ +typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, + const struct file_operations **fops); -struct eventfs_file *eventfs_add_dir(const char *name, - struct eventfs_file *ef_parent); +/** + * struct eventfs_entry - dynamically created eventfs file call back handler + * @name: Then name of the dynamic file in an eventfs directory + * @callback: The callback to get the fops of the file when it is created + * + * See evenfs_callback() typedef for how to set up @callback. + */ +struct eventfs_entry { + const char *name; + eventfs_callback callback; +}; -int eventfs_add_file(const char *name, umode_t mode, - struct eventfs_file *ef_parent, void *data, - const struct file_operations *fops); +struct eventfs_inode; -int eventfs_add_events_file(const char *name, umode_t mode, - struct dentry *parent, void *data, - const struct file_operations *fops); +struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry *parent, + const struct eventfs_entry *entries, + int size, void *data); -void eventfs_remove(struct eventfs_file *ef); +struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode *parent, + const struct eventfs_entry *entries, + int size, void *data); -void eventfs_remove_events_dir(struct dentry *dentry); +void eventfs_remove_events_dir(struct eventfs_inode *ei); +void eventfs_remove_dir(struct eventfs_inode *ei); struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, diff --git a/include/net/tls.h b/include/net/tls.h index a2b44578dcb75..5fdd5dd251df2 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -96,9 +96,6 @@ struct tls_sw_context_tx { struct tls_rec *open_rec; struct list_head tx_list; atomic_t encrypt_pending; - /* protect crypto_wait with encrypt_pending */ - spinlock_t encrypt_compl_lock; - int async_notify; u8 async_capable:1; #define BIT_TX_SCHEDULED 0 @@ -135,8 +132,6 @@ struct tls_sw_context_rx { struct tls_strparser strp; atomic_t decrypt_pending; - /* protect crypto_wait with decrypt_pending*/ - spinlock_t decrypt_compl_lock; struct sk_buff_head async_hold; struct wait_queue_head wq; }; diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h index a6c808b223183..475294c853aa4 100644 --- a/include/sound/tas2781.h +++ b/include/sound/tas2781.h @@ -135,6 +135,7 @@ struct tasdevice_priv { void tas2781_reset(struct tasdevice_priv *tas_dev); int tascodec_init(struct tasdevice_priv *tas_priv, void *codec, + struct module *module, void (*cont)(const struct firmware *fw, void *context)); struct tasdevice_priv *tasdevice_kzalloc(struct i2c_client *i2c); int tasdevice_init(struct tasdevice_priv *tas_priv); diff --git a/init/Kconfig b/init/Kconfig index 6d35728b94b2b..18fece8fe0857 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -89,6 +89,15 @@ config CC_HAS_ASM_GOTO_TIED_OUTPUT # Detect buggy gcc and clang, fixed in gcc-11 clang-14. def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) +config GCC_ASM_GOTO_OUTPUT_WORKAROUND + bool + depends on CC_IS_GCC && CC_HAS_ASM_GOTO_OUTPUT + # Fixed in GCC 14, 13.3, 12.4 and 11.5 + # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 + default y if GCC_VERSION < 110500 + default y if GCC_VERSION >= 120000 && GCC_VERSION < 120400 + default y if GCC_VERSION >= 130000 && GCC_VERSION < 130300 + config TOOLS_SUPPORT_RELR def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh) diff --git a/io_uring/net.c b/io_uring/net.c index 43bc9a5f96f9d..161622029147c 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1372,7 +1372,7 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags) * has already been done */ if (issue_flags & IO_URING_F_MULTISHOT) - ret = IOU_ISSUE_SKIP_COMPLETE; + return IOU_ISSUE_SKIP_COMPLETE; return ret; } if (ret == -ERESTARTSYS) @@ -1397,7 +1397,8 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags) ret, IORING_CQE_F_MORE)) goto retry; - return -ECANCELED; + io_req_set_res(req, ret, 0); + return IOU_STOP_MULTISHOT; } int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 2ad881d07752c..4e715b9b278e7 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -162,6 +162,9 @@ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ | MEMBARRIER_CMD_GET_REGISTRATIONS) +static DEFINE_MUTEX(membarrier_ipi_mutex); +#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex) + static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ @@ -259,6 +262,7 @@ static int membarrier_global_expedited(void) if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { @@ -347,6 +351,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); if (cpu_id >= 0) { @@ -460,6 +465,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) * between threads which are users of @mm has its membarrier state * updated. */ + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b01ae7d360218..83ba342aef31f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5325,7 +5325,17 @@ static LIST_HEAD(ftrace_direct_funcs); static int register_ftrace_function_nolock(struct ftrace_ops *ops); +/* + * If there are multiple ftrace_ops, use SAVE_REGS by default, so that direct + * call will be jumped from ftrace_regs_caller. Only if the architecture does + * not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it + * jumps from ftrace_caller for multiple ftrace_ops. + */ +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS #define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS) +#else +#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS) +#endif static int check_direct_multi(struct ftrace_ops *ops) { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f232cf56fa057..1ac6637895a44 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1091,7 +1091,7 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return -EINVAL; + return EPOLLERR; cpu_buffer = buffer->buffers[cpu]; work = &cpu_buffer->irq_work; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index fc00356a5a0a1..82e28777cacf5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include @@ -2311,7 +2312,7 @@ struct saved_cmdlines_buffer { unsigned *map_cmdline_to_pid; unsigned cmdline_num; int cmdline_idx; - char *saved_cmdlines; + char saved_cmdlines[]; }; static struct saved_cmdlines_buffer *savedcmd; @@ -2325,47 +2326,60 @@ static inline void set_cmdline(int idx, const char *cmdline) strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); } -static int allocate_cmdlines_buffer(unsigned int val, - struct saved_cmdlines_buffer *s) +static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) +{ + int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); + + kfree(s->map_cmdline_to_pid); + kmemleak_free(s); + free_pages((unsigned long)s, order); +} + +static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) { + struct saved_cmdlines_buffer *s; + struct page *page; + int orig_size, size; + int order; + + /* Figure out how much is needed to hold the given number of cmdlines */ + orig_size = sizeof(*s) + val * TASK_COMM_LEN; + order = get_order(orig_size); + size = 1 << (order + PAGE_SHIFT); + page = alloc_pages(GFP_KERNEL, order); + if (!page) + return NULL; + + s = page_address(page); + kmemleak_alloc(s, size, 1, GFP_KERNEL); + memset(s, 0, sizeof(*s)); + + /* Round up to actual allocation */ + val = (size - sizeof(*s)) / TASK_COMM_LEN; + s->cmdline_num = val; + s->map_cmdline_to_pid = kmalloc_array(val, sizeof(*s->map_cmdline_to_pid), GFP_KERNEL); - if (!s->map_cmdline_to_pid) - return -ENOMEM; - - s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL); - if (!s->saved_cmdlines) { - kfree(s->map_cmdline_to_pid); - return -ENOMEM; + if (!s->map_cmdline_to_pid) { + free_saved_cmdlines_buffer(s); + return NULL; } s->cmdline_idx = 0; - s->cmdline_num = val; memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(s->map_pid_to_cmdline)); memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, val * sizeof(*s->map_cmdline_to_pid)); - return 0; + return s; } static int trace_create_savedcmd(void) { - int ret; + savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT); - savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); - if (!savedcmd) - return -ENOMEM; - - ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd); - if (ret < 0) { - kfree(savedcmd); - savedcmd = NULL; - return -ENOMEM; - } - - return 0; + return savedcmd ? 0 : -ENOMEM; } int is_tracing_stopped(void) @@ -6056,26 +6070,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) -{ - kfree(s->saved_cmdlines); - kfree(s->map_cmdline_to_pid); - kfree(s); -} - static int tracing_resize_saved_cmdlines(unsigned int val) { struct saved_cmdlines_buffer *s, *savedcmd_temp; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = allocate_cmdlines_buffer(val); if (!s) return -ENOMEM; - if (allocate_cmdlines_buffer(val, s) < 0) { - kfree(s); - return -ENOMEM; - } - preempt_disable(); arch_spin_lock(&trace_cmdline_lock); savedcmd_temp = savedcmd; @@ -9758,7 +9760,6 @@ static __init void create_trace_instances(struct dentry *d_tracer) static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) { - struct trace_event_file *file; int cpu; trace_create_file("available_tracers", TRACE_MODE_READ, d_tracer, @@ -9791,11 +9792,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("trace_marker", 0220, d_tracer, tr, &tracing_mark_fops); - file = __find_event_file(tr, "ftrace", "print"); - if (file && file->ef) - eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef, - file, &event_trigger_fops); - tr->trace_marker_file = file; + tr->trace_marker_file = __find_event_file(tr, "ftrace", "print"); trace_create_file("trace_marker_raw", 0220, d_tracer, tr, &tracing_mark_raw_fops); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 51c0a970339e2..02b727a54648f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -381,7 +381,7 @@ struct trace_array { struct dentry *dir; struct dentry *options; struct dentry *percpu_dir; - struct dentry *event_dir; + struct eventfs_inode *event_dir; struct trace_options *topts; struct list_head systems; struct list_head events; @@ -1345,7 +1345,7 @@ struct trace_subsystem_dir { struct list_head list; struct event_subsystem *subsystem; struct trace_array *tr; - struct eventfs_file *ef; + struct eventfs_inode *ei; int ref_count; int nr_events; }; diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c index ca224d53bfdcd..5bbdbcbbde3cd 100644 --- a/kernel/trace/trace_btf.c +++ b/kernel/trace/trace_btf.c @@ -91,8 +91,8 @@ const struct btf_member *btf_find_struct_member(struct btf *btf, for_each_member(i, type, member) { if (!member->name_off) { /* Anonymous union/struct: push it for later use */ - type = btf_type_skip_modifiers(btf, member->type, &tid); - if (type && top < BTF_ANON_STACK_MAX) { + if (btf_type_skip_modifiers(btf, member->type, &tid) && + top < BTF_ANON_STACK_MAX) { anon_stack[top].tid = tid; anon_stack[top++].offset = cur_offset + member->offset; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 82cb22ad6d617..941a394d39118 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -984,7 +984,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) return; if (!--dir->nr_events) { - eventfs_remove(dir->ef); + eventfs_remove_dir(dir->ei); list_del(&dir->list); __put_system_dir(dir); } @@ -1013,7 +1013,7 @@ void event_file_put(struct trace_event_file *file) static void remove_event_file_dir(struct trace_event_file *file) { - eventfs_remove(file->ef); + eventfs_remove_dir(file->ei); list_del(&file->list); remove_subsystem(file->system); free_event_filter(file->filter); @@ -2302,14 +2302,40 @@ create_new_subsystem(const char *name) return NULL; } -static struct eventfs_file * +static int system_callback(const char *name, umode_t *mode, void **data, + const struct file_operations **fops) +{ + if (strcmp(name, "filter") == 0) + *fops = &ftrace_subsystem_filter_fops; + + else if (strcmp(name, "enable") == 0) + *fops = &ftrace_system_enable_fops; + + else + return 0; + + *mode = TRACE_MODE_WRITE; + return 1; +} + +static struct eventfs_inode * event_subsystem_dir(struct trace_array *tr, const char *name, - struct trace_event_file *file, struct dentry *parent) + struct trace_event_file *file, struct eventfs_inode *parent) { struct event_subsystem *system, *iter; struct trace_subsystem_dir *dir; - struct eventfs_file *ef; - int res; + struct eventfs_inode *ei; + int nr_entries; + static struct eventfs_entry system_entries[] = { + { + .name = "filter", + .callback = system_callback, + }, + { + .name = "enable", + .callback = system_callback, + } + }; /* First see if we did not already create this dir */ list_for_each_entry(dir, &tr->systems, list) { @@ -2317,7 +2343,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name, if (strcmp(system->name, name) == 0) { dir->nr_events++; file->system = dir; - return dir->ef; + return dir->ei; } } @@ -2341,39 +2367,29 @@ event_subsystem_dir(struct trace_array *tr, const char *name, } else __get_system(system); - ef = eventfs_add_subsystem_dir(name, parent); - if (IS_ERR(ef)) { + /* ftrace only has directories no files */ + if (strcmp(name, "ftrace") == 0) + nr_entries = 0; + else + nr_entries = ARRAY_SIZE(system_entries); + + ei = eventfs_create_dir(name, parent, system_entries, nr_entries, dir); + if (IS_ERR(ei)) { pr_warn("Failed to create system directory %s\n", name); __put_system(system); goto out_free; } - dir->ef = ef; + dir->ei = ei; dir->tr = tr; dir->ref_count = 1; dir->nr_events = 1; dir->subsystem = system; file->system = dir; - /* the ftrace system is special, do not create enable or filter files */ - if (strcmp(name, "ftrace") != 0) { - - res = eventfs_add_file("filter", TRACE_MODE_WRITE, - dir->ef, dir, - &ftrace_subsystem_filter_fops); - if (res) { - kfree(system->filter); - system->filter = NULL; - pr_warn("Could not create tracefs '%s/filter' entry\n", name); - } - - eventfs_add_file("enable", TRACE_MODE_WRITE, dir->ef, dir, - &ftrace_system_enable_fops); - } - list_add(&dir->list, &tr->systems); - return dir->ef; + return dir->ei; out_free: kfree(dir); @@ -2422,15 +2438,134 @@ event_define_fields(struct trace_event_call *call) return ret; } +static int event_callback(const char *name, umode_t *mode, void **data, + const struct file_operations **fops) +{ + struct trace_event_file *file = *data; + struct trace_event_call *call = file->event_call; + + if (strcmp(name, "format") == 0) { + *mode = TRACE_MODE_READ; + *fops = &ftrace_event_format_fops; + *data = call; + return 1; + } + + /* + * Only event directories that can be enabled should have + * triggers or filters, with the exception of the "print" + * event that can have a "trigger" file. + */ + if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) { + if (call->class->reg && strcmp(name, "enable") == 0) { + *mode = TRACE_MODE_WRITE; + *fops = &ftrace_enable_fops; + return 1; + } + + if (strcmp(name, "filter") == 0) { + *mode = TRACE_MODE_WRITE; + *fops = &ftrace_event_filter_fops; + return 1; + } + } + + if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) || + strcmp(trace_event_name(call), "print") == 0) { + if (strcmp(name, "trigger") == 0) { + *mode = TRACE_MODE_WRITE; + *fops = &event_trigger_fops; + return 1; + } + } + +#ifdef CONFIG_PERF_EVENTS + if (call->event.type && call->class->reg && + strcmp(name, "id") == 0) { + *mode = TRACE_MODE_READ; + *data = (void *)(long)call->event.type; + *fops = &ftrace_event_id_fops; + return 1; + } +#endif + +#ifdef CONFIG_HIST_TRIGGERS + if (strcmp(name, "hist") == 0) { + *mode = TRACE_MODE_READ; + *fops = &event_hist_fops; + return 1; + } +#endif +#ifdef CONFIG_HIST_TRIGGERS_DEBUG + if (strcmp(name, "hist_debug") == 0) { + *mode = TRACE_MODE_READ; + *fops = &event_hist_debug_fops; + return 1; + } +#endif +#ifdef CONFIG_TRACE_EVENT_INJECT + if (call->event.type && call->class->reg && + strcmp(name, "inject") == 0) { + *mode = 0200; + *fops = &event_inject_fops; + return 1; + } +#endif + return 0; +} + static int -event_create_dir(struct dentry *parent, struct trace_event_file *file) +event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) { struct trace_event_call *call = file->event_call; - struct eventfs_file *ef_subsystem = NULL; struct trace_array *tr = file->tr; - struct eventfs_file *ef; + struct eventfs_inode *e_events; + struct eventfs_inode *ei; const char *name; + int nr_entries; int ret; + static struct eventfs_entry event_entries[] = { + { + .name = "enable", + .callback = event_callback, + }, + { + .name = "filter", + .callback = event_callback, + }, + { + .name = "trigger", + .callback = event_callback, + }, + { + .name = "format", + .callback = event_callback, + }, +#ifdef CONFIG_PERF_EVENTS + { + .name = "id", + .callback = event_callback, + }, +#endif +#ifdef CONFIG_HIST_TRIGGERS + { + .name = "hist", + .callback = event_callback, + }, +#endif +#ifdef CONFIG_HIST_TRIGGERS_DEBUG + { + .name = "hist_debug", + .callback = event_callback, + }, +#endif +#ifdef CONFIG_TRACE_EVENT_INJECT + { + .name = "inject", + .callback = event_callback, + }, +#endif + }; /* * If the trace point header did not define TRACE_SYSTEM @@ -2440,29 +2575,20 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) if (WARN_ON_ONCE(strcmp(call->class->system, TRACE_SYSTEM) == 0)) return -ENODEV; - ef_subsystem = event_subsystem_dir(tr, call->class->system, file, parent); - if (!ef_subsystem) + e_events = event_subsystem_dir(tr, call->class->system, file, parent); + if (!e_events) return -ENOMEM; + nr_entries = ARRAY_SIZE(event_entries); + name = trace_event_name(call); - ef = eventfs_add_dir(name, ef_subsystem); - if (IS_ERR(ef)) { + ei = eventfs_create_dir(name, e_events, event_entries, nr_entries, file); + if (IS_ERR(ei)) { pr_warn("Could not create tracefs '%s' directory\n", name); return -1; } - file->ef = ef; - - if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) - eventfs_add_file("enable", TRACE_MODE_WRITE, file->ef, file, - &ftrace_enable_fops); - -#ifdef CONFIG_PERF_EVENTS - if (call->event.type && call->class->reg) - eventfs_add_file("id", TRACE_MODE_READ, file->ef, - (void *)(long)call->event.type, - &ftrace_event_id_fops); -#endif + file->ei = ei; ret = event_define_fields(call); if (ret < 0) { @@ -2470,35 +2596,6 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) return ret; } - /* - * Only event directories that can be enabled should have - * triggers or filters. - */ - if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) { - eventfs_add_file("filter", TRACE_MODE_WRITE, file->ef, - file, &ftrace_event_filter_fops); - - eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef, - file, &event_trigger_fops); - } - -#ifdef CONFIG_HIST_TRIGGERS - eventfs_add_file("hist", TRACE_MODE_READ, file->ef, file, - &event_hist_fops); -#endif -#ifdef CONFIG_HIST_TRIGGERS_DEBUG - eventfs_add_file("hist_debug", TRACE_MODE_READ, file->ef, file, - &event_hist_debug_fops); -#endif - eventfs_add_file("format", TRACE_MODE_READ, file->ef, call, - &ftrace_event_format_fops); - -#ifdef CONFIG_TRACE_EVENT_INJECT - if (call->event.type && call->class->reg) - eventfs_add_file("inject", 0200, file->ef, file, - &event_inject_fops); -#endif - return 0; } @@ -3644,30 +3741,65 @@ static __init int setup_trace_event(char *str) } __setup("trace_event=", setup_trace_event); +static int events_callback(const char *name, umode_t *mode, void **data, + const struct file_operations **fops) +{ + if (strcmp(name, "enable") == 0) { + *mode = TRACE_MODE_WRITE; + *fops = &ftrace_tr_enable_fops; + return 1; + } + + if (strcmp(name, "header_page") == 0) + *data = ring_buffer_print_page_header; + + else if (strcmp(name, "header_event") == 0) + *data = ring_buffer_print_entry_header; + + else + return 0; + + *mode = TRACE_MODE_READ; + *fops = &ftrace_show_header_fops; + return 1; +} + /* Expects to have event_mutex held when called */ static int create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) { - struct dentry *d_events; + struct eventfs_inode *e_events; struct dentry *entry; - int error = 0; + int nr_entries; + static struct eventfs_entry events_entries[] = { + { + .name = "enable", + .callback = events_callback, + }, + { + .name = "header_page", + .callback = events_callback, + }, + { + .name = "header_event", + .callback = events_callback, + }, + }; entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent, tr, &ftrace_set_event_fops); if (!entry) return -ENOMEM; - d_events = eventfs_create_events_dir("events", parent); - if (IS_ERR(d_events)) { + nr_entries = ARRAY_SIZE(events_entries); + + e_events = eventfs_create_events_dir("events", parent, events_entries, + nr_entries, tr); + if (IS_ERR(e_events)) { pr_warn("Could not create tracefs 'events' directory\n"); return -ENOMEM; } - error = eventfs_add_events_file("enable", TRACE_MODE_WRITE, d_events, - tr, &ftrace_tr_enable_fops); - if (error) - return -ENOMEM; - /* There are not as crucial, just warn if they are not created */ trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent, @@ -3677,16 +3809,7 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) TRACE_MODE_WRITE, parent, tr, &ftrace_set_event_notrace_pid_fops); - /* ring buffer internal formats */ - eventfs_add_events_file("header_page", TRACE_MODE_READ, d_events, - ring_buffer_print_page_header, - &ftrace_show_header_fops); - - eventfs_add_events_file("header_event", TRACE_MODE_READ, d_events, - ring_buffer_print_entry_header, - &ftrace_show_header_fops); - - tr->event_dir = d_events; + tr->event_dir = e_events; return 0; } diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 846e02c0fb59a..624e0867316d0 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -441,8 +441,9 @@ static unsigned int trace_string(struct synth_trace_event *entry, if (is_dynamic) { union trace_synth_field *data = &entry->fields[*n_u64]; + len = fetch_store_strlen((unsigned long)str_val); data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size; - data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val); + data->as_dynamic.len = len; ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 46439e3bcec4d..b33c3861fbbbf 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1470,8 +1470,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { - if (tracing_alloc_snapshot_instance(file->tr) != 0) - return 0; + int ret = tracing_alloc_snapshot_instance(file->tr); + + if (ret < 0) + return ret; return register_trigger(glob, data, file); } diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index bd0d01d00fb9d..a8e28f9b9271c 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -2444,6 +2444,9 @@ static int timerlat_fd_open(struct inode *inode, struct file *file) tlat = this_cpu_tmr_var(); tlat->count = 0; + hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); + tlat->timer.function = timerlat_irq; + migrate_enable(); return 0; }; @@ -2526,9 +2529,6 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count, tlat->tracing_thread = false; tlat->kthread = current; - hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); - tlat->timer.function = timerlat_irq; - /* Annotate now to drift new period */ tlat->abs_period = hrtimer_cb_get_time(&tlat->timer); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 4dc74d73fc1df..34289f9c67076 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1159,9 +1159,12 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, if (!(ctx->flags & TPARG_FL_TEVENT) && (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 || strncmp(arg, "\\\"", 2) == 0)) { - /* The type of $comm must be "string", and not an array. */ - if (parg->count || (t && strcmp(t, "string"))) + /* The type of $comm must be "string", and not an array type. */ + if (parg->count || (t && strcmp(t, "string"))) { + trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), + NEED_STRING_TYPE); goto out; + } parg->type = find_fetch_type("string", ctx->flags); } else parg->type = find_fetch_type(t, ctx->flags); @@ -1169,18 +1172,6 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE); goto out; } - parg->offset = *size; - *size += parg->type->size * (parg->count ?: 1); - - ret = -ENOMEM; - if (parg->count) { - len = strlen(parg->type->fmttype) + 6; - parg->fmt = kmalloc(len, GFP_KERNEL); - if (!parg->fmt) - goto out; - snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype, - parg->count); - } code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL); if (!code) @@ -1204,6 +1195,19 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, goto fail; } } + parg->offset = *size; + *size += parg->type->size * (parg->count ?: 1); + + if (parg->count) { + len = strlen(parg->type->fmttype) + 6; + parg->fmt = kmalloc(len, GFP_KERNEL); + if (!parg->fmt) { + ret = -ENOMEM; + goto out; + } + snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype, + parg->count); + } ret = -EINVAL; /* Store operation */ diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 850d9ecb6765a..c1877d0182691 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -515,7 +515,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(BAD_HYPHEN, "Failed to parse single hyphen. Forgot '>'?"), \ C(NO_BTF_FIELD, "This field is not found."), \ C(BAD_BTF_TID, "Failed to get BTF type info."),\ - C(BAD_TYPE4STR, "This type does not fit for string."), + C(BAD_TYPE4STR, "This type does not fit for string."),\ + C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"), #undef C #define C(a, b) TP_ERR_##a diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e6a95bb74e228..fd7b84b06d926 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5793,13 +5793,9 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND)) continue; - /* creating multiple pwqs breaks ordering guarantee */ - if (!list_empty(&wq->pwqs)) { - if (wq->flags & __WQ_ORDERED_EXPLICIT) - continue; - wq->flags &= ~__WQ_ORDERED; - } + if (wq->flags & __WQ_ORDERED) + continue; ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { diff --git a/lib/kobject.c b/lib/kobject.c index 59dbcbdb1c916..72fa20f405f15 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -74,10 +74,12 @@ static int create_dir(struct kobject *kobj) if (error) return error; - error = sysfs_create_groups(kobj, ktype->default_groups); - if (error) { - sysfs_remove_dir(kobj); - return error; + if (ktype) { + error = sysfs_create_groups(kobj, ktype->default_groups); + if (error) { + sysfs_remove_dir(kobj); + return error; + } } /* @@ -589,7 +591,8 @@ static void __kobject_del(struct kobject *kobj) sd = kobj->sd; ktype = get_ktype(kobj); - sysfs_remove_groups(kobj, ktype->default_groups); + if (ktype) + sysfs_remove_groups(kobj, ktype->default_groups); /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { @@ -666,6 +669,10 @@ static void kobject_cleanup(struct kobject *kobj) pr_debug("'%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); + if (t && !t->release) + pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", + kobject_name(kobj), kobj); + /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { pr_debug("'%s' (%p): auto cleanup kobject_del\n", @@ -676,13 +683,10 @@ static void kobject_cleanup(struct kobject *kobj) parent = NULL; } - if (t->release) { + if (t && t->release) { pr_debug("'%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); - } else { - pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", - kobject_name(kobj), kobj); } /* free name if we allocated it */ @@ -1056,7 +1060,7 @@ const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *pa { const struct kobj_ns_type_operations *ops = NULL; - if (parent && parent->ktype->child_ns_type) + if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent); return ops; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 1e3447bccdb14..e039d05304dd9 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -436,7 +436,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); - wb->dirty_sleep = jiffies; err = fprop_local_init_percpu(&wb->completions, gfp); if (err) @@ -921,6 +920,7 @@ int bdi_init(struct backing_dev_info *bdi) INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); + bdi->last_bdp_sleep = jiffies; return cgwb_bdi_init(bdi); } diff --git a/mm/memory.c b/mm/memory.c index dccf9203dd536..b3be18f1f1206 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5315,7 +5315,7 @@ static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs return true; if (regs && !user_mode(regs)) { - unsigned long ip = instruction_pointer(regs); + unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } @@ -5340,7 +5340,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r { mmap_read_unlock(mm); if (regs && !user_mode(regs)) { - unsigned long ip = instruction_pointer(regs); + unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4656534b8f5cc..a9303f8866399 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1638,7 +1638,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? - div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; + div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need @@ -1921,7 +1921,7 @@ static int balance_dirty_pages(struct bdi_writeback *wb, break; } __set_current_state(TASK_KILLABLE); - wb->dirty_sleep = now; + bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 96d9eae5c7cc8..cd5ad448ac2f0 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; @@ -472,6 +473,15 @@ static __always_inline ssize_t mfill_atomic_hugetlb( goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ @@ -622,8 +633,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return mfill_atomic_hugetlb(dst_vma, dst_start, - src_start, len, flags); + return mfill_atomic_hugetlb(dst_vma, dst_start, src_start, + len, mmap_changing, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 16af1a7f80f60..31a93cae5111b 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -86,7 +86,7 @@ struct j1939_priv { unsigned int tp_max_packet_size; /* lock for j1939_socks list */ - spinlock_t j1939_socks_lock; + rwlock_t j1939_socks_lock; struct list_head j1939_socks; struct kref rx_kref; @@ -301,6 +301,7 @@ struct j1939_sock { int ifindex; struct j1939_addr addr; + spinlock_t filters_lock; struct j1939_filter *filters; int nfilters; pgn_t pgn_rx_filter; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index ecff1c947d683..a6fb89fa62785 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) return ERR_PTR(-ENOMEM); j1939_tp_init(priv); - spin_lock_init(&priv->j1939_socks_lock); + rwlock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); mutex_lock(&j1939_netdev_lock); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index b28c976f52a0a..1f49d6164ea1d 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); } static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) { - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_del_init(&jsk->list); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; @@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk, static bool j1939_sk_match_filter(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { - const struct j1939_filter *f = jsk->filters; - int nfilter = jsk->nfilters; + const struct j1939_filter *f; + int nfilter; + + spin_lock_bh(&jsk->filters_lock); + + f = jsk->filters; + nfilter = jsk->nfilters; if (!nfilter) /* receive all when no filters are assigned */ - return true; + goto filter_match_found; for (; nfilter; ++f, --nfilter) { if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) @@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk, continue; if ((skcb->addr.src_name & f->name_mask) != f->name) continue; - return true; + goto filter_match_found; } + + spin_unlock_bh(&jsk->filters_lock); return false; + +filter_match_found: + spin_unlock_bh(&jsk->filters_lock); + return true; } static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, @@ -329,13 +340,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb) struct j1939_sock *jsk; bool match = false; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { match = j1939_sk_recv_match_one(jsk, skcb); if (match) break; } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); return match; } @@ -344,11 +355,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sock *jsk; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { j1939_sk_recv_one(jsk, skb); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static void j1939_sk_sock_destruct(struct sock *sk) @@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + spin_lock_init(&jsk->filters_lock); /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ sock_set_flag(sk, SOCK_RCU_FREE); @@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, } lock_sock(&jsk->sk); + spin_lock_bh(&jsk->filters_lock); ofilters = jsk->filters; jsk->filters = filters; jsk->nfilters = count; + spin_unlock_bh(&jsk->filters_lock); release_sock(&jsk->sk); kfree(ofilters); return 0; @@ -1080,12 +1094,12 @@ void j1939_sk_errqueue(struct j1939_session *session, } /* spread RX notifications to all sockets subscribed to this session */ - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { if (j1939_sk_recv_match_one(jsk, &session->skcb)) __j1939_sk_errqueue(session, &jsk->sk, type); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); }; void j1939_sk_send_loop_abort(struct sock *sk, int err) @@ -1273,7 +1287,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) struct j1939_sock *jsk; int error_code = ENETDOWN; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) @@ -1281,7 +1295,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) j1939_sk_queue_drop_all(priv, jsk, error_code); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index 16ed7bfd29e4f..34fd1d9b2db86 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -471,7 +471,10 @@ static void handshake_req_destroy_test1(struct kunit *test) handshake_req_cancel(sock->sk); /* Act */ - fput(filp); + /* Ensure the close/release/put process has run to + * completion before checking the result. + */ + __fput_sync(filp); /* Assert */ KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 306f942c3b28a..dd4b5f0aa1318 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -291,7 +291,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "HSR: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } @@ -338,7 +338,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "PRP: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 5481acbfc1d43..5ab9594ae119e 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation * * Transmit and frame generation functions. */ @@ -3913,6 +3913,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, goto begin; skb = __skb_dequeue(&tx.skbs); + info = IEEE80211_SKB_CB(skb); if (!skb_queue_empty(&tx.skbs)) { spin_lock_bh(&fq->lock); @@ -3957,7 +3958,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, } encap_out: - IEEE80211_SKB_CB(skb)->control.vif = vif; + info->control.vif = vif; if (tx.sta && wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index d042d32beb4df..c1717322c8922 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -130,10 +130,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { - struct mptcp_pm_addr_entry new_entry; + struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry; __be16 msk_sport = ((struct inet_sock *) inet_sk((struct sock *)msk))->inet_sport; + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&e->addr, skc, false)) { + entry = e; + break; + } + } + spin_unlock_bh(&msk->pm.lock); + if (entry) + return