diff options
248 files changed, 4379 insertions, 2857 deletions
diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst index 8aed9103e48a..5c0552e78c58 100644 --- a/Documentation/core-api/cachetlb.rst +++ b/Documentation/core-api/cachetlb.rst @@ -326,6 +326,12 @@ maps this page at its virtual address. dirty. Again, see sparc64 for examples of how to deal with this. + ``void flush_dcache_folio(struct folio *folio)`` + This function is called under the same circumstances as + flush_dcache_page(). It allows the architecture to + optimise for flushing the entire folio of pages instead + of flushing one page at a time. + ``void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len)`` ``void copy_from_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index a42f9baddfbf..395835f9289f 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -95,6 +95,11 @@ More Memory Management Functions .. kernel-doc:: mm/mempolicy.c .. kernel-doc:: include/linux/mm_types.h :internal: +.. kernel-doc:: include/linux/mm_inline.h +.. kernel-doc:: include/linux/page-flags.h .. kernel-doc:: include/linux/mm.h :internal: +.. kernel-doc:: include/linux/page_ref.h .. kernel-doc:: include/linux/mmzone.h +.. kernel-doc:: mm/util.c + :functions: folio_mapping diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 57a641847818..bb68d39f03b7 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -524,3 +524,5 @@ Note that these methods are passed a pointer to the cache resource structure, not the read request structure as they could be used in other situations where there isn't a read request structure as well, such as writing dirty data to the cache. + +.. kernel-doc:: include/linux/netfs.h diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 2e8134059c87..6655d929a351 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -104,6 +104,7 @@ Code Seq# Include File Comments '8' all SNP8023 advanced NIC card <mailto:[email protected]> ';' 64-7F linux/vfio.h +'=' 00-3f uapi/linux/ptp_clock.h <mailto:[email protected]> '@' 00-0F linux/radeonfb.h conflict! '@' 00-0F drivers/video/aty/aty128fb.c conflict! 'A' 00-1F linux/apm_bios.h conflict! diff --git a/MAINTAINERS b/MAINTAINERS index f26920f0fa65..3b79fd441dde 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5458,6 +5458,19 @@ F: include/net/devlink.h F: include/uapi/linux/devlink.h F: net/core/devlink.c +DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT +M: Christoph Niedermaier <[email protected]> +S: Maintained +F: arch/arm/boot/dts/imx6*-dhcom-* + +DH ELECTRONICS STM32MP1 DHCOM/DHCOR BOARD SUPPORT +M: Marek Vasut <[email protected]> +S: Maintained +F: arch/arm/boot/dts/stm32mp1*-dhcom-* +F: arch/arm/boot/dts/stm32mp1*-dhcor-* + DIALOG SEMICONDUCTOR DRIVERS M: Support Opensource <[email protected]> S: Supported @@ -6147,8 +6160,7 @@ T: git git://anongit.freedesktop.org/drm/drm F: Documentation/devicetree/bindings/display/ F: Documentation/devicetree/bindings/gpu/ F: Documentation/gpu/ -F: drivers/gpu/drm/ -F: drivers/gpu/vga/ +F: drivers/gpu/ F: include/drm/ F: include/linux/vga* F: include/uapi/drm/ @@ -11278,7 +11290,6 @@ F: Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst F: drivers/net/ethernet/marvell/octeontx2/af/ MARVELL PRESTERA ETHERNET SWITCH DRIVER -M: Vadym Kochan <[email protected]> M: Taras Chornyi <[email protected]> S: Supported W: https://github.com/Marvell-switching/switchdev-prestera @@ -2,8 +2,8 @@ VERSION = 5 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc7 -NAME = Opossums on Parade +EXTRAVERSION = +NAME = Trick or Treat # *DOCUMENTATION* # To see a list of typical targets execute "make help" diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index e201b4b1655a..e8c2c7469e10 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -36,6 +36,7 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); +void flush_dcache_folio(struct folio *folio); void dma_cache_wback_inv(phys_addr_t start, unsigned long sz); void dma_cache_inv(phys_addr_t start, unsigned long sz); diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts index 8077f1716fbc..ecb91fb899ff 100644 --- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts +++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts @@ -112,7 +112,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 5e56288e343b..e68fb879e4f9 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -290,6 +290,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); +void flush_dcache_folio(struct folio *folio); #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts index 02f8e72f0cad..05486cccee1c 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts @@ -75,7 +75,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts index d17abb515835..e99e7644ff39 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts @@ -70,7 +70,9 @@ regulator-name = "rst-usb-eth2"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb_eth2>; - gpio = <&gpio3 2 GPIO_ACTIVE_LOW>; + gpio = <&gpio3 2 GPIO_ACTIVE_HIGH>; + enable-active-high; + regulator-always-on; }; reg_vdd_5v: regulator-5v { @@ -95,7 +97,7 @@ clocks = <&osc_can>; interrupt-parent = <&gpio4>; interrupts = <28 IRQ_TYPE_EDGE_FALLING>; - spi-max-frequency = <100000>; + spi-max-frequency = <10000000>; vdd-supply = <®_vdd_3v3>; xceiver-supply = <®_vdd_5v>; }; @@ -111,7 +113,7 @@ &fec1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-connection-type = "rgmii"; + phy-connection-type = "rgmii-rxid"; phy-handle = <ðphy>; status = "okay"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi index 9db9b90bf2bc..42bbbb3f532b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi @@ -91,10 +91,12 @@ reg_vdd_soc: BUCK1 { regulator-name = "buck1"; regulator-min-microvolt = <800000>; - regulator-max-microvolt = <900000>; + regulator-max-microvolt = <850000>; regulator-boot-on; regulator-always-on; regulator-ramp-delay = <3125>; + nxp,dvs-run-voltage = <850000>; + nxp,dvs-standby-voltage = <800000>; }; reg_vdd_arm: BUCK2 { @@ -111,7 +113,7 @@ reg_vdd_dram: BUCK3 { regulator-name = "buck3"; regulator-min-microvolt = <850000>; - regulator-max-microvolt = <900000>; + regulator-max-microvolt = <950000>; regulator-boot-on; regulator-always-on; }; @@ -150,7 +152,7 @@ reg_vdd_snvs: LDO2 { regulator-name = "ldo2"; - regulator-min-microvolt = <850000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index 8c15d9fed08f..d12e4cbfc852 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -2590,9 +2590,10 @@ power-domains = <&dispcc MDSS_GDSC>; clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&gcc GCC_DISP_HF_AXI_CLK>, <&gcc GCC_DISP_SF_AXI_CLK>, <&dispcc DISP_CC_MDSS_MDP_CLK>; - clock-names = "iface", "nrt_bus", "core"; + clock-names = "iface", "bus", "nrt_bus", "core"; assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>; assigned-clock-rates = <460000000>; diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 41c23f474ea6..803e7773fa86 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1136,6 +1136,11 @@ out: return prog; } +u64 bpf_jit_alloc_exec_limit(void) +{ + return BPF_JIT_REGION_SIZE; +} + void *bpf_jit_alloc_exec(unsigned long size) { return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index 1ac55e7b47f0..8ab46625ddd3 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -250,6 +250,7 @@ static inline void __flush_page_to_ram(void *vaddr) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) __flush_page_to_ram(page_address(page)) +void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_icache_page(vma, page) __flush_page_to_ram(page_address(page)) diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index b3dc9c589442..f207388541d5 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -61,6 +61,8 @@ static inline void flush_dcache_page(struct page *page) SetPageDcacheDirty(page); } +void flush_dcache_folio(struct folio *folio); + #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index c2a222ebfa2a..3fc0bb7d6487 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -27,6 +27,7 @@ void flush_cache_vunmap(unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); +void flush_dcache_folio(struct folio *folio); void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, void *src, int len); void copy_from_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c index 0e23e3a8df6b..d55b73b18149 100644 --- a/arch/nds32/kernel/ftrace.c +++ b/arch/nds32/kernel/ftrace.c @@ -6,7 +6,7 @@ #ifndef CONFIG_DYNAMIC_FTRACE extern void (*ftrace_trace_function)(unsigned long, unsigned long, - struct ftrace_ops*, struct pt_regs*); + struct ftrace_ops*, struct ftrace_regs*); extern void ftrace_graph_caller(void); noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h index 18eb9f69f806..1999561b22aa 100644 --- a/arch/nios2/include/asm/cacheflush.h +++ b/arch/nios2/include/asm/cacheflush.h @@ -28,7 +28,8 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 -extern void flush_dcache_page(struct page *page); +void flush_dcache_page(struct page *page); +void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_icache_page(struct vm_area_struct *vma, struct page *page); diff --git a/arch/nios2/platform/Kconfig.platform b/arch/nios2/platform/Kconfig.platform index 9e32fb7f3d4c..e849daff6fd1 100644 --- a/arch/nios2/platform/Kconfig.platform +++ b/arch/nios2/platform/Kconfig.platform @@ -37,6 +37,7 @@ config NIOS2_DTB_PHYS_ADDR config NIOS2_DTB_SOURCE_BOOL bool "Compile and link device tree into kernel image" + depends on !COMPILE_TEST help This allows you to specify a dts (device tree source) file which will be compiled and linked into the kernel image. diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index eef0096db5f8..da0cd4b3a28f 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -49,7 +49,8 @@ void invalidate_kernel_vmap_range(void *vaddr, int size); #define flush_cache_vunmap(start, end) flush_cache_all() #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 -extern void flush_dcache_page(struct page *page); +void flush_dcache_page(struct page *page); +void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index dab5c56ffd0e..a52af8fbf571 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1302,6 +1302,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) struct property *default_win; int reset_win_ext; + /* DDW + IOMMU on single window may fail if there is any allocation */ + if (iommu_table_in_use(tbl)) { + dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n"); + goto out_failed; + } + default_win = of_find_property(pdn, "ibm,dma-window", NULL); if (!default_win) goto out_failed; @@ -1356,12 +1362,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) query.largest_available_block, 1ULL << page_shift); - /* DDW + IOMMU on single window may fail if there is any allocation */ - if (default_win_removed && iommu_table_in_use(tbl)) { - dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n"); - goto out_failed; - } - len = order_base_2(query.largest_available_block << page_shift); win_name = DMA64_PROPNAME; } else { @@ -1411,18 +1411,19 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) } else { struct iommu_table *newtbl; int i; + unsigned long start = 0, end = 0; for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) { const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM; /* Look for MMIO32 */ - if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) + if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) { + start = pci->phb->mem_resources[i].start; + end = pci->phb->mem_resources[i].end; break; + } } - if (i == ARRAY_SIZE(pci->phb->mem_resources)) - goto out_del_list; - /* New table for using DDW instead of the default DMA window */ newtbl = iommu_pseries_alloc_table(pci->phb->node); if (!newtbl) { @@ -1432,15 +1433,15 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr, 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops); - iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start, - pci->phb->mem_resources[i].end); + iommu_init_table(newtbl, pci->phb->node, start, end); pci->table_group->tables[1] = newtbl; /* Keep default DMA window stuct if removed */ if (default_win_removed) { tbl->it_size = 0; - kfree(tbl->it_map); + vfree(tbl->it_map); + tbl->it_map = NULL; } set_iommu_table_base(&dev->dev, newtbl); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 6a6fa9e976d5..f076cee11af6 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -163,6 +163,12 @@ config PAGE_OFFSET default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB +config KASAN_SHADOW_OFFSET + hex + depends on KASAN_GENERIC + default 0xdfffffc800000000 if 64BIT + default 0xffffffff if 32BIT + config ARCH_FLATMEM_ENABLE def_bool !NUMA diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h index a2b3d9cdbc86..b00f503ec124 100644 --- a/arch/riscv/include/asm/kasan.h +++ b/arch/riscv/include/asm/kasan.h @@ -30,8 +30,7 @@ #define KASAN_SHADOW_SIZE (UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_SHADOW_START KERN_VIRT_START #define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE) -#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \ - (64 - KASAN_SHADOW_SCALE_SHIFT))) +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) void kasan_init(void); asmlinkage void kasan_early_init(void); diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index fce5184b22c3..52c5ff9804c5 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -193,6 +193,7 @@ setup_trap_vector: csrw CSR_SCRATCH, zero ret +.align 2 .Lsecondary_park: /* We lack SMP support or have too many harts, so park this hart */ wfi diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index d7189c8714a9..54294f83513d 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -17,6 +17,9 @@ asmlinkage void __init kasan_early_init(void) uintptr_t i; pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START); + BUILD_BUG_ON(KASAN_SHADOW_OFFSET != + KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT))); + for (i = 0; i < PTRS_PER_PTE; ++i) set_pte(kasan_early_shadow_pte + i, mk_pte(virt_to_page(kasan_early_shadow_page), @@ -172,21 +175,10 @@ void __init kasan_init(void) phys_addr_t p_start, p_end; u64 i; - /* - * Populate all kernel virtual address space with kasan_early_shadow_page - * except for the linear mapping and the modules/kernel/BPF mapping. - */ - kasan_populate_early_shadow((void *)KASAN_SHADOW_START, - (void *)kasan_mem_to_shadow((void *) - VMEMMAP_END)); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) kasan_shallow_populate( (void *)kasan_mem_to_shadow((void *)VMALLOC_START), (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); - else - kasan_populate_early_shadow( - (void *)kasan_mem_to_shadow((void *)VMALLOC_START), - (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); /* Populate the linear mapping */ for_each_mem_range(i, &p_start, &p_end) { diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index fed86f42dfbe..753d85bdfad0 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -125,7 +125,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (i == NR_JIT_ITERATIONS) { pr_err("bpf-jit: image did not converge in <%d passes!\n", i); - bpf_jit_binary_free(jit_data->header); + if (jit_data->header) + bpf_jit_binary_free(jit_data->header); prog = orig_prog; goto out_offset; } @@ -166,6 +167,11 @@ out: return prog; } +u64 bpf_jit_alloc_exec_limit(void) +{ + return BPF_JIT_REGION_SIZE; +} + void *bpf_jit_alloc_exec(unsigned long size) { return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 10722455fd02..2245f4b8d362 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3053,13 +3053,14 @@ static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask) int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus); struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; struct kvm_vcpu *vcpu; + u8 vcpu_isc_mask; for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) { vcpu = kvm_get_vcpu(kvm, vcpu_idx); if (psw_ioint_disabled(vcpu)) continue; - deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24); - if (deliverable_mask) { + vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24); + if (deliverable_mask & vcpu_isc_mask) { /* lately kicked but not yet running */ if (test_and_set_bit(vcpu_idx, gi->kicked_mask)) return; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6a6dd5e1daf6..1c97493d21e1 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3363,6 +3363,7 @@ out_free_sie_block: int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); return kvm_s390_vcpu_has_irq(vcpu, 0); } diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index 372afa82fee6..c7a97f32432f 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -42,7 +42,8 @@ extern void flush_cache_page(struct vm_area_struct *vma, extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 -extern void flush_dcache_page(struct page *page); +void flush_dcache_page(struct page *page); +void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); #define flush_icache_user_range flush_icache_range extern void flush_icache_page(struct vm_area_struct *vma, diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index 18d2f5199194..1cc72b4804fa 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -78,7 +78,7 @@ vpxor tmp0, x, x; -.section .rodata.cst164, "aM", @progbits, 164 +.section .rodata.cst16, "aM", @progbits, 16 .align 16 /* @@ -133,6 +133,10 @@ .L0f0f0f0f: .long 0x0f0f0f0f +/* 12 bytes, only for padding */ +.Lpadding_deadbeef: + .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef + .text .align 16 diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S index d2ffd7f76ee2..9c5d3f3ad45a 100644 --- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S @@ -93,7 +93,7 @@ vpxor tmp0, x, x; -.section .rodata.cst164, "aM", @progbits, 164 +.section .rodata.cst16, "aM", @progbits, 16 .align 16 /* @@ -148,6 +148,10 @@ .L0f0f0f0f: .long 0x0f0f0f0f +/* 12 bytes, only for padding */ +.Lpadding_deadbeef: + .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef + .text .align 16 diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5a0298aa56ba..13f64654dfff 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1098,7 +1098,7 @@ struct kvm_arch { u64 cur_tsc_generation; int nr_vcpus_matched_tsc; - spinlock_t pvclock_gtod_sync_lock; + raw_spinlock_t pvclock_gtod_sync_lock; bool use_master_clock; u64 master_kernel_ns; u64 master_cycle_now; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 2e4916be290e..7e34d7163ada 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2591,11 +2591,20 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) { - if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2)) + int count; + int bytes; + + if (svm->vmcb->control.exit_info_2 > INT_MAX) + return -EINVAL; + + count = svm->vmcb->control.exit_info_2; + if (unlikely(check_mul_overflow(count, size, &bytes))) + return -EINVAL; + + if (!setup_vmgexit_scratch(svm, in, bytes)) return -EINVAL; - return kvm_sev_es_string_io(&svm->vcpu, size, port, - svm->ghcb_sa, svm->ghcb_sa_len / size, in); + return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b26647a5ea22..bfe0de3008a6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2542,7 +2542,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) kvm_vcpu_write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); - spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); if (!matched) { kvm->arch.nr_vcpus_matched_tsc = 0; } else if (!already_matched) { @@ -2550,7 +2550,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } kvm_track_tsc_matching(vcpu); - spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, @@ -2780,9 +2780,9 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2800,15 +2800,15 @@ u64 get_kvmclock_ns(struct kvm *kvm) unsigned long flags; u64 ret; - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); if (!ka->use_master_clock) { - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); return get_kvmclock_base_ns() + ka->kvmclock_offset; } hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); @@ -2902,13 +2902,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); use_master_clock = ka->use_master_clock; if (use_master_clock) { host_tsc = ka->master_cycle_now; kernel_ns = ka->master_kernel_ns; } - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); @@ -6100,13 +6100,13 @@ set_pit2_out: * is slightly ahead) here we risk going negative on unsigned * 'system_time' when 'user_ns.clock' is very small. */ - spin_lock_irq(&ka->pvclock_gtod_sync_lock); + raw_spin_lock_irq(&ka->pvclock_gtod_sync_lock); if (kvm->arch.use_master_clock) now_ns = ka->master_kernel_ns; else now_ns = get_kvmclock_base_ns(); ka->kvmclock_offset = user_ns.clock - now_ns; - spin_unlock_irq(&ka->pvclock_gtod_sync_lock); + raw_spin_unlock_irq(&ka->pvclock_gtod_sync_lock); kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; @@ -8156,9 +8156,9 @@ static void kvm_hyperv_tsc_notifier(void) list_for_each_entry(kvm, &vm_list, vm_list) { struct kvm_arch *ka = &kvm->arch; - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -8800,9 +8800,17 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); + + /* + * The call to kvm_ready_for_interrupt_injection() may end up in + * kvm_xen_has_interrupt() which may require the srcu lock to be + * held, to protect against changes in the vcpu_info address. + */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; @@ -11199,7 +11207,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); - spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); + raw_spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); kvm->arch.kvmclock_offset = -get_kvmclock_base_ns(); pvclock_update_vm_gtod_copy(kvm); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 9ea9c3dabe37..8f62baebd028 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -190,6 +190,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) int __kvm_xen_has_interrupt(struct kvm_vcpu *v) { + int err; u8 rc = 0; /* @@ -216,13 +217,29 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) if (likely(slots->generation == ghc->generation && !kvm_is_error_hva(ghc->hva) && ghc->memslot)) { /* Fast path */ - __get_user(rc, (u8 __user *)ghc->hva + offset); - } else { - /* Slow path */ - kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, - sizeof(rc)); + pagefault_disable(); + err = __get_user(rc, (u8 __user *)ghc->hva + offset); + pagefault_enable(); + if (!err) + return rc; } + /* Slow path */ + + /* + * This function gets called from kvm_vcpu_block() after setting the + * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately + * from a HLT. So we really mustn't sleep. If the page ended up absent + * at that point, just return 1 in order to trigger an immediate wake, + * and we'll end up getting called again from a context where we *can* + * fault in the page and wait for it. + */ + if (in_atomic() || !task_is_running(current)) + return 1; + + kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, + sizeof(rc)); + return rc; } diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index cf907e5bf2f2..a8a041609c5d 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -120,7 +120,8 @@ void flush_cache_page(struct vm_area_struct*, #define flush_cache_vunmap(start,end) flush_cache_all() #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 -extern void flush_dcache_page(struct page*); +void flush_dcache_page(struct page *); +void flush_dcache_folio(struct folio *); void local_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -137,7 +138,9 @@ void local_flush_cache_page(struct vm_area_struct *vma, #define flush_cache_vunmap(start,end) do { } while (0) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO #define flush_dcache_page(page) do { } while (0) +static inline void flush_dcache_folio(struct folio *folio) { } #define flush_icache_range local_flush_icache_range #define flush_cache_page(vma, addr, pfn) do { } while (0) diff --git a/block/blk-mq.c b/block/blk-mq.c index bc026372de43..652a31fc3bb3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1325,6 +1325,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, int errors, queued; blk_status_t ret = BLK_STS_OK; LIST_HEAD(zone_list); + bool needs_resource = false; if (list_empty(list)) return false; @@ -1370,6 +1371,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, queued++; break; case BLK_STS_RESOURCE: + needs_resource = true; + fallthrough; case BLK_STS_DEV_RESOURCE: blk_mq_handle_dev_resource(rq, list); goto out; @@ -1380,6 +1383,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, * accept. */ blk_mq_handle_zone_resource(rq, &zone_list); + needs_resource = true; break; default: errors++; @@ -1406,7 +1410,6 @@ out: /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED); - bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET; if (nr_budgets) blk_mq_release_budgets(q, list); @@ -1447,14 +1450,16 @@ out: * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls * that could otherwise occur if the queue is idle. We'll do - * similar if we couldn't get budget and SCHED_RESTART is set. + * similar if we couldn't get budget or couldn't lock a zone + * and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); + if (prep == PREP_DISPATCH_NO_BUDGET) + needs_resource = true; if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); - else if (needs_restart && (ret == BLK_STS_RESOURCE || - no_budget_avail)) + else if (needs_restart && needs_resource) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); diff --git a/block/blk-settings.c b/block/blk-settings.c index a7c857ad7d10..b880c70e22e4 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -842,6 +842,24 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging); +static bool disk_has_partitions(struct gendisk *disk) +{ + unsigned long idx; + struct block_device *part; + bool ret = false; + + rcu_read_lock(); + xa_for_each(&disk->part_tbl, idx, part) { + if (bdev_is_partition(part)) { + ret = true; + break; + } + } + rcu_read_unlock(); + + return ret; +} + /** * blk_queue_set_zoned - configure a disk queue zoned model. * @disk: the gendisk of the queue to configure @@ -876,7 +894,7 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) * we do nothing special as far as the block layer is concerned. */ if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || - !xa_empty(&disk->part_tbl)) + disk_has_partitions(disk)) model = BLK_ZONED_NONE; break; case BLK_ZONED_NONE: diff --git a/block/genhd.c b/block/genhd.c index b49858550fa6..ab12ae6e636e 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -588,16 +588,6 @@ void del_gendisk(struct gendisk *disk) * Prevent new I/O from crossing bio_queue_enter(). */ blk_queue_start_drain(q); - blk_mq_freeze_queue_wait(q); - - rq_qos_exit(q); - blk_sync_queue(q); - blk_flush_integrity(); - /* - * Allow using passthrough request again after the queue is torn down. - */ - blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q); - __blk_mq_unfreeze_queue(q, true); if (!(disk->flags & GENHD_FL_HIDDEN)) { sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); @@ -620,6 +610,18 @@ void del_gendisk(struct gendisk *disk) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); + + blk_mq_freeze_queue_wait(q); + + rq_qos_exit(q); + blk_sync_queue(q); + blk_flush_integrity(); + /* + * Allow using passthrough request again after the queue is torn down. + */ + blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q); + __blk_mq_unfreeze_queue(q, true); + } EXPORT_SYMBOL(del_gendisk); diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index cfa29dc89bbf..fabf87058d80 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -281,14 +281,14 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, if (!blk) return -ENOMEM; + rbnode->block = blk; + if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) { present = krealloc(rbnode->cache_present, BITS_TO_LONGS(blklen) * sizeof(*present), GFP_KERNEL); - if (!present) { - kfree(blk); + if (!present) return -ENOMEM; - } memset(present + BITS_TO_LONGS(rbnode->blklen), 0, (BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen)) @@ -305,7 +305,6 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, } /* update the rbnode block, its size and the base register */ - rbnode->block = blk; rbnode->blklen = blklen; rbnode->base_reg = base_reg; rbnode->cache_present = present; diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c index 0506046a5f4b..510a9965633b 100644 --- a/drivers/clk/clk-composite.c +++ b/drivers/clk/clk-composite.c @@ -58,11 +58,8 @@ static int clk_composite_determine_rate(struct clk_hw *hw, long rate; int i; - if (rate_hw && rate_ops && rate_ops->determine_rate) { - __clk_hw_set_clk(rate_hw, hw); - return rate_ops->determine_rate(rate_hw, req); - } else if (rate_hw && rate_ops && rate_ops->round_rate && - mux_hw && mux_ops && mux_ops->set_parent) { + if (rate_hw && rate_ops && rate_ops->round_rate && + mux_hw && mux_ops && mux_ops->set_parent) { req->best_parent_hw = NULL; if (clk_hw_get_flags(hw) & CLK_SET_RATE_NO_REPARENT) { @@ -107,6 +104,9 @@ static int clk_composite_determine_rate(struct clk_hw *hw, req->rate = best_rate; return 0; + } else if (rate_hw && rate_ops && rate_ops->determine_rate) { + __clk_hw_set_clk(rate_hw, hw); + return rate_ops->determine_rate(rate_hw, req); } else if (mux_hw && mux_ops && mux_ops->determine_rate) { __clk_hw_set_clk(mux_hw, hw); return mux_ops->determine_rate(mux_hw, req); diff --git a/drivers/gpio/gpio-mlxbf2.c b/drivers/gpio/gpio-mlxbf2.c index 177d03ef4529..40a052bc6784 100644 --- a/drivers/gpio/gpio-mlxbf2.c +++ b/drivers/gpio/gpio-mlxbf2.c @@ -256,6 +256,11 @@ mlxbf2_gpio_probe(struct platform_device *pdev) NULL, 0); + if (ret) { + dev_err(dev, "bgpio_init failed\n"); + return ret; + } + gc->direction_input = mlxbf2_gpio_direction_input; gc->direction_output = mlxbf2_gpio_direction_output; gc->ngpio = npins; diff --git a/drivers/gpio/gpio-xgs-iproc.c b/drivers/gpio/gpio-xgs-iproc.c index fa9b4d8c3ff5..43ca52fa6f9a 100644 --- a/drivers/gpio/gpio-xgs-iproc.c +++ b/drivers/gpio/gpio-xgs-iproc.c @@ -224,7 +224,7 @@ static int iproc_gpio_probe(struct platform_device *pdev) } chip->gc.label = dev_name(dev); - if (of_property_read_u32(dn, "ngpios", &num_gpios)) + if (!of_property_read_u32(dn, "ngpios", &num_gpios)) chip->gc.ngpio = num_gpios; irq = platform_get_irq(pdev, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index ff80786e3918..01efda4398e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -1257,7 +1257,7 @@ static int nv_common_early_init(void *handle) AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; if (adev->pdev->device == 0x1681) - adev->external_rev_id = adev->rev_id + 0x19; + adev->external_rev_id = 0x20; else adev->external_rev_id = adev->rev_id + 0x01; break; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 87daa78a32b8..8080bba5b7a7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -263,7 +263,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, if (!wr_buf) return -ENOSPC; - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -487,7 +487,7 @@ static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf, if (!wr_buf) return -ENOSPC; - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -639,7 +639,7 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us if (!wr_buf) return -ENOSPC; - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -914,7 +914,7 @@ static ssize_t dp_dsc_passthrough_set(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, ¶m, buf, max_param_num, ¶m_nums)) { @@ -1211,7 +1211,7 @@ static ssize_t trigger_hotplug(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -1396,7 +1396,7 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -1581,7 +1581,7 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -1766,7 +1766,7 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -1944,7 +1944,7 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { @@ -2382,7 +2382,7 @@ static ssize_t dp_max_bpc_write(struct file *f, const char __user *buf, return -ENOSPC; } - if (parse_write_buffer_into_params(wr_buf, size, + if (parse_write_buffer_into_params(wr_buf, wr_buf_size, (long *)param, buf, max_param_num, ¶m_nums)) { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index 4a4894e9d9c9..377c4e53a2b3 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -366,32 +366,32 @@ static struct wm_table lpddr5_wm_table = { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 5.32, - .sr_enter_plus_exit_time_us = 6.38, + .sr_exit_time_us = 11.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.82, - .sr_enter_plus_exit_time_us = 11.196, + .sr_exit_time_us = 11.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.89, - .sr_enter_plus_exit_time_us = 11.24, + .sr_exit_time_us = 11.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.748, - .sr_enter_plus_exit_time_us = 11.102, + .sr_exit_time_us = 11.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, } @@ -518,14 +518,21 @@ static unsigned int find_clk_for_voltage( unsigned int voltage) { int i; + int max_voltage = 0; + int clock = 0; for (i = 0; i < NUM_SOC_VOLTAGE_LEVELS; i++) { - if (clock_table->SocVoltage[i] == voltage) + if (clock_table->SocVoltage[i] == voltage) { return clocks[i]; + } else if (clock_table->SocVoltage[i] >= max_voltage && + clock_table->SocVoltage[i] < voltage) { + max_voltage = clock_table->SocVoltage[i]; + clock = clocks[i]; + } } - ASSERT(0); - return 0; + ASSERT(clock); + return clock; } void dcn31_clk_mgr_helper_populate_bw_params( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 3f2333ec67e2..3afa1159a5f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -76,10 +76,6 @@ void dcn31_init_hw(struct dc *dc) if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks) dc->clk_mgr->funcs->init_clocks(dc->clk_mgr); - // Initialize the dccg - if (res_pool->dccg->funcs->dccg_init) - res_pool->dccg->funcs->dccg_init(res_pool->dccg); - if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) { REG_WRITE(REFCLK_CNTL, 0); @@ -106,6 +102,9 @@ void dcn31_init_hw(struct dc *dc) hws->funcs.bios_golden_init(dc); hws->funcs.disable_vga(dc->hwseq); } + // Initialize the dccg + if (res_pool->dccg->funcs->dccg_init) + res_pool->dccg->funcs->dccg_init(res_pool->dccg); if (dc->debug.enable_mem_low_power.bits.dmcu) { // Force ERAM to shutdown if DMCU is not enabled diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 0006bbac466c..79e92ecca96c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -217,8 +217,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = { .num_states = 5, .sr_exit_time_us = 9.0, .sr_enter_plus_exit_time_us = 11.0, - .sr_exit_z8_time_us = 402.0, - .sr_enter_plus_exit_z8_time_us = 520.0, + .sr_exit_z8_time_us = 442.0, + .sr_enter_plus_exit_z8_time_us = 560.0, .writeback_latency_us = 12.0, .dram_channel_width_bytes = 4, .round_trip_ping_latency_dcfclk_cycles = 106, @@ -928,7 +928,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_dcc = DCC_ENABLE, .vsr_support = true, .performance_trace = false, - .max_downscale_src_width = 3840,/*upto 4K*/ + .max_downscale_src_width = 4096,/*upto true 4K*/ .disable_pplib_wm_range = false, .scl_reset_length10 = true, .sanity_checks = false, @@ -1590,6 +1590,13 @@ static int dcn31_populate_dml_pipes_from_context( pipe = &res_ctx->pipe_ctx[i]; timing = &pipe->stream->timing; + /* + * Immediate flip can be set dynamically after enabling the plane. + * We need to require support for immediate flip or underflow can be + * intermittently experienced depending on peak b/w requirements. + */ + pipes[pipe_cnt].pipe.src.immediate_flip = true; + pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; pipes[pipe_cnt].pipe.src.gpuvm = true; pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index ce55c9caf9a2..d58925cff420 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -5398,9 +5398,9 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->MaximumReadBandwidthWithPrefetch = v->MaximumReadBandwidthWithPrefetch - + dml_max4( - v->VActivePixelBandwidth[i][j][k], - v->VActiveCursorBandwidth[i][j][k] + + dml_max3( + v->VActivePixelBandwidth[i][j][k] + + v->VActiveCursorBandwidth[i][j][k] + v->NoOfDPP[i][j][k] * (v->meta_row_bandwidth[i][j][k] + v->dpte_row_bandwidth[i][j][k]), diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 5adc471bef57..3d2f0817e40a 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -227,7 +227,7 @@ enum { #define FAMILY_YELLOW_CARP 146 #define YELLOW_CARP_A0 0x01 -#define YELLOW_CARP_B0 0x1A +#define YELLOW_CARP_B0 0x20 #define YELLOW_CARP_UNKNOWN 0xFF #ifndef ASICREV_IS_YELLOW_CARP diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index e9bd84ec027d..be61975f1470 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -105,6 +105,7 @@ static enum mod_hdcp_status remove_display_from_topology_v3( dtm_cmd->dtm_status = TA_DTM_STATUS__GENERIC_FAILURE; psp_dtm_invoke(psp, dtm_cmd->cmd_id); + mutex_unlock(&psp->dtm_context.mutex); if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) { status = remove_display_from_topology_v2(hdcp, index); @@ -115,8 +116,6 @@ static enum mod_hdcp_status remove_display_from_topology_v3( HDCP_TOP_REMOVE_DISPLAY_TRACE(hdcp, display->index); } - mutex_unlock(&psp->dtm_context.mutex); - return status; } @@ -205,6 +204,7 @@ static enum mod_hdcp_status add_display_to_topology_v3( dtm_cmd->dtm_in_message.topology_update_v3.link_hdcp_cap = link->hdcp_supported_informational; psp_dtm_invoke(psp, dtm_cmd->cmd_id); + mutex_unlock(&psp->dtm_context.mutex); if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) { status = add_display_to_topology_v2(hdcp, display); @@ -214,8 +214,6 @@ static enum mod_hdcp_status add_display_to_topology_v3( HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, display->index); } - mutex_unlock(&psp->dtm_context.mutex); - return status; } diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index f6bdec7fa925..e1b2ce4921ae 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -134,6 +134,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T103HAF"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* AYA NEO 2021 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYADEVICE"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "AYA NEO 2021"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* GPD MicroPC (generic strings, also match on bios date) */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"), @@ -185,6 +191,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "Default string"), }, .driver_data = (void *)&gpd_win2, + }, { /* GPD Win 3 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1618-03") + }, + .driver_data = (void *)&lcd720x1280_rightside_up, }, { /* I.T.Works TW891 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index abe3d61b6243..5cf152be4487 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1916,6 +1916,9 @@ void intel_dp_sync_state(struct intel_encoder *encoder, { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + if (!crtc_state) + return; + /* * Don't clobber DPCD if it's been already read out during output * setup (eDP) or detect. diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 1257f4f11e66..438bbc7b8147 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -64,7 +64,7 @@ intel_timeline_pin_map(struct intel_timeline *timeline) timeline->hwsp_map = vaddr; timeline->hwsp_seqno = memset(vaddr + ofs, 0, TIMELINE_SEQNO_BYTES); - clflush(vaddr + ofs); + drm_clflush_virt_range(vaddr + ofs, TIMELINE_SEQNO_BYTES); return 0; } @@ -225,7 +225,7 @@ void intel_timeline_reset_seqno(const struct intel_timeline *tl) memset(hwsp_seqno + 1, 0, TIMELINE_SEQNO_BYTES - sizeof(*hwsp_seqno)); WRITE_ONCE(*hwsp_seqno, tl->seqno); - clflush(hwsp_seqno); + drm_clflush_virt_range(hwsp_seqno, TIMELINE_SEQNO_BYTES); } void intel_timeline_enter(struct intel_timeline *tl) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 4037030f0984..9023d4ecf3b3 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -11048,12 +11048,6 @@ enum skl_power_gate { #define DC_STATE_DEBUG_MASK_CORES (1 << 0) #define DC_STATE_DEBUG_MASK_MEMORY_UP (1 << 1) -#define BXT_P_CR_MC_BIOS_REQ_0_0_0 _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x7114) -#define BXT_REQ_DATA_MASK 0x3F -#define BXT_DRAM_CHANNEL_ACTIVE_SHIFT 12 -#define BXT_DRAM_CHANNEL_ACTIVE_MASK (0xF << 12) -#define BXT_MEMORY_FREQ_MULTIPLIER_HZ 133333333 - #define BXT_D_CR_DRP0_DUNIT8 0x1000 #define BXT_D_CR_DRP0_DUNIT9 0x1200 #define BXT_D_CR_DRP0_DUNIT_START 8 @@ -11084,9 +11078,7 @@ enum skl_power_gate { #define BXT_DRAM_TYPE_LPDDR4 (0x2 << 22) #define BXT_DRAM_TYPE_DDR4 (0x4 << 22) -#define SKL_MEMORY_FREQ_MULTIPLIER_HZ 266666666 #define SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5E04) -#define SKL_REQ_DATA_MASK (0xF << 0) #define DG1_GEAR_TYPE REG_BIT(16) #define SKL_MAD_INTER_CHANNEL_0_0_0_MCHBAR_MCMAIN _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5000) diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 806ad688274b..63fec1c3c132 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -794,7 +794,6 @@ DECLARE_EVENT_CLASS(i915_request, TP_STRUCT__entry( __field(u32, dev) __field(u64, ctx) - __field(u32, guc_id) __field(u16, class) __field(u16, instance) __field(u32, seqno) @@ -805,16 +804,14 @@ DECLARE_EVENT_CLASS(i915_request, __entry->dev = rq->engine->i915->drm.primary->index; __entry->class = rq->engine->uabi_class; __entry->instance = rq->engine->uabi_instance; - __entry->guc_id = rq->context->guc_id; __entry->ctx = rq->fence.context; __entry->seqno = rq->fence.seqno; __entry->tail = rq->tail; ), - TP_printk("dev=%u, engine=%u:%u, guc_id=%u, ctx=%llu, seqno=%u, tail=%u", + TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u, tail=%u", __entry->dev, __entry->class, __entry->instance, - __entry->guc_id, __entry->ctx, __entry->seqno, - __entry->tail) + __entry->ctx, __entry->seqno, __entry->tail) ); DEFINE_EVENT(i915_request, i915_request_add, diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c index 91866520c173..7acce64b0941 100644 --- a/drivers/gpu/drm/i915/intel_dram.c +++ b/drivers/gpu/drm/i915/intel_dram.c @@ -244,7 +244,6 @@ static int skl_get_dram_info(struct drm_i915_private *i915) { struct dram_info *dram_info = &i915->dram_info; - u32 mem_freq_khz, val; int ret; dram_info->type = skl_get_dram_type(i915); @@ -255,17 +254,6 @@ skl_get_dram_info(struct drm_i915_private *i915) if (ret) return ret; - val = intel_uncore_read(&i915->uncore, - SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU); - mem_freq_khz = DIV_ROUND_UP((val & SKL_REQ_DATA_MASK) * - SKL_MEMORY_FREQ_MULTIPLIER_HZ, 1000); - - if (dram_info->num_channels * mem_freq_khz == 0) { - drm_info(&i915->drm, - "Couldn't get system memory bandwidth\n"); - return -EINVAL; - } - return 0; } @@ -350,24 +338,10 @@ static void bxt_get_dimm_info(struct dram_dimm_info *dimm, u32 val) static int bxt_get_dram_info(struct drm_i915_private *i915) { struct dram_info *dram_info = &i915->dram_info; - u32 dram_channels; - u32 mem_freq_khz, val; - u8 num_active_channels, valid_ranks = 0; + u32 val; + u8 valid_ranks = 0; int i; - val = intel_uncore_read(&i915->uncore, BXT_P_CR_MC_BIOS_REQ_0_0_0); - mem_freq_khz = DIV_ROUND_UP((val & BXT_REQ_DATA_MASK) * - BXT_MEMORY_FREQ_MULTIPLIER_HZ, 1000); - - dram_channels = val & BXT_DRAM_CHANNEL_ACTIVE_MASK; - num_active_channels = hweight32(dram_channels); - - if (mem_freq_khz * num_active_channels == 0) { - drm_info(&i915->drm, - "Couldn't get system memory bandwidth\n"); - return -EINVAL; - } - /* * Now read each DUNIT8/9/10/11 to check the rank of each dimms. */ diff --git a/drivers/gpu/drm/selftests/test-drm_damage_helper.c b/drivers/gpu/drm/selftests/test-drm_damage_helper.c index 1c19a5d3eefb..8d8d8e214c28 100644 --- a/drivers/gpu/drm/selftests/test-drm_damage_helper.c +++ b/drivers/gpu/drm/selftests/test-drm_damage_helper.c @@ -30,6 +30,7 @@ static void mock_setup(struct drm_plane_state *state) mock_device.driver = &mock_driver; mock_device.mode_config.prop_fb_damage_clips = &mock_prop; mock_plane.dev = &mock_device; + mock_obj_props.count = 0; mock_plane.base.properties = &mock_obj_props; mock_prop.base.id = 1; /* 0 is an invalid id */ mock_prop.dev = &mock_device; diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 1c5ffe2935af..abf2d7a4fdf1 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -190,6 +190,7 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo) struct ttm_transfer_obj *fbo; fbo = container_of(bo, struct ttm_transfer_obj, base); + dma_resv_fini(&fbo->base.base._resv); ttm_bo_put(fbo->bo); kfree(fbo); } diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index a20b8108e160..c00f8e28aab7 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -706,8 +706,9 @@ static void ib_nl_set_path_rec_attrs(struct sk_buff *skb, /* Construct the family header first */ header = skb_put(skb, NLMSG_ALIGN(sizeof(*header))); - memcpy(header->device_name, dev_name(&query->port->agent->device->dev), - LS_DEVICE_NAME_MAX); + strscpy_pad(header->device_name, + dev_name(&query->port->agent->device->dev), + LS_DEVICE_NAME_MAX); header->port_num = query->port->port_num; if ((comp_mask & IB_SA_PATH_REC_REVERSIBLE) && diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 489b436f19bb..3d42bd2b36bd 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -878,6 +878,7 @@ void sc_disable(struct send_context *sc) { u64 reg; struct pio_buf *pbuf; + LIST_HEAD(wake_list); if (!sc) return; @@ -912,19 +913,21 @@ void sc_disable(struct send_context *sc) spin_unlock(&sc->release_lock); write_seqlock(&sc->waitlock); - while (!list_empty(&sc->piowait)) { + if (!list_empty(&sc->piowait)) + list_move(&sc->piowait, &wake_list); + write_sequnlock(&sc->waitlock); + while (!list_empty(&wake_list)) { struct iowait *wait; struct rvt_qp *qp; struct hfi1_qp_priv *priv; - wait = list_first_entry(&sc->piowait, struct iowait, list); + wait = list_first_entry(&wake_list, struct iowait, list); qp = iowait_to_qp(wait); priv = qp->priv; list_del_init(&priv->s_iowait.list); priv->s_iowait.lock = NULL; hfi1_qp_wakeup(qp, RVT_S_WAIT_PIO | HFI1_S_WAIT_PIO_DRAIN); } - write_sequnlock(&sc->waitlock); spin_unlock_irq(&sc->alloc_lock); } diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index 5fb92de1f015..9b544a3b1288 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -1092,12 +1092,12 @@ irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, struct irdma_cq_poll_info *info) if (cq->avoid_mem_cflct) { ext_cqe = (__le64 *)((u8 *)cqe + 32); get_64bit_val(ext_cqe, 24, &qword7); - polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3); + polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7); } else { peek_head = (cq->cq_ring.head + 1) % cq->cq_ring.size; ext_cqe = cq->cq_base[peek_head].buf; get_64bit_val(ext_cqe, 24, &qword7); - polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3); + polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7); if (!peek_head) polarity ^= 1; } diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 7110ebf834f9..102dc9342f2a 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -3399,9 +3399,13 @@ static void irdma_process_cqe(struct ib_wc *entry, } if (cq_poll_info->ud_vlan_valid) { - entry->vlan_id = cq_poll_info->ud_vlan & VLAN_VID_MASK; - entry->wc_flags |= IB_WC_WITH_VLAN; + u16 vlan = cq_poll_info->ud_vlan & VLAN_VID_MASK; + entry->sl = cq_poll_info->ud_vlan >> VLAN_PRIO_SHIFT; + if (vlan) { + entry->vlan_id = vlan; + entry->wc_flags |= IB_WC_WITH_VLAN; + } } else { entry->sl = 0; } diff --git a/drivers/infiniband/hw/irdma/ws.c b/drivers/infiniband/hw/irdma/ws.c index b68c575eb78e..b0d6ee0739f5 100644 --- a/drivers/infiniband/hw/irdma/ws.c +++ b/drivers/infiniband/hw/irdma/ws.c @@ -330,8 +330,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri) tc_node->enable = true; ret = irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_MODIFY_NODE); - if (ret) + if (ret) { + vsi->unregister_qset(vsi, tc_node); goto reg_err; + } } ibdev_dbg(to_ibdev(vsi->dev), "WS: Using node %d which represents VSI %d TC %d\n", @@ -350,6 +352,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri) } goto exit; +reg_err: + irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_DELETE_NODE); + list_del(&tc_node->siblings); + irdma_free_node(vsi, tc_node); leaf_add_err: if (list_empty(&vsi_node->child_list_head)) { if (irdma_ws_cqp_cmd(vsi, vsi_node, IRDMA_OP_WS_DELETE_NODE)) @@ -369,11 +375,6 @@ vsi_add_err: exit: mutex_unlock(&vsi->dev->ws_mutex); return ret; - -reg_err: - mutex_unlock(&vsi->dev->ws_mutex); - irdma_ws_remove(vsi, user_pri); - return ret; } /** diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 3be36ebbf67a..22e2f4d79743 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1339,7 +1339,6 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem, goto err_2; } mr->mmkey.type = MLX5_MKEY_MR; - mr->desc_size = sizeof(struct mlx5_mtt); mr->umem = umem; set_mr_fields(dev, mr, umem->length, access_flags); kvfree(in); @@ -1533,6 +1532,7 @@ static struct ib_mr *create_user_odp_mr(struct ib_pd *pd, u64 start, u64 length, ib_umem_release(&odp->umem); return ERR_CAST(mr); } + xa_init(&mr->implicit_children); odp->private = mr; err = mlx5r_store_odp_mkey(dev, &mr->mmkey); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index b2fca110346c..e5abbcfc1d57 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4458,6 +4458,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr, MLX5_SET(dctc, dctc, mtu, attr->path_mtu); MLX5_SET(dctc, dctc, my_addr_index, attr->ah_attr.grh.sgid_index); MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit); + if (attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE) + MLX5_SET(dctc, dctc, eth_prio, attr->ah_attr.sl & 0x7); err = mlx5_core_create_dct(dev, &qp->dct.mdct, qp->dct.in, MLX5_ST_SZ_BYTES(create_dct_in), out, diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index 3cb4febaad0f..8def88cfa300 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -455,6 +455,7 @@ struct qedr_qp { /* synchronization objects used with iwarp ep */ struct kref refcnt; struct completion iwarp_cm_comp; + struct completion qp_rel_comp; unsigned long iwarp_cm_flags; /* enum iwarp_cm_flags */ }; diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 1715fbe0719d..a51fc6854984 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -83,7 +83,7 @@ static void qedr_iw_free_qp(struct kref *ref) { struct qedr_qp *qp = container_of(ref, struct qedr_qp, refcnt); - kfree(qp); + complete(&qp->qp_rel_comp); } static void diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 3fbf172dbbef..dcb3653db72d 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1357,6 +1357,7 @@ static void qedr_set_common_qp_params(struct qedr_dev *dev, if (rdma_protocol_iwarp(&dev->ibdev, 1)) { kref_init(&qp->refcnt); init_completion(&qp->iwarp_cm_comp); + init_completion(&qp->qp_rel_comp); } qp->pd = pd; @@ -2857,8 +2858,10 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) qedr_free_qp_resources(dev, qp, udata); - if (rdma_protocol_iwarp(&dev->ibdev, 1)) + if (rdma_protocol_iwarp(&dev->ibdev, 1)) { qedr_iw_qp_rem_ref(&qp->ibqp); + wait_for_completion(&qp->qp_rel_comp); + } return 0; } diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c index a67599b5a550..ac11943a5ddb 100644 --- a/drivers/infiniband/hw/qib/qib_user_sdma.c +++ b/drivers/infiniband/hw/qib/qib_user_sdma.c @@ -602,7 +602,7 @@ done: /* * How many pages in this iovec element? */ -static int qib_user_sdma_num_pages(const struct iovec *iov) +static size_t qib_user_sdma_num_pages(const struct iovec *iov) { const unsigned long addr = (unsigned long) iov->iov_base; const unsigned long len = iov->iov_len; @@ -658,7 +658,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev, static int qib_user_sdma_pin_pages(const struct qib_devdata *dd, struct qib_user_sdma_queue *pq, struct qib_user_sdma_pkt *pkt, - unsigned long addr, int tlen, int npages) + unsigned long addr, int tlen, size_t npages) { struct page *pages[8]; int i, j; @@ -722,7 +722,7 @@ static int qib_user_sdma_pin_pkt(const struct qib_devdata *dd, unsigned long idx; for (idx = 0; idx < niov; idx++) { - const int npages = qib_user_sdma_num_pages(iov + idx); + const size_t npages = qib_user_sdma_num_pages(iov + idx); const unsigned long addr = (unsigned long) iov[idx].iov_base; ret = qib_user_sdma_pin_pages(dd, pq, pkt, addr, @@ -824,8 +824,8 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd, unsigned pktnw; unsigned pktnwc; int nfrags = 0; - int npages = 0; - int bytes_togo = 0; + size_t npages = 0; + size_t bytes_togo = 0; int tiddma = 0; int cfur; @@ -885,7 +885,11 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd, npages += qib_user_sdma_num_pages(&iov[idx]); - bytes_togo += slen; + if (check_add_overflow(bytes_togo, slen, &bytes_togo) || + bytes_togo > type_max(typeof(pkt->bytes_togo))) { + ret = -EINVAL; + goto free_pbc; + } pktnwc += slen >> 2; idx++; nfrags++; @@ -904,8 +908,7 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd, } if (frag_size) { - int tidsmsize, n; - size_t pktsize; + size_t tidsmsize, n, pktsize, sz, addrlimit; n = npages*((2*PAGE_SIZE/frag_size)+1); pktsize = struct_size(pkt, addr, n); @@ -923,14 +926,24 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd, else tidsmsize = 0; - pkt = kmalloc(pktsize+tidsmsize, GFP_KERNEL); + if (check_add_overflow(pktsize, tidsmsize, &sz)) { + ret = -EINVAL; + goto free_pbc; + } + pkt = kmalloc(sz, GFP_KERNEL); if (!pkt) { ret = -ENOMEM; goto free_pbc; } pkt->largepkt = 1; pkt->frag_size = frag_size; - pkt->addrlimit = n + ARRAY_SIZE(pkt->addr); + if (check_add_overflow(n, ARRAY_SIZE(pkt->addr), + &addrlimit) || + addrlimit > type_max(typeof(pkt->addrlimit))) { + ret = -EINVAL; + goto free_pbc; + } + pkt->addrlimit = addrlimit; if (tiddma) { char *tidsm = (char *)pkt + pktsize; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 49bdd78ac664..3305f2744bfa 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1223,7 +1223,7 @@ int rvt_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr, spin_lock(&rdi->n_qps_lock); if (rdi->n_qps_allocated == rdi->dparms.props.max_qp) { spin_unlock(&rdi->n_qps_lock); - ret = ENOMEM; + ret = -ENOMEM; goto bail_ip; } diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 95b3511b0560..ccc148cdb5ee 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -506,7 +506,7 @@ config MMC_OMAP_HS config MMC_WBSD tristate "Winbond W83L51xD SD/MMC Card Interface support" - depends on ISA_DMA_API + depends on ISA_DMA_API && !M68K help This selects the Winbond(R) W83L51xD Secure digital and Multimedia card Interface. diff --git a/drivers/mmc/host/cqhci-core.c b/drivers/mmc/host/cqhci-core.c index 38559a956330..31f841231609 100644 --- a/drivers/mmc/host/cqhci-core.c +++ b/drivers/mmc/host/cqhci-core.c @@ -282,6 +282,9 @@ static void __cqhci_enable(struct cqhci_host *cq_host) cqhci_writel(cq_host, cqcfg, CQHCI_CFG); + if (cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT) + cqhci_writel(cq_host, 0, CQHCI_CTL); + mmc->cqe_on = true; if (cq_host->ops->enable) diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c index 0c75810812a0..1f8a3c0ddfe1 100644 --- a/drivers/mmc/host/dw_mmc-exynos.c +++ b/drivers/mmc/host/dw_mmc-exynos.c @@ -464,6 +464,18 @@ static s8 dw_mci_exynos_get_best_clksmpl(u8 candiates) } } + /* + * If there is no cadiates value, then it needs to return -EIO. + * If there are candiates values and don't find bset clk sample value, + * then use a first candiates clock sample value. + */ + for (i = 0; i < iter; i++) { + __c = ror8(candiates, i); + if ((__c & 0x1) == 0x1) { + loc = i; + goto out; + } + } out: return loc; } @@ -494,6 +506,8 @@ static int dw_mci_exynos_execute_tuning(struct dw_mci_slot *slot, u32 opcode) priv->tuned_sample = found; } else { ret = -EIO; + dev_warn(&mmc->class_dev, + "There is no candiates value about clksmpl!