diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2014-03-27 17:41:03 +1100 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2014-03-27 17:41:05 +1100 |
commit | 7f621e3333963ff65e2cf2bb14710cb3d808ad4e (patch) | |
tree | 7b0cd30f3efc98fbf818ffc18fd6bffc808fe3bf | |
parent | aaedc3d6496e64563732ecbe326e317e81a6b8f4 (diff) | |
parent | dbecf25f72b59c0b75d6cab4ff6854e06c691abf (diff) |
Merge branch 'akpm/master'
109 files changed, 1294 insertions, 866 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi index d773d5697cf5..3187a18af6da 100644 --- a/Documentation/ABI/testing/sysfs-class-bdi +++ b/Documentation/ABI/testing/sysfs-class-bdi @@ -53,3 +53,11 @@ stable_pages_required (read-only) If set, the backing device requires that all pages comprising a write request must not be changed until writeout is complete. + +strictlimit (read-write) + + Forces per-BDI checks for the share of given device in the write-back + cache even before the global background dirty limit is reached. This + is useful in situations where the global limit is much higher than + affordable for given relatively slow (or untrusted) device. Turning + strictlimit on has no visible effect if max_ratio is equal to 100%. diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl index d0758b241b23..b90959ba37e4 100644 --- a/Documentation/DocBook/kernel-hacking.tmpl +++ b/Documentation/DocBook/kernel-hacking.tmpl @@ -671,7 +671,7 @@ printk(KERN_INFO "my ip: %pI4\n", &ipaddress); <sect1 id="routines-local-irqs"> <title><function>local_irq_save()</function>/<function>local_irq_restore()</function> - <filename class="headerfile">include/asm/system.h</filename> + <filename class="headerfile">include/linux/irqflags.h</filename> </title> <para> diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt index 85e24c4f215c..d50fa618371b 100644 --- a/Documentation/arm64/memory.txt +++ b/Documentation/arm64/memory.txt @@ -39,7 +39,7 @@ ffffffbffa000000 ffffffbffaffffff 16MB PCI I/O space ffffffbffb000000 ffffffbffbbfffff 12MB [guard] -ffffffbffbc00000 ffffffbffbdfffff 2MB earlyprintk device +ffffffbffbc00000 ffffffbffbdfffff 2MB fixed mappings ffffffbffbe00000 ffffffbffbffffff 2MB [guard] @@ -66,7 +66,7 @@ fffffdfffa000000 fffffdfffaffffff 16MB PCI I/O space fffffdfffb000000 fffffdfffbbfffff 12MB [guard] -fffffdfffbc00000 fffffdfffbdfffff 2MB earlyprintk device +fffffdfffbc00000 fffffdfffbdfffff 2MB fixed mappings fffffdfffbe00000 fffffdfffbffffff 2MB [guard] diff --git a/Documentation/devicetree/bindings/mfd/qcom,pm8xxx.txt b/Documentation/devicetree/bindings/mfd/qcom,pm8xxx.txt index e3fe625ffd58..03518dc8b6bd 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,pm8xxx.txt +++ b/Documentation/devicetree/bindings/mfd/qcom,pm8xxx.txt @@ -1,6 +1,9 @@ Qualcomm PM8xxx PMIC multi-function devices -PROPERTIES +The PM8xxx family of Power Management ICs are used to provide regulated +voltages and other various functionality to Qualcomm SoCs. + += PROPERTIES - compatible: Usage: required @@ -45,7 +48,37 @@ PROPERTIES Value type: <empty> Definition: identifies this node as an interrupt controller -EXAMPLE += SUBCOMPONENTS + +The PMIC contains multiple independent functions, each described in a subnode. +The below bindings specify the set of valid subnodes. + +== Real-Time Clock + +- compatible: + Usage: required + Value type: <string> + Definition: must be one of: + "qcom,pm8058-rtc" + "qcom,pm8921-rtc" + +- reg: + Usage: required + Value type: <prop-encoded-array> + Definition: single entry specifying the base address of the RTC registers + +- interrupts: + Usage: required + Value type: <prop-encoded-array> + Definition: single entry specifying the RTC's alarm interrupt + +- allow-set-time: + Usage: optional + Value type: <empty> + Definition: indicates that the setting of RTC time is allowed by + the host CPU + += EXAMPLE pmicintc: pmic@0 { compatible = "qcom,pm8921"; @@ -55,9 +88,9 @@ EXAMPLE #address-cells = <1>; #size-cells = <0>; - pwrkey { - compatible = "qcom,pm8921-pwrkey"; - interrupt-parent = <&pmicintc>; - interrupts = <50 1>, <51 1>; + rtc@11d { + compatible = "qcom,pm8921-rtc"; + reg = <0x11d>; + interrupts = <0x27 0>; }; }; diff --git a/Documentation/irqflags-tracing.txt b/Documentation/irqflags-tracing.txt index 67aa71e73035..f6da05670e16 100644 --- a/Documentation/irqflags-tracing.txt +++ b/Documentation/irqflags-tracing.txt @@ -22,13 +22,6 @@ rather straightforward and risk-free manner. Architectures that want to support this need to do a couple of code-organizational changes first: -- move their irq-flags manipulation code from their asm/system.h header - to asm/irqflags.h - -- rename local_irq_disable()/etc to raw_local_irq_disable()/etc. so that - the linux/irqflags.h code can inject callbacks and can construct the - real local_irq_disable()/etc APIs. - - add and enable TRACE_IRQFLAGS_SUPPORT in their arch level Kconfig file and then a couple of functional changes are needed as well to implement diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 2311dad7a57a..50a001a00659 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -878,6 +878,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Enable debug messages at boot time. See Documentation/dynamic-debug-howto.txt for details. + early_ioremap_debug [KNL] + Enable debug messages in early_ioremap support. This + is useful for tracking down temporary