entry->addr.id; + memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry)); new_entry.addr = *skc; new_entry.addr.id = 0; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5c003a0f0fe5b..9d4d5dbdbb53b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1522,8 +1522,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, void mptcp_check_and_set_pending(struct sock *sk) { - if (mptcp_send_head(sk)) - mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING); + if (mptcp_send_head(sk)) { + mptcp_data_lock(sk); + mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); + mptcp_data_unlock(sk); + } } static int __subflow_push_pending(struct sock *sk, struct sock *ssk, @@ -1964,6 +1967,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (copied <= 0) return; + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); + msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); @@ -2318,9 +2324,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) if (__mptcp_check_fallback(msk)) return false; - if (tcp_rtx_and_write_queues_empty(sk)) - return false; - /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue @@ -3137,7 +3140,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; - msk->push_pending = 0; msk->recovery = false; msk->can_ack = false; msk->fully_established = false; @@ -3152,6 +3154,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; + msk->rcvspace_init = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); @@ -3239,6 +3242,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); + msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; @@ -3249,8 +3253,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; - - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err, @@ -3362,8 +3364,7 @@ static void mptcp_release_cb(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { - unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) | - msk->push_pending; + unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; if (!flags) @@ -3379,7 +3380,6 @@ static void mptcp_release_cb(struct sock *sk) * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ - msk->push_pending = 0; msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); @@ -3510,10 +3510,9 @@ void mptcp_finish_connect(struct sock *ssk) WRITE_ONCE(msk->write_seq, subflow->idsn + 1); WRITE_ONCE(msk->snd_nxt, msk->write_seq); WRITE_ONCE(msk->snd_una, msk->write_seq); + WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); mptcp_pm_new_connection(msk, ssk, 0); - - mptcp_rcv_space_init(msk, ssk); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 07c5ac37d092b..094d3fd47a92f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -283,7 +283,6 @@ struct mptcp_sock { int rmem_released; unsigned long flags; unsigned long cb_flags; - unsigned long push_pending; bool recovery; /* closing subflow write queue reinjected */ bool can_ack; bool fully_established; @@ -302,7 +301,8 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1, - free_first:1; + free_first:1, + rcvspace_init:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -1104,7 +1104,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) && + return (1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) && is_active_ssk(subflow) && !subflow->conn_finished; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index d3c5ecf8ddf52..8c7e22a9a37bd 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -424,6 +424,8 @@ void __mptcp_sync_state(struct sock *sk, int state) struct mptcp_sock *msk = mptcp_sk(sk); __mptcp_propagate_sndbuf(sk, msk->first); + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); if (sk->sk_state == TCP_SYN_SENT) { inet_sk_state_store(sk, state); sk->sk_state_change(sk); @@ -545,7 +547,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_rcv_space_init(msk, sk); mptcp_propagate_state(parent, sk); } return; @@ -1736,7 +1737,6 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_do_fallback(sk); - mptcp_rcv_space_init(msk, sk); pr_fallback(msk); subflow->conn_finished = 1; mptcp_propagate_state(parent, sk); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 26ab0e9612d82..9523104a90da4 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -28,6 +28,7 @@ #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) @@ -57,9 +58,6 @@ mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); @@ -288,6 +286,15 @@ mtype_gc(struct timer_list *t) add_timer(&map->gc); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct mtype *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, @@ -301,6 +308,7 @@ static const struct ip_set_type_variant mtype = { .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 4c133e06be1de..3184cc6be4c9d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1154,6 +1154,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, return ret; cleanup: + set->variant->cancel_gc(set); set->variant->destroy(set); put_out: module_put(set->type->me); @@ -1182,6 +1183,14 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } +static void +ip_set_destroy_set_rcu(struct rcu_head *head) +{ + struct ip_set *set = container_of(head, struct ip_set, rcu); + + ip_set_destroy_set(set); +} + static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const attr[]) { @@ -1193,8 +1202,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); /* Commands are serialized and references are * protected by the ip_set_ref_lock. @@ -1206,8 +1213,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, * counter, so if it's already zero, we can proceed * without holding the lock. */ - read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { + /* Must wait for flush to be really finished in list:set */ + rcu_barrier(); + read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); if (s && (s->ref || s->ref_netlink)) { @@ -1221,6 +1230,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, s = ip_set(inst, i); if (s) { ip_set(inst, i) = NULL; + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); ip_set_destroy_set(s); } } @@ -1228,6 +1239,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, inst->is_destroyed = false; } else { u32 flags = flag_exist(info->nlh); + u16 features = 0; + + read_lock_bh(&ip_set_ref_lock); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1238,10 +1252,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, ret = -IPSET_ERR_BUSY; goto out; } + features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - - ip_set_destroy_set(s); + if (features & IPSET_TYPE_NAME) { + /* Must wait for flush to be really finished */ + rcu_barrier(); + } + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); + call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; out: @@ -1394,9 +1414,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); - /* Make sure all readers of the old set pointers are completed. */ - synchronize_rcu(); - return 0; } @@ -2362,6 +2379,7 @@ ip_set_net_exit(struct net *net) set = ip_set(inst, i); if (set) { ip_set(inst, i) = NULL; + set->variant->cancel_gc(set); ip_set_destroy_set(set); } } @@ -2409,8 +2427,11 @@ ip_set_fini(void) { nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - unregister_pernet_subsys(&ip_set_net_ops); + + /* Wait for call_rcu() in destroy */ + rcu_barrier(); + pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7c2399541771f..20aad81fcad7e 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -221,6 +221,7 @@ static const union nf_inet_addr zeromask = {}; #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init +#undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match @@ -265,6 +266,7 @@ static const union nf_inet_addr zeromask = {}; #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) @@ -429,7 +431,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference(hbucket(t, i)); + n = (__force struct hbucket *)hbucket(t, i); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -449,10 +451,7 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - if (SET_WITH_TIMEOUT(set)) - cancel_delayed_work_sync(&h->gc.dwork); - - mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + mtype_ahash_destroy(set, (__force struct htable *)h->table, true); list_for_each_safe(l, lt, &h->ad) { list_del(l); kfree(l); @@ -598,6 +597,15 @@ mtype_gc_init(struct htable_gc *gc) queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct htype *h = set->data; + + if (SET_WITH_TIMEOUT(set)) + cancel_delayed_work_sync(&h->gc.dwork); +} + static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); @@ -1440,6 +1448,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, .region_lock = true, }; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index e162636525cfb..6c3f28bc59b32 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) struct list_set *map = set->data; struct set_elem *e, *n; - if (SET_WITH_TIMEOUT(set)) - timer_shutdown_sync(&map->gc); - list_for_each_entry_safe(e, n, &map->members, list) { list_del(&e->list); ip_set_put_byindex(map->net, e->id); @@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } +static void +list_set_cancel_gc(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + timer_shutdown_sync(&map->gc); +} + static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, @@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, + .cancel_gc = list_set_cancel_gc, }; static void diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 90e275bb3e5d7..a3a8ddca99189 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -57,7 +57,7 @@ /* Jump to label if @reg is zero */ #define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label) \ - asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ + asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ "je %l[" #label "]" : : : : label) /* Store 256 bits from YMM register into memory. Contrary to bucket load diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6c9592d051206..12684d835cb53 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1208,6 +1208,10 @@ void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); nci_hci_deallocate(ndev); + + /* drop partial rx data packet if present */ + if (ndev->rx_data_reassembly) + kfree_skb(ndev->rx_data_reassembly); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 88965e2068ac6..ebc5728aab4ea 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,7 @@ struct ovs_len_tbl { #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 +#define OVS_COPY_ACTIONS_MAX_DEPTH 16 static bool actions_may_change_flow(const struct nlattr *actions) { @@ -2545,13 +2546,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log); + u32 mpls_label_count, bool log, + u32 depth); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; @@ -2602,7 +2605,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return err; err = __ovs_nla_copy_actions(net, actions, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2617,7 +2621,8 @@ static int validate_and_copy_dec_ttl(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; int start, action_start, err, rem; @@ -2660,7 +2665,8 @@ static int validate_and_copy_dec_ttl(struct net *net, return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, - vlan_tci, mpls_label_count, log); + vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2674,7 +2680,8 @@ static int validate_and_copy_clone(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { int start, err; u32 exec; @@ -2694,7 +2701,8 @@ static int validate_and_copy_clone(struct net *net, return err; err = __ovs_nla_copy_actions(net, attr, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3063,7 +3071,7 @@ static int validate_and_copy_check_pkt_len(struct net *net, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, - bool log, bool last) + bool log, bool last, u32 depth) { const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; @@ -3111,7 +3119,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3124,7 +3133,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3152,12 +3162,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; + if (depth > OVS_COPY_ACTIONS_MAX_DEPTH) + return -EOVERFLOW; + nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { @@ -3355,7 +3369,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_sample(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3426,7 +3440,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_clone(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3440,7 +3454,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, + depth); if (err) return err; skip_copy = true; @@ -3450,7 +3465,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_DEC_TTL: err = validate_and_copy_dec_ttl(net, a, key, sfa, eth_type, vlan_tci, - mpls_label_count, log); + mpls_label_count, log, + depth); if (err) return err; skip_copy = true; @@ -3495,7 +3511,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, - key->eth.vlan.tci, mpls_label_count, log); + key->eth.vlan.tci, mpls_label_count, log, + 0); if (err) ovs_nla_free_flow_actions(*sfa); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index dba523cdc73da..e1f8ff6e9a739 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -63,6 +63,7 @@ struct tls_decrypt_ctx { u8 iv[MAX_IV_SIZE]; u8 aad[TLS_MAX_AAD_SIZE]; u8 tail; + bool free_sgout; struct scatterlist sg[]; }; @@ -187,7 +188,6 @@ static void tls_decrypt_done(void *data, int err) struct aead_request *aead_req = data; struct crypto_aead *aead = crypto_aead_reqtfm(aead_req); struct scatterlist *sgout = aead_req->dst; - struct scatterlist *sgin = aead_req->src; struct tls_sw_context_rx *ctx; struct tls_decrypt_ctx *dctx; struct tls_context *tls_ctx; @@ -196,6 +196,17 @@ static void tls_decrypt_done(void *data, int err) struct sock *sk; int aead_size; + /* If requests get too backlogged crypto API returns -EBUSY and calls + * ->complete(-EINPROGRESS) immediately followed by ->complete(0) + * to make waiting for backlog to flush with crypto_wait_req() easier. + * First wait converts -EBUSY -> -EINPROGRESS, and the second one + * -EINPROGRESS -> 0. + * We have a single struct crypto_async_request per direction, this + * scheme doesn't help us, so just ignore the first ->complete(). + */ + if (err == -EINPROGRESS) + return; + aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead); aead_size = ALIGN(aead_size, __alignof__(*dctx)); dctx = (void *)((u8 *)aead_req + aead_size); @@ -213,7 +224,7 @@ static void tls_decrypt_done(void *data, int err) } /* Free the destination pages if skb was not decrypted inplace */ - if (sgout != sgin) { + if (dctx->free_sgout) { /* Skip the first S/G entry as it points to AAD */ for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { if (!sg) @@ -224,10 +235,17 @@ static void tls_decrypt_done(void *data, int err) kfree(aead_req); - spin_lock_bh(&ctx->decrypt_compl_lock); - if (!atomic_dec_return(&ctx->decrypt_pending)) + if (atomic_dec_and_test(&ctx->decrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->decrypt_compl_lock); +} + +static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx) +{ + if (!atomic_dec_and_test(&ctx->decrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->decrypt_pending); + + return ctx->async_wait.err; } static int tls_do_decryption(struct sock *sk, @@ -253,6 +271,7 @@ static int tls_do_decryption(struct sock *sk, aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_decrypt_done, aead_req); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1); atomic_inc(&ctx->decrypt_pending); } else { aead_request_set_callback(aead_req, @@ -261,6 +280,10 @@ static int tls_do_decryption(struct sock *sk, } ret = crypto_aead_decrypt(aead_req); + if (ret == -EBUSY) { + ret = tls_decrypt_async_wait(ctx); + ret = ret ?: -EINPROGRESS; + } if (ret == -EINPROGRESS) { if (darg->async) return 0; @@ -439,9 +462,10 @@ static void tls_encrypt_done(void *data, int err) struct tls_rec *rec = data; struct scatterlist *sge; struct sk_msg *msg_en; - bool ready = false; struct sock *sk; - int pending; + + if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */ + return; msg_en = &rec->msg_encrypted; @@ -476,23 +500,25 @@ static void tls_encrypt_done(void *data, int err) /* If received record is at head of tx_list, schedule tx */ first_rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); - if (rec == first_rec) - ready = true; + if (rec == first_rec) { + /* Schedule the transmission */ + if (!test_and_set_bit(BIT_TX_SCHEDULED, + &ctx->tx_bitmask)) + schedule_delayed_work(&ctx->tx_work.work, 1); + } } - spin_lock_bh(&ctx->encrypt_compl_lock); - pending = atomic_dec_return(&ctx->encrypt_pending); - - if (!pending && ctx->async_notify) + if (atomic_dec_and_test(&ctx->encrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->encrypt_compl_lock); +} - if (!ready) - return; +static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx) +{ + if (!atomic_dec_and_test(&ctx->encrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->encrypt_pending); - /* Schedule the transmission */ - if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) - schedule_delayed_work(&ctx->tx_work.work, 1); + return ctx->async_wait.err; } static int tls_do_encryption(struct sock *sk, @@ -541,9 +567,14 @@ static int tls_do_encryption(struct sock *sk, /* Add the record in tx_list */ list_add_tail((struct list_head *)&rec->list, &ctx->tx_list); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1); atomic_inc(&ctx->encrypt_pending); rc = crypto_aead_encrypt(aead_req); + if (rc == -EBUSY) { + rc = tls_encrypt_async_wait(ctx); + rc = rc ?: -EINPROGRESS; + } if (!rc || rc != -EINPROGRESS) { atomic_dec(&ctx->encrypt_pending); sge->offset -= prot->prepend_size; @@ -984,7 +1015,6 