\n"); } return ret; diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 4dfc246c5f95..b06b4dcb7c78 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2577,6 +2577,25 @@ static int msdc_drv_probe(struct platform_device *pdev) host->dma_mask = DMA_BIT_MASK(32); mmc_dev(mmc)->dma_mask = &host->dma_mask; + host->timeout_clks = 3 * 1048576; + host->dma.gpd = dma_alloc_coherent(&pdev->dev, + 2 * sizeof(struct mt_gpdma_desc), + &host->dma.gpd_addr, GFP_KERNEL); + host->dma.bd = dma_alloc_coherent(&pdev->dev, + MAX_BD_NUM * sizeof(struct mt_bdma_desc), + &host->dma.bd_addr, GFP_KERNEL); + if (!host->dma.gpd || !host->dma.bd) { + ret = -ENOMEM; + goto release_mem; + } + msdc_init_gpd_bd(host, &host->dma); + INIT_DELAYED_WORK(&host->req_timeout, msdc_request_timeout); + spin_lock_init(&host->lock); + + platform_set_drvdata(pdev, mmc); + msdc_ungate_clock(host); + msdc_init_hw(host); + if (mmc->caps2 & MMC_CAP2_CQE) { host->cq_host = devm_kzalloc(mmc->parent, sizeof(*host->cq_host), @@ -2597,25 +2616,6 @@ static int msdc_drv_probe(struct platform_device *pdev) mmc->max_seg_size = 64 * 1024; } - host->timeout_clks = 3 * 1048576; - host->dma.gpd = dma_alloc_coherent(&pdev->dev, - 2 * sizeof(struct mt_gpdma_desc), - &host->dma.gpd_addr, GFP_KERNEL); - host->dma.bd = dma_alloc_coherent(&pdev->dev, - MAX_BD_NUM * sizeof(struct mt_bdma_desc), - &host->dma.bd_addr, GFP_KERNEL); - if (!host->dma.gpd || !host->dma.bd) { - ret = -ENOMEM; - goto release_mem; - } - msdc_init_gpd_bd(host, &host->dma); - INIT_DELAYED_WORK(&host->req_timeout, msdc_request_timeout); - spin_lock_init(&host->lock); - - platform_set_drvdata(pdev, mmc); - msdc_ungate_clock(host); - msdc_init_hw(host); - ret = devm_request_irq(&pdev->dev, host->irq, msdc_irq, IRQF_TRIGGER_NONE, pdev->name, host); if (ret) diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index f18d169bc8ff..e658f0174242 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1187,6 +1187,7 @@ static void esdhc_reset_tuning(struct sdhci_host *host) struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host); u32 ctrl; + int ret; /* Reset the tuning circuit */ if (esdhc_is_usdhc(imx_data)) { @@ -1199,7 +1200,22 @@ static void esdhc_reset_tuning(struct sdhci_host *host) } else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) { ctrl = readl(host->ioaddr + SDHCI_AUTO_CMD_STATUS); ctrl &= ~ESDHC_MIX_CTRL_SMPCLK_SEL; + ctrl &= ~ESDHC_MIX_CTRL_EXE_TUNE; writel(ctrl, host->ioaddr + SDHCI_AUTO_CMD_STATUS); + /* Make sure ESDHC_MIX_CTRL_EXE_TUNE cleared */ + ret = readl_poll_timeout(host->ioaddr + SDHCI_AUTO_CMD_STATUS, + ctrl, !(ctrl & ESDHC_MIX_CTRL_EXE_TUNE), 1, 50); + if (ret == -ETIMEDOUT) + dev_warn(mmc_dev(host->mmc), + "Warning! clear execute tuning bit failed\n"); + /* + * SDHCI_INT_DATA_AVAIL is W1C bit, set this bit will clear the + * usdhc IP internal logic flag execute_tuning_with_clr_buf, which + * will finally make sure the normal data transfer logic correct. + */ + ctrl = readl(host->ioaddr + SDHCI_INT_STATUS); + ctrl |= SDHCI_INT_DATA_AVAIL; + writel(ctrl, host->ioaddr + SDHCI_INT_STATUS); } } } diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index be19785227fe..d0f2edfe296c 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -616,16 +616,12 @@ static int intel_select_drive_strength(struct mmc_card *card, return intel_host->drv_strength; } -static int bxt_get_cd(struct mmc_host *mmc) +static int sdhci_get_cd_nogpio(struct mmc_host *mmc) { - int gpio_cd = mmc_gpio_get_cd(mmc); struct sdhci_host *host = mmc_priv(mmc); unsigned long flags; int ret = 0; - if (!gpio_cd) - return 0; - spin_lock_irqsave(&host->lock, flags); if (host->flags & SDHCI_DEVICE_DEAD) @@ -638,6 +634,21 @@ out: return ret; } +static int bxt_get_cd(struct mmc_host *mmc) +{ + int gpio_cd = mmc_gpio_get_cd(mmc); + + if (!gpio_cd) + return 0; + + return sdhci_get_cd_nogpio(mmc); +} + +static int mrfld_get_cd(struct mmc_host *mmc) +{ + return sdhci_get_cd_nogpio(mmc); +} + #define SDHCI_INTEL_PWR_TIMEOUT_CNT 20 #define SDHCI_INTEL_PWR_TIMEOUT_UDELAY 100 @@ -1341,6 +1352,14 @@ static int intel_mrfld_mmc_probe_slot(struct sdhci_pci_slot *slot) MMC_CAP_1_8V_DDR; break; case INTEL_MRFLD_SD: + slot->cd_idx = 0; + slot->cd_override_level = true; + /* + * There are two PCB designs of SD card slot with the opposite + * card detection sense. Quirk this out by ignoring GPIO state + * completely in the custom ->get_cd() callback. + */ + slot->host->mmc_host_ops.get_cd = mrfld_get_cd; slot->host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V; break; case INTEL_MRFLD_SDIO: diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 8eefa7d5fe85..2d80a04e11d8 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2042,6 +2042,12 @@ void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode, break; case MMC_VDD_32_33: case MMC_VDD_33_34: + /* + * 3.4 ~ 3.6V are valid only for those platforms where it's + * known that the voltage range is supported by hardware. + */ + case MMC_VDD_34_35: + case MMC_VDD_35_36: pwr = SDHCI_POWER_330; break; default: diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 7dfc26f48c18..e2affa52ef46 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -195,6 +195,10 @@ static void tmio_mmc_reset(struct tmio_mmc_host *host) sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask_all); host->sdcard_irq_mask = host->sdcard_irq_mask_all; + if (host->native_hotplug) + tmio_mmc_enable_mmc_irqs(host, + TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT); + tmio_mmc_set_bus_width(host, host->mmc->ios.bus_width); if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) { @@ -956,8 +960,15 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) case MMC_POWER_OFF: tmio_mmc_power_off(host); /* For R-Car Gen2+, we need to reset SDHI specific SCC */ - if (host->pdata->flags & TMIO_MMC_MIN_RCAR2) + if (host->pdata->flags & TMIO_MMC_MIN_RCAR2) { host->reset(host); + + if (host->native_hotplug) + tmio_mmc_enable_mmc_irqs(host, + TMIO_STAT_CARD_REMOVE | + TMIO_STAT_CARD_INSERT); + } + host->set_clock(host, 0); break; case MMC_POWER_UP: @@ -1185,10 +1196,6 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host) _host->set_clock(_host, 0); tmio_mmc_reset(_host); - if (_host->native_hotplug) - tmio_mmc_enable_mmc_irqs(_host, - TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT); - spin_lock_init(&_host->lock); mutex_init(&_host->ios_lock); diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index 4950d10d3a19..97beece62fec 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -576,7 +576,7 @@ static void check_vub300_port_status(struct vub300_mmc_host *vub300) GET_SYSTEM_PORT_STATUS, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0x0000, 0x0000, &vub300->system_port_status, - sizeof(vub300->system_port_status), HZ); + sizeof(vub300->system_port_status), 1000); if (sizeof(vub300->system_port_status) == retval) new_system_port_status(vub300); } @@ -1241,7 +1241,7 @@ static void __download_offload_pseudocode(struct vub300_mmc_host *vub300, SET_INTERRUPT_PSEUDOCODE, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0x0000, 0x0000, - xfer_buffer, xfer_length, HZ); + xfer_buffer, xfer_length, 1000); kfree(xfer_buffer); if (retval < 0) goto copy_error_message; @@ -1284,7 +1284,7 @@ static void __download_offload_pseudocode(struct vub300_mmc_host *vub300, SET_TRANSFER_PSEUDOCODE, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0x0000, 0x0000, - xfer_buffer, xfer_length, HZ); + xfer_buffer, xfer_length, 1000); kfree(xfer_buffer); if (retval < 0) goto copy_error_message; @@ -1991,7 +1991,7 @@ static void __set_clock_speed(struct vub300_mmc_host *vub300, u8 buf[8], usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0), SET_CLOCK_SPEED, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - 0x00, 0x00, buf, buf_array_size, HZ); + 0x00, 0x00, buf, buf_array_size, 1000); if (retval != 8) { dev_err(&vub300->udev->dev, "SET_CLOCK_SPEED" " %dkHz failed with retval=%d\n", kHzClock, retval); @@ -2013,14 +2013,14 @@ static void vub300_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0), SET_SD_POWER, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - 0x0000, 0x0000, NULL, 0, HZ); + 0x0000, 0x0000, NULL, 0, 1000); /* must wait for the VUB300 u-proc to boot up */ msleep(600); } else if ((ios->power_mode == MMC_POWER_UP) && !vub300->card_powered) { usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0), SET_SD_POWER, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - 0x0001, 0x0000, NULL, 0, HZ); + 0x0001, 0x0000, NULL, 0, 1000); msleep(600); vub300->card_powered = 1; } else if (ios->power_mode == MMC_POWER_ON) { @@ -2275,14 +2275,14 @@ static int vub300_probe(struct usb_interface *interface, GET_HC_INF0, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0x0000, 0x0000, &vub300->hc_info, - sizeof(vub300->hc_info), HZ); + sizeof(vub300->hc_info), 1000); if (retval < 0) goto error5; retval = usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0), SET_ROM_WAIT_STATES, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - firmware_rom_wait_states, 0x0000, NULL, 0, HZ); + firmware_rom_wait_states, 0x0000, NULL, 0, 1000); if (retval < 0) goto error5; dev_info(&vub300->udev->dev, @@ -2297,7 +2297,7 @@ static int vub300_probe(struct usb_interface *interface, GET_SYSTEM_PORT_STATUS, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0x0000, 0x0000, &vub300->system_port_status, - sizeof(vub300->system_port_status), HZ); + sizeof(vub300->system_port_status), 1000); if (retval < 0) { goto error4; } else if (sizeof(vub300->system_port_status) == retval) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 2b66c59f5eaf..e54f96251fea 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -137,7 +137,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "uc", .cmd = HNAE3_DBG_CMD_MAC_UC, .dentry = HNS3_DBG_DENTRY_MAC, - .buf_len = HNS3_DBG_READ_LEN, + .buf_len = HNS3_DBG_READ_LEN_128KB, .init = hns3_dbg_common_file_init, }, { @@ -256,7 +256,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "tqp", .cmd = HNAE3_DBG_CMD_REG_TQP, .dentry = HNS3_DBG_DENTRY_REG, - .buf_len = HNS3_DBG_READ_LEN, + .buf_len = HNS3_DBG_READ_LEN_128KB, .init = hns3_dbg_common_file_init, }, { @@ -298,7 +298,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "fd_tcam", .cmd = HNAE3_DBG_CMD_FD_TCAM, .dentry = HNS3_DBG_DENTRY_FD, - .buf_len = HNS3_DBG_READ_LEN, + .buf_len = HNS3_DBG_READ_LEN_1MB, .init = hns3_dbg_common_file_init, }, { @@ -462,7 +462,7 @@ static const struct hns3_dbg_item rx_queue_info_items[] = { { "TAIL", 2 }, { "HEAD", 2 }, { "FBDNUM", 2 }, - { "PKTNUM", 2 }, + { "PKTNUM", 5 }, { "COPYBREAK", 2 }, { "RING_EN", 2 }, { "RX_RING_EN", 2 }, @@ -565,7 +565,7 @@ static const struct hns3_dbg_item tx_queue_info_items[] = { { "HEAD", 2 }, { "FBDNUM", 2 }, { "OFFSET", 2 }, - { "PKTNUM", 2 }, + { "PKTNUM", 5 }, { "RING_EN", 2 }, { "TX_RING_EN", 2 }, { "BASE_ADDR", 10 }, @@ -790,13 +790,13 @@ static int hns3_dbg_rx_bd_info(struct hns3_dbg_data *d, char *buf, int len) } static const struct hns3_dbg_item tx_bd_info_items[] = { - { "BD_IDX", 5 }, - { "ADDRESS", 2 }, + { "BD_IDX", 2 }, + { "ADDRESS", 13 }, { "VLAN_TAG", 2 }, { "SIZE", 2 }, { "T_CS_VLAN_TSO", 2 }, { "OT_VLAN_TAG", 3 }, - { "TV", 2 }, + { "TV", 5 }, { "OLT_VLAN_LEN", 2 }, { "PAYLEN_OL4CS", 2 }, { "BD_FE_SC_VLD", 2 }, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 32f62cd2dd99..9cda8b3562b8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -391,7 +391,7 @@ static int hclge_dbg_dump_mac(struct hclge_dev *hdev, char *buf, int len) static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len, int *pos) { - struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_dbg_bitmap_cmd req; struct hclge_desc desc; u16 qset_id, qset_num; int ret; @@ -408,12 +408,12 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len, if (ret) return ret; - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + req.bitmap = (u8)le32_to_cpu(desc.data[1]); *pos += scnprintf(buf + *pos, len - *pos, "%04u %#x %#x %#x %#x\n", - qset_id, bitmap->bit0, bitmap->bit1, - bitmap->bit2, bitmap->bit3); + qset_id, req.bit0, req.bit1, req.bit2, + req.bit3); } return 0; @@ -422,7 +422,7 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len, static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len, int *pos) { - struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_dbg_bitmap_cmd req; struct hclge_desc desc; u8 pri_id, pri_num; int ret; @@ -439,12 +439,11 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len, if (ret) return ret; - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + req.bitmap = (u8)le32_to_cpu(desc.data[1]); *pos += scnprintf(buf + *pos, len - *pos, "%03u %#x %#x %#x\n", - pri_id, bitmap->bit0, bitmap->bit1, - bitmap->bit2); + pri_id, req.bit0, req.bit1, req.bit2); } return 0; @@ -453,7 +452,7 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len, static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len, int *pos) { - struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_dbg_bitmap_cmd req; struct hclge_desc desc; u8 pg_id; int ret; @@ -466,12 +465,11 @@ static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len, if (ret) return ret; - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + req.bitmap = (u8)le32_to_cpu(desc.data[1]); *pos += scnprintf(buf + *pos, len - *pos, "%03u %#x %#x %#x\n", - pg_id, bitmap->bit0, bitmap->bit1, - bitmap->bit2); + pg_id, req.bit0, req.bit1, req.bit2); } return 0; @@ -511,7 +509,7 @@ static int hclge_dbg_dump_dcb_queue(struct hclge_dev *hdev, char *buf, int len, static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len, int *pos) { - struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_dbg_bitmap_cmd req; struct hclge_desc desc; u8 port_id = 0; int ret; @@ -521,12 +519,12 @@ static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len, if (ret) return ret; - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + req.bitmap = (u8)le32_to_cpu(desc.data[1]); *pos += scnprintf(buf + *pos, len - *pos, "port_mask: %#x\n", - bitmap->bit0); + req.bit0); *pos += scnprintf(buf + *pos, len - *pos, "port_shaping_pass: %#x\n", - bitmap->bit1); + req.bit1); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index dcd40cc73082..d891390d492f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2847,33 +2847,29 @@ static void hclge_mbx_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && !test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state)) - mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), - hclge_wq, &hdev->service_task, 0); + mod_delayed_work(hclge_wq, &hdev->service_task, 0); } static void hclge_reset_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && + test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state) && !test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state)) - mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), - hclge_wq, &hdev->service_task, 0); + mod_delayed_work(hclge_wq, &hdev->service_task, 0); } static void hclge_errhand_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && !test_and_set_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state)) - mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), - hclge_wq, &hdev->service_task, 0); + mod_delayed_work(hclge_wq, &hdev->service_task, 0); } void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && !test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) - mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), - hclge_wq, &hdev->service_task, - delay_time); + mod_delayed_work(hclge_wq, &hdev->service_task, delay_time); } static int hclge_get_mac_link_status(struct hclge_dev *hdev, int *link_status) @@ -3491,33 +3487,14 @@ static void hclge_get_misc_vector(struct hclge_dev *hdev) hdev->num_msi_used += 1; } -static void hclge_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) -{ - struct hclge_dev *hdev = container_of(notify, struct hclge_dev, - affinity_notify); - - cpumask_copy(&hdev->affinity_mask, mask); -} - -static void hclge_irq_affinity_release(struct kref *ref) -{ -} - static void hclge_misc_affinity_setup(struct hclge_dev *hdev) { irq_set_affinity_hint(hdev->misc_vector.vector_irq, &hdev->affinity_mask); - - hdev->affinity_notify.notify = hclge_irq_affinity_notify; - hdev->affinity_notify.release = hclge_irq_affinity_release; - irq_set_affinity_notifier(hdev->misc_vector.vector_irq, - &hdev->affinity_notify); } static void hclge_misc_affinity_teardown(struct hclge_dev *hdev) { - irq_set_affinity_notifier(hdev->misc_vector.vector_irq, NULL); irq_set_affinity_hint(hdev->misc_vector.vector_irq, NULL); } @@ -13052,7 +13029,7 @@ static int hclge_init(void) { pr_info("%s is initializing\n", HCLGE_NAME); - hclge_wq = alloc_workqueue("%s", 0, 0, HCLGE_NAME); + hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGE_NAME); if (!hclge_wq) { pr_err("%s: failed to create workqueue\n", HCLGE_NAME); return -ENOMEM; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index de6afbcbfbac..69cd8f87b4c8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -944,7 +944,6 @@ struct hclge_dev { /* affinity mask and notify for misc interrupt */ cpumask_t affinity_mask; - struct irq_affinity_notify affinity_notify; struct hclge_ptp *ptp; struct devlink *devlink; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index bef6b98e2f50..cf00ad7bb881 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2232,6 +2232,7 @@ static void hclgevf_get_misc_vector(struct hclgevf_dev *hdev) void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev) { if (!test_bit(HCLGEVF_STATE_REMOVING, &hdev->state) && + test_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state) && !test_and_set_bit(HCLGEVF_STATE_RST_SERVICE_SCHED, &hdev->state)) mod_delayed_work(hclgevf_wq, &hdev->service_task, 0); @@ -3449,6 +3450,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) hclgevf_init_rxd_adv_layout(hdev); + set_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state); + hdev->last_reset_time = jiffies; dev_info(&hdev->pdev->dev, "finished initializing %s driver\n", HCLGEVF_DRIVER_NAME); @@ -3899,7 +3902,7 @@ static int hclgevf_init(void) { pr_info("%s is initializing\n", HCLGEVF_NAME); - hclgevf_wq = alloc_workqueue("%s", 0, 0, HCLGEVF_NAME); + hclgevf_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGEVF_NAME); if (!hclgevf_wq) { pr_err("%s: failed to create workqueue\n", HCLGEVF_NAME); return -ENOMEM; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 883130a9b48f..28288d7e3303 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -146,6 +146,7 @@ enum hclgevf_states { HCLGEVF_STATE_REMOVING, HCLGEVF_STATE_NIC_REGISTERED, HCLGEVF_STATE_ROCE_REGISTERED, + HCLGEVF_STATE_SERVICE_INITED, /* task states */ HCLGEVF_STATE_RST_SERVICE_SCHED, HCLGEVF_STATE_RST_HANDLING, diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 37c18c66b5c7..e375ac849aec 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -100,9 +100,9 @@ static void ice_display_lag_info(struct ice_lag *lag) */ static void ice_lag_info_event(struct ice_lag *lag, void *ptr) { - struct net_device *event_netdev, *netdev_tmp; struct netdev_notifier_bonding_info *info; struct netdev_bonding_info *bonding_info; + struct net_device *event_netdev; const char *lag_netdev_name; event_netdev = netdev_notifier_info_to_dev(ptr); @@ -123,19 +123,6 @@ static void ice_lag_info_event(struct ice_lag *lag, void *ptr) goto lag_out; } - rcu_read_lock(); - for_each_netdev_in_bond_rcu(lag->upper_netdev, netdev_tmp) { - if (!netif_is_ice(netdev_tmp)) - continue; - - if (netdev_tmp && netdev_tmp != lag->netdev && - lag->peer_netdev != netdev_tmp) { - dev_hold(netdev_tmp); - lag->peer_netdev = netdev_tmp; - } - } - rcu_read_unlock(); - if (bonding_info->slave.state) ice_lag_set_backup(lag); else @@ -319,6 +306,9 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, case NETDEV_BONDING_INFO: ice_lag_info_event(lag, ptr); break; + case NETDEV_UNREGISTER: + ice_lag_unlink(lag, ptr); + break; default: break; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 80380aed8882..d1ef3d48a4b0 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1571,6 +1571,9 @@ err_kworker: */ void ice_ptp_release(struct ice_pf *pf) { + if (!test_bit(ICE_FLAG_PTP, pf->flags)) + return; + /* Disable timestamping for both Tx and Rx */ ice_ptp_cfg_timestamp(pf, false); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 9338765da048..49d822a98ada 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -226,18 +226,85 @@ static const struct file_operations rvu_dbg_##name##_fops = { \ static void print_nix_qsize(struct seq_file *filp, struct rvu_pfvf *pfvf); +static void get_lf_str_list(struct rvu_block block, int pcifunc, + char *lfs) +{ + int lf = 0, seq = 0, len = 0, prev_lf = block.lf.max; + + for_each_set_bit(lf, block.lf.bmap, block.lf.max) { + if (lf >= block.lf.max) + break; + + if (block.fn_map[lf] != pcifunc) + continue; + + if (lf == prev_lf + 1) { + prev_lf = lf; + seq = 1; + continue; + } + + if (seq) + len += sprintf(lfs + len, "-%d,%d", prev_lf, lf); + else + len += (len ? sprintf(lfs + len, ",%d", lf) : + sprintf(lfs + len, "%d", lf)); + + prev_lf = lf; + seq = 0; + } + + if (seq) + len += sprintf(lfs + len, "-%d", prev_lf); + + lfs[len] = '\0'; +} + +static int get_max_column_width(struct rvu *rvu) +{ + int index, pf, vf, lf_str_size = 12, buf_size = 256; + struct rvu_block block; + u16 pcifunc; + char *buf; + + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + for (pf = 0; pf < rvu->hw->total_pfs; pf++) { + for (vf = 0; vf <= rvu->hw->total_vfs; vf++) { + pcifunc = pf << 10 | vf; + if (!pcifunc) + continue; + + for (index = 0; index < BLK_COUNT; index++) { + block = rvu->hw->block[index]; + if (!strlen(block.name)) + continue; + + get_lf_str_list(block, pcifunc, buf); + if (lf_str_size <= strlen(buf)) + lf_str_size = strlen(buf) + 1; + } + } + } + + kfree(buf); + return lf_str_size; +} + /* Dumps current provisioning status of all RVU block LFs */ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { - int index, off = 0, flag = 0, go_back = 0, len = 0; + int index, off = 0, flag = 0, len = 0, i = 0; struct rvu *rvu = filp->private_data; - int lf, pf, vf, pcifunc; + int bytes_not_copied = 0; struct rvu_block block; - int bytes_not_copied; - int lf_str_size = 12; + int pf, vf, pcifunc; int buf_size = 2048; + int lf_str_size; char *lfs; char *buf; @@ -249,6 +316,9 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, if (!buf) return -ENOSPC; + /* Get the maximum width of a column */ + lf_str_size = get_max_column_width(rvu); + lfs = kzalloc(lf_str_size, GFP_KERNEL); if (!lfs) { kfree(buf); @@ -262,65 +332,69 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, "%-*s", lf_str_size, rvu->hw->block[index].name); } + off += scnprintf(&buf[off], buf_size - 1 - off, "\n"); + bytes_not_copied = copy_to_user(buffer + (i * off), buf, off); + if (bytes_not_copied) + goto out; + + i++; + *ppos += off; for (pf = 0; pf < rvu->hw->total_pfs; pf++) { for (vf = 0; vf <= rvu->hw->total_vfs; vf++) { + off = 0; + flag = 0; pcifunc = pf << 10 | vf; if (!pcifunc) continue; if (vf) { sprintf(lfs, "PF%d:VF%d", pf, vf - 1); - go_back = scnprintf(&buf[off], - buf_size - 1 - off, - "%-*s", lf_str_size, lfs); + off = scnprintf(&buf[off], + buf_size - 1 - off, + "%-*s", lf_str_size, lfs); } else { sprintf(lfs, "PF%d", pf); - go_back = scnprintf(&buf[off], - buf_size - 1 - off, - "%-*s", lf_str_size, lfs); + off = scnprintf(&buf[off], + buf_size - 1 - off, + "%-*s", lf_str_size, lfs); } - off += go_back; - for (index = 0; index < BLKTYPE_MAX; index++) { + for (index = 0; index < BLK_COUNT; index++) { block = rvu->hw->block[index]; if (!strlen(block.name)) continue; len = 0; lfs[len] = '\0'; - for (lf = 0; lf < block.lf.max; lf++) { - if (block.fn_map[lf] != pcifunc) - continue; + get_lf_str_list(block, pcifunc, lfs); + if (strlen(lfs)) flag = 1; - len += sprintf(&lfs[len], "%d,", lf); - } - if (flag) - len--; - lfs[len] = '\0'; off += scnprintf(&buf[off], buf_size - 1 - off, "%-*s", lf_str_size, lfs); - if (!strlen(lfs)) - go_back += lf_str_size; } - if (!flag) - off -= go_back; - else - flag = 0; - off--; - off += scnprintf(&buf[off], buf_size - 1 - off, "\n"); + if (flag) { + off += scnprintf(&buf[off], + buf_size - 1 - off, "\n"); + bytes_not_copied = copy_to_user(buffer + + (i * off), + buf, off); + if (bytes_not_copied) + goto out; + + i++; + *ppos += off; + } } } - bytes_not_copied = copy_to_user(buffer, buf, off); +out: kfree(lfs); kfree(buf); - if (bytes_not_copied) return -EFAULT; - *ppos = off; - return off; + return *ppos; } RVU_DEBUG_FOPS(rsrc_status, rsrc_attach_status, NULL); @@ -504,7 +578,7 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, if (cmd_buf) ret = -EINVAL; - if (!strncmp(subtoken, "help", 4) || ret < 0) { + if (ret < 0 || !strncmp(subtoken, "help", 4)) { dev_info(rvu->dev, "Use echo <%s-lf > qsize\n", blk_string); goto qsize_write_done; } @@ -1719,6 +1793,10 @@ static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused) u16 pcifunc; char *str; + /* Ingress policers do not exist on all platforms */ + if (!nix_hw->ipolicer) + return 0; + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { if (layer == BAND_PROF_INVAL_LAYER) continue; @@ -1768,6 +1846,10 @@ static int rvu_dbg_nix_band_prof_rsrc_display(struct seq_file *m, void *unused) int layer; char *str; + /* Ingress policers do not exist on all platforms */ + if (!nix_hw->ipolicer) + return 0; + seq_puts(m, "\nBandwidth profile resource free count\n"); seq_puts(m, "=====================================\n"); for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 9ef4e942e31e..6970540dc470 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -2507,6 +2507,9 @@ static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc) return; nix_hw = get_nix_hw(rvu->hw, blkaddr); + if (!nix_hw) + return; + vlan = &nix_hw->txvlan; mutex_lock(&vlan->rsrc_lock); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 13b0259f7ea6..fcace73eae40 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -353,13 +353,10 @@ static int mlxsw_pci_rdq_skb_alloc(struct mlxsw_pci *mlxsw_pci, struct sk_buff *skb; int err; - elem_info->u.rdq.skb = NULL; skb = netdev_alloc_skb_ip_align(NULL, buf_len); if (!skb) return -ENOMEM; - /* Assume that wqe was previously zeroed. */ - err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data, buf_len, DMA_FROM_DEVICE); if (err) @@ -597,21 +594,26 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, struct pci_dev *pdev = mlxsw_pci->pdev; struct mlxsw_pci_queue_elem_info *elem_info; struct mlxsw_rx_info rx_info = {}; - char *wqe; + char wqe[MLXSW_PCI_WQE_SIZE]; struct sk_buff *skb; u16 byte_count; int err; elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); - skb = elem_info->u.sdq.skb; - if (!skb) - return; - wqe = elem_info->elem; - mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE); + skb = elem_info->u.rdq.skb; + memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE); if (q->consumer_counter++ != consumer_counter_limit) dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n"); + err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info); + if (err) { + dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n"); + goto out; + } + + mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE); + if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) { rx_info.is_lag = true; rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe); @@ -647,10 +649,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, skb_put(skb, byte_count); mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info); - memset(wqe, 0, q->elem_size); - err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info); - if (err) - dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n"); +out: /* Everything is set up, ring doorbell to pass elem to HW */ q->producer_counter++; mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 9e8561cdc32a..4d5a5d6595b3 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1743,6 +1743,16 @@ static int lan743x_tx_ring_init(struct lan743x_tx *tx) ret = -EINVAL; goto cleanup; } + if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev, + DMA_BIT_MASK(64))) { + if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev, + DMA_BIT_MASK(32))) { + dev_warn(&tx->adapter->pdev->dev, + "lan743x_: No suitable DMA available\n"); + ret = -ENOMEM; + goto cleanup; + } + } ring_allocation_size = ALIGN(tx->ring_size * sizeof(struct lan743x_tx_descriptor), PAGE_SIZE); @@ -1934,7 +1944,8 @@ static void lan743x_rx_update_tail(struct lan743x_rx *rx, int index) index); } -static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index) +static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index, + gfp_t gfp) { struct net_device *netdev = rx->adapter->netdev; struct device *dev = &rx->adapter->pdev->dev; @@ -1948,7 +1959,7 @@ static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index) descriptor = &rx->ring_cpu_ptr[index]; buffer_info = &rx->buffer_info[index]; - skb = __netdev_alloc_skb(netdev, buffer_length, GFP_ATOMIC | GFP_DMA); + skb = __netdev_alloc_skb(netdev, buffer_length, gfp); if (!skb) return -ENOMEM; dma_ptr = dma_map_single(dev, skb->data, buffer_length, DMA_FROM_DEVICE); @@ -2110,7 +2121,8 @@ static int lan743x_rx_process_buffer(struct lan743x_rx *rx) /* save existing skb, allocate new skb and map to dma */ skb = buffer_info->skb; - if (lan743x_rx_init_ring_element(rx, rx->last_head)) { + if (lan743x_rx_init_ring_element(rx, rx->last_head, + GFP_ATOMIC | GFP_DMA)) { /* failed to allocate next skb. * Memory is very low. * Drop this packet and reuse buffer. @@ -2276,6 +2288,16 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx) ret = -EINVAL; goto cleanup; } + if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev, + DMA_BIT_MASK(64))) { + if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev, + DMA_BIT_MASK(32))) { + dev_warn(&rx->adapter->pdev->dev, + "lan743x_: No suitable DMA available\n"); + ret = -ENOMEM; + goto cleanup; + } + } ring_allocation_size = ALIGN(rx->ring_size * sizeof(struct lan743x_rx_descriptor), PAGE_SIZE); @@ -2315,13 +2337,16 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx) rx->last_head = 0; for (index = 0; index < rx->ring_size; index++) { - ret = lan743x_rx_init_ring_element(rx, index); + ret = lan743x_rx_init_ring_element(rx, index, GFP_KERNEL); if (ret) goto cleanup; } return 0; cleanup: + netif_warn(rx->adapter, ifup, rx->adapter->netdev, + "Error allocating memory for LAN743x\n"); + lan743x_rx_ring_cleanup(rx); return ret; } @@ -3019,6 +3044,8 @@ static int lan743x_pm_resume(struct device *dev) if (ret) { netif_err(adapter, probe, adapter->netdev, "lan743x_hardware_init returned %d\n", ret); + lan743x_pci_cleanup(adapter); + return ret; } /* open netdev when netdev is at running state while resume. diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 11c83a99b014..f469950c7265 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -182,15 +182,21 @@ static int nfp_bpf_check_mtu(struct nfp_app *app, struct net_device *netdev, int new_mtu) { struct nfp_net *nn = netdev_priv(netdev); - unsigned int max_mtu; + struct nfp_bpf_vnic *bv; + struct bpf_prog *prog; if (~nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) return 0; - max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; - if (new_mtu > max_mtu) { - nn_info(nn, "BPF offload active, MTU over %u not supported\n", - max_mtu); + if (nn->xdp_hw.prog) { + prog = nn->xdp_hw.prog; + } else { + bv = nn->app_priv; + prog = bv->tc_prog; + } + + if (nfp_bpf_offload_check_mtu(nn, prog, new_mtu)) { + nn_info(nn, "BPF offload active, potential packet access beyond hardware packet boundary"); return -EBUSY; } return 0; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index d0e17eebddd9..16841bb750b7 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -560,6 +560,8 @@ bool nfp_is_subprog_start(struct nfp_insn_meta *meta); void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog); int nfp_bpf_jit(struct nfp_prog *prog); bool nfp_bpf_supported_opcode(u8 code); +bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog, + unsigned int mtu); int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 53851853562c..9d97cd281f18 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -481,19 +481,28 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data, return 0; } +bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog, + unsigned int mtu) +{ + unsigned int fw_mtu, pkt_off; + + fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; + pkt_off = min(prog->aux->max_pkt_offset, mtu); + + return fw_mtu < pkt_off; +} + static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv; - unsigned int fw_mtu, pkt_off, max_stack, max_prog_len; + unsigned int max_stack, max_prog_len; dma_addr_t dma_addr; void *img; int err; - fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; - pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu); - if (fw_mtu < pkt_off) { + if (nfp_bpf_offload_check_mtu(nn, prog, nn->dp.netdev->mtu)) { NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index d29fe562b3de..c910fa2f40a4 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1015,9 +1015,6 @@ static int lpc_eth_close(struct net_device *ndev) napi_disable(&pldat->napi); netif_stop_queue(ndev); - if (ndev->phydev) - phy_stop(ndev->phydev); - spin_lock_irqsave(&pldat->lock, flags); __lpc_eth_reset(pldat); netif_carrier_off(ndev); @@ -1025,6 +1022,8 @@ static int lpc_eth_close(struct net_device *ndev) writel(0, LPC_ENET_MAC2(pldat->net_base)); spin_unlock_irqrestore(&pldat->lock, flags); + if (ndev->phydev) + phy_stop(ndev->phydev); clk_disable_unprepare(pldat->clk); return 0; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 46a6ff9a782d..2918947dd57c 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -157,6 +157,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = { { PCI_VDEVICE(REALTEK, 0x8129) }, { PCI_VDEVICE(REALTEK, 0x8136), RTL_CFG_NO_GBIT }, { PCI_VDEVICE(REALTEK, 0x8161) }, + { PCI_VDEVICE(REALTEK, 0x8162) }, { PCI_VDEVICE(REALTEK, 0x8167) }, { PCI_VDEVICE(REALTEK, 0x8168) }, { PCI_VDEVICE(NCUBE, 0x8168) }, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index f124a8a58bd4..a3bfb156c83d 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -243,62 +243,10 @@ static void phy_sanitize_settings(struct phy_device *phydev) } } -int phy_ethtool_ksettings_set(struct phy_device *phydev, - const struct ethtool_link_ksettings *cmd) -{ - __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); - u8 autoneg = cmd->base.autoneg; - u8 duplex = cmd->base.duplex; - u32 speed = cmd->base.speed; - - if (cmd->base.phy_address != phydev->mdio.addr) - return -EINVAL; - - linkmode_copy(advertising, cmd->link_modes.advertising); - - /* We make sure that we don't pass unsupported values in to the PHY */ - linkmode_and(advertising, advertising, phydev->supported); - - /* Verify the settings we care about. */ - if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE) - return -EINVAL; - - if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising)) - return -EINVAL; - - if (autoneg == AUTONEG_DISABLE && - ((speed != SPEED_1000 && - speed != SPEED_100 && - speed != SPEED_10) || - (duplex != DUPLEX_HALF && - duplex != DUPLEX_FULL))) - return -EINVAL; - - phydev->autoneg = autoneg; - - if (autoneg == AUTONEG_DISABLE) { - phydev->speed = speed; - phydev->duplex = duplex; - } - - linkmode_copy(phydev->advertising, advertising); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - phydev->advertising, autoneg == AUTONEG_ENABLE); - - phydev->master_slave_set = cmd->base.master_slave_cfg; - phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl; - - /* Restart the PHY */ - phy_start_aneg(phydev); - - return 0; -} -EXPORT_SYMBOL(phy_ethtool_ksettings_set); - void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd) { + mutex_lock(&phydev->lock); linkmode_copy(cmd->link_modes.supported, phydev->supported); linkmode_copy(cmd->link_modes.advertising, phydev->advertising); linkmode_copy(cmd->link_modes.lp_advertising, phydev->lp_advertising); @@ -317,6 +265,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, cmd->base.autoneg = phydev->autoneg; cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl; cmd->base.eth_tp_mdix = phydev->mdix; + mutex_unlock(&phydev->lock); } EXPORT_SYMBOL(phy_ethtool_ksettings_get); @@ -751,7 +700,7 @@ static int phy_check_link_status(struct phy_device *phydev) } /** - * phy_start_aneg - start auto-negotiation for this PHY device + * _phy_start_aneg - start auto-negotiation for this PHY device * @phydev: the phy_device struct * * Description: Sanitizes the settings (if we're not autonegotiating @@ -759,25 +708,43 @@ static int phy_check_link_status(struct phy_device *phydev) * If the PHYCONTROL Layer is operating, we change the state to * reflect the beginning of Auto-negotiation or forcing. */ -int phy_start_aneg(struct phy_device *phydev) +static int _phy_start_aneg(struct phy_device *phydev) { int err; + lockdep_assert_held(&phydev->lock); + if (!phydev->drv) return -EIO; - mutex_lock(&phydev->lock); - if (AUTONEG_DISABLE == phydev->autoneg) phy_sanitize_settings(phydev); err = phy_config_aneg(phydev); if (err < 0) - goto out_unlock; + return err; if (phy_is_started(phydev)) err = phy_check_link_status(phydev); -out_unlock: + + return err; +} + +/** + * phy_start_aneg - start auto-negotiation for this PHY device + * @phydev: the phy_device struct + * + * Description: Sanitizes the settings (if we're not autonegotiating + * them), and then calls the driver's config_aneg function. + * If the PHYCONTROL Layer is operating, we change the state to + * reflect the beginning of Auto-negotiation or forcing. + */ +int phy_start_aneg(struct phy_device *phydev) +{ + int err; + + mutex_lock(&phydev->lock); + err = _phy_start_aneg(phydev); mutex_unlock(&phydev->lock); return err; @@ -800,6 +767,61 @@ static int phy_poll_aneg_done(struct phy_device *phydev) return ret < 0 ? ret : 0; } +int phy_ethtool_ksettings_set(struct phy_device *phydev, + const struct ethtool_link_ksettings *cmd) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + u8 autoneg = cmd->base.autoneg; + u8 duplex = cmd->base.duplex; + u32 speed = cmd->base.speed; + + if (cmd->base.phy_address != phydev->mdio.addr) + return -EINVAL; + + linkmode_copy(advertising, cmd->link_modes.advertising); + + /* We make sure that we don't pass unsupported values in to the PHY */ + linkmode_and(advertising, advertising, phydev->supported); + + /* Verify the settings we care about. */ + if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE) + return -EINVAL; + + if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising)) + return -EINVAL; + + if (autoneg == AUTONEG_DISABLE && + ((speed != SPEED_1000 && + speed != SPEED_100 && + speed != SPEED_10) || + (duplex != DUPLEX_HALF && + duplex != DUPLEX_FULL))) + return -EINVAL; + + mutex_lock(&phydev->lock); + phydev->autoneg = autoneg; + + if (autoneg == AUTONEG_DISABLE) { + phydev->speed = speed; + phydev->duplex = duplex; + } + + linkmode_copy(phydev->advertising, advertising); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->advertising, autoneg == AUTONEG_ENABLE); + + phydev->master_slave_set = cmd->base.master_slave_cfg; + phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl; + + /* Restart the PHY */ + _phy_start_aneg(phydev); + + mutex_unlock(&phydev->lock); + return 0; +} +EXPORT_SYMBOL(phy_ethtool_ksettings_set); + /** * phy_speed_down - set speed to lowest speed supported by both link partners * @phydev: the phy_device struct diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 793f8fbe0069..63cd72c5f580 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -4122,6 +4122,12 @@ static int lan78xx_probe(struct usb_interface *intf, dev->maxpacket = usb_maxpacket(dev->udev, dev->pipe_out, 1); + /* Reject broken descriptors. */ + if (dev->maxpacket == 0) { + ret = -ENODEV; + goto out4; + } + /* driver requires remote-wakeup capability during autosuspend. */ intf->needs_remote_wakeup = 1; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 80432ee0ce69..a33d7fb82a00 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1790,6 +1790,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->maxpacket = usb_maxpacket (dev->udev, dev->out, 1); if (dev->maxpacket == 0) { /* that is a broken device */ + status = -ENODEV; goto out4; } diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 142f70670f5c..8799854bacb2 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -3833,7 +3833,6 @@ vmxnet3_suspend(struct device *device) vmxnet3_free_intr_resources(adapter); netif_device_detach(netdev); - netif_tx_stop_all_queues(netdev); /* Create wake-up filters. */ pmConf = adapter->pm_conf; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e31b98403f31..fc41ba95f81d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1730,6 +1730,10 @@ static int netfront_resume(struct xenbus_device *dev) dev_dbg(&dev->dev, "%s\n", dev->nodename); + netif_tx_lock_bh(info->netdev); + netif_device_detach(info->netdev); + netif_tx_unlock_bh(info->netdev); + xennet_disconnect_backend(info); return 0; } @@ -2349,6 +2353,10 @@ static int xennet_connect(struct net_device *dev) * domain a kick because we've probably just requeued some * packets. */ + netif_tx_lock_bh(np->netdev); + netif_device_attach(np->netdev); + netif_tx_unlock_bh(np->netdev); + netif_carrier_on(np->netdev); for (j = 0; j < num_queues; ++j) { queue = &np->queues[j]; diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 517376c43b86..16ceb763594f 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -1006,11 +1006,11 @@ static u64 port100_get_command_type_mask(struct port100 *dev) skb = port100_alloc_skb(dev, 0); if (!skb) - return -ENOMEM; + return 0; resp = port100_send_cmd_sync(dev, PORT100_CMD_GET_COMMAND_TYPE, skb); if (IS_ERR(resp)) - return PTR_ERR(resp); + return 0; if (resp->len < 8) mask = 0; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index ef4950f80832..054154c22899 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -333,26 +333,6 @@ static const struct attribute_group *pmem_attribute_groups[] = { NULL, }; -static void pmem_pagemap_cleanup(struct dev_pagemap *pgmap) -{ - struct pmem_device *pmem = pgmap->owner; - - blk_cleanup_disk(pmem->disk); -} - -static void pmem_release_queue(void *pgmap) -{ - pmem_pagemap_cleanup(pgmap); -} - -static void pmem_pagemap_kill(struct dev_pagemap *pgmap) -{ - struct request_queue *q = - container_of(pgmap->ref, struct request_queue, q_usage_counter); - - blk_freeze_queue_start(q); -} - static void pmem_release_disk(void *__pmem) { struct pmem_device *pmem = __pmem; @@ -360,12 +340,9 @@ static void pmem_release_disk(void *__pmem) kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); del_gendisk(pmem->disk); -} -static const struct dev_pagemap_ops fsdax_pagemap_ops = { - .kill = pmem_pagemap_kill, - .cleanup = pmem_pagemap_cleanup, -}; + blk_cleanup_disk(pmem->disk); +} static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) @@ -427,10 +404,8 @@ static int pmem_attach_disk(struct device *dev, pmem->disk = disk; pmem->pgmap.owner = pmem; pmem->pfn_flags = PFN_DEV; - pmem->pgmap.ref = &q->q_usage_counter; if (is_nd_pfn(dev)) { pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; - pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); pfn_sb = nd_pfn->pfn_sb; pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); @@ -444,16 +419,12 @@ static int pmem_attach_disk(struct device *dev, pmem->pgmap.range.end = res->end; pmem->pgmap.nr_range = 1; pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; - pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); pmem->pfn_flags |= PFN_MAP; bb_range = pmem->pgmap.range; } else { addr = devm_memremap(dev, pmem->phys_addr, pmem->size, ARCH_MEMREMAP_PMEM); - if (devm_add_action_or_reset(dev, pmem_release_queue, - &pmem->pgmap)) - return -ENOMEM; bb_range.start = res->start; bb_range.end = res->end; } diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 3c1c29dd3020..4ae562d30d2b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -926,12 +926,14 @@ static void nvme_tcp_fail_request(struct nvme_tcp_request *req) static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) { struct nvme_tcp_queue *queue = req->queue; + int req_data_len = req->data_len; while (true) { struct page *page = nvme_tcp_req_cur_page(req); size_t offset = nvme_tcp_req_cur_offset(req); size_t len = nvme_tcp_req_cur_length(req); bool last = nvme_tcp_pdu_last_send(req, len); + int req_data_sent = req->data_sent; int ret, flags = MSG_DONTWAIT; if (last && !queue->data_digest && !nvme_tcp_queue_more(queue)) @@ -958,7 +960,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) * in the request where we don't want to modify it as we may * compete with the RX path completing the request. */ - if (req->data_sent + ret < req->data_len) + if (req_data_sent + ret < req_data_len) nvme_tcp_advance_req(req, ret); /* fully successful last send in current PDU */ @@ -1048,10 +1050,11 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req) static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req) { struct nvme_tcp_queue *queue = req->queue; + size_t offset = req->offset; int ret; struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; struct kvec iov = { - .iov_base = &req->ddgst + req->offset, + .iov_base = (u8 *)&req->ddgst + req->offset, .iov_len = NVME_TCP_DIGEST_LENGTH - req->offset }; @@ -1064,7 +1067,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req) if (unlikely(ret <= 0)) return ret; - if (req->offset + ret == NVME_TCP_DIGEST_LENGTH) { + if (offset + ret == NVME_TCP_DIGEST_LENGTH) { nvme_tcp_done_send_req(queue); return 1; } diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 07ee347ea3f3..46c3b3be7e03 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -702,7 +702,7 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch) struct nvmet_tcp_queue *queue = cmd->queue; struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; struct kvec iov = { - .iov_base = &cmd->exp_ddgst + cmd->offset, + .iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset, .iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset }; int ret; @@ -1096,7 +1096,7 @@ recv: } if (queue->hdr_digest && - nvmet_tcp_verify_hdgst(queue, &queue->pdu, queue->offset)) { + nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) { nvmet_tcp_fatal_error(queue); /* fatal */ return -EPROTO; } @@ -1428,6 +1428,7 @@ static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue) static void nvmet_tcp_release_queue_work(struct work_struct *w) { + struct page *page; struct nvmet_tcp_queue *queue = container_of(w, struct nvmet_tcp_queue, release_work); @@ -1447,6 +1448,8 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w) nvmet_tcp_free_crypto(queue); ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx); + page = virt_to_head_page(queue->pf_cache.va); + __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); kfree(queue); } diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index be799a5abf8a..b0056ae5d463 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -147,8 +147,8 @@ config RESET_OXNAS bool config RESET_PISTACHIO - bool "Pistachio Reset Driver" if COMPILE_TEST - default MACH_PISTACHIO + bool "Pistachio Reset Driver" + depends on MIPS || COMPILE_TEST help This enables the reset driver for ImgTec Pistachio SoCs. diff --git a/drivers/reset/reset-brcmstb-rescal.c b/drivers/reset/reset-brcmstb-rescal.c index b6f074d6a65f..433fa0c40e47 100644 --- a/drivers/reset/reset-brcmstb-rescal.c +++ b/drivers/reset/reset-brcmstb-rescal.c @@ -38,7 +38,7 @@ static int brcm_rescal_reset_set(struct reset_controller_dev *rcdev, } ret = readl_poll_timeout(base + BRCM_RESCAL_STATUS, reg, - !