diff options
266 files changed, 2642 insertions, 1649 deletions
@@ -266,6 +266,9 @@ Jens Osterkamp <Jens.Osterkamp@de.ibm.com> Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net> Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org> Jilai Wang <quic_jilaiw@quicinc.com> <jilaiw@codeaurora.org> +Jiri Kosina <jikos@kernel.org> <jikos@jikos.cz> +Jiri Kosina <jikos@kernel.org> <jkosina@suse.cz> +Jiri Kosina <jikos@kernel.org> <jkosina@suse.com> Jiri Pirko <jiri@resnulli.us> <jiri@nvidia.com> Jiri Pirko <jiri@resnulli.us> <jiri@mellanox.com> Jiri Pirko <jiri@resnulli.us> <jpirko@redhat.com> diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml index 73674baea75d..f9160d7bac3c 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml @@ -42,6 +42,8 @@ properties: - lg,acx467akm-7 # LG Corporation 7" WXGA TFT LCD panel - lg,ld070wx3-sl01 + # LG Corporation 5" HD TFT LCD panel + - lg,lh500wx1-sd03 # One Stop Displays OSD101T2587-53TS 10.1" 1920x1200 panel - osddisplays,osd101t2587-53ts # Panasonic 10" WUXGA TFT LCD panel diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml index 3ec9ee95045f..11422af3477e 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml @@ -208,8 +208,6 @@ properties: - lemaker,bl035-rgb-002 # LG 7" (800x480 pixels) TFT LCD panel - lg,lb070wv8 - # LG Corporation 5" HD TFT LCD panel - - lg,lh500wx1-sd03 # LG LP079QX1-SP0V 7.9" (1536x2048 pixels) TFT LCD panel - lg,lp079qx1-sp0v # LG 9.7" (2048x1536 pixels) TFT LCD panel diff --git a/Documentation/filesystems/fuse-io.rst b/Documentation/filesystems/fuse-io.rst index 255a368fe534..6464de4266ad 100644 --- a/Documentation/filesystems/fuse-io.rst +++ b/Documentation/filesystems/fuse-io.rst @@ -15,7 +15,8 @@ The direct-io mode can be selected with the FOPEN_DIRECT_IO flag in the FUSE_OPEN reply. In direct-io mode the page cache is completely bypassed for reads and writes. -No read-ahead takes place. Shared mmap is disabled. +No read-ahead takes place. Shared mmap is disabled by default. To allow shared +mmap, the FUSE_DIRECT_IO_ALLOW_MMAP flag may be enabled in the FUSE_INIT reply. In cached mode reads may be satisfied from the page cache, and data may be read-ahead by the kernel to fill the cache. The cache is always kept consistent diff --git a/MAINTAINERS b/MAINTAINERS index e2c6187a3ac8..9104430e148e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12189,6 +12189,8 @@ LINUX FOR POWERPC (32-BIT AND 64-BIT) M: Michael Ellerman <mpe@ellerman.id.au> R: Nicholas Piggin <npiggin@gmail.com> R: Christophe Leroy <christophe.leroy@csgroup.eu> +R: Aneesh Kumar K.V <aneesh.kumar@kernel.org> +R: Naveen N. Rao <naveen.n.rao@linux.ibm.com> L: linuxppc-dev@lists.ozlabs.org S: Supported W: https://github.com/linuxppc/wiki/wiki @@ -19564,7 +19566,6 @@ S: Maintained F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS -M: Karsten Graul <kgraul@linux.ibm.com> M: Wenjia Zhang <wenjia@linux.ibm.com> M: Jan Karcher <jaka@linux.ibm.com> R: D. Wythe <alibuda@linux.alibaba.com> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b19a8aee684c..79ce70fbb751 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -834,6 +834,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); + /* + * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware + * dirtiness again. + */ + if (pte_sw_dirty(pte)) + pte = pte_mkdirty(pte); return pte; } diff --git a/arch/loongarch/include/asm/efi.h b/arch/loongarch/include/asm/efi.h index 091897d40b03..91d81f9730ab 100644 --- a/arch/loongarch/include/asm/efi.h +++ b/arch/loongarch/include/asm/efi.h @@ -32,6 +32,6 @@ static inline unsigned long efi_get_kimg_min_align(void) #define EFI_KIMG_PREFERRED_ADDRESS PHYSADDR(VMLINUX_LOAD_ADDRESS) -unsigned long kernel_entry_address(void); +unsigned long kernel_entry_address(unsigned long kernel_addr); #endif /* _ASM_LOONGARCH_EFI_H */ diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index 4fcc168f0732..3c808c680370 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -57,7 +57,7 @@ obj-$(CONFIG_MAGIC_SYSRQ) += sysrq.o obj-$(CONFIG_RELOCATABLE) += relocate.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o diff --git a/arch/m68k/include/asm/kexec.h b/arch/m68k/include/asm/kexec.h index f5a8b2defa4b..3b0b64f0a353 100644 --- a/arch/m68k/include/asm/kexec.h +++ b/arch/m68k/include/asm/kexec.h @@ -2,7 +2,7 @@ #ifndef _ASM_M68K_KEXEC_H #define _ASM_M68K_KEXEC_H -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* Maximum physical address we can use pages from */ #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) @@ -25,6 +25,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs, #endif /* __ASSEMBLY__ */ -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ #endif /* _ASM_M68K_KEXEC_H */ diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile index 01fb69a5095f..f335bf3268a1 100644 --- a/arch/m68k/kernel/Makefile +++ b/arch/m68k/kernel/Makefile @@ -25,7 +25,7 @@ obj-$(CONFIG_PCI) += pcibios.o obj-$(CONFIG_M68K_NONCOHERENT_DMA) += dma.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_BOOTINFO_PROC) += bootinfo_proc.o obj-$(CONFIG_UBOOT) += uboot.o diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi index f878f47e4501..ee3e2153dd13 100644 --- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi +++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi @@ -130,8 +130,7 @@ compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass0c0320", - "pciclass0c03", - "loongson, pci-gmac"; + "pciclass0c03"; reg = <0x1800 0x0 0x0 0x0 0x0>; interrupts = <12 IRQ_TYPE_LEVEL_LOW>, diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi index 7c69e8245c2f..cce9428afc41 100644 --- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi +++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi @@ -193,8 +193,7 @@ compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass020000", - "pciclass0200", - "loongson, pci-gmac"; + "pciclass0200"; reg = <0x1800 0x0 0x0 0x0 0x0>; interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 33c09688210f..08ea2cde1eb5 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -422,7 +422,7 @@ static const struct plat_smp_ops octeon_smp_ops = { .cpu_disable = octeon_cpu_disable, .cpu_die = octeon_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; @@ -502,7 +502,7 @@ static const struct plat_smp_ops octeon_78xx_smp_ops = { .cpu_disable = octeon_cpu_disable, .cpu_die = octeon_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; diff --git a/arch/mips/include/asm/kexec.h b/arch/mips/include/asm/kexec.h index d6d5fa5cc31d..69e579e41e66 100644 --- a/arch/mips/include/asm/kexec.h +++ b/arch/mips/include/asm/kexec.h @@ -31,7 +31,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, prepare_frametrace(newregs); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE struct kimage; extern unsigned long kexec_args[4]; extern int (*_machine_kexec_prepare)(struct kimage *); diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h index 5719ff49eff1..0c59e168f800 100644 --- a/arch/mips/include/asm/smp-ops.h +++ b/arch/mips/include/asm/smp-ops.h @@ -35,7 +35,7 @@ struct plat_smp_ops { void (*cpu_die)(unsigned int cpu); void (*cleanup_dead_cpu)(unsigned cpu); #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void (*kexec_nonboot_cpu)(void); #endif }; diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index a40d8c0e4b87..901bc61fa7ae 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -93,7 +93,7 @@ static inline void __cpu_die(unsigned int cpu) extern void __noreturn play_dead(void); #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE static inline void kexec_nonboot_cpu(void) { extern const struct plat_smp_ops *mp_ops; /* private */ diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 853a43ee4b44..ecf3278a32f7 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -90,7 +90,7 @@ obj-$(CONFIG_GPIO_TXX9) += gpio_txx9.o obj-$(CONFIG_RELOCATABLE) += relocate.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_EARLY_PRINTK_8250) += early_printk_8250.o diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index c074ecce3fbf..b3dbf9ecb0d6 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -434,7 +434,7 @@ const struct plat_smp_ops bmips43xx_smp_ops = { .cpu_disable = bmips_cpu_disable, .cpu_die = bmips_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; @@ -451,7 +451,7 @@ const struct plat_smp_ops bmips5000_smp_ops = { .cpu_disable = bmips_cpu_disable, .cpu_die = bmips_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index dd55d59b88db..f6c37d407f36 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -392,7 +392,7 @@ static void cps_smp_finish(void) local_irq_enable(); } -#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC) +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC_CORE) enum cpu_death { CPU_DEATH_HALT, @@ -429,7 +429,7 @@ static void cps_shutdown_this_cpu(enum cpu_death death) } } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE static void cps_kexec_nonboot_cpu(void) { @@ -439,9 +439,9 @@ static void cps_kexec_nonboot_cpu(void) cps_shutdown_this_cpu(CPU_DEATH_POWER); } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ -#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC */ +#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC_CORE */ #ifdef CONFIG_HOTPLUG_CPU @@ -610,7 +610,7 @@ static const struct plat_smp_ops cps_smp_ops = { .cpu_die = cps_cpu_die, .cleanup_dead_cpu = cps_cleanup_dead_cpu, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = cps_kexec_nonboot_cpu, #endif }; diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c index e420800043b0..e01c8d4a805a 100644 --- a/arch/mips/loongson64/reset.c +++ b/arch/mips/loongson64/reset.c @@ -53,7 +53,7 @@ static void loongson_halt(void) } } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* 0X80000000~0X80200000 is safe */ #define MAX_ARGS 64 @@ -158,7 +158,7 @@ static int __init mips_reboot_setup(void) _machine_halt = loongson_halt; pm_power_off = loongson_poweroff; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL); if (WARN_ON(!kexec_argv)) return -ENOMEM; diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index e015a26a40f7..498bdc1bb0ed 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -864,7 +864,7 @@ const struct plat_smp_ops loongson3_smp_ops = { .cpu_disable = loongson3_cpu_disable, .cpu_die = loongson3_cpu_die, #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .kexec_nonboot_cpu = kexec_nonboot_cpu_jump, #endif }; diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 8d3eacb50d56..9d44e6630908 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -301,7 +301,6 @@ CONFIG_WQ_WATCHDOG=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_DEBUG_CREDENTIALS=y # CONFIG_FTRACE is not set CONFIG_XMON=y # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index b1f25bac280b..71d52a670d95 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -385,11 +385,15 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * same fault IRQ is not freed by the OS before. */ mutex_lock(&vas_pseries_mutex); - if (migration_in_progress) + if (migration_in_progress) { rc = -EBUSY; - else + } else { rc = allocate_setup_window(txwin, (u64 *)&domain[0], cop_feat_caps->win_type); + if (!rc) + caps->nr_open_wins_progress++; + } + mutex_unlock(&vas_pseries_mutex); if (rc) goto out; @@ -404,8 +408,17 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, goto out_free; txwin->win_type = cop_feat_caps->win_type; - mutex_lock(&vas_pseries_mutex); + /* + * The migration SUSPEND thread sets migration_in_progress and + * closes all open windows from the list. But the window is + * added to the list after open and modify HCALLs. So possible + * that migration_in_progress is set before modify HCALL which + * may cause some windows are still open when the hypervisor + * initiates the migration. + * So checks the migration_in_progress flag again and close all + * open windows. + * * Possible to lose the acquired credit with DLPAR core * removal after the window is opened. So if there are any * closed windows (means with lost credits), do not give new @@ -413,9 +426,11 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * after the existing windows are reopened when credits are * available. */ - if (!caps->nr_close_wins) { + mutex_lock(&vas_pseries_mutex); + if (!caps->nr_close_wins && !migration_in_progress) { list_add(&txwin->win_list, &caps->list); caps->nr_open_windows++; + caps->nr_open_wins_progress--; mutex_unlock(&vas_pseries_mutex); vas_user_win_add_mm_context(&txwin->vas_win.task_ref); return &txwin->vas_win; @@ -433,6 +448,12 @@ out_free: */ free_irq_setup(txwin); h_deallocate_vas_window(txwin->vas_win.winid); + /* + * Hold mutex and reduce nr_open_wins_progress counter. + */ + mutex_lock(&vas_pseries_mutex); + caps->nr_open_wins_progress--; + mutex_unlock(&vas_pseries_mutex); out: atomic_dec(&cop_feat_caps->nr_used_credits); kfree(txwin); @@ -937,14 +958,14 @@ int vas_migration_handler(int action) struct vas_caps *vcaps; int i, rc = 0; + pr_info("VAS migration event %d\n", action); + /* * NX-GZIP is not enabled. Nothing to do for migration. */ if (!copypaste_feat) return rc; - mutex_lock(&vas_pseries_mutex); - if (action == VAS_SUSPEND) migration_in_progress = true; else @@ -990,12 +1011,27 @@ int vas_migration_handler(int action) switch (action) { case VAS_SUSPEND: + mutex_lock(&vas_pseries_mutex); rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows, true); + /* + * Windows are included in the list after successful + * open. So wait for closing these in-progress open + * windows in vas_allocate_window() which will be + * done if the migration_in_progress is set. + */ + while (vcaps->nr_open_wins_progress) { + mutex_unlock(&vas_pseries_mutex); + msleep(10); + mutex_lock(&vas_pseries_mutex); + } + mutex_unlock(&vas_pseries_mutex); break; case VAS_RESUME: + mutex_lock(&vas_pseries_mutex); atomic_set(&caps->nr_total_credits, new_nr_creds); rc = reconfig_open_windows(vcaps, new_nr_creds, true); + mutex_unlock(&vas_pseries_mutex); break; default: /* should not happen */ @@ -1011,8 +1047,9 @@ int vas_migration_handler(int action) goto out; } + pr_info("VAS migration event (%d) successful\n", action); + out: - mutex_unlock(&vas_pseries_mutex); return rc; } diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 7115043ec488..45567cd13178 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -91,6 +91,8 @@ struct vas_cop_feat_caps { struct vas_caps { struct vas_cop_feat_caps caps; struct list_head list; /* List of open windows */ + int nr_open_wins_progress; /* Number of open windows in */ + /* progress. Used in migration */ int nr_close_wins; /* closed windows in the hypervisor for DLPAR */ int nr_open_windows; /* Number of successful open windows */ u8 feat; /* Feature type */ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 95a2a06acc6a..24c1799e2ec4 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -685,7 +685,7 @@ config RISCV_BOOT_SPINWAIT If unsure what to do here, say N. config ARCH_SUPPORTS_KEXEC - def_bool MMU + def_bool y config ARCH_SELECTS_KEXEC def_bool y @@ -693,7 +693,7 @@ config ARCH_SELECTS_KEXEC select HOTPLUG_CPU if SMP config ARCH_SUPPORTS_KEXEC_FILE - def_bool 64BIT && MMU + def_bool 64BIT config ARCH_SELECTS_KEXEC_FILE def_bool y diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 294044429e8e..ab00235b018f 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -899,7 +899,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL #define TASK_SIZE 0xffffffffUL -#define VMALLOC_START 0 +#define VMALLOC_START _AC(0, UL) #define VMALLOC_END TASK_SIZE #endif /* !CONFIG_MMU */ diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c index 55f1d7856b54..8706736fd4e2 100644 --- a/arch/riscv/kernel/crash_core.c +++ b/arch/riscv/kernel/crash_core.c @@ -5,18 +5,20 @@ void arch_crash_save_vmcoreinfo(void) { - VMCOREINFO_NUMBER(VA_BITS); VMCOREINFO_NUMBER(phys_ram_base); vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START); vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); +#ifdef CONFIG_MMU + VMCOREINFO_NUMBER(VA_BITS); vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); #ifdef CONFIG_64BIT vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); #endif +#endif vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", kernel_map.va_kernel_pa_offset); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 438cd92e6080..dd0608629310 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -834,7 +834,6 @@ CONFIG_DEBUG_IRQFLAGS=y CONFIG_DEBUG_LIST=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 diff --git a/arch/sh/include/asm/kexec.h b/arch/sh/include/asm/kexec.h index 927d80ba2332..76631714673c 100644 --- a/arch/sh/include/asm/kexec.h +++ b/arch/sh/include/asm/kexec.h @@ -28,7 +28,7 @@ /* The native architecture */ #define KEXEC_ARCH KEXEC_ARCH_SH -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* arch/sh/kernel/machine_kexec.c */ void reserve_crashkernel(void); @@ -67,6 +67,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs, } #else static inline void reserve_crashkernel(void) { } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ #endif /* __ASM_SH_KEXEC_H */ diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile index 69cd9ac4b2ab..2d7e70537de0 100644 --- a/arch/sh/kernel/Makefile +++ b/arch/sh/kernel/Makefile @@ -33,7 +33,7 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SH_STANDARD_BIOS) += sh_bios.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_MODULES) += sh_ksyms_32.o module.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_IO_TRAPPED) += io_trapped.o diff --git a/arch/sh/kernel/reboot.c b/arch/sh/kernel/reboot.c index e8eeedc9b182..1de006b1c339 100644 --- a/arch/sh/kernel/reboot.c +++ b/arch/sh/kernel/reboot.c @@ -63,7 +63,7 @@ struct machine_ops machine_ops = { .shutdown = native_machine_shutdown, .restart = native_machine_restart, .halt = native_machine_halt, -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .crash_shutdown = native_machine_crash_shutdown, #endif }; @@ -88,7 +88,7 @@ void machine_halt(void) machine_ops.halt(); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void machine_crash_shutdown(struct pt_regs *regs) { machine_ops.crash_shutdown(regs); diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 3d80515298d2..d3175f09b3aa 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -220,7 +220,7 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn, request_resource(res, &code_resource); request_resource(res, &data_resource); request_resource(res, &bss_resource); -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE request_resource(res, &crashk_res); #endif diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 55c98fdd67d2..18d15d1ce87d 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -178,7 +178,7 @@ static unsigned long get_cmdline_acpi_rsdp(void) { unsigned long addr = 0; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE char val[MAX_ADDR_LEN] = { }; int ret; diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index 4ccf1994b97a..d530384f8d60 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -53,10 +53,12 @@ #define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK) -#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \ - (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ +#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR))) +#define BUTTRESS_ALL_IRQ_MASK (BUTTRESS_IRQ_MASK | \ + (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE))) + #define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK) #define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1) @@ -74,8 +76,12 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) vdev->wa.clear_runtime_mem = false; vdev->wa.d3hot_after_power_off = true; - if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4) + REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK); + if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) { + /* Writing 1s does not clear the interrupt status register */ vdev->wa.interrupt_clear_with_0 = true; + REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, 0x0); + } IVPU_PRINT_WA(punit_disabled); IVPU_PRINT_WA(clear_runtime_mem); diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 94fbc3abe60e..d3c30a28c410 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -449,9 +449,9 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr, struct sk_buff *skb; unsigned int len; - spin_lock(&card->cli_queue_lock); + spin_lock_bh(&card->cli_queue_lock); skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]); - spin_unlock(&card->cli_queue_lock); + spin_unlock_bh(&card->cli_queue_lock); if(skb == NULL) return sprintf(buf, "No data.\n"); @@ -956,14 +956,14 @@ static void pclose(struct atm_vcc *vcc) struct pkt_hdr *header; /* Remove any yet-to-be-transmitted packets from the pending queue */ - spin_lock(&card->tx_queue_lock); + spin_lock_bh(&card->tx_queue_lock); skb_queue_walk_safe(&card->tx_queue[port], skb, tmpskb) { if (SKB_CB(skb)->vcc == vcc) { skb_unlink(skb, &card->tx_queue[port]); solos_pop(vcc, skb); } } - spin_unlock(&card->tx_queue_lock); + spin_unlock_bh(&card->tx_queue_lock); skb = alloc_skb(sizeof(*header), GFP_KERNEL); if (!skb) { diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index ad1acd9b7426..dbc3950c5960 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -767,6 +767,7 @@ config SM_CAMCC_8450 config SM_CAMCC_8550 tristate "SM8550 Camera Clock Controller" + depends on ARM64 || COMPILE_TEST select SM_GCC_8550 help Support for the camera clock controller on SM8550 devices. diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index aa53797dbfc1..75071e0cd321 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -138,7 +138,7 @@ PNAME(mux_pll_src_5plls_p) = { "cpll", "gpll", "gpll_div2", "gpll_div3", "usb480 PNAME(mux_pll_src_4plls_p) = { "cpll", "gpll", "gpll_div2", "usb480m" }; PNAME(mux_pll_src_3plls_p) = { "cpll", "gpll", "gpll_div2" }; -PNAME(mux_aclk_peri_src_p) = { "gpll_peri", "cpll_peri", "gpll_div2_peri", "gpll_div3_peri" }; +PNAME(mux_clk_peri_src_p) = { "gpll", "cpll", "gpll_div2", "gpll_div3" }; PNAME(mux_mmc_src_p) = { "cpll", "gpll", "gpll_div2", "xin24m" }; PNAME(mux_clk_cif_out_src_p) = { "clk_cif_src", "xin24m" }; PNAME(mux_sclk_vop_src_p) = { "cpll", "gpll", "gpll_div2", "gpll_div3" }; @@ -275,23 +275,17 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { RK2928_CLKGATE_CON(0), 11, GFLAGS), /* PD_PERI */ - GATE(0, "gpll_peri", "gpll", CLK_IGNORE_UNUSED, + COMPOSITE(0, "clk_peri_src", mux_clk_peri_src_p, 0, + RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "cpll_peri", "cpll", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "gpll_div2_peri", "gpll_div2", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - GATE(0, "gpll_div3_peri", "gpll_div3", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(2), 0, GFLAGS), - COMPOSITE_NOGATE(0, "aclk_peri_src", mux_aclk_peri_src_p, 0, - RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS), - COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "aclk_peri_src", 0, + + COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "clk_peri_src", 0, RK2928_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO, RK2928_CLKGATE_CON(2), 3, GFLAGS), - COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "aclk_peri_src", 0, + COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "clk_peri_src", 0, RK2928_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO, RK2928_CLKGATE_CON(2), 2, GFLAGS), - GATE(ACLK_PERI, "aclk_peri", "aclk_peri_src", 0, + GATE(ACLK_PERI, "aclk_peri", "clk_peri_src", 0, RK2928_CLKGATE_CON(2), 1, GFLAGS), GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0, @@ -316,7 +310,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(2), 15, GFLAGS), - COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0, + COMPOSITE(SCLK_SDMMC, "sclk_sdmmc", mux_mmc_src_p, 0, RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS, RK2928_CLKGATE_CON(2), 11, GFLAGS), @@ -490,7 +484,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(HCLK_I2S_2CH, "hclk_i2s_2ch", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS), GATE(0, "hclk_usb_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 13, GFLAGS), GATE(HCLK_HOST2, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS), - GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(3), 13, GFLAGS), + GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 13, GFLAGS), GATE(0, "hclk_peri_ahb", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 14, GFLAGS), GATE(HCLK_SPDIF, "hclk_spdif", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 9, GFLAGS), GATE(HCLK_TSP, "hclk_tsp", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 12, GFLAGS), diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c index 16dabe2b9c47..db713e1526cd 100644 --- a/drivers/clk/rockchip/clk-rk3568.c +++ b/drivers/clk/rockchip/clk-rk3568.c @@ -72,6 +72,7 @@ static struct rockchip_pll_rate_table rk3568_pll_rates[] = { RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0), RK3036_PLL_RATE(312000000, 1, 78, 6, 1, 1, 0), RK3036_PLL_RATE(297000000, 2, 99, 4, 1, 1, 0), + RK3036_PLL_RATE(292500000, 1, 195, 4, 4, 1, 0), RK3036_PLL_RATE(241500000, 2, 161, 4, 2, 1, 0), RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0), RK3036_PLL_RATE(200000000, 1, 100, 3, 4, 1, 0), diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 1cc9be85ba4c..7d97790b893d 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -363,10 +363,9 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled) { resource_size_t base = -1; - down_read(&cxl_dpa_rwsem); + lockdep_assert_held(&cxl_dpa_rwsem); if (cxled->dpa_res) base = cxled->dpa_res->start; - up_read(&cxl_dpa_rwsem); return base; } @@ -839,6 +838,8 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, cxld->target_type = CXL_DECODER_HOSTONLYMEM; else cxld->target_type = CXL_DECODER_DEVMEM; + + guard(rwsem_write)(&cxl_region_rwsem); if (cxld->id != cxl_num_decoders_committed(port)) { dev_warn(&port->dev, "decoder%d.%d: Committed out of order\n", diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index fc5c2b414793..2f43d368ba07 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -227,10 +227,16 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) if (!port || !is_cxl_endpoint(port)) return -EINVAL; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + if (cxl_num_decoders_committed(port) == 0) { /* No regions mapped to this memdev */ rc = cxl_get_poison_by_memdev(cxlmd); @@ -239,6 +245,7 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) rc = cxl_get_poison_by_endpoint(port); } up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } @@ -324,10 +331,16 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) goto out; @@ -355,6 +368,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT); out: up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } @@ -372,10 +386,16 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) goto out; @@ -412,6 +432,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR); out: up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index eff20e83d0a6..37e1652afbc7 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -620,7 +620,7 @@ void read_cdat_data(struct cxl_port *port) struct pci_dev *pdev = NULL; struct cxl_memdev *cxlmd; size_t cdat_length; - void *cdat_table; + void *cdat_table, *cdat_buf; int rc; if (is_cxl_memdev(uport)) { @@ -651,16 +651,15 @@ void read_cdat_data(struct cxl_port *port) return; } - cdat_table = devm_kzalloc(dev, cdat_length + sizeof(__le32), - GFP_KERNEL); - if (!cdat_table) + cdat_buf = devm_kzalloc(dev, cdat_length + sizeof(__le32), GFP_KERNEL); + if (!cdat_buf) return; - rc = cxl_cdat_read_table(dev, cdat_doe, cdat_table, &cdat_length); + rc = cxl_cdat_read_table(dev, cdat_doe, cdat_buf, &cdat_length); if (rc) goto err; - cdat_table = cdat_table + sizeof(__le32); + cdat_table = cdat_buf + sizeof(__le32); if (cdat_checksum(cdat_table, cdat_length)) goto err; @@ -670,7 +669,7 @@ void read_cdat_data(struct cxl_port *port) err: /* Don't leave table data allocated on error */ - devm_kfree(dev, cdat_table); + devm_kfree(dev, cdat_buf); dev_err(dev, "Failed to read/validate CDAT.\n"); } EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL); diff --git a/drivers/cxl/core/pmu.c b/drivers/cxl/core/pmu.c index 7684c843e5a5..5d8e06b0ba6e 100644 --- a/drivers/cxl/core/pmu.c +++ b/drivers/cxl/core/pmu.c @@ -23,7 +23,7 @@ const struct device_type cxl_pmu_type = { static void remove_dev(void *dev) { - device_del(dev); + device_unregister(dev); } int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs, diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 38441634e4c6..b7c93bb18f6e 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -226,9 +226,9 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at char *buf) { struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev); - u64 base = cxl_dpa_resource_start(cxled); - return sysfs_emit(buf, "%#llx\n", base); + guard(rwsem_read)(&cxl_dpa_rwsem); + return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled)); } static DEVICE_ATTR_RO(dpa_resource); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 56e575c79bb4..3e817a6f94c6 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -2467,10 +2467,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port) struct cxl_poison_context ctx; int rc = 0; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) - return rc; - ctx = (struct cxl_poison_context) { .port = port }; @@ -2480,7 +2476,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port) rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport_dev), &ctx); - up_read(&cxl_region_rwsem); return rc; } diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 6a3abe5b1790..b53f46245c37 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -828,6 +828,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan) dma_pool_destroy(fsl_chan->tcd_pool); fsl_chan->tcd_pool = NULL; fsl_chan->is_sw = false; + fsl_chan->srcid = 0; } void fsl_edma_cleanup_vchan(struct dma_device *dmadev) diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 4635e16d7705..238a69bd0d6f 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -396,9 +396,8 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (IS_ERR(link)) { - dev_err(dev, "Failed to add device_link to %d: %ld\n", i, - PTR_ERR(link)); + if (!link) { + dev_err(dev, "Failed to add device_link to %d\n", i); return -EINVAL; } @@ -631,6 +630,8 @@ static int fsl_edma_suspend_late(struct device *dev) for (i = 0; i < fsl_edma->n_chans; i++) { fsl_chan = &fsl_edma->chans[i]; + if (fsl_edma->chan_masked & BIT(i)) + continue; spin_lock_irqsave(&fsl_chan->vchan.lock, flags); /* Make sure chan is idle or will force disable. */ if (unlikely(!fsl_chan->idle)) { @@ -655,13 +656,16 @@ static int fsl_edma_resume_early(struct device *dev) for (i = 0; i < fsl_edma->n_chans; i++) { fsl_chan = &fsl_edma->chans[i]; + if (fsl_edma->chan_masked & BIT(i)) + continue; fsl_chan->pm_state = RUNNING; edma_write_tcdreg(fsl_chan, 0, csr); if (fsl_chan->slave_id != 0) fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true); } - edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr); + if (!(fsl_edma->drvdata->flags & FSL_EDMA_DRV_SPLIT_REG)) + edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr); return 0; } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 7b54a3939ea1..315c004f58e4 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -440,12 +440,14 @@ union wqcfg { /* * This macro calculates the offset into the GRPCFG register * idxd - struct idxd * - * n - wq id - * ofs - the index of the 32b dword for the config register + * n - group id + * ofs - the index of the 64b qword for the config register * - * The WQCFG register block is divided into groups per each wq. The n index - * allows us to move to the register group that's for that particular wq. - * Each register is 32bits. The ofs gives us the number of register to access. + * The GRPCFG register block is divided into three sub-registers, which + * are GRPWQCFG, GRPENGCFG and GRPFLGCFG. The n index allows us to move + * to the register block that contains the three sub-registers. + * Each register block is 64bits. And the ofs gives us the offset + * within the GRPWQCFG register to access. */ #define GRPWQCFG_OFFSET(idxd_dev, n, ofs) ((idxd_dev)->grpcfg_offset +\ (n) * GRPCFG_SIZE + sizeof(u64) * (ofs)) diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index c01db23e3333..3f922518e3a5 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -183,13 +183,6 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) portal = idxd_wq_portal_addr(wq); /* - * The wmb() flushes writes to coherent DMA data before - * possibly triggering a DMA read. The wmb() is necessary - * even on UP because the recipient is a device. - */ - wmb(); - - /* * Pending the descriptor to the lockless list for the irq_entry * that we designated the descriptor to. */ @@ -199,6 +192,13 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) llist_add(&desc->llnode, &ie->pending_llist); } + /* + * The wmb() flushes writes to coherent DMA data before + * possibly triggering a DMA read. The wmb() is necessary + * even on UP because the recipient is a device. + */ + wmb(); + if (wq_dedicated(wq)) { iosubmit_cmds512(portal, desc->hw, 1); } else { diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 72d83cd9ed6b..90857d08a1a7 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -1246,8 +1246,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy( enum dma_slave_buswidth max_width; struct stm32_dma_desc *desc; size_t xfer_count, offset; - u32 num_sgs, best_burst, dma_burst, threshold; - int i; + u32 num_sgs, best_burst, threshold; + int dma_burst, i; num_sgs = DIV_ROUND_UP(len, STM32_DMA_ALIGNED_MAX_DATA_ITEMS); desc = kzalloc(struct_size(desc, sg_req, num_sgs), GFP_NOWAIT); @@ -1266,6 +1266,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy( best_burst = stm32_dma_get_best_burst(len, STM32_DMA_MAX_BURST, threshold, max_width); dma_burst = stm32_dma_get_burst(chan, best_burst); + if (dma_burst < 0) { + kfree(desc); + return NULL; + } stm32_dma_clear_reg(&desc->sg_req[i].chan_reg); desc->sg_req[i].chan_reg.dma_scr = diff --git a/drivers/dma/ti/k3-psil-am62.c b/drivers/dma/ti/k3-psil-am62.c index 2b6fd6e37c61..1272b1541f61 100644 --- a/drivers/dma/ti/k3-psil-am62.c +++ b/drivers/dma/ti/k3-psil-am62.c @@ -74,7 +74,9 @@ static struct psil_ep am62_src_ep_map[] = { PSIL_SAUL(0x7505, 21, 35, 8, 36, 0), PSIL_SAUL(0x7506, 22, 43, 8, 43, 0), PSIL_SAUL(0x7507, 23, 43, 8, 44, 0), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0x4300), + PSIL_PDMA_XY_PKT(0x4301), PSIL_PDMA_XY_PKT(0x4302), PSIL_PDMA_XY_PKT(0x4303), PSIL_PDMA_XY_PKT(0x4304), @@ -85,8 +87,6 @@ static struct psil_ep am62_src_ep_map[] = { PSIL_PDMA_XY_PKT(0x4309), PSIL_PDMA_XY_PKT(0x430a), PSIL_PDMA_XY_PKT(0x430b), - PSIL_PDMA_XY_PKT(0x430c), - PSIL_PDMA_XY_PKT(0x430d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0x4400), PSIL_PDMA_XY_PKT(0x4401), @@ -141,7 +141,9 @@ static struct psil_ep am62_dst_ep_map[] = { /* SAUL */ PSIL_SAUL(0xf500, 27, 83, 8, 83, 1), PSIL_SAUL(0xf501, 28, 91, 8, 91, 1), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0xc300), + PSIL_PDMA_XY_PKT(0xc301), PSIL_PDMA_XY_PKT(0xc302), PSIL_PDMA_XY_PKT(0xc303), PSIL_PDMA_XY_PKT(0xc304), @@ -152,8 +154,6 @@ static struct psil_ep am62_dst_ep_map[] = { PSIL_PDMA_XY_PKT(0xc309), PSIL_PDMA_XY_PKT(0xc30a), PSIL_PDMA_XY_PKT(0xc30b), - PSIL_PDMA_XY_PKT(0xc30c), - PSIL_PDMA_XY_PKT(0xc30d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0xc400), PSIL_PDMA_XY_PKT(0xc401), diff --git a/drivers/dma/ti/k3-psil-am62a.c b/drivers/dma/ti/k3-psil-am62a.c index ca9d71f91422..4cf9123b0e93 100644 --- a/drivers/dma/ti/k3-psil-am62a.c +++ b/drivers/dma/ti/k3-psil-am62a.c @@ -84,7 +84,9 @@ static struct psil_ep am62a_src_ep_map[] = { PSIL_SAUL(0x7505, 21, 35, 8, 36, 0), PSIL_SAUL(0x7506, 22, 43, 8, 43, 0), PSIL_SAUL(0x7507, 23, 43, 8, 44, 0), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0x4300), + PSIL_PDMA_XY_PKT(0x4301), PSIL_PDMA_XY_PKT(0x4302), PSIL_PDMA_XY_PKT(0x4303), PSIL_PDMA_XY_PKT(0x4304), @@ -95,8 +97,6 @@ static struct psil_ep am62a_src_ep_map[] = { PSIL_PDMA_XY_PKT(0x4309), PSIL_PDMA_XY_PKT(0x430a), PSIL_PDMA_XY_PKT(0x430b), - PSIL_PDMA_XY_PKT(0x430c), - PSIL_PDMA_XY_PKT(0x430d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0x4400), PSIL_PDMA_XY_PKT(0x4401), @@ -151,7 +151,9 @@ static struct psil_ep am62a_dst_ep_map[] = { /* SAUL */ PSIL_SAUL(0xf500, 27, 83, 8, 83, 1), PSIL_SAUL(0xf501, 28, 91, 8, 91, 1), - /* PDMA_MAIN0 - SPI0-3 */ + /* PDMA_MAIN0 - SPI0-2 */ + PSIL_PDMA_XY_PKT(0xc300), + PSIL_PDMA_XY_PKT(0xc301), PSIL_PDMA_XY_PKT(0xc302), PSIL_PDMA_XY_PKT(0xc303), PSIL_PDMA_XY_PKT(0xc304), @@ -162,8 +164,6 @@ static struct psil_ep am62a_dst_ep_map[] = { PSIL_PDMA_XY_PKT(0xc309), PSIL_PDMA_XY_PKT(0xc30a), PSIL_PDMA_XY_PKT(0xc30b), - PSIL_PDMA_XY_PKT(0xc30c), - PSIL_PDMA_XY_PKT(0xc30d), /* PDMA_MAIN1 - UART0-6 */ PSIL_PDMA_XY_PKT(0xc400), PSIL_PDMA_XY_PKT(0xc401), diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 442a0ebeb953..ce7cf736f020 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -925,7 +925,6 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest, struct netlink_ext_ack *extack) { struct nlattr *tb[DPLL_A_PIN_MAX + 1]; - enum dpll_pin_state state; u32 ppin_idx; int ret; @@ -936,10 +935,14 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest, return -EINVAL; } ppin_idx = nla_get_u32(tb[DPLL_A_PIN_PARENT_ID]); - state = nla_get_u32(tb[DPLL_A_PIN_STATE]); - ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack); - if (ret) - return ret; + + if (tb[DPLL_A_PIN_STATE]) { + enum dpll_pin_state state = nla_get_u32(tb[DPLL_A_PIN_STATE]); + + ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack); + if (ret) + return ret; + } return 0; } diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c index 87e730dfefa0..8625de20fc71 100644 --- a/drivers/edac/versal_edac.c +++ b/drivers/edac/versal_edac.c @@ -966,10 +966,10 @@ static int mc_probe(struct platform_device *pdev) edac_mc_id = emif_get_id(pdev->dev.of_node); regval = readl(ddrmc_baseaddr + XDDR_REG_CONFIG0_OFFSET); - num_chans = FIELD_PREP(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval); + num_chans = FIELD_GET(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval); num_chans++; - num_csrows = FIELD_PREP(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval); + num_csrows = FIELD_GET(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval); num_csrows *= 2; if (!num_csrows) num_csrows = 1; diff --git a/drivers/firmware/efi/libstub/loongarch-stub.c b/drivers/firmware/efi/libstub/loongarch-stub.c index 72c71ae201f0..d6ec5d4b8dbe 100644 --- a/drivers/firmware/efi/libstub/loongarch-stub.c +++ b/drivers/firmware/efi/libstub/loongarch-stub.c @@ -35,9 +35,9 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, return status; } -unsigned long kernel_entry_address(void) +unsigned long kernel_entry_address(unsigned long kernel_addr) { unsigned long base = (unsigned long)&kernel_offset - kernel_offset; - return (unsigned long)&kernel_entry - base + VMLINUX_LOAD_ADDRESS; + return (unsigned long)&kernel_entry - base + kernel_addr; } diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c index 807cba2693fc..0e0aa6cda73f 100644 --- a/drivers/firmware/efi/libstub/loongarch.c +++ b/drivers/firmware/efi/libstub/loongarch.c @@ -37,9 +37,9 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv) return EFI_SUCCESS; } -unsigned long __weak kernel_entry_address(void) +unsigned long __weak kernel_entry_address(unsigned long kernel_addr) { - return *(unsigned long *)(PHYSADDR(VMLINUX_LOAD_ADDRESS) + 8); + return *(unsigned long *)(kernel_addr + 8) - VMLINUX_LOAD_ADDRESS + kernel_addr; } efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image, @@ -73,7 +73,7 @@ efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image, csr_write64(CSR_DMW0_INIT, LOONGARCH_CSR_DMWIN0); csr_write64(CSR_DMW1_INIT, LOONGARCH_CSR_DMWIN1); - real_kernel_entry = (void *)kernel_entry_address(); + real_kernel_entry = (void *)kernel_entry_address(kernel_addr); real_kernel_entry(true, (unsigned long)cmdline_ptr, (unsigned long)efi_system_table); diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 1bfdae34df39..da9b7b8d0716 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -307,17 +307,20 @@ static void setup_unaccepted_memory(void) efi_err("Memory acceptance protocol failed\n"); } +static efi_char16_t *efistub_fw_vendor(void) +{ + unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor); + + return (efi_char16_t *)vendor; +} + static const efi_char16_t apple[] = L"Apple"; static void setup_quirks(struct boot_params *boot_params) { - efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table, fw_vendor); - - if (!memcmp(fw_vendor, apple, sizeof(apple))) { - if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) - retrieve_apple_device_properties(boot_params); - } + if (IS_ENABLED(CONFIG_APPLE_PROPERTIES) && + !memcmp(efistub_fw_vendor(), apple, sizeof(apple))) + retrieve_apple_device_properties(boot_params); } /* @@ -765,11 +768,25 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) { u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size; + static const efi_char16_t ami[] = L"American Megatrends"; efi_get_seed(seed, sizeof(seed)); virt_addr += (range * seed[1]) >> 32; virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1); + + /* + * Older Dell systems with AMI UEFI firmware v2.0 may hang + * while decompressing the kernel if physical address + * randomization is enabled. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=218173 + */ + if (efi_system_table->hdr.revision <= EFI_2_00_SYSTEM_TABLE_REVISION && + !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) { + efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n"); + seed[0] = 0; + } } status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 1f64d8cbb14d..8dee52ce26d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4516,8 +4516,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) amdgpu_ras_suspend(adev); - amdgpu_ttm_set_buffer_funcs_status(adev, false); - amdgpu_device_ip_suspend_phase1(adev); if (!adev->in_s0ix) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index d79b4ca1ecfc..5ad03f2afdb4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1343,6 +1343,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) abo = ttm_to_amdgpu_bo(bo); + WARN_ON(abo->vm_bo); + if (abo->kfd_bo) amdgpu_amdkfd_release_notify(abo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index a2287bb25223..a160265ddc07 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -642,13 +642,14 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) if (!entry->bo) return; + + entry->bo->vm_bo = NULL; shadow = amdgpu_bo_shadowed(entry->bo); if (shadow) { ttm_bo_set_bulk_move(&shadow->tbo, NULL); amdgpu_bo_unref(&shadow); } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); - entry->bo->vm_bo = NULL; spin_lock(&entry->vm->status_lock); list_del(&entry->vm_status); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index 9df011323d4b..6ede85b28cc8 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -155,13 +155,6 @@ static int jpeg_v4_0_5_hw_init(void *handle) struct amdgpu_ring *ring = adev->jpeg.inst->ring_dec; int r; - adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell, - (adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0); - - WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL, - ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT | - VCN_JPEG_DB_CTRL__EN_MASK); - r = amdgpu_ring_test_helper(ring); if (r) return r; @@ -336,6 +329,14 @@ static int jpeg_v4_0_5_start(struct amdgpu_device *adev) if (adev->pm.dpm_enabled) amdgpu_dpm_enable_jpeg(adev, true); + /* doorbell programming is done for every playback */ + adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell, + (adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0); + + WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL, + ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT | + VCN_JPEG_DB_CTRL__EN_MASK); + /* disable power gating */ r = jpeg_v4_0_5_disable_static_power_gating(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 45377a175250..8d5d86675a7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -813,12 +813,12 @@ static int sdma_v2_4_early_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; + adev->sdma.num_instances = SDMA_MAX_INSTANCE; + r = sdma_v2_4_init_microcode(adev); if (r) return r; - adev->sdma.num_instances = SDMA_MAX_INSTANCE; - sdma_v2_4_set_ring_funcs(adev); sdma_v2_4_set_buffer_funcs(adev); sdma_v2_4_set_vm_pte_funcs(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 83c240f741b5..0058f3f7cf6e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1643,6 +1643,32 @@ static void sdma_v5_2_get_clockgating_state(void *handle, u64 *flags) *flags |= AMD_CG_SUPPORT_SDMA_LS; } +static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + /* SDMA 5.2.3 (RMB) FW doesn't seem to properly + * disallow GFXOFF in some cases leading to + * hangs in SDMA. Disallow GFXOFF while SDMA is active. + * We can probably just limit this to 5.2.3, + * but it shouldn't hurt for other parts since + * this GFXOFF will be disallowed anyway when SDMA is + * active, this just makes it explicit. + */ + amdgpu_gfx_off_ctrl(adev, false); +} + +static void sdma_v5_2_ring_end_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + /* SDMA 5.2.3 (RMB) FW doesn't seem to properly + * disallow GFXOFF in some cases leading to + * hangs in SDMA. Allow GFXOFF when SDMA is complete. + */ + amdgpu_gfx_off_ctrl(adev, true); +} + const struct amd_ip_funcs sdma_v5_2_ip_funcs = { .name = "sdma_v5_2", .early_init = sdma_v5_2_early_init, @@ -1690,6 +1716,8 @@ static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = { .test_ib = sdma_v5_2_ring_test_ib, .insert_nop = sdma_v5_2_ring_insert_nop, .pad_ib = sdma_v5_2_ring_pad_ib, + .begin_use = sdma_v5_2_ring_begin_use, + .end_use = sdma_v5_2_ring_end_use, .emit_wreg = sdma_v5_2_ring_emit_wreg, .emit_reg_wait = sdma_v5_2_ring_emit_reg_wait, .emit_reg_write_reg_wait = sdma_v5_2_ring_emit_reg_write_reg_wait, 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 b452796fc6d3..c8c00c2a5224 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5182,6 +5182,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, if (plane->type == DRM_PLANE_TYPE_CURSOR) return; + if (new_plane_state->rotation != DRM_MODE_ROTATE_0) + goto ffu; + num_clips = drm_plane_get_damage_clips_count(new_plane_state); clips = drm_plane_get_damage_clips(new_plane_state); diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 9649934ea186..e2a3aa8812df 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -465,6 +465,7 @@ struct dc_cursor_mi_param { struct fixed31_32 v_scale_ratio; enum dc_rotation_angle rotation; bool mirror; + struct dc_stream_state *stream; }; /* IPP related types */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 139cf31d2e45..89c3bf0fe0c9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1077,8 +1077,16 @@ void hubp2_cursor_set_position( if (src_y_offset < 0) src_y_offset = 0; /* Save necessary cursor info x, y position. w, h is saved in attribute func. */ - hubp->cur_rect.x = src_x_offset + param->viewport.x; - hubp->cur_rect.y = src_y_offset + param->viewport.y; + if (param->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 && + param->rotation != ROTATION_ANGLE_0) { + hubp->cur_rect.x = 0; + hubp->cur_rect.y = 0; + hubp->cur_rect.w = param->stream->timing.h_addressable; + hubp->cur_rect.h = param->stream->timing.v_addressable; + } else { + hubp->cur_rect.x = src_x_offset + param->viewport.x; + hubp->cur_rect.y = src_y_offset + param->viewport.y; + } } void hubp2_clk_cntl(struct hubp *hubp, bool enable) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index 39cf1ae3a3e1..f154a3eb1d1a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -124,7 +124,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 600.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 186.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, { .state = 1, @@ -133,7 +133,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 209.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, { .state = 2, @@ -142,7 +142,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 209.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, { .state = 3, @@ -151,7 +151,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 371.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, { .state = 4, @@ -160,7 +160,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, .dscclk_mhz = 417.0, - .dtbclk_mhz = 625.0, + .dtbclk_mhz = 600.0, }, }, .num_states = 5, @@ -348,6 +348,8 @@ void dcn35_update_bw_bounding_box_fpu(struct dc *dc, clock_limits[i].socclk_mhz; dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz = clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio; + dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz = + clock_limits[i].dtbclk_mhz; dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels = clk_table->num_entries; dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels = @@ -360,6 +362,8 @@ void dcn35_update_bw_bounding_box_fpu(struct dc *dc, clk_table->num_entries; dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels = clk_table->num_entries; + dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels = + clk_table->num_entries; } } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c index 4d1336e5afc2..180f8a98a361 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c @@ -6329,7 +6329,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib) mode_lib->ms.NoOfDPPThisState, mode_lib->ms.dpte_group_bytes, s->HostVMInefficiencyFactor, - mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, + mode_lib->ms.soc.hostvm_min_page_size_kbytes, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels); s->NextMaxVStartup = s->MaxVStartupAllPlanes[j]; @@ -6542,7 +6542,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib) mode_lib->ms.cache_display_cfg.plane.HostVMEnable, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels, mode_lib->ms.cache_display_cfg.plane.GPUVMEnable, - mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, + mode_lib->ms.soc.hostvm_min_page_size_kbytes, mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k], mode_lib->ms.MetaRowBytes[j][k], mode_lib->ms.DPTEBytesPerRow[j][k], @@ -7687,7 +7687,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib) CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes; - CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; + CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn; CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode; CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = mode_lib->ms.PTEBufferSizeNotExceededPerState; @@ -7957,7 +7957,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib) UseMinimumDCFCLK_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; UseMinimumDCFCLK_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable; UseMinimumDCFCLK_params->NumberOfActiveSurfaces = mode_lib->ms.num_active_planes; - UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; + UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; UseMinimumDCFCLK_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; UseMinimumDCFCLK_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled; UseMinimumDCFCLK_params->ImmediateFlipRequirement = s->ImmediateFlipRequiredFinal; @@ -8699,7 +8699,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels; CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes; - CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; + CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn; CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode; CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = s->dummy_boolean_array[0]; @@ -8805,7 +8805,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc mode_lib->ms.cache_display_cfg.hw.DPPPerSurface, locals->dpte_group_bytes, s->HostVMInefficiencyFactor, - mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, + mode_lib->ms.soc.hostvm_min_page_size_kbytes, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels); locals->TCalc = 24.0 / locals->DCFCLKDeepSleep; @@ -8995,7 +8995,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable; CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable; CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels; - CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024; + CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes; CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k]; CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled; CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k]; @@ -9240,7 +9240,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc mode_lib->ms.cache_display_cfg.plane.HostVMEnable, mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels, mode_lib->ms.cache_display_cfg.plane.GPUVMEnable, - mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024, + mode_lib->ms.soc.hostvm_min_page_size_kbytes, locals->PDEAndMetaPTEBytesFrame[k], locals->MetaRowByte[k], locals->PixelPTEBytesPerRow[k], diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index fa8fe5bf7e57..db06a5b749b4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -423,8 +423,9 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc, } for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels; i++) { - p->in_states->state_array[i].dtbclk_mhz = - dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz; + if (dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz > 0) + p->in_states->state_array[i].dtbclk_mhz = + dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz; } for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dispclk_levels; i++) { diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 2b8b8366538e..cdb903116eb7 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -3417,7 +3417,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz, .v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert, .rotation = pipe_ctx->plane_state->rotation, - .mirror = pipe_ctx->plane_state->horizontal_mirror + .mirror = pipe_ctx->plane_state->horizontal_mirror, + .stream = pipe_ctx->stream, }; bool pipe_split_on = false; bool odm_combine_on = (pipe_ctx->next_odm_pipe != NULL) || diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index 996e4ee99023..e5cfaaef70b3 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -287,8 +287,8 @@ bool set_default_brightness_aux(struct dc_link *link) if (link && link->dpcd_sink_ext_caps.bits.oled == 1) { if (!read_default_bl_aux(link, &default_backlight)) default_backlight = 150000; - // if > 5000, it might be wrong readback - if (default_backlight > 5000000) + // if < 1 nits or > 5000, it might be wrong readback + if (default_backlight < 1000 || default_backlight > 5000000) default_backlight = 150000; return edp_set_backlight_level_nits(link, true, diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index a522a7c02911..1675314a3ff2 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -839,6 +839,8 @@ bool is_psr_su_specific_panel(struct dc_link *link) ((dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x08) || (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x07))) isPSRSUSupported = false; + else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03) + isPSRSUSupported = false; else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1) isPSRSUSupported = true; } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index ca2ece24e1e0..49028dde0f87 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2198,10 +2198,10 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ } else if (DEVICE_ATTR_IS(xgmi_plpd_policy)) { if (amdgpu_dpm_get_xgmi_plpd_mode(adev, NULL) == XGMI_PLPD_NONE) *states = ATTR_STATE_UNSUPPORTED; - } else if (DEVICE_ATTR_IS(pp_dpm_mclk_od)) { + } else if (DEVICE_ATTR_IS(pp_mclk_od)) { if (amdgpu_dpm_get_mclk_od(adev) == -EOPNOTSUPP) *states = ATTR_STATE_UNSUPPORTED; - } else if (DEVICE_ATTR_IS(pp_dpm_sclk_od)) { + } else if (DEVICE_ATTR_IS(pp_sclk_od)) { if (amdgpu_dpm_get_sclk_od(adev) == -EOPNOTSUPP) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(apu_thermal_cap)) { diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index 2ed2585ded37..6899b3dc1f12 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -236,7 +236,7 @@ static int drm_master_check_perm(struct drm_device *dev, struct drm_file *file_priv) { if (file_priv->was_master && - rcu_access_pointer(file_priv->pid) == task_pid(current)) + rcu_access_pointer(file_priv->pid) == task_tgid(current)) return 0; if (!capable(CAP_SYS_ADMIN)) diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index df9bf3c9206e..cb90e70d85e8 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -715,8 +715,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, struct drm_mode_set set; uint32_t __user *set_connectors_ptr; struct drm_modeset_acquire_ctx ctx; - int ret; - int i; + int ret, i, num_connectors = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; @@ -871,6 +870,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, connector->name); connector_set[i] = connector; + num_connectors++; } } @@ -879,7 +879,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, set.y = crtc_req->y; set.mode = mode; set.connectors = connector_set; - set.num_connectors = crtc_req->count_connectors; + set.num_connectors = num_connectors; set.fb = fb; if (drm_drv_uses_atomic_modeset(dev)) @@ -892,7 +892,7 @@ out: drm_framebuffer_put(fb); if (connector_set) { - for (i = 0; i < crtc_req->count_connectors; i++) { + for (i = 0; i < num_connectors; i++) { if (connector_set[i]) drm_connector_put(connector_set[i]); } diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 39db08f803ea..3b4065099872 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -2309,7 +2309,8 @@ int drm_edid_override_connector_update(struct drm_connector *connector) override = drm_edid_override_get(connector); if (override) { - num_modes = drm_edid_connector_update(connector, override); + if (drm_edid_connector_update(connector, override) == 0) + num_modes = drm_edid_connector_add_modes(connector); drm_edid_free(override); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index dbc1b66c8ee4..1abfafbbfa75 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -650,19 +650,30 @@ intel_dp_update_link_bw_set(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, u8 link_bw, u8 rate_select) { - u8 link_config[2]; + u8 lane_count = crtc_state->lane_count; - /* Write the link configuration data */ - link_config[0] = link_bw; - link_config[1] = crtc_state->lane_count; if (crtc_state->enhanced_framing) - link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; - drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2); + lane_count |= DP_LANE_COUNT_ENHANCED_FRAME_EN; + + if (link_bw) { + /* DP and eDP v1.3 and earlier link bw set method. */ + u8 link_config[] = { link_bw, lane_count }; - /* eDP 1.4 rate select method. */ - if (!link_bw) - drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET, - &rate_select, 1); + drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, + ARRAY_SIZE(link_config)); + } else { + /* + * eDP v1.4 and later link rate set method. + * + * eDP v1.4x sinks shall ignore DP_LINK_RATE_SET if + * DP_LINK_BW_SET is set. Avoid writing DP_LINK_BW_SET. + * + * eDP v1.5 sinks allow choosing either, and the last choice + * shall be active. + */ + drm_dp_dpcd_writeb(&intel_dp->aux, DP_LANE_COUNT_SET, lane_count); + drm_dp_dpcd_writeb(&intel_dp->aux, DP_LINK_RATE_SET, rate_select); + } } /* diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index 19b35ece31f1..646f367a13f5 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -1374,7 +1374,8 @@ plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane, struct drm_i915_private *i915 = to_i915(fb->base.dev); unsigned int stride_tiles; - if (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) + if ((IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) && + src_stride_tiles < dst_stride_tiles) stride_tiles = src_stride_tiles; else stride_tiles = dst_stride_tiles; @@ -1501,8 +1502,20 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p size += remap_info->size; } else { - unsigned int dst_stride = plane_view_dst_stride_tiles(fb, color_plane, - remap_info->width); + unsigned int dst_stride; + + /* + * The hardware automagically calculates the CCS AUX surface + * stride from the main surface stride so can't really remap a + * smaller subset (unless we'd remap in whole AUX page units). + */ + if (intel_fb_needs_pot_stride_remap(fb) && + intel_fb_is_ccs_modifier(fb->base.modifier)) + dst_stride = remap_info->src_stride; + else + dst_stride = remap_info->width; + + dst_stride = plane_view_dst_stride_tiles(fb, color_plane, dst_stride); assign_chk_ovf(i915, remap_info->dst_stride, dst_stride); color_plane_info->mapping_stride = dst_stride * diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 1e7c97243fcf..8a934bada624 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -504,7 +504,6 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, { struct drm_plane *plane = NULL; struct intel_plane *intel_plane; - struct intel_plane_state *plane_state = NULL; struct intel_crtc_scaler_state *scaler_state = &crtc_state->scaler_state; struct drm_atomic_state *drm_state = crtc_state->uapi.state; @@ -536,6 +535,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, /* walkthrough scaler_users bits and start assigning scalers */ for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) { + struct intel_plane_state *plane_state = NULL; int *scaler_id; const char *name; int idx, ret; diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index d5ed904f355d..6801f8b95c53 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -1293,7 +1293,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg) if (msg) drm_notice(&engine->i915->drm, "Resetting %s for %s\n", engine->name, msg); - atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]); + i915_increase_reset_engine_count(&engine->i915->gpu_error, engine); ret = intel_gt_reset_engine(engine); if (ret) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index d37698bd6b91..17df71117cc7 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -5001,7 +5001,8 @@ static void capture_error_state(struct intel_guc *guc, if (match) { intel_engine_set_hung_context(e, ce); engine_mask |= e->mask; - atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]); + i915_increase_reset_engine_count(&i915->gpu_error, + e); } } @@ -5013,7 +5014,7 @@ static void capture_error_state(struct intel_guc *guc, } else { intel_engine_set_hung_context(ce->engine, ce); engine_mask = ce->engine->mask; - atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]); + i915_increase_reset_engine_count(&i915->gpu_error, ce->engine); } with_intel_runtime_pm(&i915->runtime_pm, wakeref) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 9f5971f5e980..48f6c00402c4 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -16,6 +16,7 @@ #include "display/intel_display_device.h" #include "gt/intel_engine.h" +#include "gt/intel_engine_types.h" #include "gt/intel_gt_types.h" #include "gt/uc/intel_uc_fw.h" @@ -232,7 +233,7 @@ struct i915_gpu_error { atomic_t reset_count; /** Number of times an engine has been reset */ - atomic_t reset_engine_count[I915_NUM_ENGINES]; + atomic_t reset_engine_count[MAX_ENGINE_CLASS]; }; struct drm_i915_error_state_buf { @@ -255,7 +256,14 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error) static inline u32 i915_reset_engine_count(struct i915_gpu_error *error, const struct intel_engine_cs *engine) { - return atomic_read(&error->reset_engine_count[engine->uabi_class]); + return atomic_read(&error->reset_engine_count[engine->class]); +} + +static inline void +i915_increase_reset_engine_count(struct i915_gpu_error *error, + const struct intel_engine_cs *engine) +{ + atomic_inc(&error->reset_engine_count[engine->class]); } #define CORE_DUMP_FLAG_NONE 0x0 diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c index 4ddc6d902752..7d41874a49c5 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.c +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c @@ -37,8 +37,9 @@ int igt_live_test_begin(struct igt_live_test *t, } for_each_engine(engine, gt, id) - t->reset_engine[id] = - i915_reset_engine_count(&i915->gpu_error, engine); + t->reset_engine[i][id] = + i915_reset_engine_count(&i915->gpu_error, + engine); } t->reset_global = i915_reset_count(&i915->gpu_error); @@ -66,14 +67,14 @@ int igt_live_test_end(struct igt_live_test *t) for_each_gt(gt, i915, i) { for_each_engine(engine, gt, id) { - if (t->reset_engine[id] == + if (t->reset_engine[i][id] == i915_reset_engine_count(&i915->gpu_error, engine)) continue; gt_err(gt, "%s(%s): engine '%s' was reset %d times!\n", t->func, t->name, engine->name, i915_reset_engine_count(&i915->gpu_error, engine) - - t->reset_engine[id]); + t->reset_engine[i][id]); return -EIO; } } diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h index 36ed42736c52..83e3ad430922 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.h +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h @@ -7,6 +7,7 @@ #ifndef IGT_LIVE_TEST_H #define IGT_LIVE_TEST_H +#include "gt/intel_gt_defines.h" /* for I915_MAX_GT */ #include "gt/intel_engine.h" /* for I915_NUM_ENGINES */ struct drm_i915_private; @@ -17,7 +18,7 @@ struct igt_live_test { const char *name; unsigned int reset_global; - unsigned int reset_engine[I915_NUM_ENGINES]; + unsigned int reset_engine[I915_MAX_GT][I915_NUM_ENGINES]; }; /* diff --git a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c index f81dc34c9c3e..c1bc8b00d938 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c @@ -203,7 +203,7 @@ void mtk_gamma_set(struct device *dev, struct drm_crtc_state *state) /* Disable RELAY mode to pass the processed image */ cfg_val &= ~GAMMA_RELAY_MODE; - cfg_val = readl(gamma->regs + DISP_GAMMA_CFG); + writel(cfg_val, gamma->regs + DISP_GAMMA_CFG); } void mtk_gamma_config(struct device *dev, unsigned int w, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index c277b9fae950..db43f9dff912 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -788,6 +788,7 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc, crtc); struct mtk_crtc_state *mtk_crtc_state = to_mtk_crtc_state(crtc_state); struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); + unsigned long flags; if (mtk_crtc->event && mtk_crtc_state->base.event) DRM_ERROR("new event while there is still a pending event\n"); @@ -795,7 +796,11 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc, if (mtk_crtc_state->base.event) { mtk_crtc_state->base.event->pipe = drm_crtc_index(crtc); WARN_ON(drm_crtc_vblank_get(crtc) != 0); + + spin_lock_irqsave(&crtc->dev->event_lock, flags); mtk_crtc->event = mtk_crtc_state->base.event; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + mtk_crtc_state->base.event = NULL; } } @@ -921,7 +926,14 @@ static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev, struct device *mtk_drm_crtc_dma_dev_get(struct drm_crtc *crtc) { - struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); + struct mtk_drm_crtc *mtk_crtc = NULL; + + if (!crtc) + return NULL; + + mtk_crtc = to_mtk_crtc(crtc); + if (!mtk_crtc) + return NULL; return mtk_crtc->dma_dev; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 2dfaa613276a..2b0c35cacbc6 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -443,6 +443,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) struct mtk_drm_private *private = drm->dev_private; struct mtk_drm_private *priv_n; struct device *dma_dev = NULL; + struct drm_crtc *crtc; int ret, i, j; if (drm_firmware_drivers_only()) @@ -519,7 +520,9 @@ static int mtk_drm_kms_init(struct drm_device *drm) } /* Use OVL device for all DMA memory allocations */ - dma_dev = mtk_drm_crtc_dma_dev_get(drm_crtc_from_index(drm, 0)); + crtc = drm_crtc_from_index(drm, 0); + if (crtc) + dma_dev = mtk_drm_crtc_dma_dev_get(crtc); if (!dma_dev) { ret = -ENODEV; dev_err(drm->dev, "Need at least one OVL device\n"); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c index e4279f1772a1..377d0e0cef84 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c @@ -385,7 +385,7 @@ nvkm_uoutp_mthd_inherit(struct nvkm_outp *outp, void *argv, u32 argc) /* Ensure an ior is hooked up to this outp already */ ior = outp->func->inherit(outp); - if (!ior) + if (!ior || !ior->arm.head) return -ENODEV; /* With iors, there will be a separate output path for each type of connector - and all of diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c index 1b811d6972a1..201022ae9214 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c @@ -49,14 +49,14 @@ #include <subdev/mmu.h> struct gk20a_instobj { - struct nvkm_memory memory; + struct nvkm_instobj base; struct nvkm_mm_node *mn; struct gk20a_instmem *imem; /* CPU mapping */ u32 *vaddr; }; -#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, memory) +#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, base.memory) /* * Used for objects allocated using the DMA API @@ -148,7 +148,7 @@ gk20a_instobj_iommu_recycle_vaddr(struct gk20a_instobj_iommu *obj) list_del(&obj->vaddr_node); vunmap(obj->base.vaddr); obj->base.vaddr = NULL; - imem->vaddr_use -= nvkm_memory_size(&obj->base.memory); + imem->vaddr_use -= nvkm_memory_size(&obj->base.base.memory); nvkm_debug(&imem->base.subdev, "vaddr used: %x/%x\n", imem->vaddr_use, imem->vaddr_max); } @@ -283,7 +283,7 @@ gk20a_instobj_map(struct nvkm_memory *memory, u64 offset, struct nvkm_vmm *vmm, { struct gk20a_instobj *node = gk20a_instobj(memory); struct nvkm_vmm_map map = { - .memory = &node->memory, + .memory = &node->base.memory, .offset = offset, .mem = node->mn, }; @@ -391,8 +391,8 @@ gk20a_instobj_ctor_dma(struct gk20a_instmem *imem, u32 npages, u32 align, return -ENOMEM; *_node = &node->base; - nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.memory); - node->base.memory.ptrs = &gk20a_instobj_ptrs; + nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.base.memory); + node->base.base.memory.ptrs = &gk20a_instobj_ptrs; node->base.vaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT, &node->handle, GFP_KERNEL, @@ -438,8 +438,8 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align, *_node = &node->base; node->dma_addrs = (void *)(node->pages + npages); - nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.memory); - node->base.memory.ptrs = &gk20a_instobj_ptrs; + nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.base.memory); + node->base.base.memory.ptrs = &gk20a_instobj_ptrs; /* Allocate backing memory */ for (i = 0; i < npages; i++) { @@ -533,7 +533,7 @@ gk20a_instobj_new(struct nvkm_instmem *base, u32 size, u32 align, bool zero, else ret = gk20a_instobj_ctor_dma(imem, size >> PAGE_SHIFT, align, &node); - *pmemory = node ? &node->memory : NULL; + *pmemory = node ? &node->base.memory : NULL; if (ret) return ret; diff --git a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c index 6e3670508e3a..30919c872ac8 100644 --- a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c +++ b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c @@ -326,7 +326,7 @@ static const struct drm_display_mode ltk050h3148w_mode = { static const struct ltk050h3146w_desc ltk050h3148w_data = { .mode = <k050h3148w_mode, .init = ltk050h3148w_init_sequence, - .mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE, + .mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_VIDEO_BURST, }; static int ltk050h3146w_init_sequence(struct ltk050h3146w *ctx) diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index d9e9829b2200..b9c7c0ed7bcc 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -347,6 +347,8 @@ static const struct apple_non_apple_keyboard non_apple_keyboards[] = { { "Hailuck" }, { "Jamesdonkey" }, { "A3R" }, + { "hfd.cn" }, + { "WKB603" }, }; static bool apple_is_non_apple_keyboard(struct hid_device *hdev) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index c6e4e0d1f214..72046039d1be 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -740,6 +740,7 @@ #define USB_VENDOR_ID_LABTEC 0x1020 #define USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD 0x0006 +#define USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE 0x8888 #define USB_VENDOR_ID_LAVIEW 0x22D4 #define USB_DEVICE_ID_GLORIOUS_MODEL_I 0x1503 diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 7c1b33be9d13..149a3c74346b 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -692,7 +692,8 @@ static int lenovo_event_cptkbd(struct hid_device *hdev, * so set middlebutton_state to 3 * to never apply workaround anymore */ - if (cptkbd_data->middlebutton_state == 1 && + if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD && + cptkbd_data->middlebutton_state == 1 && usage->type == EV_REL && (usage->code == REL_X || usage->code == REL_Y)) { cptkbd_data->middlebutton_state = 3; diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index ea472923fab0..e0bbf0c6345d 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -121,6 +121,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_T609A), HID_QUIRK_MULTI_INPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/i2c-hid/i2c-hid-acpi.c b/drivers/hid/i2c-hid/i2c-hid-acpi.c index ac918a9ea8d3..1b49243adb16 100644 --- a/drivers/hid/i2c-hid/i2c-hid-acpi.c +++ b/drivers/hid/i2c-hid/i2c-hid-acpi.c @@ -40,6 +40,11 @@ static const struct acpi_device_id i2c_hid_acpi_blacklist[] = { * ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible. */ { "CHPN0001" }, + /* + * The IDEA5002 ACPI device causes high interrupt usage and spurious + * wakeups from suspend. + */ + { "IDEA5002" }, { } }; diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index 3d6f0a466a9e..f9f886289b97 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -328,9 +328,6 @@ static int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io_sq, * compare it to the stored version, just create the meta */ if (io_sq->disable_meta_caching) { - if (unlikely(!ena_tx_ctx->meta_valid)) - return -EINVAL; - *have_meta = true; return ena_com_create_meta(io_sq, ena_meta); } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index b5bca4814830..c44c44e26ddf 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -74,6 +74,8 @@ static void ena_unmap_tx_buff(struct ena_ring *tx_ring, struct ena_tx_buffer *tx_info); static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter, int first_index, int count); +static void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter, + int first_index, int count); /* Increase a stat by cnt while holding syncp seqlock on 32bit machines */ static void ena_increase_stat(u64 *statp, u64 cnt, @@ -457,23 +459,22 @@ static void ena_init_all_xdp_queues(struct ena_adapter *adapter) static int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter) { + u32 xdp_first_ring = adapter->xdp_first_ring; + u32 xdp_num_queues = adapter->xdp_num_queues; int rc = 0; - rc = ena_setup_tx_resources_in_range(adapter, adapter->xdp_first_ring, - adapter->xdp_num_queues); + rc = ena_setup_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues); if (rc) goto setup_err; - rc = ena_create_io_tx_queues_in_range(adapter, - adapter->xdp_first_ring, - adapter->xdp_num_queues); + rc = ena_create_io_tx_queues_in_range(adapter, xdp_first_ring, xdp_num_queues); if (rc) goto create_err; return 0; create_err: - ena_free_all_io_tx_resources(adapter); + ena_free_all_io_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues); setup_err: return rc; } @@ -1492,11 +1493,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, if (unlikely(!skb)) return NULL; - /* sync this buffer for CPU use */ - dma_sync_single_for_cpu(rx_ring->dev, - dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, - len, - DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, buf_addr + buf_offset, len); dma_sync_single_for_device(rx_ring->dev, dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, @@ -1515,17 +1511,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, buf_len = SKB_DATA_ALIGN(len + buf_offset + tailroom); - pre_reuse_paddr = dma_unmap_addr(&rx_info->ena_buf, paddr); - /* If XDP isn't loaded try to reuse part of the RX buffer */ reuse_rx_buf_page = !is_xdp_loaded && ena_try_rx_buf_page_reuse(rx_info, buf_len, len, pkt_offset); - dma_sync_single_for_cpu(rx_ring->dev, - pre_reuse_paddr + pkt_offset, - len, - DMA_FROM_DEVICE); - if (!reuse_rx_buf_page) ena_unmap_rx_buff_attrs(rx_ring, rx_info, DMA_ATTR_SKIP_CPU_SYNC); @@ -1671,20 +1660,23 @@ static void ena_set_rx_hash(struct ena_ring *rx_ring, } } -static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp) +static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp, u16 num_descs) { struct ena_rx_buffer *rx_info; int ret; + /* XDP multi-buffer packets not supported */ + if (unlikely(num_descs > 1)) { + netdev_err_once(rx_ring->adapter->netdev, + "xdp: dropped unsupported multi-buffer packets\n"); + ena_increase_stat(&rx_ring->rx_stats.xdp_drop, 1, &rx_ring->syncp); + return ENA_XDP_DROP; + } + rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; xdp_prepare_buff(xdp, page_address(rx_info->page), rx_info->buf_offset, rx_ring->ena_bufs[0].len, false); - /* If for some reason we received a bigger packet than - * we expect, then we simply drop it - */ - if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU)) - return ENA_XDP_DROP; ret = ena_xdp_execute(rx_ring, xdp); @@ -1719,6 +1711,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, int xdp_flags = 0; int total_len = 0; int xdp_verdict; + u8 pkt_offset; int rc = 0; int i; @@ -1745,15 +1738,21 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, /* First descriptor might have an offset set by the device */ rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; - rx_info->buf_offset += ena_rx_ctx.pkt_offset; + pkt_offset = ena_rx_ctx.pkt_offset; + rx_info->buf_offset += pkt_offset; netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n", rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto, ena_rx_ctx.l4_proto, ena_rx_ctx.hash); + dma_sync_single_for_cpu(rx_ring->dev, + dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, + rx_ring->ena_bufs[0].len, + DMA_FROM_DEVICE); + if (ena_xdp_present_ring(rx_ring)) - xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp); + xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp, ena_rx_ctx.descs); /* allocate skb and fill it */ if (xdp_verdict == ENA_XDP_PASS) @@ -1777,7 +1776,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, if (xdp_verdict & ENA_XDP_FORWARDED) { ena_unmap_rx_buff_attrs(rx_ring, &rx_ring->rx_buffer_info[req_id], - 0); + DMA_ATTR_SKIP_CPU_SYNC); rx_ring->rx_buffer_info[req_id].page = NULL; } } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 694daeaf3e61..e1885c1eb100 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -938,11 +938,14 @@ void aq_ring_free(struct aq_ring_s *self) return; kfree(self->buff_ring); + self->buff_ring = NULL; - if (self->dx_ring) + if (self->dx_ring) { dma_free_coherent(aq_nic_get_dev(self->aq_nic), self->size * self->dx_size, self->dx_ring, self->dx_ring_pa); + self->dx_ring = NULL; + } } unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index d0359b569afe..579eebb6fc56 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1748,16 +1748,32 @@ static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi, struct sk_buff *skb) { + skb_mark_for_recycle(skb); + if (skb->dev != bp->dev) { /* this packet belongs to a vf-rep */ bnxt_vf_rep_rx(bp, skb); return; } skb_record_rx_queue(skb, bnapi->index); - skb_mark_for_recycle(skb); napi_gro_receive(&bnapi->napi, skb); } +static bool bnxt_rx_ts_valid(struct bnxt *bp, u32 flags, + struct rx_cmp_ext *rxcmp1, u32 *cmpl_ts) +{ + u32 ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp); + + if (BNXT_PTP_RX_TS_VALID(flags)) + goto ts_valid; + if (!bp->ptp_all_rx_tstamp || !ts || !BNXT_ALL_RX_TS_VALID(flags)) + return false; + +ts_valid: + *cmpl_ts = ts; + return true; +} + /* returns the following: * 1 - 1 packet successfully received * 0 - successful TPA_START, packet not completed yet @@ -1783,6 +1799,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, struct sk_buff *skb; struct xdp_buff xdp; u32 flags, misc; + u32 cmpl_ts; void *data; int rc = 0; @@ -2005,10 +2022,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } } - if (unlikely((flags & RX_CMP_FLAGS_ITYPES_MASK) == - RX_CMP_FLAGS_ITYPE_PTP_W_TS) || bp->ptp_all_rx_tstamp) { + if (bnxt_rx_ts_valid(bp, flags, rxcmp1, &cmpl_ts)) { if (bp->flags & BNXT_FLAG_CHIP_P5) { - u32 cmpl_ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp); u64 ns, ts; if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) { @@ -10731,10 +10746,8 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bnxt_free_mem(bp, irq_re_init); } -int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) +void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) { - int rc = 0; - if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { /* If we get here, it means firmware reset is in progress * while we are trying to close. We can safely proceed with @@ -10749,15 +10762,18 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) #ifdef CONFIG_BNXT_SRIOV if (bp->sriov_cfg) { + int rc; + rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait, !bp->sriov_cfg, BNXT_SRIOV_CFG_WAIT_TMO); - if (rc) - netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n"); + if (!rc) + netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete, proceeding to close!\n"); + else if (rc < 0) + netdev_warn(bp->dev, "SRIOV config operation interrupted, proceeding to close!\n"); } #endif __bnxt_close_nic(bp, irq_re_init, link_re_init); - return rc; } static int bnxt_close(struct net_device *dev) @@ -13940,6 +13956,8 @@ static int bnxt_resume(struct device *device) if (rc) goto resume_exit; + bnxt_clear_reservations(bp, true); + if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) { rc = -ENODEV; goto resume_exit; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index e702dbc3e6b1..a7d7b09ea162 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -161,7 +161,7 @@ struct rx_cmp { #define RX_CMP_FLAGS_ERROR (1 << 6) #define RX_CMP_FLAGS_PLACEMENT (7 << 7) #define RX_CMP_FLAGS_RSS_VALID (1 << 10) - #define RX_CMP_FLAGS_UNUSED (1 << 11) + #define RX_CMP_FLAGS_PKT_METADATA_PRESENT (1 << 11) #define RX_CMP_FLAGS_ITYPES_SHIFT 12 #define RX_CMP_FLAGS_ITYPES_MASK 0xf000 #define RX_CMP_FLAGS_ITYPE_UNKNOWN (0 << 12) @@ -188,6 +188,12 @@ struct rx_cmp { __le32 rx_cmp_rss_hash; }; +#define BNXT_PTP_RX_TS_VALID(flags) \ + (((flags) & RX_CMP_FLAGS_ITYPES_MASK) == RX_CMP_FLAGS_ITYPE_PTP_W_TS) + +#define BNXT_ALL_RX_TS_VALID(flags) \ + !((flags) & RX_CMP_FLAGS_PKT_METADATA_PRESENT) + #define RX_CMP_HASH_VALID(rxcmp) \ ((rxcmp)->rx_cmp_len_flags_type & cpu_to_le32(RX_CMP_FLAGS_RSS_VALID)) @@ -2375,7 +2381,7 @@ int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); void bnxt_reenable_sriov(struct bnxt *bp); -int bnxt_close_nic(struct bnxt *, bool, bool); +void bnxt_close_nic(struct bnxt *, bool, bool); void bnxt_get_ring_err_stats(struct bnxt *bp, struct bnxt_total_ring_err_stats *stats); int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index f302dac56599..89809f1b129c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -449,15 +449,8 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change, return -ENODEV; } bnxt_ulp_stop(bp); - if (netif_running(bp->dev)) { - rc = bnxt_close_nic(bp, true, true); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Failed to close"); - dev_close(bp->dev); - rtnl_unlock(); - break; - } - } + if (netif_running(bp->dev)) + bnxt_close_nic(bp, true, true); bnxt_vf_reps_free(bp); rc = bnxt_hwrm_func_drv_unrgtr(bp); if (rc) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index f3f384773ac0..5f67a7f94e7d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -165,9 +165,8 @@ static int bnxt_set_coalesce(struct net_device *dev, reset_coalesce: if (test_bit(BNXT_STATE_OPEN, &bp->state)) { if (update_stats) { - rc = bnxt_close_nic(bp, true, false); - if (!rc) - rc = bnxt_open_nic(bp, true, false); + bnxt_close_nic(bp, true, false); + rc = bnxt_open_nic(bp, true, false); } else { rc = bnxt_hwrm_set_coal(bp); } @@ -972,12 +971,7 @@ static int bnxt_set_channels(struct net_device *dev, * before PF unload */ } - rc = bnxt_close_nic(bp, true, false); - if (rc) { - netdev_err(bp->dev, "Set channel failure rc :%x\n", - rc); - return rc; - } + bnxt_close_nic(bp, true, false); } if (sh) { @@ -4042,12 +4036,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, bnxt_run_fw_tests(bp, test_mask, &test_results); } else { bnxt_ulp_stop(bp); - rc = bnxt_close_nic(bp, true, false); - if (rc) { - etest->flags |= ETH_TEST_FL_FAILED; - bnxt_ulp_start(bp, rc); - return; - } + bnxt_close_nic(bp, true, false); bnxt_run_fw_tests(bp, test_mask, &test_results); buf[BNXT_MACLPBK_TEST_IDX] = 1; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index f3886710e778..6e3da3362bd6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -521,9 +521,8 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp) if (netif_running(bp->dev)) { if (ptp->rx_filter == HWTSTAMP_FILTER_ALL) { - rc = bnxt_close_nic(bp, false, false); - if (!rc) - rc = bnxt_open_nic(bp, false, false); + bnxt_close_nic(bp, false, false); + rc = bnxt_open_nic(bp, false, false); } else { bnxt_ptp_cfg_tstamp_filters(bp); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c index 4798fb7fe35d..b6a534a3e0b1 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c @@ -139,7 +139,8 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block, err = dpsw_acl_add_entry(ethsw->mc_io, 0, ethsw->dpsw_handle, filter_block->acl_id, acl_entry_cfg); - dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff), + dma_unmap_single(dev, acl_entry_cfg->key_iova, + DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err); @@ -181,8 +182,8 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block, err = dpsw_acl_remove_entry(ethsw->mc_io, 0, ethsw->dpsw_handle, block->acl_id, acl_entry_cfg); - dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff), - DMA_TO_DEVICE); + dma_unmap_single(dev, acl_entry_cfg->key_iova, + DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err); kfree(cmd_buff); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 97d3151076d5..e01a246124ac 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1998,9 +1998,6 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev, return notifier_from_errno(err); } -static struct notifier_block dpaa2_switch_port_switchdev_nb; -static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb; - static int dpaa2_switch_port_bridge_join(struct net_device *netdev, struct net_device *upper_dev, struct netlink_ext_ack *extack) @@ -2043,9 +2040,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, goto err_egress_flood; err = switchdev_bridge_port_offload(netdev, netdev, NULL, - &dpaa2_switch_port_switchdev_nb, - &dpaa2_switch_port_switchdev_blocking_nb, - false, extack); + NULL, NULL, false, extack); if (err) goto err_switchdev_offload; @@ -2079,9 +2074,7 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev) { - switchdev_bridge_port_unoffload(netdev, NULL, - &dpaa2_switch_port_switchdev_nb, - &dpaa2_switch_port_switchdev_blocking_nb); + switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL); } static int dpaa2_switch_port_bridge_leave(struct net_device *netdev) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index c3b7694a7485..e08c7b572497 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3731,31 +3731,26 @@ static int fec_set_features(struct net_device *netdev, return 0; } -static u16 fec_enet_get_raw_vlan_tci(struct sk_buff *skb) -{ - struct vlan_ethhdr *vhdr; - unsigned short vlan_TCI = 0; - - if (skb->protocol == htons(ETH_P_ALL)) { - vhdr = (struct vlan_ethhdr *)(skb->data); - vlan_TCI = ntohs(vhdr->h_vlan_TCI); - } - - return vlan_TCI; -} - static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb, struct net_device *sb_dev) { struct fec_enet_private *fep = netdev_priv(ndev); - u16 vlan_tag; + u16 vlan_tag = 0; if (!(fep->quirks & FEC_QUIRK_HAS_AVB)) return netdev_pick_tx(ndev, skb, NULL); - vlan_tag = fec_enet_get_raw_vlan_tci(skb); - if (!vlan_tag) + /* VLAN is present in the payload.*/ + if (eth_type_vlan(skb->protocol)) { + struct vlan_ethhdr *vhdr = skb_vlan_eth_hdr(skb); + + vlan_tag = ntohs(vhdr->h_vlan_TCI); + /* VLAN is present in the skb but not yet pushed in the payload.*/ + } else if (skb_vlan_tag_present(skb)) { + vlan_tag = skb->vlan_tci; + } else { return vlan_tag; + } return fec_enet_vlan_pri_to_queue[vlan_tag >> 13]; } diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e7ab89dc883a..63b45c61cc4a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -292,6 +292,7 @@ struct iavf_adapter { #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) +#define IAVF_FLAG_FDIR_ENABLED BIT(21) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 19cbfe554689..dc499fe7734e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1061,7 +1061,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, struct iavf_fdir_fltr *rule = NULL; int ret = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; spin_lock_bh(&adapter->fdir_fltr_lock); @@ -1203,7 +1203,7 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, unsigned int cnt = 0; int val = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; cmd->data = IAVF_MAX_FDIR_FILTERS; @@ -1395,7 +1395,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx int count = 50; int err; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; if (fsp->flow_type & FLOW_MAC_EXT) @@ -1436,12 +1436,16 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx spin_lock_bh(&adapter->fdir_fltr_lock); iavf_fdir_list_add_fltr(adapter, fltr); adapter->fdir_active_fltr++; - fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + if (adapter->link_up) { + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } else { + fltr->state = IAVF_FDIR_FLTR_INACTIVE; + } spin_unlock_bh(&adapter->fdir_fltr_lock); - mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); - + if (adapter->link_up) + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); ret: if (err && fltr) kfree(fltr); @@ -1463,7 +1467,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx struct iavf_fdir_fltr *fltr = NULL; int err = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; spin_lock_bh(&adapter->fdir_fltr_lock); @@ -1472,6 +1476,11 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { + list_del(&fltr->list); + kfree(fltr); + adapter->fdir_active_fltr--; + fltr = NULL; } else { err = -EBUSY; } @@ -1780,7 +1789,7 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, ret = 0; break; case ETHTOOL_GRXCLSRLCNT: - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) break; spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index 9eb9f73f6adf..d31bd923ba8c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -6,12 +6,25 @@ struct iavf_adapter; -/* State of Flow Director filter */ +/* State of Flow Director filter + * + * *_REQUEST states are used to mark filter to be sent to PF driver to perform + * an action (either add or delete filter). *_PENDING states are an indication + * that request was sent to PF and the driver is waiting for response. + * + * Both DELETE and DISABLE states are being used to delete a filter in PF. + * The difference is that after a successful response filter in DEL_PENDING + * state is being deleted from VF driver as well and filter in DIS_PENDING state + * is being changed to INACTIVE state. + */ enum iavf_fdir_fltr_state_t { IAVF_FDIR_FLTR_ADD_REQUEST, /* User requests to add filter */ IAVF_FDIR_FLTR_ADD_PENDING, /* Filter pending add by the PF */ IAVF_FDIR_FLTR_DEL_REQUEST, /* User requests to delete filter */ IAVF_FDIR_FLTR_DEL_PENDING, /* Filter pending delete by the PF */ + IAVF_FDIR_FLTR_DIS_REQUEST, /* Filter scheduled to be disabled */ + IAVF_FDIR_FLTR_DIS_PENDING, /* Filter pending disable by the PF */ + IAVF_FDIR_FLTR_INACTIVE, /* Filter inactive on link down */ IAVF_FDIR_FLTR_ACTIVE, /* Filter is active */ }; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index c862ebcd2e39..e8d5b889addc 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -277,27 +277,6 @@ void iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem) } /** - * iavf_lock_timeout - try to lock mutex but give up after timeout - * @lock: mutex that should be locked - * @msecs: timeout in msecs - * - * Returns 0 on success, negative on failure - **/ -static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) -{ - unsigned int wait, delay = 10; - - for (wait = 0; wait < msecs; wait += delay) { - if (mutex_trylock(lock)) - return 0; - - msleep(delay); - } - - return -1; -} - -/** * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED @@ -1353,18 +1332,20 @@ static void iavf_clear_cloud_filters(struct iavf_adapter *adapter) **/ static void iavf_clear_fdir_filters(struct iavf_adapter *adapter) { - struct iavf_fdir_fltr *fdir, *fdirtmp; + struct iavf_fdir_fltr *fdir; /* remove all Flow Director filters */ spin_lock_bh(&adapter->fdir_fltr_lock); - list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, - list) { + list_for_each_entry(fdir, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) { - list_del(&fdir->list); - kfree(fdir); - adapter->fdir_active_fltr--; - } else { - fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + /* Cancel a request, keep filter as inactive */ + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Disable filters which are active or have a pending + * request to PF to be added + */ + fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -4113,6 +4094,33 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, } /** + * iavf_restore_fdir_filters + * @adapter: board private structure + * + * Restore existing FDIR filters when VF netdev comes back up. + **/ +static void iavf_restore_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(f, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + /* Cancel a request, keep filter as active */ + f->state = IAVF_FDIR_FLTR_ACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING || + f->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Add filters which are inactive or have a pending + * request to PF to be deleted + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); +} + +/** * iavf_open - Called when a network interface is made active * @netdev: network interface device structure * @@ -4179,8 +4187,9 @@ static int iavf_open(struct net_device *netdev) spin_unlock_bh(&adapter->mac_vlan_list_lock); - /* Restore VLAN filters that were removed with IFF_DOWN */ + /* Restore filters that were removed with IFF_DOWN */ iavf_restore_filters(adapter); + iavf_restore_fdir_filters(adapter); iavf_configure(adapter); @@ -4311,6 +4320,49 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) return ret; } +/** + * iavf_disable_fdir - disable Flow Director and clear existing filters + * @adapter: board private structure + **/ +static void iavf_disable_fdir(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *fdir, *fdirtmp; + bool del_filters = false; + + adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED; + + /* remove all Flow Director filters */ + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST || + fdir->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Delete filters not registered in PF */ + list_del(&fdir->list); + kfree(fdir); + adapter->fdir_active_fltr--; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Filters registered in PF, schedule their deletion */ + fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + del_filters = true; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Request to delete filter already sent to PF, change + * state to DEL_PENDING to delete filter after PF's + * response, not set as INACTIVE + */ + fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (del_filters) { + adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); + } +} + #define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_RX | \ @@ -4336,6 +4388,13 @@ static int iavf_set_features(struct net_device *netdev, ((netdev->features & NETIF_F_RXFCS) ^ (features & NETIF_F_RXFCS))) iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) { + if (features & NETIF_F_NTUPLE) + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + else + iavf_disable_fdir(adapter); + } + return 0; } @@ -4685,6 +4744,9 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, features = iavf_fix_netdev_vlan_features(adapter, features); + if (!FDIR_FLTR_SUPPORT(adapter)) + features &= ~NETIF_F_NTUPLE; + return iavf_fix_strip_features(adapter, features); } @@ -4802,6 +4864,12 @@ int iavf_process_config(struct iavf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (FDIR_FLTR_SUPPORT(adapter)) { + netdev->hw_features |= NETIF_F_NTUPLE; + netdev->features |= NETIF_F_NTUPLE; + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + } + netdev->priv_flags |= IFF_UNICAST_FLT; /* Do not turn on offloads when they are requested to be turned off. @@ -4826,34 +4894,6 @@ int iavf_process_config(struct iavf_adapter *adapter) } /** - * iavf_shutdown - Shutdown the device in preparation for a reboot - * @pdev: pci device structure - **/ -static void iavf_shutdown(struct pci_dev *pdev) -{ - struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - struct net_device *netdev = adapter->netdev; - - netif_device_detach(netdev); - - if (netif_running(netdev)) - iavf_close(netdev); - - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__); - /* Prevent the watchdog from running. */ - iavf_change_state(adapter, __IAVF_REMOVE); - adapter->aq_required = 0; - mutex_unlock(&adapter->crit_lock); - -#ifdef CONFIG_PM - pci_save_state(pdev); - -#endif - pci_disable_device(pdev); -} - -/** * iavf_probe - Device Initialization Routine * @pdev: PCI device information struct * @ent: entry in iavf_pci_tbl @@ -5063,16 +5103,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d) **/ static void iavf_remove(struct pci_dev *pdev) { - struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_cloud_filter *cf, *cftmp; struct iavf_adv_rss *rss, *rsstmp; struct iavf_mac_filter *f, *ftmp; + struct iavf_adapter *adapter; struct net_device *netdev; struct iavf_hw *hw; - netdev = adapter->netdev; + /* Don't proceed with remove if netdev is already freed */ + netdev = pci_get_drvdata(pdev); + if (!netdev) + return; + + adapter = iavf_pdev_to_adapter(pdev); hw = &adapter->hw; if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) @@ -5184,11 +5229,25 @@ static void iavf_remove(struct pci_dev *pdev) destroy_workqueue(adapter->wq); + pci_set_drvdata(pdev, NULL); + free_netdev(netdev); pci_disable_device(pdev); } +/** + * iavf_shutdown - Shutdown the device in preparation for a reboot + * @pdev: pci device structure + **/ +static void iavf_shutdown(struct pci_dev *pdev) +{ + iavf_remove(pdev); + + if (system_state == SYSTEM_POWER_OFF) + pci_set_power_state(pdev, PCI_D3hot); +} + static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); static struct pci_driver iavf_driver = { diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 64c4443dbef9..2d9366be0ec5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1735,8 +1735,8 @@ void iavf_add_fdir_filter(struct iavf_adapter *adapter) **/ void iavf_del_fdir_filter(struct iavf_adapter *adapter) { + struct virtchnl_fdir_del f = {}; struct iavf_fdir_fltr *fdir; - struct virtchnl_fdir_del f; bool process_fltr = false; int len; @@ -1753,11 +1753,16 @@ void iavf_del_fdir_filter(struct iavf_adapter *adapter) list_for_each_entry(fdir, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) { process_fltr = true; - memset(&f, 0, len); f.vsi_id = fdir->vc_add_msg.vsi_id; f.flow_id = fdir->flow_id; fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; break; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + process_fltr = true; + f.vsi_id = fdir->vc_add_msg.vsi_id; + f.flow_id = fdir->flow_id; + fdir->state = IAVF_FDIR_FLTR_DIS_PENDING; + break; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1902,6 +1907,48 @@ static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev, } /** + * iavf_activate_fdir_filters - Reactivate all FDIR filters after a reset + * @adapter: private adapter structure + * + * Called after a reset to re-add all FDIR filters and delete some of them + * if they were pending to be deleted. + */ +static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f, *ftmp; + bool add_filters = false; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(f, ftmp, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_ADD_REQUEST || + f->state == IAVF_FDIR_FLTR_ADD_PENDING || + f->state == IAVF_FDIR_FLTR_ACTIVE) { + /* All filters and requests have been removed in PF, + * restore them + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + add_filters = true; + } else if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST || + f->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Link down state, leave filters as inactive */ + f->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DEL_REQUEST || + f->state == IAVF_FDIR_FLTR_DEL_PENDING) { + /* Delete filters that were pending to be deleted, the + * list on PF is already cleared after a reset + */ + list_del(&f->list); + kfree(f); + adapter->fdir_active_fltr--; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (add_filters) + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -2078,7 +2125,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fdir, &adapter->fdir_list_head, list) { - if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { + if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n", iavf_stat_str(&adapter->hw, @@ -2214,6 +2262,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->mac_vlan_list_lock); + iavf_activate_fdir_filters(adapter); + iavf_parse_vf_resource_msg(adapter); /* negotiated VIRTCHNL_VF_OFFLOAD_VLAN_V2, so wait for the @@ -2390,7 +2440,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { - if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || + del_fltr->status == + VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", fdir->loc); list_del(&fdir->list); @@ -2402,6 +2454,17 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, del_fltr->status); iavf_print_fdir_fltr(adapter, fdir); } + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || + del_fltr->status == + VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else { + fdir->state = IAVF_FDIR_FLTR_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to disable Flow Director filter with status: %d\n", + del_fltr->status); + iavf_print_fdir_fltr(adapter, fdir); + } } } spin_unlock_bh(&adapter->fdir_fltr_lock); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 552970c7dec0..a9bdf3283a85 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1193,6 +1193,13 @@ int octep_device_setup(struct octep_device *oct) if (ret) return ret; + INIT_WORK(&oct->tx_timeout_task, octep_tx_timeout_task); + INIT_WORK(&oct->ctrl_mbox_task, octep_ctrl_mbox_task); + INIT_DELAYED_WORK(&oct->intr_poll_task, octep_intr_poll_task); + oct->poll_non_ioq_intr = true; + queue_delayed_work(octep_wq, &oct->intr_poll_task, + msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS)); + atomic_set(&oct->hb_miss_cnt, 0); INIT_DELAYED_WORK(&oct->hb_task, octep_hb_timeout_task); @@ -1258,7 +1265,8 @@ static bool get_fw_ready_status(struct pci_dev *pdev) pci_read_config_byte(pdev, (pos + 8), &status); dev_info(&pdev->dev, "Firmware ready status = %u\n", status); - return status; +#define FW_STATUS_READY 1ULL + return status == FW_STATUS_READY; } return false; } @@ -1325,21 +1333,18 @@ static int octep_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_octep_config; } - octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID, - &octep_dev->conf->fw_info); + err = octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID, + &octep_dev->conf->fw_info); + if (err) { + dev_err(&pdev->dev, "Failed to get firmware info\n"); + goto register_dev_err; + } dev_info(&octep_dev->pdev->dev, "Heartbeat interval %u msecs Heartbeat miss count %u\n", octep_dev->conf->fw_info.hb_interval, octep_dev->conf->fw_info.hb_miss_count); queue_delayed_work(octep_wq, &octep_dev->hb_task, msecs_to_jiffies(octep_dev->conf->fw_info.hb_interval)); - INIT_WORK(&octep_dev->tx_timeout_task, octep_tx_timeout_task); - INIT_WORK(&octep_dev->ctrl_mbox_task, octep_ctrl_mbox_task); - INIT_DELAYED_WORK(&octep_dev->intr_poll_task, octep_intr_poll_task); - octep_dev->poll_non_ioq_intr = true; - queue_delayed_work(octep_wq, &octep_dev->intr_poll_task, - msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS)); - netdev->netdev_ops = &octep_netdev_ops; octep_set_ethtool_ops(netdev); netif_carrier_off(netdev); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index af21e2030cff..4728ba34b0e3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -373,6 +373,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable) cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Disable forward pause to driver */ + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD; + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Enable channel mask for all LMACS */ if (is_dev_rpm2(rpm)) rpm_write(rpm, lmac_id, RPM2_CMR_CHAN_MSK_OR, 0xffff); @@ -616,12 +621,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p if (rx_pause) { cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } else { cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } if (tx_pause) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 62780d8b4f9a..21b5d71c1e37 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -538,7 +538,7 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl) rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq"); if (!rvu_dl->devlink_wq) - goto err; + return -ENOMEM; INIT_WORK(&rvu_reporters->intr_work, rvu_nix_intr_work); INIT_WORK(&rvu_reporters->gen_work, rvu_nix_gen_work); @@ -546,9 +546,6 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl) INIT_WORK(&rvu_reporters->ras_work, rvu_nix_ras_work); return 0; -err: - rvu_nix_health_reporters_destroy(rvu_dl); - return -ENOMEM; } static int rvu_nix_health_reporters_create(struct rvu_devlink *rvu_dl) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index f65805860c8d..0bcf3e559280 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -671,6 +671,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, int blkaddr, ucast_idx, index; struct nix_rx_action action = { 0 }; u64 relaxed_mask; + u8 flow_key_alg; if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc)) return; @@ -701,6 +702,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, action.op = NIX_RX_ACTIONOP_UCAST; } + flow_key_alg = action.flow_key_alg; + /* RX_ACTION set to MCAST for CGX PF's */ if (hw->cap.nix_rx_multicast && pfvf->use_mce_list && is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { @@ -740,7 +743,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, req.vf = pcifunc; req.index = action.index; req.match_id = action.match_id; - req.flow_key_alg = action.flow_key_alg; + req.flow_key_alg = flow_key_alg; rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } @@ -854,6 +857,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u8 mac_addr[ETH_ALEN] = { 0 }; struct nix_rx_action action = { 0 }; struct rvu_pfvf *pfvf; + u8 flow_key_alg; u16 vf_func; /* Only CGX PF/VF can add allmulticast entry */ @@ -888,6 +892,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, *(u64 *)&action = npc_get_mcam_action(rvu, mcam, blkaddr, ucast_idx); + flow_key_alg = action.flow_key_alg; if (action.op != NIX_RX_ACTIONOP_RSS) { *(u64 *)&action = 0; action.op = NIX_RX_ACTIONOP_UCAST; @@ -924,7 +929,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, req.vf = pcifunc | vf_func; req.index = action.index; req.match_id = action.match_id; - req.flow_key_alg = action.flow_key_alg; + req.flow_key_alg = flow_key_alg; rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } @@ -990,11 +995,38 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam, mutex_unlock(&mcam->lock); } +static void npc_update_rx_action_with_alg_idx(struct rvu *rvu, struct nix_rx_action action, + struct rvu_pfvf *pfvf, int mcam_index, int blkaddr, + int alg_idx) + +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + int bank, op_rss; + + if (!is_mcam_entry_enabled(rvu, mcam, blkaddr, mcam_index)) + return; + + op_rss = (!hw->cap.nix_rx_multicast || !pfvf->use_mce_list); + + bank = npc_get_bank(mcam, mcam_index); + mcam_index &= (mcam->banksize - 1); + + /* If Rx action is MCAST update only RSS algorithm index */ + if (!op_rss) { + *(u64 *)&action = rvu_read64(rvu, blkaddr, + NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank)); + + action.flow_key_alg = alg_idx; + } + rvu_write64(rvu, blkaddr, + NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank), *(u64 *)&action); +} + void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, int group, int alg_idx, int mcam_index) { struct npc_mcam *mcam = &rvu->hw->mcam; - struct rvu_hwinfo *hw = rvu->hw; struct nix_rx_action action; int blkaddr, index, bank; struct rvu_pfvf *pfvf; @@ -1050,15 +1082,16 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, /* If PF's promiscuous entry is enabled, * Set RSS action for that entry as well */ - if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) && - is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) { - bank = npc_get_bank(mcam, index); - index &= (mcam->banksize - 1); + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr, + alg_idx); - rvu_write64(rvu, blkaddr, - NPC_AF_MCAMEX_BANKX_ACTION(index, bank), - *(u64 *)&action); - } + index = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_ALLMULTI_ENTRY); + /* If PF's allmulti entry is enabled, + * Set RSS action for that entry as well + */ + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr, + alg_idx); } void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 0c17ebdda148..a57455aebff6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1650,6 +1650,21 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) mutex_unlock(&mbox->lock); } +static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf) +{ + int vf; + + /* The AF driver will determine whether to allow the VF netdev or not */ + if (is_otx2_vf(pfvf->pcifunc)) + return true; + + /* check if there are any trusted VFs associated with the PF netdev */ + for (vf = 0; vf < pci_num_vf(pfvf->pdev); vf++) + if (pfvf->vf_configs[vf].trusted) + return true; + return false; +} + static void otx2_do_set_rx_mode(struct otx2_nic *pf) { struct net_device *netdev = pf->netdev; @@ -1682,7 +1697,8 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf) if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) req->mode |= NIX_RX_MODE_ALLMULTI; - req->mode |= NIX_RX_MODE_USE_MCE; + if (otx2_promisc_use_mce_list(pf)) + req->mode |= NIX_RX_MODE_USE_MCE; otx2_sync_mbox_msg(&pf->mbox); mutex_unlock(&pf->mbox.lock); @@ -2691,11 +2707,14 @@ static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf, pf->vf_configs[vf].trusted = enable; rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF); - if (rc) + if (rc) { pf->vf_configs[vf].trusted = !enable; - else + } else { netdev_info(pf->netdev, "VF %d is %strusted\n", vf, enable ? "" : "not "); + otx2_set_rx_mode(netdev); + } + return rc; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b2a5da9739d2..729a11b5fb25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -826,6 +826,7 @@ enum { MLX5E_STATE_DESTROYING, MLX5E_STATE_XDP_TX_ENABLED, MLX5E_STATE_XDP_ACTIVE, + MLX5E_STATE_CHANNELS_ACTIVE, }; struct mlx5e_modify_sq_param { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 4e923a2874ae..86bf007fd05b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -83,6 +83,9 @@ mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act, struct mlx5_flow_spec *spec; int err; + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) return -ENOMEM; @@ -111,6 +114,9 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *po struct mlx5e_post_act_handle *handle; int err; + if (IS_ERR(post_act)) + return ERR_CAST(post_act); + handle = kzalloc(sizeof(*handle), GFP_KERNEL); if (!handle) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 655496598c68..161c5190c236 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -121,7 +121,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO) esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom)); - sa_entry->esn_state.esn = esn; + if (sa_entry->esn_state.esn_msb) + sa_entry->esn_state.esn = esn; + else + /* According to RFC4303, section "3.3.3. Sequence Number Generation", + * the first packet sent using a given SA will contain a sequence + * number of 1. + */ + sa_entry->esn_state.esn = max_t(u32, esn, 1); sa_entry->esn_state.esn_msb = esn_msb; if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) { @@ -335,6 +342,27 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, attrs->replay_esn.esn = sa_entry->esn_state.esn; attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb; attrs->replay_esn.overlap = sa_entry->esn_state.overlap; + switch (x->replay_esn->replay_window) { + case 32: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_32BIT; + break; + case 64: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_64BIT; + break; + case 128: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_128BIT; + break; + case 256: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_256BIT; + break; + default: + WARN_ON(true); + return; + } } attrs->dir = x->xso.dir; @@ -907,9 +935,11 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv) return; mlx5e_accel_ipsec_fs_cleanup(ipsec); - if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_TUNNEL) + if (ipsec->netevent_nb.notifier_call) { unregister_netevent_notifier(&ipsec->netevent_nb); - if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) + ipsec->netevent_nb.notifier_call = NULL; + } + if (ipsec->aso) mlx5e_ipsec_aso_cleanup(ipsec); destroy_workqueue(ipsec->wq); kfree(ipsec); @@ -1018,6 +1048,12 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev, } } + if (x->xdo.type == XFRM_DEV_OFFLOAD_PACKET && + !