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, int num_zc = 0; int orig_size; int ret = 0; - int pending; if (!eor && (msg->msg_flags & MSG_EOR)) return -EINVAL; @@ -1163,24 +1193,12 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, if (!num_async) { goto send_end; } else if (num_zc) { - /* Wait for pending encryptions to get completed */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no - * pending encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); + int err; - if (ctx->async_wait.err) { - ret = ctx->async_wait.err; + /* Wait for pending encryptions to get completed */ + err = tls_encrypt_async_wait(ctx); + if (err) { + ret = err; copied = 0; } } @@ -1229,7 +1247,6 @@ void tls_sw_splice_eof(struct socket *sock) ssize_t copied = 0; bool retrying = false; int ret = 0; - int pending; if (!ctx->open_rec) return; @@ -1264,22 +1281,7 @@ void tls_sw_splice_eof(struct socket *sock) } /* Wait for pending encryptions to get completed */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no pending - * encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); - - if (ctx->async_wait.err) + if (tls_encrypt_async_wait(ctx)) goto unlock; /* Transmit if any encryptions have completed */ @@ -1581,6 +1583,7 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov, } else if (out_sg) { memcpy(sgout, out_sg, n_sgout * sizeof(*sgout)); } + dctx->free_sgout = !!pages; /* Prepare and submit AEAD request */ err = tls_do_decryption(sk, sgin, sgout, dctx->iv, @@ -2109,16 +2112,10 @@ int tls_sw_recvmsg(struct sock *sk, recv_end: if (async) { - int ret, pending; + int ret; /* Wait for all previously submitted records to be decrypted */ - spin_lock_bh(&ctx->decrypt_compl_lock); - reinit_completion(&ctx->async_wait.completion); - pending = atomic_read(&ctx->decrypt_pending); - spin_unlock_bh(&ctx->decrypt_compl_lock); - ret = 0; - if (pending) - ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + ret = tls_decrypt_async_wait(ctx); __skb_queue_purge(&ctx->async_hold); if (ret) { @@ -2135,7 +2132,6 @@ int tls_sw_recvmsg(struct sock *sk, else err = process_rx_list(ctx, msg, &control, 0, async_copy_bytes, is_peek); - decrypted += max(err, 0); } copied += decrypted; @@ -2435,16 +2431,9 @@ void tls_sw_release_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; - int pending; /* Wait for any pending async encryptions to complete */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + tls_encrypt_async_wait(ctx); tls_tx_records(sk, -1); @@ -2597,6 +2586,48 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx) tls_ctx->prot_info.version != TLS_1_3_VERSION; } +static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct sock *sk) +{ + struct tls_sw_context_tx *sw_ctx_tx; + + if (!ctx->priv_ctx_tx) { + sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); + if (!sw_ctx_tx) + return NULL; + } else { + sw_ctx_tx = ctx->priv_ctx_tx; + } + + crypto_init_wait(&sw_ctx_tx->async_wait); + atomic_set(&sw_ctx_tx->encrypt_pending, 1); + INIT_LIST_HEAD(&sw_ctx_tx->tx_list); + INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); + sw_ctx_tx->tx_work.sk = sk; + + return sw_ctx_tx; +} + +static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx) +{ + struct tls_sw_context_rx *sw_ctx_rx; + + if (!ctx->priv_ctx_rx) { + sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); + if (!sw_ctx_rx) + return NULL; + } else { + sw_ctx_rx = ctx->priv_ctx_rx; + } + + crypto_init_wait(&sw_ctx_rx->async_wait); + atomic_set(&sw_ctx_rx->decrypt_pending, 1); + init_waitqueue_head(&sw_ctx_rx->wq); + skb_queue_head_init(&sw_ctx_rx->rx_list); + skb_queue_head_init(&sw_ctx_rx->async_hold); + + return sw_ctx_rx; +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2618,48 +2649,22 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) } if (tx) { - if (!ctx->priv_ctx_tx) { - sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); - if (!sw_ctx_tx) { - rc = -ENOMEM; - goto out; - } - ctx->priv_ctx_tx = sw_ctx_tx; - } else { - sw_ctx_tx = - (struct tls_sw_context_tx *)ctx->priv_ctx_tx; - } - } else { - if (!ctx->priv_ctx_rx) { - sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); - if (!sw_ctx_rx) { - rc = -ENOMEM; - goto out; - } - ctx->priv_ctx_rx = sw_ctx_rx; - } else { - sw_ctx_rx = - (struct tls_sw_context_rx *)ctx->priv_ctx_rx; - } - } + ctx->priv_ctx_tx = init_ctx_tx(ctx, sk); + if (!ctx->priv_ctx_tx) + return -ENOMEM; - if (tx) { - crypto_init_wait(&sw_ctx_tx->async_wait); - spin_lock_init(&sw_ctx_tx->encrypt_compl_lock); + sw_ctx_tx = ctx->priv_ctx_tx; crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; - INIT_LIST_HEAD(&sw_ctx_tx->tx_list); - INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); - sw_ctx_tx->tx_work.sk = sk; } else { - crypto_init_wait(&sw_ctx_rx->async_wait); - spin_lock_init(&sw_ctx_rx->decrypt_compl_lock); - init_waitqueue_head(&sw_ctx_rx->wq); + ctx->priv_ctx_rx = init_ctx_rx(ctx); + if (!ctx->priv_ctx_rx) + return -ENOMEM; + + sw_ctx_rx = ctx->priv_ctx_rx; crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; - skb_queue_head_init(&sw_ctx_rx->rx_list); - skb_queue_head_init(&sw_ctx_rx->async_hold); aead = &sw_ctx_rx->aead_recv; } diff --git a/net/wireless/core.c b/net/wireless/core.c index f6ada0a729778..ff743e1f2e2cb 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1675,6 +1675,7 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy, unsigned long delay) { if (!delay) { + del_timer(&dwork->timer); wiphy_work_queue(wiphy, &dwork->work); return; } diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h index 7048bb3594d65..634e81d83efd9 100644 --- a/samples/bpf/asm_goto_workaround.h +++ b/samples/bpf/asm_goto_workaround.h @@ -4,14 +4,14 @@ #define __ASM_GOTO_WORKAROUND_H /* - * This will bring in asm_volatile_goto and asm_inline macro definitions + * This will bring in asm_goto_output and asm_inline macro definitions * if enabled by compiler and config options. */ #include -#ifdef asm_volatile_goto -#undef asm_volatile_goto -#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto") +#ifdef asm_goto_output +#undef asm_goto_output +#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output") #endif /* diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index a432b171be826..7862a81017477 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -135,8 +135,13 @@ gen_btf() ${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \ --strip-all ${1} ${2} 2>/dev/null # Change e_type to ET_REL so that it can be used to link final vmlinux. - # Unlike GNU ld, lld does not allow an ET_EXEC input. - printf '\1' | dd of=${2} conv=notrunc bs=1 seek=16 status=none + # GNU ld 2.35+ and lld do not allow an ET_EXEC input. + if is_enabled CONFIG_CPU_BIG_ENDIAN; then + et_rel='\0\1' + else + et_rel='\1\0' + fi + printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none } # Create ${2} .S file with all symbols from the ${1} object file diff --git a/scripts/mksysmap b/scripts/mksysmap index 9ba1c9da0a40f..57ff5656d566f 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -48,17 +48,8 @@ ${NM} -n ${1} | sed >${2} -e " / __kvm_nvhe_\\$/d / __kvm_nvhe_\.L/d -# arm64 lld -/ __AArch64ADRPThunk_/d - -# arm lld -/ __ARMV5PILongThunk_/d -/ __ARMV7PILongThunk_/d -/ __ThumbV7PILongThunk_/d - -# mips lld -/ __LA25Thunk_/d -/ __microLA25Thunk_/d +# lld arm/aarch64/mips thunks +/ __[[:alnum:]]*Thunk_/d # CFI type identifiers / __kcfi_typeid_/d diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index ac4ef3e206bbd..5191fdbd3fa23 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -798,7 +798,7 @@ static void check_section(const char *modname, struct elf_info *elf, #define ALL_INIT_TEXT_SECTIONS \ ".init.text", ".meminit.text" #define ALL_EXIT_TEXT_SECTIONS \ - ".exit.text", ".memexit.text" + ".exit.text" #define ALL_PCI_INIT_SECTIONS \ ".pci_fixup_early", ".pci_fixup_header", ".pci_fixup_final", \ @@ -806,14 +806,14 @@ static void check_section(const char *modname, struct elf_info *elf, ".pci_fixup_resume_early", ".pci_fixup_suspend" #define ALL_XXXINIT_SECTIONS MEM_INIT_SECTIONS -#define ALL_XXXEXIT_SECTIONS MEM_EXIT_SECTIONS #define ALL_INIT_SECTIONS INIT_SECTIONS, ALL_XXXINIT_SECTIONS -#define ALL_EXIT_SECTIONS EXIT_SECTIONS, ALL_XXXEXIT_SECTIONS +#define ALL_EXIT_SECTIONS EXIT_SECTIONS #define DATA_SECTIONS ".data", ".data.rel" #define TEXT_SECTIONS ".text", ".text.*", ".sched.text", \ - ".kprobes.text", ".cpuidle.text", ".noinstr.text" + ".kprobes.text", ".cpuidle.text", ".noinstr.text", \ + ".ltext", ".ltext.*" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ ".fixup", ".entry.text", ".exception.text", \ ".coldtext", ".softirqentry.text" @@ -822,7 +822,6 @@ static void check_section(const char *modname, struct elf_info *elf, #define MEM_INIT_SECTIONS ".meminit.*" #define EXIT_SECTIONS ".exit.*" -#define MEM_EXIT_SECTIONS ".memexit.*" #define ALL_TEXT_SECTIONS ALL_INIT_TEXT_SECTIONS, ALL_EXIT_TEXT_SECTIONS, \ TEXT_SECTIONS, OTHER_TEXT_SECTIONS @@ -832,7 +831,6 @@ enum mismatch { DATA_TO_ANY_INIT, TEXTDATA_TO_ANY_EXIT, XXXINIT_TO_SOME_INIT, - XXXEXIT_TO_SOME_EXIT, ANY_INIT_TO_ANY_EXIT, ANY_EXIT_TO_ANY_INIT, EXTABLE_TO_NON_TEXT, @@ -883,12 +881,6 @@ static const struct sectioncheck sectioncheck[] = { .bad_tosec = { INIT_SECTIONS, NULL }, .mismatch = XXXINIT_TO_SOME_INIT, }, -/* Do not reference exit code/data from memexit code/data */ -{ - .fromsec = { ALL_XXXEXIT_SECTIONS, NULL }, - .bad_tosec = { EXIT_SECTIONS, NULL }, - .mismatch = XXXEXIT_TO_SOME_EXIT, -}, /* Do not use exit code/data from init code */ { .fromsec = { ALL_INIT_SECTIONS, NULL }, @@ -1017,7 +1009,7 @@ static int secref_whitelist(const char *fromsec, const char *fromsym, /* symbols in data sections that may refer to meminit sections */ if (match(fromsec, PATTERNS(DATA_SECTIONS)) && - match(tosec, PATTERNS(ALL_XXXINIT_SECTIONS, ALL_XXXEXIT_SECTIONS)) && + match(tosec, PATTERNS(ALL_XXXINIT_SECTIONS)) && match(fromsym, PATTERNS("*driver"))) return 0; diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c index 31066bfdba04e..dc4878502276c 100644 --- a/scripts/mod/sumversion.c +++ b/scripts/mod/sumversion.c @@ -326,7 +326,12 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md) /* Sum all files in the same dir or subdirs. */ while ((line = get_line(&pos))) { - char* p = line; + char* p; + + /* trim the leading spaces away */ + while (isspace(*line)) + line++; + p = line; if (strncmp(line, "source_", sizeof("source_")-1) == 0) { p = strrchr(line, ' '); diff --git a/security/security.c b/security/security.c index 840a3d58a2902..407b51719f797 100644 --- a/security/security.c +++ b/security/security.c @@ -4030,7 +4030,19 @@ EXPORT_SYMBOL(security_inode_setsecctx); */ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { - return call_int_hook(inode_getsecctx, -EOPNOTSUPP, inode, ctx, ctxlen); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) { + rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen); + if (rc != LSM_RET_DEFAULT(inode_getsecctx)) + return rc; + } + + return LSM_RET_DEFAULT(inode_getsecctx); } EXPORT_SYMBOL(security_inode_getsecctx); @@ -4387,8 +4399,20 @@ EXPORT_SYMBOL(security_sock_rcv_skb); int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { - return call_int_hook(socket_getpeersec_stream, -ENOPROTOOPT, sock, - optval, optlen, len); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_stream, + list) { + rc = hp->hook.socket_getpeersec_stream(sock, optval, optlen, + len); + if (rc != LSM_RET_DEFAULT(socket_getpeersec_stream)) + return rc; + } + return LSM_RET_DEFAULT(socket_getpeersec_stream); } /** @@ -4408,8 +4432,19 @@ int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { - return call_int_hook(socket_getpeersec_dgram, -ENOPROTOOPT, sock, - skb, secid); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_dgram, + list) { + rc = hp->hook.socket_getpeersec_dgram(sock, skb, secid); + if (rc != LSM_RET_DEFAULT(socket_getpeersec_dgram)) + return rc; + } + return LSM_RET_DEFAULT(socket_getpeersec_dgram); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig index 0d7502d6e0604..21046f72cdca9 100644 --- a/sound/pci/hda/Kconfig +++ b/sound/pci/hda/Kconfig @@ -140,7 +140,7 @@ config SND_HDA_SCODEC_CS35L56_I2C depends on I2C depends on ACPI || COMPILE_TEST depends on SND_SOC - select CS_DSP + select FW_CS_DSP select SND_HDA_GENERIC select SND_SOC_CS35L56_SHARED select SND_HDA_SCODEC_CS35L56 @@ -154,7 +154,7 @@ config SND_HDA_SCODEC_CS35L56_SPI depends on SPI_MASTER depends on ACPI || COMPILE_TEST depends on SND_SOC - select CS_DSP + select FW_CS_DSP select SND_HDA_GENERIC select SND_SOC_CS35L56_SHARED select SND_HDA_SCODEC_CS35L56 diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index e8819e8a98763..e8209178d87bb 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -344,6 +344,7 @@ enum { CXT_FIXUP_HP_ZBOOK_MUTE_LED, CXT_FIXUP_HEADSET_MIC, CXT_FIXUP_HP_MIC_NO_PRESENCE, + CXT_PINCFG_SWS_JS201D, }; /* for hda_fixup_thinkpad_acpi() */ @@ -841,6 +842,17 @@ static const struct hda_pintbl cxt_pincfg_lemote[] = { {} }; +/* SuoWoSi/South-holding JS201D with sn6140 */ +static const struct hda_pintbl cxt_pincfg_sws_js201d[] = { + { 0x16, 0x03211040 }, /* hp out */ + { 0x17, 0x91170110 }, /* SPK/Class_D */ + { 0x18, 0x95a70130 }, /* Internal mic */ + { 0x19, 0x03a11020 }, /* Headset Mic */ + { 0x1a, 0x40f001f0 }, /* Not used */ + { 0x21, 0x40f001f0 }, /* Not used */ + {} +}; + static const struct hda_fixup cxt_fixups[] = { [CXT_PINCFG_LENOVO_X200] = { .type = HDA_FIXUP_PINS, @@ -996,6 +1008,10 @@ static const struct hda_fixup cxt_fixups[] = { .chained = true, .chain_id = CXT_FIXUP_HEADSET_MIC, }, + [CXT_PINCFG_SWS_JS201D] = { + .type = HDA_FIXUP_PINS, + .v.pins = cxt_pincfg_sws_js201d, + }, }; static const struct snd_pci_quirk cxt5045_fixups[] = { @@ -1069,6 +1085,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8458, "HP Z2 G4 mini premium", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), + SND_PCI_QUIRK(0x14f1, 0x0265, "SWS JS201D", CXT_PINCFG_SWS_JS201D), SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410), @@ -1109,6 +1126,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = { { .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" }, { .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" }, { .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" }, + { .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" }, {} }; diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 627899959ffe8..e41316e2e9833 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -1371,6 +1371,7 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac spec->scodecs[CS8409_CODEC1] = &dolphin_cs42l42_1; spec->scodecs[CS8409_CODEC1]->codec = codec; spec->num_scodecs = 2; + spec->gen.suppress_vmaster = 1; codec->patch_ops = cs8409_dolphin_patch_ops; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 375569d0864b3..0cb8ccdabc095 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -438,6 +438,10 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000); fallthrough; case 0x10ec0215: + case 0x10ec0285: + case 0x10ec0289: + alc_update_coef_idx(codec, 0x36, 1<<13, 0); + fallthrough; case 0x10ec0230: case 0x10ec0233: case 0x10ec0235: @@ -451,9 +455,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0283: case 0x10ec0286: case 0x10ec0288: - case 0x10ec0285: case 0x10ec0298: - case 0x10ec0289: case 0x10ec0300: alc_update_coef_idx(codec, 0x10, 1<<9, 0); break; @@ -9479,7 +9481,7 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, .chained = true, - .