(reg & BRCM_RESCAL_STATUS_BIT), 100, 1000); + (reg & BRCM_RESCAL_STATUS_BIT), 100, 1000); if (ret) { dev_err(data->dev, "time out on SATA/PCIe rescal\n"); return ret; diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c index 2a72f861f798..8c6492e5693c 100644 --- a/drivers/reset/reset-socfpga.c +++ b/drivers/reset/reset-socfpga.c @@ -92,3 +92,29 @@ void __init socfpga_reset_init(void) for_each_matching_node(np, socfpga_early_reset_dt_ids) a10_reset_init(np); } + +/* + * The early driver is problematic, because it doesn't register + * itself as a driver. This causes certain device links to prevent + * consumer devices from probing. The hacky solution is to register + * an empty driver, whose only job is to attach itself to the reset + * manager and call probe. + */ +static const struct of_device_id socfpga_reset_dt_ids[] = { + { .compatible = "altr,rst-mgr", }, + { /* sentinel */ }, +}; + +static int reset_simple_probe(struct platform_device *pdev) +{ + return 0; +} + +static struct platform_driver reset_socfpga_driver = { + .probe = reset_simple_probe, + .driver = { + .name = "socfpga-reset", + .of_match_table = socfpga_reset_dt_ids, + }, +}; +builtin_platform_driver(reset_socfpga_driver); diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c index 24d3395964cc..4c5bba52b105 100644 --- a/drivers/reset/tegra/reset-bpmp.c +++ b/drivers/reset/tegra/reset-bpmp.c @@ -20,6 +20,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc); struct mrq_reset_request request; struct tegra_bpmp_message msg; + int err; memset(&request, 0, sizeof(request)); request.cmd = command; @@ -30,7 +31,13 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, msg.tx.data = &request; msg.tx.size = sizeof(request); - return tegra_bpmp_transfer(bpmp, &msg); + err = tegra_bpmp_transfer(bpmp, &msg); + if (err) + return err; + if (msg.rx.ret) + return -EINVAL; + + return 0; } static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc, diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 1f1586ad48fe..01f79991bf4a 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -1696,6 +1696,7 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt, spin_lock_irqsave(&evt->queue->l_lock, flags); list_add_tail(&evt->queue_list, &evt->queue->sent); + atomic_set(&evt->active, 1); mb(); @@ -1710,6 +1711,7 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt, be64_to_cpu(crq_as_u64[1])); if (rc) { + atomic_set(&evt->active, 0); list_del(&evt->queue_list); spin_unlock_irqrestore(&evt->queue->l_lock, flags); del_timer(&evt->timer); @@ -1737,7 +1739,6 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt, evt->done(evt); } else { - atomic_set(&evt->active, 1); spin_unlock_irqrestore(&evt->queue->l_lock, flags); ibmvfc_trc_start(evt); } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index d383d4a03436..ad1b6c2b37a7 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -5065,9 +5065,12 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd, if (scmd->prot_flags & SCSI_PROT_GUARD_CHECK) eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD; - if (scmd->prot_flags & SCSI_PROT_REF_CHECK) { - eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_INC_PRI_REFTAG | - MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG; + if (scmd->prot_flags & SCSI_PROT_REF_CHECK) + eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG; + + if (scmd->prot_flags & SCSI_PROT_REF_INCREMENT) { + eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_INC_PRI_REFTAG; + mpi_request->CDB.EEDP32.PrimaryReferenceTag = cpu_to_be32(scsi_prot_ref_tag(scmd)); } diff --git a/drivers/scsi/ufs/ufs-exynos.c b/drivers/scsi/ufs/ufs-exynos.c index a14dd8ce56d4..bb2dd79a1bcd 100644 --- a/drivers/scsi/ufs/ufs-exynos.c +++ b/drivers/scsi/ufs/ufs-exynos.c @@ -642,9 +642,9 @@ static int exynos_ufs_pre_pwr_mode(struct ufs_hba *hba, } /* setting for three timeout values for traffic class #0 */ - ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA0), 8064); - ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA1), 28224); - ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA2), 20160); + ufshcd_dme_set(hba, UIC_ARG_MIB(DL_FC0PROTTIMEOUTVAL), 8064); + ufshcd_dme_set(hba, UIC_ARG_MIB(DL_TC0REPLAYTIMEOUTVAL), 28224); + ufshcd_dme_set(hba, UIC_ARG_MIB(DL_AFC0REQTIMEOUTVAL), 20160); return 0; out: diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 95be7ecdfe10..41f2ff35f82b 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -2737,12 +2737,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) lrbp->req_abort_skip = false; - err = ufshpb_prep(hba, lrbp); - if (err == -EAGAIN) { - lrbp->cmd = NULL; - ufshcd_release(hba); - goto out; - } + ufshpb_prep(hba, lrbp); ufshcd_comp_scsi_upiu(hba, lrbp); diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 589af5f6b940..026a133149dc 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -84,16 +84,6 @@ static bool ufshpb_is_supported_chunk(struct ufshpb_lu *hpb, int transfer_len) return transfer_len <= hpb->pre_req_max_tr_len; } -/* - * In this driver, WRITE_BUFFER CMD support 36KB (len=9) ~ 1MB (len=256) as - * default. It is possible to change range of transfer_len through sysfs. - */ -static inline bool ufshpb_is_required_wb(struct ufshpb_lu *hpb, int len) -{ - return len > hpb->pre_req_min_tr_len && - len <= hpb->pre_req_max_tr_len; -} - static bool ufshpb_is_general_lun(int lun) { return lun < UFS_UPIU_MAX_UNIT_NUM_ID; @@ -334,7 +324,7 @@ ufshpb_get_pos_from_lpn(struct ufshpb_lu *hpb, unsigned long lpn, int *rgn_idx, static void ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, - __be64 ppn, u8 transfer_len, int read_id) + __be64 ppn, u8 transfer_len) { unsigned char *cdb = lrbp->cmd->cmnd; __be64 ppn_tmp = ppn; @@ -346,256 +336,11 @@ ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, /* ppn value is stored as big-endian in the host memory */ memcpy(&cdb[6], &ppn_tmp, sizeof(__be64)); cdb[14] = transfer_len; - cdb[15] = read_id; + cdb[15] = 0; lrbp->cmd->cmd_len = UFS_CDB_SIZE; } -static inline void ufshpb_set_write_buf_cmd(unsigned char *cdb, - unsigned long lpn, unsigned int len, - int read_id) -{ - cdb[0] = UFSHPB_WRITE_BUFFER; - cdb[1] = UFSHPB_WRITE_BUFFER_PREFETCH_ID; - - put_unaligned_be32(lpn, &cdb[2]); - cdb[6] = read_id; - put_unaligned_be16(len * HPB_ENTRY_SIZE, &cdb[7]); - - cdb[9] = 0x00; /* Control = 0x00 */ -} - -static struct ufshpb_req *ufshpb_get_pre_req(struct ufshpb_lu *hpb) -{ - struct ufshpb_req *pre_req; - - if (hpb->num_inflight_pre_req >= hpb->throttle_pre_req) { - dev_info(&hpb->sdev_ufs_lu->sdev_dev, - "pre_req throttle. inflight %d throttle %d", - hpb->num_inflight_pre_req, hpb->throttle_pre_req); - return NULL; - } - - pre_req = list_first_entry_or_null(&hpb->lh_pre_req_free, - struct ufshpb_req, list_req); - if (!pre_req) { - dev_info(&hpb->sdev_ufs_lu->sdev_dev, "There is no pre_req"); - return NULL; - } - - list_del_init(&pre_req->list_req); - hpb->num_inflight_pre_req++; - - return pre_req; -} - -static inline void ufshpb_put_pre_req(struct ufshpb_lu *hpb, - struct ufshpb_req *pre_req) -{ - pre_req->req = NULL; - bio_reset(pre_req->bio); - list_add_tail(&pre_req->list_req, &hpb->lh_pre_req_free); - hpb->num_inflight_pre_req--; -} - -static void ufshpb_pre_req_compl_fn(struct request *req, blk_status_t error) -{ - struct ufshpb_req *pre_req = (struct ufshpb_req *)req->end_io_data; - struct ufshpb_lu *hpb = pre_req->hpb; - unsigned long flags; - - if (error) { - struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req); - struct scsi_sense_hdr sshdr; - - dev_err(&hpb->sdev_ufs_lu->sdev_dev, "block status %d", error); - scsi_command_normalize_sense(cmd, &sshdr); - dev_err(&hpb->sdev_ufs_lu->sdev_dev, - "code %x sense_key %x asc %x ascq %x", - sshdr.response_code, - sshdr.sense_key, sshdr.asc, sshdr.ascq); - dev_err(&hpb->sdev_ufs_lu->sdev_dev, - "byte4 %x byte5 %x byte6 %x additional_len %x", - sshdr.byte4, sshdr.byte5, - sshdr.byte6, sshdr.additional_length); - } - - blk_mq_free_request(req); - spin_lock_irqsave(&hpb->rgn_state_lock, flags); - ufshpb_put_pre_req(pre_req->hpb, pre_req); - spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); -} - -static int ufshpb_prep_entry(struct ufshpb_req *pre_req, struct page *page) -{ - struct ufshpb_lu *hpb = pre_req->hpb; - struct ufshpb_region *rgn; - struct ufshpb_subregion *srgn; - __be64 *addr; - int offset = 0; - int copied; - unsigned long lpn = pre_req->wb.lpn; - int rgn_idx, srgn_idx, srgn_offset; - unsigned long flags; - - addr = page_address(page); - ufshpb_get_pos_from_lpn(hpb, lpn, &rgn_idx, &srgn_idx, &srgn_offset); - - spin_lock_irqsave(&hpb->rgn_state_lock, flags); - -next_offset: - rgn = hpb->rgn_tbl + rgn_idx; - srgn = rgn->srgn_tbl + srgn_idx; - - if (!ufshpb_is_valid_srgn(rgn, srgn)) - goto mctx_error; - - if (!srgn->mctx) - goto mctx_error; - - copied = ufshpb_fill_ppn_from_page(hpb, srgn->mctx, srgn_offset, - pre_req->wb.len - offset, - &addr[offset]); - - if (copied < 0) - goto mctx_error; - - offset += copied; - srgn_offset += copied; - - if (srgn_offset == hpb->entries_per_srgn) { - srgn_offset = 0; - - if (++srgn_idx == hpb->srgns_per_rgn) { - srgn_idx = 0; - rgn_idx++; - } - } - - if (offset < pre_req->wb.len) - goto next_offset; - - spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); - return 0; -mctx_error: - spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); - return -ENOMEM; -} - -static int ufshpb_pre_req_add_bio_page(struct ufshpb_lu *hpb, - struct request_queue *q, - struct ufshpb_req *pre_req) -{ - struct page *page = pre_req->wb.m_page; - struct bio *bio = pre_req->bio; - int entries_bytes, ret; - - if (!page) - return -ENOMEM; - - if (ufshpb_prep_entry(pre_req, page)) - return -ENOMEM; - - entries_bytes = pre_req->wb.len * sizeof(__be64); - - ret = bio_add_pc_page(q, bio, page, entries_bytes, 0); - if (ret != entries_bytes) { - dev_err(&hpb->sdev_ufs_lu->sdev_dev, - "bio_add_pc_page fail: %d", ret); - return -ENOMEM; - } - return 0; -} - -static inline int ufshpb_get_read_id(struct ufshpb_lu *hpb) -{ - if (++hpb->cur_read_id >= MAX_HPB_READ_ID) - hpb->cur_read_id = 1; - return hpb->cur_read_id; -} - -static int ufshpb_execute_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd, - struct ufshpb_req *pre_req, int read_id) -{ - struct scsi_device *sdev = cmd->device; - struct request_queue *q = sdev->request_queue; - struct request *req; - struct scsi_request *rq; - struct bio *bio = pre_req->bio; - - pre_req->hpb = hpb; - pre_req->wb.lpn = sectors_to_logical(cmd->device, - blk_rq_pos(scsi_cmd_to_rq(cmd))); - pre_req->wb.len = sectors_to_logical(cmd->device, - blk_rq_sectors(scsi_cmd_to_rq(cmd))); - if (ufshpb_pre_req_add_bio_page(hpb, q, pre_req)) - return -ENOMEM; - - req = pre_req->req; - - /* 1. request setup */ - blk_rq_append_bio(req, bio); - req->rq_disk = NULL; - req->end_io_data = (void *)pre_req; - req->end_io = ufshpb_pre_req_compl_fn; - - /* 2. scsi_request setup */ - rq = scsi_req(req); - rq->retries = 1; - - ufshpb_set_write_buf_cmd(rq->cmd, pre_req->wb.lpn, pre_req->wb.len, - read_id); - rq->cmd_len = scsi_command_size(rq->cmd); - - if (blk_insert_cloned_request(q, req) != BLK_STS_OK) - return -EAGAIN; - - hpb->stats.pre_req_cnt++; - - return 0; -} - -static int ufshpb_issue_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd, - int *read_id) -{ - struct ufshpb_req *pre_req; - struct request *req = NULL; - unsigned long flags; - int _read_id; - int ret = 0; - - req = blk_get_request(cmd->device->request_queue, - REQ_OP_DRV_OUT | REQ_SYNC, BLK_MQ_REQ_NOWAIT); - if (IS_ERR(req)) - return -EAGAIN; - - spin_lock_irqsave(&hpb->rgn_state_lock, flags); - pre_req = ufshpb_get_pre_req(hpb); - if (!pre_req) { - ret = -EAGAIN; - goto unlock_out; - } - _read_id = ufshpb_get_read_id(hpb); - spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); - - pre_req->req = req; - - ret = ufshpb_execute_pre_req(hpb, cmd, pre_req, _read_id); - if (ret) - goto free_pre_req; - - *read_id = _read_id; - - return ret; -free_pre_req: - spin_lock_irqsave(&hpb->rgn_state_lock, flags); - ufshpb_put_pre_req(hpb, pre_req); -unlock_out: - spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); - blk_put_request(req); - return ret; -} - /* * This function will set up HPB read command using host-side L2P map data. */ @@ -609,7 +354,6 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) __be64 ppn; unsigned long flags; int transfer_len, rgn_idx, srgn_idx, srgn_offset; - int read_id = 0; int err = 0; hpb = ufshpb_get_hpb_data(cmd->device); @@ -685,24 +429,8 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) dev_err(hba->dev, "get ppn failed. err %d\n", err); return err; } - if (!ufshpb_is_legacy(hba) && - ufshpb_is_required_wb(hpb, transfer_len)) { - err = ufshpb_issue_pre_req(hpb, cmd, &read_id); - if (err) { - unsigned long timeout; - - timeout = cmd->jiffies_at_alloc + msecs_to_jiffies( - hpb->params.requeue_timeout_ms); - - if (time_before(jiffies, timeout)) - return -EAGAIN; - - hpb->stats.miss_cnt++; - return 0; - } - } - ufshpb_set_hpb_read_to_upiu(hba, lrbp, ppn, transfer_len, read_id); + ufshpb_set_hpb_read_to_upiu(hba, lrbp, ppn, transfer_len); hpb->stats.hit_cnt++; return 0; @@ -1841,16 +1569,11 @@ static void ufshpb_lu_parameter_init(struct ufs_hba *hba, u32 entries_per_rgn; u64 rgn_mem_size, tmp; - /* for pre_req */ - hpb->pre_req_min_tr_len = hpb_dev_info->max_hpb_single_cmd + 1; - if (ufshpb_is_legacy(hba)) hpb->pre_req_max_tr_len = HPB_LEGACY_CHUNK_HIGH; else hpb->pre_req_max_tr_len = HPB_MULTI_CHUNK_HIGH; - hpb->cur_read_id = 0; - hpb->lu_pinned_start = hpb_lu_info->pinned_start; hpb->lu_pinned_end = hpb_lu_info->num_pinned ? (hpb_lu_info->pinned_start + hpb_lu_info->num_pinned - 1) diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h index a79e07398970..f15d8fdbce2e 100644 --- a/drivers/scsi/ufs/ufshpb.h +++ b/drivers/scsi/ufs/ufshpb.h @@ -241,8 +241,6 @@ struct ufshpb_lu { spinlock_t param_lock; struct list_head lh_pre_req_free; - int cur_read_id; - int pre_req_min_tr_len; int pre_req_max_tr_len; /* cached L2P map management worker */ diff --git a/drivers/spi/spi-altera-dfl.c b/drivers/spi/spi-altera-dfl.c index 44fc9ee13fc7..ca40923258af 100644 --- a/drivers/spi/spi-altera-dfl.c +++ b/drivers/spi/spi-altera-dfl.c @@ -134,7 +134,7 @@ static int dfl_spi_altera_probe(struct dfl_device *dfl_dev) if (!master) return -ENOMEM; - master->bus_num = dfl_dev->id; + master->bus_num = -1; hw = spi_master_get_devdata(master); diff --git a/drivers/spi/spi-altera-platform.c b/drivers/spi/spi-altera-platform.c index f7a7c14e3679..65147aae82a1 100644 --- a/drivers/spi/spi-altera-platform.c +++ b/drivers/spi/spi-altera-platform.c @@ -48,7 +48,7 @@ static int altera_spi_probe(struct platform_device *pdev) return err; /* setup the master state. */ - master->bus_num = pdev->id; + master->bus_num = -1; if (pdata) { if (pdata->num_chipselect > ALTERA_SPI_MAX_CS) { diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c index feebda66f56e..e4484ace584e 100644 --- a/drivers/spi/spi-pl022.c +++ b/drivers/spi/spi-pl022.c @@ -1716,12 +1716,13 @@ static int verify_controller_parameters(struct pl022 *pl022, return -EINVAL; } } else { - if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX) + if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX) { dev_err(&pl022->adev->dev, "Microwire half duplex mode requested," " but this is only available in the" " ST version of PL022\n"); - return -EINVAL; + return -EINVAL; + } } } return 0; diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 26e3d90d1e7c..841667a896dd 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -80,6 +80,7 @@ struct vduse_dev { struct vdpa_callback config_cb; struct work_struct inject; spinlock_t irq_lock; + struct rw_semaphore rwsem; int minor; bool broken; bool connected; @@ -410,6 +411,8 @@ static void vduse_dev_reset(struct vduse_dev *dev) if (domain->bounce_map) vduse_domain_reset_bounce_map(domain); + down_write(&dev->rwsem); + dev->status = 0; dev->driver_features = 0; dev->generation++; @@ -443,6 +446,8 @@ static void vduse_dev_reset(struct vduse_dev *dev) flush_work(&vq->inject); flush_work(&vq->kick); } + + up_write(&dev->rwsem); } static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx, @@ -885,6 +890,23 @@ static void vduse_vq_irq_inject(struct work_struct *work) spin_unlock_irq(&vq->irq_lock); } +static int vduse_dev_queue_irq_work(struct vduse_dev *dev, + struct work_struct *irq_work) +{ + int ret = -EINVAL; + + down_read(&dev->rwsem); + if (!(dev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto unlock; + + ret = 0; + queue_work(vduse_irq_wq, irq_work); +unlock: + up_read(&dev->rwsem); + + return ret; +} + static long vduse_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -966,8 +988,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; } case VDUSE_DEV_INJECT_CONFIG_IRQ: - ret = 0; - queue_work(vduse_irq_wq, &dev->inject); + ret = vduse_dev_queue_irq_work(dev, &dev->inject); break; case VDUSE_VQ_SETUP: { struct vduse_vq_config config; @@ -1053,9 +1074,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, if (index >= dev->vq_num) break; - ret = 0; index = array_index_nospec(index, dev->vq_num); - queue_work(vduse_irq_wq, &dev->vqs[index].inject); + ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index].inject); break; } default: @@ -1136,6 +1156,7 @@ static struct vduse_dev *vduse_dev_create(void) INIT_LIST_HEAD(&dev->send_list); INIT_LIST_HEAD(&dev->recv_list); spin_lock_init(&dev->irq_lock); + init_rwsem(&dev->rwsem); INIT_WORK(&dev->inject, vduse_dev_irq_inject); init_waitqueue_head(&dev->waitq); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index dd95dfd85e98..3035bb6f5458 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -576,7 +576,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, /* Last one doesn't continue. */ desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT); if (!indirect && vq->use_dma_api) - vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags = + vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags &= ~VRING_DESC_F_NEXT; if (indirect) { diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c index 643c6c2d0b72..ced2fc0deb8c 100644 --- a/drivers/watchdog/iTCO_wdt.c +++ b/drivers/watchdog/iTCO_wdt.c @@ -71,8 +71,6 @@ #define TCOBASE(p) ((p)->tco_res->start) /* SMI Control and Enable Register */ #define SMI_EN(p) ((p)->smi_res->start) -#define TCO_EN (1 << 13) -#define GBL_SMI_EN (1 << 0) #define TCO_RLD(p) (TCOBASE(p) + 0x00) /* TCO Timer Reload/Curr. Value */ #define TCOv1_TMR(p) (TCOBASE(p) + 0x01) /* TCOv1 Timer Initial Value*/ @@ -357,12 +355,8 @@ static int iTCO_wdt_set_timeout(struct watchdog_device *wd_dev, unsigned int t) tmrval = seconds_to_ticks(p, t); - /* - * If TCO SMIs are off, the timer counts down twice before rebooting. - * Otherwise, the BIOS generally reboots when the SMI triggers. - */ - if (p->smi_res && - (inl(SMI_EN(p)) & (TCO_EN | GBL_SMI_EN)) != (TCO_EN | GBL_SMI_EN)) + /* For TCO v1 the timer counts down twice before rebooting */ + if (p->iTCO_version == 1) tmrval /= 2; /* from the specs: */ @@ -527,7 +521,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev) * Disables TCO logic generating an SMI# */ val32 = inl(SMI_EN(p)); - val32 &= ~TCO_EN; /* Turn off SMI clearing watchdog */ + val32 &= 0xffffdfff; /* Turn off SMI clearing watchdog */ outl(val32, SMI_EN(p)); } diff --git a/drivers/watchdog/ixp4xx_wdt.c b/drivers/watchdog/ixp4xx_wdt.c index 2693ffb24ac7..31b03fa71341 100644 --- a/drivers/watchdog/ixp4xx_wdt.c +++ b/drivers/watchdog/ixp4xx_wdt.c @@ -119,7 +119,7 @@ static int ixp4xx_wdt_probe(struct platform_device *pdev) iwdt = devm_kzalloc(dev, sizeof(*iwdt), GFP_KERNEL); if (!iwdt) return -ENOMEM; - iwdt->base = dev->platform_data; + iwdt->base = (void __iomem *)dev->platform_data; /* * Retrieve rate from a fixed clock from the device tree if diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c index 1616f93dfad7..74d785b2b478 100644 --- a/drivers/watchdog/omap_wdt.c +++ b/drivers/watchdog/omap_wdt.c @@ -268,8 +268,12 @@ static int omap_wdt_probe(struct platform_device *pdev) wdev->wdog.bootstatus = WDIOF_CARDRESET; } - if (!early_enable) + if (early_enable) { + omap_wdt_start(&wdev->wdog); + set_bit(WDOG_HW_RUNNING, &wdev->wdog.status); + } else { omap_wdt_disable(wdev); + } ret = watchdog_register_device(&wdev->wdog); if (ret) { diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c index ee9ff38929eb..9791c74aebd4 100644 --- a/drivers/watchdog/sbsa_gwdt.c +++ b/drivers/watchdog/sbsa_gwdt.c @@ -130,7 +130,7 @@ static u64 sbsa_gwdt_reg_read(struct sbsa_gwdt *gwdt) if (gwdt->version == 0) return readl(gwdt->control_base + SBSA_GWDT_WOR); else - return readq(gwdt->control_base + SBSA_GWDT_WOR); + return lo_hi_readq(gwdt->control_base + SBSA_GWDT_WOR); } static void sbsa_gwdt_reg_write(u64 val, struct sbsa_gwdt *gwdt) @@ -138,7 +138,7 @@ static void sbsa_gwdt_reg_write(u64 val, struct sbsa_gwdt *gwdt) if (gwdt->version == 0) writel((u32)val, gwdt->control_base + SBSA_GWDT_WOR); else - writeq(val, gwdt->control_base + SBSA_GWDT_WOR); + lo_hi_writeq(val, gwdt->control_base + SBSA_GWDT_WOR); } /* @@ -411,4 +411,3 @@ MODULE_AUTHOR("Suravee Suthikulpanit <[email protected]>"); MODULE_AUTHOR("Al Stone <[email protected]>"); MODULE_AUTHOR("Timur Tabi <[email protected]>"); MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:" DRV_NAME); diff --git a/fs/afs/write.c b/fs/afs/write.c index f24370f5c774..8b1d9c2f6bec 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -861,7 +861,8 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) */ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) { - struct page *page = thp_head(vmf->page); + struct folio *folio = page_folio(vmf->page); + struct page *page = &folio->page; struct file *file = vmf->vma->vm_file; struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); @@ -884,7 +885,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) goto out; #endif - if (wait_on_page_writeback_killable(page)) + if (folio_wait_writeback_killable(folio)) goto out; if (lock_page_killable(page) < 0) @@ -894,8 +895,8 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) * details the portion of the page we need to write back and we might * need to redirty the page if there's a problem. */ - if (wait_on_page_writeback_killable(page) < 0) { - unlock_page(page); + if (folio_wait_writeback_killable(folio) < 0) { + folio_unlock(folio); goto out; } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 7869ad12bc6e..0913ee50e6c3 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -172,9 +172,10 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio, /* Hash through the page sector by sector */ for (pg_offset = 0; pg_offset < bytes_left; pg_offset += sectorsize) { - kaddr = page_address(page); + kaddr = kmap_atomic(page); crypto_shash_digest(shash, kaddr + pg_offset, sectorsize, csum); + kunmap_atomic(kaddr); if (memcmp(&csum, cb_sum, csum_size) != 0) { btrfs_print_data_csum_error(inode, disk_start, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 487533c35ddb..7c096ab9bb5e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -287,8 +287,9 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, cur_size = min_t(unsigned long, compressed_size, PAGE_SIZE); - kaddr = page_address(cpage); + kaddr = kmap_atomic(cpage); write_extent_buffer(leaf, kaddr, ptr, cur_size); + kunmap_atomic(kaddr); i++; ptr += cur_size; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index c25dfd1a8a54..3dbe6eb5fda7 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -141,7 +141,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, *total_in = 0; in_page = find_get_page(mapping, start >> PAGE_SHIFT); - data_in = page_address(in_page); + data_in = kmap(in_page); /* * store the size of all chunks of compressed data in @@ -152,7 +152,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, ret = -ENOMEM; goto out; } - cpage_out = page_address(out_page); + cpage_out = kmap(out_page); out_offset = LZO_LEN; tot_out = LZO_LEN; pages[0] = out_page; @@ -210,6 +210,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, if (out_len == 0 && tot_in >= len) break; + kunmap(out_page); if (nr_pages == nr_dest_pages) { out_page = NULL; ret = -E2BIG; @@ -221,7 +222,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, ret = -ENOMEM; goto out; } - cpage_out = page_address(out_page); + cpage_out = kmap(out_page); pages[nr_pages++] = out_page; pg_bytes_left = PAGE_SIZE; @@ -243,11 +244,12 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, break; bytes_left = len - tot_in; + kunmap(in_page); put_page(in_page); start += PAGE_SIZE; in_page = find_get_page(mapping, start >> PAGE_SHIFT); - data_in = page_address(in_page); + data_in = kmap(in_page); in_len = min(bytes_left, PAGE_SIZE); } @@ -257,17 +259,22 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, } /* store the size of all chunks of compressed data */ - sizes_ptr = page_address(pages[0]); + sizes_ptr = kmap_local_page(pages[0]); write_compress_length(sizes_ptr, tot_out); + kunmap_local(sizes_ptr); ret = 0; *total_out = tot_out; *total_in = tot_in; out: *out_pages = nr_pages; + if (out_page) + kunmap(out_page); - if (in_page) + if (in_page) { + kunmap(in_page); put_page(in_page); + } return ret; } @@ -283,6 +290,7 @@ static void copy_compressed_segment(struct compressed_bio *cb, u32 orig_in = *cur_in; while (*cur_in < orig_in + len) { + char *kaddr; struct page *cur_page; u32 copy_len = min_t(u32, PAGE_SIZE - offset_in_page(*cur_in), orig_in + len - *cur_in); @@ -290,9 +298,11 @@ static void copy_compressed_segment(struct compressed_bio *cb, ASSERT(copy_len); cur_page = cb->compressed_pages[*cur_in / PAGE_SIZE]; + kaddr = kmap(cur_page); memcpy(dest + *cur_in - orig_in, - page_address(cur_page) + offset_in_page(*cur_in), + kaddr + offset_in_page(*cur_in), copy_len); + kunmap(cur_page); *cur_in += copy_len; } @@ -303,6 +313,7 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) struct workspace *workspace = list_entry(ws, struct workspace, list); const struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb); const u32 sectorsize = fs_info->sectorsize; + char *kaddr; int ret; /* Compressed data length, can be unaligned */ u32 len_in; @@ -311,7 +322,9 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) /* Bytes decompressed so far */ u32 cur_out = 0; - len_in = read_compress_length(page_address(cb->compressed_pages[0])); + kaddr = kmap(cb->compressed_pages[0]); + len_in = read_compress_length(kaddr); + kunmap(cb->compressed_pages[0]); cur_in += LZO_LEN; /* @@ -344,9 +357,9 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) ASSERT(cur_in / sectorsize == (cur_in + LZO_LEN - 1) / sectorsize); cur_page = cb->compressed_pages[cur_in / PAGE_SIZE]; + kaddr = kmap(cur_page); ASSERT(cur_page); - seg_len = read_compress_length(page_address(cur_page) + - offset_in_page(cur_in)); + seg_len = read_compress_length(kaddr + offset_in_page(cur_in)); cur_in += LZO_LEN; /* Copy the compressed segment payload into workspace */ @@ -431,7 +444,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in, destlen = min_t(unsigned long, destlen, PAGE_SIZE); bytes = min_t(unsigned long, destlen, out_len - start_byte); - kaddr = page_address(dest_page); + kaddr = kmap_local_page(dest_page); memcpy(kaddr, workspace->buf + start_byte, bytes); /* @@ -441,6 +454,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in, */ if (bytes < destlen) memset(kaddr+bytes, 0, destlen-bytes); + kunmap_local(kaddr); out: return ret; } diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 8afa90074891..767a0c6c9694 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -126,7 +126,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, ret = -ENOMEM; goto out; } - cpage_out = page_address(out_page); + cpage_out = kmap(out_page); pages[0] = out_page; nr_pages = 1; @@ -148,22 +148,26 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, int i; for (i = 0; i < in_buf_pages; i++) { - if (in_page) + if (in_page) { + kunmap(in_page); put_page(in_page); + } in_page = find_get_page(mapping, start >> PAGE_SHIFT); - data_in = page_address(in_page); + data_in = kmap(in_page); memcpy(workspace->buf + i * PAGE_SIZE, data_in, PAGE_SIZE); start += PAGE_SIZE; } workspace->strm.next_in = workspace->buf; } else { - if (in_page) + if (in_page) { + kunmap(in_page); put_page(in_page); + } in_page = find_get_page(mapping, start >> PAGE_SHIFT); - data_in = page_address(in_page); + data_in = kmap(in_page); start += PAGE_SIZE; workspace->strm.next_in = data_in; } @@ -192,6 +196,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, * the stream end if required */ if (workspace->strm.avail_out == 0) { + kunmap(out_page); if (nr_pages == nr_dest_pages) { out_page = NULL; ret = -E2BIG; @@ -202,7 +207,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, ret = -ENOMEM; goto out; } - cpage_out = page_address(out_page); + cpage_out = kmap(out_page); pages[nr_pages] = out_page; nr_pages++; workspace->strm.avail_out = PAGE_SIZE; @@ -229,6 +234,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, goto out; } else if (workspace->strm.avail_out == 0) { /* get another page for the stream end */ + kunmap(out_page); if (nr_pages == nr_dest_pages) { out_page = NULL; ret = -E2BIG; @@ -239,7 +245,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, ret = -ENOMEM; goto out; } - cpage_out = page_address(out_page); + cpage_out = kmap(out_page); pages[nr_pages] = out_page; nr_pages++; workspace->strm.avail_out = PAGE_SIZE; @@ -258,8 +264,13 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, *total_in = workspace->strm.total_in; out: *out_pages = nr_pages; - if (in_page) + if (out_page) + kunmap(out_page); + + if (in_page) { + kunmap(in_page); put_page(in_page); + } return ret; } @@ -276,7 +287,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb) unsigned long buf_start; struct page **pages_in = cb->compressed_pages; - data_in = page_address(pages_in[page_in_index]); + data_in = kmap(pages_in[page_in_index]); workspace->strm.next_in = data_in; workspace->strm.avail_in = min_t(size_t, srclen, PAGE_SIZE); workspace->strm.total_in = 0; @@ -298,6 +309,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb) if (Z_OK != zlib_inflateInit2(&workspace->strm, wbits)) { pr_warn("BTRFS: inflateInit failed\n"); + kunmap(pages_in[page_in_index]); return -EIO; } while (workspace->strm.total_in < srclen) { @@ -324,13 +336,13 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb) if (workspace->strm.avail_in == 0) { unsigned long tmp; - + kunmap(pages_in[page_in_index]); page_in_index++; if (page_in_index >= total_pages_in) { data_in = NULL; break; } - data_in = page_address(pages_in[page_in_index]); + data_in = kmap(pages_in[page_in_index]); workspace->strm.next_in = data_in; tmp = srclen - workspace->strm.total_in; workspace->strm.avail_in = min(tmp, PAGE_SIZE); @@ -342,6 +354,8 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb) ret = 0; done: zlib_inflateEnd(&workspace->strm); + if (data_in) + kunmap(pages_in[page_in_index]); if (!ret) zero_fill_bio(cb->orig_bio); return ret; diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index 56dce9f00988..f06b68040352 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -399,7 +399,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, /* map in the first page of input data */ in_page = find_get_page(mapping, start >> PAGE_SHIFT); - workspace->in_buf.src = page_address(in_page); + workspace->in_buf.src = kmap(in_page); workspace->in_buf.pos = 0; workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE); @@ -411,7 +411,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, goto out; } pages[nr_pages++] = out_page; - workspace->out_buf.dst = page_address(out_page); + workspace->out_buf.dst = kmap(out_page); workspace->out_buf.pos = 0; workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE); @@ -446,6 +446,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, if (workspace->out_buf.pos == workspace->out_buf.size) { tot_out += PAGE_SIZE; max_out -= PAGE_SIZE; + kunmap(out_page); if (nr_pages == nr_dest_pages) { out_page = NULL; ret = -E2BIG; @@ -457,7 +458,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, goto out; } pages[nr_pages++] = out_page; - workspace->out_buf.dst = page_address(out_page); + workspace->out_buf.dst = kmap(out_page); workspace->out_buf.pos = 0; workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE); @@ -472,12 +473,13 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, /* Check if we need more input */ if (workspace->in_buf.pos == workspace->in_buf.size) { tot_in += PAGE_SIZE; + kunmap(in_page); put_page(in_page); start += PAGE_SIZE; len -= PAGE_SIZE; in_page = find_get_page(mapping, start >> PAGE_SHIFT); - workspace->in_buf.src = page_address(in_page); + workspace->in_buf.src = kmap(in_page); workspace->in_buf.pos = 0; workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE); } @@ -504,6 +506,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, tot_out += PAGE_SIZE; max_out -= PAGE_SIZE; + kunmap(out_page); if (nr_pages == nr_dest_pages) { out_page = NULL; ret = -E2BIG; @@ -515,7 +518,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, goto out; } pages[nr_pages++] = out_page; - workspace->out_buf.dst = page_address(out_page); + workspace->out_buf.dst = kmap(out_page); workspace->out_buf.pos = 0; workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE); } @@ -531,8 +534,12 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, out: *out_pages = nr_pages; /* Cleanup */ - if (in_page) + if (in_page) { + kunmap(in_page); put_page(in_page); + } + if (out_page) + kunmap(out_page); return ret; } @@ -556,7 +563,7 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) goto done; } - workspace->in_buf.src = page_address(pages_in[page_in_index]); + workspace->in_buf.src = kmap(pages_in[page_in_index]); workspace->in_buf.pos = 0; workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE); @@ -592,14 +599,14 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) break; if (workspace->in_buf.pos == workspace->in_buf.size) { - page_in_index++; + kunmap(pages_in[page_in_index++]); if (page_in_index >= total_pages_in) { workspace->in_buf.src = NULL; ret = -EIO; goto done; } srclen -= PAGE_SIZE; - workspace->in_buf.src = page_address(pages_in[page_in_index]); + workspace->in_buf.src = kmap(pages_in[page_in_index]); workspace->in_buf.pos = 0; workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE); } @@ -607,6 +614,8 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) ret = 0; zero_fill_bio(cb->orig_bio); done: + if (workspace->in_buf.src) + kunmap(pages_in[page_in_index]); return ret; } diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 8ffc40e84a59..fcf4f3b72923 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -25,20 +25,20 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, struct cachefiles_object *object; struct fscache_retrieval *op = monitor->op; struct wait_page_key *key = _key; - struct page *page = wait->private; + struct folio *folio = wait->private; ASSERT(key); _enter("{%lu},%u,%d,{%p,%u}", monitor->netfs_page->index, mode, sync, - key->page, key->bit_nr); + key->folio, key->bit_nr); - if (key->page != page || key->bit_nr != PG_locked) + if (key->folio != folio || key->bit_nr != PG_locked) return 0; - _debug("--- monitor %p %lx ---", page, page->flags); + _debug("--- monitor %p %lx ---", folio, folio->flags); - if (!PageUptodate(page) && !PageError(page)) { + if (!folio_test_uptodate(folio) && !folio_test_error(folio)) { /* unlocked, not uptodate and not erronous? */ _debug("page probably truncated"); } @@ -107,7 +107,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object, put_page(backpage2); INIT_LIST_HEAD(&monitor->op_link); - add_page_wait_queue(backpage, &monitor->monitor); + folio_add_wait_queue(page_folio(backpage), &monitor->monitor); if (trylock_page(backpage)) { ret = -EIO; @@ -294,7 +294,7 @@ monitor_backing_page: get_page(backpage); monitor->back_page = backpage; monitor->monitor.private = backpage; - add_page_wait_queue(backpage, &monitor->monitor); + folio_add_wait_queue(page_folio(backpage), &monitor->monitor); monitor = NULL; /* but the page may have been read before the monitor was installed, so @@ -548,7 +548,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, get_page(backpage); monitor->back_page = backpage; monitor->monitor.private = backpage; - add_page_wait_queue(backpage, &monitor->monitor); + folio_add_wait_queue(page_folio(backpage), &monitor->monitor); monitor = NULL; /* but the page may have been read before the monitor was diff --git a/fs/io_uring.c b/fs/io_uring.c index bc18af5e0a93..3a098b473401 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3356,7 +3356,7 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) } /* - * This is our waitqueue callback handler, registered through lock_page_async() + * This is our waitqueue callback handler, registered through __folio_lock_async() * when we initially tried to do the IO with the iocb armed our waitqueue. * This gets called when the page is unlocked, and we generally expect that to * happen when the page IO is completed and the page is now uptodate. This will diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 176580f54af9..104ae698443e 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -13,6 +13,7 @@ #include <linux/buffer_head.h> #include <linux/mempool.h> #include <linux/seq_file.h> +#include <linux/writeback.h> #include "jfs_incore.h" #include "jfs_superblock.h" #include "jfs_filsys.h" diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 8521942f5af2..481017e1dac5 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1251,7 +1251,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, { struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; struct journal_head *jh; - int ret; + int ret = 1; if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap)) return 0; @@ -1259,14 +1259,18 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, if (!buffer_jbd(bg_bh)) return 1; - jh = bh2jh(bg_bh); - spin_lock(&jh->b_state_lock); - bg = (struct ocfs2_group_desc *) jh->b_committed_data; - if (bg) - ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); - else - ret = 1; - spin_unlock(&jh->b_state_lock); + jbd_lock_bh_journal_head(bg_bh); + if (buffer_jbd(bg_bh)) { + jh = bh2jh(bg_bh); + spin_lock(&jh->b_state_lock); + bg = (struct ocfs2_group_desc *) jh->b_committed_data; + if (bg) + ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); + else + ret = 1; + spin_unlock(&jh->b_state_lock); + } + jbd_unlock_bh_journal_head(bg_bh); return ret; } diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index 4a674db4e1fa..fedc0dfa4877 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -49,9 +49,15 @@ static inline void flush_cache_page(struct vm_area_struct *vma, static inline void flush_dcache_page(struct page *page) { } + +static inline void flush_dcache_folio(struct folio *folio) { } #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO #endif +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO +void flush_dcache_folio(struct folio *folio); +#endif #ifndef flush_dcache_mmap_lock static inline void flush_dcache_mmap_lock(struct address_space *mapping) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ac7f231b8825..a62e72dd829f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -64,7 +64,7 @@ static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) return atomic_long_read(&bdi->tot_write_bandwidth); } -static inline void __add_wb_stat(struct bdi_writeback *wb, +static inline void wb_stat_mod(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); @@ -72,12 +72,12 @@ static inline void __add_wb_stat(struct bdi_writeback *wb, static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - __add_wb_stat(wb, item, 1); + wb_stat_mod(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - __add_wb_stat(wb, item, -1); + wb_stat_mod(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 020a7d5bf470..3db6f6c95489 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -929,8 +929,11 @@ struct bpf_array_aux { * stored in the map to make sure that all callers and callees have * the same prog type and JITed flag. */ - enum bpf_prog_type type; - bool jited; + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9c81724e4b98..bbe1eefa4c8a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -101,14 +101,14 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) -#ifdef CONFIG_NET -BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) -BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) -BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #ifdef CONFIG_BPF_LSM BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops) +#ifdef CONFIG_NET +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) diff --git a/include/linux/filter.h b/include/linux/filter.h index 4a93c12543ee..ef03ff34234d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1051,6 +1051,7 @@ extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; extern long bpf_jit_limit; +extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h index c12df59d3f5f..3e378b1fb0bc 100644 --- a/include/linux/flex_proportions.h +++ b/include/linux/flex_proportions.h @@ -83,9 +83,10 @@ struct fprop_local_percpu { int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp); void fprop_local_destroy_percpu(struct fprop_local_percpu *pl); -void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl); -void __fprop_inc_percpu_max(struct fprop_global *p, struct fprop_local_percpu *pl, - int max_frac); +void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl, + long nr); +void __fprop_add_percpu_max(struct fprop_global *p, + struct fprop_local_percpu *pl, int max_frac, long nr); void fprop_fraction_percpu(struct fprop_global *p, struct fprop_local_percpu *pl, unsigned long *numerator, unsigned long *denominator); @@ -96,7 +97,7 @@ void fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl) unsigned long flags; local_irq_save(flags); - __fprop_inc_percpu(p, pl); + __fprop_add_percpu(p, pl, 1); local_irq_restore(flags); } diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 55b2ec1f965a..3745efd21cf6 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -520,15 +520,11 @@ static inline void arch_free_page(struct page *page, int order) { } #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif -#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE -static inline int arch_make_page_accessible(struct page *page) -{ - return 0; -} -#endif struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); +struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask); unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, @@ -570,6 +566,15 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) return __alloc_pages(gfp_mask, order, nid, NULL); } +static inline +struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid) +{ + VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); + VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid)); + + return __folio_alloc(gfp, order, nid, NULL); +} + /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and @@ -586,6 +591,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); +struct folio *folio_alloc(gfp_t gfp, unsigned order); extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage); @@ -596,6 +602,10 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node(numa_node_id(), gfp_mask, order); } +static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) +{ + return __folio_alloc_node(gfp, order, numa_node_id()); +} #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 4aa1031d3e4c..0a0b2b09b1b8 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -73,6 +73,12 @@ static inline void *kmap_local_page(struct page *page) return __kmap_local_page_prot(page, kmap_prot); } +static inline void *kmap_local_folio(struct folio *folio, size_t offset) +{ + struct page *page = folio_page(folio, offset / PAGE_SIZE); + return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE; +} + static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return __kmap_local_page_prot(page, prot); @@ -171,6 +177,11 @@ static inline void *kmap_local_page(struct page *page) return page_address(page); } +static inline void *kmap_local_folio(struct folio *folio, size_t offset) +{ + return page_address(&folio->page) + offset; +} + static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return kmap_local_page(page); diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b4c49f9cc379..27cdd715c5f9 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -97,6 +97,43 @@ static inline void kmap_flush_unused(void); static inline void *kmap_local_page(struct page *page); /** + * kmap_local_folio - Map a page in this folio for temporary usage + * @folio: The folio containing the page. + * @offset: The byte offset within the folio which identifies the page. + * + * Requires careful handling when nesting multiple mappings because the map + * management is stack based. The unmap has to be in the reverse order of + * the map operation:: + * + * addr1 = kmap_local_folio(folio1, offset1); + * addr2 = kmap_local_folio(folio2, offset2); + * ... + * kunmap_local(addr2); + * kunmap_local(addr1); + * + * Unmapping addr1 before addr2 is invalid and causes malfunction. + * + * Contrary to kmap() mappings the mapping is only valid in the context of + * the caller and cannot be handed to other contexts. + * + * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the + * virtual address of the direct mapping. Only real highmem pages are + * temporarily mapped. + * + * While it is significantly faster than kmap() for the higmem case it + * comes with restrictions about the pointer validity. Only use when really + * necessary. + * + * On HIGHMEM enabled systems mapping a highmem page has the side effect of + * disabling migration in order to keep the virtual address stable across + * preemption. No caller of kmap_local_folio() can rely on this side effect. + * + * Context: Can be invoked from any context. + * Return: The virtual address of @offset. + */ +static inline void *kmap_local_folio(struct folio *folio, size_t offset); + +/** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped * diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f123e15d966e..f280f33ff223 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -251,15 +251,6 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, } /** - * thp_head - Head page of a transparent huge page. - * @page: Any page (tail, head or regular) found in the page cache. - */ -static inline struct page *thp_head(struct page *page) -{ - return compound_head(page); -} - -/** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ @@ -336,12 +327,6 @@ static inline struct list_head *page_deferred_list(struct page *page) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) -static inline struct page *thp_head(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return page; -} - static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 161e8164abcf..a38a5bca1ba5 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -52,7 +52,7 @@ struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); -void ksm_migrate_page(struct page *newpage, struct page *oldpage); +void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -83,7 +83,7 @@ static inline void rmap_walk_ksm(struct page *page, { } -static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) +static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old) { } #endif /* CONFIG_MMU */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3096c9a0ee01..e34bf0cbdf55 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -369,7 +369,7 @@ enum page_memcg_data_flags { #define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) -static inline bool PageMemcgKmem(struct page *page); +static inline bool folio_memcg_kmem(struct folio *folio); /* * After the initialization objcg->memcg is always pointing at @@ -384,89 +384,95 @@ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) } /* - * __page_memcg - get the memory cgroup associated with a non-kmem page - * @page: a pointer to the page struct + * __folio_memcg - Get the memory cgroup associated with a non-kmem folio + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the memory cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages or - * kmem pages. + * against some type of folios, e.g. slab folios or ex-slab folios or + * kmem folios. */ -static inline struct mem_cgroup *__page_memcg(struct page *page) +static inline struct mem_cgroup *__folio_memcg(struct folio *folio) { - unsigned long memcg_data = page->memcg_data; + unsigned long memcg_data = folio->memcg_data; - VM_BUG_ON_PAGE(PageSlab(page), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); + VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } /* - * __page_objcg - get the object cgroup associated with a kmem page - * @page: a pointer to the page struct + * __folio_objcg - get the object cgroup associated with a kmem folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the object cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the object cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper object cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages or - * LRU pages. + * against some type of folios, e.g. slab folios or ex-slab folios or + * LRU folios. */ -static inline struct obj_cgroup *__page_objcg(struct page *page) +static inline struct obj_cgroup *__folio_objcg(struct folio *folio) { - unsigned long memcg_data = page->memcg_data; + unsigned long memcg_data = folio->memcg_data; - VM_BUG_ON_PAGE(PageSlab(page), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); - VM_BUG_ON_PAGE(!(memcg_data & MEMCG_DATA_KMEM), page); + VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } /* - * page_memcg - get the memory cgroup associated with a page - * @page: a pointer to the page struct + * folio_memcg - Get the memory cgroup associated with a folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the memory cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages. + * against some type of folios, e.g. slab folios or ex-slab folios. * - * For a non-kmem page any of the following ensures page and memcg binding + * For a non-kmem folio any of the following ensures folio and memcg binding * stability: * - * - the page lock + * - the folio lock * - LRU isolation * - lock_page_memcg() * - exclusive reference * - * For a kmem page a caller should hold an rcu read lock to protect memcg - * associated with a kmem page from being released. + * For a kmem folio a caller should hold an rcu read lock to protect memcg + * associated with a kmem folio from being released. */ +static inline struct mem_cgroup *folio_memcg(struct folio *folio) +{ + if (folio_memcg_kmem(folio)) + return obj_cgroup_memcg(__folio_objcg(folio)); + return __folio_memcg(folio); +} + static inline struct mem_cgroup *page_memcg(struct page *page) { - if (PageMemcgKmem(page)) - return obj_cgroup_memcg(__page_objcg(page)); - else - return __page_memcg(page); + return folio_memcg(page_folio(page)); } -/* - * page_memcg_rcu - locklessly get the memory cgroup associated with a page - * @page: a pointer to the page struct +/** + * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages. + * against some type of folios, e.g. slab folios or ex-slab folios. + * + * Return: A pointer to the memory cgroup associated with the folio, + * or NULL. */ -static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { - unsigned long memcg_data = READ_ONCE(page->memcg_data); + unsigned long memcg_data = READ_ONCE(folio->memcg_data); - VM_BUG_ON_PAGE(PageSlab(page), page); + VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); WARN_ON_ONCE(!rcu_read_lock_held()); if (memcg_data & MEMCG_DATA_KMEM) { @@ -523,17 +529,18 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) #ifdef CONFIG_MEMCG_KMEM /* - * PageMemcgKmem - check if the page has MemcgKmem flag set - * @page: a pointer to the page struct + * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. + * @folio: Pointer to the folio. * - * Checks if the page has MemcgKmem flag set. The caller must ensure that - * the page has an associated memory cgroup. It's not safe to call this function - * against some types of pages, e.g. slab pages. + * Checks if the folio has MemcgKmem flag set. The caller must ensure + * that the folio has an associated memory cgroup. It's not safe to call + * this function against some types of folios, e.g. slab folios. */ -static inline bool PageMemcgKmem(struct page *page) +static inline bool folio_memcg_kmem(struct folio *folio) { - VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page); - return page->memcg_data & MEMCG_DATA_KMEM; + VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); + VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio); + return folio->memcg_data & MEMCG_DATA_KMEM; } /* @@ -577,7 +584,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) } #else -static inline bool PageMemcgKmem(struct page *page) +static inline bool folio_memcg_kmem(struct folio *folio) { return false; } @@ -593,6 +600,11 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) } #endif +static inline bool PageMemcgKmem(struct page *page) +{ + return folio_memcg_kmem(page_folio(page)); +} + static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); @@ -684,26 +696,47 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) page_counter_read(&memcg->memory); } -int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask); -static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); + +/** + * mem_cgroup_charge - Charge a newly allocated folio to a cgroup. + * @folio: Folio to charge. + * @mm: mm context of the allocating task. + * @gfp: Reclaim mode. + * + * Try to charge @folio to the memcg that @mm belongs to, reclaiming + * pages according to @gfp if necessary. If @mm is NULL, try to + * charge to the active memcg. + * + * Do not use this for folios allocated for swapin. + * + * Return: 0 on success. Otherwise, an error code is returned. + */ +static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, + gfp_t gfp) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_charge(page, mm, gfp_mask); + return __mem_cgroup_charge(folio, mm, gfp); } int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); -void __mem_cgroup_uncharge(struct page *page); -static inline void mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct folio *folio); + +/** + * mem_cgroup_uncharge - Uncharge a folio. + * @folio: Folio to uncharge. + * + * Uncharge a folio previously charged with mem_cgroup_charge(). + */ +static inline void mem_cgroup_uncharge(struct folio *folio) { if (mem_cgroup_disabled()) return; - __mem_cgroup_uncharge(page); + __mem_cgroup_uncharge(folio); } void __mem_cgroup_uncharge_list(struct list_head *page_list); @@ -714,7 +747,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) __mem_cgroup_uncharge_list(page_list); } -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); +void mem_cgroup_migrate(struct folio *old, struct folio *new); /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node @@ -753,33 +786,33 @@ out: } /** - * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page - * @page: the page + * folio_lruvec - return lruvec for isolating/putting an LRU folio + * @folio: Pointer to the folio. * - * This function relies on page->mem_cgroup being stable. + * This function relies on folio->mem_cgroup being stable. */ -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec(struct folio *folio) { - pg_data_t *pgdat = page_pgdat(page); - struct mem_cgroup *memcg = page_memcg(page); + struct mem_cgroup *memcg = folio_memcg(folio); - VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page); - return mem_cgroup_lruvec(memcg, pgdat); + VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio); + return mem_cgroup_lruvec(memcg, folio_pgdat(folio)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); -struct lruvec *lock_page_lruvec(struct page *page); -struct lruvec *lock_page_lruvec_irq(struct page *page); -struct lruvec *lock_page_lruvec_irqsave(struct page *page, +struct lruvec *folio_lruvec_lock(struct folio *folio); +struct lruvec *folio_lruvec_lock_irq(struct folio *folio); +struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags); #ifdef CONFIG_DEBUG_VM -void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page); +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio); #else -static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +static inline +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } #endif @@ -947,6 +980,8 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); extern bool cgroup_memory_noswap; #endif +void folio_memcg_lock(struct folio *folio); +void folio_memcg_unlock(struct folio *folio); void lock_page_memcg(struct page *page); void unlock_page_memcg(struct page *page); @@ -1115,12 +1150,17 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 +static inline struct mem_cgroup *folio_memcg(struct folio *folio) +{ + return NULL; +} + static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; } -static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { WARN_ON_ONCE(!rcu_read_lock_held()); return NULL; @@ -1131,6 +1171,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return NULL; } +static inline bool folio_memcg_kmem(struct folio *folio) +{ + return false; +} + static inline bool PageMemcgKmem(struct page *page) { return false; @@ -1179,8 +1224,8 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) return false; } -static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +static inline int mem_cgroup_charge(struct folio *folio, + struct mm_struct *mm, gfp_t gfp) { return 0; } @@ -1195,7 +1240,7 @@ static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) { } -static inline void mem_cgroup_uncharge(struct page *page) +static inline void mem_cgroup_uncharge(struct folio *folio) { } @@ -1203,7 +1248,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } -static inline void mem_cgroup_migrate(struct page *old, struct page *new) +static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } @@ -1213,14 +1258,14 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, return &pgdat->__lruvec; } -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec(struct folio *folio) { - pg_data_t *pgdat = page_pgdat(page); - + struct pglist_data *pgdat = folio_pgdat(folio); return &pgdat->__lruvec; } -static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +static inline +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } @@ -1250,26 +1295,26 @@ static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } -static inline struct lruvec *lock_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec_lock(struct folio *folio) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } -static inline struct lruvec *lock_page_lruvec_irq(struct page *page) +static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irq(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } -static inline struct lruvec *lock_page_lruvec_irqsave(struct page *page, +static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flagsp) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); return &pgdat->__lruvec; @@ -1356,6 +1401,14 @@ static inline void unlock_page_memcg(struct page *page) { } +static inline void folio_memcg_lock(struct folio *folio) +{ +} + +static inline void folio_memcg_unlock(struct folio *folio) +{ +} + static inline void mem_cgroup_handle_over_high(void) { } @@ -1517,38 +1570,39 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, } /* Test requires a stable page->memcg binding, see page_memcg() */ -static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec) +static inline bool folio_matches_lruvec(struct folio *folio, + struct lruvec *lruvec) { - return lruvec_pgdat(lruvec) == page_pgdat(page) && - lruvec_memcg(lruvec) == page_memcg(page); + return lruvec_pgdat(lruvec) == folio_pgdat(folio) && + lruvec_memcg(lruvec) == folio_memcg(folio); } /* Don't lock again iff page's lruvec locked */ -static inline struct lruvec *relock_page_lruvec_irq(struct page *page, +static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, struct lruvec *locked_lruvec) { if (locked_lruvec) { - if (page_matches_lruvec(page, locked_lruvec)) + if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irq(locked_lruvec); } - return lock_page_lruvec_irq(page); + return folio_lruvec_lock_irq(folio); } /* Don't lock again iff page's lruvec locked */ -static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, +static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio, struct lruvec *locked_lruvec, unsigned long *flags) { if (locked_lruvec) { - if (page_matches_lruvec(page, locked_lruvec)) + if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irqrestore(locked_lruvec, *flags); } - return lock_page_lruvec_irqsave(page, flags); + return folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -1558,17 +1612,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); -void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, +void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); -static inline void mem_cgroup_track_foreign_dirty(struct page *page, +static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { if (mem_cgroup_disabled()) return; - if (unlikely(&page_memcg(page)->css != wb->memcg_css)) - mem_cgroup_track_foreign_dirty_slowpath(page, wb); + if (unlikely(&folio_memcg(folio)->css != wb->memcg_css)) + mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); @@ -1588,7 +1642,7 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, { } -static inline void mem_cgroup_track_foreign_dirty(struct page *page, +static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { } diff --git a/include/linux/migrate.h b/include/linux/migrate.h index c8077e936691..0d2aeb9b0f66 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -57,6 +57,10 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +void folio_migrate_flags(struct folio *newfolio, struct folio *folio); +void folio_migrate_copy(struct folio *newfolio, struct folio *folio); +int folio_migrate_mapping(struct address_space *mapping, + struct folio *newfolio, struct folio *folio, int extra_count); #else static inline void putback_movable_pages(struct list_head *l) {} diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a52aba448f..40ff114aaf9e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -36,10 +36,7 @@ struct mempolicy; struct anon_vma; struct anon_vma_chain; -struct file_ra_state; struct user_struct; -struct writeback_control; -struct bdi_writeback; struct pt_regs; extern int sysctl_page_lock_unfairness; @@ -216,13 +213,6 @@ int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -/* - * Any attempt to mark this function as static leads to build failure - * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked() - * is referred to by BPF code. This must be visible for error injection. - */ -int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp, void **shadowp); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) @@ -748,13 +738,18 @@ static inline int put_page_testzero(struct page *page) return page_ref_dec_and_test(page); } +static inline int folio_put_testzero(struct folio *folio) +{ + return