(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)) { + NL_SET_ERR_MSG_MOD(extack, "Packet offload is not supported"); + return -EINVAL; + } + return 0; } @@ -1113,14 +1149,6 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = { .xdo_dev_state_free = mlx5e_xfrm_free_state, .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, -}; - -static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = { - .xdo_dev_state_add = mlx5e_xfrm_add_state, - .xdo_dev_state_delete = mlx5e_xfrm_del_state, - .xdo_dev_state_free = mlx5e_xfrm_free_state, - .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, - .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, .xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft, .xdo_dev_policy_add = mlx5e_xfrm_add_policy, @@ -1138,11 +1166,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n"); - if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) - netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops; - else - netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; - + netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; netdev->features |= NETIF_F_HW_ESP; netdev->hw_enc_features |= NETIF_F_HW_ESP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 8f4a37bceaf4..adaea3493193 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -189,11 +189,19 @@ struct mlx5e_ipsec_ft { u32 refcnt; }; +struct mlx5e_ipsec_drop { + struct mlx5_flow_handle *rule; + struct mlx5_fc *fc; +}; + struct mlx5e_ipsec_rule { struct mlx5_flow_handle *rule; struct mlx5_modify_hdr *modify_hdr; struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_fc *fc; + struct mlx5e_ipsec_drop replay; + struct mlx5e_ipsec_drop auth; + struct mlx5e_ipsec_drop trailer; }; struct mlx5e_ipsec_miss { @@ -201,19 +209,6 @@ struct mlx5e_ipsec_miss { struct mlx5_flow_handle *rule; }; -struct mlx5e_ipsec_rx { - struct mlx5e_ipsec_ft ft; - struct mlx5e_ipsec_miss pol; - struct mlx5e_ipsec_miss sa; - struct mlx5e_ipsec_rule status; - struct mlx5e_ipsec_miss status_drop; - struct mlx5_fc *status_drop_cnt; - struct mlx5e_ipsec_fc *fc; - struct mlx5_fs_chains *chains; - u8 allow_tunnel_mode : 1; - struct xarray ipsec_obj_id_map; -}; - struct mlx5e_ipsec_tx_create_attr { int prio; int pol_level; @@ -248,6 +243,7 @@ struct mlx5e_ipsec { struct mlx5_ipsec_fs *roce; u8 is_uplink_rep: 1; struct mlx5e_ipsec_mpv_work mpv_work; + struct xarray ipsec_obj_id_map; }; struct mlx5e_ipsec_esn_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index f41c976dc33f..c1e89dc77db9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -32,6 +32,22 @@ struct mlx5e_ipsec_tx { u8 allow_tunnel_mode : 1; }; +struct mlx5e_ipsec_status_checks { + struct mlx5_flow_group *drop_all_group; + struct mlx5e_ipsec_drop all; +}; + +struct mlx5e_ipsec_rx { + struct mlx5e_ipsec_ft ft; + struct mlx5e_ipsec_miss pol; + struct mlx5e_ipsec_miss sa; + struct mlx5e_ipsec_rule status; + struct mlx5e_ipsec_status_checks status_drops; + struct mlx5e_ipsec_fc *fc; + struct mlx5_fs_chains *chains; + u8 allow_tunnel_mode : 1; +}; + /* IPsec RX flow steering */ static enum mlx5_traffic_types family2tt(u32 family) { @@ -128,14 +144,37 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns, return mlx5_create_auto_grouped_flow_table(ns, &ft_attr); } -static int ipsec_status_rule(struct mlx5_core_dev *mdev, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) +static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + mlx5_del_flow_rules(rx->status_drops.all.rule); + mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc); + mlx5_destroy_flow_group(rx->status_drops.drop_all_group); +} + +static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) { - u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + mlx5_del_flow_rules(rx->status.rule); + + if (rx != ipsec->rx_esw) + return; + +#ifdef CONFIG_MLX5_ESWITCH + mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); +#endif +} + +static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry, + struct mlx5e_ipsec_rx *rx) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; - struct mlx5_modify_hdr *modify_hdr; - struct mlx5_flow_handle *fte; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; struct mlx5_flow_spec *spec; int err; @@ -143,48 +182,273 @@ static int ipsec_status_rule(struct mlx5_core_dev *mdev, if (!spec) return -ENOMEM; - /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */ - MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY); - MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME); - MLX5_SET(copy_action_in, action, src_offset, 0); - MLX5_SET(copy_action_in, action, length, 7); - MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(copy_action_in, action, dst_offset, 24); + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + sa_entry->ipsec_rule.auth.fc = flow_counter; - modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL, - 1, action); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + flow_act.flags = FLOW_ACT_NO_APPEND; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - if (IS_ERR(modify_hdr)) { - err = PTR_ERR(modify_hdr); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.metadata_reg_c_2, + sa_entry->ipsec_obj_id | BIT(31)); + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); mlx5_core_err(mdev, - "fail to alloc ipsec copy modify_header_id err=%d\n", err); - goto out_spec; + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; } + sa_entry->ipsec_rule.auth.rule = rule; - /* create fte */ - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt_2; + } + sa_entry->ipsec_rule.trailer.fc = flow_counter; + + dest.counter_id = mlx5_fc_id(flow_counter); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2); + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule_2; + } + sa_entry->ipsec_rule.trailer.rule = rule; + + kvfree(spec); + return 0; + +err_rule_2: + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.trailer.fc); +err_cnt_2: + mlx5_del_flow_rules(sa_entry->ipsec_rule.auth.rule); +err_rule: + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.auth.fc); +err_cnt: + kvfree(spec); + return err; +} + +static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_ipsec_rx *rx) +{ + struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + flow_counter = mlx5_fc_create(mdev, true); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + flow_act.flags = FLOW_ACT_NO_APPEND; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2); + MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_2, + sa_entry->ipsec_obj_id | BIT(31)); + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; + } + + sa_entry->ipsec_rule.replay.rule = rule; + sa_entry->ipsec_rule.replay.fc = flow_counter; + + kvfree(spec); + return 0; + +err_rule: + mlx5_fc_destroy(mdev, flow_counter); +err_cnt: + kvfree(spec); + return err; +} + +static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; + struct mlx5_flow_spec *spec; + struct mlx5_flow_group *g; + u32 *flow_group_in; + int err = 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!flow_group_in || !spec) { + err = -ENOMEM; + goto err_out; + } + + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); + g = mlx5_create_flow_group(ft, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop flow group, err=%d\n", err); + goto err_out; + } + + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; + } + + rx->status_drops.drop_all_group = g; + rx->status_drops.all.rule = rule; + rx->status_drops.all.fc = flow_counter; + + kvfree(flow_group_in); + kvfree(spec); + return 0; + +err_rule: + mlx5_fc_destroy(mdev, flow_counter); +err_cnt: + mlx5_destroy_flow_group(g); +err_out: + kvfree(flow_group_in); + kvfree(spec); + return err; +} + +static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.ipsec_syndrome); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.metadata_reg_c_4); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.ipsec_syndrome, 0); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.metadata_reg_c_4, 0); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + flow_act.flags = FLOW_ACT_NO_APPEND; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - flow_act.modify_hdr = modify_hdr; - fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); - if (IS_ERR(fte)) { - err = PTR_ERR(fte); - mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err); - goto out; + rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_warn(ipsec->mdev, + "Failed to add ipsec rx status pass rule, err=%d\n", err); + goto err_rule; } + rx->status.rule = rule; kvfree(spec); - rx->status.rule = fte; - rx->status.modify_hdr = modify_hdr; return 0; -out: - mlx5_modify_header_dealloc(mdev, modify_hdr); -out_spec: +err_rule: kvfree(spec); return err; } +static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + ipsec_rx_status_pass_destroy(ipsec, rx); + ipsec_rx_status_drop_destroy(ipsec, rx); +} + +static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + int err; + + err = ipsec_rx_status_drop_all_create(ipsec, rx); + if (err) + return err; + + err = ipsec_rx_status_pass_create(ipsec, rx, dest); + if (err) + goto err_pass_create; + + return 0; + +err_pass_create: + ipsec_rx_status_drop_destroy(ipsec, rx); + return err; +} + static int ipsec_miss_create(struct mlx5_core_dev *mdev, struct mlx5_flow_table *ft, struct mlx5e_ipsec_miss *miss, @@ -333,12 +597,7 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, mlx5_destroy_flow_table(rx->ft.sa); if (rx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); - if (rx == ipsec->rx_esw) { - mlx5_esw_ipsec_rx_status_destroy(ipsec, rx); - } else { - mlx5_del_flow_rules(rx->status.rule); - mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); - } + mlx5_ipsec_rx_status_destroy(ipsec, rx); mlx5_destroy_flow_table(rx->ft.status); mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev); @@ -419,7 +678,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, if (err) return err; - ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 0); + ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0); if (IS_ERR(ft)) { err = PTR_ERR(ft); goto err_fs_ft_status; @@ -428,10 +687,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; dest[1].counter_id = mlx5_fc_id(rx->fc->cnt); - if (rx == ipsec->rx_esw) - err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest); - else - err = ipsec_status_rule(mdev, rx, dest); + err = mlx5_ipsec_rx_status_create(ipsec, rx, dest); if (err) goto err_add; @@ -956,13 +1212,22 @@ static void setup_fte_esp(struct mlx5_flow_spec *spec) MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP); } -static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi) +static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap) { /* SPI number */ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi); - MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi); + if (encap) { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters.inner_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters.inner_esp_spi, spi); + } else { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters.outer_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters.outer_esp_spi, spi); + } } static void setup_fte_no_frags(struct mlx5_flow_spec *spec) @@ -1052,29 +1317,48 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8 struct mlx5_flow_act *flow_act) { enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir); - u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + u8 action[3][MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; struct mlx5_core_dev *mdev = ipsec->mdev; struct mlx5_modify_hdr *modify_hdr; + u8 num_of_actions = 1; - MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[0], action_type, MLX5_ACTION_TYPE_SET); switch (dir) { case XFRM_DEV_OFFLOAD_IN: - MLX5_SET(set_action_in, action, field, + MLX5_SET(set_action_in, action[0], field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); + + num_of_actions++; + MLX5_SET(set_action_in, action[1], action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[1], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_2); + MLX5_SET(set_action_in, action[1], data, val); + MLX5_SET(set_action_in, action[1], offset, 0); + MLX5_SET(set_action_in, action[1], length, 32); + + if (type == XFRM_DEV_OFFLOAD_CRYPTO) { + num_of_actions++; + MLX5_SET(set_action_in, action[2], action_type, + MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action[2], field, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_4); + MLX5_SET(set_action_in, action[2], data, 0); + MLX5_SET(set_action_in, action[2], offset, 0); + MLX5_SET(set_action_in, action[2], length, 32); + } break; case XFRM_DEV_OFFLOAD_OUT: - MLX5_SET(set_action_in, action, field, + MLX5_SET(set_action_in, action[0], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_4); break; default: return -EINVAL; } - MLX5_SET(set_action_in, action, data, val); - MLX5_SET(set_action_in, action, offset, 0); - MLX5_SET(set_action_in, action, length, 32); + MLX5_SET(set_action_in, action[0], data, val); + MLX5_SET(set_action_in, action[0], offset, 0); + MLX5_SET(set_action_in, action[0], length, 32); - modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, 1, action); + modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, num_of_actions, action); if (IS_ERR(modify_hdr)) { mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n", PTR_ERR(modify_hdr)); @@ -1321,8 +1605,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) else setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); - setup_fte_spi(spec, attrs->spi); - setup_fte_esp(spec); + setup_fte_spi(spec, attrs->spi, attrs->encap); + if (!attrs->encap) + setup_fte_esp(spec); setup_fte_no_frags(spec); setup_fte_upper_proto_match(spec, &attrs->upspec); @@ -1372,6 +1657,15 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err); goto err_add_flow; } + if (attrs->type == XFRM_DEV_OFFLOAD_PACKET) + err = rx_add_rule_drop_replay(sa_entry, rx); + if (err) + goto err_add_replay; + + err = rx_add_rule_drop_auth_trailer(sa_entry, rx); + if (err) + goto err_drop_reason; + kvfree(spec); sa_entry->ipsec_rule.rule = rule; @@ -1380,6 +1674,13 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat; return 0; +err_drop_reason: + if (sa_entry->ipsec_rule.replay.rule) { + mlx5_del_flow_rules(sa_entry->ipsec_rule.replay.rule); + mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc); + } +err_add_replay: + mlx5_del_flow_rules(rule); err_add_flow: mlx5_fc_destroy(mdev, counter); err_add_cnt: @@ -1428,7 +1729,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) switch (attrs->type) { case XFRM_DEV_OFFLOAD_CRYPTO: - setup_fte_spi(spec, attrs->spi); + setup_fte_spi(spec, attrs->spi, false); setup_fte_esp(spec); setup_fte_reg_a(spec); break; @@ -1809,8 +2110,11 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) struct mlx5_eswitch *esw = mdev->priv.eswitch; int err = 0; - if (esw) - down_write(&esw->mode_lock); + if (esw) { + err = mlx5_esw_lock(esw); + if (err) + return err; + } if (mdev->num_block_ipsec) { err = -EBUSY; @@ -1821,7 +2125,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) unlock: if (esw) - up_write(&esw->mode_lock); + mlx5_esw_unlock(esw); return err; } @@ -1887,6 +2191,17 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry) if (ipsec_rule->modify_hdr) mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr); + + mlx5_del_flow_rules(ipsec_rule->trailer.rule); + mlx5_fc_destroy(mdev, ipsec_rule->trailer.fc); + + mlx5_del_flow_rules(ipsec_rule->auth.rule); + mlx5_fc_destroy(mdev, ipsec_rule->auth.fc); + + if (ipsec_rule->replay.rule) { + mlx5_del_flow_rules(ipsec_rule->replay.rule); + mlx5_fc_destroy(mdev, ipsec_rule->replay.fc); + } mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry); rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type); } @@ -1957,7 +2272,7 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec) kfree(ipsec->rx_ipv6); if (ipsec->is_uplink_rep) { - xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map); + xa_destroy(&ipsec->ipsec_obj_id_map); mutex_destroy(&ipsec->tx_esw->ft.mutex); WARN_ON(ipsec->tx_esw->ft.refcnt); @@ -2020,7 +2335,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec, mutex_init(&ipsec->tx_esw->ft.mutex); mutex_init(&ipsec->rx_esw->ft.mutex); ipsec->tx_esw->ns = ns_esw; - xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1); + xa_init_flags(&ipsec->ipsec_obj_id_map, XA_FLAGS_ALLOC1); } else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) { ipsec->roce = mlx5_ipsec_fs_roce_init(mdev, devcom); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index a91f772dc981..6e00afe4671b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -6,6 +6,8 @@ #include "ipsec.h" #include "lib/crypto.h" #include "lib/ipsec_fs_roce.h" +#include "fs_core.h" +#include "eswitch.h" enum { MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET, @@ -38,7 +40,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp)) caps |= MLX5_IPSEC_CAP_CRYPTO; - if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload)) { + if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) && + (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS || + (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS && + is_mdev_legacy_mode(mdev)))) { if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_esp_trasport) && MLX5_CAP_FLOWTABLE_NIC_RX(mdev, @@ -95,7 +100,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, if (attrs->dir == XFRM_DEV_OFFLOAD_IN) { MLX5_SET(ipsec_aso, aso_ctx, window_sz, - attrs->replay_esn.replay_window / 64); + attrs->replay_esn.replay_window); MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_REPLAY_PROTECTION); } @@ -559,6 +564,7 @@ void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec) dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx), DMA_BIDIRECTIONAL); kfree(aso); + ipsec->aso = NULL; } static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ea58c6917433..0c87ddb8a7a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2731,6 +2731,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) { int i; + ASSERT_RTNL(); if (chs->ptp) { mlx5e_ptp_close(chs->ptp); chs->ptp = NULL; @@ -3012,17 +3013,29 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) if (mlx5e_is_vport_rep(priv)) mlx5e_rep_activate_channels(priv); + set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state); + mlx5e_wait_channels_min_rx_wqes(&priv->channels); if (priv->rx_res) mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels); } +static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv) +{ + WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)); + if (current_work() != &priv->tx_timeout_work) + cancel_work_sync(&priv->tx_timeout_work); +} + void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { if (priv->rx_res) mlx5e_rx_res_channels_deactivate(priv->rx_res); + clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state); + mlx5e_cancel_tx_timeout_work(priv); + if (mlx5e_is_vport_rep(priv)) mlx5e_rep_deactivate_channels(priv); @@ -4801,8 +4814,17 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) struct net_device *netdev = priv->netdev; int i; - rtnl_lock(); - mutex_lock(&priv->state_lock); + /* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues + * through this flow. However, channel closing flows have to wait for + * this work to finish while holding rtnl lock too. So either get the + * lock or find that channels are being closed for other reason and + * this work is not relevant anymore. + */ + while (!rtnl_trylock()) { + if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) + return; + msleep(20); + } if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; @@ -4821,7 +4843,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) } unlock: - mutex_unlock(&priv->state_lock); rtnl_unlock(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 3ab682bbcf86..1bf7540a65ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1497,7 +1497,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) { + if (!IS_ERR(dl_port)) { SET_NETDEV_DEVLINK_PORT(netdev, dl_port); mlx5e_rep_vnic_reporter_create(priv, dl_port); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 7ca9e5b86778..4809a66f3491 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -444,6 +444,9 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv, struct mlx5e_flow_meter_handle *meter; enum mlx5e_post_meter_type type; + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params); if (IS_ERR(meter)) { mlx5_core_err(priv->mdev, "Failed to get flow meter\n"); @@ -3739,6 +3742,20 @@ out_free: } static int +set_branch_dest_ft(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) +{ + struct mlx5e_post_act *post_act = get_post_action(priv); + + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act); + + return 0; +} + +static int alloc_branch_attr(struct mlx5e_tc_flow *flow, struct mlx5e_tc_act_branch_ctrl *cond, struct mlx5_flow_attr **cond_attr, @@ -3761,8 +3778,8 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow, break; case FLOW_ACTION_ACCEPT: case FLOW_ACTION_PIPE: - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + if (set_branch_dest_ft(flow->priv, attr)) + goto out_err; break; case FLOW_ACTION_JUMP: if (*jump_count) { @@ -3771,8 +3788,8 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow, goto out_err; } *jump_count = cond->extval; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + if (set_branch_dest_ft(flow->priv, attr)) + goto out_err; break; default: err = -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 095f31f380fa..190f10aba170 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -21,158 +21,6 @@ enum { MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL, }; -static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - mlx5_del_flow_rules(rx->status_drop.rule); - mlx5_destroy_flow_group(rx->status_drop.group); - mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt); -} - -static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - mlx5_del_flow_rules(rx->status.rule); - mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); -} - -static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5_flow_table *ft = rx->ft.status; - struct mlx5_core_dev *mdev = ipsec->mdev; - struct mlx5_flow_destination dest = {}; - struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_handle *rule; - struct mlx5_fc *flow_counter; - struct mlx5_flow_spec *spec; - struct mlx5_flow_group *g; - u32 *flow_group_in; - int err = 0; - - flow_group_in = kvzalloc(inlen, GFP_KERNEL); - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!flow_group_in || !spec) { - err = -ENOMEM; - goto err_out; - } - - MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); - g = mlx5_create_flow_group(ft, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop flow group, err=%d\n", err); - goto err_out; - } - - flow_counter = mlx5_fc_create(mdev, false); - if (IS_ERR(flow_counter)) { - err = PTR_ERR(flow_counter); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop rule counter, err=%d\n", err); - goto err_cnt; - } - - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; - dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(flow_counter); - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop rule, err=%d\n", err); - goto err_rule; - } - - rx->status_drop.group = g; - rx->status_drop.rule = rule; - rx->status_drop_cnt = flow_counter; - - kvfree(flow_group_in); - kvfree(spec); - return 0; - -err_rule: - mlx5_fc_destroy(mdev, flow_counter); -err_cnt: - mlx5_destroy_flow_group(g); -err_out: - kvfree(flow_group_in); - kvfree(spec); - return err; -} - -static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_handle *rule; - struct mlx5_flow_spec *spec; - int err; - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return -ENOMEM; - - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, - misc_parameters_2.ipsec_syndrome); - MLX5_SET(fte_match_param, spec->match_value, - misc_parameters_2.ipsec_syndrome, 0); - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; - flow_act.flags = FLOW_ACT_NO_APPEND; - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_warn(ipsec->mdev, - "Failed to add ipsec rx status pass rule, err=%d\n", err); - goto err_rule; - } - - rx->status.rule = rule; - kvfree(spec); - return 0; - -err_rule: - kvfree(spec); - return err; -} - -void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - esw_ipsec_rx_status_pass_destroy(ipsec, rx); - esw_ipsec_rx_status_drop_destroy(ipsec, rx); -} - -int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - int err; - - err = esw_ipsec_rx_status_drop_create(ipsec, rx); - if (err) - return err; - - err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest); - if (err) - goto err_pass_create; - - return 0; - -err_pass_create: - esw_ipsec_rx_status_drop_destroy(ipsec, rx); - return err; -} - void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr) { @@ -202,7 +50,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, u32 mapped_id; int err; - err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id, + err = xa_alloc_bh(&ipsec->ipsec_obj_id_map, &mapped_id, xa_mk_value(sa_entry->ipsec_obj_id), XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0); if (err) @@ -233,7 +81,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry, return 0; err_header_alloc: - xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id); + xa_erase_bh(&ipsec->ipsec_obj_id_map, mapped_id); return err; } @@ -242,7 +90,7 @@ void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry) struct mlx5e_ipsec *ipsec = sa_entry->ipsec; if (sa_entry->rx_mapped_id) - xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, + xa_erase_bh(&ipsec->ipsec_obj_id_map, sa_entry->rx_mapped_id); } @@ -252,7 +100,7 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id, struct mlx5e_ipsec *ipsec = priv->ipsec; void *val; - val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id); + val = xa_load(&ipsec->ipsec_obj_id_map, id); if (!val) return -ENOENT; @@ -304,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) xa_for_each(&esw->offloads.vport_reps, i, rep) { rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev) + if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems)) continue; rhashtable_walk_enter(&rpriv->tc_ht, &iter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h index 0c90f7a8b0d3..ac9c65b89166 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h @@ -8,11 +8,6 @@ struct mlx5e_ipsec; struct mlx5e_ipsec_sa_entry; #ifdef CONFIG_MLX5_ESWITCH -void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx); -int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest); void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr); int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, @@ -26,16 +21,6 @@ void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx_create_attr *attr); void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev); #else -static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) {} - -static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - return -EINVAL; -} - static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr) {} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 8d0b915a3121..3047d7015c52 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1463,7 +1463,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) { int err; - lockdep_assert_held(&esw->mode_lock); + devl_assert_locked(priv_to_devlink(esw->dev)); if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "FDB is not supported, aborting ...\n"); @@ -1531,7 +1531,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) if (toggle_lag) mlx5_lag_disable_change(esw->dev); - down_write(&esw->mode_lock); if (!mlx5_esw_is_fdb_created(esw)) { ret = mlx5_eswitch_enable_locked(esw, num_vfs); } else { @@ -1554,8 +1553,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) } } - up_write(&esw->mode_lock); - if (toggle_lag) mlx5_lag_enable_change(esw->dev); @@ -1569,12 +1566,11 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) return; devl_assert_locked(priv_to_devlink(esw->dev)); - down_write(&esw->mode_lock); /* If driver is unloaded, this function is called twice by remove_one() * and mlx5_unload(). Prevent the second call. */ if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf) - goto unlock; + return; esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", @@ -1603,9 +1599,6 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) esw->esw_funcs.num_vfs = 0; else esw->esw_funcs.num_ec_vfs = 0; - -unlock: - up_write(&esw->mode_lock); } /* Free resources for corresponding eswitch mode. It is called by devlink @@ -1647,10 +1640,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) devl_assert_locked(priv_to_devlink(esw->dev)); mlx5_lag_disable_change(esw->dev); - down_write(&esw->mode_lock); mlx5_eswitch_disable_locked(esw); esw->mode = MLX5_ESWITCH_LEGACY; - up_write(&esw->mode_lock); mlx5_lag_enable_change(esw->dev); } @@ -2254,8 +2245,13 @@ bool mlx5_esw_hold(struct mlx5_core_dev *mdev) if (!mlx5_esw_allowed(esw)) return true; - if (down_read_trylock(&esw->mode_lock) != 0) + if (down_read_trylock(&esw->mode_lock) != 0) { + if (esw->eswitch_operation_in_progress) { + up_read(&esw->mode_lock); + return false; + } return true; + } return false; } @@ -2312,7 +2308,8 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) if (down_write_trylock(&esw->mode_lock) == 0) return -EINVAL; - if (atomic64_read(&esw->user_count) > 0) { + if (esw->eswitch_operation_in_progress || + atomic64_read(&esw->user_count) > 0) { up_write(&esw->mode_lock); return -EBUSY; } @@ -2320,6 +2317,18 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) return esw->mode; } +int mlx5_esw_lock(struct mlx5_eswitch *esw) +{ + down_write(&esw->mode_lock); + + if (esw->eswitch_operation_in_progress) { + up_write(&esw->mode_lock); + return -EBUSY; + } + + return 0; +} + /** * mlx5_esw_unlock() - Release write lock on esw mode lock * @esw: eswitch device. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 37ab66e7b403..b674b57d05aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -383,6 +383,7 @@ struct mlx5_eswitch { struct xarray paired; struct mlx5_devcom_comp_dev *devcom; u16 enabled_ipsec_vf_count; + bool eswitch_operation_in_progress; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -827,6 +828,7 @@ void mlx5_esw_release(struct mlx5_core_dev *dev); void mlx5_esw_get(struct mlx5_core_dev *dev); void mlx5_esw_put(struct mlx5_core_dev *dev); int mlx5_esw_try_lock(struct mlx5_eswitch *esw); +int mlx5_esw_lock(struct mlx5_eswitch *esw); void mlx5_esw_unlock(struct mlx5_eswitch *esw); void esw_vport_change_handle_locked(struct mlx5_vport *vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 88236e75fd90..bb8bcb448ae9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3653,14 +3653,18 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink) { + struct mlx5_core_dev *dev = devlink_priv(devlink); struct net *devl_net, *netdev_net; - struct mlx5_eswitch *esw; - - esw = mlx5_devlink_eswitch_nocheck_get(devlink); - netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev); - devl_net = devlink_net(devlink); + bool ret = false; - return net_eq(devl_net, netdev_net); + mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); + if (dev->mlx5e_res.uplink_netdev) { + netdev_net = dev_net(dev->mlx5e_res.uplink_netdev); + devl_net = devlink_net(devlink); + ret = net_eq(devl_net, netdev_net); + } + mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); + return ret; } int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) @@ -3733,13 +3737,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, goto unlock; } + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + mlx5_eswitch_disable_locked(esw); if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { if (mlx5_devlink_trap_get_num_active(esw->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can't change mode while devlink traps are active"); err = -EOPNOTSUPP; - goto unlock; + goto skip; } err = esw_offloads_start(esw, extack); } else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) { @@ -3749,6 +3756,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, err = -EINVAL; } +skip: + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; unlock: mlx5_esw_unlock(esw); enable_lag: @@ -3759,16 +3769,12 @@ enable_lag: int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) { struct mlx5_eswitch *esw; - int err; esw = mlx5_devlink_eswitch_get(devlink); if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); - err = esw_mode_to_devlink(esw->mode, mode); - up_read(&esw->mode_lock); - return err; + return esw_mode_to_devlink(esw->mode, mode); } static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode, @@ -3862,11 +3868,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, if (err) goto out; + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack); - if (err) - goto out; + if (!err) + esw->offloads.inline_mode = mlx5_mode; - esw->offloads.inline_mode = mlx5_mode; + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; up_write(&esw->mode_lock); return 0; @@ -3878,16 +3888,12 @@ out: int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) { struct mlx5_eswitch *esw; - int err; esw = mlx5_devlink_eswitch_get(devlink); if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); - err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); - up_read(&esw->mode_lock); - return err; + return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); } bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev) @@ -3969,6 +3975,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, goto unlock; } + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + esw_destroy_offloads_fdb_tables(esw); esw->offloads.encap = encap; @@ -3982,6 +3991,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, (void)esw_create_offloads_fdb_tables(esw); } + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; + unlock: up_write(&esw->mode_lock); return err; @@ -3996,9 +4008,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); *encap = esw->offloads.encap; - up_read(&esw->mode_lock); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index b568988e92e3..c4e19d627da2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -325,6 +325,29 @@ static void mlx5_fw_live_patch_event(struct work_struct *work) mlx5_core_err(dev, "Failed to reload FW tracer\n"); } +#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE) +static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev) +{ + struct pci_dev *bridge = dev->pdev->bus->self; + u16 reg16; + int err; + + if (!bridge) + return -EOPNOTSUPP; + + err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, ®16); + if (err) + return err; + + if ((reg16 & PCI_EXP_SLTCTL_HPIE) && (reg16 & PCI_EXP_SLTCTL_DLLSCE)) { + mlx5_core_warn(dev, "FW reset is not supported as HotPlug is enabled\n"); + return -EOPNOTSUPP; + } + + return 0; +} +#endif + static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id) { struct pci_bus *bridge_bus = dev->pdev->bus; @@ -357,6 +380,12 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev) return false; } +#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE) + err = mlx5_check_hotplug_interrupt(dev); + if (err) + return false; +#endif + err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id); if (err) return false; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 65e20693c549..33f4f58ee51c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -933,6 +933,7 @@ static void qed_ilt_shadow_free(struct qed_hwfn *p_hwfn) p_dma->virt_addr = NULL; } kfree(p_mngr->ilt_shadow); + p_mngr->ilt_shadow = NULL; } static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index 6f2fa2a42770..1822f2ad8f0d 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -30,6 +30,8 @@ #define QCASPI_MAX_REGS 0x20 +#define QCASPI_RX_MAX_FRAMES 4 + static const u16 qcaspi_spi_regs[] = { SPI_REG_BFR_SIZE, SPI_REG_WRBUF_SPC_AVA, @@ -252,9 +254,9 @@ qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, { struct qcaspi *qca = netdev_priv(dev); - ring->rx_max_pending = 4; + ring->rx_max_pending = QCASPI_RX_MAX_FRAMES; ring->tx_max_pending = TX_RING_MAX_LEN; - ring->rx_pending = 4; + ring->rx_pending = QCASPI_RX_MAX_FRAMES; ring->tx_pending = qca->txr.count; } @@ -263,22 +265,21 @@ qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { - const struct net_device_ops *ops = dev->netdev_ops; struct qcaspi *qca = netdev_priv(dev); - if ((ring->rx_pending) || + if (ring->rx_pending != QCASPI_RX_MAX_FRAMES || (ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; - if (netif_running(dev)) - ops->ndo_stop(dev); + if (qca->spi_thread) + kthread_park(qca->spi_thread); qca->txr.count = max_t(u32, ring->tx_pending, TX_RING_MIN_LEN); qca->txr.count = min_t(u16, qca->txr.count, TX_RING_MAX_LEN); - if (netif_running(dev)) - ops->ndo_open(dev); + if (qca->spi_thread) + kthread_unpark(qca->spi_thread); return 0; } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index bec723028e96..5f3c11fb3fa2 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -580,6 +580,18 @@ qcaspi_spi_thread(void *data) netdev_info(qca->net_dev, "SPI thread created\n"); while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); + if (kthread_should_park()) { + netif_tx_disable(qca->net_dev); + netif_carrier_off(qca->net_dev); + qcaspi_flush_tx_ring(qca); + kthread_parkme(); + if (qca->sync == QCASPI_SYNC_READY) { + netif_carrier_on(qca->net_dev); + netif_wake_queue(qca->net_dev); + } + continue; + } + if ((qca->intr_req == qca->intr_svc) && !qca->txr.skb[qca->txr.head]) schedule(); @@ -608,11 +620,17 @@ qcaspi_spi_thread(void *data) if (intr_cause & SPI_INT_CPU_ON) { qcaspi_qca7k_sync(qca, QCASPI_EVENT_CPUON); + /* Frame decoding in progress */ + if (qca->frm_handle.state != qca->frm_handle.init) + qca->net_dev->stats.rx_dropped++; + + qcafrm_fsm_init_spi(&qca->frm_handle); + qca->stats.device_reset++; + /* not synced. */ if (qca->sync != QCASPI_SYNC_READY) continue; - qca->stats.device_reset++; netif_wake_queue(qca->net_dev); netif_carrier_on(qca->net_dev); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 2cd6fce5c993..9e40c28d453a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -59,26 +59,19 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id return -ENODEV; } - if (!of_device_is_compatible(np, "loongson, pci-gmac")) { - pr_info("dwmac_loongson_pci: Incompatible OF node\n"); - return -ENODEV; - } - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) return -ENOMEM; + plat->mdio_bus_data = devm_kzalloc(&pdev->dev, + sizeof(*plat->mdio_bus_data), + GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; + plat->mdio_node = of_get_child_by_name(np, "mdio"); if (plat->mdio_node) { dev_info(&pdev->dev, "Found MDIO subnode\n"); - - plat->mdio_bus_data = devm_kzalloc(&pdev->dev, - sizeof(*plat->mdio_bus_data), - GFP_KERNEL); - if (!plat->mdio_bus_data) { - ret = -ENOMEM; - goto err_put_node; - } plat->mdio_bus_data->needs_reset = true; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index d3bf42d0fceb..31631e3f89d0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -34,6 +34,7 @@ #define RGMII_CONFIG_LOOPBACK_EN BIT(2) #define RGMII_CONFIG_PROG_SWAP BIT(1) #define RGMII_CONFIG_DDR_MODE BIT(0) +#define RGMII_CONFIG_SGMII_CLK_DVDR GENMASK(18, 10) /* SDCC_HC_REG_DLL_CONFIG fields */ #define SDCC_DLL_CONFIG_DLL_RST BIT(30) @@ -78,6 +79,8 @@ #define ETHQOS_MAC_CTRL_SPEED_MODE BIT(14) #define ETHQOS_MAC_CTRL_PORT_SEL BIT(15) +#define SGMII_10M_RX_CLK_DVDR 0x31 + struct ethqos_emac_por { unsigned int offset; unsigned int value; @@ -598,6 +601,9 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos) return 0; } +/* On interface toggle MAC registers gets reset. + * Configure MAC block for SGMII on ethernet phy link up + */ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) { int val; @@ -617,6 +623,10 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) case SPEED_10: val |= ETHQOS_MAC_CTRL_PORT_SEL; val &= ~ETHQOS_MAC_CTRL_SPEED_MODE; + rgmii_updatel(ethqos, RGMII_CONFIG_SGMII_CLK_DVDR, + FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR, + SGMII_10M_RX_CLK_DVDR), + RGMII_IO_MACRO_CONFIG); break; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index fa9e7e7040b9..0542cfd1817e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -591,7 +591,11 @@ int stmmac_mdio_register(struct net_device *ndev) new_bus->parent = priv->device; err = of_mdiobus_register(new_bus, mdio_node); - if (err != 0) { + if (err == -ENODEV) { + err = 0; + dev_info(dev, "MDIO bus is disabled\n"); + goto bus_register_fail; + } else if (err) { dev_err_probe(dev, err, "Cannot register the MDIO bus\n"); goto bus_register_fail; } diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 508d9a392ab1..f575f225d417 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -281,8 +281,10 @@ static int __team_options_register(struct team *team, return 0; inst_rollback: - for (i--; i >= 0; i--) + for (i--; i >= 0; i--) { __team_option_inst_del_option(team, dst_opts[i]); + list_del(&dst_opts[i]->list); + } i = option_count; alloc_rollback: diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 6902e97719d1..11c80555d975 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -968,9 +968,12 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata) { - /* Downstream devices need to be in D0 state before enabling PCI PM substates */ + /* + * Downstream devices need to be in D0 state before enabling PCI PM + * substates. + */ pci_set_power_state(pdev, PCI_D0); - pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL); + pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); return 0; } diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c index d45e7b8dc530..8b34ccff073a 100644 --- a/drivers/pci/controller/pci-loongson.c +++ b/drivers/pci/controller/pci-loongson.c @@ -80,13 +80,49 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DEV_LS7A_LPC, system_bus_quirk); +/* + * Some Loongson PCIe ports have hardware limitations on their Maximum Read + * Request Size. They can't handle anything larger than this. Sane + * firmware will set proper MRRS at boot, so we only need no_inc_mrrs for + * bridges. However, some MIPS Loongson firmware doesn't set MRRS properly, + * so we have to enforce maximum safe MRRS, which is 256 bytes. + */ +#ifdef CONFIG_MIPS +static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev) +{ + struct pci_bus *bus = pdev->bus; + struct pci_dev *bridge; + static const struct pci_device_id bridge_devids[] = { + { PCI_VDEVICE(LOONGSON, DEV_LS2K_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT1) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT2) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT3) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT4) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT5) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT6) }, + { 0, }, + }; + + /* look for the matching bridge */ + while (!pci_is_root_bus(bus)) { + bridge = bus->self; + bus = bus->parent; + + if (pci_match_id(bridge_devids, bridge)) { + if (pcie_get_readrq(pdev) > 256) { + pci_info(pdev, "limiting MRRS to 256\n"); + pcie_set_readrq(pdev, 256); + } + break; + } + } +} +DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_set_min_mrrs_quirk); +#endif + static void loongson_mrrs_quirk(struct pci_dev *pdev) { - /* - * Some Loongson PCIe ports have h/w limitations of maximum read - * request size. They can't handle anything larger than this. So - * force this limit on any devices attached under these ports. - */ struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); bridge->no_inc_mrrs = 1; diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 94ba61fe1c44..0452cbc362ee 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -751,7 +751,7 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata) if (!(features & VMD_FEAT_BIOS_PM_QUIRK)) return 0; - pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL); + pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR); if (!pos) diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 601129772b2d..5b1f271c6034 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -512,15 +512,12 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); - if (pci_is_root_bus(bus)) - __pci_bus_size_bridges(dev->subordinate, &add_list); + __pci_bus_size_bridges(dev->subordinate, + &add_list); } } } - if (pci_is_root_bus(bus)) - __pci_bus_assign_resources(bus, &add_list, NULL); - else - pci_assign_unassigned_bridge_resources(bus->self); + __pci_bus_assign_resources(bus, &add_list, NULL); } acpiphp_sanitize_bus(bus); diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 50b04ae5c394..5dab531c8654 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1041,7 +1041,7 @@ static struct pcie_link_state *pcie_aspm_get_link(struct pci_dev *pdev) return bridge->link_state; } -static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) +static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool locked) { struct pcie_link_state *link = pcie_aspm_get_link(pdev); @@ -1060,7 +1060,7 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) return -EPERM; } - if (sem) + if (!locked) down_read(&pci_bus_sem); mutex_lock(&aspm_lock); if (state & PCIE_LINK_STATE_L0S) @@ -1082,7 +1082,7 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) link->clkpm_disable = 1; pcie_set_clkpm(link, policy_to_clkpm_state(link)); mutex_unlock(&aspm_lock); - if (sem) + if (!locked) up_read(&pci_bus_sem); return 0; @@ -1090,7 +1090,9 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) int pci_disable_link_state_locked(struct pci_dev *pdev, int state) { - return __pci_disable_link_state(pdev, state, false); + lockdep_assert_held_read(&pci_bus_sem); + + return __pci_disable_link_state(pdev, state, true); } EXPORT_SYMBOL(pci_disable_link_state_locked); @@ -1105,21 +1107,11 @@ EXPORT_SYMBOL(pci_disable_link_state_locked); */ int pci_disable_link_state(struct pci_dev *pdev, int state) { - return __pci_disable_link_state(pdev, state, true); + return __pci_disable_link_state(pdev, state, false); } EXPORT_SYMBOL(pci_disable_link_state); -/** - * pci_enable_link_state - Clear and set the default device link state so that - * the link may be allowed to enter the specified states. Note that if the - * BIOS didn't grant ASPM control to the OS, this does nothing because we can't - * touch the LNKCTL register. Also note that this does not enable states - * disabled by pci_disable_link_state(). Return 0 or a negative errno. - * - * @pdev: PCI device - * @state: Mask of ASPM link states to enable - */ -int pci_enable_link_state(struct pci_dev *pdev, int state) +static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked) { struct pcie_link_state *link = pcie_aspm_get_link(pdev); @@ -1136,7 +1128,8 @@ int pci_enable_link_state(struct pci_dev *pdev, int state) return -EPERM; } - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); link->aspm_default = 0; if (state & PCIE_LINK_STATE_L0S) @@ -1157,12 +1150,48 @@ int pci_enable_link_state(struct pci_dev *pdev, int state) link->clkpm_default = (state & PCIE_LINK_STATE_CLKPM) ? 1 : 0; pcie_set_clkpm(link, policy_to_clkpm_state(link)); mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); return 0; } + +/** + * pci_enable_link_state - Clear and set the default device link state so that + * the link may be allowed to enter the specified states. Note that if the + * BIOS didn't grant ASPM control to the OS, this does nothing because we can't + * touch the LNKCTL register. Also note that this does not enable states + * disabled by pci_disable_link_state(). Return 0 or a negative errno. + * + * @pdev: PCI device + * @state: Mask of ASPM link states to enable + */ +int pci_enable_link_state(struct pci_dev *pdev, int state) +{ + return __pci_enable_link_state(pdev, state, false); +} EXPORT_SYMBOL(pci_enable_link_state); +/** + * pci_enable_link_state_locked - Clear and set the default device link state + * so that the link may be allowed to enter the specified states. Note that if + * the BIOS didn't grant ASPM control to the OS, this does nothing because we + * can't touch the LNKCTL register. Also note that this does not enable states + * disabled by pci_disable_link_state(). Return 0 or a negative errno. + * + * @pdev: PCI device + * @state: Mask of ASPM link states to enable + * + * Context: Caller holds pci_bus_sem read lock. + */ +int pci_enable_link_state_locked(struct pci_dev *pdev, int state) +{ + lockdep_assert_held_read(&pci_bus_sem); + + return __pci_enable_link_state(pdev, state, true); +} +EXPORT_SYMBOL(pci_enable_link_state_locked); + static int pcie_aspm_set_policy(const char *val, const struct kernel_param *kp) { diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 014010d03588..847b0dc41293 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -1816,7 +1816,7 @@ static int arm_cmn_event_add(struct perf_event *event, int flags) idx = 0; while (cmn->dtc[j].counters[idx]) if (++idx == CMN_DT_NUM_COUNTERS) - goto free_dtms; + return -ENOSPC; } hw->dtc_idx[j] = idx; } diff --git a/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c b/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c index f021ec5a70e5..553725e1269c 100644 --- a/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c +++ b/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c @@ -100,7 +100,7 @@ static void mtk_mipi_tx_pll_disable(struct clk_hw *hw) static long mtk_mipi_tx_pll_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) { - return clamp_val(rate, 50000000, 1600000000); + return clamp_val(rate, 125000000, 1600000000); } static const struct clk_ops mtk_mipi_tx_pll_ops = { diff --git a/drivers/phy/sunplus/phy-sunplus-usb2.c b/drivers/phy/sunplus/phy-sunplus-usb2.c index 0efe74ac9c6a..637a5fbae6d9 100644 --- a/drivers/phy/sunplus/phy-sunplus-usb2.c +++ b/drivers/phy/sunplus/phy-sunplus-usb2.c @@ -275,7 +275,7 @@ static int sp_usb_phy_probe(struct platform_device *pdev) phy = devm_phy_create(&pdev->dev, NULL, &sp_uphy_ops); if (IS_ERR(phy)) { - ret = -PTR_ERR(phy); + ret = PTR_ERR(phy); return ret; } diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index 555b323f45da..bc847d3879f7 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -64,6 +64,7 @@ struct phy_gmii_sel_priv { u32 num_ports; u32 reg_offset; u32 qsgmii_main_ports; + bool no_offset; }; static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode) @@ -402,7 +403,8 @@ static int phy_gmii_sel_init_ports(struct phy_gmii_sel_priv *priv) priv->num_ports = size / sizeof(u32); if (!priv->num_ports) return -EINVAL; - priv->reg_offset = __be32_to_cpu(*offset); + if (!priv->no_offset) + priv->reg_offset = __be32_to_cpu(*offset); } if_phys = devm_kcalloc(dev, priv->num_ports, @@ -471,6 +473,7 @@ static int phy_gmii_sel_probe(struct platform_device *pdev) dev_err(dev, "Failed to get syscon %d\n", ret); return ret; } + priv->no_offset = true; } ret = phy_gmii_sel_init_ports(priv); diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 6fa1735ad7a4..210b0a81b7ec 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -73,10 +73,10 @@ struct intel_vbtn_priv { bool wakeup_mode; }; -static void detect_tablet_mode(struct platform_device *device) +static void detect_tablet_mode(struct device *dev) { - struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev); - acpi_handle handle = ACPI_HANDLE(&device->dev); + struct intel_vbtn_priv *priv = dev_get_drvdata(dev); + acpi_handle handle = ACPI_HANDLE(dev); unsigned long long vgbs; acpi_status status; int m; @@ -89,6 +89,8 @@ static void detect_tablet_mode(struct platform_device *device) input_report_switch(priv->switches_dev, SW_TABLET_MODE, m); m = (vgbs & VGBS_DOCK_MODE_FLAG) ? 1 : 0; input_report_switch(priv->switches_dev, SW_DOCK, m); + + input_sync(priv->switches_dev); } /* @@ -134,7 +136,7 @@ static int intel_vbtn_input_setup(struct platform_device *device) priv->switches_dev->id.bustype = BUS_HOST; if (priv->has_switches) { - detect_tablet_mode(device); + detect_tablet_mode(&device->dev); ret = input_register_device(priv->switches_dev); if (ret) @@ -198,6 +200,9 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE); sparse_keymap_report_event(input_dev, event, val, autorelease); + + /* Some devices need this to report further events */ + acpi_evaluate_object(handle, "VBDL", NULL, NULL); } /* @@ -352,7 +357,13 @@ static void intel_vbtn_pm_complete(struct device *dev) static int intel_vbtn_pm_resume(struct device *dev) { + struct intel_vbtn_priv *priv = dev_get_drvdata(dev); + intel_vbtn_pm_complete(dev); + + if (priv->has_switches) + detect_tablet_mode(dev); + return 0; } diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c index 4dfdbfca6841..c66808601fdd 100644 --- a/drivers/platform/x86/intel_ips.c +++ b/drivers/platform/x86/intel_ips.c @@ -590,6 +590,8 @@ static void ips_disable_gpu_turbo(struct ips_driver *ips) * @ips: IPS driver struct * * Check whether the MCP is over its thermal or power budget. + * + * Returns: %true if the temp or power has exceeded its maximum, else %false */ static bool mcp_exceeded(struct ips_driver *ips) { @@ -619,6 +621,8 @@ static bool mcp_exceeded(struct ips_driver *ips) * @cpu: CPU number to check * * Check a given CPU's average temp or power is over its limit. + * + * Returns: %true if the temp or power has exceeded its maximum, else %false */ static bool cpu_exceeded(struct ips_driver *ips, int cpu) { @@ -645,6 +649,8 @@ static bool cpu_exceeded(struct ips_driver *ips, int cpu) * @ips: IPS driver struct * * Check the MCH temp & power against their maximums. + * + * Returns: %true if the temp or power has exceeded its maximum, else %false */ static bool mch_exceeded(struct ips_driver *ips) { @@ -742,12 +748,13 @@ static void update_turbo_limits(struct ips_driver *ips) * - down (at TDP limit) * - adjust both CPU and GPU down if possible * - cpu+ gpu+ cpu+gpu- cpu-gpu+ cpu-gpu- -cpu < gpu < cpu+gpu+ cpu+ gpu+ nothing -cpu < gpu >= cpu+gpu-(mcp<) cpu+gpu-(mcp<) gpu- gpu- -cpu >= gpu < cpu-gpu+(mcp<) cpu- cpu-gpu+(mcp<) cpu- -cpu >= gpu >= cpu-gpu- cpu-gpu- cpu-gpu- cpu-gpu- + * |cpu+ gpu+ cpu+gpu- cpu-gpu+ cpu-gpu- + * cpu < gpu < |cpu+gpu+ cpu+ gpu+ nothing + * cpu < gpu >= |cpu+gpu-(mcp<) cpu+gpu-(mcp<) gpu- gpu- + * cpu >= gpu < |cpu-gpu+(mcp<) cpu- cpu-gpu+(mcp<) cpu- + * cpu >= gpu >=|cpu-gpu- cpu-gpu- cpu-gpu- cpu-gpu- * + * Returns: %0 */ static int ips_adjust(void *data) { @@ -935,11 +942,13 @@ static void monitor_timeout(struct timer_list *t) * @data: ips driver structure * * This is the main function for the IPS driver. It monitors power and - * tempurature in the MCP and adjusts CPU and GPU power clams accordingly. + * temperature in the MCP and adjusts CPU and GPU power clamps accordingly. * - * We keep a 5s moving average of power consumption and tempurature. Using + * We keep a 5s moving average of power consumption and temperature. Using * that data, along with CPU vs GPU preference, we adjust the power clamps * up or down. + * + * Returns: %0 on success or -errno on error */ static int ips_monitor(void *data) { @@ -1146,6 +1155,8 @@ static void dump_thermal_info(struct ips_driver *ips) * Handle temperature limit trigger events, generally by lowering the clamps. * If we're at a critical limit, we clamp back to the lowest possible value * to prevent emergency shutdown. + * + * Returns: IRQ_NONE or IRQ_HANDLED */ static irqreturn_t ips_irq_handler(int irq, void *arg) { @@ -1293,9 +1304,12 @@ static void ips_debugfs_init(struct ips_driver *ips) /** * ips_detect_cpu - detect whether CPU supports IPS + * @ips: IPS driver struct * * Walk our list and see if we're on a supported CPU. If we find one, * return the limits for it. + * + * Returns: the &ips_mcp_limits struct that matches the boot CPU or %NULL */ static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips) { @@ -1352,6 +1366,8 @@ static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips) * monitor and control graphics turbo mode. If we can find them, we can * enable graphics turbo, otherwise we must disable it to avoid exceeding * thermal and power limits in the MCP. + * + * Returns: %true if the required symbols are found, else %false */ static bool ips_get_i915_syms(struct ips_driver *ips) { diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index d0b5fd4137bc..3392ae99ac3f 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -512,10 +512,10 @@ struct tpacpi_quirk { * Iterates over a quirks list until one is found that matches the * ThinkPad's vendor, BIOS and EC model. * - * Returns 0 if nothing matches, otherwise returns the quirks field of + * Returns: %0 if nothing matches, otherwise returns the quirks field of * the matching &struct tpacpi_quirk entry. * - * The match criteria is: vendor, ec and bios much match. + * The match criteria is: vendor, ec and bios must match. */ static unsigned long __init tpacpi_check_quirks( const struct tpacpi_quirk *qlist, @@ -9303,7 +9303,7 @@ static struct tpacpi_battery_driver_data battery_info; /* ACPI helpers/functions/probes */ -/** +/* * This evaluates a ACPI method call specific to the battery * ACPI extension. The specifics are that an error is marked * in the 32rd bit of the response, so we just check that here. diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c index 82672fcbc2aa..8280baa3254b 100644 --- a/drivers/soundwire/intel_ace2x.c +++ b/drivers/soundwire/intel_ace2x.c @@ -23,8 +23,9 @@ static void intel_shim_vs_init(struct sdw_intel *sdw) { void __iomem *shim_vs = sdw->link_res->shim_vs; - u16 act = 0; + u16 act; + act = intel_readw(shim_vs, SDW_SHIM2_INTEL_VS_ACTMCTL); u16p_replace_bits(&act, 0x1, SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS); act |= SDW_SHIM2_INTEL_VS_ACTMCTL_DACTQE; act |= SDW_SHIM2_INTEL_VS_ACTMCTL_DODS; diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 69719b335bcb..f048b3d55b2e 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -742,14 +742,15 @@ error_1: * sdw_ml_sync_bank_switch: Multilink register bank switch * * @bus: SDW bus instance + * @multi_link: whether this is a multi-link stream with hardware-based sync * * Caller function should free the buffers on error */ -static int sdw_ml_sync_bank_switch(struct sdw_bus *bus) +static int sdw_ml_sync_bank_switch(struct sdw_bus *bus, bool multi_link) { unsigned long time_left; - if (!bus->multi_link) + if (!multi_link) return 0; /* Wait for completion of transfer */ @@ -847,7 +848,7 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) bus->bank_switch_timeout = DEFAULT_BANK_SWITCH_TIMEOUT; /* Check if bank switch was successful */ - ret = sdw_ml_sync_bank_switch(bus); + ret = sdw_ml_sync_bank_switch(bus, multi_link); if (ret < 0) { dev_err(bus->dev, "multi link bank switch failed: %d\n", ret); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index ed1644e7683f..d642d06a453b 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -424,7 +424,7 @@ error_kill_call: if (call->async) { if (cancel_work_sync(&call->async_work)) afs_put_call(call); - afs_put_call(call); + afs_set_call_complete(call, ret, 0); } ac->error = ret; diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 47e7770d0583..79495cd7a794 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -9,6 +9,7 @@ #include "debug.h" #include "errcode.h" #include "error.h" +#include "journal.h" #include "trace.h" #include <linux/prefetch.h> @@ -424,14 +425,11 @@ void bch2_fs_btree_cache_exit(struct bch_fs *c) BUG_ON(btree_node_read_in_flight(b) || btree_node_write_in_flight(b)); - if (btree_node_dirty(b)) - bch2_btree_complete_write(c, b, btree_current_write(b)); - clear_btree_node_dirty_acct(c, b); - btree_node_data_free(c, b); } - BUG_ON(atomic_read(&c->btree_cache.dirty)); + BUG_ON(!bch2_journal_error(&c->journal) && + atomic_read(&c->btree_cache.dirty)); list_splice(&bc->freed_pcpu, &bc->freed_nonpcpu); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 57c20390e10e..5a720f0cd5a6 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -1704,8 +1704,8 @@ int bch2_btree_root_read(struct bch_fs *c, enum btree_id id, return bch2_trans_run(c, __bch2_btree_root_read(trans, id, k, level)); } -void bch2_btree_complete_write(struct bch_fs *c, struct btree *b, - struct btree_write *w) +static void bch2_btree_complete_write(struct bch_fs *c, struct btree *b, + struct btree_write *w) { unsigned long old, new, v = READ_ONCE(b->will_make_reachable); diff --git a/fs/bcachefs/btree_io.h b/fs/bcachefs/btree_io.h index 7e03dd76fb38..e0d7fa5b1dfb 100644 --- a/fs/bcachefs/btree_io.h +++ b/fs/bcachefs/btree_io.h @@ -134,9 +134,6 @@ void bch2_btree_node_read(struct bch_fs *, struct btree *, bool); int bch2_btree_root_read(struct bch_fs *, enum btree_id, const struct bkey_i *, unsigned); -void bch2_btree_complete_write(struct bch_fs *, struct btree *, - struct btree_write *); - bool bch2_btree_post_write_cleanup(struct bch_fs *, struct btree *); enum btree_write_flags { diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 37fbf22de8fc..1b7a5668df7c 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -992,8 +992,6 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc) list_for_each_entry_safe(ck, n, &items, list) { cond_resched(); - bch2_journal_pin_drop(&c->journal, &ck->journal); - list_del(&ck->list); kfree(ck->k); six_lock_exit(&ck->c.lock); diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c index 324767c0ddcc..25fdca00bf7b 100644 --- a/fs/bcachefs/btree_update.c +++ b/fs/bcachefs/btree_update.c @@ -554,6 +554,19 @@ int __must_check bch2_trans_update_seq(struct btree_trans *trans, u64 seq, BTREE_UPDATE_PREJOURNAL); } +static noinline int bch2_btree_insert_clone_trans(struct btree_trans *trans, + enum btree_id btree, + struct bkey_i *k) +{ + struct bkey_i *n = bch2_trans_kmalloc(trans, bkey_bytes(&k->k)); + int ret = PTR_ERR_OR_ZERO(n); + if (ret) + return ret; + + bkey_copy(n, k); + return bch2_btree_insert_trans(trans, btree, n, 0); +} + int __must_check bch2_trans_update_buffered(struct btree_trans *trans, enum btree_id btree, struct bkey_i *k) @@ -564,6 +577,9 @@ int __must_check bch2_trans_update_buffered(struct btree_trans *trans, EBUG_ON(trans->nr_wb_updates > trans->wb_updates_size); EBUG_ON(k->k.u64s > BTREE_WRITE_BUFERED_U64s_MAX); + if (unlikely(trans->journal_replay_not_finished)) + return bch2_btree_insert_clone_trans(trans, btree, k); + trans_for_each_wb_update(trans, i) { if (i->btree == btree && bpos_eq(i->k.k.p, k->k.p)) { bkey_copy(&i->k, k); diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index 6697417273aa..26be38ab6ecb 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -1056,6 +1056,17 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, flags &= ~BCH_WATERMARK_MASK; flags |= watermark; + if (!(flags & BTREE_INSERT_JOURNAL_RECLAIM) && + watermark < c->journal.watermark) { + struct journal_res res = { 0 }; + + ret = drop_locks_do(trans, + bch2_journal_res_get(&c->journal, &res, 1, + watermark|JOURNAL_RES_GET_CHECK)); + if (ret) + return ERR_PTR(ret); + } + while (1) { nr_nodes[!!update_level] += 1 + split; update_level++; diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 71aa5e59787b..2418c528c533 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -471,7 +471,7 @@ int bch2_extent_drop_ptrs(struct btree_trans *trans, * we aren't using the extent overwrite path to delete, we're * just using the normal key deletion path: */ - if (bkey_deleted(&n->k)) + if (bkey_deleted(&n->k) && !(iter->flags & BTREE_ITER_IS_EXTENTS)) n->k.size = 0; return bch2_trans_relock(trans) ?: @@ -591,7 +591,7 @@ int bch2_data_update_init(struct btree_trans *trans, m->data_opts.rewrite_ptrs = 0; /* if iter == NULL, it's just a promote */ if (iter) - ret = bch2_extent_drop_ptrs(trans, iter, k, data_opts); + ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts); goto done; } diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index 1a0f2d571569..2bfff0da7000 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -485,20 +485,15 @@ retry: return ret; } -int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir) +int bch2_empty_dir_snapshot(struct btree_trans *trans, u64 dir, u32 snapshot) { struct btree_iter iter; struct bkey_s_c k; - u32 snapshot; int ret; - ret = bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot); - if (ret) - return ret; - for_each_btree_key_upto_norestart(trans, iter, BTREE_ID_dirents, - SPOS(dir.inum, 0, snapshot), - POS(dir.inum, U64_MAX), 0, k, ret) + SPOS(dir, 0, snapshot), + POS(dir, U64_MAX), 0, k, ret) if (k.k->type == KEY_TYPE_dirent) { ret = -ENOTEMPTY; break; @@ -508,6 +503,14 @@ int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir) return ret; } +int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir) +{ + u32 snapshot; + + return bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot) ?: + bch2_empty_dir_snapshot(trans, dir.inum, snapshot); +} + int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx) { struct btree_trans *trans = bch2_trans_get(c); diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index cd262bf4d9c5..1e3431990abd 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -64,6 +64,7 @@ u64 bch2_dirent_lookup(struct bch_fs *, subvol_inum, const struct bch_hash_info *, const struct qstr *, subvol_inum *); +int bch2_empty_dir_snapshot(struct btree_trans *, u64, u32); int bch2_empty_dir_trans(struct btree_trans *, subvol_inum); int bch2_readdir(struct bch_fs *, subvol_inum, struct dir_context *); diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index f6c92df55270..9d8afcb5979a 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -1294,7 +1294,8 @@ unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, struct bkey_s_c k, unsigned i = 0; bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible) { + if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible || + p.ptr.unwritten) { rewrite_ptrs = 0; goto incompressible; } diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index 5a39bcb597a3..a70b7a03057d 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -413,7 +413,7 @@ retry: if ((arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE) && !arg.src_ptr) - snapshot_src.subvol = to_bch_ei(dir)->ei_inode.bi_subvol; + snapshot_src.subvol = inode_inum(to_bch_ei(dir)).subvol; inode = __bch2_create(file_mnt_idmap(filp), to_bch_ei(dir), dst_dentry, arg.mode|S_IFDIR, diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 4d51be813509..371565e02ff2 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1733,6 +1733,9 @@ static int bch2_unfreeze(struct super_block *sb) struct bch_fs *c = sb->s_fs_info; int ret; + if (test_bit(BCH_FS_EMERGENCY_RO, &c->flags)) + return 0; + down_write(&c->state_lock); ret = bch2_fs_read_write(c); up_write(&c->state_lock); diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index c7849b0753e7..9309cfeecd8d 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -7,6 +7,7 @@ #include "btree_update.h" #include "buckets.h" #include "compress.h" +#include "dirent.h" #include "error.h" #include "extents.h" #include "extent_update.h" @@ -1093,11 +1094,15 @@ static int may_delete_deleted_inode(struct btree_trans *trans, if (ret) goto out; - if (fsck_err_on(S_ISDIR(inode.bi_mode), c, - deleted_inode_is_dir, - "directory %llu:%u in deleted_inodes btree", - pos.offset, pos.snapshot)) - goto delete; + if (S_ISDIR(inode.bi_mode)) { + ret = bch2_empty_dir_snapshot(trans, pos.offset, pos.snapshot); + if (fsck_err_on(ret == -ENOTEMPTY, c, deleted_inode_is_dir, + "non empty directory %llu:%u in deleted_inodes btree", + pos.offset, pos.snapshot)) + goto delete; + if (ret) + goto out; + } if (fsck_err_on(!(inode.bi_flags & BCH_INODE_unlinked), c, deleted_inode_not_unlinked, diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index 489b34046e78..8cf238be6213 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -249,7 +249,7 @@ static bool journal_entry_want_write(struct journal *j) return ret; } -static bool journal_entry_close(struct journal *j) +bool bch2_journal_entry_close(struct journal *j) { bool ret; @@ -383,7 +383,7 @@ static bool journal_quiesced(struct journal *j) bool ret = atomic64_read(&j->seq) == j->seq_ondisk; if (!ret) - journal_entry_close(j); + bch2_journal_entry_close(j); return ret; } @@ -436,7 +436,7 @@ retry: /* * Recheck after taking the lock, so we don't race with another thread - * that just did journal_entry_open() and call journal_entry_close() + * that just did journal_entry_open() and call bch2_journal_entry_close() * unnecessarily */ if (journal_res_get_fast(j, res, flags)) { @@ -1041,7 +1041,7 @@ void bch2_fs_journal_stop(struct journal *j) bch2_journal_reclaim_stop(j); bch2_journal_flush_all_pins(j); - wait_event(j->wait, journal_entry_close(j)); + wait_event(j->wait, bch2_journal_entry_close(j)); /* * Always write a new journal entry, to make sure the clock hands are up diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h index 4c513fca5ef2..2f768e11aec9 100644 --- a/fs/bcachefs/journal.h +++ b/fs/bcachefs/journal.h @@ -266,6 +266,7 @@ static inline union journal_res_state journal_state_buf_put(struct journal *j, u return s; } +bool bch2_journal_entry_close(struct journal *); void bch2_journal_buf_put_final(struct journal *, u64, bool); static inline void __bch2_journal_buf_put(struct journal *j, unsigned idx, u64 seq) diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 0f17fc5f8d68..5de1b68fb8af 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -1599,6 +1599,7 @@ static CLOSURE_CALLBACK(journal_write_done) } while ((v = atomic64_cmpxchg(&j->reservations.counter, old.v, new.v)) != old.v); + bch2_journal_reclaim_fast(j); bch2_journal_space_available(j); closure_wake_up(&w->wait); diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index e63c6eda86af..ec712104addb 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -776,6 +776,9 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush, (1U << JOURNAL_PIN_btree), 0, 0, 0)) *did_work = true; + if (seq_to_flush > journal_cur_seq(j)) + bch2_journal_entry_close(j); + spin_lock(&j->lock); /* * If journal replay hasn't completed, the unreplayed journal entries diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 770ced1c6285..c7d9074c82d9 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -144,7 +144,7 @@ static int bch2_journal_replay(struct bch_fs *c) u64 start_seq = c->journal_replay_seq_start; u64 end_seq = c->journal_replay_seq_start; size_t i; - int ret; + int ret = 0; move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr); keys->gap = keys->nr; diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index 6e1bfe9feb59..37d16e04e671 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -121,6 +121,14 @@ int bch2_trans_mark_reflink_v(struct btree_trans *trans, { check_indirect_extent_deleting(new, &flags); + if (old.k->type == KEY_TYPE_reflink_v && + new->k.type == KEY_TYPE_reflink_v && + old.k->u64s == new->k.u64s && + !memcmp(bkey_s_c_to_reflink_v(old).v->start, + bkey_i_to_reflink_v(new)->v.start, + bkey_val_bytes(&new->k) - 8)) + return 0; + return bch2_trans_mark_extent(trans, btree_id, level, old, new, flags); } diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c index ab743115f169..f3cb7115b530 100644 --- a/fs/bcachefs/sysfs.c +++ b/fs/bcachefs/sysfs.c @@ -276,8 +276,8 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c if (!btree_type_has_ptrs(id)) continue; - for_each_btree_key(trans, iter, id, POS_MIN, - BTREE_ITER_ALL_SNAPSHOTS, k, ret) { + ret = for_each_btree_key2(trans, iter, id, POS_MIN, + BTREE_ITER_ALL_SNAPSHOTS, k, ({ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; struct extent_ptr_decoded p; @@ -309,8 +309,8 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c nr_uncompressed_extents++; else if (compressed) nr_compressed_extents++; - } - bch2_trans_iter_exit(trans, &iter); + 0; + })); } bch2_trans_put(trans); diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 51453d4928fa..2833e8ef4c09 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -199,7 +199,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, start = round_down(start, fs_info->sectorsize); btrfs_free_reserved_data_space_noquota(fs_info, len); - btrfs_qgroup_free_data(inode, reserved, start, len); + btrfs_qgroup_free_data(inode, reserved, start, len, NULL); } /* diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index bbcc3df77646..62cb97f7c94f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4799,6 +4799,32 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, } } +static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *gang[8]; + int i; + int ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + while (1) { + ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix, + (void **)gang, 0, + ARRAY_SIZE(gang), + BTRFS_ROOT_TRANS_TAG); + if (ret == 0) + break; + for (i = 0; i < ret; i++) { + struct btrfs_root *root = gang[i]; + + btrfs_qgroup_free_meta_all_pertrans(root); + radix_tree_tag_clear(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + } + } + spin_unlock(&fs_info->fs_roots_radix_lock); +} + void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_fs_info *fs_info) { @@ -4827,6 +4853,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); + btrfs_free_all_qgroup_pertrans(fs_info); + cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0455935ff558..01423670bc8a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1547,6 +1547,23 @@ out: return ret; } +static void free_head_ref_squota_rsv(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_head *href) +{ + u64 root = href->owning_root; + + /* + * Don't check must_insert_reserved, as this is called from contexts + * where it has already been unset. + */ + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE || + !href->is_data || !is_fstree(root)) + return; + + btrfs_qgroup_free_refroot(fs_info, root, href->reserved_bytes, + BTRFS_QGROUP_RSV_DATA); +} + static int run_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *href, struct btrfs_delayed_ref_node *node, @@ -1569,7 +1586,6 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_squota_delta delta = { .root = href->owning_root, .num_bytes = node->num_bytes, - .rsv_bytes = href->reserved_bytes, .is_data = true, .is_inc = true, .generation = trans->transid, @@ -1586,11 +1602,9 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans, flags, ref->objectid, ref->offset, &key, node->ref_mod, href->owning_root); + free_head_ref_squota_rsv(trans->fs_info, href); if (!ret) ret = btrfs_record_squota_delta(trans->fs_info, &delta); - else - btrfs_qgroup_free_refroot(trans->fs_info, delta.root, - delta.rsv_bytes, BTRFS_QGROUP_RSV_DATA); } else if (node->action == BTRFS_ADD_DELAYED_REF) { ret = __btrfs_inc_extent_ref(trans, node, parent, ref->root, ref->objectid, ref->offset, @@ -1742,7 +1756,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_squota_delta delta = { .root = href->owning_root, .num_bytes = fs_info->nodesize, - .rsv_bytes = 0, .is_data = false, .is_inc = true, .generation = trans->transid, @@ -1774,8 +1787,10 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, int ret = 0; if (TRANS_ABORTED(trans)) { - if (insert_reserved) + if (insert_reserved) { btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1); + free_head_ref_squota_rsv(trans->fs_info, href); + } return 0; } @@ -1871,6 +1886,8 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head) { + u64 ret = 0; + /* * We had csum deletions accounted for in our delayed refs rsv, we need * to drop the csum leaves for this update