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + .chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, }, [ALC287_FIXUP_TAS2781_I2C] = { .type = HDA_FIXUP_FUNC, @@ -9500,6 +9502,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC287_FIXUP_THINKPAD_I2S_SPK] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_bind_dacs, + .chained = true, + .chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, }, [ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD] = { .type = HDA_FIXUP_FUNC, @@ -9549,6 +9553,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1269, "Acer SWIFT SF314-54", ALC256_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x126a, "Acer Swift SF114-32", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), @@ -9626,6 +9631,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0beb, "Dell XPS 15 9530 (2023)", ALC289_FIXUP_DELL_CS35L41_SPI_2), SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0c0b, "Dell Oasis 14 RPL-P", ALC289_FIXUP_RTK_AMP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x0c0d, "Dell Oasis", ALC289_FIXUP_RTK_AMP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x0c0e, "Dell Oasis 16", ALC289_FIXUP_RTK_AMP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), @@ -9745,6 +9753,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8786, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8787, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e7, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -9814,6 +9823,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9821,6 +9831,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b45, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b46, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b59, "HP Elite mt645 G7 Mobile Thin Client U89", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9850,6 +9861,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8ca1, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -10200,6 +10213,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), + SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 731664fc8b217..26928d5ae5f70 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -627,7 +627,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, strscpy(comps->name, dev_name(dev), sizeof(comps->name)); - ret = tascodec_init(tas_hda->priv, codec, tasdev_fw_ready); + ret = tascodec_init(tas_hda->priv, codec, THIS_MODULE, tasdev_fw_ready); if (!ret) comps->playback_hook = tas2781_hda_playback_hook; diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index d83cb6e4c62ae..80ad60d485ea0 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -248,6 +248,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82YM"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83AS"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -297,6 +304,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 B7ED"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VF"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index edcb85bd8ea7f..ea08b7cfc31da 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -3314,6 +3314,7 @@ static void rt5645_jack_detect_work(struct work_struct *work) report, SND_JACK_HEADPHONE); snd_soc_jack_report(rt5645->mic_jack, report, SND_JACK_MICROPHONE); + mutex_unlock(&rt5645->jd_mutex); return; case 4: val = snd_soc_component_read(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020; diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c index 00e35169ae495..add16302f711e 100644 --- a/sound/soc/codecs/tas2781-comlib.c +++ b/sound/soc/codecs/tas2781-comlib.c @@ -267,6 +267,7 @@ void tas2781_reset(struct tasdevice_priv *tas_dev) EXPORT_SYMBOL_GPL(tas2781_reset); int tascodec_init(struct tasdevice_priv *tas_priv, void *codec, + struct module *module, void (*cont)(const struct firmware *fw, void *context)) { int ret = 0; @@ -280,7 +281,7 @@ int tascodec_init(struct tasdevice_priv *tas_priv, void *codec, tas_priv->dev_name, tas_priv->ndev); crc8_populate_msb(tas_priv->crc8_lkp_tbl, TASDEVICE_CRC8_POLYNOMIAL); tas_priv->codec = codec; - ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT, + ret = request_firmware_nowait(module, FW_ACTION_UEVENT, tas_priv->rca_binaryname, tas_priv->dev, GFP_KERNEL, tas_priv, cont); if (ret) diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 917b1c15f71d4..2f7f8b18c36fa 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -564,7 +564,7 @@ static int tasdevice_codec_probe(struct snd_soc_component *codec) { struct tasdevice_priv *tas_priv = snd_soc_component_get_drvdata(codec); - return tascodec_init(tas_priv, codec, tasdevice_fw_ready); + return tascodec_init(tas_priv, codec, THIS_MODULE, tasdevice_fw_ready); } static void tasdevice_deinit(void *context) diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index 23d06338f716f..7df1719e07239 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -3589,7 +3589,7 @@ static int wcd938x_probe(struct platform_device *pdev) ret = wcd938x_populate_dt_data(wcd938x, dev); if (ret) { dev_err(dev, "%s: Fail to obtain platform data\n", __func__); - return -EINVAL; + return ret; } ret = wcd938x_add_slave_components(wcd938x, dev, &match); diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c index 2c7a5e7a364cf..d96555438c6bf 100644 --- a/sound/soc/sof/ipc3-topology.c +++ b/sound/soc/sof/ipc3-topology.c @@ -2309,27 +2309,16 @@ static int sof_tear_down_left_over_pipelines(struct snd_sof_dev *sdev) return 0; } -/* - * For older firmware, this function doesn't free widgets for static pipelines during suspend. - * It only resets use_count for all widgets. - */ -static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verify) +static int sof_ipc3_free_widgets_in_list(struct snd_sof_dev *sdev, bool include_scheduler, + bool *dyn_widgets, bool verify) { struct sof_ipc_fw_version *v = &sdev->fw_ready.version; struct snd_sof_widget *swidget; - struct snd_sof_route *sroute; - bool dyn_widgets = false; int ret; - /* - * This function is called during suspend and for one-time topology verification during - * first boot. In both cases, there is no need to protect swidget->use_count and - * sroute->setup because during suspend all running streams are suspended and during - * topology loading the sound card unavailable to open PCMs. - */ list_for_each_entry(swidget, &sdev->widget_list, list) { if (swidget->dynamic_pipeline_widget) { - dyn_widgets = true; + *dyn_widgets = true; continue; } @@ -2344,11 +2333,49 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif continue; } + if (include_scheduler && swidget->id != snd_soc_dapm_scheduler) + continue; + + if (!include_scheduler && swidget->id == snd_soc_dapm_scheduler) + continue; + ret = sof_widget_free(sdev, swidget); if (ret < 0) return ret; } + return 0; +} + +/* + * For older firmware, this function doesn't free widgets for static pipelines during suspend. + * It only resets use_count for all widgets. + */ +static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verify) +{ + struct sof_ipc_fw_version *v = &sdev->fw_ready.version; + struct snd_sof_widget *swidget; + struct snd_sof_route *sroute; + bool dyn_widgets = false; + int ret; + + /* + * This function is called during suspend and for one-time topology verification during + * first boot. In both cases, there is no need to protect swidget->use_count and + * sroute->setup because during suspend all running streams are suspended and during + * topology loading the sound card unavailable to open PCMs. Do not free the scheduler + * widgets yet so that the secondary cores do not get powered down before all the widgets + * associated with the scheduler are freed. + */ + ret = sof_ipc3_free_widgets_in_list(sdev, false, &dyn_widgets, verify); + if (ret < 0) + return ret; + + /* free all the scheduler widgets now */ + ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify); + if (ret < 0) + return ret; + /* * Tear down all pipelines associated with PCMs that did not get suspended * and unset the prepare flag so that they can be set up again during resume. diff --git a/sound/soc/sof/ipc3.c b/sound/soc/sof/ipc3.c index fb40378ad0840..c03dd513fbff1 100644 --- a/sound/soc/sof/ipc3.c +++ b/sound/soc/sof/ipc3.c @@ -1067,7 +1067,7 @@ static void sof_ipc3_rx_msg(struct snd_sof_dev *sdev) return; } - if (hdr.size < sizeof(hdr)) { + if (hdr.size < sizeof(hdr) || hdr.size > SOF_IPC_MSG_MAX_SIZE) { dev_err(sdev->dev, "The received message size is invalid\n"); return; } diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h index 11ff975242cac..e2ff22b379a44 100644 --- a/tools/arch/x86/include/asm/rmwcc.h +++ b/tools/arch/x86/include/asm/rmwcc.h @@ -4,7 +4,7 @@ #define __GEN_RMWcc(fullop, var, cc, ...) \ do { \ - asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \ + asm goto (fullop "; j" cc " %l[cc_label]" \ : : "m" (var), ## __VA_ARGS__ \ : "memory" : cc_label); \ return 0; \ diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index 1bdd834bdd571..d09f9dc172a48 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -36,8 +36,8 @@ #include #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +#ifndef asm_goto_output +#define asm_goto_output(x...) asm goto(x) #endif #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 936f3a8d1b83e..e96fababd3f06 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -376,7 +376,10 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, cleared = kvm_vm_reset_dirty_ring(vcpu->vm); - /* Cleared pages should be the same as collected */ + /* + * Cleared pages should be the same as collected, as KVM is supposed to + * clear only the entries that have been harvested. + */ TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch " "with collected (%u)", cleared, count); @@ -415,12 +418,6 @@ static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) } } -static void dirty_ring_before_vcpu_join(void) -{ - /* Kick another round of vcpu just to make sure it will quit */ - sem_post(&sem_vcpu_cont); -} - struct log_mode { const char *name; /* Return true if this mode is supported, otherwise false */ @@ -433,7 +430,6 @@ struct log_mode { uint32_t *ring_buf_idx); /* Hook to call when after each vcpu run */ void (*after_vcpu_run)(struct kvm_vcpu *vcpu, int ret, int err); - void (*before_vcpu_join) (void); } log_modes[LOG_MODE_NUM] = { { .name = "dirty-log", @@ -452,7 +448,6 @@ struct log_mode { .supported = dirty_ring_supported, .create_vm_done = dirty_ring_create_vm_done, .collect_dirty_pages = dirty_ring_collect_dirty_pages, - .before_vcpu_join = dirty_ring_before_vcpu_join, .after_vcpu_run = dirty_ring_after_vcpu_run, }, }; @@ -513,14 +508,6 @@ static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) mode->after_vcpu_run(vcpu, ret, err); } -static void log_mode_before_vcpu_join(void) -{ - struct log_mode *mode = &log_modes[host_log_mode]; - - if (mode->before_vcpu_join) - mode->before_vcpu_join(); -} - static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -719,6 +706,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct kvm_vm *vm; unsigned long *bmap; uint32_t ring_buf_idx = 0; + int sem_val; if (!log_mode_supported()) { print_skip("Log mode '%s' not supported", @@ -788,12 +776,22 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Start the iterations */ iteration = 1; sync_global_to_guest(vm, iteration); - host_quit = false; + WRITE_ONCE(host_quit, false); host_dirty_count = 0; host_clear_count = 0; host_track_next_count = 0; WRITE_ONCE(dirty_ring_vcpu_ring_full, false); + /* + * Ensure the previous iteration didn't leave a dangling semaphore, i.e. + * that the main task and vCPU worker were synchronized and completed + * verification of all iterations. + */ + sem_getvalue(&sem_vcpu_stop, &sem_val); + TEST_ASSERT_EQ(sem_val, 0); + sem_getvalue(&sem_vcpu_cont, &sem_val); + TEST_ASSERT_EQ(sem_val, 0); + pthread_create(&vcpu_thread, NULL, vcpu_worker, vcpu); while (iteration < p->iterations) { @@ -819,15 +817,21 @@ static void run_test(enum vm_guest_mode mode, void *arg) assert(host_log_mode == LOG_MODE_DIRTY_RING || atomic_read(&vcpu_sync_stop_requested) == false); vm_dirty_log_verify(mode, bmap); - sem_post(&sem_vcpu_cont); - iteration++; + /* + * Set host_quit before sem_vcpu_cont in the final iteration to + * ensure that the vCPU worker doesn't resume the guest. As + * above, the dirty ring test may stop and wait even when not + * explicitly request to do so, i.e. would hang waiting for a + * "continue" if it's allowed to resume the guest. + */ + if (++iteration == p->iterations) + WRITE_ONCE(host_quit, true); + + sem_post(&sem_vcpu_cont); sync_global_to_guest(vm, iteration); } - /* Tell the vcpu thread to quit */ - host_quit = true; - log_mode_before_vcpu_join(); pthread_join(vcpu_thread, NULL); pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), " diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 11329e5ff945e..309ee5c72b46a 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -221,7 +221,7 @@ int main(int argc, char *argv[]) vm_vaddr_t amx_cfg, tiledata, xstate; struct ucall uc; u32 amx_offset; - int stage, ret; + int ret; /* * Note, all off-by-default features must be enabled before anything @@ -263,7 +263,7 @@ int main(int argc, char *argv[]) memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); - for (stage = 1; ; stage++) { + for (;;) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 9f28aa276c4e2..a726831b80244 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -454,7 +454,7 @@ static void guest_test_msrs_access(void) case 44: /* MSR is not available when CPUID feature bit is unset */ if (!has_invtsc) - continue; + goto next_stage; msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; msr->write = false; msr->fault_expected = true; @@ -462,7 +462,7 @@ static void guest_test_msrs_access(void) case 45: /* MSR is vailable when CPUID feature bit is set */ if (!has_invtsc) - continue; + goto next_stage; vcpu_set_cpuid_feature(vcpu, HV_ACCESS_TSC_INVARIANT); msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; msr->write = false; @@ -471,7 +471,7 @@ static void guest_test_msrs_access(void) case 46: /* Writing bits other than 0 is forbidden */ if (!has_invtsc) - continue; + goto next_stage; msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; msr->write = true; msr->write_val = 0xdeadbeef; @@ -480,7 +480,7 @@ static void guest_test_msrs_access(void) case 47: /* Setting bit 0 enables the feature */ if (!has_invtsc) - continue; + goto next_stage; msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; msr->write = true; msr->write_val = 1; @@ -513,6 +513,7 @@ static void guest_test_msrs_access(void) return; } +next_stage: stage++; kvm_vm_free(vm); } diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 251594306d409..720bafa0f87be 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -241,9 +241,11 @@ struct mnt_opt { const char *const data; }; -const struct mnt_opt mnt_tmp = { +#define MNT_TMP_DATA "size=4m,mode=700" + +static const struct mnt_opt mnt_tmp = { .type = "tmpfs", - .data = "size=4m,mode=700", + .data = MNT_TMP_DATA, }; static int mount_opt(const struct mnt_opt *const mnt, const char *const target) @@ -4523,7 +4525,10 @@ FIXTURE_VARIANT(layout3_fs) /* clang-format off */ FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) { /* clang-format on */ - .mnt = mnt_tmp, + .mnt = { + .type = "tmpfs", + .data = MNT_TMP_DATA, + }, .file_path = file1_s1d1, }; diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index 0899019a7fcb4..e14bdd4455f2d 100755 --- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Kselftest framework requirement - SKIP code is 4. diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index 380b691d3eb9f..b748c48908d9d 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -566,7 +566,7 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot, if (map_ptr_orig == MAP_FAILED) err(2, "initial mmap"); - if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE)) + if (madvise(map_ptr, len, MADV_HUGEPAGE)) err(2, "MADV_HUGEPAGE"); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 193281560b61b..86e8f2048a409 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -15,6 +15,7 @@ #include #include #include +#include "vm_util.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) @@ -58,10 +59,16 @@ int main(int argc, char **argv) { void *addr; int ret; + size_t hugepage_size; size_t length = LENGTH; int flags = FLAGS; int shift = 0; + hugepage_size = default_huge_page_size(); + /* munmap with fail if the length is not page aligned */ + if (hugepage_size > length) + length = hugepage_size; + if (argc > 1) length = atol(argv[1]) << 20; if (argc > 2) { diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh index 45cae7cab27e1..a0a75f3029043 100755 --- a/tools/testing/selftests/mm/va_high_addr_switch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh @@ -29,9 +29,15 @@ check_supported_x86_64() # See man 1 gzip under '-f'. local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;} + else {print 1}; exit}' /proc/cpuinfo 2>/dev/null) + if [[ "${pg_table_levels}" -lt 5 ]]; then echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" exit $ksft_skip + elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then + echo "$0: CPU does not have the necessary la57 flag to support page table level 5" + exit $ksft_skip fi } diff --git a/tools/testing/selftests/mm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh index 70a02301f4c27..3d2d2eb9d6fff 100755 --- a/tools/testing/selftests/mm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh index 9af9f6964808b..c62331b2e0060 100755 --- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh +++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh @@ -327,10 +327,10 @@ locked_port_mab_redirect() RET=0 check_port_mab_support || return 0 - bridge link set dev $swp1 learning on locked on mab on tc qdisc add dev $swp1 clsact tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \ action mirred egress redirect dev $swp2 + bridge link set dev $swp1 learning on locked on mab on ping_do $h1 192.0.2.2 check_err $? "Ping did not work with redirection" @@ -349,8 +349,8 @@ locked_port_mab_redirect() check_err $? "Locked entry not created after deleting filter" bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master - tc qdisc del dev $swp1 clsact bridge link set dev $swp1 learning off locked off mab off + tc qdisc del dev $swp1 clsact log_test "Locked port MAB redirect" } diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index d0c6c499d5dab..a3678dfe5848a 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -145,14 +145,14 @@ cfg_test_host_common() # Check basic add, replace and delete behavior. bridge mdb add dev br0 port br0 grp $grp $state vid 10 - bridge mdb show dev br0 vid 10 | grep -q "$grp" + bridge mdb get dev br0 grp $grp vid 10 &> /dev/null check_err $? "Failed to add $name host entry" bridge mdb replace dev br0 port br0 grp $grp $state vid 10 &> /dev/null check_fail $? "Managed to replace $name host entry" bridge mdb del dev br0 port br0 grp $grp $state vid 10 - bridge mdb show dev br0 vid 10 | grep -q "$grp" + bridge mdb get dev br0 grp $grp vid 10 &> /dev/null check_fail $? "Failed to delete $name host entry" # Check error cases. @@ -200,7 +200,7 @@ cfg_test_port_common() # Check basic add, replace and delete behavior. bridge mdb add dev br0 port $swp1 $grp_key permanent vid 10 - bridge mdb show dev br0 vid 10 | grep -q "$grp_key" + bridge mdb get dev br0 $grp_key vid 10 &> /dev/null check_err $? "Failed to add $name entry" bridge mdb replace dev br0 port $swp1 $grp_key permanent vid 10 \ @@ -208,31 +208,31 @@ cfg_test_port_common() check_err $? "Failed to replace $name entry" bridge mdb del dev br0 port $swp1 $grp_key