put_page_testzero(&folio->page); +} + /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ -static inline int get_page_unless_zero(struct page *page) +static inline bool get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } @@ -907,7 +902,7 @@ void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); -void copy_huge_page(struct page *dst, struct page *src); +void folio_copy(struct folio *dst, struct folio *src); /* * Compound pages have a destructor function. Provide a @@ -950,6 +945,20 @@ static inline unsigned int compound_order(struct page *page) return page[1].compound_order; } +/** + * folio_order - The allocation order of a folio. + * @folio: The folio. + * + * A folio is composed of 2^order pages. See get_order() for the definition + * of order. + * + * Return: The order of the folio. + */ +static inline unsigned int folio_order(struct folio *folio) +{ + return compound_order(&folio->page); +} + static inline bool hpage_pincount_available(struct page *page) { /* @@ -1131,6 +1140,11 @@ static inline enum zone_type page_zonenum(const struct page *page) return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } +static inline enum zone_type folio_zonenum(const struct folio *folio) +{ + return page_zonenum(&folio->page); +} + #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { @@ -1200,18 +1214,26 @@ static inline bool is_pci_p2pdma_page(const struct page *page) } /* 127: arbitrary random number, small enough to assemble well */ -#define page_ref_zero_or_close_to_overflow(page) \ - ((unsigned int) page_ref_count(page) + 127u <= 127u) +#define folio_ref_zero_or_close_to_overflow(folio) \ + ((unsigned int) folio_ref_count(folio) + 127u <= 127u) + +/** + * folio_get - Increment the reference count on a folio. + * @folio: The folio. + * + * Context: May be called in any context, as long as you know that + * you have a refcount on the folio. If you do not already have one, + * folio_try_get() may be the right interface for you to use. + */ +static inline void folio_get(struct folio *folio) +{ + VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio); + folio_ref_inc(folio); +} static inline void get_page(struct page *page) { - page = compound_head(page); - /* - * Getting a normal page or the head of a compound page - * requires to already have an elevated page->_refcount. - */ - VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); - page_ref_inc(page); + folio_get(page_folio(page)); } bool __must_check try_grab_page(struct page *page, unsigned int flags); @@ -1228,9 +1250,28 @@ static inline __must_check bool try_get_page(struct page *page) return true; } +/** + * folio_put - Decrement the reference count on a folio. + * @folio: The folio. + * + * If the folio's reference count reaches zero, the memory will be + * released back to the page allocator and may be used by another + * allocation immediately. Do not access the memory or the struct folio + * after calling folio_put() unless you can be sure that it wasn't the + * last reference. + * + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. + */ +static inline void folio_put(struct folio *folio) +{ + if (folio_put_testzero(folio)) + __put_page(&folio->page); +} + static inline void put_page(struct page *page) { - page = compound_head(page); + struct folio *folio = page_folio(page); /* * For devmap managed pages we need to catch refcount transition from @@ -1238,13 +1279,12 @@ static inline void put_page(struct page *page) * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ - if (page_is_devmap_managed(page)) { - put_devmap_managed_page(page); + if (page_is_devmap_managed(&folio->page)) { + put_devmap_managed_page(&folio->page); return; } - if (put_page_testzero(page)) - __put_page(page); + folio_put(folio); } /* @@ -1379,6 +1419,11 @@ static inline int page_to_nid(const struct page *page) } #endif +static inline int folio_nid(const struct folio *folio) +{ + return page_to_nid(&folio->page); +} + #ifdef CONFIG_NUMA_BALANCING static inline int cpu_pid_to_cpupid(int cpu, int pid) { @@ -1546,6 +1591,16 @@ static inline pg_data_t *page_pgdat(const struct page *page) return NODE_DATA(page_to_nid(page)); } +static inline struct zone *folio_zone(const struct folio *folio) +{ + return page_zone(&folio->page); +} + +static inline pg_data_t *folio_pgdat(const struct folio *folio) +{ + return page_pgdat(&folio->page); +} + #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { @@ -1559,6 +1614,20 @@ static inline unsigned long page_to_section(const struct page *page) } #endif +/** + * folio_pfn - Return the Page Frame Number of a folio. + * @folio: The folio. + * + * A folio may contain multiple pages. The pages have consecutive + * Page Frame Numbers. + * + * Return: The Page Frame Number of the first page in the folio. + */ +static inline unsigned long folio_pfn(struct folio *folio) +{ + return page_to_pfn(&folio->page); +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) @@ -1595,6 +1664,89 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } +/** + * folio_nr_pages - The number of pages in the folio. + * @folio: The folio. + * + * Return: A positive power of two. + */ +static inline long folio_nr_pages(struct folio *folio) +{ + return compound_nr(&folio->page); +} + +/** + * folio_next - Move to the next physical folio. + * @folio: The folio we're currently operating on. + * + * If you have physically contiguous memory which may span more than + * one folio (eg a &struct bio_vec), use this function to move from one + * folio to the next. Do not use it if the memory is only virtually + * contiguous as the folios are almost certainly not adjacent to each + * other. This is the folio equivalent to writing ``page++``. + * + * Context: We assume that the folios are refcounted and/or locked at a + * higher level and do not adjust the reference counts. + * Return: The next struct folio. + */ +static inline struct folio *folio_next(struct folio *folio) +{ + return (struct folio *)folio_page(folio, folio_nr_pages(folio)); +} + +/** + * folio_shift - The size of the memory described by this folio. + * @folio: The folio. + * + * A folio represents a number of bytes which is a power-of-two in size. + * This function tells you which power-of-two the folio is. See also + * folio_size() and folio_order(). + * + * Context: The caller should have a reference on the folio to prevent + * it from being split. It is not necessary for the folio to be locked. + * Return: The base-2 logarithm of the size of this folio. + */ +static inline unsigned int folio_shift(struct folio *folio) +{ + return PAGE_SHIFT + folio_order(folio); +} + +/** + * folio_size - The number of bytes in a folio. + * @folio: The folio. + * + * Context: The caller should have a reference on the folio to prevent + * it from being split. It is not necessary for the folio to be locked. + * Return: The number of bytes in this folio. + */ +static inline size_t folio_size(struct folio *folio) +{ + return PAGE_SIZE << folio_order(folio); +} + +#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE +static inline int arch_make_page_accessible(struct page *page) +{ + return 0; +} +#endif + +#ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE +static inline int arch_make_folio_accessible(struct folio *folio) +{ + int ret; + long i, nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) { + ret = arch_make_page_accessible(folio_page(folio, i)); + if (ret) + break; + } + + return ret; +} +#endif + /* * Some inline functions in vmstat.h depend on page_zone() */ @@ -1635,19 +1787,6 @@ void page_address_init(void); extern void *page_rmapping(struct page *page); extern struct anon_vma *page_anon_vma(struct page *page); -extern struct address_space *page_mapping(struct page *page); - -extern struct address_space *__page_file_mapping(struct page *); - -static inline -struct address_space *page_file_mapping(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return __page_file_mapping(page); - - return page->mapping; -} - extern pgoff_t __page_file_index(struct page *page); /* @@ -1662,7 +1801,7 @@ static inline pgoff_t page_index(struct page *page) } bool page_mapped(struct page *page); -struct address_space *page_mapping(struct page *page); +bool folio_mapped(struct folio *folio); /* * Return true only if the page has been allocated with @@ -1700,6 +1839,7 @@ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) +#define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* * Flags passed to show_mem() and show_free_areas() to suppress output in @@ -1854,20 +1994,9 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); -int redirty_page_for_writepage(struct writeback_control *wbc, - struct page *page); -void account_page_cleaned(struct page *page, struct address_space *mapping, - struct bdi_writeback *wb); -int set_page_dirty(struct page *page); +bool folio_mark_dirty(struct folio *folio); +bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); -void __cancel_dirty_page(struct page *page); -static inline void cancel_dirty_page(struct page *page) -{ - /* Avoid atomic ops, locking, etc. when not actually needed. */ - if (PageDirty(page)) - __cancel_dirty_page(page); -} -int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); @@ -2659,10 +2788,6 @@ extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); -/* mm/page-writeback.c */ -int __must_check write_one_page(struct page *page); -void task_dirty_inc(struct task_struct *tsk); - extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 355ea1ee32bd..e2ec68b0515c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -6,27 +6,33 @@ #include <linux/swap.h> /** - * page_is_file_lru - should the page be on a file LRU or anon LRU? - * @page: the page to test - * - * Returns 1 if @page is a regular filesystem backed page cache page or a lazily - * freed anonymous page (e.g. via MADV_FREE). Returns 0 if @page is a normal - * anonymous page, a tmpfs page or otherwise ram or swap backed page. Used by - * functions that manipulate the LRU lists, to sort a page onto the right LRU - * list. + * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? + * @folio: The folio to test. * * We would like to get this info without a page flag, but the state - * needs to survive until the page is last deleted from the LRU, which + * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. + * + * Return: An integer (not a boolean!) used to sort a folio onto the + * right LRU list and to account folios correctly. + * 1 if @folio is a regular filesystem backed page cache folio + * or a lazily freed anonymous folio (e.g. via MADV_FREE). + * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise + * ram or swap backed folio. */ +static inline int folio_is_file_lru(struct folio *folio) +{ + return !folio_test_swapbacked(folio); +} + static inline int page_is_file_lru(struct page *page) { - return !PageSwapBacked(page); + return folio_is_file_lru(page_folio(page)); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, - int nr_pages) + long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); @@ -39,69 +45,94 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, } /** - * __clear_page_lru_flags - clear page lru flags before releasing a page - * @page: the page that was on lru and now has a zero reference + * __folio_clear_lru_flags - Clear page lru flags before releasing a page. + * @folio: The folio that was on lru and now has a zero reference. */ -static __always_inline void __clear_page_lru_flags(struct page *page) +static __always_inline void __folio_clear_lru_flags(struct folio *folio) { - VM_BUG_ON_PAGE(!PageLRU(page), page); + VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); - __ClearPageLRU(page); + __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ - if (PageActive(page) && PageUnevictable(page)) + if (folio_test_active(folio) && folio_test_unevictable(folio)) return; - __ClearPageActive(page); - __ClearPageUnevictable(page); + __folio_clear_active(folio); + __folio_clear_unevictable(folio); +} + +static __always_inline void __clear_page_lru_flags(struct page *page) +{ + __folio_clear_lru_flags(page_folio(page)); } /** - * page_lru - which LRU list should a page be on? - * @page: the page to test + * folio_lru_list - Which LRU list should a folio be on? + * @folio: The folio to test. * - * Returns the LRU list a page should be on, as an index + * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ -static __always_inline enum lru_list page_lru(struct page *page) +static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; - VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); + VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); - if (PageUnevictable(page)) + if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; - lru = page_is_file_lru(page) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; - if (PageActive(page)) + lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; + if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } +static __always_inline +void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) +{ + enum lru_list lru = folio_lru_list(folio); + + update_lru_size(lruvec, lru, folio_zonenum(folio), + folio_nr_pages(folio)); + list_add(&folio->lru, &lruvec->lists[lru]); +} + static __always_inline void add_page_to_lru_list(struct page *page, struct lruvec *lruvec) { - enum lru_list lru = page_lru(page); + lruvec_add_folio(lruvec, page_folio(page)); +} - update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); - list_add(&page->lru, &lruvec->lists[lru]); +static __always_inline +void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) +{ + enum lru_list lru = folio_lru_list(folio); + + update_lru_size(lruvec, lru, folio_zonenum(folio), + folio_nr_pages(folio)); + list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void add_page_to_lru_list_tail(struct page *page, struct lruvec *lruvec) { - enum lru_list lru = page_lru(page); + lruvec_add_folio_tail(lruvec, page_folio(page)); +} - update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); - list_add_tail(&page->lru, &lruvec->lists[lru]); +static __always_inline +void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) +{ + list_del(&folio->lru); + update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio), + -folio_nr_pages(folio)); } static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec) { - list_del(&page->lru); - update_lru_size(lruvec, page_lru(page), page_zonenum(page), - -thp_nr_pages(page)); + lruvec_del_folio(lruvec, page_folio(page)); } #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..82dab23205c3 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -239,6 +239,72 @@ struct page { #endif } _struct_page_alignment; +/** + * struct folio - Represents a contiguous set of bytes. + * @flags: Identical to the page flags. + * @lru: Least Recently Used list; tracks how recently this folio was used. + * @mapping: The file this page belongs to, or refers to the anon_vma for + * anonymous memory. + * @index: Offset within the file, in units of pages. For anonymous memory, + * this is the index from the beginning of the mmap. + * @private: Filesystem per-folio data (see folio_attach_private()). + * Used for swp_entry_t if folio_test_swapcache(). + * @_mapcount: Do not access this member directly. Use folio_mapcount() to + * find out how many times this folio is mapped by userspace. + * @_refcount: Do not access this member directly. Use folio_ref_count() + * to find how many references there are to this folio. + * @memcg_data: Memory Control Group data. + * + * A folio is a physically, virtually and logically contiguous set + * of bytes. It is a power-of-two in size, and it is aligned to that + * same power-of-two. It is at least as large as %PAGE_SIZE. If it is + * in the page cache, it is at a file offset which is a multiple of that + * power-of-two. It may be mapped into userspace at an address which is + * at an arbitrary page offset, but its kernel virtual address is aligned + * to its size. + */ +struct folio { + /* private: don't document the anon union */ + union { + struct { + /* public: */ + unsigned long flags; + struct list_head lru; + struct address_space *mapping; + pgoff_t index; + void *private; + atomic_t _mapcount; + atomic_t _refcount; +#ifdef CONFIG_MEMCG + unsigned long memcg_data; +#endif + /* private: the union with struct page is transitional */ + }; + struct page page; + }; +}; + +static_assert(sizeof(struct page) == sizeof(struct folio)); +#define FOLIO_MATCH(pg, fl) \ + static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) +FOLIO_MATCH(flags, flags); +FOLIO_MATCH(lru, lru); +FOLIO_MATCH(compound_head, lru); +FOLIO_MATCH(index, index); +FOLIO_MATCH(private, private); +FOLIO_MATCH(_mapcount, _mapcount); +FOLIO_MATCH(_refcount, _refcount); +#ifdef CONFIG_MEMCG +FOLIO_MATCH(memcg_data, memcg_data); +#endif +#undef FOLIO_MATCH + +static inline atomic_t *folio_mapcount_ptr(struct folio *folio) +{ + struct page *tail = &folio->page + 1; + return &tail->compound_mapcount; +} + static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; @@ -257,6 +323,12 @@ static inline atomic_t *compound_pincount_ptr(struct page *page) #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +/* + * page_private can be used on tail pages. However, PagePrivate is only + * checked by the VM on the head page. So page_private on the tail pages + * should be used for data that's ancillary to the head page (eg attaching + * buffer heads to tail pages after attaching buffer heads to the head page) + */ #define page_private(page) ((page)->private) static inline void set_page_private(struct page *page, unsigned long private) @@ -264,6 +336,11 @@ static inline void set_page_private(struct page *page, unsigned long private) page->private = private; } +static inline void *folio_get_private(struct folio *folio) +{ + return folio->private; +} + struct page_frag_cache { void * va; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 1935d4c72d10..d7285f8148a3 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -22,6 +22,13 @@ void dump_mm(const struct mm_struct *mm); BUG(); \ } \ } while (0) +#define VM_BUG_ON_FOLIO(cond, folio) \ + do { \ + if (unlikely(cond)) { \ + dump_page(&folio->page, "VM_BUG_ON_FOLIO(" __stringify(cond)")");\ + BUG(); \ + } \ + } while (0) #define VM_BUG_ON_VMA(cond, vma) \ do { \ if (unlikely(cond)) { \ @@ -47,6 +54,17 @@ void dump_mm(const struct mm_struct *mm); } \ unlikely(__ret_warn_once); \ }) +#define VM_WARN_ON_ONCE_FOLIO(cond, folio) ({ \ + static bool __section(".data.once") __warned; \ + int __ret_warn_once = !!(cond); \ + \ + if (unlikely(__ret_warn_once && !__warned)) { \ + dump_page(&folio->page, "VM_WARN_ON_ONCE_FOLIO(" __stringify(cond)")");\ + __warned = true; \ + WARN_ON(1); \ + } \ + unlikely(__ret_warn_once); \ +}) #define VM_WARN_ON(cond) (void)WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) @@ -55,11 +73,13 @@ void dump_mm(const struct mm_struct *mm); #else #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond) +#define VM_BUG_ON_FOLIO(cond, folio) VM_BUG_ON(cond) #define VM_BUG_ON_VMA(cond, vma) VM_BUG_ON(cond) #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond) #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_ONCE_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5d6a4158a9a6..12c4177f7703 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -22,6 +22,7 @@ * Overload PG_private_2 to give us PG_fscache - this is used to indicate that * a page is currently backed by a local disk cache */ +#define folio_test_fscache(folio) folio_test_private_2(folio) #define PageFsCache(page) PagePrivate2((page)) #define SetPageFsCache(page) SetPagePrivate2((page)) #define ClearPageFsCache(page) ClearPagePrivate2((page)) @@ -29,60 +30,80 @@ #define TestClearPageFsCache(page) TestClearPagePrivate2((page)) /** - * set_page_fscache - Set PG_fscache on a page and take a ref - * @page: The page. + * folio_start_fscache - Start an fscache write on a folio. + * @folio: The folio. * - * Set the PG_fscache (PG_private_2) flag on a page and take the reference - * needed for the VM to handle its lifetime correctly. This sets the flag and - * takes the reference unconditionally, so care must be taken not to set the - * flag again if it's already set. + * Call this function before writing a folio to a local cache. Starting a + * second write before the first one finishes is not allowed. */ -static inline void set_page_fscache(struct page *page) +static inline void folio_start_fscache(struct folio *folio) { - set_page_private_2(page); + VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio); + folio_get(folio); + folio_set_private_2(folio); } /** - * end_page_fscache - Clear PG_fscache and release any waiters - * @page: The page - * - * Clear the PG_fscache (PG_private_2) bit on a page and wake up any sleepers - * waiting for this. The page ref held for PG_private_2 being set is released. + * folio_end_fscache - End an fscache write on a folio. + * @folio: The folio. * - * This is, for example, used when a netfs page is being written to a local - * disk cache, thereby allowing writes to the cache for the same page to be - * serialised. + * Call this function after the folio has been written to the local cache. + * This will wake any sleepers waiting on this folio. */ -static inline void end_page_fscache(struct page *page) +static inline void folio_end_fscache(struct folio *folio) { - end_page_private_2(page); + folio_end_private_2(folio); } /** - * wait_on_page_fscache - Wait for PG_fscache to be cleared on a page - * @page: The page to wait on + * folio_wait_fscache - Wait for an fscache write on this folio to end. + * @folio: The folio. * - * Wait for PG_fscache (aka PG_private_2) to be cleared on a page. + * If this folio is currently being written to a local cache, wait for + * the write to finish. Another write may start after this one finishes, + * unless the caller holds the folio lock. */ -static inline void wait_on_page_fscache(struct page *page) +static inline void folio_wait_fscache(struct folio *folio) { - wait_on_page_private_2(page); + folio_wait_private_2(folio); } /** - * wait_on_page_fscache_killable - Wait for PG_fscache to be cleared on a page - * @page: The page to wait on + * folio_wait_fscache_killable - Wait for an fscache write on this folio to end. + * @folio: The folio. * - * Wait for PG_fscache (aka PG_private_2) to be cleared on a page or until a - * fatal signal is received by the calling task. + * If this folio is currently being written to a local cache, wait + * for the write to finish or for a fatal signal to be received. + * Another write may start after this one finishes, unless the caller + * holds the folio lock. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ +static inline int folio_wait_fscache_killable(struct folio *folio) +{ + return folio_wait_private_2_killable(folio); +} + +static inline void set_page_fscache(struct page *page) +{ + folio_start_fscache(page_folio(page)); +} + +static inline void end_page_fscache(struct page *page) +{ + folio_end_private_2(page_folio(page)); +} + +static inline void wait_on_page_fscache(struct page *page) +{ + folio_wait_private_2(page_folio(page)); +} + static inline int wait_on_page_fscache_killable(struct page *page) { - return wait_on_page_private_2_killable(page); + return folio_wait_private_2_killable(page_folio(page)); } enum netfs_read_source { diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a558d67ee86f..d8623d6e1141 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -143,6 +143,8 @@ enum pageflags { #endif __NR_PAGEFLAGS, + PG_readahead = PG_reclaim, + /* Filesystems */ PG_checked = PG_owner_priv_1, @@ -171,6 +173,15 @@ enum pageflags { /* Compound pages. Stored in first tail page's flags */ PG_double_map = PG_workingset, +#ifdef CONFIG_MEMORY_FAILURE + /* + * Compound pages. Stored in first tail page's flags. + * Indicates that at least one subpage is hwpoisoned in the + * THP. + */ + PG_has_hwpoisoned = PG_mappedtodisk, +#endif + /* non-lru isolated movable page */ PG_isolated = PG_reclaim, @@ -193,6 +204,34 @@ static inline unsigned long _compound_head(const struct page *page) #define compound_head(page) ((typeof(page))_compound_head(page)) +/** + * page_folio - Converts from page to folio. + * @p: The page. + * + * Every page is part of a folio. This function cannot be called on a + * NULL pointer. + * + * Context: No reference, nor lock is required on @page. If the caller + * does not hold a reference, this call may race with a folio split, so + * it should re-check the folio still contains this page after gaining + * a reference on the folio. + * Return: The folio which contains this page. + */ +#define page_folio(p) (_Generic((p), \ + const struct page *: (const struct folio *)_compound_head(p), \ + struct page *: (struct folio *)_compound_head(p))) + +/** + * folio_page - Return a page from a folio. + * @folio: The folio. + * @n: The page number to return. + * + * @n is relative to the start of the folio. This function does not + * check that the page number lies within @folio; the caller is presumed + * to have a reference to the page. + */ +#define folio_page(folio, n) nth_page(&(folio)->page, n) + static __always_inline int PageTail(struct page *page) { return READ_ONCE(page->compound_head) & 1; @@ -217,6 +256,15 @@ static inline void page_init_poison(struct page *page, size_t size) } #endif +static unsigned long *folio_flags(struct folio *folio, unsigned n) +{ + struct page *page = &folio->page; + + VM_BUG_ON_PGFLAGS(PageTail(page), page); + VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); + return &page[n].flags; +} + /* * Page flags policies wrt compound pages * @@ -261,36 +309,64 @@ static inline void page_init_poison(struct page *page, size_t size) VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) +/* Which page is the flag stored in */ +#define FOLIO_PF_ANY 0 +#define FOLIO_PF_HEAD 0 +#define FOLIO_PF_ONLY_HEAD 0 +#define FOLIO_PF_NO_TAIL 0 +#define FOLIO_PF_NO_COMPOUND 0 +#define FOLIO_PF_SECOND 1 + /* * Macros to create function definitions for page flags */ #define TESTPAGEFLAG(uname, lname, policy) \ +static __always_inline bool folio_test_##lname(struct folio *folio) \ +{ return test_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline int Page##uname(struct page *page) \ - { return test_bit(PG_##lname, &policy(page, 0)->flags); } +{ return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ +static __always_inline \ +void folio_set_##lname(struct folio *folio) \ +{ set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline void SetPage##uname(struct page *page) \ - { set_bit(PG_##lname, &policy(page, 1)->flags); } +{ set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ +static __always_inline \ +void folio_clear_##lname(struct folio *folio) \ +{ clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline void ClearPage##uname(struct page *page) \ - { clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ +static __always_inline \ +void __folio_set_##lname(struct folio *folio) \ +{ __set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline void __SetPage##uname(struct page *page) \ - { __set_bit(PG_##lname, &policy(page, 1)->flags); } +{ __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ +static __always_inline \ +void __folio_clear_##lname(struct folio *folio) \ +{ __clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline void __ClearPage##uname(struct page *page) \ - { __clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ +static __always_inline \ +bool folio_test_set_##lname(struct folio *folio) \ +{ return test_and_set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline int TestSetPage##uname(struct page *page) \ - { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } +{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ +static __always_inline \ +bool folio_test_clear_##lname(struct folio *folio) \ +{ return test_and_clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline int TestClearPage##uname(struct page *page) \ - { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ @@ -306,29 +382,37 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) -#define TESTPAGEFLAG_FALSE(uname) \ +#define TESTPAGEFLAG_FALSE(uname, lname) \ +static inline bool folio_test_##lname(const struct folio *folio) { return 0; } \ static inline int Page##uname(const struct page *page) { return 0; } -#define SETPAGEFLAG_NOOP(uname) \ +#define SETPAGEFLAG_NOOP(uname, lname) \ +static inline void folio_set_##lname(struct folio *folio) { } \ static inline void SetPage##uname(struct page *page) { } -#define CLEARPAGEFLAG_NOOP(uname) \ +#define CLEARPAGEFLAG_NOOP(uname, lname) \ +static inline void folio_clear_##lname(struct folio *folio) { } \ static inline void ClearPage##uname(struct page *page) { } -#define __CLEARPAGEFLAG_NOOP(uname) \ +#define __CLEARPAGEFLAG_NOOP(uname, lname) \ +static inline void __folio_clear_##lname(struct folio *folio) { } \ static inline void __ClearPage##uname(struct page *page) { } -#define TESTSETFLAG_FALSE(uname) \ +#define TESTSETFLAG_FALSE(uname, lname) \ +static inline bool folio_test_set_##lname(struct folio *folio) \ +{ return 0; } \ static inline int TestSetPage##uname(struct page *page) { return 0; } -#define TESTCLEARFLAG_FALSE(uname) \ +#define TESTCLEARFLAG_FALSE(uname, lname) \ +static inline bool folio_test_clear_##lname(struct folio *folio) \ +{ return 0; } \ static inline int TestClearPage##uname(struct page *page) { return 0; } -#define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \ - SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname) +#define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ + SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname) -#define TESTSCFLAG_FALSE(uname) \ - TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) +#define TESTSCFLAG_FALSE(uname, lname) \ + TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) @@ -384,8 +468,8 @@ PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) -PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) - TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) +PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND) + TESTCLEARFLAG(Readahead, readahead, PF_NO_COMPOUND) #ifdef CONFIG_HIGHMEM /* @@ -394,22 +478,25 @@ PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #else -PAGEFLAG_FALSE(HighMem) +PAGEFLAG_FALSE(HighMem, highmem) #endif #ifdef CONFIG_SWAP -static __always_inline int PageSwapCache(struct page *page) +static __always_inline bool folio_test_swapcache(struct folio *folio) { -#ifdef CONFIG_THP_SWAP - page = compound_head(page); -#endif - return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags); + return folio_test_swapbacked(folio) && + test_bit(PG_swapcache, folio_flags(folio, 0)); +} +static __always_inline bool PageSwapCache(struct page *page) +{ + return folio_test_swapcache(page_folio(page)); } + SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) #else -PAGEFLAG_FALSE(SwapCache) +PAGEFLAG_FALSE(SwapCache, swapcache) #endif PAGEFLAG(Unevictable, unevictable, PF_HEAD) @@ -421,14 +508,14 @@ PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) #else -PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) - TESTSCFLAG_FALSE(Mlocked) +PAGEFLAG_FALSE(Mlocked, mlocked) __CLEARPAGEFLAG_NOOP(Mlocked, mlocked) + TESTSCFLAG_FALSE(Mlocked, mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) #else -PAGEFLAG_FALSE(Uncached) +PAGEFLAG_FALSE(Uncached, uncached) #endif #ifdef CONFIG_MEMORY_FAILURE @@ -437,7 +524,7 @@ TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) extern bool take_page_off_buddy(struct page *page); #else -PAGEFLAG_FALSE(HWPoison) +PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif @@ -451,7 +538,7 @@ PAGEFLAG(Idle, idle, PF_ANY) #ifdef CONFIG_KASAN_HW_TAGS PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD) #else -PAGEFLAG_FALSE(SkipKASanPoison) +PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) #endif /* @@ -489,10 +576,14 @@ static __always_inline int PageMappingFlags(struct page *page) return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } -static __always_inline int PageAnon(struct page *page) +static __always_inline bool folio_test_anon(struct folio *folio) +{ + return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; +} + +static __always_inline bool PageAnon(struct page *page) { - page = compound_head(page); - return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; + return folio_test_anon(page_folio(page)); } static __always_inline int __PageMovable(struct page *page) @@ -508,30 +599,32 @@ static __always_inline int __PageMovable(struct page *page) * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ -static __always_inline int PageKsm(struct page *page) +static __always_inline bool folio_test_ksm(struct folio *folio) { - page = compound_head(page); - return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == + return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } + +static __always_inline bool PageKsm(struct page *page) +{ + return folio_test_ksm(page_folio(page)); +} #else -TESTPAGEFLAG_FALSE(Ksm) +TESTPAGEFLAG_FALSE(Ksm, ksm) #endif u64 stable_page_flags(struct page *page); -static inline int PageUptodate(struct page *page) +static inline bool folio_test_uptodate(struct folio *folio) { - int ret; - page = compound_head(page); - ret = test_bit(PG_uptodate, &(page)->flags); + bool ret = test_bit(PG_uptodate, folio_flags(folio, 0)); /* - * Must ensure that the data we read out of the page is loaded - * _after_ we've loaded page->flags to check for PageUptodate. - * We can skip the barrier if the page is not uptodate, because + * Must ensure that the data we read out of the folio is loaded + * _after_ we've loaded folio->flags to check the uptodate bit. + * We can skip the barrier if the folio is not uptodate, because * we wouldn't be reading anything from it. * - * See SetPageUptodate() for the other side of the story. + * See folio_mark_uptodate() for the other side of the story. */ if (ret) smp_rmb(); @@ -539,47 +632,71 @@ static inline int PageUptodate(struct page *page) return ret; } -static __always_inline void __SetPageUptodate(struct page *page) +static inline int PageUptodate(struct page *page) +{ + return folio_test_uptodate(page_folio(page)); +} + +static __always_inline void __folio_mark_uptodate(struct folio *folio) { - VM_BUG_ON_PAGE(PageTail(page), page); smp_wmb(); - __set_bit(PG_uptodate, &page->flags); + __set_bit(PG_uptodate, folio_flags(folio, 0)); } -static __always_inline void SetPageUptodate(struct page *page) +static __always_inline void folio_mark_uptodate(struct folio *folio) { - VM_BUG_ON_PAGE(PageTail(page), page); /* * Memory barrier must be issued before setting the PG_uptodate bit, - * so that all previous stores issued in order to bring the page - * uptodate are actually visible before PageUptodate becomes true. + * so that all previous stores issued in order to bring the folio + * uptodate are actually visible before folio_test_uptodate becomes true. */ smp_wmb(); - set_bit(PG_uptodate, &page->flags); + set_bit(PG_uptodate, folio_flags(folio, 0)); +} + +static __always_inline void __SetPageUptodate(struct page *page) +{ + __folio_mark_uptodate((struct folio *)page); +} + +static __always_inline void SetPageUptodate(struct page *page) +{ + folio_mark_uptodate((struct folio *)page); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) -int test_clear_page_writeback(struct page *page); -int __test_set_page_writeback(struct page *page, bool keep_write); +bool __folio_start_writeback(struct folio *folio, bool keep_write); +bool set_page_writeback(struct page *page); -#define test_set_page_writeback(page) \ - __test_set_page_writeback(page, false) -#define test_set_page_writeback_keepwrite(page) \ - __test_set_page_writeback(page, true) +#define folio_start_writeback(folio) \ + __folio_start_writeback(folio, false) +#define folio_start_writeback_keepwrite(folio) \ + __folio_start_writeback(folio, true) -static inline void set_page_writeback(struct page *page) +static inline void set_page_writeback_keepwrite(struct page *page) { - test_set_page_writeback(page); + folio_start_writeback_keepwrite(page_folio(page)); } -static inline void set_page_writeback_keepwrite(struct page *page) +static inline bool test_set_page_writeback(struct page *page) { - test_set_page_writeback_keepwrite(page); + return set_page_writeback(page); } __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) +/* Whether there are one or multiple pages in a folio */ +static inline bool folio_test_single(struct folio *folio) +{ + return !folio_test_head(folio); +} + +static inline bool folio_test_multi(struct folio *folio) +{ + return folio_test_head(folio); +} + static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); @@ -603,12 +720,15 @@ static inline void ClearPageCompound(struct page *page) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); int PageHeadHuge(struct page *page); +static inline bool folio_test_hugetlb(struct folio *folio) +{ + return PageHeadHuge(&folio->page); +} #else -TESTPAGEFLAG_FALSE(Huge) -TESTPAGEFLAG_FALSE(HeadHuge) +TESTPAGEFLAG_FALSE(Huge, hugetlb) +TESTPAGEFLAG_FALSE(HeadHuge, headhuge) #endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -624,6 +744,11 @@ static inline int PageTransHuge(struct page *page) return PageHead(page); } +static inline bool folio_test_transhuge(struct folio *folio) +{ + return folio_test_head(folio); +} + /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known @@ -660,12 +785,26 @@ static inline int PageTransTail(struct page *page) PAGEFLAG(DoubleMap, double_map, PF_SECOND) TESTSCFLAG(DoubleMap, double_map, PF_SECOND) #else -TESTPAGEFLAG_FALSE(TransHuge) -TESTPAGEFLAG_FALSE(TransCompound) -TESTPAGEFLAG_FALSE(TransCompoundMap) -TESTPAGEFLAG_FALSE(TransTail) -PAGEFLAG_FALSE(DoubleMap) - TESTSCFLAG_FALSE(DoubleMap) +TESTPAGEFLAG_FALSE(TransHuge, transhuge) +TESTPAGEFLAG_FALSE(TransCompound, transcompound) +TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap) +TESTPAGEFLAG_FALSE(TransTail, transtail) +PAGEFLAG_FALSE(DoubleMap, double_map) + TESTSCFLAG_FALSE(DoubleMap, double_map) +#endif + +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +/* + * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the + * compound page. + * + * This flag is set by hwpoison handler. Cleared by THP split or free page. + */ +PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) + TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) +#else +PAGEFLAG_FALSE(HasHWPoisoned) + TESTSCFLAG_FALSE(HasHWPoisoned) #endif /* @@ -849,6 +988,11 @@ static inline int page_has_private(struct page *page) return !!(page->flags & PAGE_FLAGS_PRIVATE); } +static inline bool folio_has_private(struct folio *folio) +{ + return page_has_private(&folio->page); +} + #undef PF_ANY #undef PF_HEAD #undef PF_ONLY_HEAD diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index d8a6aecf99cb..83abf95e9fa7 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -8,46 +8,16 @@ #ifdef CONFIG_PAGE_IDLE_FLAG -#ifdef CONFIG_64BIT -static inline bool page_is_young(struct page *page) -{ - return PageYoung(page); -} - -static inline void set_page_young(struct page *page) -{ - SetPageYoung(page); -} - -static inline bool test_and_clear_page_young(struct page *page) -{ - return TestClearPageYoung(page); -} - -static inline bool page_is_idle(struct page *page) -{ - return PageIdle(page); -} - -static inline void set_page_idle(struct page *page) -{ - SetPageIdle(page); -} - -static inline void clear_page_idle(struct page *page) -{ - ClearPageIdle(page); -} -#else /* !CONFIG_64BIT */ +#ifndef CONFIG_64BIT /* * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ extern struct page_ext_operations page_idle_ops; -static inline bool page_is_young(struct page *page) +static inline bool folio_test_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return false; @@ -55,9 +25,9 @@ static inline bool page_is_young(struct page *page) return test_bit(PAGE_EXT_YOUNG, &page_ext->flags); } -static inline void set_page_young(struct page *page) +static inline void folio_set_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return; @@ -65,9 +35,9 @@ static inline void set_page_young(struct page *page) set_bit(PAGE_EXT_YOUNG, &page_ext->flags); } -static inline bool test_and_clear_page_young(struct page *page) +static inline bool folio_test_clear_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return false; @@ -75,9 +45,9 @@ static inline bool test_and_clear_page_young(struct page *page) return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); } -static inline bool page_is_idle(struct page *page) +static inline bool folio_test_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return false; @@ -85,9 +55,9 @@ static inline bool page_is_idle(struct page *page) return test_bit(PAGE_EXT_IDLE, &page_ext->flags); } -static inline void set_page_idle(struct page *page) +static inline void folio_set_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return; @@ -95,46 +65,75 @@ static inline void set_page_idle(struct page *page) set_bit(PAGE_EXT_IDLE, &page_ext->flags); } -static inline void clear_page_idle(struct page *page) +static inline void folio_clear_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return; clear_bit(PAGE_EXT_IDLE, &page_ext->flags); } -#endif /* CONFIG_64BIT */ +#endif /* !CONFIG_64BIT */ #else /* !CONFIG_PAGE_IDLE_FLAG */ -static inline bool page_is_young(struct page *page) +static inline bool folio_test_young(struct folio *folio) { return false; } -static inline void set_page_young(struct page *page) +static inline void folio_set_young(struct folio *folio) { } -static inline bool test_and_clear_page_young(struct page *page) +static inline bool folio_test_clear_young(struct folio *folio) { return false; } -static inline bool page_is_idle(struct page *page) +static inline bool folio_test_idle(struct folio *folio) { return false; } -static inline void set_page_idle(struct page *page) +static inline void folio_set_idle(struct folio *folio) { } -static inline void clear_page_idle(struct page *page) +static inline void folio_clear_idle(struct folio *folio) { } #endif /* CONFIG_PAGE_IDLE_FLAG */ +static inline bool page_is_young(struct page *page) +{ + return folio_test_young(page_folio(page)); +} + +static inline void set_page_young(struct page *page) +{ + folio_set_young(page_folio(page)); +} + +static inline bool test_and_clear_page_young(struct page *page) +{ + return folio_test_clear_young(page_folio(page)); +} + +static inline bool page_is_idle(struct page *page) +{ + return folio_test_idle(page_folio(page)); +} + +static inline void set_page_idle(struct page *page) +{ + folio_set_idle(page_folio(page)); +} + +static inline void clear_page_idle(struct page *page) +{ + folio_clear_idle(page_folio(page)); +} #endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 719bfe5108c5..43c638c51c1f 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -12,7 +12,7 @@ extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); extern void __split_page_owner(struct page *page, unsigned int nr); -extern void __copy_page_owner(struct page *oldpage, struct page *newpage); +extern void __folio_copy_owner(struct folio *newfolio, struct folio *old); extern void __set_page_owner_migrate_reason(struct page *page, int reason); extern void __dump_page_owner(const struct page *page); extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, @@ -36,10 +36,10 @@ static inline void split_page_owner(struct page *page, unsigned int nr) if (static_branch_unlikely(&page_owner_inited)) __split_page_owner(page, nr); } -static inline void copy_page_owner(struct page *oldpage, struct page *newpage) +static inline void folio_copy_owner(struct folio *newfolio, struct folio *old) { if (static_branch_unlikely(&page_owner_inited)) - __copy_page_owner(oldpage, newpage); + __folio_copy_owner(newfolio, old); } static inline void set_page_owner_migrate_reason(struct page *page, int reason) { @@ -63,7 +63,7 @@ static inline void split_page_owner(struct page *page, unsigned int order) { } -static inline void copy_page_owner(struct page *oldpage, struct page *newpage) +static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio) { } static inline void set_page_owner_migrate_reason(struct page *page, int reason) diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 7ad46f45df39..2e677e6ad09f 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -67,9 +67,31 @@ static inline int page_ref_count(const struct page *page) return atomic_read(&page->_refcount); } +/** + * folio_ref_count - The reference count on this folio. + * @folio: The folio. + * + * The refcount is usually incremented by calls to folio_get() and + * decremented by calls to folio_put(). Some typical users of the + * folio refcount: + * + * - Each reference from a page table + * - The page cache + * - Filesystem private data + * - The LRU list + * - Pipes + * - Direct IO which references this page in the process address space + * + * Return: The number of references to this folio. + */ +static inline int folio_ref_count(const struct folio *folio) +{ + return page_ref_count(&folio->page); +} + static inline int page_count(const struct page *page) { - return atomic_read(&compound_head(page)->_refcount); + return folio_ref_count(page_folio(page)); } static inline void set_page_count(struct page *page, int v) @@ -79,6 +101,11 @@ static inline void set_page_count(struct page *page, int v) __page_ref_set(page, v); } +static inline void folio_set_count(struct folio *folio, int v) +{ + set_page_count(&folio->page, v); +} + /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) @@ -95,6 +122,11 @@ static inline void page_ref_add(struct page *page, int nr) __page_ref_mod(page, nr); } +static inline void folio_ref_add(struct folio *folio, int nr) +{ + page_ref_add(&folio->page, nr); +} + static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); @@ -102,6 +134,11 @@ static inline void page_ref_sub(struct page *page, int nr) __page_ref_mod(page, -nr); } +static inline void folio_ref_sub(struct folio *folio, int nr) +{ + page_ref_sub(&folio->page, nr); +} + static inline int page_ref_sub_return(struct page *page, int nr) { int ret = atomic_sub_return(nr, &page->_refcount); @@ -111,6 +148,11 @@ static inline int page_ref_sub_return(struct page *page, int nr) return ret; } +static inline int folio_ref_sub_return(struct folio *folio, int nr) +{ + return page_ref_sub_return(&folio->page, nr); +} + static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); @@ -118,6 +160,11 @@ static inline void page_ref_inc(struct page *page) __page_ref_mod(page, 1); } +static inline void folio_ref_inc(struct folio *folio) +{ + page_ref_inc(&folio->page); +} + static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); @@ -125,6 +172,11 @@ static inline void page_ref_dec(struct page *page) __page_ref_mod(page, -1); } +static inline void folio_ref_dec(struct folio *folio) +{ + page_ref_dec(&folio->page); +} + static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); @@ -134,6 +186,11 @@ static inline int page_ref_sub_and_test(struct page *page, int nr) return ret; } +static inline int folio_ref_sub_and_test(struct folio *folio, int nr) +{ + return page_ref_sub_and_test(&folio->page, nr); +} + static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); @@ -143,6 +200,11 @@ static inline int page_ref_inc_return(struct page *page) return ret; } +static inline int folio_ref_inc_return(struct folio *folio) +{ + return page_ref_inc_return(&folio->page); +} + static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); @@ -152,6 +214,11 @@ static inline int page_ref_dec_and_test(struct page *page) return ret; } +static inline int folio_ref_dec_and_test(struct folio *folio) +{ + return page_ref_dec_and_test(&folio->page); +} + static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); @@ -161,15 +228,91 @@ static inline int page_ref_dec_return(struct page *page) return ret; } -static inline int page_ref_add_unless(struct page *page, int nr, int u) +static inline int folio_ref_dec_return(struct folio *folio) +{ + return page_ref_dec_return(&folio->page); +} + +static inline bool page_ref_add_unless(struct page *page, int nr, int u) { - int ret = atomic_add_unless(&page->_refcount, nr, u); + bool ret = atomic_add_unless(&page->_refcount, nr, u); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } +static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u) +{ + return page_ref_add_unless(&folio->page, nr, u); +} + +/** + * folio_try_get - Attempt to increase the refcount on a folio. + * @folio: The folio. + * + * If you do not already have a reference to a folio, you can attempt to + * get one using this function. It may fail if, for example, the folio + * has been freed since you found a pointer to it, or it is frozen for + * the purposes of splitting or migration. + * + * Return: True if the reference count was successfully incremented. + */ +static inline bool folio_try_get(struct folio *folio) +{ + return folio_ref_add_unless(folio, 1, 0); +} + +static inline bool folio_ref_try_add_rcu(struct folio *folio, int count) +{ +#ifdef CONFIG_TINY_RCU + /* + * The caller guarantees the folio will not be freed from interrupt + * context, so (on !SMP) we only need preemption to be disabled + * and TINY_RCU does that for us. + */ +# ifdef CONFIG_PREEMPT_COUNT + VM_BUG_ON(!in_atomic() && !irqs_disabled()); +# endif + VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio); + folio_ref_add(folio, count); +#else + if (unlikely(!folio_ref_add_unless(folio, count, 0))) { + /* Either the folio has been freed, or will be freed. */ + return false; + } +#endif + return true; +} + +/** + * folio_try_get_rcu - Attempt to increase the refcount on a folio. + * @folio: The folio. + * + * This is a version of folio_try_get() optimised for non-SMP kernels. + * If you are still holding the rcu_read_lock() after looking up the + * page and know that the page cannot have its refcount decreased to + * zero in interrupt context, you can use this instead of folio_try_get(). + * + * Example users include get_user_pages_fast() (as pages are not unmapped + * from interrupt context) and the page cache lookups (as pages are not + * truncated from interrupt context). We also know that pages are not + * frozen in interrupt context for the purposes of splitting or migration. + * + * You can also use this function if you're holding a lock that prevents + * pages being frozen & removed; eg the i_pages lock for the page cache + * or the mmap_sem or page table lock for page tables. In this case, + * it will always succeed, and you could have used a plain folio_get(), + * but it's sometimes more convenient to have a common function called + * from both locked and RCU-protected contexts. + * + * Return: True if the reference count was successfully incremented. + */ +static inline bool folio_try_get_rcu(struct folio *folio) +{ + return folio_ref_try_add_rcu(folio, 1); +} + static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); @@ -179,6 +322,11 @@ static inline int page_ref_freeze(struct page *page, int count) return ret; } +static inline int folio_ref_freeze(struct folio *folio, int count) +{ + return page_ref_freeze(&folio->page, count); +} + static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); @@ -189,4 +337,8 @@ static inline void page_ref_unfreeze(struct page *page, int count) __page_ref_unfreeze(page, count); } +static inline void folio_ref_unfreeze(struct folio *folio, int count) +{ + page_ref_unfreeze(&folio->page, count); +} #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 62db6b0176b9..013cdc90f5fd 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -162,149 +162,119 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) void release_pages(struct page **pages, int nr); -/* - * For file cache pages, return the address_space, otherwise return NULL +struct address_space *page_mapping(struct page *); +struct address_space *folio_mapping(struct folio *); +struct address_space *swapcache_mapping(struct folio *); + +/** + * folio_file_mapping - Find the mapping this folio belongs to. + * @folio: The folio. + * + * For folios which are in the page cache, return the mapping that this + * page belongs to. Folios in the swap cache return the mapping of the + * swap file or swap device where the data is stored. This is different + * from the mapping returned by folio_mapping(). The only reason to + * use it is if, like NFS, you return 0 from ->activate_swapfile. + * + * Do not call this for folios which aren't in the page cache or swap cache. */ -static inline struct address_space *page_mapping_file(struct page *page) +static inline struct address_space *folio_file_mapping(struct folio *folio) { - if (unlikely(PageSwapCache(page))) - return NULL; - return page_mapping(page); + if (unlikely(folio_test_swapcache(folio))) + return swapcache_mapping(folio); + + return folio->mapping; +} + +static inline struct address_space *page_file_mapping(struct page *page) +{ + return folio_file_mapping(page_folio(page)); } /* - * speculatively take a reference to a page. - * If the page is free (_refcount == 0), then _refcount is untouched, and 0 - * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned. - * - * This function must be called inside the same rcu_read_lock() section as has - * been used to lookup the page in the pagecache radix-tree (or page table): - * this allows allocators to use a synchronize_rcu() to stabilize _refcount. - * - * Unless an RCU grace period has passed, the count of all pages coming out - * of the allocator must be considered unstable. page_count may return higher - * than expected, and put_page must be able to do the right thing when the - * page has been finished with, no matter what it is subsequently allocated - * for (because put_page is what is used here to drop an invalid speculative - * reference). - * - * This is the interesting part of the lockless pagecache (and lockless - * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page) - * has the following pattern: - * 1. find page in radix tree - * 2. conditionally increment refcount - * 3. check the page is still in pagecache (if no, goto 1) - * - * Remove-side that cares about stability of _refcount (eg. reclaim) has the - * following (with the i_pages lock held): - * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) - * B. remove page from pagecache - * C. free the page - * - * There are 2 critical interleavings that matter: - * - 2 runs before A: in this case, A sees elevated refcount and bails out - * - A runs before 2: in this case, 2 sees zero refcount and retries; - * subsequently, B will complete and 1 will find no page, causing the - * lookup to return NULL. - * - * It is possible that between 1 and 2, the page is removed then the exact same - * page is inserted into the same position in pagecache. That's OK: the - * old find_get_page using a lock could equally have run before or after - * such a re-insertion, depending on order that locks are granted. - * - * Lookups racing against pagecache insertion isn't a big problem: either 1 - * will find the page or it will not. Likewise, the old find_get_page could run - * either before the insertion or afterwards, depending on timing. + * For file cache pages, return the address_space, otherwise return NULL */ -static inline int __page_cache_add_speculative(struct page *page, int count) +static inline struct address_space *page_mapping_file(struct page *page) { -#ifdef CONFIG_TINY_RCU -# ifdef CONFIG_PREEMPT_COUNT - VM_BUG_ON(!in_atomic() && !irqs_disabled()); -# endif - /* - * Preempt must be disabled here - we rely on rcu_read_lock doing - * this for us. - * - * Pagecache won't be truncated from interrupt context, so if we have - * found a page in the radix tree here, we have pinned its refcount by - * disabling preempt, and hence no need for the "speculative get" that - * SMP requires. - */ - VM_BUG_ON_PAGE(page_count(page) == 0, page); - page_ref_add(page, count); + struct folio *folio = page_folio(page); -#else - if (unlikely(!page_ref_add_unless(page, count, 0))) { - /* - * Either the page has been freed, or will be freed. - * In either case, retry here and the caller should - * do the right thing (see comments above). - */ - return 0; - } -#endif - VM_BUG_ON_PAGE(PageTail(page), page); - - return 1; + if (unlikely(folio_test_swapcache(folio))) + return NULL; + return folio_mapping(folio); } -static inline int page_cache_get_speculative(struct page *page) +static inline bool page_cache_add_speculative(struct page *page, int count) { - return __page_cache_add_speculative(page, 1); + VM_BUG_ON_PAGE(PageTail(page), page); + return folio_ref_try_add_rcu((struct folio *)page, count); } -static inline int page_cache_add_speculative(struct page *page, int count) +static inline bool page_cache_get_speculative(struct page *page) { - return __page_cache_add_speculative(page, count); + return page_cache_add_speculative(page, 1); } /** - * attach_page_private - Attach private data to a page. - * @page: Page to attach data to. - * @data: Data to attach to page. + * folio_attach_private - Attach private data to a folio. + * @folio: Folio to attach data to. + * @data: Data to attach to folio. * - * Attaching private data to a page increments the page's reference count. - * The data must be detached before the page will be freed. + * Attaching private data to a folio increments the page's reference count. + * The data must be detached before the folio will be freed. */ -static inline void attach_page_private(struct page *page, void *data) +static inline void folio_attach_private(struct folio *folio, void *data) { - get_page(page); - set_page_private(page, (unsigned long)data); - SetPagePrivate(page); + folio_get(folio); + folio->private = data; + folio_set_private(folio); } /** - * detach_page_private - Detach private data from a page. - * @page: Page to detach data from. + * folio_detach_private - Detach private data from a folio. + * @folio: Folio to detach data from. * - * Removes the data that was previously attached to the page and decrements + * Removes the data that was previously attached to the folio and decrements * the refcount on the page. * - * Return: Data that was attached to the page. + * Return: Data that was attached to the folio. */ -static inline void *detach_page_private(struct page *page) +static inline void *folio_detach_private(struct folio *folio) { - void *data = (void *)page_private(page); + void *data = folio_get_private(folio); - if (!PagePrivate(page)) + if (!folio_test_private(folio)) return NULL; - ClearPagePrivate(page); - set_page_private(page, 0); - put_page(page); + folio_clear_private(folio); + folio->private = NULL; + folio_put(folio); return data; } +static inline void attach_page_private(struct page *page, void *data) +{ + folio_attach_private(page_folio(page), data); +} + +static inline void *detach_page_private(struct page *page) +{ + return folio_detach_private(page_folio(page)); +} + #ifdef CONFIG_NUMA -extern struct page *__page_cache_alloc(gfp_t gfp); +struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order); #else -static inline struct page *__page_cache_alloc(gfp_t gfp) +static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) { - return alloc_pages(gfp, 0); + return folio_alloc(gfp, order); } #endif +static inline struct page *__page_cache_alloc(gfp_t gfp) +{ + return &filemap_alloc_folio(gfp, 0)->page; +} + static inline struct page *page_cache_alloc(struct address_space *x) { return __page_cache_alloc(mapping_gfp_mask(x)); @@ -331,9 +301,28 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_FOR_MMAP 0x00000040 #define FGP_HEAD 0x00000080 #define FGP_ENTRY 0x00000100 +#define FGP_STABLE 0x00000200 -struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, - int fgp_flags, gfp_t cache_gfp_mask); +struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp); +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp); + +/** + * filemap_get_folio - Find and get a folio. + * @mapping: The address_space to search. + * @index: The page index. + * + * Looks up the page cache entry at @mapping & @index. If a folio is + * present, it is returned with an increased refcount. + * + * Otherwise, %NULL is returned. + */ +static inline struct folio *filemap_get_folio(struct address_space *mapping, + pgoff_t index) +{ + return __filemap_get_folio(mapping, index, 0, 0); +} /** * find_get_page - find and get a page reference @@ -377,25 +366,6 @@ static inline struct page *find_lock_page(struct address_space *mapping, } /** - * find_lock_head - Locate, pin and lock a pagecache page. - * @mapping: The address_space to search. - * @index: The page index. - * - * Looks up the page cache entry at @mapping & @index. If there is a - * page cache page, its head page is returned locked and with an increased - * refcount. - * - * Context: May sleep. - * Return: A struct page which is !PageTail, or %NULL if there is no page - * in the cache for this index. - */ -static inline struct page *find_lock_head(struct address_space *mapping, - pgoff_t index) -{ - return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0); -} - -/** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping @@ -452,6 +422,73 @@ static inline bool thp_contains(struct page *head, pgoff_t index) return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); } +#define swapcache_index(folio) __page_file_index(&(folio)->page) + +/** + * folio_index - File index of a folio. + * @folio: The folio. + * + * For a folio which is either in the page cache or the swap cache, + * return its index within the address_space it belongs to. If you know + * the page is definitely in the page cache, you can look at the folio's + * index directly. + * + * Return: The index (offset in units of pages) of a folio in its file. + */ +static inline pgoff_t folio_index(struct folio *folio) +{ + if (unlikely(folio_test_swapcache(folio))) + return swapcache_index(folio); + return folio->index; +} + +/** + * folio_next_index - Get the index of the next folio. + * @folio: The current folio. + * + * Return: The index of the folio which follows this folio in the file. + */ +static inline pgoff_t folio_next_index(struct folio *folio) +{ + return folio->index + folio_nr_pages(folio); +} + +/** + * folio_file_page - The page for a particular index. + * @folio: The folio which contains this index. + * @index: The index we want to look up. + * + * Sometimes after looking up a folio in the page cache, we need to + * obtain the specific page for an index (eg a page fault). + * + * Return: The page containing the file data for this index. + */ +static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) +{ + /* HugeTLBfs indexes the page cache in units of hpage_size */ + if (folio_test_hugetlb(folio)) + return &folio->page; + return folio_page(folio, index & (folio_nr_pages(folio) - 1)); +} + +/** + * folio_contains - Does this folio contain this index? + * @folio: The folio. + * @index: The page index within the file. + * + * Context: The caller should have the page locked in order to prevent + * (eg) shmem from moving the page between the page cache and swap cache + * and changing its index in the middle of the operation. + * Return: true or false. + */ +static inline bool folio_contains(struct folio *folio, pgoff_t index) +{ + /* HugeTLBfs indexes the page cache in units of hpage_size */ + if (folio_test_hugetlb(folio)) + return folio->index == index; + return index - folio_index(folio) < folio_nr_pages(folio); +} + /* * Given the page we found in the page cache, return the page corresponding * to this index in the file @@ -560,6 +597,27 @@ static inline loff_t page_file_offset(struct page *page) return ((loff_t)page_index(page)) << PAGE_SHIFT; } +/** + * folio_pos - Returns the byte position of this folio in its file. + * @folio: The folio. + */ +static inline loff_t folio_pos(struct folio *folio) +{ + return page_offset(&folio->page); +} + +/** + * folio_file_pos - Returns the byte position of this folio in its file. + * @folio: The folio. + * + * This differs from folio_pos() for folios which belong to a swap file. + * NFS is the only filesystem today which needs to use folio_file_pos(). + */ +static inline loff_t folio_file_pos(struct folio *folio) +{ + return page_file_offset(&folio->page); +} + extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); @@ -575,13 +633,13 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, } struct wait_page_key { - struct page *page; + struct folio *folio; int bit_nr; int page_match; }; struct wait_page_queue { - struct page *page; + struct folio *folio; int bit_nr; wait_queue_entry_t wait; }; @@ -589,7 +647,7 @@ struct wait_page_queue { static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key) { - if (wait_page->page != key->page) + if (wait_page->folio != key->folio) return false; key->page_match = 1; @@ -599,20 +657,31 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page, return true; } -extern void __lock_page(struct page *page); -extern int __lock_page_killable(struct page *page); -extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); -extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, +void __folio_lock(struct folio *folio); +int __folio_lock_killable(struct folio *folio); +bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, unsigned int flags); -extern void unlock_page(struct page *page); +void unlock_page(struct page *page); +void folio_unlock(struct folio *folio); + +static inline bool folio_trylock(struct folio *folio) +{ + return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); +} /* * Return true if the page was successfully locked */ static inline int trylock_page(struct page *page) { - page = compound_head(page); - return (likely(!test_and_set_bit_lock(PG_locked, &page->flags))); + return folio_trylock(page_folio(page)); +} + +static inline void folio_lock(struct folio *folio) +{ + might_sleep(); + if (!folio_trylock(folio)) + __folio_lock(folio); } /* @@ -620,38 +689,30 @@ static inline int trylock_page(struct page *page) */ static inline void lock_page(struct page *page) { + struct folio *folio; might_sleep(); - if (!trylock_page(page)) - __lock_page(page); + + folio = page_folio(page); + if (!folio_trylock(folio)) + __folio_lock(folio); } -/* - * lock_page_killable is like lock_page but can be interrupted by fatal - * signals. It returns 0 if it locked the page and -EINTR if it was - * killed while waiting. - */ -static inline int lock_page_killable(struct page *page) +static inline int folio_lock_killable(struct folio *folio) { might_sleep(); - if (!trylock_page(page)) - return __lock_page_killable(page); + if (!folio_trylock(folio)) + return __folio_lock_killable(folio); return 0; } /* - * lock_page_async - Lock the page, unless this would block. If the page - * is already locked, then queue a callback when the page becomes unlocked. - * This callback can then retry the operation. - * - * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page - * was already locked and the callback defined in 'wait' was queued. + * lock_page_killable is like lock_page but can be interrupted by fatal + * signals. It returns 0 if it locked the page and -EINTR if it was + * killed while waiting. */ -static inline int lock_page_async(struct page *page, - struct wait_page_queue *wait) +static inline int lock_page_killable(struct page *page) { - if (!trylock_page(page)) - return __lock_page_async(page, wait); - return 0; + return folio_lock_killable(page_folio(page)); } /* @@ -659,78 +720,108 @@ static inline int lock_page_async(struct page *page, * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see - * __lock_page_or_retry(). + * __folio_lock_or_retry(). */ -static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, +static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { + struct folio *folio; might_sleep(); - return trylock_page(page) || __lock_page_or_retry(page, mm, flags); + + folio = page_folio(page); + return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags); } /* - * This is exported only for wait_on_page_locked/wait_on_page_writeback, etc., + * This is exported only for folio_wait_locked/folio_wait_writeback, etc., * and should not be used directly. */ -extern void wait_on_page_bit(struct page *page, int bit_nr); -extern int wait_on_page_bit_killable(struct page *page, int bit_nr); +void folio_wait_bit(struct folio *folio, int bit_nr); +int folio_wait_bit_killable(struct folio *folio, int bit_nr); /* - * Wait for a page to be unlocked. + * Wait for a folio to be unlocked. * - * This must be called with the caller "holding" the page, - * ie with increased "page->count" so that the page won't + * This must be called with the caller "holding" the folio, + * ie with increased "page->count" so that the folio won't * go away during the wait.. */ +static inline void folio_wait_locked(struct folio *folio) +{ + if (folio_test_locked(folio)) + folio_wait_bit(folio, PG_locked); +} + +static inline int folio_wait_locked_killable(struct folio *folio) +{ + if (!folio_test_locked(folio)) + return 0; + return folio_wait_bit_killable(folio, PG_locked); +} + static inline void wait_on_page_locked(struct page *page) { - if (PageLocked(page)) - wait_on_page_bit(compound_head(page), PG_locked); + folio_wait_locked(page_folio(page)); } static inline int wait_on_page_locked_killable(struct page *page) { - if (!PageLocked(page)) - return 0; - return wait_on_page_bit_killable(compound_head(page), PG_locked); + return folio_wait_locked_killable(page_folio(page)); } int put_and_wait_on_page_locked(struct page *page, int state); void wait_on_page_writeback(struct page *page); -int wait_on_page_writeback_killable(struct page *page); -extern void end_page_writeback(struct page *page); +void folio_wait_writeback(struct folio *folio); +int folio_wait_writeback_killable(struct folio *folio); +void end_page_writeback(struct page *page); +void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); +void folio_wait_stable(struct folio *folio); +void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); +static inline void __set_page_dirty(struct page *page, + struct address_space *mapping, int warn) +{ + __folio_mark_dirty(page_folio(page), mapping, warn); +} +void folio_account_cleaned(struct folio *folio, struct address_space *mapping, + struct bdi_writeback *wb); +static inline void account_page_cleaned(struct page *page, + struct address_space *mapping, struct bdi_writeback *wb) +{ + return folio_account_cleaned(page_folio(page), mapping, wb); +} +void __folio_cancel_dirty(struct folio *folio); +static inline void folio_cancel_dirty(struct folio *folio) +{ + /* Avoid atomic ops, locking, etc. when not actually needed. */ + if (folio_test_dirty(folio)) + __folio_cancel_dirty(folio); +} +static inline void cancel_dirty_page(struct page *page) +{ + folio_cancel_dirty(page_folio(page)); +} +bool folio_clear_dirty_for_io(struct folio *folio); +bool clear_page_dirty_for_io(struct page *page); +int __must_check folio_write_one(struct folio *folio); +static inline int __must_check write_one_page(struct page *page) +{ + return folio_write_one(page_folio(page)); +} -void __set_page_dirty(struct page *, struct address_space *, int warn); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); void page_endio(struct page *page, bool is_write, int err); -/** - * set_page_private_2 - Set PG_private_2 on a page and take a ref - * @page: The page. - * - * Set the PG_private_2 flag on a page and take the reference needed for the VM - * to handle its lifetime correctly. This sets the flag and takes the - * reference unconditionally, so care must be taken not to set the flag again - * if it's already set. - */ -static inline void set_page_private_2(struct page *page) -{ - page = compound_head(page); - get_page(page); - SetPagePrivate2(page); -} - -void end_page_private_2(struct page *page); -void wait_on_page_private_2(struct page *page); -int wait_on_page_private_2_killable(struct page *page); +void folio_end_private_2(struct folio *folio); +void folio_wait_private_2(struct folio *folio); +int folio_wait_private_2_killable(struct folio *folio); /* * Add an arbitrary waiter to a page's wait queue */ -extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); +void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); /* * Fault everything in given userspace address range in. @@ -790,9 +881,11 @@ static inline int fault_in_pages_readable(const char __user *uaddr, size_t size) } int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); + pgoff_t index, gfp_t gfp); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); + pgoff_t index, gfp_t gfp); +int filemap_add_folio(struct address_space *mapping, struct folio *folio, + pgoff_t index, gfp_t gfp); extern void delete_from_page_cache(struct page *page); extern void __delete_from_page_cache(struct page *page, void *shadow); void replace_page_cache_page(struct page *old, struct page *new); @@ -817,6 +910,10 @@ static inline int add_to_page_cache(struct page *page, return error; } +/* Must be non-static for BPF error injection */ +int __filemap_add_folio(struct address_space *mapping, struct folio *folio, + pgoff_t index, gfp_t gfp, void **shadowp); + /** * struct readahead_control - Describes a readahead request. * @@ -906,33 +1003,57 @@ void page_cache_async_readahead(struct address_space *mapping, page_cache_async_ra(&ractl, page, req_count); } +static inline struct folio *__readahead_folio(struct readahead_control *ractl) +{ + struct folio *folio; + + BUG_ON(ractl->_batch_count > ractl->_nr_pages); + ractl->_nr_pages -= ractl->_batch_count; + ractl->_index += ractl->_batch_count; + + if (!ractl->_nr_pages) { + ractl->_batch_count = 0; + return NULL; + } + + folio = xa_load(&ractl->mapping->i_pages, ractl->_index); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + ractl->_batch_count = folio_nr_pages(folio); + + return folio; +} + /** * readahead_page - Get the next page to read. - * @rac: The current readahead request. + * @ractl: The current readahead request. * * Context: The page is locked and has an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: A pointer to the next page, or %NULL if we are done. */ -static inline struct page *readahead_page(struct readahead_control *rac) +static inline struct page *readahead_page(struct readahead_control *ractl) { - struct page *page; - - BUG_ON(rac->_batch_count > rac->_nr_pages); - rac->_nr_pages -= rac->_batch_count; - rac->_index += rac->_batch_count; + struct folio *folio = __readahead_folio(ractl); - if (!rac->_nr_pages) { - rac->_batch_count = 0; - return NULL; - } + return &folio->page; +} - page = xa_load(&rac->mapping->i_pages, rac->_index); - VM_BUG_ON_PAGE(!PageLocked(page), page); - rac->_batch_count = thp_nr_pages(page); +/** + * readahead_folio - Get the next folio to read. + * @ractl: The current readahead request. + * + * Context: The folio is locked. The caller should unlock the folio once + * all I/O to that folio has completed. + * Return: A pointer to the next folio, or %NULL if we are done. + */ +static inline struct folio *readahead_folio(struct readahead_control *ractl) +{ + struct folio *folio = __readahead_folio(ractl); - return page; + if (folio) + folio_put(folio); + return folio; } static inline unsigned int __readahead_batch(struct readahead_control *rac, @@ -1040,6 +1161,34 @@ static inline unsigned long dir_pages(struct inode *inode) } /** + * folio_mkwrite_check_truncate - check if folio was truncated + * @folio: the folio to check + * @inode: the inode to check the folio against + * + * Return: the number of bytes in the folio up to EOF, + * or -EFAULT if the folio was truncated. + */ +static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, + struct inode *inode) +{ + loff_t size = i_size_read(inode); + pgoff_t index = size >> PAGE_SHIFT; + size_t offset = offset_in_folio(folio, size); + + if (!folio->mapping) + return -EFAULT; + + /* folio is wholly inside EOF */ + if (folio_next_index(folio) - 1 < index) + return folio_size(folio); + /* folio is wholly past EOF */ + if (folio->index > index || !offset) + return -EFAULT; + /* folio is partially inside EOF */ + return offset; +} + +/** * page_mkwrite_check_truncate - check if page was truncated * @page: the page to check * @inode: the inode to check the page against @@ -1068,19 +1217,25 @@ static inline int page_mkwrite_check_truncate(struct page *page, } /** - * i_blocks_per_page - How many blocks fit in this page. + * i_blocks_per_folio - How many blocks fit in this folio. * @inode: The inode which contains the blocks. - * @page: The page (head page if the page is a THP). + * @folio: The folio. * - * If the block size is larger than the size of this page, return zero. + * If the block size is larger than the size of this folio, return zero. * - * Context: The caller should hold a refcount on the page to prevent it + * Context: The caller should hold a refcount on the folio to prevent it * from being split. - * Return: The number of filesystem blocks covered by this page. + * Return: The number of filesystem blocks covered by this folio. */ static inline +unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio) +{ + return folio_size(folio) >> inode->i_blkbits; +} + +static inline unsigned int i_blocks_per_page(struct inode *inode, struct page *page) { - return thp_size(page) >> inode->i_blkbits; + return i_blocks_per_folio(inode, page_folio(page)); } #endif /* _LINUX_PAGEMAP_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c976cc6de257..e704b1a4c06c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -235,7 +235,7 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); * * returns the number of cleaned PTEs. */ -int page_mkclean(struct page *); +int folio_mkclean(struct folio *); /* * called in munlock()/munmap() path to check for other vmas holding @@ -295,12 +295,14 @@ static inline void try_to_unmap(struct page *page, enum ttu_flags flags) { } -static inline int page_mkclean(struct page *page) +static inline int folio_mkclean(struct folio *folio) { return 0; } - - #endif /* CONFIG_MMU */ +static inline int page_mkclean(struct page *page) +{ + return folio_mkclean(page_folio(page)); +} #endif /* _LINUX_RMAP_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 14ab0c0bc924..1ce9a9eb223b 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -128,6 +128,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); +bool sk_msg_is_readable(struct sock *sk); static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) { diff --git a/include/linux/swap.h b/include/linux/swap.h index ba52f3a3478e..cdf0957a88a4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -320,11 +320,17 @@ struct vma_swap_readahead { #endif }; +static inline swp_entry_t folio_swap_entry(struct folio *folio) +{ + swp_entry_t entry = { .val = page_private(&folio->page) }; + return entry; +} + /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); -void workingset_refault(struct page *page, void *shadow); -void workingset_activation(struct page *page); +void workingset_refault(struct folio *folio, void *shadow); +void workingset_activation(struct folio *folio); /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); @@ -344,9 +350,11 @@ extern unsigned long nr_free_buffer_pages(void); /* linux/mm/swap.c */ extern void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); -extern void lru_note_cost_page(struct page *); +extern void lru_note_cost_folio(struct folio *); +extern void folio_add_lru(struct folio *); extern void lru_cache_add(struct page *); -extern void mark_page_accessed(struct page *); +void mark_page_accessed(struct page *); +void folio_mark_accessed(struct folio *); extern atomic_t lru_disable_count; @@ -365,7 +373,6 @@ extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); -extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d6a6cf53b127..bfe38869498d 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -415,6 +415,78 @@ static inline void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ +static inline void __zone_stat_mod_folio(struct folio *folio, + enum zone_stat_item item, long nr) +{ + __mod_zone_page_state(folio_zone(folio), item, nr); +} + +static inline void __zone_stat_add_folio(struct folio *folio, + enum zone_stat_item item) +{ + __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); +} + +static inline void __zone_stat_sub_folio(struct folio *folio, + enum zone_stat_item item) +{ + __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); +} + +static inline void zone_stat_mod_folio(struct folio *folio, + enum zone_stat_item item, long nr) +{ + mod_zone_page_state(folio_zone(folio), item, nr); +} + +static inline void zone_stat_add_folio(struct folio *folio, + enum zone_stat_item item) +{ + mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); +} + +static inline void zone_stat_sub_folio(struct folio *folio, + enum zone_stat_item item) +{ + mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); +} + +static inline void __node_stat_mod_folio(struct folio *folio, + enum node_stat_item item, long nr) +{ + __mod_node_page_state(folio_pgdat(folio), item, nr); +} + +static inline void __node_stat_add_folio(struct folio *folio, + enum node_stat_item item) +{ + __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); +} + +static inline void __node_stat_sub_folio(struct folio *folio, + enum node_stat_item item) +{ + __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); +} + +static inline void node_stat_mod_folio(struct folio *folio, + enum node_stat_item item, long nr) +{ + mod_node_page_state(folio_pgdat(folio), item, nr); +} + +static inline void node_stat_add_folio(struct folio *folio, + enum node_stat_item item) +{ + mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); +} + +static inline void node_stat_sub_folio(struct folio *folio, + enum node_stat_item item) +{ + mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); +} + static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, int migratetype) { @@ -525,12 +597,6 @@ static inline void mod_lruvec_page_state(struct page *page, #endif /* CONFIG_MEMCG */ -static inline void inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, 1); -} - static inline void __inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { @@ -543,6 +609,24 @@ static inline void __dec_lruvec_page_state(struct page *page, __mod_lruvec_page_state(page, idx, -1); } +static inline void __lruvec_stat_mod_folio(struct folio *folio, + enum node_stat_item idx, int val) +{ + __mod_lruvec_page_state(&folio->page, idx, val); +} + +static inline void __lruvec_stat_add_folio(struct folio *folio, + enum node_stat_item idx) +{ + __lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); +} + +static inline void __lruvec_stat_sub_folio(struct folio *folio, + enum node_stat_item idx) +{ + __lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); +} + static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { @@ -555,4 +639,21 @@ static inline void dec_lruvec_page_state(struct page *page, mod_lruvec_page_state(page, idx, -1); } +static inline void lruvec_stat_mod_folio(struct folio *folio, + enum node_stat_item idx, int val) +{ + mod_lruvec_page_state(&folio->page, idx, val); +} + +static inline void lruvec_stat_add_folio(struct folio *folio, + enum node_stat_item idx) +{ + lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); +} + +static inline void lruvec_stat_sub_folio(struct folio *folio, + enum node_stat_item idx) +{ + lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); +} #endif /* _LINUX_VMSTAT_H */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d1f65adf6a26..3571f383dfb6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -393,7 +393,14 @@ void writeback_set_ratelimit(void); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); -void account_page_redirty(struct page *page); +bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio); +void folio_account_redirty(struct folio *folio); +static inline void account_page_redirty(struct page *page) +{ + folio_account_redirty(page_folio(page)); +} +bool folio_redirty_for_writepage(struct writeback_control *, struct folio *); +bool redirty_page_for_writepage(struct writeback_control *, struct page *); void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 62dd8422e0dc..27336fc70467 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5376,7 +5376,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * netdev and may otherwise be used by driver read-only, will be update * by cfg80211 on change_interface * @mgmt_registrations: list of registrations for management frames - * @mgmt_registrations_lock: lock for the list * @mgmt_registrations_need_update: mgmt registrations were updated, * need to propagate the update to the driver * @mtx: mutex used to lock data in this struct, may be used by drivers @@ -5423,7 +5422,6 @@ struct wireless_dev { u32 identifier; struct list_head mgmt_registrations; - spinlock_t mgmt_registrations_lock; u8 mgmt_registrations_need_update:1; struct mutex mtx; diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 6026bbefbffd..3214848402ec 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -69,6 +69,10 @@ struct mptcp_out_options { struct { u64 sndr_key; u64 rcvr_key; + u64 data_seq; + u32 subflow_seq; + u16 data_len; + __sum16 csum; }; struct { struct mptcp_addr_info addr; diff --git a/include/net/sock.h b/include/net/sock.h index ea6fbc88c8f9..463f390d90b3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1208,7 +1208,7 @@ struct proto { #endif bool (*stream_memory_free)(const struct sock *sk, int wake); - bool (*stream_memory_read)(const struct sock *sk); + bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); @@ -2820,4 +2820,10 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); +static inline bool sk_is_readable(struct sock *sk) +{ + if (sk->sk_prot->sock_is_readable) + return sk->sk_prot->sock_is_readable(sk); + return false; +} #endif /* _SOCK_H */ diff --git a/include/net/tls.h b/include/net/tls.h index be4b3e1cac46..1fffb206f09f 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -358,6 +358,7 @@ int tls_sk_query(struct sock *sk, int optname, char __user *optval, int __user *optlen); int tls_sk_attach(struct sock *sk, int optname, char __user *optval, unsigned int optlen); +void tls_err_abort(struct sock *sk, int err); int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); @@ -375,7 +376,7 @@ void tls_sw_release_resources_rx(struct sock *sk); void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); -bool tls_sw_stream_read(const struct sock *sk); +bool tls_sw_sock_is_readable(struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); @@ -466,12 +467,6 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) #endif } -static inline void tls_err_abort(struct sock *sk, int err) -{ - sk->sk_err = err; - sk_error_report(sk); -} - static inline bool tls_bigint_increment(unsigned char *seq, int len) { int i; @@ -512,7 +507,7 @@ static inline void tls_advance_record_sn(struct sock *sk, struct cipher_context *ctx) { if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); if (prot->version != TLS_1_3_VERSION && prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) diff --git a/include/net/udp.h b/include/net/udp.h index 360df454356c..909ecf447e0f 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -494,8 +494,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial * packets in udp_gro_complete_segment. As does UDP GSO, verified by * udp_send_skb. But when those packets are looped in dev_loopback_xmit - * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this - * specific case, where PARTIAL is both correct and required. + * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY. + * Reset in this specific case, where PARTIAL is both correct and + * required. */ if (skb->pkt_type == PACKET_LOOPBACK) skb->ip_summed = CHECKSUM_PARTIAL; diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h index 1d28431e85bd..171524d3526d 100644 --- a/include/trace/events/pagemap.h +++ b/include/trace/events/pagemap.h @@ -16,38 +16,38 @@ #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u -#define trace_pagemap_flags(page) ( \ - (PageAnon(page) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ - (page_mapped(page) ? PAGEMAP_MAPPED : 0) | \ - (PageSwapCache(page) ? PAGEMAP_SWAPCACHE : 0) | \ - (PageSwapBacked(page) ? PAGEMAP_SWAPBACKED : 0) | \ - (PageMappedToDisk(page) ? PAGEMAP_MAPPEDDISK : 0) | \ - (page_has_private(page) ? PAGEMAP_BUFFERS : 0) \ +#define trace_pagemap_flags(folio) ( \ + (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ + (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \ + (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \ + (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \ + (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \ + (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, - TP_PROTO(struct page *page), + TP_PROTO(struct folio *folio), - TP_ARGS(page), + TP_ARGS(folio), TP_STRUCT__entry( - __field(struct page *, page ) + __field(struct folio *, folio ) __field(unsigned long, pfn ) __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( - __entry->page = page; - __entry->pfn = page_to_pfn(page); - __entry->lru = page_lru(page); - __entry->flags = trace_pagemap_flags(page); + __entry->folio = folio; + __entry->pfn = folio_pfn(folio); + __entry->lru = folio_lru_list(folio); + __entry->flags = trace_pagemap_flags(folio); ), /* Flag format is based on page-types.c formatting for pagemap */ - TP_printk("page=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", - __entry->page, + TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", + __entry->folio, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", @@ -60,23 +60,21 @@ TRACE_EVENT(mm_lru_insertion, TRACE_EVENT(mm_lru_activate, - TP_PROTO(struct page *page), + TP_PROTO(struct folio *folio), - TP_ARGS(page), + TP_ARGS(folio), TP_STRUCT__entry( - __field(struct page *, page ) + __field(struct folio *, folio ) __field(unsigned long, pfn ) ), TP_fast_assign( - __entry->page = page; - __entry->pfn = page_to_pfn(page); + __entry->folio = folio; + __entry->pfn = folio_pfn(folio); ), - /* Flag format is based on page-types.c formatting for pagemap */ - TP_printk("page=%p pfn=0x%lx", __entry->page, __entry->pfn) - + TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 840d1ba84cf5..7dccb66474f7 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -52,11 +52,11 @@ WB_WORK_REASON struct wb_writeback_work; -DECLARE_EVENT_CLASS(writeback_page_template, +DECLARE_EVENT_CLASS(writeback_folio_template, - TP_PROTO(struct page *page, struct address_space *mapping), + TP_PROTO(struct folio *folio, struct address_space *mapping), - TP_ARGS(page, mapping), + TP_ARGS(folio, mapping), TP_STRUCT__entry ( __array(char, name, 32) @@ -69,7 +69,7 @@ DECLARE_EVENT_CLASS(writeback_page_template, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = mapping ? mapping->host->i_ino : 0; - __entry->index = page->index; + __entry->index = folio->index; ), TP_printk("bdi %s: ino=%lu index=%lu", @@ -79,18 +79,18 @@ DECLARE_EVENT_CLASS(writeback_page_template, ) ); -DEFINE_EVENT(writeback_page_template, writeback_dirty_page, +DEFINE_EVENT(writeback_folio_template, writeback_dirty_folio, - TP_PROTO(struct page *page, struct address_space *mapping), + TP_PROTO(struct folio *folio, struct address_space *mapping), - TP_ARGS(page, mapping) + TP_ARGS(folio, mapping) ); -DEFINE_EVENT(writeback_page_template, wait_on_page_writeback, +DEFINE_EVENT(writeback_folio_template, folio_wait_writeback, - TP_PROTO(struct page *page, struct address_space *mapping), + TP_PROTO(struct folio *folio, struct address_space *mapping), - TP_ARGS(page, mapping) + TP_ARGS(folio, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, @@ -236,9 +236,9 @@ TRACE_EVENT(inode_switch_wbs, TRACE_EVENT(track_foreign_dirty, - TP_PROTO(struct page *page, struct bdi_writeback *wb), + TP_PROTO(struct folio *folio, struct bdi_writeback *wb), - TP_ARGS(page, wb), + TP_ARGS(folio, wb), TP_STRUCT__entry( __array(char, name, 32) @@ -250,7 +250,7 @@ TRACE_EVENT(track_foreign_dirty, ), TP_fast_assign( - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio_mapping(folio); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); @@ -258,7 +258,7 @@ TRACE_EVENT(track_foreign_dirty, __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - __entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup); + __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index cebd4fb06d19..447def540544 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -1072,6 +1072,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) INIT_WORK(&aux->work, prog_array_map_clear_deferred); INIT_LIST_HEAD(&aux->poke_progs); mutex_init(&aux->poke_mutex); + spin_lock_init(&aux->owner.lock); map = array_map_alloc(attr); if (IS_ERR(map)) { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d6b7dfdd8066..6e3ae90ad107 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -524,6 +524,7 @@ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; +long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) @@ -817,7 +818,8 @@ u64 __weak bpf_jit_alloc_exec_limit(void) static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ - bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2, + bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); + bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2, PAGE_SIZE), LONG_MAX); return 0; } @@ -1821,20 +1823,26 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx, bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { + bool ret; + if (fp->kprobe_override) return false; - if (!array->aux->type) { + spin_lock(&array->aux->owner.lock); + + if (!array->aux->owner.type) { /* There's no owner yet where we could check for * compatibility. */ - array->aux->type = fp->type; - array->aux->jited = fp->jited; - return true; + array->aux->owner.type = fp->type; + array->aux->owner.jited = fp->jited; + ret = true; + } else { + ret = array->aux->owner.type == fp->type && + array->aux->owner.jited == fp->jited; } - - return array->aux->type == fp->type && - array->aux->jited == fp->jited; + spin_unlock(&array->aux->owner.lock); + return ret; } static int bpf_check_tail_call(const struct bpf_prog *fp) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e50c0bfdb7d..1cad6979a0d0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -543,8 +543,10 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { array = container_of(map, struct bpf_array, map); - type = array->aux->type; - jited = array->aux->jited; + spin_lock(&array->aux->owner.lock); + type = array->aux->owner.type; + jited = array->aux->owner.jited; + spin_unlock(&array->aux->owner.lock); } seq_printf(m, @@ -1337,12 +1339,11 @@ int generic_map_update_batch(struct bpf_map *map, void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; - int ufd = attr->map_fd; + int ufd = attr->batch.map_fd; void *key, *value; struct fd f; int err = 0; - f = fdget(ufd); if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; @@ -1367,6 +1368,7 @@ int generic_map_update_batch(struct bpf_map *map, return -ENOMEM; } + f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */ for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, @@ -1386,6 +1388,7 @@ int generic_map_update_batch(struct bpf_map *map, kvfree(value); kvfree(key); + fdput(f); return err; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e76b55917905..de006552be8a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13319,7 +13319,7 @@ BTF_SET_START(btf_non_sleepable_error_inject) /* Three functions below can be called from sleepable and non-sleepable context. * Assume non-sleepable from bpf safety point of view. */ -BTF_ID(func, __add_to_page_cache_locked) +BTF_ID(func, __filemap_add_folio) BTF_ID(func, should_fail_alloc_page) BTF_ID(func, should_failslab) BTF_SET_END(btf_non_sleepable_error_inject) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 570b0c97392a..ea08f01d0111 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2187,8 +2187,10 @@ static void cgroup_kill_sb(struct super_block *sb) * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && - !percpu_ref_is_dying(&root->cgrp.self.refcnt)) + !percpu_ref_is_dying(&root->cgrp.self.refcnt)) { + cgroup_bpf_offline(&root->cgrp); percpu_ref_kill(&root->cgrp.self.refcnt); + } cgroup_put(&root->cgrp); kernfs_kill_sb(sb); } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index af24dc3febbe..6357c3580d07 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -167,7 +167,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, addr + PAGE_SIZE); if (new_page) { - err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL); + err = mem_cgroup_charge(page_folio(new_page), vma->vm_mm, + GFP_KERNEL); if (err) return err; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 635fbdc9d589..feebf57c6458 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2208,7 +2208,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) } /** - * ftrace_update_record, set a record that now is tracing or not + * ftrace_update_record - set a record that now is tracing or not * @rec: the record to update * @enable: set to true if the record is tracing, false to force disable * @@ -2221,7 +2221,7 @@ int ftrace_update_record(struct dyn_ftrace *rec, bool enable) } /** - * ftrace_test_record, check if the record has been enabled or not + * ftrace_test_record - check if the record has been enabled or not * @rec: the record to test * @enable: set to true to check if enabled, false if it is disabled * @@ -2574,7 +2574,7 @@ struct ftrace_rec_iter { }; /** - * ftrace_rec_iter_start, start up iterating over traced functions + * ftrace_rec_iter_start - start up iterating over traced functions * * Returns an iterator handle that is used to iterate over all * the records that represent address locations where functions @@ -2605,7 +2605,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_start(void) } /** - * ftrace_rec_iter_next, get the next record to process. + * ftrace_rec_iter_next - get the next record to process. * @iter: The handle to the iterator. * * Returns the next iterator after the given iterator @iter. @@ -2630,7 +2630,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter) } /** - * ftrace_rec_iter_record, get the record at the iterator location + * ftrace_rec_iter_record - get the record at the iterator location * @iter: The current iterator location * * Returns the record that the current @iter is at. @@ -2733,7 +2733,7 @@ static int __ftrace_modify_code(void *data) } /** - * ftrace_run_stop_machine, go back to the stop machine method + * ftrace_run_stop_machine - go back to the stop machine method * @command: The command to tell ftrace what to do * * If an arch needs to fall back to the stop machine method, the @@ -2745,7 +2745,7 @@ void ftrace_run_stop_machine(int command) } /** - * arch_ftrace_update_code, modify the code to trace or not trace + * arch_ftrace_update_code - modify the code to trace or not trace * @command: The command that needs to be done * * Archs can override this function if it does not need to @@ -7525,7 +7525,9 @@ void ftrace_kill(void) } /** - * Test if ftrace is dead or not. + * ftrace_is_dead - Test if ftrace is dead or not. + * + * Returns 1 if ftrace is "dead", zero otherwise. */ int ftrace_is_dead(void) { diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index c4a15aef36af..928867f527e7 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -904,8 +904,8 @@ static int __trace_eprobe_create(int argc, const char *argv[]) if (IS_ERR(ep)) { ret = PTR_ERR(ep); - /* This must return -ENOMEM, else there is a bug */ - WARN_ON_ONCE(ret != -ENOMEM); + /* This must return -ENOMEM or missing event, else there is a bug */ + WARN_ON_ONCE(ret != -ENOMEM && ret != -ENODEV); ep = NULL; goto error; } diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c index 451543937524..53e7eb1dd76c 100644 --- a/lib/flex_proportions.c +++ b/lib/flex_proportions.c @@ -217,11 +217,12 @@ static void fprop_reflect_period_percpu(struct fprop_global *p, } /* Event of type pl happened */ -void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl) +void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl, + long nr) { fprop_reflect_period_percpu(p, pl); - percpu_counter_add_batch(&pl->events, 1, PROP_BATCH); - percpu_counter_add(&p->events, 1); + percpu_counter_add_batch(&pl->events, nr, PROP_BATCH); + percpu_counter_add(&p->events, nr); } void fprop_fraction_percpu(struct fprop_global *p, @@ -253,20 +254,29 @@ void fprop_fraction_percpu(struct fprop_global *p, } /* - * Like __fprop_inc_percpu() except that event is counted only if the given + * Like __fprop_add_percpu() except that event is counted only if the given * type has fraction smaller than @max_frac/FPROP_FRAC_BASE */ -void __fprop_inc_percpu_max(struct fprop_global *p, - struct fprop_local_percpu *pl, int max_frac) +void __fprop_add_percpu_max(struct fprop_global *p, + struct fprop_local_percpu *pl, int max_frac, long nr) { if (unlikely(max_frac < FPROP_FRAC_BASE)) { unsigned long numerator, denominator; + s64 tmp; fprop_fraction_percpu(p, pl, &numerator, &denominator); - if (numerator > - (((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT) + /* Adding 'nr' to fraction exceeds max_frac/FPROP_FRAC_BASE? */ + tmp = (u64)denominator * max_frac - + ((u64)numerator << FPROP_FRAC_SHIFT); + if (tmp < 0) { + /* Maximum fraction already exceeded? */ return; + } else if (tmp < nr * (FPROP_FRAC_BASE - max_frac)) { + /* Add just enough for the fraction to saturate */ + nr = div_u64(tmp + FPROP_FRAC_BASE - max_frac - 1, + FPROP_FRAC_BASE - max_frac); + } } - __fprop_inc_percpu(p, pl); + __fprop_add_percpu(p, pl, nr); } diff --git a/mm/Makefile b/mm/Makefile index fc60a40ce954..d6c0042e3aa0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -46,7 +46,7 @@ mmu-$(CONFIG_MMU) += process_vm_access.o endif obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ - maccess.o page-writeback.o \ + maccess.o page-writeback.o folio-compat.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o percpu.o slab_common.o \ diff --git a/mm/compaction.c b/mm/compaction.c index bfc93da1c2c7..fbc60f964c38 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1022,7 +1022,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (!TestClearPageLRU(page)) goto isolate_fail_put; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(page_folio(page)); /* If we already hold the lock, we can skip some rechecking */ if (lruvec != locked) { @@ -1032,7 +1032,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, compact_lock_irqsave(&lruvec->lru_lock, &flags, cc); locked = lruvec; - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, page_folio(page)); /* Try get exclusive access under lock */ if (!skip_updated) { diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h index c938a9c34e6c..7008c3735e99 100644 --- a/mm/damon/core-test.h +++ b/mm/damon/core-test.h @@ -219,14 +219,14 @@ static void damon_test_split_regions_of(struct kunit *test) r = damon_new_region(0, 22); damon_add_region(r, t); damon_split_regions_of(c, t, 2); - KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 2u); + KUNIT_EXPECT_LE(test, damon_nr_regions(t), 2u); damon_free_target(t); t = damon_new_target(42); r = damon_new_region(0, 220); damon_add_region(r, t); damon_split_regions_of(c, t, 4); - KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 4u); + KUNIT_EXPECT_LE(test, damon_nr_regions(t), 4u); damon_free_target(t); damon_destroy_ctx(c); } diff --git a/mm/filemap.c b/mm/filemap.c index dae481293b5d..3e9feb5cc570 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -835,6 +835,8 @@ EXPORT_SYMBOL(file_write_and_wait_range); */ void replace_page_cache_page(struct page *old, struct page *new) { + struct folio *fold = page_folio(old); + struct folio *fnew = page_folio(new); struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; pgoff_t offset = old->index; @@ -848,7 +850,7 @@ void replace_page_cache_page(struct page *old, struct page *new) new->mapping = mapping; new->index = offset; - mem_cgroup_migrate(old, new); + mem_cgroup_migrate(fold, fnew); xas_lock_irq(&xas); xas_store(&xas, new); @@ -870,26 +872,25 @@ void replace_page_cache_page(struct page *old, struct page *new) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -noinline int __add_to_page_cache_locked(struct page *page, - struct address_space *mapping, - pgoff_t offset, gfp_t gfp, - void **shadowp) +noinline int __filemap_add_folio(struct address_space *mapping, + struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { - XA_STATE(xas, &mapping->i_pages, offset); - int huge = PageHuge(page); + XA_STATE(xas, &mapping->i_pages, index); + int huge = folio_test_hugetlb(folio); int error; bool charged = false; - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageSwapBacked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); mapping_set_update(&xas, mapping); - get_page(page); - page->mapping = mapping; - page->index = offset; + folio_get(folio); + folio->mapping = mapping; + folio->index = index; if (!huge) { - error = mem_cgroup_charge(page, NULL, gfp); + error = mem_cgroup_charge(folio, NULL, gfp); + VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); if (error) goto error; charged = true; @@ -901,7 +902,7 @@ noinline int __add_to_page_cache_locked(struct page *page, unsigned int order = xa_get_order(xas.xa, xas.xa_index); void *entry, *old = NULL; - if (order > thp_order(page)) + if (order > folio_order(folio)) xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), order, gfp); xas_lock_irq(&xas); @@ -918,13 +919,13 @@ noinline int __add_to_page_cache_locked(struct page *page, *shadowp = old; /* entry may have been split before we acquired lock */ order = xa_get_order(xas.xa, xas.xa_index); - if (order > thp_order(page)) { + if (order > folio_order(folio)) { xas_split(&xas, old, order); xas_reset(&xas); } } - xas_store(&xas, page); + xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; @@ -932,7 +933,7 @@ noinline int __add_to_page_cache_locked(struct page *page, /* hugetlb pages do not participate in page cache accounting */ if (!huge) - __inc_lruvec_page_state(page, NR_FILE_PAGES); + __lruvec_stat_add_folio(folio, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); @@ -940,19 +941,19 @@ unlock: if (xas_error(&xas)) { error = xas_error(&xas); if (charged) - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(folio); goto error; } - trace_mm_filemap_add_to_page_cache(page); + trace_mm_filemap_add_to_page_cache(&folio->page); return 0; error: - page->mapping = NULL; + folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - put_page(page); + folio_put(folio); return error; } -ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); +ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); /** * add_to_page_cache_locked - add a locked page to the pagecache @@ -969,59 +970,58 @@ ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { - return __add_to_page_cache_locked(page, mapping, offset, + return __filemap_add_folio(mapping, page_folio(page), offset, gfp_mask, NULL); } EXPORT_SYMBOL(add_to_page_cache_locked); -int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask) +int filemap_add_folio(struct address_space *mapping, struct folio *folio, + pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; - __SetPageLocked(page); - ret = __add_to_page_cache_locked(page, mapping, offset, - gfp_mask, &shadow); + __folio_set_locked(folio); + ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) - __ClearPageLocked(page); + __folio_clear_locked(folio); else { /* - * The page might have been evicted from cache only + * The folio might have been evicted from cache only * recently, in which case it should be activated like - * any other repeatedly accessed page. - * The exception is pages getting rewritten; evicting other + * any other repeatedly accessed folio. + * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - WARN_ON_ONCE(PageActive(page)); - if (!(gfp_mask & __GFP_WRITE) && shadow) - workingset_refault(page, shadow); - lru_cache_add(page); + WARN_ON_ONCE(folio_test_active(folio)); + if (!