from our delayed_refs_rsv. @@ -1885,14 +1902,13 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, btrfs_delayed_refs_rsv_release(fs_info, 0, nr_csums); - return btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums); + ret = btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums); } - if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE && - head->must_insert_reserved && head->is_data) - btrfs_qgroup_free_refroot(fs_info, head->owning_root, - head->reserved_bytes, BTRFS_QGROUP_RSV_DATA); + /* must_insert_reserved can be set only if we didn't run the head ref. */ + if (head->must_insert_reserved) + free_head_ref_squota_rsv(fs_info, head); - return 0; + return ret; } static int cleanup_ref_head(struct btrfs_trans_handle *trans, @@ -2033,6 +2049,12 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, * spin lock. */ must_insert_reserved = locked_ref->must_insert_reserved; + /* + * Unsetting this on the head ref relinquishes ownership of + * the rsv_bytes, so it is critical that every possible code + * path from here forward frees all reserves including qgroup + * reserve. + */ locked_ref->must_insert_reserved = false; extent_op = locked_ref->extent_op; @@ -3292,7 +3314,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_squota_delta delta = { .root = delayed_ref_root, .num_bytes = num_bytes, - .rsv_bytes = 0, .is_data = is_data, .is_inc = false, .generation = btrfs_extent_generation(leaf, ei), @@ -4937,7 +4958,6 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, .root = root_objectid, .num_bytes = ins->offset, .generation = trans->transid, - .rsv_bytes = 0, .is_data = true, .is_inc = true, }; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e6230a6ffa98..8f724c54fc8e 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2302,7 +2302,8 @@ static int try_release_extent_state(struct extent_io_tree *tree, ret = 0; } else { u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM | - EXTENT_DELALLOC_NEW | EXTENT_CTLBITS); + EXTENT_DELALLOC_NEW | EXTENT_CTLBITS | + EXTENT_QGROUP_RESERVED); /* * At this point we can safely clear everything except the diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f47731c45bb5..32611a4edd6b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3192,7 +3192,7 @@ static long btrfs_fallocate(struct file *file, int mode, qgroup_reserved -= range->len; } else if (qgroup_reserved > 0) { btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved, - range->start, range->len); + range->start, range->len, NULL); qgroup_reserved -= range->len; } list_del(&range->list); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9f5a9894f88f..fb3c3f43c3fa 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -688,7 +688,7 @@ out: * And at reserve time, it's always aligned to page size, so * just free one page here. */ - btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL); btrfs_free_path(path); btrfs_end_transaction(trans); return ret; @@ -5132,7 +5132,7 @@ static void evict_inode_truncate_pages(struct inode *inode) */ if (state_flags & EXTENT_DELALLOC) btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start, - end - start + 1); + end - start + 1, NULL); clear_extent_bit(io_tree, start, end, EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING, @@ -8059,7 +8059,7 @@ next: * reserved data space. * Since the IO will never happen for this page. */ - btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur); + btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL); if (!inode_evicting) { clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_UPTODATE | @@ -9491,7 +9491,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( struct btrfs_path *path; u64 start = ins->objectid; u64 len = ins->offset; - int qgroup_released; + u64 qgroup_released = 0; int ret; memset(&stack_fi, 0, sizeof(stack_fi)); @@ -9504,9 +9504,9 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); /* Encryption and other encoding is reserved and all 0 */ - qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len); - if (qgroup_released < 0) - return ERR_PTR(qgroup_released); + ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released); + if (ret < 0) + return ERR_PTR(ret); if (trans) { ret = insert_reserved_file_extent(trans, inode, @@ -10401,7 +10401,7 @@ out_delalloc_release: btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0); out_qgroup_free_data: if (ret < 0) - btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes); + btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL); out_free_data_space: /* * If btrfs_reserve_extent() succeeded, then we already decremented diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4e50b62db2a8..a1743904202b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1290,6 +1290,15 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file, * are limited to own subvolumes only */ ret = -EPERM; + } else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) { + /* + * Snapshots must be made with the src_inode referring + * to the subvolume inode, otherwise the permission + * checking above is useless because we may have + * permission on a lower directory but not the subvol + * itself. + */ + ret = -EINVAL; } else { ret = btrfs_mksnapshot(&file->f_path, idmap, name, namelen, diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 574e8a55e24a..a82e1417c4d2 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -152,11 +152,12 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( { struct btrfs_ordered_extent *entry; int ret; + u64 qgroup_rsv = 0; if (flags & ((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) { /* For nocow write, we can release the qgroup rsv right now */ - ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes); + ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ERR_PTR(ret); } else { @@ -164,7 +165,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( * The ordered extent has reserved qgroup space, release now * and pass the reserved number for qgroup_record to free. */ - ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes); + ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ERR_PTR(ret); } @@ -182,7 +183,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( entry->inode = igrab(&inode->vfs_inode); entry->compress_type = compress_type; entry->truncated_len = (u64)-1; - entry->qgroup_rsv = ret; + entry->qgroup_rsv = qgroup_rsv; entry->flags = flags; refcount_set(&entry->refs, 1); init_waitqueue_head(&entry->wait); @@ -599,7 +600,9 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, release = entry->disk_num_bytes; else release = entry->num_bytes; - btrfs_delalloc_release_metadata(btrfs_inode, release, false); + btrfs_delalloc_release_metadata(btrfs_inode, release, + test_bit(BTRFS_ORDERED_IOERR, + &entry->flags)); } percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index ce446d9d7f23..e46774e8f49f 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -4057,13 +4057,14 @@ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, /* Free ranges specified by @reserved, normally in error path */ static int qgroup_free_reserved_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed_ret) { struct btrfs_root *root = inode->root; struct ulist_node *unode; struct ulist_iterator uiter; struct extent_changeset changeset; - int freed = 0; + u64 freed = 0; int ret; extent_changeset_init(&changeset); @@ -4104,7 +4105,9 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode, } btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed, BTRFS_QGROUP_RSV_DATA); - ret = freed; + if (freed_ret) + *freed_ret = freed; + ret = 0; out: extent_changeset_release(&changeset); return ret; @@ -4112,7 +4115,7 @@ out: static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, - int free) + u64 *released, int free) { struct extent_changeset changeset; int trace_op = QGROUP_RELEASE; @@ -4128,7 +4131,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, /* In release case, we shouldn't have @reserved */ WARN_ON(!free && reserved); if (free && reserved) - return qgroup_free_reserved_data(inode, reserved, start, len); + return qgroup_free_reserved_data(inode, reserved, start, len, released); extent_changeset_init(&changeset); ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); @@ -4143,7 +4146,8 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, btrfs_qgroup_free_refroot(inode->root->fs_info, inode->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); - ret = changeset.bytes_changed; + if (released) + *released = changeset.bytes_changed; out: extent_changeset_release(&changeset); return ret; @@ -4162,9 +4166,10 @@ out: * NOTE: This function may sleep for memory allocation. */ int btrfs_qgroup_free_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed) { - return __btrfs_qgroup_release_data(inode, reserved, start, len, 1); + return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1); } /* @@ -4182,9 +4187,9 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode, * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len) +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released) { - return __btrfs_qgroup_release_data(inode, NULL, start, len, 0); + return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0); } static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes, @@ -4332,8 +4337,9 @@ static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root, qgroup_rsv_release(fs_info, qgroup, num_bytes, BTRFS_QGROUP_RSV_META_PREALLOC); - qgroup_rsv_add(fs_info, qgroup, num_bytes, - BTRFS_QGROUP_RSV_META_PERTRANS); + if (!sb_rdonly(fs_info->sb)) + qgroup_rsv_add(fs_info, qgroup, num_bytes, + BTRFS_QGROUP_RSV_META_PERTRANS); list_for_each_entry(glist, &qgroup->groups, next_group) qgroup_iterator_add(&qgroup_list, glist->group); @@ -4655,6 +4661,17 @@ void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans) *root = RB_ROOT; } +void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes) +{ + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE) + return; + + if (!is_fstree(root)) + return; + + btrfs_qgroup_free_refroot(fs_info, root, rsv_bytes, BTRFS_QGROUP_RSV_DATA); +} + int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, struct btrfs_squota_delta *delta) { @@ -4699,8 +4716,5 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, out: spin_unlock(&fs_info->qgroup_lock); - if (!ret && delta->rsv_bytes) - btrfs_qgroup_free_refroot(fs_info, root, delta->rsv_bytes, - BTRFS_QGROUP_RSV_DATA); return ret; } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 855a4f978761..be18c862e64e 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -274,8 +274,6 @@ struct btrfs_squota_delta { u64 root; /* The number of bytes in the extent being counted. */ u64 num_bytes; - /* The number of bytes reserved for this extent. */ - u64 rsv_bytes; /* The generation the extent was created in. */ u64 generation; /* Whether we are using or freeing the extent. */ @@ -358,10 +356,10 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, /* New io_tree based accurate qgroup reserve API */ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len); +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released); int btrfs_qgroup_free_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, - u64 len); + u64 len, u64 *freed); int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce); int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, @@ -422,6 +420,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb); void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans); bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info); +void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes); int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, struct btrfs_squota_delta *delta); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index bfc0eb5e3b7c..5b3333ceef04 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -37,8 +37,6 @@ static struct kmem_cache *btrfs_trans_handle_cachep; -#define BTRFS_ROOT_TRANS_TAG 0 - /* * Transaction states and transitions * diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 18c4f6e83b78..2bf8bbdfd0b3 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -12,6 +12,9 @@ #include "ctree.h" #include "misc.h" +/* Radix-tree tag for roots that are part of the trasaction. */ +#define BTRFS_ROOT_TRANS_TAG 0 + enum btrfs_trans_state { TRANS_STATE_RUNNING, TRANS_STATE_COMMIT_PREP, diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 0166bb9ca160..6aa15dafc677 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -349,9 +349,10 @@ static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count) return; } /* - * If i_disksize got extended due to writeback of delalloc blocks while - * the DIO was running we could fail to cleanup the orphan list in - * ext4_handle_inode_extension(). Do it now. + * If i_disksize got extended either due to writeback of delalloc + * blocks or extending truncate while the DIO was running we could fail + * to cleanup the orphan list in ext4_handle_inode_extension(). Do it + * now. */ if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); @@ -386,10 +387,11 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, * blocks. But the code in ext4_iomap_alloc() is careful to use * zeroed/unwritten extents if this is possible; thus we won't leave * uninitialized blocks in a file even if we didn't succeed in writing - * as much as we intended. + * as much as we intended. Also we can race with truncate or write + * expanding the file so we have to be a bit careful here. */ - WARN_ON_ONCE(i_size_read(inode) < READ_ONCE(EXT4_I(inode)->i_disksize)); - if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize)) + if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) && + pos + size <= i_size_read(inode)) return size; return ext4_handle_inode_extension(inode, pos, size); } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 454d5612641e..d72b5e3c92ec 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4478,6 +4478,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, start = max(start, rounddown(ac->ac_o_ex.fe_logical, (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); + /* avoid unnecessary preallocation that may trigger assertions */ + if (start + size > EXT_MAX_BLOCKS) + size = EXT_MAX_BLOCKS - start; + /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index 23904a6a9a96..12ef91d170bb 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -1222,6 +1222,7 @@ void fuse_dax_conn_free(struct fuse_conn *fc) if (fc->dax) { fuse_free_dax_mem_ranges(&fc->dax->free_ranges); kfree(fc->dax); + fc->dax = NULL; } } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 1cdb6327511e..a660f1f21540 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1448,7 +1448,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (!ia) return -ENOMEM; - if (fopen_direct_io && fc->direct_io_relax) { + if (fopen_direct_io && fc->direct_io_allow_mmap) { res = filemap_write_and_wait_range(mapping, pos, pos + count - 1); if (res) { fuse_io_free(ia); @@ -1574,6 +1574,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t res; bool exclusive_lock = !(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) || + get_fuse_conn(inode)->direct_io_allow_mmap || iocb->ki_flags & IOCB_APPEND || fuse_direct_write_extending_i_size(iocb, from); @@ -1581,6 +1582,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) * Take exclusive lock if * - Parallel direct writes are disabled - a user space decision * - Parallel direct writes are enabled and i_size is being extended. + * - Shared mmap on direct_io file is supported (FUSE_DIRECT_IO_ALLOW_MMAP). * This might not be needed at all, but needs further investigation. */ if (exclusive_lock) @@ -2466,9 +2468,9 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) if (ff->open_flags & FOPEN_DIRECT_IO) { /* Can't provide the coherency needed for MAP_SHARED - * if FUSE_DIRECT_IO_RELAX isn't set. + * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set. */ - if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax) + if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap) return -ENODEV; invalidate_inode_pages2(file->f_mapping); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 6e6e721f421b..1df83eebda92 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -63,6 +63,19 @@ struct fuse_forget_link { struct fuse_forget_link *next; }; +/* Submount lookup tracking */ +struct fuse_submount_lookup { + /** Refcount */ + refcount_t count; + + /** Unique ID, which identifies the inode between userspace + * and kernel */ + u64 nodeid; + + /** The request used for sending the FORGET message */ + struct fuse_forget_link *forget; +}; + /** FUSE inode */ struct fuse_inode { /** Inode data */ @@ -158,6 +171,8 @@ struct fuse_inode { */ struct fuse_inode_dax *dax; #endif + /** Submount specific lookup tracking */ + struct fuse_submount_lookup *submount_lookup; }; /** FUSE inode state bits */ @@ -797,8 +812,8 @@ struct fuse_conn { /* Is tmpfile not implemented by fs? */ unsigned int no_tmpfile:1; - /* relax restrictions in FOPEN_DIRECT_IO mode */ - unsigned int direct_io_relax:1; + /* Relax restrictions to allow shared mmap in FOPEN_DIRECT_IO mode */ + unsigned int direct_io_allow_mmap:1; /* Is statx not implemented by fs? */ unsigned int no_statx:1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 74d4f09d5827..2a6d44f91729 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -68,6 +68,24 @@ struct fuse_forget_link *fuse_alloc_forget(void) return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT); } +static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void) +{ + struct fuse_submount_lookup *sl; + + sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT); + if (!sl) + return NULL; + sl->forget = fuse_alloc_forget(); + if (!sl->forget) + goto out_free; + + return sl; + +out_free: + kfree(sl); + return NULL; +} + static struct inode *fuse_alloc_inode(struct super_block *sb) { struct fuse_inode *fi; @@ -83,6 +101,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->attr_version = 0; fi->orig_ino = 0; fi->state = 0; + fi->submount_lookup = NULL; mutex_init(&fi->mutex); spin_lock_init(&fi->lock); fi->forget = fuse_alloc_forget(); @@ -113,6 +132,17 @@ static void fuse_free_inode(struct inode *inode) kmem_cache_free(fuse_inode_cachep, fi); } +static void fuse_cleanup_submount_lookup(struct fuse_conn *fc, + struct fuse_submount_lookup *sl) +{ + if (!refcount_dec_and_test(&sl->count)) + return; + + fuse_queue_forget(fc, sl->forget, sl->nodeid, 1); + sl->forget = NULL; + kfree(sl); +} + static void fuse_evict_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -132,6 +162,11 @@ static void fuse_evict_inode(struct inode *inode) fi->nlookup); fi->forget = NULL; } + + if (fi->submount_lookup) { + fuse_cleanup_submount_lookup(fc, fi->submount_lookup); + fi->submount_lookup = NULL; + } } if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { WARN_ON(!list_empty(&fi->write_files)); @@ -330,6 +365,13 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, fuse_dax_dontcache(inode, attr->flags); } +static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl, + u64 nodeid) +{ + sl->nodeid = nodeid; + refcount_set(&sl->count, 1); +} + static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr, struct fuse_conn *fc) { @@ -392,12 +434,22 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, */ if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) && S_ISDIR(attr->mode)) { + struct fuse_inode *fi; + inode = new_inode(sb); if (!inode) return NULL; fuse_init_inode(inode, attr, fc); - get_fuse_inode(inode)->nodeid = nodeid; + fi = get_fuse_inode(inode); + fi->nodeid = nodeid; + fi->submount_lookup = fuse_alloc_submount_lookup(); + if (!fi->submount_lookup) { + iput(inode); + return NULL; + } + /* Sets nlookup = 1 on fi->submount_lookup->nlookup */ + fuse_init_submount_lookup(fi->submount_lookup, nodeid); inode->i_flags |= S_AUTOMOUNT; goto done; } @@ -420,11 +472,11 @@ retry: iput(inode); goto retry; } -done: fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->nlookup++; spin_unlock(&fi->lock); +done: fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version); return inode; @@ -1230,8 +1282,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->init_security = 1; if (flags & FUSE_CREATE_SUPP_GROUP) fc->create_supp_group = 1; - if (flags & FUSE_DIRECT_IO_RELAX) - fc->direct_io_relax = 1; + if (flags & FUSE_DIRECT_IO_ALLOW_MMAP) + fc->direct_io_allow_mmap = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1278,7 +1330,7 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | - FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX; + FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; @@ -1465,6 +1517,8 @@ static int fuse_fill_super_submount(struct super_block *sb, struct super_block *parent_sb = parent_fi->inode.i_sb; struct fuse_attr root_attr; struct inode *root; + struct fuse_submount_lookup *sl; + struct fuse_inode *fi; fuse_sb_defaults(sb); fm->sb = sb; @@ -1487,12 +1541,27 @@ static int fuse_fill_super_submount(struct super_block *sb, * its nlookup should not be incremented. fuse_iget() does * that, though, so undo it here. */ - get_fuse_inode(root)->nlookup--; + fi = get_fuse_inode(root); + fi->nlookup--; + sb->s_d_op = &fuse_dentry_operations; sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; + /* + * Grab the parent's submount_lookup pointer and take a + * reference on the shared nlookup from the parent. This is to + * prevent the last forget for this nodeid from getting + * triggered until all users have finished with it. + */ + sl = parent_fi->submount_lookup; + WARN_ON(!sl); + if (sl) { + refcount_inc(&sl->count); + fi->submount_lookup = sl; + } + return 0; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 8d6f934c3d95..5e122586e06e 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -119,7 +119,7 @@ static int journal_submit_commit_record(journal_t *journal, struct commit_header *tmp; struct buffer_head *bh; struct timespec64 now; - blk_opf_t write_flags = REQ_OP_WRITE | REQ_SYNC; + blk_opf_t write_flags = REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS; *cbh = NULL; @@ -270,6 +270,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, if (!ret) ret = err; } + cond_resched(); spin_lock(&journal->j_list_lock); jinode->i_flags &= ~JI_COMMIT_RUNNING; smp_mb(); @@ -395,8 +396,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, - journal->j_tail, - REQ_SYNC); + journal->j_tail, 0); mutex_unlock(&journal->j_checkpoint_mutex); } else { jbd2_debug(3, "superblock not updated\n"); @@ -715,6 +715,7 @@ start_journal_io: for (i = 0; i < bufs; i++) { struct buffer_head *bh = wbuf[i]; + /* * Compute checksum. */ @@ -727,7 +728,8 @@ start_journal_io: clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; - submit_bh(REQ_OP_WRITE | REQ_SYNC, bh); + submit_bh(REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS, + bh); } cond_resched(); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index ed53188472f9..206cb53ef2b0 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1100,8 +1100,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) * space and if we lose sb update during power failure we'd replay * old transaction with possibly newly overwritten data. */ - ret = jbd2_journal_update_sb_log_tail(journal, tid, block, - REQ_SYNC | REQ_FUA); + ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA); if (ret) goto out; @@ -1775,8 +1774,7 @@ static int journal_reset(journal_t *journal) */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, - journal->j_tail, - REQ_SYNC | REQ_FUA); + journal->j_tail, REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } return jbd2_journal_start_thread(journal); @@ -1798,9 +1796,16 @@ static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags) return -EIO; } - trace_jbd2_write_superblock(journal, write_flags); + /* + * Always set high priority flags to exempt from block layer's + * QOS policies, e.g. writeback throttle. + */ + write_flags |= JBD2_JOURNAL_REQ_FLAGS; if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); + + trace_jbd2_write_superblock(journal, write_flags); + if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal @@ -2050,7 +2055,7 @@ void jbd2_journal_update_sb_errno(journal_t *journal) jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); sb->s_errno = cpu_to_be32(errcode); - jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA); + jbd2_write_superblock(journal, REQ_FUA); } EXPORT_SYMBOL(jbd2_journal_update_sb_errno); @@ -2171,8 +2176,7 @@ int jbd2_journal_destroy(journal_t *journal) ++journal->j_transaction_sequence; write_unlock(&journal->j_state_lock); - jbd2_mark_journal_empty(journal, - REQ_SYNC | REQ_PREFLUSH | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } else err = -EIO; @@ -2473,7 +2477,7 @@ int jbd2_journal_flush(journal_t *journal, unsigned int flags) * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ - jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_FUA); if (flags) err = __jbd2_journal_erase(journal, flags); @@ -2519,7 +2523,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) if (write) { /* Lock to make assertions happy... */ mutex_lock_io(&journal->j_checkpoint_mutex); - jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index fdf2aad73470..e6beaaf4f170 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -26,8 +26,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) int i; int flags = nfsexp_flags(rqstp, exp); - validate_process_creds(); - /* discard any old override before preparing the new set */ revert_creds(get_cred(current_real_cred())); new = prepare_creds(); @@ -81,10 +79,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) else new->cap_effective = cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); - validate_process_creds(); put_cred(override_creds(new)); put_cred(new); - validate_process_creds(); return 0; oom: diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index fe61d9bbcc1f..5014ab87d313 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -955,7 +955,6 @@ nfsd(void *vrqstp) rqstp->rq_server->sv_maxconn = nn->max_connections; svc_recv(rqstp); - validate_process_creds(); } atomic_dec(&nfsdstats.th_cnt); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index fbbea7498f02..e01e4e2acbd9 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -901,7 +901,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int host_err; bool retried = false; - validate_process_creds(); /* * If we get here, then the client has already done an "open", * and (hopefully) checked permission - so allow OWNER_OVERRIDE @@ -926,7 +925,6 @@ retry: } err = nfserrno(host_err); } - validate_process_creds(); return err; } @@ -943,12 +941,7 @@ int nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, struct file **filp) { - int err; - - validate_process_creds(); - err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); - validate_process_creds(); - return err; + return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); } /* diff --git a/fs/open.c b/fs/open.c index 02dc608d40d8..3494a9cd8046 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1088,8 +1088,6 @@ struct file *dentry_open(const struct path *path, int flags, int error; struct file *f; - validate_creds(cred); - /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); @@ -1128,7 +1126,6 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode, struct file *f; int error; - validate_creds(cred); f = alloc_empty_file(flags, cred); if (IS_ERR(f)) return f; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 59f6b8e32cc9..d64a306a414b 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -291,16 +291,23 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId); #endif /* CIFS_DEBUG2 */ - rc = -EINVAL; + if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) { spin_unlock(&cfids->cfid_list_lock); + rc = -EINVAL; + goto oshr_free; + } + + rc = smb2_parse_contexts(server, rsp_iov, + &oparms.fid->epoch, + oparms.fid->lease_key, + &oplock, NULL, NULL); + if (rc) { + spin_unlock(&cfids->cfid_list_lock); goto oshr_free; } - smb2_parse_contexts(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); + rc = -EINVAL; if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) { spin_unlock(&cfids->cfid_list_lock); goto oshr_free; diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 32dfa0f7a78c..e20b4354e703 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -313,6 +313,9 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = { char * smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) { + const int max_off = 4096; + const int max_len = 128 * 1024; + *off = 0; *len = 0; @@ -384,29 +387,20 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) * Invalid length or offset probably means data area is invalid, but * we have little choice but to ignore the data area in this case. */ - if (*off > 4096) { - cifs_dbg(VFS, "offset %d too large, data area ignored\n", *off); - *len = 0; - *off = 0; - } else if (*off < 0) { - cifs_dbg(VFS, "negative offset %d to data invalid ignore data area\n", - *off); + if (unlikely(*off < 0 || *off > max_off || + *len < 0 || *len > max_len)) { + cifs_dbg(VFS, "%s: invalid data area (off=%d len=%d)\n", + __func__, *off, *len); *off = 0; *len = 0; - } else if (*len < 0) { - cifs_dbg(VFS, "negative data length %d invalid, data area ignored\n", - *len); - *len = 0; - } else if (*len > 128 * 1024) { - cifs_dbg(VFS, "data area larger than 128K: %d\n", *len); + } else if (*off == 0) { *len = 0; } /* return pointer to beginning of data area, ie offset from SMB start */ - if ((*off != 0) && (*len != 0)) + if (*off > 0 && *len > 0) return (char *)shdr + *off; - else - return NULL; + return NULL; } /* diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index fcfb6566b899..8f6f0a38b886 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -3003,7 +3003,7 @@ static int smb2_query_reparse_point(const unsigned int xid, struct kvec *rsp_iov; struct smb2_ioctl_rsp *ioctl_rsp; struct reparse_data_buffer *reparse_buf; - u32 plen; + u32 off, count, len; cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); @@ -3084,16 +3084,22 @@ static int smb2_query_reparse_point(const unsigned int xid, */ if (rc == 0) { /* See MS-FSCC 2.3.23 */ + off = le32_to_cpu(ioctl_rsp->OutputOffset); + count = le32_to_cpu(ioctl_rsp->OutputCount); + if (check_add_overflow(off, count, &len) || + len > rsp_iov[1].iov_len) { + cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n", + __func__, off, count); + rc = -EIO; + goto query_rp_exit; + } - reparse_buf = (struct reparse_data_buffer *) - ((char *)ioctl_rsp + - le32_to_cpu(ioctl_rsp->OutputOffset)); - plen = le32_to_cpu(ioctl_rsp->OutputCount); - - if (plen + le32_to_cpu(ioctl_rsp->OutputOffset) > - rsp_iov[1].iov_len) { - cifs_tcon_dbg(FYI, "srv returned invalid ioctl len: %d\n", - plen); + reparse_buf = (void *)((u8 *)ioctl_rsp + off); + len = sizeof(*reparse_buf); + if (count < len || + count < le16_to_cpu(reparse_buf->ReparseDataLength) + len) { + cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n", + __func__, off, count); rc = -EIO; goto query_rp_exit; } @@ -4943,6 +4949,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4971,14 +4978,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -5002,8 +5010,8 @@ one_more: else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 20634fc6d4f0..c571760ad39a 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -2236,17 +2236,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, posix->nlink, posix->mode, posix->reparse_tag); } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf, - struct create_posix_rsp *posix) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; static const char smb3_create_tag_posix[] = { 0x93, 0xAD, 0x25, 0x50, 0x9C, @@ -2255,45 +2256,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server, }; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - else if ((le16_to_cpu(cc->NameLength) == 16)) { - if (posix && - memcmp(name, smb3_create_tag_posix, 16) == 0) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen >= doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + case 16: + if (posix && !memcmp(name, smb3_create_tag_posix, 16)) parse_posix_ctxt(cc, buf, posix); + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; } - /* else { - cifs_dbg(FYI, "Context not matched with len %d\n", - le16_to_cpu(cc->NameLength)); - cifs_dump_mem("Cctxt name: ", name, 4); - } */ - - next = le32_to_cpu(cc->Next); - if (!next) + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -3124,8 +3143,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf, posix); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 46eff9ec302a..0e371f7e2854 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -251,11 +251,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf, - struct create_posix_rsp *posix); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 9fbaaa387dcc..57f2343164a3 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1145,7 +1145,7 @@ struct smb2_server_client_notification { #define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */ #define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ" #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC" -#define SMB2_CREATE_ALLOCATION_SIZE "AISi" +#define SMB2_CREATE_ALLOCATION_SIZE "AlSi" #define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc" #define SMB2_CREATE_TIMEWARP_REQUEST "TWrp" #define SMB2_CREATE_QUERY_ON_DISK_ID "QFid" @@ -1253,6 +1253,7 @@ struct create_mxac_rsp { #define SMB2_LEASE_WRITE_CACHING_LE cpu_to_le32(0x04) #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02) +#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE cpu_to_le32(0x04) #define SMB2_LEASE_KEY_SIZE 16 diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 50c68beb71d6..562b180459a1 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -102,9 +102,10 @@ static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) lease->new_state = 0; lease->flags = lctx->flags; lease->duration = lctx->duration; + lease->is_dir = lctx->is_dir; memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE); lease->version = lctx->version; - lease->epoch = 0; + lease->epoch = le16_to_cpu(lctx->epoch); INIT_LIST_HEAD(&opinfo->lease_entry); opinfo->o_lease = lease; @@ -395,8 +396,8 @@ void close_id_del_oplock(struct ksmbd_file *fp) { struct oplock_info *opinfo; - if (S_ISDIR(file_inode(fp->filp)->i_mode)) - return; + if (fp->reserve_lease_break) + smb_lazy_parent_lease_break_close(fp); opinfo = opinfo_get(fp); if (!opinfo) @@ -543,12 +544,13 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, /* upgrading lease */ if ((atomic_read(&ci->op_count) + atomic_read(&ci->sop_count)) == 1) { - if (lease->state == - (lctx->req_state & lease->state)) { + if (lease->state != SMB2_LEASE_NONE_LE && + lease->state == (lctx->req_state & lease->state)) { lease->state |= lctx->req_state; if (lctx->req_state & SMB2_LEASE_WRITE_CACHING_LE) lease_read_to_write(opinfo); + } } else if ((atomic_read(&ci->op_count) + atomic_read(&ci->sop_count)) > 1) { @@ -900,7 +902,8 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) lease->new_state = SMB2_LEASE_READ_CACHING_LE; } else { - if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE) + if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE && + !lease->is_dir) lease->new_state = SMB2_LEASE_READ_CACHING_LE; else @@ -1032,6 +1035,7 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2) SMB2_LEASE_KEY_SIZE); lease2->duration = lease1->duration; lease2->flags = lease1->flags; + lease2->epoch = lease1->epoch++; } static int add_lease_global_list(struct oplock_info *opinfo) @@ -1081,6 +1085,89 @@ static void set_oplock_level(struct oplock_info *opinfo, int level, } } +void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + struct lease_ctx_info *lctx) +{ + struct oplock_info *opinfo; + struct ksmbd_inode *p_ci = NULL; + + if (lctx->version != 2) + return; + + p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); + if (!p_ci) + return; + + read_lock(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (!opinfo->is_lease) + continue; + + if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE && + (!(lctx->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) || + !compare_guid_key(opinfo, fp->conn->ClientGUID, + lctx->parent_lease_key))) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; + + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + continue; + } + + read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); + read_lock(&p_ci->m_lock); + } + } + read_unlock(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); +} + +void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) +{ + struct oplock_info *opinfo; + struct ksmbd_inode *p_ci = NULL; + + rcu_read_lock(); + opinfo = rcu_dereference(fp->f_opinfo); + rcu_read_unlock(); + + if (!opinfo->is_lease || opinfo->o_lease->version != 2) + return; + + p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); + if (!p_ci) + return; + + read_lock(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (!opinfo->is_lease) + continue; + + if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; + + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + continue; + } + read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); + read_lock(&p_ci->m_lock); + } + } + read_unlock(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); +} + /** * smb_grant_oplock() - handle oplock/lease request on file open * @work: smb work @@ -1104,10 +1191,6 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, bool prev_op_has_lease; __le32 prev_op_state = 0; - /* not support directory lease */ - if (S_ISDIR(file_inode(fp->filp)->i_mode)) - return 0; - opinfo = alloc_opinfo(work, pid, tid); if (!opinfo) return -ENOMEM; @@ -1364,6 +1447,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseFlags = lease->flags; + buf->lcontext.Epoch = cpu_to_le16(++lease->epoch); buf->lcontext.LeaseState = lease->state; memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, SMB2_LEASE_KEY_SIZE); @@ -1400,10 +1484,11 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) /** * parse_lease_state() - parse lease context containted in file open request * @open_req: buffer containing smb2 file open(create) request + * @is_dir: whether leasing file is directory * * Return: oplock state, -ENOENT if create lease context not found */ -struct lease_ctx_info *parse_lease_state(void *open_req) +struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) { struct create_context *cc; struct smb2_create_req *req = (struct smb2_create_req *)open_req; @@ -1421,8 +1506,14 @@ struct lease_ctx_info *parse_lease_state(void *open_req) struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); - lreq->req_state = lc->lcontext.LeaseState; + if (is_dir) { + lreq->req_state = lc->lcontext.LeaseState & + ~SMB2_LEASE_WRITE_CACHING_LE; + lreq->is_dir = true; + } else + lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; + lreq->epoch = lc->lcontext.Epoch; lreq->duration = lc->lcontext.LeaseDuration; memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, SMB2_LEASE_KEY_SIZE); diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 4b0fe6da7694..5b93ea9196c0 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -34,7 +34,9 @@ struct lease_ctx_info { __le32 flags; __le64 duration; __u8 parent_lease_key[SMB2_LEASE_KEY_SIZE]; + __le16 epoch; int version; + bool is_dir; }; struct lease_table { @@ -53,6 +55,7 @@ struct lease { __u8 parent_lease_key[SMB2_LEASE_KEY_SIZE]; int version; unsigned short epoch; + bool is_dir; struct lease_table *l_lb; }; @@ -108,7 +111,7 @@ void opinfo_put(struct oplock_info *opinfo); /* Lease related functions */ void create_lease_buf(u8 *rbuf, struct lease *lease); -struct lease_ctx_info *parse_lease_state(void *open_req); +struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir); __u8 smb2_map_lease_to_oplock(__le32 lease_state); int lease_read_to_write(struct oplock_info *opinfo); @@ -124,4 +127,7 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); +void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + struct lease_ctx_info *lctx); +void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index aed7704a0672..27a9dce3e03a 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -221,7 +221,8 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION && conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) @@ -245,7 +246,8 @@ void init_smb3_02_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && @@ -270,7 +272,8 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d369b98a6e10..652ab429bf2e 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2516,7 +2516,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path * da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, false); + rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, true); if (rc) ksmbd_debug(SMB, "failed to store file attribute into xattr\n"); } @@ -2732,10 +2732,6 @@ int smb2_open(struct ksmbd_work *work) } } - req_op_level = req->RequestedOplockLevel; - if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) - lc = parse_lease_state(req); - if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) { pr_err("Invalid impersonationlevel : 0x%x\n", le32_to_cpu(req->ImpersonationLevel)); @@ -3189,23 +3185,6 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } - rc = ksmbd_vfs_getattr(&path, &stat); - if (rc) - goto err_out; - - if (stat.result_mask & STATX_BTIME) - fp->create_time = ksmbd_UnixTimeToNT(stat.btime); - else - fp->create_time = ksmbd_UnixTimeToNT(stat.ctime); - if (req->FileAttributes || fp->f_ci->m_fattr == 0) - fp->f_ci->m_fattr = - cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes))); - - if (!created) - smb2_update_xattrs(tcon, &path, fp); - else - smb2_new_xattrs(tcon, &path, fp); - if (file_present || created) ksmbd_vfs_kern_path_unlock(&parent_path, &path); @@ -3215,6 +3194,10 @@ int smb2_open(struct ksmbd_work *work) need_truncate = 1; } + req_op_level = req->RequestedOplockLevel; + if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) + lc = parse_lease_state(req, S_ISDIR(file_inode(filp)->i_mode)); + share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp); if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) || (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && @@ -3225,6 +3208,13 @@ int smb2_open(struct ksmbd_work *work) } } else { if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { + /* + * Compare parent lease using parent key. If there is no + * a lease that has same parent key, Send lease break + * notification. + */ + smb_send_parent_lease_break_noti(fp, lc); + req_op_level = smb2_map_lease_to_oplock(lc->req_state); ksmbd_debug(SMB, "lease req for(%s) req oplock state 0x%x, lease state 0x%x\n", @@ -3295,6 +3285,23 @@ int smb2_open(struct ksmbd_work *work) } } + rc = ksmbd_vfs_getattr(&path, &stat); + if (rc) + goto err_out1; + + if (stat.result_mask & STATX_BTIME) + fp->create_time = ksmbd_UnixTimeToNT(stat.btime); + else + fp->create_time = ksmbd_UnixTimeToNT(stat.ctime); + if (req->FileAttributes || fp->f_ci->m_fattr == 0) + fp->f_ci->m_fattr = + cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes))); + + if (!created) + smb2_update_xattrs(tcon, &path, fp); + else + smb2_new_xattrs(tcon, &path, fp); + memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); rsp->StructureSize = cpu_to_le16(89); @@ -7080,6 +7087,7 @@ skip: smb2_remove_blocked_lock, argv); if (rc) { + kfree(argv); err = -ENOMEM; goto out; } @@ -8211,6 +8219,11 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) le32_to_cpu(req->LeaseState)); } + if (ret < 0) { + rsp->hdr.Status = err; + goto err_out; + } + lease_state = lease->state; opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); @@ -8218,11 +8231,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) wake_up_interruptible_all(&opinfo->oplock_brk); opinfo_put(opinfo); - if (ret < 0) { - rsp->hdr.Status = err; - goto err_out; - } - rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; rsp->Flags = 0; diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 9091dcd7a310..4277750a6da1 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -517,6 +517,9 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, } } + /* Reserve lease break for parent dir at closing time */ + fp->reserve_lease_break = true; + /* Do we need to break any of a levelII oplock? */ smb_break_all_levII_oplock(work, fp, 1); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index ddf233994ddb..4e82ff627d12 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -87,6 +87,17 @@ static struct ksmbd_inode *ksmbd_inode_lookup(struct ksmbd_file *fp) return __ksmbd_inode_lookup(fp->filp->f_path.dentry); } +struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d) +{ + struct ksmbd_inode *ci; + + read_lock(&inode_hash_lock); + ci = __ksmbd_inode_lookup(d); + read_unlock(&inode_hash_lock); + + return ci; +} + int ksmbd_query_inode_status(struct dentry *dentry) { struct ksmbd_inode *ci; @@ -199,7 +210,7 @@ static void ksmbd_inode_free(struct ksmbd_inode *ci) kfree(ci); } -static void ksmbd_inode_put(struct ksmbd_inode *ci) +void ksmbd_inode_put(struct ksmbd_inode *ci) { if (atomic_dec_and_test(&ci->m_count)) ksmbd_inode_free(ci); diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 8325cf4527c4..a528f0cc775a 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -105,6 +105,7 @@ struct ksmbd_file { struct ksmbd_readdir_data readdir_data; int dot_dotdot[2]; unsigned int f_state; + bool reserve_lease_break; }; static inline void set_ctx_actor(struct dir_context *ctx, @@ -138,6 +139,8 @@ struct ksmbd_file *ksmbd_lookup_foreign_fd(struct ksmbd_work *work, u64 id); struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id, u64 pid); void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp); +struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d); +void ksmbd_inode_put(struct ksmbd_inode *ci); struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 0b90869fd805..43e237864a42 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -546,6 +546,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, if (strcmp(ei_child->name, name) != 0) continue; ret = simple_lookup(dir, dentry, flags); + if (IS_ERR(ret)) + goto out; create_dir_dentry(ei, ei_child, ei_dentry, true); created = true; break; @@ -568,6 +570,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, if (r <= 0) continue; ret = simple_lookup(dir, dentry, flags); + if (IS_ERR(ret)) + goto out; create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops, true); break; diff --git a/fs/ufs/util.c b/fs/ufs/util.c index 13ba34e6d64f..2acf191eb89e 100644 --- a/fs/ufs/util.c +++ b/fs/ufs/util.c @@ -245,7 +245,7 @@ struct folio *ufs_get_locked_folio(struct address_space *mapping, { struct inode *inode = mapping->host; struct folio *folio = filemap_lock_folio(mapping, index); - if (!folio) { + if (IS_ERR(folio)) { folio = read_mapping_folio(mapping, index, NULL); if (IS_ERR(folio)) { diff --git a/include/linux/cred.h b/include/linux/cred.h index af8d353a4b86..2976f534a7a3 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -109,14 +109,7 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp) * same context as task->real_cred. */ struct cred { - atomic_t usage; -#ifdef CONFIG_DEBUG_CREDENTIALS - atomic_t subscribers; /* number of processes subscribed */ - void *put_addr; - unsigned magic; -#define CRED_MAGIC 0x43736564 -#define CRED_MAGIC_DEAD 0x44656144 -#endif + atomic_long_t usage; kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ @@ -172,46 +165,6 @@ extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); extern int set_cred_ucounts(struct cred *); -/* - * check for validity of credentials - */ -#ifdef CONFIG_DEBUG_CREDENTIALS -extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned); -extern void __validate_process_creds(struct task_struct *, - const char *, unsigned); - -extern bool creds_are_invalid(const struct cred *cred); - -static inline void __validate_creds(const struct cred *cred, - const char *file, unsigned line) -{ - if (unlikely(creds_are_invalid(cred))) - __invalid_creds(cred, file, line); -} - -#define validate_creds(cred) \ -do { \ - __validate_creds((cred), __FILE__, __LINE__); \ -} while(0) - -#define validate_process_creds() \ -do { \ - __validate_process_creds(current, __FILE__, __LINE__); \ -} while(0) - -extern void validate_creds_for_do_exit(struct task_struct *); -#else -static inline void validate_creds(const struct cred *cred) -{ -} -static inline void validate_creds_for_do_exit(struct task_struct *tsk) -{ -} -static inline void validate_process_creds(void) -{ -} -#endif - static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, @@ -229,7 +182,7 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) */ static inline struct cred *get_new_cred_many(struct cred *cred, int nr) { - atomic_add(nr, &cred->usage); + atomic_long_add(nr, &cred->usage); return cred; } @@ -264,7 +217,6 @@ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; - validate_creds(cred); nonconst_cred->non_rcu = 0; return get_new_cred_many(nonconst_cred, nr); } @@ -288,9 +240,8 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred) struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; - if (!atomic_inc_not_zero(&nonconst_cred->usage)) + if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; - validate_creds(cred); nonconst_cred->non_rcu = 0; return cred; } @@ -312,8 +263,7 @@ static inline void put_cred_many(const struct cred *_cred, int nr) struct cred *cred = (struct cred *) _cred; if (cred) { - validate_creds(cred); - if (atomic_sub_and_test(nr, &cred->usage)) + if (atomic_long_sub_and_test(nr, &cred->usage)) __put_cred(cred); } } diff --git a/include/linux/damon.h b/include/linux/damon.h index ab2f17d9926b..e00ddf1ed39c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -559,6 +559,8 @@ struct damon_ctx { * update */ unsigned long next_ops_update_sis; + /* for waiting until the execution of the kdamond_fn is started */ + struct completion kdamond_started; /* public: */ struct task_struct *kdamond; diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 805bb635cdf5..239a4f68801b 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -434,6 +434,7 @@ enum { /* keep async read/write and isreg together and in order */ REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, + REQ_F_POLL_NO_LAZY_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -501,6 +502,8 @@ enum { REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT), /* hashed into ->cancel_hash_locked, protected by ->uring_lock */ REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT), + /* don't use lazy poll wake for this request */ + REQ_F_POLL_NO_LAZY = BIT(REQ_F_POLL_NO_LAZY_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 6dcbb4eb80fb..beb30719ee16 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1374,6 +1374,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) +/* Journal high priority write IO operation flags */ +#define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) + /* * Journal flag definitions */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6f3631425f38..3f7b664d625b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -621,7 +621,7 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_140[0x8]; u8 bth_dst_qp[0x18]; - u8 reserved_at_160[0x20]; + u8 inner_esp_spi[0x20]; u8 outer_esp_spi[0x20]; u8 reserved_at_1a0[0x60]; }; @@ -12001,6 +12001,13 @@ enum { MLX5_IPSEC_ASO_INC_SN = 0x2, }; +enum { + MLX5_IPSEC_ASO_REPLAY_WIN_32BIT = 0x0, + MLX5_IPSEC_ASO_REPLAY_WIN_64BIT = 0x1, + MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2, + MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3, +}; + struct mlx5_ifc_ipsec_aso_bits { u8 valid[0x1]; u8 reserved_at_201[0x1]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 418d26608ece..da5219b48d52 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -886,8 +886,8 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma) */ static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) { - return vma->vm_start <= vma->vm_mm->brk && - vma->vm_end >= vma->vm_mm->start_brk; + return vma->vm_start < vma->vm_mm->brk && + vma->vm_end > vma->vm_mm->start_brk; } /* @@ -901,8 +901,8 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) * its "stack". It's not even well-defined for programs written * languages like Go. */ - return vma->vm_start <= vma->vm_mm->start_stack && - vma->vm_end >= vma->vm_mm->start_stack; + return vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 9ae7def16cb2..f4fe593c1400 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -232,22 +232,27 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* - * There are three common cases for this page: - * 1. If it's hot, e.g., freshly faulted in or previously hot and - * migrated, add it to the youngest generation. - * 2. If it's cold but can't be evicted immediately, i.e., an anon page - * not in swapcache or a dirty page pending writeback, add it to the - * second oldest generation. - * 3. Everything else (clean, cold) is added to the oldest generation. + * There are four common cases for this page: + * 1. If it's hot, i.e., freshly faulted in, add it to the youngest + * generation, and it's protected over the rest below. + * 2. If it can't be evicted immediately, i.e., a dirty page pending + * writeback, add it to the second youngest generation. + * 3. If it should be evicted first, e.g., cold and clean from + * folio_rotate_reclaimable(), add it to the oldest generation. + * 4. Everything else falls between 2 & 3 above and is added to the + * second oldest generation if it's considered inactive, or the + * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) - seq = lrugen->min_seq[type] + 1; - else + seq = lrugen->max_seq - 1; + else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; + else + seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3c25226beeed..9db36e197712 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -505,33 +505,37 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); * the old generation, is incremented when all its bins become empty. * * There are four operations: - * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its + * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; - * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its + * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; - * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old + * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; - * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the + * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; - * 2. The first attempt to reclaim an memcg below low, which triggers + * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; - * 3. The first attempt to reclaim an memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_TAIL; - * 4. The second attempt to reclaim an memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_YOUNG; - * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; + * 3. The first attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; - * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. + * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * - * Note that memcg LRU only applies to global reclaim, and the round-robin - * incrementing of their max_seq counters ensures the eventual fairness to all - * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * Notes: + * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing + * of their max_seq counters ensures the eventual fairness to all eligible + * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * 2. There are only two valid generations: old (seq) and young (seq+1). + * MEMCG_NR_GENS is set to three so that when reading the generation counter + * locklessly, a stale value (seq-1) does not wraparound to young. */ -#define MEMCG_NR_GENS 2 +#define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { diff --git a/include/linux/pci.h b/include/linux/pci.h index 60ca768bc867..dea043bc1e38 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1829,6 +1829,7 @@ extern bool pcie_ports_native; int pci_disable_link_state(struct pci_dev *pdev, int state); int pci_disable_link_state_locked(struct pci_dev *pdev, int state); int pci_enable_link_state(struct pci_dev *pdev, int state); +int pci_enable_link_state_locked(struct pci_dev *pdev, int state); void pcie_no_aspm(void); bool pcie_aspm_support_enabled(void); bool pcie_aspm_enabled(struct pci_dev *pdev); @@ -1839,6 +1840,8 @@ static inline int pci_disable_link_state_locked(struct pci_dev *pdev, int state) { return 0; } static inline int pci_enable_link_state(struct pci_dev *pdev, int state) { return 0; } +static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state) +{ return 0; } static inline void pcie_no_aspm(void) { } static inline bool pcie_aspm_support_enabled(void) { return false; } static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; } diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 82da55101b5a..61ebe723ee4d 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -31,17 +31,22 @@ struct prefix_info { __u8 length; __u8 prefix_len; + union __packed { + __u8 flags; + struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) - __u8 onlink : 1, + __u8 onlink : 1, autoconf : 1, reserved : 6; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 6, autoconf : 1, onlink : 1; #else #error "Please fix <asm/byteorder.h>" #endif + }; + }; __be32 valid; __be32 prefered; __be32 reserved2; @@ -49,6 +54,9 @@ struct prefix_info { struct in6_addr prefix; }; +/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */ +static_assert(sizeof(struct prefix_info) == 32); + #include <linux/ipv6.h> #include <linux/netdevice.h> #include <net/if_inet6.h> diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 3e454c4d7ba6..f07642264c1e 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -22,10 +22,6 @@ #define IF_RS_SENT 0x10 #define IF_READY 0x80000000 -/* prefix flags */ -#define IF_PREFIX_ONLINK 0x01 -#define IF_PREFIX_AUTOCONF 0x02 - enum { INET6_IFADDR_STATE_PREDAD, INET6_IFADDR_STATE_DAD, diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index fe1507c1db82..692d5955911c 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -62,6 +62,8 @@ struct nf_flowtable_type { enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); + void (*get)(struct nf_flowtable *ft); + void (*put)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; }; @@ -240,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, } list_add_tail(&block_cb->list, &block->cb_list); + up_write(&flow_table->flow_block_lock); + + if (flow_table->type->get) + flow_table->type->get(flow_table); + return 0; unlock: up_write(&flow_table->flow_block_lock); @@ -262,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, WARN_ON(true); } up_write(&flow_table->flow_block_lock); + + if (flow_table->type->put) + flow_table->type->put(flow_table); } void flow_offload_route_init(struct flow_offload *flow, diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index db92a7202b34..e7418d15fe39 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -209,7 +209,7 @@ * - add FUSE_HAS_EXPIRE_ONLY * * 7.39 - * - add FUSE_DIRECT_IO_RELAX + * - add FUSE_DIRECT_IO_ALLOW_MMAP * - add FUSE_STATX and related structures */ @@ -409,8 +409,7 @@ struct fuse_file_lock { * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, * symlink and mknod (single group that matches parent) * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation - * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now - * allow shared mmap + * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode. */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -449,7 +448,10 @@ struct fuse_file_lock { #define FUSE_HAS_INODE_DAX (1ULL << 33) #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) -#define FUSE_DIRECT_IO_RELAX (1ULL << 36) +#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) + +/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ +#define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP /** * CUSE INIT request/reply flags diff --git a/io_uring/poll.c b/io_uring/poll.c index d38d05edb4fa..d59b74a99d4e 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -366,11 +366,16 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts) static void __io_poll_execute(struct io_kiocb *req, int mask) { + unsigned flags = 0; + io_req_set_res(req, mask, 0); req->io_task_work.func = io_poll_task_func; trace_io_uring_task_add(req, mask); - __io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE); + + if (!(req->flags & REQ_F_POLL_NO_LAZY)) + flags = IOU_F_TWQ_LAZY_WAKE; + __io_req_task_work_add(req, flags); } static inline void io_poll_execute(struct io_kiocb *req, int res) @@ -526,10 +531,19 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt, poll->head = head; poll->wait.private = (void *) wqe_private; - if (poll->events & EPOLLEXCLUSIVE) + if (poll->events & EPOLLEXCLUSIVE) { + /* + * Exclusive waits may only wake a limited amount of entries + * rather than all of them, this may interfere with lazy + * wake if someone does wait(events > 1). Ensure we don't do + * lazy wake for those, as we need to process each one as they + * come in. + */ + req->flags |= REQ_F_POLL_NO_LAZY; add_wait_queue_exclusive(head, &poll->wait); - else + } else { add_wait_queue(head, &poll->wait); + } } static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index acbc2924ecd2..7d3ef62e620a 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -7,7 +7,7 @@ #include <linux/nospec.h> #include <uapi/linux/io_uring.h> -#include <uapi/asm-generic/ioctls.h> +#include <asm/ioctls.h> #include "io_uring.h" #include "rsrc.h" diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 1cc3b1c595d7..2fd510256604 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -94,7 +94,6 @@ config KEXEC_JUMP config CRASH_DUMP bool "kernel crash dumps" depends on ARCH_SUPPORTS_CRASH_DUMP - depends on ARCH_SUPPORTS_KEXEC select CRASH_CORE select KEXEC_CORE help diff --git a/kernel/crash_core.c b/kernel/crash_core.c index efe87d501c8c..d4313b53837e 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -199,7 +199,7 @@ static __initdata char *suffix_tbl[] = { * It returns 0 on success and -EINVAL on failure. */ static int __init parse_crashkernel_suffix(char *cmdline, - unsigned long long *crash_size, + unsigned long long *crash_size, const char *suffix) { char *cur = cmdline; @@ -268,9 +268,9 @@ static int __init __parse_crashkernel(char *cmdline, unsigned long long *crash_base, const char *suffix) { - char *first_colon, *first_space; - char *ck_cmdline; - char *name = "crashkernel="; + char *first_colon, *first_space; + char *ck_cmdline; + char *name = "crashkernel="; BUG_ON(!crash_size || !crash_base); *crash_size = 0; @@ -440,7 +440,7 @@ retry: return; } - if ((crash_base > CRASH_ADDR_LOW_MAX) && + if ((crash_base >= CRASH_ADDR_LOW_MAX) && crash_low_size && reserve_crashkernel_low(crash_low_size)) { memblock_phys_free(crash_base, crash_size); return; diff --git a/kernel/cred.c b/kernel/cred.c index 3c714cb31660..c033a201c808 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -43,10 +43,6 @@ static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) }; */ struct cred init_cred = { .usage = ATOMIC_INIT(4), -#ifdef CONFIG_DEBUG_CREDENTIALS - .subscribers = ATOMIC_INIT(2), - .magic = CRED_MAGIC, -#endif .uid = GLOBAL_ROOT_UID, .gid = GLOBAL_ROOT_GID, .suid = GLOBAL_ROOT_UID, @@ -66,31 +62,6 @@ struct cred init_cred = { .ucounts = &init_ucounts, }; -static inline void set_cred_subscribers(struct cred *cred, int n) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - atomic_set(&cred->subscribers, n); -#endif -} - -static inline int read_cred_subscribers(const struct cred *cred) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - return atomic_read(&cred->subscribers); -#else - return 0; -#endif -} - -static inline void alter_cred_subscribers(const struct cred *_cred, int n) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - struct cred *cred = (struct cred *) _cred; - - atomic_add(n, &cred->subscribers); -#endif -} - /* * The RCU callback to actually dispose of a set of credentials */ @@ -100,20 +71,9 @@ static void put_cred_rcu(struct rcu_head *rcu) kdebug("put_cred_rcu(%p)", cred); -#ifdef CONFIG_DEBUG_CREDENTIALS - if (cred->magic != CRED_MAGIC_DEAD || - atomic_read(&cred->usage) != 0 || - read_cred_subscribers(cred) != 0) - panic("CRED: put_cred_rcu() sees %p with" - " mag %x, put %p, usage %d, subscr %d\n", - cred, cred->magic, cred->put_addr, - atomic_read(&cred->usage), - read_cred_subscribers(cred)); -#else - if (atomic_read(&cred->usage) != 0) - panic("CRED: put_cred_rcu() sees %p with usage %d\n", - cred, atomic_read(&cred->usage)); -#endif + if (atomic_long_read(&cred->usage) != 0) + panic("CRED: put_cred_rcu() sees %p with usage %ld\n", + cred, atomic_long_read(&cred->usage)); security_cred_free(cred); key_put(cred->session_keyring); @@ -137,16 +97,10 @@ static void put_cred_rcu(struct rcu_head *rcu) */ void __put_cred(struct cred *cred) { - kdebug("__put_cred(%p{%d,%d})", cred, - atomic_read(&cred->usage), - read_cred_subscribers(cred)); - - BUG_ON(atomic_read(&cred->usage) != 0); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(cred) != 0); - cred->magic = CRED_MAGIC_DEAD; - cred->put_addr = __builtin_return_address(0); -#endif + kdebug("__put_cred(%p{%ld})", cred, + atomic_long_read(&cred->usage)); + + BUG_ON(atomic_long_read(&cred->usage) != 0); BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); @@ -164,9 +118,8 @@ void exit_creds(struct task_struct *tsk) { struct cred *real_cred, *cred; - kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred, - atomic_read(&tsk->cred->usage), - read_cred_subscribers(tsk->cred)); + kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred, + atomic_long_read(&tsk->cred->usage)); real_cred = (struct cred *) tsk->real_cred; tsk->real_cred = NULL; @@ -174,15 +127,10 @@ void exit_creds(struct task_struct *tsk) cred = (struct cred *) tsk->cred; tsk->cred = NULL; - validate_creds(cred); if (real_cred == cred) { - alter_cred_subscribers(cred, -2); put_cred_many(cred, 2); } else { - validate_creds(real_cred); - alter_cred_subscribers(real_cred, -1); put_cred(real_cred); - alter_cred_subscribers(cred, -1); put_cred(cred); } @@ -230,10 +178,7 @@ struct cred *cred_alloc_blank(void) if (!new) return NULL; - atomic_set(&new->usage, 1); -#ifdef CONFIG_DEBUG_CREDENTIALS - new->magic = CRED_MAGIC; -#endif + atomic_long_set(&new->usage, 1); if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; @@ -264,8 +209,6 @@ struct cred *prepare_creds(void) const struct cred *old; struct cred *new; - validate_process_creds(); - new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) return NULL; @@ -276,8 +219,7 @@ struct cred *prepare_creds(void) memcpy(new, old, sizeof(struct cred)); new->non_rcu = 0; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); + atomic_long_set(&new->usage, 1); get_group_info(new->group_info); get_uid(new->user); get_user_ns(new->user_ns); @@ -300,7 +242,6 @@ struct cred *prepare_creds(void) if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; - validate_creds(new); return new; error: @@ -362,10 +303,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) clone_flags & CLONE_THREAD ) { p->real_cred = get_cred_many(p->cred, 2); - alter_cred_subscribers(p->cred, 2); - kdebug("share_creds(%p{%d,%d})", - p->cred, atomic_read(&p->cred->usage), - read_cred_subscribers(p->cred)); + kdebug("share_creds(%p{%ld})", + p->cred, atomic_long_read(&p->cred->usage)); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); return 0; } @@ -404,8 +343,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) p->cred = p->real_cred = get_cred(new); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); - alter_cred_subscribers(new, 2); - validate_creds(new); return 0; error_put: @@ -457,17 +394,11 @@ int commit_creds(struct cred *new) struct task_struct *task = current; const struct cred *old = task->real_cred; - kdebug("commit_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); + kdebug("commit_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); BUG_ON(task->cred != old); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(old) < 2); - validate_creds(old); - validate_creds(new); -#endif - BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_long_read(&new->usage) < 1); get_cred(new); /* we will require a ref for the subj creds too */ @@ -502,14 +433,12 @@ int commit_creds(struct cred *new) * RLIMIT_NPROC limits on user->processes have already been checked * in set_user(). */ - alter_cred_subscribers(new, 2); if (new->user != old->user || new->user_ns != old->user_ns) inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1); rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); if (new->user != old->user || new->user_ns != old->user_ns) dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1); - alter_cred_subscribers(old, -2); /* send notifications */ if (!uid_eq(new->uid, old->uid) || @@ -539,14 +468,10 @@ EXPORT_SYMBOL(commit_creds); */ void abort_creds(struct cred *new) { - kdebug("abort_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); + kdebug("abort_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(new) != 0); -#endif - BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_long_read(&new->usage) < 1); put_cred(new); } EXPORT_SYMBOL(abort_creds); @@ -562,12 +487,8 @@ const struct cred *override_creds(const struct cred *new) { const struct cred *old = current->cred; - kdebug("override_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); - - validate_creds(old); - validate_creds(new); + kdebug("override_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); /* * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. @@ -576,18 +497,12 @@ const struct cred *override_creds(const struct cred *new) * we are only installing the cred into the thread-synchronous * '->cred' pointer, not the '->real_cred' pointer that is * visible to other threads under RCU. - * - * Also note that we did validate_creds() manually, not depending - * on the validation in 'get_cred()'. */ get_new_cred((struct cred *)new); - alter_cred_subscribers(new, 1); rcu_assign_pointer(current->cred, new); - alter_cred_subscribers(old, -1); - kdebug("override_creds() = %p{%d,%d}", old, - atomic_read(&old->usage), - read_cred_subscribers(old)); + kdebug("override_creds() = %p{%ld}", old, + atomic_long_read(&old->usage)); return old; } EXPORT_SYMBOL(override_creds); @@ -603,15 +518,10 @@ void revert_creds(const struct cred *old) { const struct cred *override = current->cred; - kdebug("revert_creds(%p{%d,%d})", old, - atomic_read(&old->usage), - read_cred_subscribers(old)); + kdebug("revert_creds(%p{%ld})", old, + atomic_long_read(&old->usage)); - validate_creds(old); - validate_creds(override); - alter_cred_subscribers(old, 1); rcu_assign_pointer(current->cred, old); - alter_cred_subscribers(override, -1); put_cred(override); } EXPORT_SYMBOL(revert_creds); @@ -731,12 +641,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) kdebug("prepare_kernel_cred() alloc %p", new); old = get_task_cred(daemon); - validate_creds(old); *new = *old; new->non_rcu = 0; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); + atomic_long_set(&new->usage, 1); get_uid(new->user); get_user_ns(new->user_ns); get_group_info(new->group_info); @@ -760,7 +668,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) goto error; put_cred(old); - validate_creds(new); return new; error: @@ -825,109 +732,3 @@ int set_create_files_as(struct cred *new, struct inode *inode) return security_kernel_create_files_as(new, inode); } EXPORT_SYMBOL(set_create_files_as); - -#ifdef CONFIG_DEBUG_CREDENTIALS - -bool creds_are_invalid(const struct cred *cred) -{ - if (cred->magic != CRED_MAGIC) - return true; - return false; -} -EXPORT_SYMBOL(creds_are_invalid); - -/* - * dump invalid credentials - */ -static void dump_invalid_creds(const struct cred *cred, const char *label, - const struct task_struct *tsk) -{ - pr_err("%s credentials: %p %s%s%s\n", - label, cred, - cred == &init_cred ? "[init]" : "", - cred == tsk->real_cred ? "[real]" : "", - cred == tsk->cred ? "[eff]" : ""); - pr_err("->magic=%x, put_addr=%p\n", - cred->magic, cred->put_addr); - pr_err("->usage=%d, subscr=%d\n", - atomic_read(&cred->usage), - read_cred_subscribers(cred)); - pr_err("->*uid = { %d,%d,%d,%d }\n", - from_kuid_munged(&init_user_ns, cred->uid), - from_kuid_munged(&init_user_ns, cred->euid), - from_kuid_munged(&init_user_ns, cred->suid), - from_kuid_munged(&init_user_ns, cred->fsuid)); - pr_err("->*gid = { %d,%d,%d,%d }\n", - from_kgid_munged(&init_user_ns, cred->gid), - from_kgid_munged(&init_user_ns, cred->egid), - from_kgid_munged(&init_user_ns, cred->sgid), - from_kgid_munged(&init_user_ns, cred->fsgid)); -#ifdef CONFIG_SECURITY - pr_err("->security is %p\n", cred->security); - if ((unsigned long) cred->security >= PAGE_SIZE && - (((unsigned long) cred->security & 0xffffff00) != - (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8))) - pr_err("->security {%x, %x}\n", - ((u32*)cred->security)[0], - ((u32*)cred->security)[1]); -#endif -} - -/* - * report use of invalid credentials - */ -void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line) -{ - pr_err("Invalid credentials\n"); - pr_err("At %s:%u\n", file, line); - dump_invalid_creds(cred, "Specified", current); - BUG(); -} -EXPORT_SYMBOL(__invalid_creds); - -/* - * check the credentials on a process - */ -void __validate_process_creds(struct task_struct *tsk, - const char *file, unsigned line) -{ - if (tsk->cred == tsk->real_cred) { - if (unlikely(read_cred_subscribers(tsk->cred) < 2 || - creds_are_invalid(tsk->cred))) - goto invalid_creds; - } else { - if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 || - read_cred_subscribers(tsk->cred) < 1 || - creds_are_invalid(tsk->real_cred) || - creds_are_invalid(tsk->cred))) - goto invalid_creds; - } - return; - -invalid_creds: - pr_err("Invalid process credentials\n"); - pr_err("At %s:%u\n", file, line); - - dump_invalid_creds(tsk->real_cred, "Real", tsk); - if (tsk->cred != tsk->real_cred) - dump_invalid_creds(tsk->cred, "Effective", tsk); - else - pr_err("Effective creds == Real creds\n"); - BUG(); -} -EXPORT_SYMBOL(__validate_process_creds); - -/* - * check creds for do_exit() - */ -void validate_creds_for_do_exit(struct task_struct *tsk) -{ - kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})", - tsk->real_cred, tsk->cred, - atomic_read(&tsk->cred->usage), - read_cred_subscribers(tsk->cred)); - - __validate_process_creds(tsk, __FILE__, __LINE__); -} - -#endif /* CONFIG_DEBUG_CREDENTIALS */ diff --git a/kernel/exit.c b/kernel/exit.c index ee9f43bed49a..aedc0832c9f4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -824,8 +824,6 @@ void __noreturn do_exit(long code) ptrace_event(PTRACE_EVENT_EXIT, code); user_events_exit(tsk); - validate_creds_for_do_exit(tsk); - io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ @@ -909,7 +907,6 @@ void __noreturn do_exit(long code) if (tsk->task_frag.page) put_page(tsk->task_frag.page); - validate_creds_for_do_exit(tsk); exit_task_stack_account(tsk); check_stack_usage(); diff --git a/kernel/resource.c b/kernel/resource.c index 866ef3663a0b..91be1bc50b60 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1844,8 +1844,8 @@ get_free_mem_region(struct device *dev, struct resource *base, write_lock(&resource_lock); for (addr = gfr_start(base, size, align, flags); - gfr_continue(base, addr, size, flags); - addr = gfr_next(addr, size, flags)) { + gfr_continue(base, addr, align, flags); + addr = gfr_next(addr, align, flags)) { if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) != REGION_DISJOINT) continue; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8d2a4f00eca9..5a114e752f11 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -644,8 +644,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) *cnt = rb_time_cnt(top); - /* If top and msb counts don't match, this interrupted a write */ - if (*cnt != rb_time_cnt(msb)) + /* If top, msb or bottom counts don't match, this interrupted a write */ + if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom)) return false; /* The shift to msb will lose its cnt bits */ @@ -706,6 +706,9 @@ static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) unsigned long cnt2, top2, bottom2, msb2; u64 val; + /* Any interruptions in this function should cause a failure */ + cnt = local_read(&t->cnt); + /* The cmpxchg always fails if it interrupted an update */ if (!