permanent vid 10 - bridge mdb show dev br0 vid 10 | grep -q "$grp_key" + bridge mdb get dev br0 $grp_key vid 10 &> /dev/null check_fail $? "Failed to delete $name entry" # Check default protocol and replacement. bridge mdb add dev br0 port $swp1 $grp_key permanent vid 10 - bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | grep -q "static" + bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "static" check_err $? "$name entry not added with default \"static\" protocol" bridge mdb replace dev br0 port $swp1 $grp_key permanent vid 10 \ proto 123 - bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | grep -q "123" + bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "123" check_err $? "Failed to replace protocol of $name entry" bridge mdb del dev br0 port $swp1 $grp_key permanent vid 10 # Check behavior when VLAN is not specified. bridge mdb add dev br0 port $swp1 $grp_key permanent - bridge mdb show dev br0 vid 10 | grep -q "$grp_key" + bridge mdb get dev br0 $grp_key vid 10 &> /dev/null check_err $? "$name entry with VLAN 10 not added when VLAN was not specified" - bridge mdb show dev br0 vid 20 | grep -q "$grp_key" + bridge mdb get dev br0 $grp_key vid 20 &> /dev/null check_err $? "$name entry with VLAN 20 not added when VLAN was not specified" bridge mdb del dev br0 port $swp1 $grp_key permanent - bridge mdb show dev br0 vid 10 | grep -q "$grp_key" + bridge mdb get dev br0 $grp_key vid 10 &> /dev/null check_fail $? "$name entry with VLAN 10 not deleted when VLAN was not specified" - bridge mdb show dev br0 vid 20 | grep -q "$grp_key" + bridge mdb get dev br0 $grp_key vid 20 &> /dev/null check_fail $? "$name entry with VLAN 20 not deleted when VLAN was not specified" # Check behavior when bridge port is down. @@ -298,21 +298,21 @@ __cfg_test_port_ip_star_g() RET=0 bridge mdb add dev br0 port $swp1 grp $grp vid 10 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "exclude" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "exclude" check_err $? "Default filter mode is not \"exclude\"" bridge mdb del dev br0 port $swp1 grp $grp vid 10 # Check basic add and delete behavior. bridge mdb add dev br0 port $swp1 grp $grp vid 10 filter_mode exclude \ source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q -v "src" + bridge -d mdb get dev br0 grp $grp vid 10 &> /dev/null check_err $? "(*, G) entry not created" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src1" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 &> /dev/null check_err $? "(S, G) entry not created" bridge mdb del dev br0 port $swp1 grp $grp vid 10 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q -v "src" + bridge -d mdb get dev br0 grp $grp vid 10 &> /dev/null check_fail $? "(*, G) entry not deleted" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src1" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 &> /dev/null check_fail $? "(S, G) entry not deleted" ## State (permanent / temp) tests. @@ -321,18 +321,15 @@ __cfg_test_port_ip_star_g() bridge mdb add dev br0 port $swp1 grp $grp permanent vid 10 \ filter_mode exclude source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "permanent" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "permanent" check_err $? "(*, G) entry not added as \"permanent\" when should" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | \ grep -q "permanent" check_err $? "(S, G) entry not added as \"permanent\" when should" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q " 0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_err $? "(*, G) \"permanent\" entry has a pending group timer" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_err $? "\"permanent\" source entry has a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -342,18 +339,14 @@ __cfg_test_port_ip_star_g() bridge mdb add dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode exclude source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "temp" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "temp" check_err $? "(*, G) EXCLUDE entry not added as \"temp\" when should" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "temp" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "temp" check_err $? "(S, G) \"blocked\" entry not added as \"temp\" when should" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q " 0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_fail $? "(*, G) EXCLUDE entry does not have a pending group timer" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_err $? "\"blocked\" source entry has a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -363,18 +356,14 @@ __cfg_test_port_ip_star_g() bridge mdb add dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode include source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "temp" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "temp" check_err $? "(*, G) INCLUDE entry not added as \"temp\" when should" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "temp" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "temp" check_err $? "(S, G) entry not added as \"temp\" when should" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q " 0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00" check_err $? "(*, G) INCLUDE entry has a pending group timer" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "\/0.00" + bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00" check_fail $? "Source entry does not have a pending source timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -383,8 +372,7 @@ __cfg_test_port_ip_star_g() bridge mdb add dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode include source_list $src1 - bridge -d -s mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q " 0.00" + bridge -d -s mdb get dev br0 grp $grp src $src1 vid 10 | grep -q " 0.00" check_err $? "(S, G) entry has a pending group timer" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -396,11 +384,9 @@ __cfg_test_port_ip_star_g() bridge mdb add dev br0 port $swp1 grp $grp vid 10 \ filter_mode include source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "include" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "include" check_err $? "(*, G) INCLUDE not added with \"include\" filter mode" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "blocked" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "blocked" check_fail $? "(S, G) entry marked as \"blocked\" when should not" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -410,11 +396,9 @@ __cfg_test_port_ip_star_g() bridge mdb add dev br0 port $swp1 grp $grp vid 10 \ filter_mode exclude source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "exclude" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "exclude" check_err $? "(*, G) EXCLUDE not added with \"exclude\" filter mode" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "blocked" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "blocked" check_err $? "(S, G) entry not marked as \"blocked\" when should" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -426,11 +410,9 @@ __cfg_test_port_ip_star_g() bridge mdb add dev br0 port $swp1 grp $grp vid 10 \ filter_mode exclude source_list $src1 proto zebra - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "zebra" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "zebra" check_err $? "(*, G) entry not added with \"zebra\" protocol" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "zebra" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "zebra" check_err $? "(S, G) entry not marked added with \"zebra\" protocol" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -443,20 +425,16 @@ __cfg_test_port_ip_star_g() bridge mdb replace dev br0 port $swp1 grp $grp permanent vid 10 \ filter_mode exclude source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "permanent" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "permanent" check_err $? "(*, G) entry not marked as \"permanent\" after replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "permanent" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "permanent" check_err $? "(S, G) entry not marked as \"permanent\" after replace" bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode exclude source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "temp" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "temp" check_err $? "(*, G) entry not marked as \"temp\" after replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "temp" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "temp" check_err $? "(S, G) entry not marked as \"temp\" after replace" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -467,20 +445,16 @@ __cfg_test_port_ip_star_g() bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode include source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "include" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "include" check_err $? "(*, G) not marked with \"include\" filter mode after replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "blocked" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "blocked" check_fail $? "(S, G) marked as \"blocked\" after replace" bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode exclude source_list $src1 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "exclude" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "exclude" check_err $? "(*, G) not marked with \"exclude\" filter mode after replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "blocked" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "blocked" check_err $? "(S, G) not marked as \"blocked\" after replace" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -491,20 +465,20 @@ __cfg_test_port_ip_star_g() bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode exclude source_list $src1,$src2,$src3 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src1" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 &> /dev/null check_err $? "(S, G) entry for source $src1 not created after replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src2" + bridge -d mdb get dev br0 grp $grp src $src2 vid 10 &> /dev/null check_err $? "(S, G) entry for source $src2 not created after replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src3" + bridge -d mdb get dev br0 grp $grp src $src3 vid 10 &> /dev/null check_err $? "(S, G) entry for source $src3 not created after replace" bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode exclude source_list $src1,$src3 - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src1" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 &> /dev/null check_err $? "(S, G) entry for source $src1 not created after second replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src2" + bridge -d mdb get dev br0 grp $grp src $src2 vid 10 &> /dev/null check_fail $? "(S, G) entry for source $src2 created after second replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -q "src $src3" + bridge -d mdb get dev br0 grp $grp src $src3 vid 10 &> /dev/null check_err $? "(S, G) entry for source $src3 not created after second replace" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -515,11 +489,9 @@ __cfg_test_port_ip_star_g() bridge mdb replace dev br0 port $swp1 grp $grp temp vid 10 \ filter_mode exclude source_list $src1 proto bgp - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep -v "src" | \ - grep -q "bgp" + bridge -d mdb get dev br0 grp $grp vid 10 | grep -q "bgp" check_err $? "(*, G) protocol not changed to \"bgp\" after replace" - bridge -d mdb show dev br0 vid 10 | grep "$grp" | grep "src" | \ - grep -q "bgp" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep -q "bgp" check_err $? "(S, G) protocol not changed to \"bgp\" after replace" bridge mdb del dev br0 port $swp1 grp $grp vid 10 @@ -532,8 +504,8 @@ __cfg_test_port_ip_star_g() bridge mdb add dev br0 port $swp2 grp $grp vid 10 \ filter_mode include source_list $src1 bridge mdb add dev br0 port $swp1 grp $grp vid 10 - bridge -d mdb show dev br0 vid 10 | grep "$swp1" | grep "$grp" | \ - grep "$src1" | grep -q "added_by_star_ex" + bridge -d mdb get dev br0 grp $grp src $src1 vid 10 | grep "$swp1" | \ + grep -q "added_by_star_ex" check_err $? "\"added_by_star_ex\" entry not created after adding (*, G) entry" bridge mdb del dev br0 port $swp1 grp $grp vid 10 bridge mdb del dev br0 port $swp2 grp $grp src $src1 vid 10 @@ -606,27 +578,23 @@ __cfg_test_port_ip_sg() RET=0 bridge mdb add dev br0 port $swp1 $grp_key vid 10 - bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | grep -q "include" + bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "include" check_err $? "Default filter mode is not \"include\"" bridge mdb del dev br0 port $swp1 $grp_key vid 10 # Check that entries can be added as both permanent and temp and that # group timer is set correctly. bridge mdb add dev br0 port $swp1 $grp_key permanent vid 10 - bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "permanent" + bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "permanent" check_err $? "Entry not added as \"permanent\" when should" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q " 0.00" + bridge -d -s mdb get dev br0 $grp_key vid 10 | grep -q " 0.00" check_err $? "\"permanent\" entry has a pending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 bridge mdb add dev br0 port $swp1 $grp_key temp vid 10 - bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "temp" + bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "temp" check_err $? "Entry not added as \"temp\" when should" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q " 0.00" + bridge -d -s mdb get dev br0 $grp_key vid 10 | grep -q " 0.00" check_fail $? "\"temp\" entry has an unpending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -650,24 +618,19 @@ __cfg_test_port_ip_sg() # Check that we can replace available attributes. bridge mdb add dev br0 port $swp1 $grp_key vid 10 proto 123 bridge mdb replace dev br0 port $swp1 $grp_key vid 10 proto 111 - bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "111" + bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "111" check_err $? "Failed to replace protocol" bridge mdb replace dev br0 port $swp1 $grp_key vid 10 permanent - bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "permanent" + bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "permanent" check_err $? "Entry not marked as \"permanent\" after replace" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q " 0.00" + bridge -d -s mdb get dev br0 $grp_key vid 10 | grep -q " 0.00" check_err $? "Entry has a pending group timer after replace" bridge mdb replace dev br0 port $swp1 $grp_key vid 10 temp - bridge -d mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "temp" + bridge -d mdb get dev br0 $grp_key vid 10 | grep -q "temp" check_err $? "Entry not marked as \"temp\" after replace" - bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q " 0.00" + bridge -d -s mdb get dev br0 $grp_key vid 10 | grep -q " 0.00" check_fail $? "Entry has an unpending group timer after replace" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -675,7 +638,7 @@ __cfg_test_port_ip_sg() # (*, G) ports need to be added to it. bridge mdb add dev br0 port $swp2 grp $grp vid 10 bridge mdb add dev br0 port $swp1 $grp_key vid 10 - bridge mdb show dev br0 vid 10 | grep "$grp_key" | grep $swp2 | \ + bridge mdb get dev br0 $grp_key vid 10 | grep $swp2 | \ grep -q "added_by_star_ex" check_err $? "\"added_by_star_ex\" entry not created after adding (S, G) entry" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -1102,14 +1065,17 @@ fwd_test() echo log_info "# Forwarding tests" + # Set the Max Response Delay to 100 centiseconds (1 second) so that the + # bridge will start forwarding according to its MDB soon after a + # multicast querier is enabled. + ip link set dev br0 type bridge mcast_query_response_interval 100 + # Forwarding according to MDB entries only takes place when the bridge # detects that there is a valid querier in the network. Set the bridge # as the querier and assign it a valid IPv6 link-local address to be # used as the source address for MLD queries. ip -6 address add fe80::1/64 nodad dev br0 ip link set dev br0 type bridge mcast_querier 1 - # Wait the default Query Response Interval (10 seconds) for the bridge - # to determine that there are no other queriers in the network. sleep 10 fwd_test_host @@ -1117,6 +1083,7 @@ fwd_test() ip link set dev br0 type bridge mcast_querier 0 ip -6 address del fe80::1/64 dev br0 + ip link set dev br0 type bridge mcast_query_response_interval 1000 } ctrl_igmpv3_is_in_test() @@ -1132,7 +1099,7 @@ ctrl_igmpv3_is_in_test() $MZ $h1.10 -c 1 -a own -b 01:00:5e:01:01:01 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q - bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2 + bridge mdb get dev br0 grp 239.1.1.1 src 192.0.2.2 vid 10 &> /dev/null check_fail $? "Permanent entry affected by IGMP packet" # Replace the permanent entry with a temporary one and check that after @@ -1145,12 +1112,10 @@ ctrl_igmpv3_is_in_test() $MZ $h1.10 -a own -b 01:00:5e:01:01:01 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q - bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \ - grep -q 192.0.2.2 + bridge -d mdb get dev br0 grp 239.1.1.1 vid 10 | grep -q 192.0.2.2 check_err $? "Source not add to source list" - bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | \ - grep -q "src 192.0.2.2" + bridge mdb get dev br0 grp 239.1.1.1 src 192.0.2.2 vid 10 &> /dev/null check_err $? "(S, G) entry not created for new source" bridge mdb del dev br0 