early mappings + which are not unmapped. + earlycon= [KNL] Output early console device and options. uart[8250],io,<addr>[,options] uart[8250],mmio,<addr>[,options] diff --git a/Documentation/scheduler/sched-arch.txt b/Documentation/scheduler/sched-arch.txt index 9290de703450..a2f27bbf2cba 100644 --- a/Documentation/scheduler/sched-arch.txt +++ b/Documentation/scheduler/sched-arch.txt @@ -8,7 +8,7 @@ Context switch By default, the switch_to arch function is called with the runqueue locked. This is usually not a problem unless switch_to may need to take the runqueue lock. This is usually due to a wake up operation in -the context switch. See arch/ia64/include/asm/system.h for an example. +the context switch. See arch/ia64/include/asm/switch_to.h for an example. To request the scheduler call switch_to with the runqueue unlocked, you must `#define __ARCH_WANT_UNLOCKED_CTXSW` in a header file diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 75de197a2fef..9596b0ab108d 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -57,7 +57,7 @@ config ARCH_FLATMEM_ENABLE config MMU def_bool y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y config GENERIC_CALIBRATE_DELAY diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9c67903c2790..7f7be1cbc55f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -127,7 +127,7 @@ config HAVE_TCM config HAVE_PROC_CPU bool -config NO_IOPORT +config NO_IOPORT_MAP bool config EISA @@ -412,7 +412,7 @@ config ARCH_EBSA110 select ISA select NEED_MACH_IO_H select NEED_MACH_MEMORY_H - select NO_IOPORT + select NO_IOPORT_MAP help This is an evaluation board for the StrongARM processor available from Digital. It has limited hardware on-board, including an @@ -430,7 +430,7 @@ config ARCH_EFM32 select CPU_V7M select GENERIC_CLOCKEVENTS select NO_DMA - select NO_IOPORT + select NO_IOPORT_MAP select SPARSE_IRQ select USE_OF help @@ -679,7 +679,7 @@ config ARCH_SHMOBILE_LEGACY select HAVE_SMP select MIGHT_HAVE_CACHE_L2X0 select MULTI_IRQ_HANDLER - select NO_IOPORT + select NO_IOPORT_MAP select PINCTRL select PM_GENERIC_DOMAINS if PM select SPARSE_IRQ @@ -701,7 +701,7 @@ config ARCH_RPC select ISA_DMA_API select NEED_MACH_IO_H select NEED_MACH_MEMORY_H - select NO_IOPORT + select NO_IOPORT_MAP select VIRT_TO_BUS help On the Acorn Risc-PC, Linux can support the internal IDE disk and @@ -762,7 +762,7 @@ config ARCH_S3C64XX select HAVE_S3C2410_I2C if I2C select HAVE_S3C2410_WATCHDOG if WATCHDOG select HAVE_TCM - select NO_IOPORT + select NO_IOPORT_MAP select PLAT_SAMSUNG select PM_GENERIC_DOMAINS if PM select S3C_DEV_NAND diff --git a/arch/arm/mach-picoxcell/Kconfig b/arch/arm/mach-picoxcell/Kconfig index eca9eb1c5931..62240f69b4ee 100644 --- a/arch/arm/mach-picoxcell/Kconfig +++ b/arch/arm/mach-picoxcell/Kconfig @@ -4,4 +4,4 @@ config ARCH_PICOXCELL select ARM_VIC select DW_APB_TIMER_OF select HAVE_TCM - select NO_IOPORT + select NO_IOPORT_MAP diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig index 3e8189186a5b..e4e505f52ba0 100644 --- a/arch/arm/mach-prima2/Kconfig +++ b/arch/arm/mach-prima2/Kconfig @@ -3,7 +3,7 @@ config ARCH_SIRF select ARCH_HAS_RESET_CONTROLLER select ARCH_REQUIRE_GPIOLIB select GENERIC_IRQ_CHIP - select NO_IOPORT + select NO_IOPORT_MAP select PINCTRL select PINCTRL_SIRF help diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig index db05be40e937..fbafb9a1975b 100644 --- a/arch/arm/mach-s3c24xx/Kconfig +++ b/arch/arm/mach-s3c24xx/Kconfig @@ -12,7 +12,7 @@ if ARCH_S3C24XX config PLAT_S3C24XX def_bool y select ARCH_REQUIRE_GPIOLIB - select NO_IOPORT + select NO_IOPORT_MAP select S3C_DEV_NAND select IRQ_DOMAIN help diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig index e265630dfff1..c655ec642d6c 100644 --- a/arch/arm/mach-shmobile/Kconfig +++ b/arch/arm/mach-shmobile/Kconfig @@ -10,7 +10,7 @@ config ARCH_SHMOBILE_MULTI select ARM_GIC select MIGHT_HAVE_PCI select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE - select NO_IOPORT + select NO_IOPORT_MAP select PINCTRL select ARCH_REQUIRE_GPIOLIB diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig index 80b4be36f10a..657d52d0391f 100644 --- a/arch/arm/mach-vexpress/Kconfig +++ b/arch/arm/mach-vexpress/Kconfig @@ -10,7 +10,7 @@ config ARCH_VEXPRESS select HAVE_ARM_TWD if SMP select HAVE_PATA_PLATFORM select ICST - select NO_IOPORT + select NO_IOPORT_MAP select PLAT_VERSATILE select PLAT_VERSATILE_CLCD select POWER_RESET diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 91a468225853..97c293e1897d 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -153,7 +153,6 @@ EXPORT_SYMBOL(arm_dma_zone_size); * allocations. This must be the smallest DMA mask in the system, * so a successful GFP_DMA allocation will always satisfy this. */ -phys_addr_t arm_dma_limit; unsigned long arm_dma_pfn_limit; static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, @@ -172,6 +171,8 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, void __init setup_dma_zone(const struct machine_desc *mdesc) { #ifdef CONFIG_ZONE_DMA + phys_addr_t arm_dma_limit; + if (mdesc->dma_zone_size) { arm_dma_zone_size = mdesc->dma_zone_size; arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1; @@ -329,7 +330,8 @@ void __init arm_memblock_init(struct meminfo *mi, * reserve memory for DMA contigouos allocations, * must come from DMA area inside low memory */ - dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit)); + dma_contiguous_reserve(min((phys_addr_t)arm_dma_pfn_limit << PAGE_SHIFT, + arm_lowmem_limit)); arm_memblock_steal_permitted = false; memblock_dump_all(); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 7ea641b7aa7d..64a40d63cad5 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -81,10 +81,8 @@ extern __init void add_static_vm_early(struct static_vm *svm); #endif #ifdef CONFIG_ZONE_DMA -extern phys_addr_t arm_dma_limit; extern unsigned long arm_dma_pfn_limit; #else -#define arm_dma_limit ((phys_addr_t)~0) #define arm_dma_pfn_limit (~0ul >> PAGE_SHIFT) #endif diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig index b57e922f1614..243dfcb2ca0e 100644 --- a/arch/arm/plat-samsung/Kconfig +++ b/arch/arm/plat-samsung/Kconfig @@ -9,7 +9,7 @@ config PLAT_SAMSUNG depends on PLAT_S3C24XX || ARCH_S3C64XX || PLAT_S5P || ARCH_EXYNOS default y select GENERIC_IRQ_CHIP - select NO_IOPORT + select NO_IOPORT_MAP help Base platform code for all Samsung SoC based systems @@ -19,7 +19,7 @@ config PLAT_S5P default y select ARCH_REQUIRE_GPIOLIB select ARM_VIC - select NO_IOPORT + select NO_IOPORT_MAP select PLAT_SAMSUNG select S3C_GPIO_TRACK select S5P_GPIO_DRVSTR diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 2876daeb8c0a..d9f23ad02262 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -17,6 +17,7 @@ config ARM64 select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CPU_AUTOPROBE + select GENERIC_EARLY_IOREMAP select GENERIC_IOMAP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW @@ -66,7 +67,7 @@ config ARCH_PHYS_ADDR_T_64BIT config MMU def_bool y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y config STACKTRACE_SUPPORT diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 4bca4923fc0b..83f71b3004a8 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -10,6 +10,7 @@ generic-y += delay.h generic-y += div64.h generic-y += dma.h generic-y += emergency-restart.h +generic-y += early_ioremap.h generic-y += errno.h generic-y += ftrace.h generic-y += hash.h diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h new file mode 100644 index 000000000000..5f7bfe6df723 --- /dev/null +++ b/arch/arm64/include/asm/fixmap.h @@ -0,0 +1,67 @@ +/* + * fixmap.h: compile-time virtual memory allocation + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1998 Ingo Molnar + * Copyright (C) 2013 Mark Salter <msalter@redhat.com> + * + * Adapted from arch/x86_64 version. + * + */ + +#ifndef _ASM_ARM64_FIXMAP_H +#define _ASM_ARM64_FIXMAP_H + +#ifndef __ASSEMBLY__ +#include <linux/kernel.h> +#include <asm/page.h> + +/* + * Here we define all the compile-time 'special' virtual + * addresses. The point is to have a constant address at + * compile time, but to set the physical address only + * in the boot process. + * + * These 'compile-time allocated' memory buffers are + * page-sized. Use set_fixmap(idx,phys) to associate + * physical memory with fixmap indices. + * + */ +enum fixed_addresses { + FIX_EARLYCON_MEM_BASE, + __end_of_permanent_fixed_addresses, + + /* + * Temporary boot-time mappings, used by early_ioremap(), + * before ioremap() is functional. + */ +#ifdef CONFIG_ARM64_64K_PAGES +#define NR_FIX_BTMAPS 4 +#else +#define NR_FIX_BTMAPS 64 +#endif +#define FIX_BTMAPS_SLOTS 7 +#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) + + FIX_BTMAP_END = __end_of_permanent_fixed_addresses, + FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1, + __end_of_fixed_addresses +}; + +#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) + +#define FIXMAP_PAGE_IO __pgprot(PROT_DEVICE_nGnRE) + +extern void __early_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t flags); + +#define __set_fixmap __early_set_fixmap + +#include <asm-generic/fixmap.h> + +#endif /* !__ASSEMBLY__ */ +#endif /* _ASM_ARM64_FIXMAP_H */ diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 7846a6bb0833..a1bef78f0303 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -27,6 +27,7 @@ #include <asm/byteorder.h> #include <asm/barrier.h> #include <asm/pgtable.h> +#include <asm/early_ioremap.h> #include <xen/xen.h> diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 9dc5dc39fded..e94f9458aa6f 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -49,7 +49,7 @@ #define PAGE_OFFSET (UL(0xffffffffffffffff) << (VA_BITS - 1)) #define MODULES_END (PAGE_OFFSET) #define MODULES_VADDR (MODULES_END - SZ_64M) -#define EARLYCON_IOBASE (MODULES_VADDR - SZ_4M) +#define FIXADDR_TOP (MODULES_VADDR - SZ_2M - PAGE_SIZE) #define TASK_SIZE_64 (UL(1) << VA_BITS) #ifdef CONFIG_COMPAT diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 2494fc01896a..f600d400c07d 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -27,5 +27,6 @@ typedef struct { extern void paging_init(void); extern void setup_mm_for_reboot(void); extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); +extern void init_mem_pgprot(void); #endif diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c index fbb6e1843659..ffbbdde7aba1 100644 --- a/arch/arm64/kernel/early_printk.c +++ b/arch/arm64/kernel/early_printk.c @@ -26,6 +26,8 @@ #include <linux/amba/serial.h> #include <linux/serial_reg.h> +#include <asm/fixmap.h> + static void __iomem *early_base; static void (*printch)(char ch); @@ -141,8 +143,10 @@ static int __init setup_early_printk(char *buf) } /* no options parsing yet */ - if (paddr) - early_base = early_io_map(paddr, EARLYCON_IOBASE); + if (paddr) { + set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr); + early_base = (void __iomem *)fix_to_virt(FIX_EARLYCON_MEM_BASE); + } printch = match->printch; early_console = &early_console_dev; diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 61035d6814cb..1fe5d8d2bdfd 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -404,7 +404,7 @@ ENDPROC(__calc_phys_offset) * - identity mapping to enable the MMU (low address, TTBR0) * - first few MB of the kernel linear mapping to jump to once the MMU has * been enabled, including the FDT blob (TTBR1) - * - UART mapping if CONFIG_EARLY_PRINTK is enabled (TTBR1) + * - pgd entry for fixed mappings (TTBR1) */ __create_page_tables: pgtbl x25, x26, x24 // idmap_pg_dir and swapper_pg_dir addresses @@ -461,15 +461,12 @@ __create_page_tables: sub x6, x6, #1 // inclusive range create_block_map x0, x7, x3, x5, x6 1: -#ifdef CONFIG_EARLY_PRINTK /* - * Create the pgd entry for the UART mapping. The full mapping is done - * later based earlyprintk kernel parameter. + * Create the pgd entry for the fixed mappings. */ - ldr x5, =EARLYCON_IOBASE // UART virtual address + ldr x5, =FIXADDR_TOP // Fixed mapping virtual address add x0, x26, #2 * PAGE_SIZE // section table address create_pgd_entry x26, x0, x5, x6, x7 -#endif ret ENDPROC(__create_page_tables) .ltorg diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 67da30741a1b..720853f70b6b 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -42,6 +42,7 @@ #include <linux/of_fdt.h> #include <linux/of_platform.h> +#include <asm/fixmap.h> #include <asm/cputype.h> #include <asm/elf.h> #include <asm/cputable.h> @@ -360,6 +361,9 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; + init_mem_pgprot(); + early_ioremap_init(); + parse_early_param(); arm64_memblock_init(); diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index 2bb1d586664c..7ec328392ae0 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -25,6 +25,10 @@ #include <linux/vmalloc.h> #include <linux/io.h> +#include <asm/fixmap.h> +#include <asm/tlbflush.h> +#include <asm/pgalloc.h> + static void __iomem *__ioremap_caller(phys_addr_t phys_addr, size_t size, pgprot_t prot, void *caller) { @@ -98,3 +102,84 @@ void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size) __builtin_return_address(0)); } EXPORT_SYMBOL(ioremap_cache); + +#ifndef CONFIG_ARM64_64K_PAGES +static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; +#endif + +static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + + pgd = pgd_offset_k(addr); + BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); + + pud = pud_offset(pgd, addr); + BUG_ON(pud_none(*pud) || pud_bad(*pud)); + + return pmd_offset(pud, addr); +} + +static inline pte_t * __init early_ioremap_pte(unsigned long addr) +{ + pmd_t *pmd = early_ioremap_pmd(addr); + + BUG_ON(pmd_none(*pmd) || pmd_bad(*pmd)); + + return pte_offset_kernel(pmd, addr); +} + +void __init early_ioremap_init(void) +{ + pmd_t *pmd; + + pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); +#ifndef CONFIG_ARM64_64K_PAGES + /* need to populate pmd for 4k pagesize only */ + pmd_populate_kernel(&init_mm, pmd, bm_pte); +#endif + /* + * The boot-ioremap range spans multiple pmds, for which + * we are not prepared: + */ + BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) + != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); + + if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) { + WARN_ON(1); + pr_warn("pmd %p != %p\n", + pmd, early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))); + pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n", + fix_to_virt(FIX_BTMAP_BEGIN)); + pr_warn("fix_to_virt(FIX_BTMAP_END): %08lx\n", + fix_to_virt(FIX_BTMAP_END)); + + pr_warn("FIX_BTMAP_END: %d\n", FIX_BTMAP_END); + pr_warn("FIX_BTMAP_BEGIN: %d\n", + FIX_BTMAP_BEGIN); + } + + early_ioremap_setup(); +} + +void __init __early_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t flags) +{ + unsigned long addr = __fix_to_virt(idx); + pte_t *pte; + + if (idx >= __end_of_fixed_addresses) { + BUG(); + return; + } + + pte = early_ioremap_pte(addr); + + if (pgprot_val(flags)) + set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); + else { + pte_clear(&init_mm, addr, pte); + flush_tlb_kernel_range(addr, addr+PAGE_SIZE); + } +} diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index f8dc7e8fce6f..6b7e89569a3a 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -125,7 +125,7 @@ early_param("cachepolicy", early_cachepolicy); /* * Adjust the PMD section entries according to the CPU in use. */ -static void __init init_mem_pgprot(void) +void __init init_mem_pgprot(void) { pteval_t default_pgprot; int i; @@ -260,47 +260,6 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt, } while (pgd++, addr = next, addr != end); } -#ifdef CONFIG_EARLY_PRINTK -/* - * Create an early I/O mapping using the pgd/pmd entries already populated - * in head.S as this function is called too early to allocated any memory. The - * mapping size is 2MB with 4KB pages or 64KB or 64KB pages. - */ -void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt) -{ - unsigned long size, mask; - bool page64k = IS_ENABLED(CONFIG_ARM64_64K_PAGES); - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - /* - * No early pte entries with !ARM64_64K_PAGES configuration, so using - * sections (pmd). - */ - size = page64k ? PAGE_SIZE : SECTION_SIZE; - mask = ~(size - 1); - - pgd = pgd_offset_k(virt); - pud = pud_offset(pgd, virt); - if (pud_none(*pud)) - return NULL; - pmd = pmd_offset(pud, virt); - - if (page64k) { - if (pmd_none(*pmd)) - return NULL; - pte = pte_offset_kernel(pmd, virt); - set_pte(pte, __pte((phys & mask) | PROT_DEVICE_nGnRE)); - } else { - set_pmd(pmd, __pmd((phys & mask) | PROT_SECT_DEVICE_nGnRE)); - } - - return (void __iomem *)((virt & mask) + (phys & ~mask)); -} -#endif - static void __init map_mem(void) { struct memblock_region *reg; @@ -357,7 +316,6 @@ void __init paging_init(void) { void *zero_page; - init_mem_pgprot(); map_mem(); /* diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index 7cb90a54b598..52731e221851 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -29,7 +29,7 @@ config GENERIC_CALIBRATE_DELAY bool default y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y config FORCE_MAX_ZONEORDER diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index fbc5c78c9ac7..0fd6138f6203 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -19,7 +19,7 @@ config HEXAGON select GENERIC_IRQ_SHOW select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK - select NO_IOPORT + select NO_IOPORT_MAP select GENERIC_IOMAP select GENERIC_SMP_IDLE_THREAD select STACKTRACE_SUPPORT diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index ca4504424dae..9e44bbd8051e 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -28,7 +28,7 @@ config ZONE_DMA bool default y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y config NO_DMA diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index b2e322939256..87b7c7581b1d 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -52,7 +52,7 @@ config TIME_LOW_RES bool default y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y config NO_DMA diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig index b1d3c9c0eff8..499b7610eaaf 100644 --- a/arch/metag/Kconfig +++ b/arch/metag/Kconfig @@ -52,7 +52,7 @@ config GENERIC_HWEIGHT config GENERIC_CALIBRATE_DELAY def_bool y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y source "init/Kconfig" diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 16d5ab1615b1..5cd695f905a1 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -175,7 +175,7 @@ config MACH_DECSTATION select CPU_R4000_WORKAROUNDS if 64BIT select CPU_R4400_WORKAROUNDS if 64BIT select DMA_NONCOHERENT - select NO_IOPORT + select NO_IOPORT_MAP select IRQ_CPU select SYS_HAS_CPU_R3000 select SYS_HAS_CPU_R4X00 @@ -947,7 +947,7 @@ config SYNC_R4K config MIPS_MACHINE def_bool n -config NO_IOPORT +config NO_IOPORT_MAP def_bool n config GENERIC_ISA_DMA diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index 9488209a5253..e71d712afb79 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -41,7 +41,7 @@ config RWSEM_XCHGADD_ALGORITHM config GENERIC_HWEIGHT def_bool y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y config TRACE_IRQFLAGS_SUPPORT diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 68b186ab8fd1..d68fe34799b0 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -52,7 +52,7 @@ config KEXEC config AUDIT_ARCH def_bool y -config NO_IOPORT +config NO_IOPORT_MAP def_bool y config PCI_QUIRKS diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index ec1eb2630215..834b67c4db5a 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -3,7 +3,7 @@ config SUPERH select ARCH_MIGHT_HAVE_PC_PARPORT select EXPERT select CLKDEV_LOOKUP - select HAVE_IDE if HAS_IOPORT + select HAVE_IDE if HAS_IOPORT_MAP select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select ARCH_DISCARD_MEMBLOCK @@ -139,7 +139,7 @@ config ARCH_HAS_ILOG2_U32 config ARCH_HAS_ILOG2_U64 def_bool n -config NO_IOPORT +config NO_IOPORT_MAP def_bool !PCI depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN && \ !SH_HP6XX && !SH_SOLUTION_ENGINE diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index eb1cf84231a2..e331e5373b8e 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -158,7 +158,7 @@ config SH_SDK7786 bool "SDK7786" depends on CPU_SUBTYPE_SH7786 select SYS_SUPPORTS_PCI - select NO_IOPORT if !PCI + select NO_IOPORT_MAP if !PCI select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_SRAM_POOL select REGULATOR_FIXED_VOLTAGE if REGULATOR @@ -204,7 +204,7 @@ config SH_URQUELL depends on CPU_SUBTYPE_SH7786 select ARCH_REQUIRE_GPIOLIB select SYS_SUPPORTS_PCI - select NO_IOPORT if !PCI + select NO_IOPORT_MAP if !PCI config SH_MIGOR bool "Migo-R" @@ -306,7 +306,7 @@ config SH_LBOX_RE2 config SH_X3PROTO bool "SH-X3 Prototype board" depends on CPU_SUBTYPE_SHX3 - select NO_IOPORT if !PCI + select NO_IOPORT_MAP if !PCI select IRQ_DOMAIN config SH_MAGIC_PANEL_R2 @@ -333,7 +333,7 @@ config SH_POLARIS config SH_SH2007 bool "SH-2007 board" - select NO_IOPORT + select NO_IOPORT_MAP select REGULATOR_FIXED_VOLTAGE if REGULATOR depends on CPU_SUBTYPE_SH7780 help diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index 629db2ad7916..728c4c571f40 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -122,7 +122,7 @@ __BUILD_MEMORY_STRING(__raw_, l, u32) __BUILD_MEMORY_STRING(__raw_, q, u64) -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP /* * Slowdown I/O port space accesses for antique hardware. @@ -218,7 +218,7 @@ __BUILD_IOPORT_STRING(w, u16) __BUILD_IOPORT_STRING(l, u32) __BUILD_IOPORT_STRING(q, u64) -#else /* !CONFIG_HAS_IOPORT */ +#else /* !CONFIG_HAS_IOPORT_MAP */ #include <asm/io_noioport.h> diff --git a/arch/sh/include/asm/io_trapped.h b/arch/sh/include/asm/io_trapped.h index f1251d4f0ba9..4ab94ef51071 100644 --- a/arch/sh/include/asm/io_trapped.h +++ b/arch/sh/include/asm/io_trapped.h @@ -36,7 +36,7 @@ __ioremap_trapped(unsigned long offset, unsigned long size) #define __ioremap_trapped(offset, size) NULL #endif -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP extern struct list_head trapped_io; static inline void __iomem * diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h index eb9c20d971dd..d3324e4f372e 100644 --- a/arch/sh/include/asm/machvec.h +++ b/arch/sh/include/asm/machvec.h @@ -21,7 +21,7 @@ struct sh_machine_vector { int (*mv_irq_demux)(int irq); void (*mv_init_irq)(void); -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP void __iomem *(*mv_ioport_map)(unsigned long port, unsigned int size); void (*mv_ioport_unmap)(void __iomem *); #endif diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile index 261c8bfd75ce..2ccf36c824c6 100644 --- a/arch/sh/kernel/Makefile +++ b/arch/sh/kernel/Makefile @@ -22,7 +22,7 @@ obj-y := debugtraps.o dma-nommu.o dumpstack.o \ ifndef CONFIG_GENERIC_IOMAP obj-y += iomap.o -obj-$(CONFIG_HAS_IOPORT) += ioport.o +obj-$(CONFIG_HAS_IOPORT_MAP) += ioport.o endif obj-$(CONFIG_SUPERH32) += sys_sh32.o diff --git a/arch/sh/kernel/io_trapped.c b/arch/sh/kernel/io_trapped.c index c0a9761f2f8a..f8ce36286cea 100644 --- a/arch/sh/kernel/io_trapped.c +++ b/arch/sh/kernel/io_trapped.c @@ -22,7 +22,7 @@ #define TRAPPED_PAGES_MAX 16 -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP LIST_HEAD(trapped_io); EXPORT_SYMBOL_GPL(trapped_io); #endif @@ -90,7 +90,7 @@ int register_trapped_io(struct trapped_io *tiop) tiop->magic = IO_TRAPPED_MAGIC; INIT_LIST_HEAD(&tiop->list); spin_lock_irq(&trapped_lock); -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP if (flags & IORESOURCE_IO) list_add(&tiop->list, &trapped_io); #endif diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 31c8c6223995..85258ca43ff5 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -411,7 +411,7 @@ config PCI_DOMAINS config NO_IOMEM def_bool !PCI -config NO_IOPORT +config NO_IOPORT_MAP def_bool !PCI config TILE_PCI_IO diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index eecc4142764c..f17bca8ed2ce 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -359,7 +359,7 @@ int singlestepping(void * t) /* * Only x86 and x86_64 have an arch_align_stack(). * All other arches have "#define arch_align_stack(x) (x)" - * in their asm/system.h + * in their asm/exec.h * As this is included in UML from asm-um/system-generic.h, * we can use it to behave as the subarch does. */ diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 25c0dba508cc..aafad6fa1667 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -27,7 +27,7 @@ config UNICORE32 config GENERIC_CSUM def_bool y -config NO_IOPORT +config NO_IOPORT_MAP bool config STACKTRACE_SUPPORT diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0a9f4363b7fd..9c0a657de3ae 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -43,6 +43,7 @@ config X86 select HAVE_DMA_ATTRS select HAVE_DMA_CONTIGUOUS if !SWIOTLB select HAVE_KRETPROBES + select GENERIC_EARLY_IOREMAP select HAVE_OPTPROBES select HAVE_KPROBES_ON_FTRACE select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 4acddc43ee0c..3ca9762e1649 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -5,5 +5,6 @@ genhdr-y += unistd_64.h genhdr-y += unistd_x32.h generic-y += clkdev.h +generic-y += early_ioremap.h generic-y += cputime.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 8dcd35c4c787..43f482a0db37 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -163,5 +163,11 @@ static inline void __set_fixmap(enum fixed_addresses idx, #include <asm-generic/fixmap.h> +#define __late_set_fixmap(idx, phys, flags) __set_fixmap(idx, phys, flags) +#define __late_clear_fixmap(idx) __set_fixmap(idx, 0, __pgprot(0)) + +void __early_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t flags); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 91d9c69a629e..b8237d8a1e0c 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -39,6 +39,7 @@ #include <linux/string.h> #include <linux/compiler.h> #include <asm/page.h> +#include <asm/early_ioremap.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ @@ -316,19 +317,6 @@ extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, unsigned long prot_val); extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); -/* - * early_ioremap() and early_iounmap() are for temporary early boot-time - * mappings, before the real ioremap() is functional. - * A boot-time mapping is currently limited to at most 16 pages. - */ -extern void early_ioremap_init(void); -extern void early_ioremap_reset(void); -extern void __iomem *early_ioremap(resource_size_t phys_addr, - unsigned long size); -extern void __iomem *early_memremap(resource_size_t phys_addr, - unsigned long size); -extern void early_iounmap(void __iomem *addr, unsigned long size); -extern void fixup_early_ioremap(void); extern bool is_early_ioremap_ptep(pte_t *ptep); #ifdef CONFIG_XEN diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 94220d14d5cc..851bcdc5db04 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -52,7 +52,7 @@ * Compared to the generic __my_cpu_offset version, the