(gfp & __GFP_WRITE) && shadow) + workingset_refault(folio, shadow); + folio_add_lru(folio); } return ret; } -EXPORT_SYMBOL_GPL(add_to_page_cache_lru); +EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA -struct page *__page_cache_alloc(gfp_t gfp) +struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) { int n; - struct page *page; + struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); - page = __alloc_pages_node(n, gfp, 0); - } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); + folio = __folio_alloc_node(gfp, order, n); + } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); - return page; + return folio; } - return alloc_pages(gfp, 0); + return folio_alloc(gfp, order); } -EXPORT_SYMBOL(__page_cache_alloc); +EXPORT_SYMBOL(filemap_alloc_folio); #endif /* @@ -1074,11 +1074,11 @@ EXPORT_SYMBOL(filemap_invalidate_unlock_two); */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) -static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; +static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; -static wait_queue_head_t *page_waitqueue(struct page *page) +static wait_queue_head_t *folio_waitqueue(struct folio *folio) { - return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; + return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) @@ -1086,7 +1086,7 @@ void __init pagecache_init(void) int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) - init_waitqueue_head(&page_wait_table[i]); + init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); } @@ -1141,10 +1141,10 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { - if (test_bit(key->bit_nr, &key->page->flags)) + if (test_bit(key->bit_nr, &key->folio->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { - if (test_and_set_bit(key->bit_nr, &key->page->flags)) + if (test_and_set_bit(key->bit_nr, &key->folio->flags)) return -1; flags |= WQ_FLAG_DONE; } @@ -1157,7 +1157,7 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs - * with the load-acquire in wait_on_page_bit_common(). + * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); @@ -1176,14 +1176,14 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, return (flags & WQ_FLAG_EXCLUSIVE) != 0; } -static void wake_up_page_bit(struct page *page, int bit_nr) +static void folio_wake_bit(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); + wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; wait_queue_entry_t bookmark; - key.page = page; + key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; @@ -1218,7 +1218,7 @@ static void wake_up_page_bit(struct page *page, int bit_nr) * page waiters. */ if (!waitqueue_active(q) || !key.page_match) { - ClearPageWaiters(page); + folio_clear_waiters(folio); /* * It's possible to miss clearing Waiters here, when we woke * our page waiters, but the hashed waitqueue has waiters for @@ -1230,19 +1230,19 @@ static void wake_up_page_bit(struct page *page, int bit_nr) spin_unlock_irqrestore(&q->lock, flags); } -static void wake_up_page(struct page *page, int bit) +static void folio_wake(struct folio *folio, int bit) { - if (!PageWaiters(page)) + if (!folio_test_waiters(folio)) return; - wake_up_page_bit(page, bit); + folio_wake_bit(folio, bit); } /* - * A choice of three behaviors for wait_on_page_bit_common(): + * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like - * __lock_page() waiting on then setting PG_locked. + * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * wait_on_page_writeback() waiting on PG_writeback. @@ -1253,16 +1253,16 @@ enum behavior { }; /* - * Attempt to check (or get) the page bit, and mark us done + * Attempt to check (or get) the folio flag, and mark us done * if successful. */ -static inline bool trylock_page_bit_common(struct page *page, int bit_nr, +static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { - if (test_and_set_bit(bit_nr, &page->flags)) + if (test_and_set_bit(bit_nr, &folio->flags)) return false; - } else if (test_bit(bit_nr, &page->flags)) + } else if (test_bit(bit_nr, &folio->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; @@ -1272,9 +1272,10 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; -static inline int wait_on_page_bit_common(wait_queue_head_t *q, - struct page *page, int bit_nr, int state, enum behavior behavior) +static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, + int state, enum behavior behavior) { + wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; @@ -1283,8 +1284,8 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, unsigned long pflags; if (bit_nr == PG_locked && - !PageUptodate(page) && PageWorkingset(page)) { - if (!PageSwapBacked(page)) { + !folio_test_uptodate(folio) && folio_test_workingset(folio)) { + if (!folio_test_swapbacked(folio)) { delayacct_thrashing_start(); delayacct = true; } @@ -1294,7 +1295,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, init_wait(wait); wait->func = wake_page_function; - wait_page.page = page; + wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: @@ -1309,7 +1310,7 @@ repeat: * Do one last check whether we can get the * page bit synchronously. * - * Do the SetPageWaiters() marking before that + * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the @@ -1320,8 +1321,8 @@ repeat: * lock to avoid races. */ spin_lock_irq(&q->lock); - SetPageWaiters(page); - if (!trylock_page_bit_common(page, bit_nr, wait)) + folio_set_waiters(folio); + if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); @@ -1331,10 +1332,10 @@ repeat: * see whether the page bit testing has already * been done by the wake function. * - * We can drop our reference to the page. + * We can drop our reference to the folio. */ if (behavior == DROP) - put_page(page); + folio_put(folio); /* * Note that until the "finish_wait()", or until @@ -1371,7 +1372,7 @@ repeat: * * And if that fails, we'll have to retry this all. */ - if (unlikely(test_and_set_bit(bit_nr, &page->flags))) + if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; @@ -1380,7 +1381,7 @@ repeat: /* * If a signal happened, this 'finish_wait()' may remove the last - * waiter from the wait-queues, but the PageWaiters bit will remain + * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ @@ -1411,19 +1412,17 @@ repeat: return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } -void wait_on_page_bit(struct page *page, int bit_nr) +void folio_wait_bit(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); - wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); + folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } -EXPORT_SYMBOL(wait_on_page_bit); +EXPORT_SYMBOL(folio_wait_bit); -int wait_on_page_bit_killable(struct page *page, int bit_nr) +int folio_wait_bit_killable(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); + return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } -EXPORT_SYMBOL(wait_on_page_bit_killable); +EXPORT_SYMBOL(folio_wait_bit_killable); /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked @@ -1440,31 +1439,28 @@ EXPORT_SYMBOL(wait_on_page_bit_killable); */ int put_and_wait_on_page_locked(struct page *page, int state) { - wait_queue_head_t *q; - - page = compound_head(page); - q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, PG_locked, state, DROP); + return folio_wait_bit_common(page_folio(page), PG_locked, state, + DROP); } /** - * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue - * @page: Page defining the wait queue of interest + * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue + * @folio: Folio defining the wait queue of interest * @waiter: Waiter to add to the queue * - * Add an arbitrary @waiter to the wait queue for the nominated @page. + * Add an arbitrary @waiter to the wait queue for the nominated @folio. */ -void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) +void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) { - wait_queue_head_t *q = page_waitqueue(page); + wait_queue_head_t *q = folio_waitqueue(folio); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); - SetPageWaiters(page); + folio_set_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL_GPL(add_page_wait_queue); +EXPORT_SYMBOL_GPL(folio_add_wait_queue); #ifndef clear_bit_unlock_is_negative_byte @@ -1490,124 +1486,116 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem #endif /** - * unlock_page - unlock a locked page - * @page: the page + * folio_unlock - Unlock a locked folio. + * @folio: The folio. * - * Unlocks the page and wakes up sleepers in wait_on_page_locked(). - * Also wakes sleepers in wait_on_page_writeback() because the wakeup - * mechanism between PageLocked pages and PageWriteback pages is shared. - * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. + * Unlocks the folio and wakes up any thread sleeping on the page lock. * - * Note that this depends on PG_waiters being the sign bit in the byte - * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to - * clear the PG_locked bit and test PG_waiters at the same time fairly - * portably (architectures that do LL/SC can test any bit, while x86 can - * test the sign bit). + * Context: May be called from interrupt or process context. May not be + * called from NMI context. */ -void unlock_page(struct page *page) +void folio_unlock(struct folio *folio) { + /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); - page = compound_head(page); - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) - wake_up_page_bit(page, PG_locked); + BUILD_BUG_ON(PG_locked > 7); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio, 0))) + folio_wake_bit(folio, PG_locked); } -EXPORT_SYMBOL(unlock_page); +EXPORT_SYMBOL(folio_unlock); /** - * end_page_private_2 - Clear PG_private_2 and release any waiters - * @page: The page + * folio_end_private_2 - Clear PG_private_2 and wake any waiters. + * @folio: The folio. * - * Clear the PG_private_2 bit on a page and wake up any sleepers waiting for - * this. The page ref held for PG_private_2 being set is released. + * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for + * it. The folio reference held for PG_private_2 being set is released. * - * This is, for example, used when a netfs page is being written to a local - * disk cache, thereby allowing writes to the cache for the same page to be + * This is, for example, used when a netfs folio is being written to a local + * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ -void end_page_private_2(struct page *page) +void folio_end_private_2(struct folio *folio) { - page = compound_head(page); - VM_BUG_ON_PAGE(!PagePrivate2(page), page); - clear_bit_unlock(PG_private_2, &page->flags); - wake_up_page_bit(page, PG_private_2); - put_page(page); + VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); + clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); + folio_wake_bit(folio, PG_private_2); + folio_put(folio); } -EXPORT_SYMBOL(end_page_private_2); +EXPORT_SYMBOL(folio_end_private_2); /** - * wait_on_page_private_2 - Wait for PG_private_2 to be cleared on a page - * @page: The page to wait on + * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. + * @folio: The folio to wait on. * - * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page. + * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio. */ -void wait_on_page_private_2(struct page *page) +void folio_wait_private_2(struct folio *folio) { - page = compound_head(page); - while (PagePrivate2(page)) - wait_on_page_bit(page, PG_private_2); + while (folio_test_private_2(folio)) + folio_wait_bit(folio, PG_private_2); } -EXPORT_SYMBOL(wait_on_page_private_2); +EXPORT_SYMBOL(folio_wait_private_2); /** - * wait_on_page_private_2_killable - Wait for PG_private_2 to be cleared on a page - * @page: The page to wait on + * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. + * @folio: The folio to wait on. * - * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page or until a + * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio or until a * fatal signal is received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ -int wait_on_page_private_2_killable(struct page *page) +int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; - page = compound_head(page); - while (PagePrivate2(page)) { - ret = wait_on_page_bit_killable(page, PG_private_2); + while (folio_test_private_2(folio)) { + ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } -EXPORT_SYMBOL(wait_on_page_private_2_killable); +EXPORT_SYMBOL(folio_wait_private_2_killable); /** - * end_page_writeback - end writeback against a page - * @page: the page + * folio_end_writeback - End writeback against a folio. + * @folio: The folio. */ -void end_page_writeback(struct page *page) +void folio_end_writeback(struct folio *folio) { /* - * TestClearPageReclaim could be used here but it is an atomic - * operation and overkill in this particular case. Failing to - * shuffle a page marked for immediate reclaim is too mild to - * justify taking an atomic operation penalty at the end of - * ever page writeback. + * folio_test_clear_reclaim() could be used here but it is an + * atomic operation and overkill in this particular case. Failing + * to shuffle a folio marked for immediate reclaim is too mild + * a gain to justify taking an atomic operation penalty at the + * end of every folio writeback. */ - if (PageReclaim(page)) { - ClearPageReclaim(page); - rotate_reclaimable_page(page); + if (folio_test_reclaim(folio)) { + folio_clear_reclaim(folio); + folio_rotate_reclaimable(folio); } /* - * Writeback does not hold a page reference of its own, relying + * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. - * But here we must make sure that the page is not freed and - * reused before the wake_up_page(). + * But here we must make sure that the folio is not freed and + * reused before the folio_wake(). */ - get_page(page); - if (!test_clear_page_writeback(page)) + folio_get(folio); + if (!__folio_end_writeback(folio)) BUG(); smp_mb__after_atomic(); - wake_up_page(page, PG_writeback); - put_page(page); + folio_wake(folio, PG_writeback); + folio_put(folio); } -EXPORT_SYMBOL(end_page_writeback); +EXPORT_SYMBOL(folio_end_writeback); /* * After completing I/O on a page, call this routine to update the page @@ -1638,39 +1626,35 @@ void page_endio(struct page *page, bool is_write, int err) EXPORT_SYMBOL_GPL(page_endio); /** - * __lock_page - get a lock on the page, assuming we need to sleep to get it - * @__page: the page to lock + * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. + * @folio: The folio to lock */ -void __lock_page(struct page *__page) +void __folio_lock(struct folio *folio) { - struct page *page = compound_head(__page); - wait_queue_head_t *q = page_waitqueue(page); - wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, + folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } -EXPORT_SYMBOL(__lock_page); +EXPORT_SYMBOL(__folio_lock); -int __lock_page_killable(struct page *__page) +int __folio_lock_killable(struct folio *folio) { - struct page *page = compound_head(__page); - wait_queue_head_t *q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, + return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } -EXPORT_SYMBOL_GPL(__lock_page_killable); +EXPORT_SYMBOL_GPL(__folio_lock_killable); -int __lock_page_async(struct page *page, struct wait_page_queue *wait) +static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { - struct wait_queue_head *q = page_waitqueue(page); + struct wait_queue_head *q = folio_waitqueue(folio); int ret = 0; - wait->page = page; + wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); - SetPageWaiters(page); - ret = !trylock_page(page); + folio_set_waiters(folio); + ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's @@ -1687,16 +1671,16 @@ int __lock_page_async(struct page *page, struct wait_page_queue *wait) /* * Return values: - * 1 - page is locked; mmap_lock is still held. - * 0 - page is not locked. + * true - folio is locked; mmap_lock is still held. + * false - folio is not locked. * mmap_lock has been released (mmap_read_unlock(), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in * which case mmap_lock is still held. * - * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 - * with the page locked and the mmap_lock unperturbed. + * If neither ALLOW_RETRY nor KILLABLE are set, will always return true + * with the folio locked and the mmap_lock unperturbed. */ -int __lock_page_or_retry(struct page *page, struct mm_struct *mm, +bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, unsigned int flags) { if (fault_flag_allow_retry_first(flags)) { @@ -1705,28 +1689,28 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) - return 0; + return false; mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) - wait_on_page_locked_killable(page); + folio_wait_locked_killable(folio); else - wait_on_page_locked(page); - return 0; + folio_wait_locked(folio); + return false; } if (flags & FAULT_FLAG_KILLABLE) { - int ret; + bool ret; - ret = __lock_page_killable(page); + ret = __folio_lock_killable(folio); if (ret) { mmap_read_unlock(mm); - return 0; + return false; } } else { - __lock_page(page); + __folio_lock(folio); } - return 1; + return true; } /** @@ -1802,143 +1786,155 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, EXPORT_SYMBOL(page_cache_prev_miss); /* + * Lockless page cache protocol: + * On the lookup side: + * 1. Load the folio from i_pages + * 2. Increment the refcount if it's not zero + * 3. If the folio is not found by xas_reload(), put the refcount and retry + * + * On the removal side: + * A. Freeze the page (by zeroing the refcount if nobody else has a reference) + * B. Remove the page from i_pages + * C. Return the page to the page allocator + * + * This means that any page may have its reference count temporarily + * increased by a speculative page cache (or fast GUP) lookup as it can + * be allocated by another user before the RCU grace period expires. + * Because the refcount temporarily acquired here may end up being the + * last refcount on the page, any page allocation must be freeable by + * folio_put(). + */ + +/* * mapping_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * - * Looks up the page cache slot at @mapping & @index. If there is a - * page cache page, the head page is returned with an increased refcount. + * Looks up the page cache entry at @mapping & @index. If it is a folio, + * it is returned with an increased refcount. If it is a shadow entry + * of a previously evicted folio, or a swap entry from shmem/tmpfs, + * it is returned without further action. * - * If the slot holds a shadow entry of a previously evicted page, or a - * swap entry from shmem/tmpfs, it is returned. - * - * Return: The head page or shadow entry, %NULL if nothing is found. + * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ -static struct page *mapping_get_entry(struct address_space *mapping, - pgoff_t index) +static void *mapping_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); - struct page *page; + struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); - page = xas_load(&xas); - if (xas_retry(&xas, page)) + folio = xas_load(&xas); + if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ - if (!page || xa_is_value(page)) + if (!folio || xa_is_value(folio)) goto out; - if (!page_cache_get_speculative(page)) + if (!folio_try_get_rcu(folio)) goto repeat; - /* - * Has the page moved or been split? - * This is part of the lockless pagecache protocol. See - * include/linux/pagemap.h for details. - */ - if (unlikely(page != xas_reload(&xas))) { - put_page(page); + if (unlikely(folio != xas_reload(&xas))) { + folio_put(folio); goto repeat; } out: rcu_read_unlock(); - return page; + return folio; } /** - * pagecache_get_page - Find and get a reference to a page. + * __filemap_get_folio - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. - * @fgp_flags: %FGP flags modify how the page is returned. - * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified. + * @fgp_flags: %FGP flags modify how the folio is returned. + * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * @fgp_flags can be zero or more of these flags: * - * * %FGP_ACCESSED - The page will be marked accessed. - * * %FGP_LOCK - The page is returned locked. - * * %FGP_HEAD - If the page is present and a THP, return the head page - * rather than the exact page specified by the index. + * * %FGP_ACCESSED - The folio will be marked accessed. + * * %FGP_LOCK - The folio is returned locked. * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it - * instead of allocating a new page to replace it. + * instead of allocating a new folio to replace it. * * %FGP_CREAT - If no page is present then a new page is allocated using - * @gfp_mask and added to the page cache and the VM's LRU list. + * @gfp and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * page is already in cache. If the page was allocated, unlock it before * returning so the caller can do the same dance. - * * %FGP_WRITE - The page will be written - * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask - * * %FGP_NOWAIT - Don't get blocked by page lock + * * %FGP_WRITE - The page will be written to by the caller. + * * %FGP_NOFS - __GFP_FS will get cleared in gfp. + * * %FGP_NOWAIT - Don't get blocked by page lock. + * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If there is a page cache page, it is returned with an increased refcount. * - * Return: The found page or %NULL otherwise. + * Return: The found folio or %NULL otherwise. */ -struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp_mask) +struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp) { - struct page *page; + struct folio *folio; repeat: - page = mapping_get_entry(mapping, index); - if (xa_is_value(page)) { + folio = mapping_get_entry(mapping, index); + if (xa_is_value(folio)) { if (fgp_flags & FGP_ENTRY) - return page; - page = NULL; + return folio; + folio = NULL; } - if (!page) + if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); return NULL; } } else { - lock_page(page); + folio_lock(folio); } /* Has the page been truncated? */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - put_page(page); + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); goto repeat; } - VM_BUG_ON_PAGE(!thp_contains(page, index), page); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) - mark_page_accessed(page); + folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ - if (page_is_idle(page)) - clear_page_idle(page); + if (folio_test_idle(folio)) + folio_clear_idle(folio); } - if (!(fgp_flags & FGP_HEAD)) - page = find_subpage(page, index); + if (fgp_flags & FGP_STABLE) + folio_wait_stable(folio); no_page: - if (!page && (fgp_flags & FGP_CREAT)) { + if (!folio && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) - gfp_mask |= __GFP_WRITE; + gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) - gfp_mask &= ~__GFP_FS; + gfp &= ~__GFP_FS; - page = __page_cache_alloc(gfp_mask); - if (!page) + folio = filemap_alloc_folio(gfp, 0); + if (!folio) return NULL; if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) @@ -1946,27 +1942,27 @@ no_page: /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) - __SetPageReferenced(page); + __folio_set_referenced(folio); - err = add_to_page_cache_lru(page, mapping, index, gfp_mask); + err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { - put_page(page); - page = NULL; + folio_put(folio); + folio = NULL; if (err == -EEXIST) goto repeat; } /* - * add_to_page_cache_lru locks the page, and for mmap we expect - * an unlocked page. + * filemap_add_folio locks the page, and for mmap + * we expect an unlocked page. */ - if (page && (fgp_flags & FGP_FOR_MMAP)) - unlock_page(page); + if (folio && (fgp_flags & FGP_FOR_MMAP)) + folio_unlock(folio); } - return page; + return folio; } -EXPORT_SYMBOL(pagecache_get_page); +EXPORT_SYMBOL(__filemap_get_folio); static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) @@ -2421,6 +2417,7 @@ static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, struct iov_iter *iter, struct page *page) { + struct folio *folio = page_folio(page); int error; if (iocb->ki_flags & IOCB_NOWAIT) { @@ -2430,40 +2427,40 @@ static int filemap_update_page(struct kiocb *iocb, filemap_invalidate_lock_shared(mapping); } - if (!trylock_page(page)) { + if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); - put_and_wait_on_page_locked(page, TASK_KILLABLE); + put_and_wait_on_page_locked(&folio->page, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } - error = __lock_page_async(page, iocb->ki_waitq); + error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; - if (!page->mapping) + if (!folio->mapping) goto unlock; error = 0; - if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page)) + if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, &folio->page)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; - error = filemap_read_page(iocb->ki_filp, mapping, page); + error = filemap_read_page(iocb->ki_filp, mapping, &folio->page); goto unlock_mapping; unlock: - unlock_page(page); + folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) - put_page(page); + folio_put(folio); return error; } @@ -2900,7 +2897,9 @@ unlock: static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, struct file **fpin) { - if (trylock_page(page)) + struct folio *folio = page_folio(page); + + if (folio_trylock(folio)) return 1; /* @@ -2913,7 +2912,7 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { - if (__lock_page_killable(page)) { + if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals @@ -2925,11 +2924,11 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, return 0; } } else - __lock_page(page); + __folio_lock(folio); + return 1; } - /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have @@ -3708,28 +3707,6 @@ out: } EXPORT_SYMBOL(generic_file_direct_write); -/* - * Find or create a page at the given pagecache position. Return the locked - * page. This function is specifically for buffered writes. - */ -struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags) -{ - struct page *page; - int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; - - if (flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; - - page = pagecache_get_page(mapping, index, fgp_flags, - mapping_gfp_mask(mapping)); - if (page) - wait_for_stable_page(page); - - return page; -} -EXPORT_SYMBOL(grab_cache_page_write_begin); - ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { diff --git a/mm/folio-compat.c b/mm/folio-compat.c new file mode 100644 index 000000000000..5b6ae1da314e --- /dev/null +++ b/mm/folio-compat.c @@ -0,0 +1,142 @@ +/* + * Compatibility functions which bloat the callers too much to make inline. + * All of the callers of these functions should be converted to use folios + * eventually. + */ + +#include <linux/migrate.h> +#include <linux/pagemap.h> +#include <linux/swap.h> + +struct address_space *page_mapping(struct page *page) +{ + return folio_mapping(page_folio(page)); +} +EXPORT_SYMBOL(page_mapping); + +void unlock_page(struct page *page) +{ + return folio_unlock(page_folio(page)); +} +EXPORT_SYMBOL(unlock_page); + +void end_page_writeback(struct page *page) +{ + return folio_end_writeback(page_folio(page)); +} +EXPORT_SYMBOL(end_page_writeback); + +void wait_on_page_writeback(struct page *page) +{ + return folio_wait_writeback(page_folio(page)); +} +EXPORT_SYMBOL_GPL(wait_on_page_writeback); + +void wait_for_stable_page(struct page *page) +{ + return folio_wait_stable(page_folio(page)); +} +EXPORT_SYMBOL_GPL(wait_for_stable_page); + +bool page_mapped(struct page *page) +{ + return folio_mapped(page_folio(page)); +} +EXPORT_SYMBOL(page_mapped); + +void mark_page_accessed(struct page *page) +{ + folio_mark_accessed(page_folio(page)); +} +EXPORT_SYMBOL(mark_page_accessed); + +#ifdef CONFIG_MIGRATION +int migrate_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page, int extra_count) +{ + return folio_migrate_mapping(mapping, page_folio(newpage), + page_folio(page), extra_count); +} +EXPORT_SYMBOL(migrate_page_move_mapping); + +void migrate_page_states(struct page *newpage, struct page *page) +{ + folio_migrate_flags(page_folio(newpage), page_folio(page)); +} +EXPORT_SYMBOL(migrate_page_states); + +void migrate_page_copy(struct page *newpage, struct page *page) +{ + folio_migrate_copy(page_folio(newpage), page_folio(page)); +} +EXPORT_SYMBOL(migrate_page_copy); +#endif + +bool set_page_writeback(struct page *page) +{ + return folio_start_writeback(page_folio(page)); +} +EXPORT_SYMBOL(set_page_writeback); + +bool set_page_dirty(struct page *page) +{ + return folio_mark_dirty(page_folio(page)); +} +EXPORT_SYMBOL(set_page_dirty); + +int __set_page_dirty_nobuffers(struct page *page) +{ + return filemap_dirty_folio(page_mapping(page), page_folio(page)); +} +EXPORT_SYMBOL(__set_page_dirty_nobuffers); + +bool clear_page_dirty_for_io(struct page *page) +{ + return folio_clear_dirty_for_io(page_folio(page)); +} +EXPORT_SYMBOL(clear_page_dirty_for_io); + +bool redirty_page_for_writepage(struct writeback_control *wbc, + struct page *page) +{ + return folio_redirty_for_writepage(wbc, page_folio(page)); +} +EXPORT_SYMBOL(redirty_page_for_writepage); + +void lru_cache_add(struct page *page) +{ + folio_add_lru(page_folio(page)); +} +EXPORT_SYMBOL(lru_cache_add); + +int add_to_page_cache_lru(struct page *page, struct address_space *mapping, + pgoff_t index, gfp_t gfp) +{ + return filemap_add_folio(mapping, page_folio(page), index, gfp); +} +EXPORT_SYMBOL(add_to_page_cache_lru); + +noinline +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp) +{ + struct folio *folio; + + folio = __filemap_get_folio(mapping, index, fgp_flags, gfp); + if ((fgp_flags & FGP_HEAD) || !folio || xa_is_value(folio)) + return &folio->page; + return folio_file_page(folio, index); +} +EXPORT_SYMBOL(pagecache_get_page); + +struct page *grab_cache_page_write_begin(struct address_space *mapping, + pgoff_t index, unsigned flags) +{ + unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + + if (flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + return pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); +} +EXPORT_SYMBOL(grab_cache_page_write_begin); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 92192cb086c7..e5483347291c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -603,7 +603,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_charge(page, vma->vm_mm, gfp)) { + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); @@ -2405,7 +2405,8 @@ static void __split_huge_page_tail(struct page *head, int tail, static void __split_huge_page(struct page *page, struct list_head *list, pgoff_t end) { - struct page *head = compound_head(page); + struct folio *folio = page_folio(page); + struct page *head = &folio->page; struct lruvec *lruvec; struct address_space *swap_cache = NULL; unsigned long offset = 0; @@ -2424,7 +2425,9 @@ static void __split_huge_page(struct page *page, struct list_head *list, } /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ - lruvec = lock_page_lruvec(head); + lruvec = folio_lruvec_lock(folio); + + ClearPageHasHWPoisoned(head); for (i = nr - 1; i >= 1; i--) { __split_huge_page_tail(head, i, lruvec, list); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 95dc7b83381f..6378c1066459 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5302,7 +5302,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, *pagep = NULL; goto out; } - copy_huge_page(page, *pagep); + folio_copy(page_folio(page), page_folio(*pagep)); put_page(*pagep); *pagep = NULL; } diff --git a/mm/internal.h b/mm/internal.h index cf3cb933eba3..b1001ebeb286 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -34,7 +34,16 @@ void page_writeback_init(void); +static inline void *folio_raw_mapping(struct folio *folio) +{ + unsigned long mapping = (unsigned long)folio->mapping; + + return (void *)(mapping & ~PAGE_MAPPING_FLAGS); +} + vm_fault_t do_swap_page(struct vm_fault *vmf); +void folio_rotate_reclaimable(struct folio *folio); +bool __folio_end_writeback(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); @@ -63,17 +72,28 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, pgoff_t end, struct pagevec *pvec, pgoff_t *indices); /** - * page_evictable - test whether a page is evictable - * @page: the page to test + * folio_evictable - Test whether a folio is evictable. + * @folio: The folio to test. * - * Test whether page is evictable--i.e., should be placed on active/inactive - * lists vs unevictable list. - * - * Reasons page might not be evictable: - * (1) page's mapping marked unevictable - * (2) page is part of an mlocked VMA + * Test whether @folio is evictable -- i.e., should be placed on + * active/inactive lists vs unevictable list. * + * Reasons folio might not be evictable: + * 1. folio's mapping marked unevictable + * 2. One of the pages in the folio is part of an mlocked VMA */ +static inline bool folio_evictable(struct folio *folio) +{ + bool ret; + + /* Prevent address_space of inode and swap cache from being freed */ + rcu_read_lock(); + ret = !mapping_unevictable(folio_mapping(folio)) && + !folio_test_mlocked(folio); + rcu_read_unlock(); + return ret; +} + static inline bool page_evictable(struct page *page) { bool ret; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 045cc579f724..5f02fda6f265 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -445,22 +445,25 @@ static bool hugepage_vma_check(struct vm_area_struct *vma, if (!transhuge_vma_enabled(vma, vm_flags)) return false; + if (vma->vm_file && !IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - + vma->vm_pgoff, HPAGE_PMD_NR)) + return false; + /* Enabled via shmem mount options or sysfs settings. */ - if (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) { - return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, - HPAGE_PMD_NR); - } + if (shmem_file(vma->vm_file)) + return shmem_huge_enabled(vma); /* THP settings require madvise. */ if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) return false; - /* Read-only file mappings need to be aligned for THP to work. */ + /* Only regular file is valid */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && - !inode_is_open_for_write(vma->vm_file->f_inode) && (vm_flags & VM_EXEC)) { - return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, - HPAGE_PMD_NR); + struct inode *inode = vma->vm_file->f_inode; + + return !inode_is_open_for_write(inode) && + S_ISREG(inode->i_mode); } if (!vma->anon_vma || vma->vm_ops) @@ -1087,7 +1090,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { + if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1211,7 +1214,7 @@ out_up_write: mmap_write_unlock(mm); out_nolock: if (!IS_ERR_OR_NULL(*hpage)) - mem_cgroup_uncharge(*hpage); + mem_cgroup_uncharge(page_folio(*hpage)); trace_mm_collapse_huge_page(mm, isolated, result); return; } @@ -1658,7 +1661,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { + if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } @@ -1763,6 +1766,10 @@ static void collapse_file(struct mm_struct *mm, filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; + } else if (PageWriteback(page)) { + xas_unlock_irq(&xas); + result = SCAN_FAIL; + goto xa_unlocked; } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); @@ -1798,7 +1805,8 @@ static void collapse_file(struct mm_struct *mm, goto out_unlock; } - if (!is_shmem && PageDirty(page)) { + if (!is_shmem && (PageDirty(page) || + PageWriteback(page))) { /* * khugepaged only works on read-only fd, so this * page is dirty because it hasn't been flushed @@ -1975,7 +1983,7 @@ xa_unlocked: out: VM_BUG_ON(!list_empty(&pagelist)); if (!IS_ERR_OR_NULL(*hpage)) - mem_cgroup_uncharge(*hpage); + mem_cgroup_uncharge(page_folio(*hpage)); /* TODO: tracepoints */ } @@ -751,7 +751,7 @@ stale: /* * We come here from above when page->mapping or !PageSwapCache * suggests that the node is stale; but it might be under migration. - * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(), + * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. */ smp_rmb(); @@ -852,9 +852,14 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma, return err; } +static inline struct stable_node *folio_stable_node(struct folio *folio) +{ + return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL; +} + static inline struct stable_node *page_stable_node(struct page *page) { - return PageKsm(page) ? page_rmapping(page) : NULL; + return folio_stable_node(page_folio(page)); } static inline void set_page_stable_node(struct page *page, @@ -2578,7 +2583,8 @@ struct page *ksm_might_need_to_copy(struct page *page, return page; /* let do_swap_page report the error */ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) { + if (new_page && + mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) { put_page(new_page); new_page = NULL; } @@ -2658,26 +2664,26 @@ again: } #ifdef CONFIG_MIGRATION -void ksm_migrate_page(struct page *newpage, struct page *oldpage) +void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) { struct stable_node *stable_node; - VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); - VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); + VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio); - stable_node = page_stable_node(newpage); + stable_node = folio_stable_node(folio); if (stable_node) { - VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage); - stable_node->kpfn = page_to_pfn(newpage); + VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio); + stable_node->kpfn = folio_pfn(newfolio); /* - * newpage->mapping was set in advance; now we need smp_wmb() + * newfolio->mapping was set in advance; now we need smp_wmb() * to make sure that the new stable_node->kpfn is visible - * to get_ksm_page() before it can see that oldpage->mapping - * has gone stale (or that PageSwapCache has been cleared). + * to get_ksm_page() before it can see that folio->mapping + * has gone stale (or that folio_test_swapcache has been cleared). */ smp_wmb(); - set_page_stable_node(oldpage, NULL); + set_page_stable_node(&folio->page, NULL); } } #endif /* CONFIG_MIGRATION */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6da5020a8656..8dab23a71fc4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -456,28 +456,6 @@ ino_t page_cgroup_ino(struct page *page) return ino; } -static struct mem_cgroup_per_node * -mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page) -{ - int nid = page_to_nid(page); - - return memcg->nodeinfo[nid]; -} - -static struct mem_cgroup_tree_per_node * -soft_limit_tree_node(int nid) -{ - return soft_limit_tree.rb_tree_per_node[nid]; -} - -static struct mem_cgroup_tree_per_node * -soft_limit_tree_from_page(struct page *page) -{ - int nid = page_to_nid(page); - - return soft_limit_tree.rb_tree_per_node[nid]; -} - static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz, struct mem_cgroup_tree_per_node *mctz, unsigned long new_usage_in_excess) @@ -548,13 +526,13 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg) return excess; } -static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) +static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid) { unsigned long excess; struct mem_cgroup_per_node *mz; struct mem_cgroup_tree_per_node *mctz; - mctz = soft_limit_tree_from_page(page); + mctz = soft_limit_tree.rb_tree_per_node[nid]; if (!mctz) return; /* @@ -562,7 +540,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) * because their event counter is not touched. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_page_nodeinfo(memcg, page); + mz = memcg->nodeinfo[nid]; excess = soft_limit_excess(memcg); /* * We have to update the tree if mz is on RB-tree or @@ -593,7 +571,7 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) for_each_node(nid) { mz = memcg->nodeinfo[nid]; - mctz = soft_limit_tree_node(nid); + mctz = soft_limit_tree.rb_tree_per_node[nid]; if (mctz) mem_cgroup_remove_exceeded(mz, mctz); } @@ -799,7 +777,6 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) } static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, - struct page *page, int nr_pages) { /* pagein of a big page is an event. So, ignore page size */ @@ -842,7 +819,7 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, * Check events in order. * */ -static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) +static void memcg_check_events(struct mem_cgroup *memcg, int nid) { /* threshold event is triggered in finer grain than soft limit */ if (unlikely(mem_cgroup_event_ratelimit(memcg, @@ -853,7 +830,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) MEM_CGROUP_TARGET_SOFTLIMIT); mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) - mem_cgroup_update_tree(memcg, page); + mem_cgroup_update_tree(memcg, nid); } } @@ -1149,64 +1126,88 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, } #ifdef CONFIG_DEBUG_VM -void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; - memcg = page_memcg(page); + memcg = folio_memcg(folio); if (!memcg) - VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != root_mem_cgroup, page); + VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != root_mem_cgroup, folio); else - VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != memcg, page); + VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio); } #endif /** - * lock_page_lruvec - lock and return lruvec for a given page. - * @page: the page + * folio_lruvec_lock - Lock the lruvec for a folio. + * @folio: Pointer to the folio. * * These functions are safe to use under any of the following conditions: - * - page locked - * - PageLRU cleared - * - lock_page_memcg() - * - page->_refcount is zero + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held. */ -struct lruvec *lock_page_lruvec(struct page *page) +struct lruvec *folio_lruvec_lock(struct folio *folio) { - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = mem_cgroup_page_lruvec(page); spin_lock(&lruvec->lru_lock); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } -struct lruvec *lock_page_lruvec_irq(struct page *page) +/** + * folio_lruvec_lock_irq - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held and interrupts + * disabled. + */ +struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = mem_cgroup_page_lruvec(page); spin_lock_irq(&lruvec->lru_lock); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } -struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags) +/** + * folio_lruvec_lock_irqsave - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * @flags: Pointer to irqsave flags. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held and interrupts + * disabled. + */ +struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, + unsigned long *flags) { - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = mem_cgroup_page_lruvec(page); spin_lock_irqsave(&lruvec->lru_lock, *flags); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } @@ -1956,18 +1957,17 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) } /** - * lock_page_memcg - lock a page and memcg binding - * @page: the page + * folio_memcg_lock - Bind a folio to its memcg. + * @folio: The folio. * - * This function protects unlocked LRU pages from being moved to + * This function prevents unlocked LRU folios from being moved to * another cgroup. * - * It ensures lifetime of the locked memcg. Caller is responsible - * for the lifetime of the page. + * It ensures lifetime of the bound memcg. The caller is responsible + * for the lifetime of the folio. */ -void lock_page_memcg(struct page *page) +void folio_memcg_lock(struct folio *folio) { - struct page *head = compound_head(page); /* rmap on tail pages */ struct mem_cgroup *memcg; unsigned long flags; @@ -1981,7 +1981,7 @@ void lock_page_memcg(struct page *page) if (mem_cgroup_disabled()) return; again: - memcg = page_memcg(head); + memcg = folio_memcg(folio); if (unlikely(!memcg)) return; @@ -1995,7 +1995,7 @@ again: return; spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != page_memcg(head)) { + if (memcg != folio_memcg(folio)) { spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } @@ -2009,9 +2009,15 @@ again: memcg->move_lock_task = current; memcg->move_lock_flags = flags; } +EXPORT_SYMBOL(folio_memcg_lock); + +void lock_page_memcg(struct page *page) +{ + folio_memcg_lock(page_folio(page)); +} EXPORT_SYMBOL(lock_page_memcg); -static void __unlock_page_memcg(struct mem_cgroup *memcg) +static void __folio_memcg_unlock(struct mem_cgroup *memcg) { if (memcg && memcg->move_lock_task == current) { unsigned long flags = memcg->move_lock_flags; @@ -2026,14 +2032,22 @@ static void __unlock_page_memcg(struct mem_cgroup *memcg) } /** - * unlock_page_memcg - unlock a page and memcg binding - * @page: the page + * folio_memcg_unlock - Release the binding between a folio and its memcg. + * @folio: The folio. + * + * This releases the binding created by folio_memcg_lock(). This does + * not change the accounting of this folio to its memcg, but it does + * permit others to change it. */ -void unlock_page_memcg(struct page *page) +void folio_memcg_unlock(struct folio *folio) { - struct page *head = compound_head(page); + __folio_memcg_unlock(folio_memcg(folio)); +} +EXPORT_SYMBOL(folio_memcg_unlock); - __unlock_page_memcg(page_memcg(head)); +void unlock_page_memcg(struct page *page) +{ + folio_memcg_unlock(page_folio(page)); } EXPORT_SYMBOL(unlock_page_memcg); @@ -2734,9 +2748,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) } #endif -static void commit_charge(struct page *page, struct mem_cgroup *memcg) +static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) { - VM_BUG_ON_PAGE(page_memcg(page), page); + VM_BUG_ON_FOLIO(folio_memcg(folio), folio); /* * Any of the following ensures page's memcg stability: * @@ -2745,7 +2759,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg) * - lock_page_memcg() * - exclusive reference */ - page->memcg_data = (unsigned long)memcg; + folio->memcg_data = (unsigned long)memcg; } static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) @@ -3015,15 +3029,16 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) */ void __memcg_kmem_uncharge_page(struct page *page, int order) { + struct folio *folio = page_folio(page); struct obj_cgroup *objcg; unsigned int nr_pages = 1 << order; - if (!PageMemcgKmem(page)) + if (!folio_memcg_kmem(folio)) return; - objcg = __page_objcg(page); + objcg = __folio_objcg(folio); obj_cgroup_uncharge_pages(objcg, nr_pages); - page->memcg_data = 0; + folio->memcg_data = 0; obj_cgroup_put(objcg); } @@ -3257,17 +3272,18 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) */ void split_page_memcg(struct page *head, unsigned int nr) { - struct mem_cgroup *memcg = page_memcg(head); + struct folio *folio = page_folio(head); + struct mem_cgroup *memcg = folio_memcg(folio); int i; if (mem_cgroup_disabled() || !memcg) return; for (i = 1; i < nr; i++) - head[i].memcg_data = head->memcg_data; + folio_page(folio, i)->memcg_data = folio->memcg_data; - if (PageMemcgKmem(head)) - obj_cgroup_get_many(__page_objcg(head), nr - 1); + if (folio_memcg_kmem(folio)) + obj_cgroup_get_many(__folio_objcg(folio), nr - 1); else css_get_many(&memcg->css, nr - 1); } @@ -3381,7 +3397,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, if (order > 0) return 0; - mctz = soft_limit_tree_node(pgdat->node_id); + mctz = soft_limit_tree.rb_tree_per_node[pgdat->node_id]; /* * Do not even bother to check the largest node if the root @@ -4537,17 +4553,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, * As being wrong occasionally doesn't matter, updates and accesses to the * records are lockless and racy. */ -void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, +void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb) { - struct mem_cgroup *memcg = page_memcg(page); + struct mem_cgroup *memcg = folio_memcg(folio); struct memcg_cgwb_frn *frn; u64 now = get_jiffies_64(); u64 oldest_at = now; int oldest = -1; int i; - trace_track_foreign_dirty(page, wb); + trace_track_foreign_dirty(folio, wb); /* * Pick the slot to use. If there is already a slot for @wb, keep @@ -5575,38 +5591,39 @@ static int mem_cgroup_move_account(struct page *page, struct mem_cgroup *from, struct mem_cgroup *to) { + struct folio *folio = page_folio(page); struct lruvec *from_vec, *to_vec; struct pglist_data *pgdat; - unsigned int nr_pages = compound ? thp_nr_pages(page) : 1; - int ret; + unsigned int nr_pages = compound ? folio_nr_pages(folio) : 1; + int nid, ret; VM_BUG_ON(from == to); - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON(compound && !PageTransHuge(page)); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + VM_BUG_ON(compound && !folio_test_multi(folio)); /* * Prevent mem_cgroup_migrate() from looking at * page's memory cgroup of its source page while we change it. */ ret = -EBUSY; - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto out; ret = -EINVAL; - if (page_memcg(page) != from) + if (folio_memcg(folio) != from) goto out_unlock; - pgdat = page_pgdat(page); + pgdat = folio_pgdat(folio); from_vec = mem_cgroup_lruvec(from, pgdat); to_vec = mem_cgroup_lruvec(to, pgdat); - lock_page_memcg(page); + folio_memcg_lock(folio); - if (PageAnon(page)) { - if (page_mapped(page)) { + if (folio_test_anon(folio)) { + if (folio_mapped(folio)) { __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); - if (PageTransHuge(page)) { + if (folio_test_transhuge(folio)) { __mod_lruvec_state(from_vec, NR_ANON_THPS, -nr_pages); __mod_lruvec_state(to_vec, NR_ANON_THPS, @@ -5617,18 +5634,18 @@ static int mem_cgroup_move_account(struct page *page, __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); - if (PageSwapBacked(page)) { + if (folio_test_swapbacked(folio)) { __mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages); __mod_lruvec_state(to_vec, NR_SHMEM, nr_pages); } - if (page_mapped(page)) { + if (folio_mapped(folio)) { __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); } - if (PageDirty(page)) { - struct address_space *mapping = page_mapping(page); + if (folio_test_dirty(folio)) { + struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { __mod_lruvec_state(from_vec, NR_FILE_DIRTY, @@ -5639,7 +5656,7 @@ static int mem_cgroup_move_account(struct page *page, } } - if (PageWriteback(page)) { + if (folio_test_writeback(folio)) { __mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages); __mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages); } @@ -5662,20 +5679,21 @@ static int mem_cgroup_move_account(struct page *page, css_get(&to->css); css_put(&from->css); - page->memcg_data = (unsigned long)to; + folio->memcg_data = (unsigned long)to; - __unlock_page_memcg(from); + __folio_memcg_unlock(from); ret = 0; + nid = folio_nid(folio); local_irq_disable(); - mem_cgroup_charge_statistics(to, page, nr_pages); - memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, -nr_pages); - memcg_check_events(from, page); + mem_cgroup_charge_statistics(to, nr_pages); + memcg_check_events(to, nid); + mem_cgroup_charge_statistics(from, -nr_pages); + memcg_check_events(from, nid); local_irq_enable(); out_unlock: - unlock_page(page); + folio_unlock(folio); out: return ret; } @@ -6680,9 +6698,10 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root, atomic_long_read(&parent->memory.children_low_usage))); } -static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) +static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg, + gfp_t gfp) { - unsigned int nr_pages = thp_nr_pages(page); + long nr_pages = folio_nr_pages(folio); int ret; ret = try_charge(memcg, gfp, nr_pages); @@ -6690,38 +6709,23 @@ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) goto out; css_get(&memcg->css); - commit_charge(page, memcg); + commit_charge(folio, memcg); local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, nr_pages); - memcg_check_events(memcg, page); + mem_cgroup_charge_statistics(memcg, nr_pages); + memcg_check_events(memcg, folio_nid(folio)); local_irq_enable(); out: return ret; } -/** - * __mem_cgroup_charge - charge a newly allocated page to a cgroup - * @page: page to charge - * @mm: mm context of the victim - * @gfp_mask: reclaim mode - * - * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. if @mm is NULL, try to - * charge to the active memcg. - * - * Do not use this for pages allocated for swapin. - * - * Returns 0 on success. Otherwise, an error code is returned. - */ -int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { struct mem_cgroup *memcg; int ret; memcg = get_mem_cgroup_from_mm(mm); - ret = charge_memcg(page, memcg, gfp_mask); + ret = charge_memcg(folio, memcg, gfp); css_put(&memcg->css); return ret; @@ -6742,6 +6746,7 @@ int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { + struct folio *folio = page_folio(page); struct mem_cgroup *memcg; unsigned short id; int ret; @@ -6756,7 +6761,7 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, memcg = get_mem_cgroup_from_mm(mm); rcu_read_unlock(); - ret = charge_memcg(page, memcg, gfp); + ret = charge_memcg(folio, memcg, gfp); css_put(&memcg->css); return ret; @@ -6800,7 +6805,7 @@ struct uncharge_gather { unsigned long nr_memory; unsigned long pgpgout; unsigned long nr_kmem; - struct page *dummy_page; + int nid; }; static inline void uncharge_gather_clear(struct uncharge_gather *ug) @@ -6824,36 +6829,36 @@ static void uncharge_batch(const struct uncharge_gather *ug) local_irq_save(flags); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_memory); - memcg_check_events(ug->memcg, ug->dummy_page); + memcg_check_events(ug->memcg, ug->nid); local_irq_restore(flags); - /* drop reference from uncharge_page */ + /* drop reference from uncharge_folio */ css_put(&ug->memcg->css); } -static void uncharge_page(struct page *page, struct uncharge_gather *ug) +static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) { - unsigned long nr_pages; + long nr_pages; struct mem_cgroup *memcg; struct obj_cgroup *objcg; - bool use_objcg = PageMemcgKmem(page); + bool use_objcg = folio_memcg_kmem(folio); - VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Nobody should be changing or seriously looking at - * page memcg or objcg at this point, we have fully - * exclusive access to the page. + * folio memcg or objcg at this point, we have fully + * exclusive access to the folio. */ if (use_objcg) { - objcg = __page_objcg(page); + objcg = __folio_objcg(folio); /* * This get matches the put at the end of the function and * kmem pages do not hold memcg references anymore. */ memcg = get_mem_cgroup_from_objcg(objcg); } else { - memcg = __page_memcg(page); + memcg = __folio_memcg(folio); } if (!memcg) @@ -6865,19 +6870,19 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) uncharge_gather_clear(ug); } ug->memcg = memcg; - ug->dummy_page = page; + ug->nid = folio_nid(folio); /* pairs with css_put in uncharge_batch */ css_get(&memcg->css); } - nr_pages = compound_nr(page); + nr_pages = folio_nr_pages(folio); if (use_objcg) { ug->nr_memory += nr_pages; ug->nr_kmem += nr_pages; - page->memcg_data = 0; + folio->memcg_data = 0; obj_cgroup_put(objcg); } else { /* LRU pages aren't accounted at the root level */ @@ -6885,28 +6890,22 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) ug->nr_memory += nr_pages; ug->pgpgout++; - page->memcg_data = 0; + folio->memcg_data = 0; } css_put(&memcg->css); } -/** - * __mem_cgroup_uncharge - uncharge a page - * @page: page to uncharge - * - * Uncharge a page previously charged with __mem_cgroup_charge(). - */ -void __mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct folio *folio) { struct uncharge_gather ug; - /* Don't touch page->lru of any random page, pre-check: */ - if (!page_memcg(page)) + /* Don't touch folio->lru of any random page, pre-check: */ + if (!folio_memcg(folio)) return; uncharge_gather_clear(&ug); - uncharge_page(page, &ug); + uncharge_folio(folio, &ug); uncharge_batch(&ug); } @@ -6920,52 +6919,49 @@ void __mem_cgroup_uncharge(struct page *page) void __mem_cgroup_uncharge_list(struct list_head *page_list) { struct uncharge_gather ug; - struct page *page; + struct folio *folio; uncharge_gather_clear(&ug); - list_for_each_entry(page, page_list, lru) - uncharge_page(page, &ug); + list_for_each_entry(folio, page_list, lru) + uncharge_folio(folio, &ug); if (ug.memcg) uncharge_batch(&ug); } /** - * mem_cgroup_migrate - charge a page's replacement - * @oldpage: currently circulating page - * @newpage: replacement page + * mem_cgroup_migrate - Charge a folio's replacement. + * @old: Currently circulating folio. + * @new: Replacement folio. * - * Charge @newpage as a replacement page for @oldpage. @oldpage will + * Charge @new as a replacement folio for @old. @old will * be uncharged upon free. * - * Both pages must be locked, @newpage->mapping must be set up. + * Both folios must be locked, @new->mapping must be set up. */ -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) +void mem_cgroup_migrate(struct folio *old, struct folio *new) { struct mem_cgroup *memcg; - unsigned int nr_pages; + long nr_pages = folio_nr_pages(new); unsigned long flags; - VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); - VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage); - VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage), - newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(old), old); + VM_BUG_ON_FOLIO(!folio_test_locked(new), new); + VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new); + VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new); if (mem_cgroup_disabled()) return; - /* Page cache replacement: new page already charged? */ - if (page_memcg(newpage)) + /* Page cache replacement: new folio already charged? */ + if (folio_memcg(new)) return; - memcg = page_memcg(oldpage); - VM_WARN_ON_ONCE_PAGE(!memcg, oldpage); + memcg = folio_memcg(old); + VM_WARN_ON_ONCE_FOLIO(!memcg, old); if (!memcg) return; /* Force-charge the new page. The old one will be freed soon */ - nr_pages = thp_nr_pages(newpage); - if (!mem_cgroup_is_root(memcg)) { page_counter_charge(&memcg->memory, nr_pages); if (do_memsw_account()) @@ -6973,11 +6969,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) } css_get(&memcg->css); - commit_charge(newpage, memcg); + commit_charge(new, memcg); local_irq_save(flags); - mem_cgroup_charge_statistics(memcg, newpage, nr_pages); - memcg_check_events(memcg, newpage); + mem_cgroup_charge_statistics(memcg, nr_pages); + memcg_check_events(memcg, folio_nid(new)); local_irq_restore(flags); } @@ -7204,8 +7200,8 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * only synchronisation we have for updating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, -nr_entries); - memcg_check_events(memcg, page); + mem_cgroup_charge_statistics(memcg, -nr_entries); + memcg_check_events(memcg, page_to_nid(page)); css_put(&memcg->css); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3e6449f2102a..93078a2859a7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -762,7 +762,7 @@ static int delete_from_lru_cache(struct page *p) * Poisoned page might never drop its ref count to 0 so we have * to uncharge it manually from its memcg. */ - mem_cgroup_uncharge(p); + mem_cgroup_uncharge(page_folio(p)); /* * drop the page count elevated by isolate_lru_page() @@ -1147,20 +1147,6 @@ static int __get_hwpoison_page(struct page *page) if (!HWPoisonHandlable(head)) return -EBUSY; - if (PageTransHuge(head)) { - /* - * Non anonymous thp exists only in allocation/free time. We - * can't handle such a case correctly, so let's give it up. - * This should be better than triggering BUG_ON when kernel - * tries to touch the "partially handled" page. - */ - if (!PageAnon(head)) { - pr_err("Memory failure: %#lx: non anonymous thp\n", - page_to_pfn(page)); - return 0; - } - } - if (get_page_unless_zero(head)) { if (head == compound_head(page)) return 1; @@ -1708,6 +1694,20 @@ try_again: } if (PageTransHuge(hpage)) { + /* + * The flag must be set after the refcount is bumped + * otherwise it may race with THP split. + * And the flag can't be set in get_hwpoison_page() since + * it is called by soft offline too and it is just called + * for !MF_COUNT_INCREASE. So here seems to be the best + * place. + * + * Don't need care about the above error handling paths for + * get_hwpoison_page() since they handle either free page + * or unhandlable page. The refcount is bumped iff the + * page is a valid handlable page. + */ + SetPageHasHWPoisoned(hpage); if (try_to_split_thp_page(p, "Memory Failure") < 0) { action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); res = -EBUSY; diff --git a/mm/memory.c b/mm/memory.c index adf9b9ef8277..4b1de80c2a9c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -990,7 +990,7 @@ page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, if (!new_page) return NULL; - if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { + if (mem_cgroup_charge(page_folio(new_page), src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } @@ -3019,7 +3019,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(new_page), mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); @@ -3539,7 +3539,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) shadow = get_shadow_from_swap_cache(entry); if (shadow) - workingset_refault(page, shadow); + workingset_refault(page_folio(page), + shadow); lru_cache_add(page); @@ -3769,7 +3770,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); @@ -3907,6 +3908,15 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) return ret; /* + * Just backoff if any subpage of a THP is corrupted otherwise + * the corrupted page may mapped by PMD silently to escape the + * check. This kind of THP just can be PTE mapped. Access to + * the corrupted subpage should trigger SIGBUS as expected. + */ + if (unlikely(PageHasHWPoisoned(page))) + return ret; + + /* * Archs like ppc64 need additional space to store information * related to pte entry. Use the preallocated table for that. */ @@ -4193,7 +4203,8 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { + if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm, + GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } @@ -4258,7 +4269,7 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf) * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * return value. See filemap_fault() and __folio_lock_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ @@ -4499,7 +4510,7 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. - * See filemap_fault() and __lock_page_or_retry(). + * See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { @@ -4603,7 +4614,7 @@ unlock: * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * return value. See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) @@ -4759,7 +4770,7 @@ static inline void mm_account_fault(struct pt_regs *regs, * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * return value. See filemap_fault() and __folio_lock_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d12e0608fced..f4b4be7af4d3 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2196,6 +2196,16 @@ struct page *alloc_pages(gfp_t gfp, unsigned order) } EXPORT_SYMBOL(alloc_pages); +struct folio *folio_alloc(gfp_t gfp, unsigned order) +{ + struct page *page = alloc_pages(gfp | __GFP_COMP, order); + + if (page && order > 1) + prep_transhuge_page(page); + return (struct folio *)page; +} +EXPORT_SYMBOL(folio_alloc); + int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(vma_policy(src)); diff --git a/mm/memremap.c b/mm/memremap.c index ed593bf87109..5a66a71ab591 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -505,7 +505,7 @@ void free_devmap_managed_page(struct page *page) __ClearPageWaiters(page); - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); /* * When a device_private page is freed, the page->mapping field diff --git a/mm/migrate.c b/mm/migrate.c index 1852d787e6ab..efa9941ebe03 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -364,7 +364,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page) */ expected_count += is_device_private_page(page); if (mapping) - expected_count += thp_nr_pages(page) + page_has_private(page); + expected_count += compound_nr(page) + page_has_private(page); return expected_count; } @@ -377,74 +377,75 @@ static int expected_page_refs(struct address_space *mapping, struct page *page) * 2 for pages with a mapping * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ -int migrate_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page, int extra_count) +int folio_migrate_mapping(struct address_space *mapping, + struct folio *newfolio, struct folio *folio, int extra_count) { - XA_STATE(xas, &mapping->i_pages, page_index(page)); + XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct zone *oldzone, *newzone; int dirty; - int expected_count = expected_page_refs(mapping, page) + extra_count; - int nr = thp_nr_pages(page); + int expected_count = expected_page_refs(mapping, &folio->page) + extra_count; + long nr = folio_nr_pages(folio); if (!mapping) { /* Anonymous page without mapping */ - if (page_count(page) != expected_count) + if (folio_ref_count(folio) != expected_count) return -EAGAIN; /* No turning back from here */ - newpage->index = page->index; - newpage->mapping = page->mapping; - if (PageSwapBacked(page)) - __SetPageSwapBacked(newpage); + newfolio->index = folio->index; + newfolio->mapping = folio->mapping; + if (folio_test_swapbacked(folio)) + __folio_set_swapbacked(newfolio); return MIGRATEPAGE_SUCCESS; } - oldzone = page_zone(page); - newzone = page_zone(newpage); + oldzone = folio_zone(folio); + newzone = folio_zone(newfolio); xas_lock_irq(&xas); - if (page_count(page) != expected_count || xas_load(&xas) != page) { + if (folio_ref_count(folio) != expected_count || + xas_load(&xas) != folio) { xas_unlock_irq(&xas); return -EAGAIN; } - if (!page_ref_freeze(page, expected_count)) { + if (!folio_ref_freeze(folio, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; } /* - * Now we know that no one else is looking at the page: + * Now we know that no one else is looking at the folio: * no turning back from here. */ - newpage->index = page->index; - newpage->mapping = page->mapping; - page_ref_add(newpage, nr); /* add cache reference */ - if (PageSwapBacked(page)) { - __SetPageSwapBacked(newpage); - if (PageSwapCache(page)) { - SetPageSwapCache(newpage); - set_page_private(newpage, page_private(page)); + newfolio->index = folio->index; + newfolio->mapping = folio->mapping; + folio_ref_add(newfolio, nr); /* add cache reference */ + if (folio_test_swapbacked(folio)) { + __folio_set_swapbacked(newfolio); + if (folio_test_swapcache(folio)) { + folio_set_swapcache(newfolio); + newfolio->private = folio_get_private(folio); } } else { - VM_BUG_ON_PAGE(PageSwapCache(page), page); + VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); } /* Move dirty while page refs frozen and newpage not yet exposed */ - dirty = PageDirty(page); + dirty = folio_test_dirty(folio); if (dirty) { - ClearPageDirty(page); - SetPageDirty(newpage); + folio_clear_dirty(folio); + folio_set_dirty(newfolio); } - xas_store(&xas, newpage); - if (PageTransHuge(page)) { + xas_store(&xas, newfolio); + if (nr > 1) { int i; for (i = 1; i < nr; i++) { xas_next(&xas); - xas_store(&xas, newpage); + xas_store(&xas, newfolio); } } @@ -453,7 +454,7 @@ int migrate_page_move_mapping(struct address_space *mapping, * to one less reference. * We know this isn't the last reference. */ - page_ref_unfreeze(page, expected_count - nr); + folio_ref_unfreeze(folio, expected_count - nr); xas_unlock(&xas); /* Leave irq disabled to prevent preemption while updating stats */ @@ -472,18 +473,18 @@ int migrate_page_move_mapping(struct address_space *mapping, struct lruvec *old_lruvec, *new_lruvec; struct mem_cgroup *memcg; - memcg = page_memcg(page); + memcg = folio_memcg(folio); old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr); __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr); - if (PageSwapBacked(page) && !PageSwapCache(page)) { + if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) { __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); __mod_lruvec_state(new_lruvec, NR_SHMEM, nr); } #ifdef CONFIG_SWAP - if (PageSwapCache(page)) { + if (folio_test_swapcache(folio)) { __mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr); __mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr); } @@ -499,11 +500,11 @@ int migrate_page_move_mapping(struct address_space *mapping, return MIGRATEPAGE_SUCCESS; } -EXPORT_SYMBOL(migrate_page_move_mapping); +EXPORT_SYMBOL(folio_migrate_mapping); /* * The expected number of remaining references is the same as that - * of migrate_page_move_mapping(). + * of folio_migrate_mapping(). */ int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page) @@ -538,91 +539,87 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, } /* - * Copy the page to its new location + * Copy the flags and some other ancillary information */ -void migrate_page_states(struct page *newpage, struct page *page) +void folio_migrate_flags(struct folio *newfolio, struct folio *folio) { int cpupid; - if (PageError(page)) - SetPageError(newpage); - if (PageReferenced(page)) - SetPageReferenced(newpage); - if (PageUptodate(page)) - SetPageUptodate(newpage); - if (TestClearPageActive(page)) { - VM_BUG_ON_PAGE(PageUnevictable(page), page); - SetPageActive(newpage); - } else if (TestClearPageUnevictable(page)) - SetPageUnevictable(newpage); - if (PageWorkingset(page)) - SetPageWorkingset(newpage); - if (PageChecked(page)) - SetPageChecked(newpage); - if (PageMappedToDisk(page)) - SetPageMappedToDisk(newpage); - - /* Move dirty on pages not done by migrate_page_move_mapping() */ - if (PageDirty(page)) - SetPageDirty(newpage); - - if (page_is_young(page)) - set_page_young(newpage); - if (page_is_idle(page)) - set_page_idle(newpage); + if (folio_test_error(folio)) + folio_set_error(newfolio); + if (folio_test_referenced(folio)) + folio_set_referenced(newfolio); + if (folio_test_uptodate(folio)) + folio_mark_uptodate(newfolio); + if (folio_test_clear_active(folio)) { + VM_BUG_ON_FOLIO(folio_test_unevictable(folio), folio); + folio_set_active(newfolio); + } else if (folio_test_clear_unevictable(folio)) + folio_set_unevictable(newfolio); + if (folio_test_workingset(folio)) + folio_set_workingset(newfolio); + if (folio_test_checked(folio)) + folio_set_checked(newfolio); + if (folio_test_mappedtodisk(folio)) + folio_set_mappedtodisk(newfolio); + + /* Move dirty on pages not done by folio_migrate_mapping() */ + if (folio_test_dirty(folio)) + folio_set_dirty(newfolio); + + if (folio_test_young(folio)) + folio_set_young(newfolio); + if (folio_test_idle(folio)) + folio_set_idle(newfolio); /* * Copy NUMA information to the new page, to prevent over-eager * future migrations of this same page. */ - cpupid = page_cpupid_xchg_last(page, -1); - page_cpupid_xchg_last(newpage, cpupid); + cpupid = page_cpupid_xchg_last(&folio->page, -1); + page_cpupid_xchg_last(&newfolio->page, cpupid); - ksm_migrate_page(newpage, page); + folio_migrate_ksm(newfolio, folio); /* * Please do not reorder this without considering how mm/ksm.c's * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). */ - if (PageSwapCache(page)) - ClearPageSwapCache(page); - ClearPagePrivate(page); + if (folio_test_swapcache(folio)) + folio_clear_swapcache(folio); + folio_clear_private(folio); /* page->private contains hugetlb specific flags */ - if (!PageHuge(page)) - set_page_private(page, 0); + if (!folio_test_hugetlb(folio)) + folio->private = NULL; /* * If any waiters have accumulated on the new page then * wake them up. */ - if (PageWriteback(newpage)) - end_page_writeback(newpage); + if (folio_test_writeback(newfolio)) + folio_end_writeback(newfolio); /* * PG_readahead shares the same bit with PG_reclaim. The above * end_page_writeback() may clear PG_readahead mistakenly, so set the * bit after that. */ - if (PageReadahead(page)) - SetPageReadahead(newpage); + if (folio_test_readahead(folio)) + folio_set_readahead(newfolio); - copy_page_owner(page, newpage); + folio_copy_owner(newfolio, folio); - if (!PageHuge(page)) - mem_cgroup_migrate(page, newpage); + if (!folio_test_hugetlb(folio)) + mem_cgroup_migrate(folio, newfolio); } -EXPORT_SYMBOL(migrate_page_states); +EXPORT_SYMBOL(folio_migrate_flags); -void migrate_page_copy(struct page *newpage, struct page *page) +void folio_migrate_copy(struct folio *newfolio, struct folio *folio) { - if (PageHuge(page) || PageTransHuge(page)) - copy_huge_page(newpage, page); - else - copy_highpage(newpage, page); - - migrate_page_states(newpage, page); + folio_copy(newfolio, folio); + folio_migrate_flags(newfolio, folio); } -EXPORT_SYMBOL(migrate_page_copy); +EXPORT_SYMBOL(folio_migrate_copy); /************************************************************ * Migration functions @@ -638,19 +635,21 @@ int migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode) { + struct folio *newfolio = page_folio(newpage); + struct folio *folio = page_folio(page); int rc; - BUG_ON(PageWriteback(page)); /* Writeback must be complete */ + BUG_ON(folio_test_writeback(folio)); /* Writeback must be complete */ - rc = migrate_page_move_mapping(mapping, newpage, page, 0); + rc = folio_migrate_mapping(mapping, newfolio, folio, 0); if (rc != MIGRATEPAGE_SUCCESS) return rc; if (mode != MIGRATE_SYNC_NO_COPY) - migrate_page_copy(newpage, page); + folio_migrate_copy(newfolio, folio); else - migrate_page_states(newpage, page); + folio_migrate_flags(newfolio, folio); return MIGRATEPAGE_SUCCESS; } EXPORT_SYMBOL(migrate_page); @@ -2468,7 +2467,7 @@ static void migrate_vma_collect(struct migrate_vma *migrate) * @page: struct page to check * * Pinned pages cannot be migrated. This is the same test as in - * migrate_page_move_mapping(), except that here we allow migration of a + * folio_migrate_mapping(), except that here we allow migration of a * ZONE_DEVICE page. */ static bool migrate_vma_check_page(struct page *page) @@ -2846,7 +2845,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) goto abort; /* diff --git a/mm/mlock.c b/mm/mlock.c index 16d2ee160d43..e263d62ae2d0 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -271,6 +271,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) /* Phase 1: page isolation */ for (i = 0; i < nr; i++) { struct page *page = pvec->pages[i]; + struct folio *folio = page_folio(page); if (TestClearPageMlocked(page)) { /* @@ -278,7 +279,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) * so we can spare the get_page() here. */ if (TestClearPageLRU(page)) { - lruvec = relock_page_lruvec_irq(page, lruvec); + lruvec = folio_lruvec_relock_irq(folio, lruvec); del_page_from_lru_list(page, lruvec); continue; } else diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 831340e7ad8b..989f35a2bbb1 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -1150,7 +1150,7 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) struct task_struct *task; struct task_struct *p; unsigned int f_flags; - bool reap = true; + bool reap = false; struct pid *pid; long ret = 0; @@ -1177,15 +1177,15 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) goto put_task; } - mm = p->mm; - mmgrab(mm); - - /* If the work has been done already, just exit with success */ - if (test_bit(MMF_OOM_SKIP, &mm->flags)) - reap = false; - else if (!task_will_free_mem(p)) { - reap = false; - ret = -EINVAL; + if (mmget_not_zero(p->mm)) { + mm = p->mm; + if (task_will_free_mem(p)) + reap = true; + else { + /* Error only if the work has not been done already */ + if (!test_bit(MMF_OOM_SKIP, &mm->flags)) + ret = -EINVAL; + } } task_unlock(p); @@ -1201,7 +1201,8 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) mmap_read_unlock(mm); drop_mm: - mmdrop(mm); + if (mm) + mmput(mm); put_task: put_task_struct(task); put_pid: diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4812a17b288c..9c64490171e0 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -562,12 +562,12 @@ static unsigned long wp_next_time(unsigned long cur_time) return cur_time; } -static void wb_domain_writeout_inc(struct wb_domain *dom, +static void wb_domain_writeout_add(struct wb_domain *dom, struct fprop_local_percpu *completions, - unsigned int max_prop_frac) + unsigned int max_prop_frac, long nr) { - __fprop_inc_percpu_max(&dom->completions, completions, - max_prop_frac); + __fprop_add_percpu_max(&dom->completions, completions, + max_prop_frac, nr); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* @@ -583,20 +583,20 @@ static void wb_domain_writeout_inc(struct wb_domain *dom, /* * Increment @wb's writeout completion count and the global writeout - * completion count. Called from test_clear_page_writeback(). + * completion count. Called from __folio_end_writeback(). */ -static inline void __wb_writeout_inc(struct bdi_writeback *wb) +static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr) { struct wb_domain *cgdom; - inc_wb_stat(wb, WB_WRITTEN); - wb_domain_writeout_inc(&global_wb_domain, &wb->completions, - wb->bdi->max_prop_frac); + wb_stat_mod(wb, WB_WRITTEN, nr); + wb_domain_writeout_add(&global_wb_domain, &wb->completions, + wb->bdi->max_prop_frac, nr); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) - wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb), - wb->bdi->max_prop_frac); + wb_domain_writeout_add(cgdom, wb_memcg_completions(wb), + wb->bdi->max_prop_frac, nr); } void wb_writeout_inc(struct bdi_writeback *wb) @@ -604,7 +604,7 @@ void wb_writeout_inc(struct bdi_writeback *wb) unsigned long flags; local_irq_save(flags); - __wb_writeout_inc(wb); + __wb_writeout_add(wb, 1); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); @@ -1084,7 +1084,7 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb, * write_bandwidth = --------------------------------------------------- * period * - * @written may have decreased due to account_page_redirty(). + * @written may have decreased due to folio_account_redirty(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); @@ -2381,44 +2381,44 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) } /** - * write_one_page - write out a single page and wait on I/O - * @page: the page to write + * folio_write_one - write out a single folio and wait on I/O. + * @folio: The folio to write. * - * The page must be locked by the caller and will be unlocked upon return. + * The folio must be locked by the caller and will be unlocked upon return. * * Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this * function returns. * * Return: %0 on success, negative error code otherwise */ -int write_one_page(struct page *page) +int folio_write_one(struct folio *folio) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; int ret = 0; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, - .nr_to_write = 1, + .nr_to_write = folio_nr_pages(folio), }; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); - wait_on_page_writeback(page); + folio_wait_writeback(folio); - if (clear_page_dirty_for_io(page)) { - get_page(page); - ret = mapping->a_ops->writepage(page, &wbc); + if (folio_clear_dirty_for_io(folio)) { + folio_get(folio); + ret = mapping->a_ops->writepage(&folio->page, &wbc); if (ret == 0) - wait_on_page_writeback(page); - put_page(page); + folio_wait_writeback(folio); + folio_put(folio); } else { - unlock_page(page); + folio_unlock(folio); } if (!ret) ret = filemap_check_errors(mapping); return ret; } -EXPORT_SYMBOL(write_one_page); +EXPORT_SYMBOL(folio_write_one); /* * For address_spaces which do not use buffers nor write back. @@ -2438,29 +2438,30 @@ EXPORT_SYMBOL(__set_page_dirty_no_writeback); * * NOTE: This relies on being atomic wrt interrupts. */ -static void account_page_dirtied(struct page *page, +static void folio_account_dirtied(struct folio *folio, struct address_space *mapping) { struct inode *inode = mapping->host; - trace_writeback_dirty_page(page, mapping); + trace_writeback_dirty_folio(folio, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; + long nr = folio_nr_pages(folio); - inode_attach_wb(inode, page); + inode_attach_wb(inode, &folio->page); wb = inode_to_wb(inode); - __inc_lruvec_page_state(page, NR_FILE_DIRTY); - __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); - __inc_node_page_state(page, NR_DIRTIED); - inc_wb_stat(wb, WB_RECLAIMABLE); - inc_wb_stat(wb, WB_DIRTIED); - task_io_account_write(PAGE_SIZE); - current->nr_dirtied++; - __this_cpu_inc(bdp_ratelimits); + __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); + __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); + __node_stat_mod_folio(folio, NR_DIRTIED, nr); + wb_stat_mod(wb, WB_RECLAIMABLE, nr); + wb_stat_mod(wb, WB_DIRTIED, nr); + task_io_account_write(nr * PAGE_SIZE); + current->nr_dirtied += nr; + __this_cpu_add(bdp_ratelimits, nr); - mem_cgroup_track_foreign_dirty(page, wb); + mem_cgroup_track_foreign_dirty(folio, wb); } } @@ -2469,130 +2470,152 @@ static void account_page_dirtied(struct page *page, * * Caller must hold lock_page_memcg(). */ -void account_page_cleaned(struct page *page, struct address_space *mapping, +void folio_account_cleaned(struct folio *folio, struct address_space *mapping, struct bdi_writeback *wb) { if (mapping_can_writeback(mapping)) { - dec_lruvec_page_state(page, NR_FILE_DIRTY); - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); - dec_wb_stat(wb, WB_RECLAIMABLE); - task_io_account_cancelled_write(PAGE_SIZE); + long nr = folio_nr_pages(folio); + lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); + wb_stat_mod(wb, WB_RECLAIMABLE, -nr); + task_io_account_cancelled_write(nr * PAGE_SIZE); } } /* - * Mark the page dirty, and set it dirty in the page cache, and mark the inode - * dirty. + * Mark the folio dirty, and set it dirty in the page cache, and mark + * the inode dirty. * - * If warn is true, then emit a warning if the page is not uptodate and has + * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * * The caller must hold lock_page_memcg(). */ -void __set_page_dirty(struct page *page, struct address_space *mapping, +void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); - if (page->mapping) { /* Race with truncate? */ - WARN_ON_ONCE(warn && !PageUptodate(page)); - account_page_dirtied(page, mapping); - __xa_set_mark(&mapping->i_pages, page_index(page), + if (folio->mapping) { /* Race with truncate? */ + WARN_ON_ONCE(warn && !folio_test_uptodate(folio)); + folio_account_dirtied(folio, mapping); + __xa_set_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } -/* - * For address_spaces which do not use buffers. Just tag the page as dirty in - * the xarray. +/** + * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads. + * @mapping: Address space this folio belongs to. + * @folio: Folio to be marked as dirty. + * + * Filesystems which do not use buffer heads should call this function + * from their set_page_dirty address space operation. It ignores the + * contents of folio_get_private(), so if the filesystem marks individual + * blocks as dirty, the filesystem should handle that itself. * - * This is also used when a single buffer is being dirtied: we want to set the - * page dirty in that case, but not all the buffers. This is a "bottom-up" - * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. + * This is also sometimes used by filesystems which use buffer_heads when + * a single buffer is being dirtied: we want to set the folio dirty in + * that case, but not all the buffers. This is a "bottom-up" dirtying, + * whereas __set_page_dirty_buffers() is a "top-down" dirtying. * - * The caller must ensure this doesn't race with truncation. Most will simply - * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and - * the pte lock held, which also locks out truncation. + * The caller must ensure this doesn't race with truncation. Most will + * simply hold the folio lock, but e.g. zap_pte_range() calls with the + * folio mapped and the pte lock held, which also locks out truncation. */ -int __set_page_dirty_nobuffers(struct page *page) +bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { - lock_page_memcg(page); - if (!TestSetPageDirty(page)) { - struct address_space *mapping = page_mapping(page); + folio_memcg_lock(folio); + if (folio_test_set_dirty(folio)) { + folio_memcg_unlock(folio); + return false; + } - if (!mapping) { - unlock_page_memcg(page); - return 1; - } - __set_page_dirty(page, mapping, !PagePrivate(page)); - unlock_page_memcg(page); + __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); + folio_memcg_unlock(folio); - if (mapping->host) { - /* !PageAnon && !swapper_space */ - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - } - return 1; + if (mapping->host) { + /* !PageAnon && !swapper_space */ + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } - unlock_page_memcg(page); - return 0; + return true; } -EXPORT_SYMBOL(__set_page_dirty_nobuffers); +EXPORT_SYMBOL(filemap_dirty_folio); -/* - * Call this whenever redirtying a page, to de-account the dirty counters - * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written - * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to - * systematic errors in balanced_dirty_ratelimit and the dirty pages position - * control. +/** + * folio_account_redirty - Manually account for redirtying a page. + * @folio: The folio which is being redirtied. + * + * Most filesystems should call folio_redirty_for_writepage() instead + * of this fuction. If your filesystem is doing writeback outside the + * context of a writeback_control(), it can call this when redirtying + * a folio, to de-account the dirty counters (NR_DIRTIED, WB_DIRTIED, + * tsk->nr_dirtied), so that they match the written counters (NR_WRITTEN, + * WB_WRITTEN) in long term. The mismatches will lead to systematic errors + * in balanced_dirty_ratelimit and the dirty pages position control. */ -void account_page_redirty(struct page *page) +void folio_account_redirty(struct folio *folio) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; + long nr = folio_nr_pages(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); - current->nr_dirtied--; - dec_node_page_state(page, NR_DIRTIED); - dec_wb_stat(wb, WB_DIRTIED); + current->nr_dirtied -= nr; + node_stat_mod_folio(folio, NR_DIRTIED, -nr); + wb_stat_mod(wb, WB_DIRTIED, -nr); unlocked_inode_to_wb_end(inode, &cookie); } } -EXPORT_SYMBOL(account_page_redirty); +EXPORT_SYMBOL(folio_account_redirty); -/* - * When a writepage implementation decides that it doesn't want to write this - * page for some reason, it should redirty the locked page via - * redirty_page_for_writepage() and it should then unlock the page and return 0 +/** + * folio_redirty_for_writepage - Decline to write a dirty folio. + * @wbc: The writeback control. + * @folio: The folio. + * + * When a writepage implementation decides that it doesn't want to write + * @folio for some reason, it should call this function, unlock @folio and + * return 0. + * + * Return: True if we redirtied the folio. False if someone else dirtied + * it first. */ -int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) +bool folio_redirty_for_writepage(struct writeback_control *wbc, + struct folio *folio) { - int ret; + bool ret; + long nr = folio_nr_pages(folio); + + wbc->pages_skipped += nr; + ret = filemap_dirty_folio(folio->mapping, folio); + folio_account_redirty(folio); - wbc->pages_skipped++; - ret = __set_page_dirty_nobuffers(page); - account_page_redirty(page); return ret; } -EXPORT_SYMBOL(redirty_page_for_writepage); +EXPORT_SYMBOL(folio_redirty_for_writepage); -/* - * Dirty a page. +/** + * folio_mark_dirty - Mark a folio as being modified. + * @folio: The folio. * - * For pages with a mapping this should be done under the page lock for the - * benefit of asynchronous memory errors who prefer a consistent dirty state. - * This rule can be broken in some special cases, but should be better not to. + * For folios with a mapping this should be done under the page lock + * for the benefit of asynchronous memory errors who prefer a consistent + * dirty state. This rule can be broken in some special cases, + * but should be better not to. + * + * Return: True if the folio was newly dirtied, false if it was already dirty. */ -int set_page_dirty(struct page *page) +bool folio_mark_dirty(struct folio *folio) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio_mapping(folio); - page = compound_head(page); if (likely(mapping)) { /* * readahead/lru_deactivate_page could remain @@ -2604,17 +2627,17 @@ int set_page_dirty(struct page *page) * it will confuse readahead and make it restart the size rampup * process. But it's a trivial problem. */ - if (PageReclaim(page)) - ClearPageReclaim(page); - return mapping->a_ops->set_page_dirty(page); + if (folio_test_reclaim(folio)) + folio_clear_reclaim(folio); + return mapping->a_ops->set_page_dirty(&folio->page); } - if (!PageDirty(page)) { - if (!TestSetPageDirty(page)) - return 1; + if (!folio_test_dirty(folio)) { + if (!folio_test_set_dirty(folio)) + return true; } - return 0; + return false; } -EXPORT_SYMBOL(set_page_dirty); +EXPORT_SYMBOL(folio_mark_dirty); /* * set_page_dirty() is racy if the caller has no reference against @@ -2650,49 +2673,49 @@ EXPORT_SYMBOL(set_page_dirty_lock); * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ -void __cancel_dirty_page(struct page *page) +void __folio_cancel_dirty(struct folio *folio) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; - lock_page_memcg(page); + folio_memcg_lock(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); - if (TestClearPageDirty(page)) - account_page_cleaned(page, mapping, wb); + if (folio_test_clear_dirty(folio)) + folio_account_cleaned(folio, mapping, wb); unlocked_inode_to_wb_end(inode, &cookie); - unlock_page_memcg(page); + folio_memcg_unlock(folio); } else { - ClearPageDirty(page); + folio_clear_dirty(folio); } } -EXPORT_SYMBOL(__cancel_dirty_page); +EXPORT_SYMBOL(__folio_cancel_dirty); /* - * Clear a page's dirty flag, while caring for dirty memory accounting. - * Returns true if the page was previously dirty. - * - * This is for preparing to put the page under writeout. We leave the page - * tagged as dirty in the xarray so that a concurrent write-for-sync - * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage - * implementation will run either set_page_writeback() or set_page_dirty(), - * at which stage we bring the page's dirty flag and xarray dirty tag - * back into sync. - * - * This incoherency between the page's dirty flag and xarray tag is - * unfortunate, but it only exists while the page is locked. + * Clear a folio's dirty flag, while caring for dirty memory accounting. + * Returns true if the folio was previously dirty. + * + * This is for preparing to put the folio under writeout. We leave + * the folio tagged as dirty in the xarray so that a concurrent + * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk. + * The ->writepage implementation will run either folio_start_writeback() + * or folio_mark_dirty(), at which stage we bring the folio's dirty flag + * and xarray dirty tag back into sync. + * + * This incoherency between the folio's dirty flag and xarray tag is + * unfortunate, but it only exists while the folio is locked. */ -int clear_page_dirty_for_io(struct page *page) +bool folio_clear_dirty_for_io(struct folio *folio) { - struct address_space *mapping = page_mapping(page); - int ret = 0; + struct address_space *mapping = folio_mapping(folio); + bool ret = false; - VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; @@ -2705,48 +2728,49 @@ int clear_page_dirty_for_io(struct page *page) * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to - * mark the whole page dirty if it was + * mark the whole folio dirty if it was * dirty in a pagetable. Only to then - * (c) clean the page again and return 1 to + * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * - * Note! Normally the "set_page_dirty(page)" + * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * - * We basically use the page "master dirty bit" + * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ - if (page_mkclean(page)) - set_page_dirty(page); + if (folio_mkclean(folio)) + folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against - * installing a dirty pte and marking the page dirty + * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the - * page lock while dirtying the page, and pages are + * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); - if (TestClearPageDirty(page)) { - dec_lruvec_page_state(page, NR_FILE_DIRTY); - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); - dec_wb_stat(wb, WB_RECLAIMABLE); - ret = 1; + if (folio_test_clear_dirty(folio)) { + long nr = folio_nr_pages(folio); + lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); + wb_stat_mod(wb, WB_RECLAIMABLE, -nr); + ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } - return TestClearPageDirty(page); + return folio_test_clear_dirty(folio); } -EXPORT_SYMBOL(clear_page_dirty_for_io); +EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { @@ -2766,27 +2790,28 @@ static void wb_inode_writeback_end(struct bdi_writeback *wb) queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); } -int test_clear_page_writeback(struct page *page) +bool __folio_end_writeback(struct folio *folio) { - struct address_space *mapping = page_mapping(page); - int ret; + long nr = folio_nr_pages(folio); + struct address_space *mapping = folio_mapping(folio); + bool ret; - lock_page_memcg(page); + folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); - ret = TestClearPageWriteback(page); + ret = folio_test_clear_writeback(folio); if (ret) { - __xa_clear_mark(&mapping->i_pages, page_index(page), + __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); - dec_wb_stat(wb, WB_WRITEBACK); - __wb_writeout_inc(wb); + wb_stat_mod(wb, WB_WRITEBACK, -nr); + __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); @@ -2799,32 +2824,34 @@ int test_clear_page_writeback(struct page *page) xa_unlock_irqrestore(&mapping->i_pages, flags); } else { - ret = TestClearPageWriteback(page); + ret = folio_test_clear_writeback(folio); } if (ret) { - dec_lruvec_page_state(page, NR_WRITEBACK); - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); - inc_node_page_state(page, NR_WRITTEN); + lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); + node_stat_mod_folio(folio, NR_WRITTEN, nr); } - unlock_page_memcg(page); + folio_memcg_unlock(folio); return ret; } -int __test_set_page_writeback(struct page *page, bool keep_write) +bool __folio_start_writeback(struct folio *folio, bool keep_write) { - struct address_space *mapping = page_mapping(page); - int ret, access_ret; + long nr = folio_nr_pages(folio); + struct address_space *mapping = folio_mapping(folio); + bool ret; + int access_ret; - lock_page_memcg(page); + folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { - XA_STATE(xas, &mapping->i_pages, page_index(page)); + XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xas_lock_irqsave(&xas, flags); xas_load(&xas); - ret = TestSetPageWriteback(page); + ret = folio_test_set_writeback(folio); if (!ret) { bool on_wblist; @@ -2835,84 +2862,105 @@ int __test_set_page_writeback(struct page *page, bool keep_write) if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); - inc_wb_stat(wb, WB_WRITEBACK); + wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* - * We can come through here when swapping anonymous - * pages, so we don't necessarily have an inode to track - * for sync. + * We can come through here when swapping + * anonymous folios, so we don't necessarily + * have an inode to track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); } - if (!PageDirty(page)) + if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { - ret = TestSetPageWriteback(page); + ret = folio_test_set_writeback(folio); } if (!ret) { - inc_lruvec_page_state(page, NR_WRITEBACK); - inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); + lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); } - unlock_page_memcg(page); - access_ret = arch_make_page_accessible(page); + folio_memcg_unlock(folio); + access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ - VM_BUG_ON_PAGE(access_ret != 0, page); + VM_BUG_ON_FOLIO(access_ret != 0, folio); return ret; - } -EXPORT_SYMBOL(__test_set_page_writeback); +EXPORT_SYMBOL(__folio_start_writeback); -/* - * Wait for a page to complete writeback +/** + * folio_wait_writeback - Wait for a folio to finish writeback. + * @folio: The folio to wait for. + * + * If the folio is currently being written back to storage, wait for the + * I/O to complete. + * + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. */ -void wait_on_page_writeback(struct page *page) +void folio_wait_writeback(struct folio *folio) { - while (PageWriteback(page)) { - trace_wait_on_page_writeback(page, page_mapping(page)); - wait_on_page_bit(page, PG_writeback); + while (folio_test_writeback(folio)) { + trace_folio_wait_writeback(folio, folio_mapping(folio)); + folio_wait_bit(folio, PG_writeback); } } -EXPORT_SYMBOL_GPL(wait_on_page_writeback); +EXPORT_SYMBOL_GPL(folio_wait_writeback); -/* - * Wait for a page to complete writeback. Returns -EINTR if we get a - * fatal signal while waiting. +/** + * folio_wait_writeback_killable - Wait for a folio to finish writeback. + * @folio: The folio to wait for. + * + * If the folio is currently being written back to storage, wait for the + * I/O to complete or a fatal signal to arrive. + * + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. + * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ -int wait_on_page_writeback_killable(struct page *page) +int folio_wait_writeback_killable(struct folio *folio) { - while (PageWriteback(page)) { - trace_wait_on_page_writeback(page, page_mapping(page)); - if (wait_on_page_bit_killable(page, PG_writeback)) + while (folio_test_writeback(folio)) { + trace_folio_wait_writeback(folio, folio_mapping(folio)); + if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } return 0; } -EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable); +EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** - * wait_for_stable_page() - wait for writeback to finish, if necessary. - * @page: The page to wait on. + * folio_wait_stable() - wait for writeback to finish, if necessary. + * @folio: The folio to wait on. + * + * This function determines if the given folio is related to a backing + * device that requires folio contents to be held stable during writeback. + * If so, then it will wait for any pending writeback to complete. * - * This function determines if the given page is related to a backing device - * that requires page contents to be held stable during writeback. If so, then - * it will wait for any pending writeback to complete. + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. */ -void wait_for_stable_page(struct page *page) +void folio_wait_stable(struct folio *folio) { - page = thp_head(page); - if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) - wait_on_page_writeback(page); + if (folio->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) + folio_wait_writeback(folio); } -EXPORT_SYMBOL_GPL(wait_for_stable_page); +EXPORT_SYMBOL_GPL(folio_wait_stable); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b37435c274cf..fee18ada46a2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -724,7 +724,7 @@ static inline void free_the_page(struct page *page, unsigned int order) void free_compound_page(struct page *page) { - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); free_the_page(page, compound_order(page)); } @@ -1312,8 +1312,10 @@ static __always_inline bool free_pages_prepare(struct page *page, VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); - if (compound) + if (compound) { ClearPageDoubleMap(page); + ClearPageHasHWPoisoned(page); + } for (i = 1; i < (1 << order); i++) { if (compound) bad += free_tail_pages_check(page, page + i); @@ -5223,6 +5225,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, if (unlikely(page_array && nr_pages - nr_populated == 0)) goto out; + /* Bulk allocator does not support memcg accounting. */ + if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT)) + goto failed; + /* Use the single page allocator for one page. */ if (nr_pages - nr_populated == 1) goto failed; @@ -5400,6 +5406,18 @@ out: } EXPORT_SYMBOL(__alloc_pages); +struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask) +{ + struct page *page = __alloc_pages(gfp | __GFP_COMP, order, + preferred_nid, nodemask); + + if (page && order > 1) + prep_transhuge_page(page); + return (struct folio *)page; +} +EXPORT_SYMBOL(__folio_alloc); + /* * Common helper functions. Never use with __GFP_HIGHMEM because the returned * address cannot represent highmem pages. Use alloc_pages and then kmap if diff --git a/mm/page_io.c b/mm/page_io.c index c493ce9ebcf5..d597bc6e6e45 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -38,7 +38,7 @@ void end_swap_bio_write(struct bio *bio) * Also print a dire warning that things will go BAD (tm) * very quickly. * - * Also clear PG_reclaim to avoid rotate_reclaimable_page() + * Also clear PG_reclaim to avoid folio_rotate_reclaimable() */ set_page_dirty(page); pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n", @@ -317,7 +317,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, * temporary failure if the system has limited * memory for allocating transmit buffers. * Mark the page dirty and avoid - * rotate_reclaimable_page but rate-limit the + * folio_rotate_reclaimable but rate-limit the * messages but do not flag PageError like * the normal direct-to-bio case as it could * be temporary. diff --git a/mm/page_owner.c b/mm/page_owner.c index 62402d22539b..d24ed221357c 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -210,10 +210,10 @@ void __split_page_owner(struct page *page, unsigned int nr) } } -void __copy_page_owner(struct page *oldpage, struct page *newpage) +void __folio_copy_owner(struct folio *newfolio, struct folio *old) { - struct page_ext *old_ext = lookup_page_ext(oldpage); - struct page_ext *new_ext = lookup_page_ext(newpage); + struct page_ext *old_ext = lookup_page_ext(&old->page); + struct page_ext *new_ext = lookup_page_ext(&newfolio->page); struct page_owner *old_page_owner, *new_page_owner; if (unlikely(!old_ext || !new_ext)) @@ -231,11 +231,11 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; /* - * We don't clear the bit on the oldpage as it's going to be freed + * We don't clear the bit on the old folio as it's going to be freed * after migration. Until then, the info can be useful in case of * a bug, and the overall stats will be off a bit only temporarily. * Also, migrate_misplaced_transhuge_page() can still fail the - * migration and then we want the oldpage to retain the info. But + * migration and then we want the old folio to retain the info. But * in that case we also don't need to explicitly clear the info from * the new page, which will be freed. */ diff --git a/mm/rmap.c b/mm/rmap.c index 6aebd1747251..3a1059c284c3 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -34,7 +34,7 @@ * mapping->private_lock (in __set_page_dirty_buffers) * lock_page_memcg move_lock (in __set_page_dirty_buffers) * i_pages lock (widely used) - * lruvec->lru_lock (in lock_page_lruvec_irq) + * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) @@ -981,7 +981,7 @@ static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) return true; } -int page_mkclean(struct page *page) +int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; @@ -991,20 +991,20 @@ int page_mkclean(struct page *page) .invalid_vma = invalid_mkclean_vma, }; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); - if (!page_mapped(page)) + if (!folio_mapped(folio)) return 0; - mapping = page_mapping(page); + mapping = folio_mapping(folio); if (!mapping) return 0; - rmap_walk(page, &rwc); + rmap_walk(&folio->page, &rwc); return cleaned; } -EXPORT_SYMBOL_GPL(page_mkclean); +EXPORT_SYMBOL_GPL(folio_mkclean); /** * page_move_anon_rmap - move a page to our anon_vma diff --git a/mm/secretmem.c b/mm/secretmem.c index c2dda408bb36..22b310adb53d 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -218,8 +218,8 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) file->f_flags |= O_LARGEFILE; - fd_install(fd, file); atomic_inc(&secretmem_users); + fd_install(fd, file); return fd; err_put_fd: diff --git a/mm/shmem.c b/mm/shmem.c index b5860f4a2738..1588f33d009a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -710,7 +710,7 @@ static int shmem_add_to_page_cache(struct page *page, page->index = index; if (!PageSwapCache(page)) { - error = mem_cgroup_charge(page, charge_mm, gfp); + error = mem_cgroup_charge(page_folio(page), charge_mm, gfp); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); @@ -1637,6 +1637,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct page *oldpage, *newpage; + struct folio *old, *new; struct address_space *swap_mapping; swp_entry_t entry; pgoff_t swap_index; @@ -1673,7 +1674,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { - mem_cgroup_migrate(oldpage, newpage); + old = page_folio(oldpage); + new = page_folio(newpage); + mem_cgroup_migrate(old, new); __inc_lruvec_page_state(newpage, NR_FILE_PAGES); __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); } diff --git a/mm/swap.c b/mm/swap.c index af3cad4e5378..8ff9ba7cf2de 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -80,10 +80,11 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { static void __page_cache_release(struct page *page) { if (PageLRU(page)) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; unsigned long flags; - lruvec = lock_page_lruvec_irqsave(page, &flags); + lruvec = folio_lruvec_lock_irqsave(folio, &flags); del_page_from_lru_list(page, lruvec); __clear_page_lru_flags(page); unlock_page_lruvec_irqrestore(lruvec, flags); @@ -94,7 +95,7 @@ static void __page_cache_release(struct page *page) static void __put_single_page(struct page *page) { __page_cache_release(page); - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); free_unref_page(page, 0); } @@ -188,12 +189,13 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; + struct folio *folio = page_folio(page); /* block memcg migration during page moving between lru */ if (!TestClearPageLRU(page)) continue; - lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); + lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); (*move_fn)(page, lruvec); SetPageLRU(page); @@ -206,11 +208,13 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec) { - if (!PageUnevictable(page)) { - del_page_from_lru_list(page, lruvec); - ClearPageActive(page); - add_page_to_lru_list_tail(page, lruvec); - __count_vm_events(PGROTATED, thp_nr_pages(page)); + struct folio *folio = page_folio(page); + + if (!folio_test_unevictable(folio)) { + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + lruvec_add_folio_tail(lruvec, folio); + __count_vm_events(PGROTATED, folio_nr_pages(folio)); } } @@ -227,23 +231,23 @@ static bool pagevec_add_and_need_flush(struct pagevec *pvec, struct page *page) } /* - * Writeback is about to end against a page which has been marked for immediate - * reclaim. If it still appears to be reclaimable, move it to the tail of the - * inactive list. + * Writeback is about to end against a folio which has been marked for + * immediate reclaim. If it still appears to be reclaimable, move it + * to the tail of the inactive list. * - * rotate_reclaimable_page() must disable IRQs, to prevent nasty races. + * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ -void rotate_reclaimable_page(struct page *page) +void folio_rotate_reclaimable(struct folio *folio) { - if (!PageLocked(page) && !PageDirty(page) && - !PageUnevictable(page) && PageLRU(page)) { + if (!folio_test_locked(folio) && !folio_test_dirty(folio) && + !folio_test_unevictable(folio) && folio_test_lru(folio)) { struct pagevec *pvec; unsigned long flags; - get_page(page); + folio_get(folio); local_lock_irqsave(&lru_rotate.lock, flags); pvec = this_cpu_ptr(&lru_rotate.pvec); - if (pagevec_add_and_need_flush(pvec, page)) + if (pagevec_add_and_need_flush(pvec, &folio->page)) pagevec_lru_move_fn(pvec, pagevec_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } @@ -289,21 +293,21 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) } while ((lruvec = parent_lruvec(lruvec))); } -void lru_note_cost_page(struct page *page) +void lru_note_cost_folio(struct folio *folio) { - lru_note_cost(mem_cgroup_page_lruvec(page), - page_is_file_lru(page), thp_nr_pages(page)); + lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio), + folio_nr_pages(folio)); } -static void __activate_page(struct page *page, struct lruvec *lruvec) +static void __folio_activate(struct folio *folio, struct lruvec *lruvec) { - if (!PageActive(page) && !PageUnevictable(page)) { - int nr_pages = thp_nr_pages(page); + if (!folio_test_active(folio) && !folio_test_unevictable(folio)) { + long nr_pages = folio_nr_pages(folio); - del_page_from_lru_list(page, lruvec); - SetPageActive(page); - add_page_to_lru_list(page, lruvec); - trace_mm_lru_activate(page); + lruvec_del_folio(lruvec, folio); + folio_set_active(folio); + lruvec_add_folio(lruvec, folio); + trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, @@ -312,6 +316,11 @@ static void __activate_page(struct page *page, struct lruvec *lruvec) } #ifdef CONFIG_SMP +static void __activate_page(struct page *page, struct lruvec *lruvec) +{ + return __folio_activate(page_folio(page), lruvec); +} + static void activate_page_drain(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu); @@ -325,16 +334,16 @@ static bool need_activate_page_drain(int cpu) return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0; } -static void activate_page(struct page *page) +static void folio_activate(struct folio *folio) { - page = compound_head(page); - if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { + if (folio_test_lru(folio) && !folio_test_active(folio) && + !folio_test_unevictable(folio)) { struct pagevec *pvec; + folio_get(folio); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.activate_page); - get_page(page); - if (pagevec_add_and_need_flush(pvec, page)) + if (pagevec_add_and_need_flush(pvec, &folio->page)) pagevec_lru_move_fn(pvec, __activate_page); local_unlock(&lru_pvecs.lock); } @@ -345,21 +354,20 @@ static inline void activate_page_drain(int cpu) { } -static void activate_page(struct page *page) +static void folio_activate(struct folio *folio) { struct lruvec *lruvec; - page = compound_head(page); - if (TestClearPageLRU(page)) { - lruvec = lock_page_lruvec_irq(page); - __activate_page(page, lruvec); + if (folio_test_clear_lru(folio)) { + lruvec = folio_lruvec_lock_irq(folio); + __folio_activate(folio, lruvec); unlock_page_lruvec_irq(lruvec); - SetPageLRU(page); + folio_set_lru(folio); } } #endif -static void __lru_cache_activate_page(struct page *page) +static void __lru_cache_activate_folio(struct folio *folio) { struct pagevec *pvec; int i; @@ -380,8 +388,8 @@ static void __lru_cache_activate_page(struct page *page) for (i = pagevec_count(pvec) - 1; i >= 0; i--) { struct page *pagevec_page = pvec->pages[i]; - if (pagevec_page == page) { - SetPageActive(page); + if (pagevec_page == &folio->page) { + folio_set_active(folio); break; } } @@ -399,61 +407,59 @@ static void __lru_cache_activate_page(struct page *page) * When a newly allocated page is not yet visible, so safe for non-atomic ops, * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). */ -void mark_page_accessed(struct page *page) +void folio_mark_accessed(struct folio *folio) { - page = compound_head(page); - - if (!PageReferenced(page)) { - SetPageReferenced(page); - } else if (PageUnevictable(page)) { + if (!folio_test_referenced(folio)) { + folio_set_referenced(folio); + } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * evictable page accessed has no effect. */ - } else if (!PageActive(page)) { + } else if (!folio_test_active(folio)) { /* * If the page is on the LRU, queue it for activation via * lru_pvecs.activate_page. Otherwise, assume the page is on a * pagevec, mark it active and it'll be moved to the active * LRU on the next drain. */ - if (PageLRU(page)) - activate_page(page); + if (folio_test_lru(folio)) + folio_activate(folio); else - __lru_cache_activate_page(page); - ClearPageReferenced(page); - workingset_activation(page); + __lru_cache_activate_folio(folio); + folio_clear_referenced(folio); + workingset_activation(folio); } - if (page_is_idle(page)) - clear_page_idle(page); + if (folio_test_idle(folio)) + folio_clear_idle(folio); } -EXPORT_SYMBOL(mark_page_accessed); +EXPORT_SYMBOL(folio_mark_accessed); /** - * lru_cache_add - add a page to a page list - * @page: the page to be added to the LRU. + * folio_add_lru - Add a folio to an LRU list. + * @folio: The folio to be added to the LRU. * - * Queue the page for addition to the LRU via pagevec. The decision on whether + * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the - * pagevec is drained. This gives a chance for the caller of lru_cache_add() - * have the page added to the active list using mark_page_accessed(). + * pagevec is drained. This gives a chance for the caller of folio_add_lru() + * have the folio added to the active list using folio_mark_accessed(). */ -void lru_cache_add(struct page *page) +void folio_add_lru(struct folio *folio) { struct pagevec *pvec; - VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); - VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - get_page(page); + folio_get(folio); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); - if (pagevec_add_and_need_flush(pvec, page)) + if (pagevec_add_and_need_flush(pvec, &folio->page)) __pagevec_lru_add(pvec); local_unlock(&lru_pvecs.lock); } -EXPORT_SYMBOL(lru_cache_add); +EXPORT_SYMBOL(folio_add_lru); /** * lru_cache_add_inactive_or_unevictable @@ -888,11 +894,12 @@ void release_pages(struct page **pages, int nr) int i; LIST_HEAD(pages_to_free); struct lruvec *lruvec = NULL; - unsigned long flags; + unsigned long flags = 0; unsigned int lock_batch; for (i = 0; i < nr; i++) { struct page *page = pages[i]; + struct folio *folio = page_folio(page); /* * Make sure the IRQ-safe lock-holding time does not get @@ -904,7 +911,7 @@ void release_pages(struct page **pages, int nr) lruvec = NULL; } - page = compound_head(page); + page = &folio->page; if (is_huge_zero_page(page)) continue; @@ -943,7 +950,7 @@ void release_pages(struct page **pages, int nr) if (PageLRU(page)) { struct lruvec *prev_lruvec = lruvec; - lruvec = relock_page_lruvec_irqsave(page, lruvec, + lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); if (prev_lruvec != lruvec) lock_batch = 0; @@ -985,17 +992,18 @@ void __pagevec_release(struct pagevec *pvec) } EXPORT_SYMBOL(__pagevec_release); -static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec) +static void __pagevec_lru_add_fn(struct folio *folio, struct lruvec *lruvec) { - int was_unevictable = TestClearPageUnevictable(page); - int nr_pages = thp_nr_pages(page); + int was_unevictable = folio_test_clear_unevictable(folio); + long nr_pages = folio_nr_pages(folio); - VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* - * Page becomes evictable in two ways: + * A folio becomes evictable in two ways: * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()]. - * 2) Before acquiring LRU lock to put the page to correct LRU and then + * 2) Before acquiring LRU lock to put the folio on the correct LRU + * and then * a) do PageLRU check with lock [check_move_unevictable_pages] * b) do PageLRU check before lock [clear_page_mlock] * @@ -1004,35 +1012,36 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec) * * #0: __pagevec_lru_add_fn #1: clear_page_mlock * - * SetPageLRU() TestClearPageMlocked() + * folio_set_lru() folio_test_clear_mlocked() * smp_mb() // explicit ordering // above provides strict * // ordering - * PageMlocked() PageLRU() + * folio_test_mlocked() folio_test_lru() * * - * if '#1' does not observe setting of PG_lru by '#0' and fails - * isolation, the explicit barrier will make sure that page_evictable - * check will put the page in correct LRU. Without smp_mb(), SetPageLRU - * can be reordered after PageMlocked check and can make '#1' to fail - * the isolation of the page whose Mlocked bit is cleared (#0 is also - * looking at the same page) and the evictable page will be stranded - * in an unevictable LRU. + * if '#1' does not observe setting of PG_lru by '#0' and + * fails isolation, the explicit barrier will make sure that + * folio_evictable check will put the folio on the correct + * LRU. Without smp_mb(), folio_set_lru() can be reordered + * after folio_test_mlocked() check and can make '#1' fail the + * isolation of the folio whose mlocked bit is cleared (#0 is + * also looking at the same folio) and the evictable folio will + * be stranded on an unevictable LRU. */ - SetPageLRU(page); + folio_set_lru(folio); smp_mb__after_atomic(); - if (page_evictable(page)) { + if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { - ClearPageActive(page); - SetPageUnevictable(page); + folio_clear_active(folio); + folio_set_unevictable(folio); if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } - add_page_to_lru_list(page, lruvec); - trace_mm_lru_insertion(page); + lruvec_add_folio(lruvec, folio); + trace_mm_lru_insertion(folio); } /* @@ -1046,10 +1055,10 @@ void __pagevec_lru_add(struct pagevec *pvec) unsigned long flags = 0; for (i = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; + struct folio *folio = page_folio(pvec->pages[i]); - lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); - __pagevec_lru_add_fn(page, lruvec); + lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); + __pagevec_lru_add_fn(folio, lruvec); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); diff --git a/mm/swap_state.c b/mm/swap_state.c index bc7cee6b2ec5..8d4104242100 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -498,7 +498,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, mem_cgroup_swapin_uncharge_swap(entry); if (shadow) - workingset_refault(page, shadow); + workingset_refault(page_folio(page), shadow); /* Caller will initiate read into locked page */ lru_cache_add(page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 22d10f713848..e3dcaeecc50f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3534,13 +3534,13 @@ struct swap_info_struct *page_swap_info(struct page *page) } /* - * out-of-line __page_file_ methods to avoid include hell. + * out-of-line methods to avoid include hell. */ -struct address_space *__page_file_mapping(struct page *page) +struct address_space *swapcache_mapping(struct folio *folio) { - return page_swap_info(page)->swap_file->f_mapping; + return page_swap_info(&folio->page)->swap_file->f_mapping; } -EXPORT_SYMBOL_GPL(__page_file_mapping); +EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __page_file_index(struct page *page) { diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 7a9008415534..36e5f6ab976f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -164,7 +164,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), dst_mm, GFP_KERNEL)) goto out_release; ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, diff --git a/mm/util.c b/mm/util.c index bacabe446906..e58151a61255 100644 --- a/mm/util.c +++ b/mm/util.c @@ -654,81 +654,78 @@ void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) } EXPORT_SYMBOL(kvrealloc); -static inline void *__page_rmapping(struct page *page) -{ - unsigned long mapping; - - mapping = (unsigned long)page->mapping; - mapping &= ~PAGE_MAPPING_FLAGS; - - return (void *)mapping; -} - /* Neutral page->mapping pointer to address_space or anon_vma or other */ void *page_rmapping(struct page *page) { - page = compound_head(page); - return __page_rmapping(page); + return folio_raw_mapping(page_folio(page)); } -/* - * Return true if this page is mapped into pagetables. - * For compound page it returns true if any subpage of compound page is mapped. +/** + * folio_mapped - Is this folio mapped into userspace? + * @folio: The folio. + * + * Return: True if any page in this folio is referenced by user page tables. */ -bool page_mapped(struct page *page) +bool folio_mapped(struct folio *folio) { - int i; + long i, nr; - if (likely(!PageCompound(page))) - return atomic_read(&page->_mapcount) >= 0; - page = compound_head(page); - if (atomic_read(compound_mapcount_ptr(page)) >= 0) + if (folio_test_single(folio)) + return atomic_read(&folio->_mapcount) >= 0; + if (atomic_read(folio_mapcount_ptr(folio)) >= 0) return true; - if (PageHuge(page)) + if (folio_test_hugetlb(folio)) return false; - for (i = 0; i < compound_nr(page); i++) { - if (atomic_read(&page[i]._mapcount) >= 0) + + nr = folio_nr_pages(folio); + for (i = 0; i < nr; i++) { + if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0) return true; } return false; } -EXPORT_SYMBOL(page_mapped); +EXPORT_SYMBOL(folio_mapped); struct anon_vma *page_anon_vma(struct page *page) { - unsigned long mapping; + struct folio *folio = page_folio(page); + unsigned long mapping = (unsigned long)folio->mapping; - page = compound_head(page); - mapping = (unsigned long)page->mapping; if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) return NULL; - return __page_rmapping(page); + return (void *)(mapping - PAGE_MAPPING_ANON); } -struct address_space *page_mapping(struct page *page) +/** + * folio_mapping - Find the mapping where this folio is stored. + * @folio: The folio. + * + * For folios which are in the page cache, return the mapping that this + * page belongs to. Folios in the swap cache return the swap mapping + * this page is stored in (which is different from the mapping for the + * swap file or swap device where the data is stored). + * + * You can call this for folios which aren't in the swap cache or page + * cache and it will return NULL. + */ +struct address_space *folio_mapping(struct folio *folio) { struct address_space *mapping; - page = compound_head(page); - /* This happens if someone calls flush_dcache_page on slab page */ - if (unlikely(PageSlab(page))) + if (unlikely(folio_test_slab(folio))) return NULL; - if (unlikely(PageSwapCache(page))) { - swp_entry_t entry; + if (unlikely(folio_test_swapcache(folio))) + return swap_address_space(folio_swap_entry(folio)); - entry.val = page_private(page); - return swap_address_space(entry); - } - - mapping = page->mapping; + mapping = folio->mapping; if ((unsigned long)mapping & PAGE_MAPPING_ANON) return NULL; return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); } -EXPORT_SYMBOL(page_mapping); +EXPORT_SYMBOL(folio_mapping); /* Slow path of page_mapcount() for compound pages */ int __page_mapcount(struct page *page) @@ -750,13 +747,26 @@ int __page_mapcount(struct page *page) } EXPORT_SYMBOL_GPL(__page_mapcount); -void copy_huge_page(struct page *dst, struct page *src) +/** + * folio_copy - Copy the contents of one folio to another. + * @dst: Folio to copy to. + * @src: Folio to copy from. + * + * The bytes in the folio represented by @src are copied to @dst. + * Assumes the caller has validated that @dst is at least as large as @src. + * Can be called in atomic context for order-0 folios, but if the folio is + * larger, it may sleep. + */ +void folio_copy(struct folio *dst, struct folio *src) { - unsigned i, nr = compound_nr(src); + long i = 0; + long nr = folio_nr_pages(src); - for (i = 0; i < nr; i++) { + for (;;) { + copy_highpage(folio_page(dst, i), folio_page(src, i)); + if (++i == nr) + break; cond_resched(); - copy_highpage(nth_page(dst, i), nth_page(src, i)); } } @@ -1079,3 +1089,14 @@ void page_offline_end(void) up_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_end); + +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO +void flush_dcache_folio(struct folio *folio) +{ + long i, nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) + flush_dcache_page(folio_page(folio, i)); +} +EXPORT_SYMBOL(flush_dcache_folio); +#endif diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d77830ff604c..e8a807c78110 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2816,6 +2816,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid, unsigned int order, unsigned int nr_pages, struct page **pages) { unsigned int nr_allocated = 0; + struct page *page; + int i; /* * For order-0 pages we make use of bulk allocator, if @@ -2823,7 +2825,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * to fails, fallback to a single page allocator that is * more permissive. */ - if (!order) { + if (!order && nid != NUMA_NO_NODE) { while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; @@ -2848,7 +2850,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, if (nr != nr_pages_request) break; } - } else + } else if (order) /* * Compound pages required for remap_vmalloc_page if * high-order pages. @@ -2856,11 +2858,12 @@ vm_area_alloc_pages(gfp_t gfp, int nid, gfp |= __GFP_COMP; /* High-order pages or fallback path if "bulk" fails. */ - while (nr_allocated < nr_pages) { - struct page *page; - int i; - page = alloc_pages_node(nid, gfp, order); + while (nr_allocated < nr_pages) { + if (nid == NUMA_NO_NODE) + page = alloc_pages(gfp, order); + else + page = alloc_pages_node(nid, gfp, order); if (unlikely(!page)) break; diff --git a/mm/vmscan.c b/mm/vmscan.c index 74296c2d1fed..306229c4313f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2090,6 +2090,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, */ int isolate_lru_page(struct page *page) { + struct folio *folio = page_folio(page); int ret = -EBUSY; VM_BUG_ON_PAGE(!page_count(page), page); @@ -2099,7 +2100,7 @@ int isolate_lru_page(struct page *page) struct lruvec *lruvec; get_page(page); - lruvec = lock_page_lruvec_irq(page); + lruvec = folio_lruvec_lock_irq(folio); del_page_from_lru_list(page, lruvec); unlock_page_lruvec_irq(lruvec); ret = 0; @@ -2199,7 +2200,7 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec, * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ - VM_BUG_ON_PAGE(!page_matches_lruvec(page, lruvec), page); + VM_BUG_ON_PAGE(!folio_matches_lruvec(page_folio(page), lruvec), page); add_page_to_lru_list(page, lruvec); nr_pages = thp_nr_pages(page); nr_moved += nr_pages; @@ -4665,6 +4666,7 @@ void check_move_unevictable_pages(struct pagevec *pvec) for (i = 0; i < pvec->nr; i++) { struct page *page = pvec->pages[i]; + struct folio *folio = page_folio(page); int nr_pages; if (PageTransTail(page)) @@ -4677,7 +4679,7 @@ void check_move_unevictable_pages(struct pagevec *pvec) if (!TestClearPageLRU(page)) continue; - lruvec = relock_page_lruvec_irq(page, lruvec); + lruvec = folio_lruvec_relock_irq(folio, lruvec); if (page_evictable(page) && PageUnevictable(page)) { del_page_from_lru_list(page, lruvec); ClearPageUnevictable(page); diff --git a/mm/workingset.c b/mm/workingset.c index d5b81e4f4cbe..109ab978251a 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -273,17 +273,17 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) } /** - * workingset_refault - evaluate the refault of a previously evicted page - * @page: the freshly allocated replacement page - * @shadow: shadow entry of the evicted page + * workingset_refault - Evaluate the refault of a previously evicted folio. + * @folio: The freshly allocated replacement folio. + * @shadow: Shadow entry of the evicted folio. * * Calculates and evaluates the refault distance of the previously - * evicted page in the context of the node and the memcg whose memory + * evicted folio in the context of the node and the memcg whose memory * pressure caused the eviction. */ -void workingset_refault(struct page *page, void *shadow) +void workingset_refault(struct folio *folio, void *shadow) { - bool file = page_is_file_lru(page); + bool file = folio_is_file_lru(folio); struct mem_cgroup *eviction_memcg; struct lruvec *eviction_lruvec; unsigned long refault_distance; @@ -295,16 +295,17 @@ void workingset_refault(struct page *page, void *shadow) unsigned long refault; bool workingset; int memcgid; + long nr; unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* * Look up the memcg associated with the stored ID. It might - * have been deleted since the page's eviction. + * have been deleted since the folio's eviction. * * Note that in rare events the ID could have been recycled - * for a new cgroup that refaults a shared page. This is + * for a new cgroup that refaults a shared folio. This is * impossible to tell from the available data. However, this * should be a rare and limited disturbance, and activations * are always speculative anyway. Ultimately, it's the aging @@ -340,17 +341,18 @@ void workingset_refault(struct page *page, void *shadow) refault_distance = (refault - eviction) & EVICTION_MASK; /* - * The activation decision for this page is made at the level + * The activation decision for this folio is made at the level * where the eviction occurred, as that is where the LRU order - * during page reclaim is being determined. + * during folio reclaim is being determined. * - * However, the cgroup that will own the page is the one that + * However, the cgroup that will own the folio is the one that * is actually experiencing the refault event. */ - memcg = page_memcg(page); + nr = folio_nr_pages(folio); + memcg = folio_memcg(folio); lruvec = mem_cgroup_lruvec(memcg, pgdat); - inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file); + mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); mem_cgroup_flush_stats(); /* @@ -376,16 +378,16 @@ void workingset_refault(struct page *page, void *shadow) if (refault_distance > workingset_size) goto out; - SetPageActive(page); - workingset_age_nonresident(lruvec, thp_nr_pages(page)); - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file); + folio_set_active(folio); + workingset_age_nonresident(lruvec, nr); + mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr); - /* Page was active prior to eviction */ + /* Folio was active prior to eviction */ if (workingset) { - SetPageWorkingset(page); + folio_set_workingset(folio); /* XXX: Move to lru_cache_add() when it supports new vs putback */ - lru_note_cost_page(page); - inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file); + lru_note_cost_folio(folio); + mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr); } out: rcu_read_unlock(); @@ -393,12 +395,11 @@ out: /** * workingset_activation - note a page activation - * @page: page that is being activated + * @folio: Folio that is being activated. */ -void workingset_activation(struct page *page) +void workingset_activation(struct folio *folio) { struct mem_cgroup *memcg; - struct lruvec *lruvec; rcu_read_lock(); /* @@ -408,11 +409,10 @@ void workingset_activation(struct page *page) * XXX: See workingset_refault() - this should return * root_mem_cgroup even for !CONFIG_MEMCG. */ - memcg = page_memcg_rcu(page); + memcg = folio_memcg_rcu(folio); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_page_lruvec(page); - workingset_age_nonresident(lruvec, thp_nr_pages(page)); + workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio)); out: rcu_read_unlock(); } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 1669744304c5..17687848daec 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1560,10 +1560,14 @@ int batadv_bla_init(struct batadv_priv *bat_priv) return 0; bat_priv->bla.claim_hash = batadv_hash_new(128); - bat_priv->bla.backbone_hash = batadv_hash_new(32); + if (!bat_priv->bla.claim_hash) + return -ENOMEM; - if (!bat_priv->bla.claim_hash || !bat_priv->bla.backbone_hash) + bat_priv->bla.backbone_hash = batadv_hash_new(32); + if (!bat_priv->bla.backbone_hash) { + batadv_hash_destroy(bat_priv->bla.claim_hash); return -ENOMEM; + } batadv_hash_set_lock_class(bat_priv->bla.claim_hash, &batadv_claim_hash_lock_class_key); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 3ddd66e4c29e..5207cd8d6ad8 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -190,29 +190,41 @@ int batadv_mesh_init(struct net_device *soft_iface) bat_priv->gw.generation = 0; - ret = batadv_v_mesh_init(bat_priv); - if (ret < 0) - goto err; - ret = batadv_originator_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_orig; + } ret = batadv_tt_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_tt; + } + + ret = batadv_v_mesh_init(bat_priv); + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_v; + } ret = batadv_bla_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_bla; + } ret = batadv_dat_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_dat; + } ret = batadv_nc_mesh_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_nc; + } batadv_gw_init(bat_priv); batadv_mcast_init(bat_priv); @@ -222,8 +234,20 @@ int batadv_mesh_init(struct net_device *soft_iface) return 0; -err: - batadv_mesh_free(soft_iface); +err_nc: + batadv_dat_free(bat_priv); +err_dat: + batadv_bla_free(bat_priv); +err_bla: + batadv_v_mesh_free(bat_priv); +err_v: + batadv_tt_free(bat_priv); +err_tt: + batadv_originator_free(bat_priv); +err_orig: + batadv_purge_outstanding_packets(bat_priv, NULL); + atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); + return ret; } diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 9f06132e007d..0a7f1d36a6a8 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -152,8 +152,10 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv) &batadv_nc_coding_hash_lock_class_key); bat_priv->nc.decoding_hash = batadv_hash_new(128); - if (!bat_priv->nc.decoding_hash) + if (!bat_priv->nc.decoding_hash) { + batadv_hash_destroy(bat_priv->nc.coding_hash); goto err; + } batadv_hash_set_lock_class(bat_priv->nc.decoding_hash, &batadv_nc_decoding_hash_lock_class_key); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index e0b3dace2020..4b7ad6684bc4 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -4162,8 +4162,10 @@ int batadv_tt_init(struct batadv_priv *bat_priv) return ret; ret = batadv_tt_global_init(bat_priv); - if (ret < 0) + if (ret < 0) { + batadv_tt_local_table_free(bat_priv); return ret; + } batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1, batadv_tt_tvlv_unicast_handler_v1, diff --git a/net/core/dev.c b/net/core/dev.c index 7ee9fecd3aff..eb3a366bf212 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3163,6 +3163,12 @@ static u16 skb_tx_hash(const struct net_device *dev, qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; + if (unlikely(!qcount)) { + net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", + sb_dev->name, qoffset, tc); + qoffset = 0; + qcount = dev->real_num_tx_queues; + } } if (skb_rx_queue_recorded(skb)) { @@ -3906,7 +3912,8 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->pkt_type = PACKET_LOOPBACK; - skb->ip_summed = CHECKSUM_UNNECESSARY; + if (skb->ip_summed == CHECKSUM_NONE) + skb->ip_summed = CHECKSUM_UNNECESSARY; WARN_ON(!skb_dst(skb)); skb_dst_force(skb); netif_rx_ni(skb); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index f6197774048b..b2e49eb7001d 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1973,9 +1973,9 @@ int netdev_register_kobject(struct net_device *ndev) int netdev_change_owner(struct net_device *ndev, const struct net *net_old, const struct net *net_new) { + kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID; + kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID; struct device *dev = &ndev->dev; - kuid_t old_uid, new_uid; - kgid_t old_gid, new_gid; int error; net_ns_get_ownership(net_old, &old_uid, &old_gid); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2170bea2c7de..fe9358437380 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -80,6 +80,7 @@ #include <linux/indirect_call_wrapper.h> #include "datagram.h" +#include "sock_destructor.h" struct kmem_cache *skbuff_head_cache __ro_after_init; static struct kmem_cache *skbuff_fclone_cache __ro_after_init; @@ -1804,30 +1805,39 @@ EXPORT_SYMBOL(skb_realloc_headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) { int delta = headroom - skb_headroom(skb); + int osize = skb_end_offset(skb); + struct sock *sk = skb->sk; if (WARN_ONCE(delta <= 0, "%s is expecting an increase in the headroom", __func__)) return skb; - /* pskb_expand_head() might crash, if skb is shared */ - if (skb_shared(skb)) { + delta = SKB_DATA_ALIGN(delta); + /* pskb_expand_head() might crash, if skb is shared. */ + if (skb_shared(skb) || !is_skb_wmem(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); - if (likely(nskb)) { - if (skb->sk) - skb_set_owner_w(nskb, skb->sk); - consume_skb(skb); - } else { - kfree_skb(skb); - } + if (unlikely(!nskb)) + goto fail; + + if (sk) + skb_set_owner_w(nskb, sk); + consume_skb(skb); skb = nskb; } - if (skb && - pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { - kfree_skb(skb); - skb = NULL; + if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) + goto fail; + + if (sk && is_skb_wmem(skb)) { + delta = skb_end_offset(skb) - osize; + refcount_add(delta, &sk->sk_wmem_alloc); + skb->truesize += delta; } return skb; + +fail: + kfree_skb(skb); + return NULL; } EXPORT_SYMBOL(skb_expand_head); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2d6249b28928..a86ef7e844f8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -474,6 +474,20 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, } EXPORT_SYMBOL_GPL(sk_msg_recvmsg); +bool sk_msg_is_readable(struct sock *sk) +{ + struct sk_psock *psock; + bool empty = true; + + rcu_read_lock(); + psock = sk_psock(sk); + if (likely(psock)) + empty = list_empty(&psock->ingress_msg); + rcu_read_unlock(); + return !empty; +} +EXPORT_SYMBOL_GPL(sk_msg_is_readable); + static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, struct sk_buff *skb) { diff --git a/net/core/sock_destructor.h b/net/core/sock_destructor.h new file mode 100644 index 000000000000..2f396e6bfba5 --- /dev/null +++ b/net/core/sock_destructor.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_CORE_SOCK_DESTRUCTOR_H +#define _NET_CORE_SOCK_DESTRUCTOR_H +#include <net/tcp.h> + +static inline bool is_skb_wmem(const struct sk_buff *skb) +{ + return skb->destructor == sock_wfree || + skb->destructor == __sock_wfree || + (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree); +} +#endif diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index c8496c1142c9..5f88526ad61c 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -419,7 +419,7 @@ static struct ctl_table net_core_table[] = { .mode = 0600, .proc_handler = proc_dolongvec_minmax_bpf_restricted, .extra1 = &long_one, - .extra2 = &long_max, + .extra2 = &bpf_jit_limit_max, }, #endif { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e8b48df73c85..f5c336f8b0c8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -486,10 +486,7 @@ static bool tcp_stream_is_readable(struct sock *sk, int target) { if (tcp_epollin_ready(sk, target)) return true; - - if (sk->sk_prot->stream_memory_read) - return sk->sk_prot->stream_memory_read(sk); - return false; + return sk_is_readable(sk); } /* diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index d3e9386b493e..5f4d6f45d87f 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -150,19 +150,6 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); #ifdef CONFIG_BPF_SYSCALL -static bool tcp_bpf_stream_read(const struct sock *sk) -{ - struct sk_psock *psock; - bool empty = true; - - rcu_read_lock(); - psock = sk_psock(sk); - if (likely(psock)) - empty = list_empty(&psock->ingress_msg); - rcu_read_unlock(); - return !empty; -} - static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) { @@ -232,6 +219,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; u32 tosend, delta = 0; + u32 eval = __SK_NONE; int ret; more_data: @@ -275,13 +263,24 @@ more_data: case __SK_REDIRECT: sk_redir = psock->sk_redir; sk_msg_apply_bytes(psock, tosend); + if (!psock->apply_bytes) { + /* Clean up before releasing the sock lock. */ + eval = psock->eval; + psock->eval = __SK_NONE; + psock->sk_redir = NULL; + } if (psock->cork) { cork = true; psock->cork = NULL; } sk_msg_return(sk, msg, tosend); release_sock(sk); + ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + + if (eval == __SK_REDIRECT) + sock_put(sk_redir); + lock_sock(sk); if (unlikely(ret < 0)) { int free = sk_msg_free_nocharge(sk, msg); @@ -479,7 +478,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], prot[TCP_BPF_BASE].unhash = sock_map_unhash; prot[TCP_BPF_BASE].close = sock_map_close; prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg; - prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read; + prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable; prot[TCP_BPF_TX] = prot[TCP_BPF_BASE]; prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8536b2a7210b..2fffcf2b54f3 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2867,6 +2867,9 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(EPOLLIN | EPOLLRDNORM); + /* psock ingress_msg queue should not contain any bad checksum frames */ + if (sk_is_readable(sk)) + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 7a1d5f473878..bbe6569c9ad3 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -114,6 +114,7 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base) *prot = *base; prot->close = sock_map_close; prot->recvmsg = udp_bpf_recvmsg; + prot->sock_is_readable = sk_msg_is_readable; } static void udp_bpf_check_v6_needs_rebuild(struct proto *ops) diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 97095b7c9c64..5dcfd53a4ab6 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -672,7 +672,7 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata, u8 *ie, u8 ie_len) { struct ieee80211_supported_band *sband; - const u8 *cap; + const struct element *cap; const struct ieee80211_he_operation *he_oper = NULL; sband = ieee80211_get_sband(sdata); @@ -687,9 +687,10 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.he_support = true; - cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ie, ie_len); - if (cap && cap[1] >= ieee80211_he_oper_size(&cap[3])) - he_oper = (void *)(cap + 3); + cap = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ie_len); + if (cap && cap->datalen >= 1 + sizeof(*he_oper) && + cap->datalen >= 1 + ieee80211_he_oper_size(cap->data + 1)) + he_oper = (void *)(cap->data + 1); if (he_oper) sdata->vif.bss_conf.he_oper.params = diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c41273cefc51..f0f22eb4fd5f 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -485,11 +485,11 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, mpext = mptcp_get_ext(skb); data_len = mpext ? mpext->data_len : 0; - /* we will check ext_copy.data_len in mptcp_write_options() to + /* we will check ops->data_len in mptcp_write_options() to * discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and * TCPOLEN_MPTCP_MPC_ACK */ - opts->ext_copy.data_len = data_len; + opts->data_len = data_len; opts->suboptions = OPTION_MPTCP_MPC_ACK; opts->sndr_key = subflow->local_key; opts->rcvr_key = subflow->remote_key; @@ -505,9 +505,9 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, len = TCPOLEN_MPTCP_MPC_ACK_DATA; if (opts->csum_reqd) { /* we need to propagate more info to csum the pseudo hdr */ - opts->ext_copy.data_seq = mpext->data_seq; - opts->ext_copy.subflow_seq = mpext->subflow_seq; - opts->ext_copy.csum = mpext->csum; + opts->data_seq = mpext->data_seq; + opts->subflow_seq = mpext->subflow_seq; + opts->csum = mpext->csum; len += TCPOLEN_MPTCP_DSS_CHECKSUM; } *size = ALIGN(len, 4); @@ -1227,7 +1227,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } -static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +static u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __sum16 sum) { struct csum_pseudo_header header; __wsum csum; @@ -1237,15 +1237,21 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext) * always the 64-bit value, irrespective of what length is used in the * DSS option itself. */ - header.data_seq = cpu_to_be64(mpext->data_seq); - header.subflow_seq = htonl(mpext->subflow_seq); - header.data_len = htons(mpext->data_len); + header.data_seq = cpu_to_be64(data_seq); + header.subflow_seq = htonl(subflow_seq); + header.data_len = htons(data_len); header.csum = 0; - csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum)); + csum = csum_partial(&header, sizeof(header), ~csum_unfold(sum)); return (__force u16)csum_fold(csum); } +static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +{ + return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len, + mpext->csum); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { @@ -1337,7 +1343,7 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, len = TCPOLEN_MPTCP_MPC_SYN; } else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYNACK; - } else if (opts->ext_copy.data_len) { + } else if (opts->data_len) { len = TCPOLEN_MPTCP_MPC_ACK_DATA; if (opts->csum_reqd) len += TCPOLEN_MPTCP_DSS_CHECKSUM; @@ -1366,14 +1372,17 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, put_unaligned_be64(opts->rcvr_key, ptr); ptr += 2; - if (!opts->ext_copy.data_len) + if (!opts->data_len) goto mp_capable_done; if (opts->csum_reqd) { - put_unaligned_be32(opts->ext_copy.data_len << 16 | - mptcp_make_csum(&opts->ext_copy), ptr); + put_unaligned_be32(opts->data_len << 16 | + __mptcp_make_csum(opts->data_seq, + opts->subflow_seq, + opts->data_len, + opts->csum), ptr); } else { - put_unaligned_be32(opts->ext_copy.data_len << 16 | + put_unaligned_be32(opts->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); } ptr += 1; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 32df65f68c12..fb3da4d8f4a3 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -156,6 +156,12 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( void *arg, struct sctp_cmd_seq *commands); +static enum sctp_disposition +__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands); + /* Small helper function that checks if the chunk length * is of the appropriate length. The 'required_length' argument * is set to be the size of a specific chunk we are testing. @@ -337,6 +343,14 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the INIT chunk has a valid length. + * Normally, this would cause an ABORT with a Protocol Violation + * error, but since we don't have an association, we'll + * just discard the packet. + */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ @@ -351,14 +365,6 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); - /* Make sure that the INIT chunk has a valid length. - * Normally, this would cause an ABORT with a Protocol Violation - * error, but since we don't have an association, we'll - * just discard the packet. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* If the INIT is coming toward a closing socket, we'll send back * and ABORT. Essentially, this catches the race of INIT being * backloged to the socket at the same time as the user issues close(). @@ -704,6 +710,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, struct sock *sk; int error = 0; + if (asoc && !sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ @@ -718,7 +727,8 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, * in sctp_unpack_cookie(). */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); /* If the endpoint is not listening or if the number of associations * on the TCP-style socket exceed the max backlog, respond with an @@ -1524,20 +1534,16 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the INIT chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* 3.1 A packet containing an INIT chunk MUST have a zero Verification * Tag. */ if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); - /* Make sure that the INIT chunk has a valid length. - * In this case, we generate a protocol violation since we have - * an association established. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); - if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port) return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands); @@ -1882,9 +1888,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( * its peer. */ if (sctp_state(asoc, SHUTDOWN_ACK_SENT)) { - disposition = sctp_sf_do_9_2_reshutack(net, ep, asoc, - SCTP_ST_CHUNK(chunk->chunk_hdr->type), - chunk, commands); + disposition = __sctp_sf_do_9_2_reshutack(net, ep, asoc, + SCTP_ST_CHUNK(chunk->chunk_hdr->type), + chunk, commands); if (SCTP_DISPOSITION_NOMEM == disposition) goto nomem; @@ -2202,9 +2208,11 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( * enough for the chunk header. Cookie length verification is * done later. */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) { + if (!sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); + } /* "Decode" the chunk. We have no optional parameters so we * are in good shape. @@ -2341,7 +2349,7 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2387,7 +2395,7 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2657,7 +2665,7 @@ enum sctp_disposition sctp_sf_do_9_1_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2970,13 +2978,11 @@ enum sctp_disposition sctp_sf_do_9_2_shut_ctsn( * that belong to this association, it should discard the INIT chunk and * retransmit the SHUTDOWN ACK chunk. */ -enum sctp_disposition sctp_sf_do_9_2_reshutack( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const union sctp_subtype type, - void *arg, - struct sctp_cmd_seq *commands) +static enum sctp_disposition +__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; @@ -3010,6 +3016,26 @@ nomem: return SCTP_DISPOSITION_NOMEM; } +enum sctp_disposition +sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands) +{ + struct sctp_chunk *chunk = arg; + + if (!chunk->singleton) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + + if (chunk->sctp_hdr->vtag != 0) + return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); + + return __sctp_sf_do_9_2_reshutack(net, ep, asoc, type, arg, commands); +} + /* * sctp_sf_do_ecn_cwr * @@ -3662,6 +3688,9 @@ enum sctp_disposition sctp_sf_ootb(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); + if (asoc && !sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + ch = (struct sctp_chunkhdr *)chunk->chunk_hdr; do { /* Report violation if the chunk is less then minimal */ @@ -3777,12 +3806,6 @@ static enum sctp_disposition sctp_sf_shut_8_4_5( SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); - /* If the chunk length is invalid, we don't want to process - * the reset of the packet. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* We need to discard the rest of the packet to prevent * potential boomming attacks from additional bundled chunks. * This is documented in SCTP Threats ID. @@ -3810,6 +3833,9 @@ enum sctp_disposition sctp_sf_do_8_5_1_E_sa(struct net *net, { struct sctp_chunk *chunk = arg; + if (!sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, @@ -3845,6 +3871,11 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } + /* Make sure that the ASCONF ADDIP chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk))) + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); + /* ADD-IP: Section 4.1.1 * This chunk MUST be sent in an authenticated way by using * the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk @@ -3853,13 +3884,7 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net, */ if (!asoc->peer.asconf_capable || (!net->sctp.addip_noauth && !chunk->auth)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, - commands); - - /* Make sure that the ASCONF ADDIP chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); hdr = (struct sctp_addiphdr *)chunk->skb->data; serial = ntohl(hdr->serial); @@ -3988,6 +4013,12 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } + /* Make sure that the ADDIP chunk has a valid length. */ + if (!sctp_chunk_length_valid(asconf_ack, + sizeof(struct sctp_addip_chunk))) + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); + /* ADD-IP, Section 4.1.2: * This chunk MUST be sent in an authenticated way by using * the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk @@ -3996,14 +4027,7 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, */ if (!asoc->peer.asconf_capable || (!net->sctp.addip_noauth && !asconf_ack->auth)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, - commands); - - /* Make sure that the ADDIP chunk has a valid length. */ - if (!sctp_chunk_length_valid(asconf_ack, - sizeof(struct sctp_addip_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); addip_hdr = (struct sctp_addiphdr *)asconf_ack->skb->data; rcvd_serial = ntohl(addip_hdr->serial); @@ -4575,6 +4599,9 @@ enum sctp_disposition sctp_sf_discard_chunk(struct net *net, { struct sctp_chunk *chunk = arg; + if (asoc && !sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the chunk has a valid length. * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. @@ -4642,6 +4669,9 @@ enum sctp_disposition sctp_sf_violation(struct net *net, { struct sctp_chunk *chunk = arg; + if (!sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, @@ -6348,6 +6378,7 @@ static struct sctp_packet *sctp_ootb_pkt_new( * yet. */ switch (chunk->chunk_hdr->type) { + case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: { struct sctp_initack_chunk *initack; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c038efc23ce3..78b663dbfa1f 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1057,7 +1057,7 @@ static void smc_connect_work(struct work_struct *work) if (smc->clcsock->sk->sk_err) { smc->sk.sk_err = smc->clcsock->sk->sk_err; } else if ((1 << smc->clcsock->sk->sk_state) & - (TCPF_SYN_SENT | TCP_SYN_RECV)) { + (TCPF_SYN_SENT | TCPF_SYN_RECV)) { rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo); if ((rc == -EPIPE) && ((1 << smc->clcsock->sk->sk_state) & diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 72f4b72eb175..f1d323439a2a 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -1822,7 +1822,7 @@ void smc_llc_link_active(struct smc_link *link) link->smcibdev->ibdev->name, link->ibport); link->state = SMC_LNK_ACTIVE; if (link->lgr->llc_testlink_time) { - link->llc_testlink_time = link->lgr->llc_testlink_time * HZ; + link->llc_testlink_time = link->lgr->llc_testlink_time; schedule_delayed_work(&link->llc_testlink_wrk, link->llc_testlink_time); } diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index c9391d38de85..dc60c32bb70d 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -2285,43 +2285,53 @@ static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr) u16 key_gen = msg_key_gen(hdr); u16 size = msg_data_sz(hdr); u8 *data = msg_data(hdr); + unsigned int keylen; + + /* Verify whether the size can exist in the packet */ + if (unlikely(size < sizeof(struct tipc_aead_key) + TIPC_AEAD_KEYLEN_MIN)) { + pr_debug("%s: message data size is too small\n", rx->name); + goto exit; + } + + keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME))); + + /* Verify the supplied size values */ + if (unlikely(size != keylen + sizeof(struct tipc_aead_key) || + keylen > TIPC_AEAD_KEY_SIZE_MAX)) { + pr_debug("%s: invalid MSG_CRYPTO key size\n", rx->name); + goto exit; + } spin_lock(&rx->lock); if (unlikely(rx->skey || (key_gen == rx->key_gen && rx->key.keys))) { pr_err("%s: key existed <%p>, gen %d vs %d\n", rx->name, rx->skey, key_gen, rx->key_gen); - goto exit; + goto exit_unlock; } /* Allocate memory for the key */ skey = kmalloc(size, GFP_ATOMIC); if (unlikely(!skey)) { pr_err("%s: unable to allocate memory for skey\n", rx->name); - goto exit; + goto exit_unlock; } /* Copy key from msg data */ - skey->keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME))); + skey->keylen = keylen; memcpy(skey->alg_name, data, TIPC_AEAD_ALG_NAME); memcpy(skey->key, data + TIPC_AEAD_ALG_NAME + sizeof(__be32), skey->keylen); - /* Sanity check */ - if (unlikely(size != tipc_aead_key_size(skey))) { - kfree(skey); - skey = NULL; - goto exit; - } - rx->key_gen = key_gen; rx->skey_mode = msg_key_mode(hdr); rx->skey = skey; rx->nokey = 0; mb(); /* for nokey flag */ -exit: +exit_unlock: spin_unlock(&rx->lock); +exit: /* Schedule the key attaching on this crypto */ if (likely(skey && queue_delayed_work(tx->wq, &rx->work, 0))) return true; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index fde56ff49163..9ab81db8a654 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -681,12 +681,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg; - prot[TLS_BASE][TLS_SW].stream_memory_read = tls_sw_stream_read; + prot[TLS_BASE][TLS_SW].sock_is_readable = tls_sw_sock_is_readable; prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close; prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE]; prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg; - prot[TLS_SW][TLS_SW].stream_memory_read = tls_sw_stream_read; + prot[TLS_SW][TLS_SW].sock_is_readable = tls_sw_sock_is_readable; prot[TLS_SW][TLS_SW].close = tls_sk_proto_close; #ifdef CONFIG_TLS_DEVICE diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 4feb95e34b64..1b08b877a890 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -35,6 +35,7 @@ * SOFTWARE. */ +#include <linux/bug.h> #include <linux/sched/signal.h> #include <linux/module.h> #include <linux/splice.h> @@ -43,6 +44,14 @@ #include <net/strparser.h> #include <net/tls.h> +noinline void tls_err_abort(struct sock *sk, int err) +{ + WARN_ON_ONCE(err >= 0); + /* sk->sk_err should contain a positive error code. */ + sk->sk_err = -err; + sk_error_report(sk); +} + static int __skb_nsg(struct sk_buff *skb, int offset, int len, unsigned int recursion_level) { @@ -419,7 +428,7 @@ int tls_tx_records(struct sock *sk, int flags) tx_err: if (rc < 0 && rc != -EAGAIN) - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); return rc; } @@ -450,7 +459,7 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err) /* If err is already set on socket, return the same code */ if (sk->sk_err) { - ctx->async_wait.err = sk->sk_err; + ctx->async_wait.err = -sk->sk_err; } else { ctx->async_wait.err = err; tls_err_abort(sk, err); @@ -763,7 +772,7 @@ static int tls_push_record(struct sock *sk, int flags, msg_pl->sg.size + prot->tail_size, i); if (rc < 0) { if (rc != -EINPROGRESS) { - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); if (split) { tls_ctx->pending_open_record_frags = true; tls_merge_open_record(sk, rec, tmp, orig_end); @@ -1827,7 +1836,7 @@ int tls_sw_recvmsg(struct sock *sk, err = decrypt_skb_update(sk, skb, &msg->msg_iter, &chunk, &zc, async_capable); if (err < 0 && err != -EINPROGRESS) { - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); goto recv_end; } @@ -2007,7 +2016,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, } if (err < 0) { - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); goto splice_read_end; } ctx->decrypted = 1; @@ -2026,7 +2035,7 @@ splice_read_end: return copied ? : err; } -bool tls_sw_stream_read(const struct sock *sk) +bool tls_sw_sock_is_readable(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 89f9e85ae970..78e08e82c08c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3052,6 +3052,8 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa /* readable? */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; + if (sk_is_readable(sk)) + mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && @@ -3091,6 +3093,8 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, /* readable? */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; + if (sk_is_readable(sk)) + mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ if (sk->sk_type == SOCK_SEQPACKET) { diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index b927e2baae50..452376c6f419 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -102,6 +102,7 @@ static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto *prot = *base; prot->close = sock_map_close; prot->recvmsg = unix_bpf_recvmsg; + prot->sock_is_readable = sk_msg_is_readable; } static void unix_stream_bpf_rebuild_protos(struct proto *prot, @@ -110,6 +111,7 @@ static void unix_stream_bpf_rebuild_protos(struct proto *prot, *prot = *base; prot->close = sock_map_close; prot->recvmsg = unix_bpf_recvmsg; + prot->sock_is_readable = sk_msg_is_readable; prot->unhash = sock_map_unhash; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 03323121ca50..aaba847d79eb 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -524,6 +524,7 @@ use_default_name: INIT_WORK(&rdev->propagate_cac_done_wk, cfg80211_propagate_cac_done_wk); INIT_WORK(&rdev->mgmt_registrations_update_wk, cfg80211_mgmt_registrations_update_wk); + spin_lock_init(&rdev->mgmt_registrations_lock); #ifdef CONFIG_CFG80211_DEFAULT_PS rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT; @@ -1279,7 +1280,6 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) INIT_LIST_HEAD(&wdev->event_list); spin_lock_init(&wdev->event_lock); INIT_LIST_HEAD(&wdev->mgmt_registrations); - spin_lock_init(&wdev->mgmt_registrations_lock); INIT_LIST_HEAD(&wdev->pmsr_list); spin_lock_init(&wdev->pmsr_lock); INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk); diff --git a/net/wireless/core.h b/net/wireless/core.h index b35d0db12f1d..1720abf36f92 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -100,6 +100,8 @@ struct cfg80211_registered_device { struct work_struct propagate_cac_done_wk; struct work_struct mgmt_registrations_update_wk; + /* lock for all wdev lists */ + spinlock_t mgmt_registrations_lock; /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 3aa69b375a10..783acd2c4211 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -452,9 +452,9 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev) lockdep_assert_held(&rdev->wiphy.mtx); - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); if (!wdev->mgmt_registrations_need_update) { - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); return; } @@ -479,7 +479,7 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev) rcu_read_unlock(); wdev->mgmt_registrations_need_update = 0; - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); rdev_update_mgmt_frame_registrations(rdev, wdev, &upd); } @@ -503,6 +503,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, int match_len, bool multicast_rx, struct netlink_ext_ack *extack) { + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_mgmt_registration *reg, *nreg; int err = 0; u16 mgmt_type; @@ -548,7 +549,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, if (!nreg) return -ENOMEM; - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); list_for_each_entry(reg, &wdev->mgmt_registrations, list) { int mlen = min(match_len, reg->match_len); @@ -583,7 +584,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, list_add(&nreg->list, &wdev->mgmt_registrations); } wdev->mgmt_registrations_need_update = 1; - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); cfg80211_mgmt_registrations_update(wdev); @@ -591,7 +592,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, out: kfree(nreg); - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); return err; } @@ -602,7 +603,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct cfg80211_mgmt_registration *reg, *tmp; - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) { if (reg->nlportid != nlportid) @@ -615,7 +616,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) schedule_work(&rdev->mgmt_registrations_update_wk); } - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); if (nlportid && rdev->crit_proto_nlportid == nlportid) { rdev->crit_proto_nlportid = 0; @@ -628,15 +629,16 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) { + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_mgmt_registration *reg, *tmp; - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) { list_del(®->list); kfree(reg); } wdev->mgmt_registrations_need_update = 1; - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); cfg80211_mgmt_registrations_update(wdev); } @@ -784,7 +786,7 @@ bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm, data = buf + ieee80211_hdrlen(mgmt->frame_control); data_len = len - ieee80211_hdrlen(mgmt->frame_control); - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); list_for_each_entry(reg, &wdev->mgmt_registrations, list) { if (reg->frame_type != ftype) @@ -808,7 +810,7 @@ bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm, break; } - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); trace_cfg80211_return_bool(result); return result; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 11c68b159324..adc0d14cfd86 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -418,14 +418,17 @@ cfg80211_add_nontrans_list(struct cfg80211_bss *trans_bss, } ssid_len = ssid[1]; ssid = ssid + 2; - rcu_read_unlock(); /* check if nontrans_bss is in the list */ list_for_each_entry(bss, &trans_bss->nontrans_list, nontrans_list) { - if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len)) + if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len)) { + rcu_read_unlock(); return 0; + } } + rcu_read_unlock(); + /* add to the list */ list_add_tail(&nontrans_bss->nontrans_list, &trans_bss->nontrans_list); return 0; diff --git a/net/wireless/util.c b/net/wireless/util.c index 18dba3d7c638..a1a99a574984 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1028,14 +1028,14 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, !(rdev->wiphy.interface_modes & (1 << ntype))) return -EOPNOTSUPP; - /* if it's part of a bridge, reject changing type to station/ibss */ - if (netif_is_bridge_port(dev) && - (ntype == NL80211_IFTYPE_ADHOC || - ntype == NL80211_IFTYPE_STATION || - ntype == NL80211_IFTYPE_P2P_CLIENT)) - return -EBUSY; - if (ntype != otype) { + /* if it's part of a bridge, reject changing type to station/ibss */ + if (netif_is_bridge_port(dev) && + (ntype == NL80211_IFTYPE_ADHOC || + ntype == NL80211_IFTYPE_STATION || + ntype == NL80211_IFTYPE_P2P_CLIENT)) + return -EBUSY; + dev->ieee80211_ptr->use_4addr = false; dev->ieee80211_ptr->mesh_id_up_len = 0; wdev_lock(dev->ieee80211_ptr); diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5cd702062a04..b856afa6eb52 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -787,6 +787,8 @@ $(OUTPUT)dlfilters/%.o: dlfilters/%.c include/perf/perf_dlfilter.h $(Q)$(MKDIR) -p $(OUTPUT)dlfilters $(QUIET_CC)$(CC) -c -Iinclude $(EXTRA_CFLAGS) -o $@ -fpic $< +.SECONDARY: $(DLFILTERS:.so=.o) + $(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o $(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $< diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3018a054526a..20cd6244863b 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = { */ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) { - Dwarf_Op ops_mem[2]; + Dwarf_Op ops_mem[3]; Dwarf_Op dummy; Dwarf_Op *ops = &dummy; size_t nops; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 6211d0b84b7a..c32c2eb16d7d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -459,7 +459,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(WEIGHT) && - evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", PERF_OUTPUT_WEIGHT)) + evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT)) return -EINVAL; if (PRINT_FIELD(SYM) && @@ -4039,11 +4039,15 @@ script_found: goto out_delete; uname(&uts); - if (data.is_pipe || /* assume pipe_mode indicates native_arch */ - !strcmp(uts.machine, session->header.env.arch) || - (!strcmp(uts.machine, "x86_64") && - !strcmp(session->header.env.arch, "i386"))) + if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */ native_arch = true; + } else if (session->header.env.arch) { + if (!strcmp(uts.machine, session->header.env.arch)) + native_arch = true; + else if (!strcmp(uts.machine, "x86_64") && + !strcmp(session->header.env.arch, "i386")) + native_arch = true; + } script.session = session; script__setup_sample_type(&script); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 5c5979046523..d88bb65b74cc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -949,7 +949,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, int err, n; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1002,17 +1001,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, goto close_peer1; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_peer1: xclose(p1); @@ -1571,7 +1564,6 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1606,17 +1598,11 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); @@ -1748,7 +1734,6 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; u32 key; char b; @@ -1781,17 +1766,11 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1841,7 +1820,6 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1876,17 +1854,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1932,7 +1904,6 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, int sfd[2]; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1963,17 +1934,11 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 8e67a252b672..3313566ce906 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -445,10 +445,13 @@ cleanup() ip -netns ${NSA} link set dev ${NSA_DEV} down ip -netns ${NSA} link del dev ${NSA_DEV} + ip netns pids ${NSA} | xargs kill 2>/dev/null ip netns del ${NSA} fi + ip netns pids ${NSB} | xargs kill 2>/dev/null ip netns del ${NSB} + ip netns pids ${NSC} | xargs kill 2>/dev/null ip netns del ${NSC} >/dev/null 2>&1 } diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c index 1af16d2c2a0a..52497b7b9f1d 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -341,7 +341,7 @@ void split_file_backed_thp(void) } /* write something to the file, so a file-backed THP can be allocated */ - num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc)); + num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1); close(fd); if (num_written < 1) { |