port $swp1 grp 239.1.1.1 vid 10 @@ -1172,8 +1137,7 @@ ctrl_mldv2_is_in_test() $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q - bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ - grep -q 2001:db8:1::2 + bridge mdb get dev br0 grp ff0e::1 src 2001:db8:1::2 vid 10 &> /dev/null check_fail $? "Permanent entry affected by MLD packet" # Replace the permanent entry with a temporary one and check that after @@ -1186,12 +1150,10 @@ ctrl_mldv2_is_in_test() $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q - bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \ - grep -q 2001:db8:1::2 + bridge -d mdb get dev br0 grp ff0e::1 vid 10 | grep -q 2001:db8:1::2 check_err $? "Source not add to source list" - bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ - grep -q "src 2001:db8:1::2" + bridge mdb get dev br0 grp ff0e::1 src 2001:db8:1::2 vid 10 &> /dev/null check_err $? "(S, G) entry not created for new source" bridge mdb del dev br0 port $swp1 grp ff0e::1 vid 10 @@ -1208,8 +1170,8 @@ ctrl_test() ctrl_mldv2_is_in_test } -if ! bridge mdb help 2>&1 | grep -q "replace"; then - echo "SKIP: iproute2 too old, missing bridge mdb replace support" +if ! bridge mdb help 2>&1 | grep -q "get"; then + echo "SKIP: iproute2 too old, missing bridge mdb get support" exit $ksft_skip fi diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh index 20a7cb7222b8b..c2420bb72c128 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -209,14 +209,17 @@ test_l2_miss_multicast() # both registered and unregistered multicast traffic. bridge link set dev $swp2 mcast_router 2 + # Set the Max Response Delay to 100 centiseconds (1 second) so that the + # bridge will start forwarding according to its MDB soon after a + # multicast querier is enabled. + ip link set dev br1 type bridge mcast_query_response_interval 100 + # Forwarding according to MDB entries only takes place when the bridge # detects that there is a valid querier in the network. Set the bridge # as the querier and assign it a valid IPv6 link-local address to be # used as the source address for MLD queries. ip link set dev br1 type bridge mcast_querier 1 ip -6 address add fe80::1/64 nodad dev br1 - # Wait the default Query Response Interval (10 seconds) for the bridge - # to determine that there are no other queriers in the network. sleep 10 test_l2_miss_multicast_ipv4 @@ -224,6 +227,7 @@ test_l2_miss_multicast() ip -6 address del fe80::1/64 dev br1 ip link set dev br1 type bridge mcast_querier 0 + ip link set dev br1 type bridge mcast_query_response_interval 1000 bridge link set dev $swp2 mcast_router 1 } diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index e317c2e44dae8..4f80014cae494 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -22,8 +22,11 @@ CONFIG_NFT_TPROXY=m CONFIG_NFT_SOCKET=m CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IP6_NF_FILTER=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_CLS_ACT=y diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 4632a954c73e6..67ca22856d54a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -682,16 +682,10 @@ wait_mpj() done } -kill_wait() -{ - kill $1 > /dev/null 2>&1 - wait $1 2>/dev/null -} - kill_events_pids() { - kill_wait $evts_ns1_pid - kill_wait $evts_ns2_pid + mptcp_lib_kill_wait $evts_ns1_pid + mptcp_lib_kill_wait $evts_ns2_pid } kill_tests_wait() diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 92a5befe80394..4cd4297ca86de 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -6,7 +6,7 @@ readonly KSFT_FAIL=1 readonly KSFT_SKIP=4 # shellcheck disable=SC2155 # declare and assign separately -readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g') +readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}" MPTCP_LIB_SUBTESTS=() @@ -207,3 +207,12 @@ mptcp_lib_result_print_all_tap() { printf "%s\n" "${subtest}" done } + +# $1: PID +mptcp_lib_kill_wait() { + [ "${1}" -eq 0 ] && return 0 + + kill -SIGUSR1 "${1}" > /dev/null 2>&1 + kill "${1}" > /dev/null 2>&1 + wait "${1}" 2>/dev/null +} diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings index 79b65bdf05db6..abc5648b59abd 100644 --- a/tools/testing/selftests/net/mptcp/settings +++ b/tools/testing/selftests/net/mptcp/settings @@ -1 +1 @@ -timeout=1200 +timeout=1800 diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b25a3e33eb253..c44bf5c7c6e04 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -108,15 +108,6 @@ test_fail() mptcp_lib_result_fail "${test_name}" } -kill_wait() -{ - [ $1 -eq 0 ] && return 0 - - kill -SIGUSR1 $1 > /dev/null 2>&1 - kill $1 > /dev/null 2>&1 - wait $1 2>/dev/null -} - # This function is used in the cleanup trap #shellcheck disable=SC2317 cleanup() @@ -128,7 +119,7 @@ cleanup() for pid in $client4_pid $server4_pid $client6_pid $server6_pid\ $server_evts_pid $client_evts_pid do - kill_wait $pid + mptcp_lib_kill_wait $pid done local netns @@ -210,7 +201,7 @@ make_connection() fi :>"$client_evts" if [ $client_evts_pid -ne 0 ]; then - kill_wait $client_evts_pid + mptcp_lib_kill_wait $client_evts_pid fi ip netns exec "$ns2" ./pm_nl_ctl events >> "$client_evts" 2>&1 & client_evts_pid=$! @@ -219,7 +210,7 @@ make_connection() fi :>"$server_evts" if [ $server_evts_pid -ne 0 ]; then - kill_wait $server_evts_pid + mptcp_lib_kill_wait $server_evts_pid fi ip netns exec "$ns1" ./pm_nl_ctl events >> "$server_evts" 2>&1 & server_evts_pid=$! @@ -627,7 +618,7 @@ test_subflows() "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2" # Delete the listener from the client ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid local sport sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") @@ -666,7 +657,7 @@ test_subflows() "$client_addr_id" "ns1" "ns2" # Delete the listener from the client ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") @@ -705,7 +696,7 @@ test_subflows() "$client_addr_id" "ns1" "ns2" # Delete the listener from the client ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") @@ -743,7 +734,7 @@ test_subflows() "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1" # Delete the listener from the server ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") @@ -782,7 +773,7 @@ test_subflows() "$server_addr_id" "ns2" "ns1" # Delete the listener from the server ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") @@ -819,7 +810,7 @@ test_subflows() "10.0.2.2" "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1" # Delete the listener from the server ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") @@ -865,7 +856,7 @@ test_subflows_v4_v6_mix() "$server_addr_id" "ns2" "ns1" # Delete the listener from the server ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") @@ -982,7 +973,7 @@ test_listener() sleep 0.5 # Delete the listener from the client ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid sleep 0.5 verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh index 112cfd8a10ad9..1b3f89e2b86e6 100755 --- a/tools/testing/selftests/net/test_bridge_backup_port.sh +++ b/tools/testing/selftests/net/test_bridge_backup_port.sh @@ -35,9 +35,8 @@ # | sw1 | | sw2 | # +------------------------------------+ +------------------------------------+ +source lib.sh ret=0 -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 # All tests in this script. Can be overridden with -t option. TESTS=" @@ -125,6 +124,16 @@ tc_check_packets() [[ $pkts == $count ]] } +bridge_link_check() +{ + local ns=$1; shift + local dev=$1; shift + local state=$1; shift + + bridge -n $ns -d -j link show dev $dev | \ + jq -e ".[][\"state\"] == \"$state\"" &> /dev/null +} + ################################################################################ # Setup @@ -132,9 +141,6 @@ setup_topo_ns() { local ns=$1; shift - ip netns add $ns - ip -n $ns link set dev lo up - ip netns exec $ns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 ip netns exec $ns sysctl -qw net.ipv6.conf.default.ignore_routes_with_linkdown=1 ip netns exec $ns sysctl -qw net.ipv6.conf.all.accept_dad=0 @@ -145,13 +151,14 @@ setup_topo() { local ns - for ns in sw1 sw2; do + setup_ns sw1 sw2 + for ns in $sw1 $sw2; do setup_topo_ns $ns done ip link add name veth0 type veth peer name veth1 - ip link set dev veth0 netns sw1 name veth0 - ip link set dev veth1 netns sw2 name veth0 + ip link set dev veth0 netns $sw1 name veth0 + ip link set dev veth1 netns $sw2 name veth0 } setup_sw_common() @@ -190,7 +197,7 @@ setup_sw_common() setup_sw1() { - local ns=sw1 + local ns=$sw1 local local_addr=192.0.2.33 local remote_addr=192.0.2.34 local veth_addr=192.0.2.49 @@ -203,7 +210,7 @@ setup_sw1() setup_sw2() { - local ns=sw2 + local ns=$sw2 local local_addr=192.0.2.34 local remote_addr=192.0.2.33 local veth_addr=192.0.2.50 @@ -229,11 +236,7 @@ setup() cleanup() { - local ns - - for ns in h1 h2 sw1 sw2; do - ip netns del $ns &> /dev/null - done + cleanup_ns $sw1 $sw2 } ################################################################################ @@ -248,85 +251,90 @@ backup_port() echo "Backup port" echo "-----------" - run_cmd "tc -n sw1 qdisc replace dev swp1 clsact" - run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + run_cmd "tc -n $sw1 qdisc replace dev swp1 clsact" + run_cmd "tc -n $sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" - run_cmd "tc -n sw1 qdisc replace dev vx0 clsact" - run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact" + run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" - run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10" + run_cmd "bridge -n $sw1 fdb replace $dmac dev swp1 master static vlan 10" # Initial state - check that packets are forwarded out of swp1 when it # has a carrier and not forwarded out of any port when it does not have # a carrier. - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 1 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 1 log_test $? 0 "Forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 0 + tc_check_packets $sw1 "dev vx0 egress" 101 0 log_test $? 0 "No forwarding out of vx0" - run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 1 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 1 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 0 + tc_check_packets $sw1 "dev vx0 egress" 101 0 log_test $? 0 "No forwarding out of vx0" - run_cmd "ip -n sw1 link set dev swp1 carrier on" + run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" # Configure vx0 as the backup port of swp1 and check that packets are # forwarded out of swp1 when it has a carrier and out of vx0 when swp1 # does not have a carrier. - run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\"" + run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_port vx0\"" log_test $? 0 "vx0 configured as backup port of swp1" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 2 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 2 log_test $? 0 "Forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 0 + tc_check_packets $sw1 "dev vx0 egress" 101 0 log_test $? 0 "No forwarding out of vx0" - run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 2 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 2 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 1 + tc_check_packets $sw1 "dev vx0 egress" 101 1 log_test $? 0 "Forwarding out of vx0" - run_cmd "ip -n sw1 link set dev swp1 carrier on" + run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 3 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 3 log_test $? 0 "Forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 1 + tc_check_packets $sw1 "dev vx0 egress" 101 1 log_test $? 0 "No forwarding out of vx0" # Remove vx0 as the backup port of swp1 and check that packets are no # longer forwarded out of vx0 when swp1 does not have a carrier. - run_cmd "bridge -n sw1 link set dev swp1 nobackup_port" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\"" + run_cmd "bridge -n $sw1 link set dev swp1 nobackup_port" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_port vx0\"" log_test $? 1 "vx0 not configured as backup port of swp1" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 4 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 4 log_test $? 0 "Forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 1 + tc_check_packets $sw1 "dev vx0 egress" 101 1 log_test $? 0 "No forwarding out of vx0" - run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 4 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 4 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 1 + tc_check_packets $sw1 "dev vx0 egress" 101 1 log_test $? 0 "No forwarding out of vx0" } @@ -339,125 +347,130 @@ backup_nhid() echo "Backup nexthop ID" echo "-----------------" - run_cmd "tc -n sw1 qdisc replace dev swp1 clsact" - run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + run_cmd "tc -n $sw1 qdisc replace dev swp1 clsact" + run_cmd "tc -n $sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" - run_cmd "tc -n sw1 qdisc replace dev vx0 clsact" - run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact" + run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" - run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb" - run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb" - run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb" + run_cmd "ip -n $sw1 nexthop replace id 1 via 192.0.2.34 fdb" + run_cmd "ip -n $sw1 nexthop replace id 2 via 192.0.2.34 fdb" + run_cmd "ip -n $sw1 nexthop replace id 10 group 1/2 fdb" - run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10" - run_cmd "bridge -n sw1 fdb replace $dmac dev vx0 self static dst 192.0.2.36 src_vni 10010" + run_cmd "bridge -n $sw1 fdb replace $dmac dev swp1 master static vlan 10" + run_cmd "bridge -n $sw1 fdb replace $dmac dev vx0 self static dst 192.0.2.36 src_vni 10010" - run_cmd "ip -n sw2 address replace 192.0.2.36/32 dev lo" + run_cmd "ip -n $sw2 address replace 192.0.2.36/32 dev lo" # The first filter matches on packets forwarded using the backup # nexthop ID and the second filter matches on packets forwarded using a # regular VXLAN FDB entry. - run_cmd "tc -n sw2 qdisc replace dev vx0 clsact" - run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass" - run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 102 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.36 action pass" + run_cmd "tc -n $sw2 qdisc replace dev vx0 clsact" + run_cmd "tc -n $sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass" + run_cmd "tc -n $sw2 filter replace dev vx0 ingress pref 1 handle 102 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.36 action pass" # Configure vx0 as the backup port of swp1 and check that packets are # forwarded out of swp1 when it has a carrier and out of vx0 when swp1 # does not have a carrier. When packets are forwarded out of vx0, check # that they are forwarded by the VXLAN FDB entry. - run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\"" + run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_port vx0\"" log_test $? 0 "vx0 configured as backup port of swp1" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 1 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 1 log_test $? 0 "Forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 0 + tc_check_packets $sw1 "dev vx0 egress" 101 0 log_test $? 0 "No forwarding out of vx0" - run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 1 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 1 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 1 + tc_check_packets $sw1 "dev vx0 egress" 101 1 log_test $? 0 "Forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 0 + tc_check_packets $sw2 "dev vx0 ingress" 101 0 log_test $? 0 "No forwarding using backup nexthop ID" - tc_check_packets sw2 "dev vx0 ingress" 102 1 + tc_check_packets $sw2 "dev vx0 ingress" 102 1 log_test $? 0 "Forwarding using VXLAN FDB entry" - run_cmd "ip -n sw1 link set dev swp1 carrier on" + run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" # Configure nexthop ID 10 as the backup nexthop ID of swp1 and check # that when packets are forwarded out of vx0, they are forwarded using # the backup nexthop ID. - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 10\"" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 10" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 10\"" log_test $? 0 "nexthop ID 10 configured as backup nexthop ID of swp1" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 2 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 2 log_test $? 0 "Forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 1 + tc_check_packets $sw1 "dev vx0 egress" 101 1 log_test $? 0 "No forwarding out of vx0" - run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 2 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 2 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 2 + tc_check_packets $sw1 "dev vx0 egress" 101 2 log_test $? 0 "Forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "Forwarding using backup nexthop ID" - tc_check_packets sw2 "dev vx0 ingress" 102 1 + tc_check_packets $sw2 "dev vx0 ingress" 102 1 log_test $? 0 "No forwarding using VXLAN FDB entry" - run_cmd "ip -n sw1 link set dev swp1 carrier on" + run_cmd "ip -n $sw1 link set dev swp1 carrier on" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding log_test $? 0 "swp1 carrier on" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 3 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 3 log_test $? 0 "Forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 2 + tc_check_packets $sw1 "dev vx0 egress" 101 2 log_test $? 