__rb_time_read(t, &val, &cnt2)) return false; @@ -713,17 +716,18 @@ static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) if (val != expect) return false; - cnt = local_read(&t->cnt); if ((cnt & 3) != cnt2) return false; cnt2 = cnt + 1; rb_time_split(val, &top, &bottom, &msb); + msb = rb_time_val_cnt(msb, cnt); top = rb_time_val_cnt(top, cnt); bottom = rb_time_val_cnt(bottom, cnt); rb_time_split(set, &top2, &bottom2, &msb2); + msb2 = rb_time_val_cnt(msb2, cnt); top2 = rb_time_val_cnt(top2, cnt2); bottom2 = rb_time_val_cnt(bottom2, cnt2); @@ -1787,6 +1791,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) free_buffer_page(bpage); } + free_page((unsigned long)cpu_buffer->free_page); + kfree(cpu_buffer); } @@ -2407,7 +2413,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter) */ barrier(); - if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE) + if ((iter->head + length) > commit || length > BUF_PAGE_SIZE) /* Writer corrupted the read? */ goto reset; @@ -2981,25 +2987,6 @@ static unsigned rb_calculate_event_length(unsigned length) return length; } -static u64 rb_time_delta(struct ring_buffer_event *event) -{ - switch (event->type_len) { - case RINGBUF_TYPE_PADDING: - return 0; - - case RINGBUF_TYPE_TIME_EXTEND: - return rb_event_time_stamp(event); - - case RINGBUF_TYPE_TIME_STAMP: - return 0; - - case RINGBUF_TYPE_DATA: - return event->time_delta; - default: - return 0; - } -} - static inline bool rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) @@ -3007,8 +2994,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, unsigned long new_index, old_index; struct buffer_page *bpage; unsigned long addr; - u64 write_stamp; - u64 delta; new_index = rb_event_index(event); old_index = new_index + rb_event_ts_length(event); @@ -3017,14 +3002,10 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, bpage = READ_ONCE(cpu_buffer->tail_page); - delta = rb_time_delta(event); - - if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp)) - return false; - - /* Make sure the write stamp is read before testing the location */ - barrier(); - + /* + * Make sure the tail_page is still the same and + * the next write location is the end of this event + */ if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) { unsigned long write_mask = local_read(&bpage->write) & ~RB_WRITE_MASK; @@ -3035,20 +3016,20 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, * to make sure that the next event adds an absolute * value and does not rely on the saved write stamp, which * is now going to be bogus. + * + * By setting the before_stamp to zero, the next event + * is not going to use the write_stamp and will instead + * create an absolute timestamp. This means there's no + * reason to update the wirte_stamp! */ rb_time_set(&cpu_buffer->before_stamp, 0); - /* Something came in, can't discard */ - if (!rb_time_cmpxchg(&cpu_buffer->write_stamp, - write_stamp, write_stamp - delta)) - return false; - /* * If an event were to come in now, it would see that the * write_stamp and the before_stamp are different, and assume * that this event just added itself before updating * the write stamp. The interrupting event will fix the - * write stamp for us, and use the before stamp as its delta. + * write stamp for us, and use an absolute timestamp. */ /* @@ -3485,7 +3466,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, return; /* - * If this interrupted another event, + * If this interrupted another event, */ if (atomic_inc_return(this_cpu_ptr(&checking)) != 1) goto out; @@ -3579,7 +3560,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, * absolute timestamp. * Don't bother if this is the start of a new page (w == 0). */ - if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) { + if (!w) { + /* Use the sub-buffer timestamp */ + info->delta = 0; + } else if (unlikely(!a_ok || !b_ok || info->before != info->after)) { info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND; info->length += RB_LEN_TIME_EXTEND; } else { @@ -3602,26 +3586,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) { - /* before and after may now different, fix it up*/ - b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - if (a_ok && b_ok && info->before != info->after) - (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, - info->before, info->after); - if (a_ok && b_ok) - check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); + check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); return rb_move_tail(cpu_buffer, tail, info); } if (likely(tail == w)) { - u64 save_before; - bool s_ok; - /* Nothing interrupted us between A and C */ /*D*/ rb_time_set(&cpu_buffer->write_stamp, info->ts); - barrier(); - /*E*/ s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before); - RB_WARN_ON(cpu_buffer, !s_ok); + /* + * If something came in between C and D, the write stamp + * may now not be in sync. But that's fine as the before_stamp + * will be different and then next event will just be forced + * to use an absolute timestamp. + */ if (likely(!(info->add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE)))) /* This did not interrupt any time update */ @@ -3629,24 +3606,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, else /* Just use full timestamp for interrupting event */ info->delta = info->ts; - barrier(); check_buffer(cpu_buffer, info, tail); - if (unlikely(info->ts != save_before)) { - /* SLOW PATH - Interrupted between C and E */ - - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - RB_WARN_ON(cpu_buffer, !a_ok); - - /* Write stamp must only go forward */ - if (save_before > info->after) { - /* - * We do not care about the result, only that - * it gets updated atomically. - */ - (void)rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, save_before); - } - } } else { u64 ts; /* SLOW PATH - Interrupted between A and C */ @@ -3714,6 +3674,12 @@ rb_reserve_next_event(struct trace_buffer *buffer, int nr_loops = 0; int add_ts_default; + /* ring buffer does cmpxchg, make sure it is safe in NMI context */ + if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && + (unlikely(in_nmi()))) { + return NULL; + } + rb_start_commit(cpu_buffer); /* The commit page can not change after this */ @@ -3737,6 +3703,8 @@ rb_reserve_next_event(struct trace_buffer *buffer, if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) { add_ts_default = RB_ADD_STAMP_ABSOLUTE; info.length += RB_LEN_TIME_EXTEND; + if (info.length > BUF_MAX_DATA_SIZE) + goto out_fail; } else { add_ts_default = RB_ADD_STAMP_NONE; } @@ -5118,7 +5086,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) if (!iter) return NULL; - iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags); + /* Holds the entire event: data and meta data */ + iter->event = kmalloc(BUF_PAGE_SIZE, flags); if (!iter->event) { kfree(iter); return NULL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index fbcd3bafb93e..199df497db07 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4722,7 +4722,11 @@ static int s_show(struct seq_file *m, void *v) iter->leftover = ret; } else { - print_trace_line(iter); + ret = print_trace_line(iter); + if (ret == TRACE_TYPE_PARTIAL_LINE) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + } ret = trace_print_seq(m, &iter->seq); /* * If we overflow the seq_file buffer, then it will @@ -4964,6 +4968,12 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp) return 0; } +int tracing_single_release_file_tr(struct inode *inode, struct file *filp) +{ + tracing_release_file_tr(inode, filp); + return single_release(inode, filp); +} + static int tracing_mark_open(struct inode *inode, struct file *filp) { stream_open(inode, filp); @@ -6344,7 +6354,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, if (!tr->array_buffer.buffer) return 0; - /* Do not allow tracing while resizng ring buffer */ + /* Do not allow tracing while resizing ring buffer */ tracing_stop_tr(tr); ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu); @@ -6352,7 +6362,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, goto out_start; #ifdef CONFIG_TRACER_MAX_TRACE - if (!tr->current_trace->use_max_tr) + if (!tr->allocated_snapshot) goto out; ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b7f4ea25a194..0489e72c8169 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -617,6 +617,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); int tracing_open_file_tr(struct inode *inode, struct file *filp); int tracing_release_file_tr(struct inode *inode, struct file *filp); +int tracing_single_release_file_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 1abc07fba1b9..5ecf3c8bde20 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5623,10 +5623,12 @@ static int event_hist_open(struct inode *inode, struct file *file) { int ret; - ret = security_locked_down(LOCKDOWN_TRACEFS); + ret = tracing_open_file_tr(inode, file); if (ret) return ret; + /* Clear private_data to avoid warning in single_open() */ + file->private_data = NULL; return single_open(file, hist_show, file); } @@ -5634,7 +5636,7 @@ const struct file_operations event_hist_fops = { .open = event_hist_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = tracing_single_release_file_tr, }; #ifdef CONFIG_HIST_TRIGGERS_DEBUG @@ -5900,10 +5902,12 @@ static int event_hist_debug_open(struct inode *inode, struct file *file) { int ret; - ret = security_locked_down(LOCKDOWN_TRACEFS); + ret = tracing_open_file_tr(inode, file); if (ret) return ret; + /* Clear private_data to avoid warning in single_open() */ + file->private_data = NULL; return single_open(file, hist_debug_show, file); } @@ -5911,7 +5915,7 @@ const struct file_operations event_hist_debug_fops = { .open = event_hist_debug_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = tracing_single_release_file_tr, }; #endif diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index d8b302d01083..3e7fa44dc2b2 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1587,11 +1587,12 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter, { struct print_entry *field; struct trace_seq *s = &iter->seq; + int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); seq_print_ip_sym(s, field->ip, flags); - trace_seq_printf(s, ": %s", field->buf); + trace_seq_printf(s, ": %.*s", max, field->buf); return trace_handle_return(s); } @@ -1600,10 +1601,11 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags, struct trace_event *event) { struct print_entry *field; + int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); - trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf); + trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf); return trace_handle_return(&iter->seq); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index cc7d53d9dc01..4405f81248fb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1739,21 +1739,6 @@ config DEBUG_MAPLE_TREE endmenu -config DEBUG_CREDENTIALS - bool "Debug credential management" - depends on DEBUG_KERNEL - help - Enable this to turn on some debug checking for credential - management. The additional code keeps track of the number of - pointers from task_structs to any given cred struct, and checks to - see that this number never exceeds the usage count of the cred - struct. - - Furthermore, if SELinux is enabled, this also checks that the - security pointer in the cred struct is never seen to be invalid. - - If unsure, say N. - source "kernel/rcu/Kconfig.debug" config DEBUG_WQ_FORCE_RR_CPU diff --git a/mm/damon/core.c b/mm/damon/core.c index ce1562783e7e..3a05e71509b9 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -445,6 +445,8 @@ struct damon_ctx *damon_new_ctx(void) if (!ctx) return NULL; + init_completion(&ctx->kdamond_started); + ctx->attrs.sample_interval = 5 * 1000; ctx->attrs.aggr_interval = 100 * 1000; ctx->attrs.ops_update_interval = 60 * 1000 * 1000; @@ -668,11 +670,14 @@ static int __damon_start(struct damon_ctx *ctx) mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; + reinit_completion(&ctx->kdamond_started); ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { err = PTR_ERR(ctx->kdamond); ctx->kdamond = NULL; + } else { + wait_for_completion(&ctx->kdamond_started); } } mutex_unlock(&ctx->kdamond_lock); @@ -1433,6 +1438,7 @@ static int kdamond_fn(void *data) pr_debug("kdamond (%d) starts\n", current->pid); + complete(&ctx->kdamond_started); kdamond_init_intervals_sis(ctx); if (ctx->ops.init) diff --git a/mm/shmem.c b/mm/shmem.c index 91e2620148b2..0d1ce70bce38 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1080,7 +1080,24 @@ whole_folios: } VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); - truncate_inode_folio(mapping, folio); + + if (!folio_test_large(folio)) { + truncate_inode_folio(mapping, folio); + } else if (truncate_inode_partial_folio(folio, lstart, lend)) { + /* + * If we split a page, reset the loop so + * that we pick up the new sub pages. + * Otherwise the THP was entirely + * dropped or the target range was + * zeroed, so just continue the loop as + * is. + */ + if (!folio_test_large(folio)) { + folio_unlock(folio); + index = start; + break; + } + } } folio_unlock(folio); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 506f8220c5fe..9dd8977de5a2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4089,6 +4089,9 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) else VM_WARN_ON_ONCE(true); + WRITE_ONCE(lruvec->lrugen.seg, seg); + WRITE_ONCE(lruvec->lrugen.gen, new); + hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) @@ -4099,9 +4102,6 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; - lruvec->lrugen.gen = new; - WRITE_ONCE(lruvec->lrugen.seg, seg); - if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); @@ -4124,11 +4124,11 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg) gen = get_memcg_gen(pgdat->memcg_lru.seq); + lruvec->lrugen.gen = gen; + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; - lruvec->lrugen.gen = gen; - spin_unlock_irq(&pgdat->memcg_lru.lock); } } @@ -4232,7 +4232,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c } /* protected */ - if (tier > tier_idx) { + if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); @@ -4598,7 +4598,12 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, } /* try to scrape all its memory if this memcg was deleted */ - *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total; + if (!mem_cgroup_online(memcg)) { + *nr_to_scan = total; + return false; + } + + *nr_to_scan = total >> sc->priority; /* * The aging tries to be lazy to reduce the overhead, while the eviction @@ -4635,7 +4640,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) - return 0; + return -1; if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan)) return nr_to_scan; @@ -4648,20 +4653,41 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0; } -static unsigned long get_nr_to_reclaim(struct scan_control *sc) +static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { + int i; + enum zone_watermarks mark; + /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) - return -1; + return false; + + if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) + return true; + + /* check the order to exclude compaction-induced reclaim */ + if (!current_is_kswapd() || sc->order) + return false; + + mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? + WMARK_PROMO : WMARK_HIGH; + + for (i = 0; i <= sc->reclaim_idx; i++) { + struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; + unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; + + if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) + return false; + } - return max(sc->nr_to_reclaim, compact_gap(sc->order)); + /* kswapd should abort if all eligible zones are safe */ + return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; - unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); int swappiness = get_swappiness(lruvec, sc); /* clean file folios are more likely to exist */ @@ -4683,13 +4709,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) if (scanned >= nr_to_scan) break; - if (sc->nr_reclaimed >= nr_to_reclaim) + if (should_abort_scan(lruvec, sc)) break; cond_resched(); } - /* whether try_to_inc_max_seq() was successful */ + /* whether this lruvec should be rotated */ return nr_to_scan < 0; } @@ -4698,14 +4724,9 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; - int seg = lru_gen_memcg_seg(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - /* see the comment on MEMCG_NR_GENS */ - if (!lruvec_is_sizable(lruvec, sc)) - return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; - mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(NULL, memcg)) @@ -4713,7 +4734,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ - if (seg != MEMCG_LRU_TAIL) + if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); @@ -4729,7 +4750,15 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) flush_reclaim_state(sc); - return success ? MEMCG_LRU_YOUNG : 0; + if (success && mem_cgroup_online(memcg)) + return MEMCG_LRU_YOUNG; + + if (!success && lruvec_is_sizable(lruvec, sc)) + return 0; + + /* one retry if offlined or too small */ + return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ? + MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } #ifdef CONFIG_MEMCG @@ -4743,14 +4772,13 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; - const struct hlist_nulls_node *pos; - unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); + struct hlist_nulls_node *pos; + gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; - gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); rcu_read_lock(); @@ -4761,6 +4789,10 @@ restart: } mem_cgroup_put(memcg); + memcg = NULL; + + if (gen != READ_ONCE(lrugen->gen)) + continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); @@ -4777,7 +4809,7 @@ restart: rcu_read_lock(); - if (sc->nr_reclaimed >= nr_to_reclaim) + if (should_abort_scan(lruvec, sc)) break; } @@ -4788,7 +4820,7 @@ restart: mem_cgroup_put(memcg); - if (sc->nr_reclaimed >= nr_to_reclaim) + if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ @@ -4845,16 +4877,14 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* - * Determine the initial priority based on ((total / MEMCG_NR_GENS) >> - * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the - * estimated reclaimed_to_scanned_ratio = inactive / total. + * Determine the initial priority based on + * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, + * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_swappiness(lruvec, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); - reclaimable /= MEMCG_NR_GENS; - /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); diff --git a/mm/workingset.c b/mm/workingset.c index b192e44a0e7c..33baad203277 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -313,10 +313,10 @@ static void lru_gen_refault(struct folio *folio, void *shadow) * 1. For pages accessed through page tables, hotter pages pushed out * hot pages which refaulted immediately. * 2. For pages accessed multiple times through file descriptors, - * numbers of accesses might have been out of the range. + * they would have been protected by sort_folio(). */ - if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) { - folio_set_workingset(folio); + if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) { + set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset)); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); } unlock: diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 9ba04a69ec2a..a852ec093fa8 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1775,15 +1775,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } case TIOCINQ: { - /* - * These two are safe on a single CPU system as only - * user tasks fiddle here - */ - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + struct sk_buff *skb; long amount = 0; + spin_lock_irq(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len - sizeof(struct ddpehdr); + spin_unlock_irq(&sk->sk_receive_queue.lock); rc = put_user(amount, (int __user *)argp); break; } diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 838ebf0cabbf..f81f8d56f5c0 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -73,14 +73,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, case SIOCINQ: { struct sk_buff *skb; + int amount; if (sock->state != SS_CONNECTED) { error = -EINVAL; goto done; } + spin_lock_irq(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); - error = put_user(skb ? skb->len : 0, - (int __user *)argp) ? -EFAULT : 0; + amount = skb ? skb->len : 0; + spin_unlock_irq(&sk->sk_receive_queue.lock); + error = put_user(amount, (int __user *)argp) ? -EFAULT : 0; goto done; } case ATM_SETSC: diff --git a/net/core/neighbour.c b/net/core/neighbour.c index df81c1f0a570..552719c3bbc3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -253,9 +253,11 @@ static int neigh_forced_gc(struct neigh_table *tbl) { int max_clean = atomic_read(&tbl->gc_entries) - READ_ONCE(tbl->gc_thresh2); + u64 tmax = ktime_get_ns() + NSEC_PER_MSEC; unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; + int loop = 0; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); @@ -278,11 +280,16 @@ static int neigh_forced_gc(struct neigh_table *tbl) shrunk++; if (shrunk >= max_clean) break; + if (++loop == 16) { + if (ktime_get_ns() > tmax) + goto unlock; + loop = 0; + } } } WRITE_ONCE(tbl->last_flush, jiffies); - +unlock: write_unlock_bh(&tbl->lock); return shrunk; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b157efea5dea..83af8aaeb893 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4522,8 +4522,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. + * Cap len to not accidentally hit GSO_BY_FRAGS. */ - partial_segs = len / mss; + partial_segs = min(len, GSO_BY_FRAGS - 1) / mss; if (partial_segs > 1) mss *= partial_segs; else diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 90de838a2745..701cb87043f2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4368,6 +4368,23 @@ EXPORT_SYMBOL(tcp_do_parse_auth_options); * up to bandwidth of 18Gigabit/sec. 8) ] */ +/* Estimates max number of increments of remote peer TSval in + * a replay window (based on our current RTO estimation). + */ +static u32 tcp_tsval_replay(const struct sock *sk) +{ + /* If we use usec TS resolution, + * then expect the remote peer to use the same resolution. + */ + if (tcp_sk(sk)->tcp_usec_ts) + return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ); + + /* RFC 7323 recommends a TSval clock between 1ms and 1sec. + * We know that some OS (including old linux) can use 1200 Hz. + */ + return inet_csk(sk)->icsk_rto * 1200 / HZ; +} + static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); @@ -4375,7 +4392,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) u32 seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; - return (/* 1. Pure ACK with correct sequence number. */ + return /* 1. Pure ACK with correct sequence number. */ (th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) && /* 2. ... and duplicate ACK. */ @@ -4385,7 +4402,8 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) !tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) && /* 4. ... and sits in replay window. */ - (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ); + (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= + tcp_tsval_replay(sk); } static inline bool tcp_paws_discard(const struct sock *sk, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f5ef15e1d9ac..e3167ad96567 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3293,7 +3293,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (skb_still_in_host_queue(sk, skb)) return -EBUSY; +start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { + if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(skb)->seq++; + goto start; + } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3aaea56b5166..2692a7b24c40 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6149,11 +6149,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, pmsg->prefix_len = pinfo->prefix_len; pmsg->prefix_type = pinfo->type; pmsg->prefix_pad3 = 0; - pmsg->prefix_flags = 0; - if (pinfo->onlink) - pmsg->prefix_flags |= IF_PREFIX_ONLINK; - if (pinfo->autoconf) - pmsg->prefix_flags |= IF_PREFIX_AUTOCONF; + pmsg->prefix_flags = pinfo->flags; if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix)) goto nla_put_failure; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 0cc5a4e19900..ecb91ad4ce63 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1315,9 +1315,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case TIOCINQ: { struct sk_buff *skb; long amount = 0L; - /* These two are safe on a single CPU system as only user tasks fiddle here */ + + spin_lock_irq(&sk->sk_receive_queue.lock); if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) amount = skb->len; + spin_unlock_irq(&sk->sk_receive_queue.lock); return put_user(amount, (unsigned int __user *) argp); } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b3f4a503ee2b..f69c47945175 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -286,9 +286,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_get(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_get_ref(ct_ft); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_put(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_put(ct_ft); +} + static struct nf_flowtable_type flowtable_ct = { .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, + .get = tcf_ct_nf_get, + .put = tcf_ct_nf_put, .owner = THIS_MODULE, }; @@ -337,9 +359,13 @@ err_alloc: return err; } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) +{ + refcount_inc(&ct_ft->ref); +} + static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { - struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; struct flow_block *block; @@ -347,13 +373,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) rwork); nf_flow_table_free(&ct_ft->nf_ft); - /* Remove any remaining callbacks before cleanup */ block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); - list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } + WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 7bfe7d9a32aa..04534ea537c8 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -40,9 +40,6 @@ static unsigned long number_cred_unused; static struct cred machine_cred = { .usage = ATOMIC_INIT(1), -#ifdef CONFIG_DEBUG_CREDENTIALS - .magic = CRED_MAGIC, -#endif }; /* diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index c8e162c9d1df..6df246b53260 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -843,7 +843,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk) struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; - bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; diff --git a/scripts/sign-file.c b/scripts/sign-file.c index 598ef5465f82..3edb156ae52c 100644 --- a/scripts/sign-file.c +++ b/scripts/sign-file.c @@ -322,7 +322,7 @@ int main(int argc, char **argv) CMS_NOSMIMECAP | use_keyid | use_signed_attrs), "CMS_add1_signer"); - ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0, + ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) != 1, "CMS_final"); #else @@ -341,10 +341,10 @@ int main(int argc, char **argv) b = BIO_new_file(sig_file_name, "wb"); ERR(!b, "%s", sig_file_name); #ifndef USE_PKCS7 - ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0, + ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) != 1, "%s", sig_file_name); #else - ERR(i2d_PKCS7_bio(b, pkcs7) < 0, + ERR(i2d_PKCS7_bio(b, pkcs7) != 1, "%s", sig_file_name); #endif BIO_free(b); @@ -374,9 +374,9 @@ int main(int argc, char **argv) if (!raw_sig) { #ifndef USE_PKCS7 - ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name); + ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) != 1, "%s", dest_name); #else - ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name); + ERR(i2d_PKCS7_bio(bd, pkcs7) != 1, "%s", dest_name); #endif } else { BIO *b; @@ -396,7 +396,7 @@ int main(int argc, char **argv) ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name); ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name); - ERR(BIO_free(bd) < 0, "%s", dest_name); + ERR(BIO_free(bd) != 1, "%s", dest_name); /* Finally, if we're signing in place, replace the original. */ if (replace_orig) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index feda711c6b7b..340b2bbbb2dd 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1660,8 +1660,6 @@ static int inode_has_perm(const struct cred *cred, struct inode_security_struct *isec; u32 sid; - validate_creds(cred); - if (unlikely(IS_PRIVATE(inode))) return 0; @@ -3056,8 +3054,6 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, struct inode_security_struct *isec; u32 sid; - validate_creds(cred); - ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; sid = cred_sid(cred); @@ -3101,8 +3097,6 @@ static int selinux_inode_permission(struct inode *inode, int mask) if (!mask) return 0; - validate_creds(cred); - if (unlikely(IS_PRIVATE(inode))) return 0; diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 1cde2a69bdb4..78cee53fee02 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1993,7 +1993,10 @@ static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1), + SND_PCI_QUIRK(0x1043, 0x86ae, "ASUS", 1), /* Z170 PRO */ + SND_PCI_QUIRK(0x1043, 0x86c7, "ASUS", 1), /* Z170M PLUS */ SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1), + SND_PCI_QUIRK(0x8086, 0x2060, "Intel NUC5CPYB", 1), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1), {} }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 0377912e9264..e45d4c405f8f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9795,6 +9795,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x84ae, "HP 15-db0403ng", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index fb802802939e..63a90c7e8976 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -455,9 +455,9 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv) status = efi.get_variable(efi_name, &efi_guid, &attr, &tas_priv->cali_data.total_sz, tas_priv->cali_data.data); - if (status != EFI_SUCCESS) - return -EINVAL; } + if (status != EFI_SUCCESS) + return -EINVAL; tmp_val = (unsigned int *)tas_priv->cali_data.data; @@ -550,11 +550,6 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) tas2781_save_calibration(tas_priv); out: - if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) { - /*If DSP FW fail, kcontrol won't be created */ - tasdevice_config_info_remove(tas_priv); - tasdevice_dsp_remove(tas_priv); - } mutex_unlock(&tas_priv->codec_lock); if (fmw) release_firmware(fmw); @@ -612,9 +607,13 @@ static void tas2781_hda_unbind(struct device *dev, { struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); struct hda_component *comps = master_data; + comps = &comps[tas_priv->index]; - if (comps[tas_priv->index].dev == dev) - memset(&comps[tas_priv->index], 0, sizeof(*comps)); + if (comps->dev == dev) { + comps->dev = NULL; + memset(comps->name, 0, sizeof(comps->name)); + comps->playback_hook = NULL; + } tasdevice_config_info_remove(tas_priv); tasdevice_dsp_remove(tas_priv); @@ -675,14 +674,14 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt) pm_runtime_put_autosuspend(tas_priv->dev); + tas2781_reset(tas_priv); + ret = component_add(tas_priv->dev, &tas2781_hda_comp_ops); if (ret) { dev_err(tas_priv->dev, "Register component failed: %d\n", ret); pm_runtime_disable(tas_priv->dev); - goto err; } - tas2781_reset(tas_priv); err: if (ret) tas2781_hda_remove(&clt->dev); diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index 649ebdef9c3f..1685d7ea6a9f 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -6,7 +6,6 @@ * * Yes, this is unfortunate. A better solution is in the works. */ -NORETURN(__invalid_creds) NORETURN(__kunit_abort) NORETURN(__module_put_and_kthread_exit) NORETURN(__reiserfs_panic) diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 90f3c9802ffb..95dc58b94178 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -62,5 +62,6 @@ cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o cxl_core-y += config_check.o cxl_core-y += cxl_core_test.o +cxl_core-y += cxl_core_exports.o obj-m += test/ diff --git a/tools/testing/cxl/cxl_core_exports.c b/tools/testing/cxl/cxl_core_exports.c new file mode 100644 index 000000000000..077e6883921d --- /dev/null +++ b/tools/testing/cxl/cxl_core_exports.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ + +#include "cxl.h" + +/* Exporting of cxl_core symbols that are only used by cxl_test */ +EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, CXL); diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index b88546299902..f4e517a0c774 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -669,10 +669,11 @@ static int mock_decoder_commit(struct cxl_decoder *cxld) return 0; dev_dbg(&port->dev, "%s commit\n", dev_name(&cxld->dev)); - if (port->commit_end + 1 != id) { + if (cxl_num_decoders_committed(port) != id) { dev_dbg(&port->dev, "%s: out of order commit, expected decoder%d.%d\n", - dev_name(&cxld->dev), port->id, port->commit_end + 1); + dev_name(&cxld->dev), port->id, + cxl_num_decoders_committed(port)); return -EBUSY; } diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 3b2061d1c1a5..8247a7c69c36 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -155,12 +155,10 @@ ifneq ($(KBUILD_OUTPUT),) abs_objtree := $(realpath $(abs_objtree)) BUILD := $(abs_objtree)/kselftest KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include - KHDR_DIR := ${abs_objtree}/usr/include else BUILD := $(CURDIR) abs_srctree := $(shell cd $(top_srcdir) && pwd) KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include - KHDR_DIR := ${abs_srctree}/usr/include DEFAULT_INSTALL_HDR_PATH := 1 endif @@ -174,7 +172,7 @@ export KHDR_INCLUDES # all isn't the first target in the file. .DEFAULT_GOAL := all -all: kernel_header_files +all: @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ @@ -185,23 +183,6 @@ all: kernel_header_files ret=$$((ret * $$?)); \ done; exit $$ret; -kernel_header_files: - @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ - if [ $$? -ne 0 ]; then \ - RED='\033[1;31m'; \ - NOCOLOR='\033[0m'; \ - echo; \ - echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ - echo "Please run this and try again:"; \ - echo; \ - echo " cd $(top_srcdir)"; \ - echo " make headers"; \ - echo; \ - exit 1; \ - fi - -.PHONY: kernel_header_files - run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64 index 2e70a6048278..49a29dbc1910 100644 --- a/tools/testing/selftests/bpf/config.x86_64 +++ b/tools/testing/selftests/bpf/config.x86_64 @@ -50,7 +50,6 @@ CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_XXHASH=y CONFIG_DCB=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common index 0617275d93cc..0f456dbab62f 100644 --- a/tools/testing/selftests/hid/config.common +++ b/tools/testing/selftests/hid/config.common @@ -46,7 +46,6 @@ CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_XXHASH=y CONFIG_DCB=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEFAULT_FQ_CODEL=y diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 118e0964bda9..aa646e0661f3 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -44,26 +44,10 @@ endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) top_srcdir = $(selfdir)/../../.. -ifeq ("$(origin O)", "command line") - KBUILD_OUTPUT := $(O) +ifeq ($(KHDR_INCLUDES),) +KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include endif -ifneq ($(KBUILD_OUTPUT),) - # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot - # expand a shell special character '~'. We use a somewhat tedious way here. - abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) - $(if $(abs_objtree),, \ - $(error failed to create output directory "$(KBUILD_OUTPUT)")) - # $(realpath ...) resolves symlinks - abs_objtree := $(realpath $(abs_objtree)) - KHDR_DIR := ${abs_objtree}/usr/include -else - abs_srctree := $(shell cd $(top_srcdir) && pwd) - KHDR_DIR := ${abs_srctree}/usr/include -endif - -KHDR_INCLUDES := -isystem $(KHDR_DIR) - # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. @@ -74,25 +58,7 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \ - $(TEST_GEN_FILES) - -kernel_header_files: - @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ - if [ $$? -ne 0 ]; then \ - RED='\033[1;31m'; \ - NOCOLOR='\033[0m'; \ - echo; \ - echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ - echo "Please run this and try again:"; \ - echo; \ - echo " cd $(top_srcdir)"; \ - echo " make headers"; \ - echo; \ - exit 1; \ - fi - -.PHONY: kernel_header_files +all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) define RUN_TESTS BASE_DIR="$(selfdir)"; \ diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 7324ce5363c0..6f2f83990441 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1680,6 +1680,8 @@ int main(int argc, char **argv) { int err; + ksft_print_header(); + pagesize = getpagesize(); thpsize = read_pmd_pagesize(); if (thpsize) @@ -1689,7 +1691,6 @@ int main(int argc, char **argv) ARRAY_SIZE(hugetlbsizes)); detect_huge_zeropage(); - ksft_print_header(); ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() + ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() + ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case()); |