0 "No forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "No forwarding using backup nexthop ID" - tc_check_packets sw2 "dev vx0 ingress" 102 1 + tc_check_packets $sw2 "dev vx0 ingress" 102 1 log_test $? 0 "No forwarding using VXLAN FDB entry" # Reset the backup nexthop ID to 0 and check that packets are no longer # forwarded using the backup nexthop ID when swp1 does not have a # carrier and are instead forwarded by the VXLAN FDB. - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 0" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid\"" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 0" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid\"" log_test $? 1 "No backup nexthop ID configured for swp1" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 4 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 4 log_test $? 0 "Forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 2 + tc_check_packets $sw1 "dev vx0 egress" 101 2 log_test $? 0 "No forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "No forwarding using backup nexthop ID" - tc_check_packets sw2 "dev vx0 ingress" 102 1 + tc_check_packets $sw2 "dev vx0 ingress" 102 1 log_test $? 0 "No forwarding using VXLAN FDB entry" - run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 4 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 4 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 3 + tc_check_packets $sw1 "dev vx0 egress" 101 3 log_test $? 0 "Forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "No forwarding using backup nexthop ID" - tc_check_packets sw2 "dev vx0 ingress" 102 2 + tc_check_packets $sw2 "dev vx0 ingress" 102 2 log_test $? 0 "Forwarding using VXLAN FDB entry" } @@ -475,109 +488,110 @@ backup_nhid_invalid() # is forwarded out of the VXLAN port, but dropped by the VXLAN driver # and does not crash the host. - run_cmd "tc -n sw1 qdisc replace dev swp1 clsact" - run_cmd "tc -n sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + run_cmd "tc -n $sw1 qdisc replace dev swp1 clsact" + run_cmd "tc -n $sw1 filter replace dev swp1 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" - run_cmd "tc -n sw1 qdisc replace dev vx0 clsact" - run_cmd "tc -n sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" + run_cmd "tc -n $sw1 qdisc replace dev vx0 clsact" + run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac action pass" # Drop all other Tx traffic to avoid changes to Tx drop counter. - run_cmd "tc -n sw1 filter replace dev vx0 egress pref 2 handle 102 proto all matchall action drop" + run_cmd "tc -n $sw1 filter replace dev vx0 egress pref 2 handle 102 proto all matchall action drop" - tx_drop=$(ip -n sw1 -s -j link show dev vx0 | jq '.[]["stats64"]["tx"]["dropped"]') + tx_drop=$(ip -n $sw1 -s -j link show dev vx0 | jq '.[]["stats64"]["tx"]["dropped"]') - run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb" - run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb" - run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb" + run_cmd "ip -n $sw1 nexthop replace id 1 via 192.0.2.34 fdb" + run_cmd "ip -n $sw1 nexthop replace id 2 via 192.0.2.34 fdb" + run_cmd "ip -n $sw1 nexthop replace id 10 group 1/2 fdb" - run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10" + run_cmd "bridge -n $sw1 fdb replace $dmac dev swp1 master static vlan 10" - run_cmd "tc -n sw2 qdisc replace dev vx0 clsact" - run_cmd "tc -n sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass" + run_cmd "tc -n $sw2 qdisc replace dev vx0 clsact" + run_cmd "tc -n $sw2 filter replace dev vx0 ingress pref 1 handle 101 proto ip flower src_mac $smac dst_mac $dmac enc_key_id 10010 enc_dst_ip 192.0.2.34 action pass" # First, check that redirection works. - run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_port vx0\"" + run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_port vx0\"" log_test $? 0 "vx0 configured as backup port of swp1" - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 10\"" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 10" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 10\"" log_test $? 0 "Valid nexthop as backup nexthop" - run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled log_test $? 0 "swp1 carrier off" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 0 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 0 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 1 + tc_check_packets $sw1 "dev vx0 egress" 101 1 log_test $? 0 "Forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "Forwarding using backup nexthop ID" - run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $tx_drop'" + run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $tx_drop'" log_test $? 0 "No Tx drop increase" # Use a non-existent nexthop ID. - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 20" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 20\"" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 20" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 20\"" log_test $? 0 "Non-existent nexthop as backup nexthop" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 0 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 0 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 2 + tc_check_packets $sw1 "dev vx0 egress" 101 2 log_test $? 0 "Forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "No forwarding using backup nexthop ID" - run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 1))'" + run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 1))'" log_test $? 0 "Tx drop increased" # Use a blckhole nexthop. - run_cmd "ip -n sw1 nexthop replace id 30 blackhole" - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 30" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 30\"" + run_cmd "ip -n $sw1 nexthop replace id 30 blackhole" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 30" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 30\"" log_test $? 0 "Blackhole nexthop as backup nexthop" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 0 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 0 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 3 + tc_check_packets $sw1 "dev vx0 egress" 101 3 log_test $? 0 "Forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "No forwarding using backup nexthop ID" - run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 2))'" + run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 2))'" log_test $? 0 "Tx drop increased" # Non-group FDB nexthop. - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 1" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 1\"" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 1" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 1\"" log_test $? 0 "Non-group FDB nexthop as backup nexthop" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 0 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 0 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 4 + tc_check_packets $sw1 "dev vx0 egress" 101 4 log_test $? 0 "Forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "No forwarding using backup nexthop ID" - run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 3))'" + run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 3))'" log_test $? 0 "Tx drop increased" # IPv6 address family nexthop. - run_cmd "ip -n sw1 nexthop replace id 100 via 2001:db8:100::1 fdb" - run_cmd "ip -n sw1 nexthop replace id 200 via 2001:db8:100::1 fdb" - run_cmd "ip -n sw1 nexthop replace id 300 group 100/200 fdb" - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 300" - run_cmd "bridge -n sw1 -d link show dev swp1 | grep \"backup_nhid 300\"" + run_cmd "ip -n $sw1 nexthop replace id 100 via 2001:db8:100::1 fdb" + run_cmd "ip -n $sw1 nexthop replace id 200 via 2001:db8:100::1 fdb" + run_cmd "ip -n $sw1 nexthop replace id 300 group 100/200 fdb" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 300" + run_cmd "bridge -n $sw1 -d link show dev swp1 | grep \"backup_nhid 300\"" log_test $? 0 "IPv6 address family nexthop as backup nexthop" - run_cmd "ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" - tc_check_packets sw1 "dev swp1 egress" 101 0 + run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1" + tc_check_packets $sw1 "dev swp1 egress" 101 0 log_test $? 0 "No forwarding out of swp1" - tc_check_packets sw1 "dev vx0 egress" 101 5 + tc_check_packets $sw1 "dev vx0 egress" 101 5 log_test $? 0 "Forwarding out of vx0" - tc_check_packets sw2 "dev vx0 ingress" 101 1 + tc_check_packets $sw2 "dev vx0 ingress" 101 1 log_test $? 0 "No forwarding using backup nexthop ID" - run_cmd "ip -n sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 4))'" + run_cmd "ip -n $sw1 -s -j link show dev vx0 | jq -e '.[][\"stats64\"][\"tx\"][\"dropped\"] == $((tx_drop + 4))'" log_test $? 0 "Tx drop increased" } @@ -591,44 +605,46 @@ backup_nhid_ping() echo "------------------------" # Test bidirectional traffic when traffic is redirected in both VTEPs. - sw1_mac=$(ip -n sw1 -j -p link show br0.10 | jq -r '.[]["address"]') - sw2_mac=$(ip -n sw2 -j -p link show br0.10 | jq -r '.[]["address"]') + sw1_mac=$(ip -n $sw1 -j -p link show br0.10 | jq -r '.[]["address"]') + sw2_mac=$(ip -n $sw2 -j -p link show br0.10 | jq -r '.[]["address"]') - run_cmd "bridge -n sw1 fdb replace $sw2_mac dev swp1 master static vlan 10" - run_cmd "bridge -n sw2 fdb replace $sw1_mac dev swp1 master static vlan 10" + run_cmd "bridge -n $sw1 fdb replace $sw2_mac dev swp1 master static vlan 10" + run_cmd "bridge -n $sw2 fdb replace $sw1_mac dev swp1 master static vlan 10" - run_cmd "ip -n sw1 neigh replace 192.0.2.66 lladdr $sw2_mac nud perm dev br0.10" - run_cmd "ip -n sw2 neigh replace 192.0.2.65 lladdr $sw1_mac nud perm dev br0.10" + run_cmd "ip -n $sw1 neigh replace 192.0.2.66 lladdr $sw2_mac nud perm dev br0.10" + run_cmd "ip -n $sw2 neigh replace 192.0.2.65 lladdr $sw1_mac nud perm dev br0.10" - run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb" - run_cmd "ip -n sw2 nexthop replace id 1 via 192.0.2.33 fdb" - run_cmd "ip -n sw1 nexthop replace id 10 group 1 fdb" - run_cmd "ip -n sw2 nexthop replace id 10 group 1 fdb" + run_cmd "ip -n $sw1 nexthop replace id 1 via 192.0.2.34 fdb" + run_cmd "ip -n $sw2 nexthop replace id 1 via 192.0.2.33 fdb" + run_cmd "ip -n $sw1 nexthop replace id 10 group 1 fdb" + run_cmd "ip -n $sw2 nexthop replace id 10 group 1 fdb" - run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" - run_cmd "bridge -n sw2 link set dev swp1 backup_port vx0" - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10" - run_cmd "bridge -n sw2 link set dev swp1 backup_nhid 10" + run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n $sw2 link set dev swp1 backup_port vx0" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 10" + run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 10" - run_cmd "ip -n sw1 link set dev swp1 carrier off" - run_cmd "ip -n sw2 link set dev swp1 carrier off" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled + run_cmd "ip -n $sw2 link set dev swp1 carrier off" + busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw2 swp1 disabled - run_cmd "ip netns exec sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66" + run_cmd "ip netns exec $sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66" log_test $? 0 "Ping with backup nexthop ID" # Reset the backup nexthop ID to 0 and check that ping fails. - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 0" - run_cmd "bridge -n sw2 link set dev swp1 backup_nhid 0" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 0" + run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 0" - run_cmd "ip netns exec sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66" + run_cmd "ip netns exec $sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66" log_test $? 1 "Ping after disabling backup nexthop ID" } backup_nhid_add_del_loop() { while true; do - ip -n sw1 nexthop del id 10 - ip -n sw1 nexthop replace id 10 group 1/2 fdb + ip -n $sw1 nexthop del id 10 + ip -n $sw1 nexthop replace id 10 group 1/2 fdb done >/dev/null 2>&1 } @@ -648,19 +664,19 @@ backup_nhid_torture() # deleting the group. The test is considered successful if nothing # crashed. - run_cmd "ip -n sw1 nexthop replace id 1 via 192.0.2.34 fdb" - run_cmd "ip -n sw1 nexthop replace id 2 via 192.0.2.34 fdb" - run_cmd "ip -n sw1 nexthop replace id 10 group 1/2 fdb" + run_cmd "ip -n $sw1 nexthop replace id 1 via 192.0.2.34 fdb" + run_cmd "ip -n $sw1 nexthop replace id 2 via 192.0.2.34 fdb" + run_cmd "ip -n $sw1 nexthop replace id 10 group 1/2 fdb" - run_cmd "bridge -n sw1 fdb replace $dmac dev swp1 master static vlan 10" + run_cmd "bridge -n $sw1 fdb replace $dmac dev swp1 master static vlan 10" - run_cmd "bridge -n sw1 link set dev swp1 backup_port vx0" - run_cmd "bridge -n sw1 link set dev swp1 backup_nhid 10" - run_cmd "ip -n sw1 link set dev swp1 carrier off" + run_cmd "bridge -n $sw1 link set dev swp1 backup_port vx0" + run_cmd "bridge -n $sw1 link set dev swp1 backup_nhid 10" + run_cmd "ip -n $sw1 link set dev swp1 carrier off" backup_nhid_add_del_loop & pid1=$! - ip netns exec sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 0 & + ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 0 & pid2=$! sleep 30 diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 2456a399eb9ae..afd18c678ff5a 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized +ifeq ($(CC),clang) + FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) + WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) +endif + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -LDFLAGS := -ggdb $(EXTRA_LDFLAGS) +LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) LIBS := $$($(PKG_CONFIG) --libs libtracefs) SRC := $(wildcard src/*.c) diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index 8f81fa0073648..01870d50942a1 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -135,8 +135,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu, if (params->output_divisor) duration = duration / params->output_divisor; - if (data->bucket_size) - bucket = duration / data->bucket_size; + bucket = duration / data->bucket_size; total_duration = duration * count; @@ -480,7 +479,11 @@ static void osnoise_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index f7c959be86777..457360db07673 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -331,7 +331,11 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 47d3d8b53cb21..dbf154082f958 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -178,8 +178,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu, if (params->output_divisor) latency = latency / params->output_divisor; - if (data->bucket_size) - bucket = latency / data->bucket_size; + bucket = latency / data->bucket_size; if (!context) { hist = data->hist[cpu].irq; @@ -546,7 +545,11 @@ static void timerlat_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 1640f121baca5..3e9af2c386888 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -375,7 +375,11 @@ static void timerlat_top_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index c769d7b3842c0..9ac71a66840c1 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -238,12 +238,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr, return syscall(__NR_sched_setattr, pid, attr, flags); } -static inline int sched_getattr(pid_t pid, struct sched_attr *attr, - unsigned int size, unsigned int flags) -{ - return syscall(__NR_sched_getattr, pid, attr, size, flags); -} - int __set_sched_attr(int pid, struct sched_attr *attr) { int flags = 0; @@ -479,13 +473,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param) if (prio == INVALID_VAL) return -1; - if (prio < sched_get_priority_min(SCHED_OTHER)) + if (prio < MIN_NICE) return -1; - if (prio > sched_get_priority_max(SCHED_OTHER)) + if (prio > MAX_NICE) return -1; sched_param->sched_policy = SCHED_OTHER; - sched_param->sched_priority = prio; + sched_param->sched_nice = prio; break; default: return -1; @@ -536,7 +530,7 @@ int set_cpu_dma_latency(int32_t latency) */ static const int find_mount(const char *fs, char *mp, int sizeof_mp) { - char mount_point[MAX_PATH]; + char mount_point[MAX_PATH+1]; char type[100]; int found = 0; FILE *fp; diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index 04ed1e650495a..d44513e6c66a0 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -9,6 +9,8 @@ */ #define BUFF_U64_STR_SIZE 24 #define MAX_PATH 1024 +#define MAX_NICE 20 +#define MIN_NICE -19 #define container_of(ptr, type, member)({ \ const typeof(((type *)0)->member) *__mptr = (ptr); \ diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile index 3d0f3888a58c6..485f8aeddbe03 100644 --- a/tools/verification/rv/Makefile +++ b/tools/verification/rv/Makefile @@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized +ifeq ($(CC),clang) + FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) + WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) +endif + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -I include -LDFLAGS := -ggdb $(EXTRA_LDFLAGS) +LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) LIBS := $$($(PKG_CONFIG) --libs libtracefs) SRC := $(wildcard src/*.c) diff --git a/tools/verification/rv/src/in_kernel.c b/tools/verification/rv/src/in_kernel.c index ad28582bcf2b1..f04479ecc96c0 100644 --- a/tools/verification/rv/src/in_kernel.c +++ b/tools/verification/rv/src/in_kernel.c @@ -210,9 +210,9 @@ static char *ikm_read_reactor(char *monitor_name) static char *ikm_get_current_reactor(char *monitor_name) { char *reactors = ikm_read_reactor(monitor_name); + char *curr_reactor = NULL; char *start; char *end; - char *curr_reactor; if (!reactors) return NULL;