following * saves one instruction and avoids clobbering a temp register. */ -#define __this_cpu_ptr(ptr) \ +#define raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ __verify_pcpu_ptr(ptr); \ @@ -362,25 +362,25 @@ do { \ */ #define this_cpu_read_stable(var) percpu_from_op("mov", var, "p" (&(var))) -#define __this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) -#define __this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) -#define __this_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) - -#define __this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val) -#define __this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val) -#define __this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val) -#define __this_cpu_add_1(pcp, val) percpu_add_op((pcp), val) -#define __this_cpu_add_2(pcp, val) percpu_add_op((pcp), val) -#define __this_cpu_add_4(pcp, val) percpu_add_op((pcp), val) -#define __this_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val) -#define __this_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val) -#define __this_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val) -#define __this_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) -#define __this_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) -#define __this_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) -#define __this_cpu_xchg_1(pcp, val) percpu_xchg_op(pcp, val) -#define __this_cpu_xchg_2(pcp, val) percpu_xchg_op(pcp, val) -#define __this_cpu_xchg_4(pcp, val) percpu_xchg_op(pcp, val) +#define raw_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define raw_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define raw_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) + +#define raw_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val) +#define raw_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val) +#define raw_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val) +#define raw_cpu_add_1(pcp, val) percpu_add_op((pcp), val) +#define raw_cpu_add_2(pcp, val) percpu_add_op((pcp), val) +#define raw_cpu_add_4(pcp, val) percpu_add_op((pcp), val) +#define raw_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val) +#define raw_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val) +#define raw_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val) +#define raw_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) +#define raw_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) +#define raw_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) +#define raw_cpu_xchg_1(pcp, val) percpu_xchg_op(pcp, val) +#define raw_cpu_xchg_2(pcp, val) percpu_xchg_op(pcp, val) +#define raw_cpu_xchg_4(pcp, val) percpu_xchg_op(pcp, val) #define this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) #define this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) @@ -401,16 +401,16 @@ do { \ #define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(pcp, nval) #define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(pcp, nval) -#define __this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val) -#define __this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val) -#define __this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val) -#define __this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) -#define __this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) -#define __this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) +#define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val) +#define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val) +#define raw_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val) +#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) +#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) +#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) -#define this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val) -#define this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val) -#define this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val) +#define this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val) +#define this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val) +#define this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val) #define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) #define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) #define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) @@ -427,7 +427,7 @@ do { \ __ret; \ }) -#define __this_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double +#define raw_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double #define this_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double #endif /* CONFIG_X86_CMPXCHG64 */ @@ -436,22 +436,22 @@ do { \ * 32 bit must fall back to generic operations. */ #ifdef CONFIG_X86_64 -#define __this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) -#define __this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) -#define __this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) -#define __this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) -#define __this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) -#define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) -#define __this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) -#define __this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) - -#define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) -#define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) -#define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) -#define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) -#define this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) -#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) -#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) +#define raw_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define raw_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) +#define raw_cpu_add_8(pcp, val) percpu_add_op((pcp), val) +#define raw_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) +#define raw_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) +#define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) +#define raw_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) +#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) + +#define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) +#define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) +#define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) +#define this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) +#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) +#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) #define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) /* @@ -474,7 +474,7 @@ do { \ __ret; \ }) -#define __this_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double +#define raw_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double #define this_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double #endif @@ -495,9 +495,9 @@ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr, unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG; #ifdef CONFIG_X86_64 - return ((1UL << (nr % BITS_PER_LONG)) & __this_cpu_read_8(*a)) != 0; + return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_8(*a)) != 0; #else - return ((1UL << (nr % BITS_PER_LONG)) & __this_cpu_read_4(*a)) != 0; + return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_4(*a)) != 0; #endif } diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index c8b051933b1b..7024c12f7bfe 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -19,12 +19,12 @@ DECLARE_PER_CPU(int, __preempt_count); */ static __always_inline int preempt_count(void) { - return __this_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; + return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; } static __always_inline void preempt_count_set(int pc) { - __this_cpu_write_4(__preempt_count, pc); + raw_cpu_write_4(__preempt_count, pc); } /* @@ -53,17 +53,17 @@ static __always_inline void preempt_count_set(int pc) static __always_inline void set_preempt_need_resched(void) { - __this_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); + raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); } static __always_inline void clear_preempt_need_resched(void) { - __this_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); + raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); } static __always_inline bool test_preempt_need_resched(void) { - return !(__this_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); + return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); } /* @@ -72,12 +72,12 @@ static __always_inline bool test_preempt_need_resched(void) static __always_inline void __preempt_count_add(int val) { - __this_cpu_add_4(__preempt_count, val); + raw_cpu_add_4(__preempt_count, val); } static __always_inline void __preempt_count_sub(int val) { - __this_cpu_add_4(__preempt_count, -val); + raw_cpu_add_4(__preempt_count, -val); } /* @@ -95,7 +95,7 @@ static __always_inline bool __preempt_count_dec_and_test(void) */ static __always_inline bool should_resched(void) { - return unlikely(!__this_cpu_read_4(__preempt_count)); + return unlikely(!raw_cpu_read_4(__preempt_count)); } #ifdef CONFIG_PREEMPT diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 799580cabc78..597ac155c91c 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -328,17 +328,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr) return; } -static int __initdata early_ioremap_debug; - -static int __init early_ioremap_debug_setup(char *str) -{ - early_ioremap_debug = 1; - - return 0; -} -early_param("early_ioremap_debug", early_ioremap_debug_setup); - -static __initdata int after_paging_init; static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) @@ -362,18 +351,11 @@ bool __init is_early_ioremap_ptep(pte_t *ptep) return ptep >= &bm_pte[0] && ptep < &bm_pte[PAGE_SIZE/sizeof(pte_t)]; } -static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata; - void __init early_ioremap_init(void) { pmd_t *pmd; - int i; - if (early_ioremap_debug) - printk(KERN_INFO "early_ioremap_init()\n"); - - for (i = 0; i < FIX_BTMAPS_SLOTS; i++) - slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i); + early_ioremap_setup(); pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); memset(bm_pte, 0, sizeof(bm_pte)); @@ -402,13 +384,8 @@ void __init early_ioremap_init(void) } } -void __init early_ioremap_reset(void) -{ - after_paging_init = 1; -} - -static void __init __early_set_fixmap(enum fixed_addresses idx, - phys_addr_t phys, pgprot_t flags) +void __init __early_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *pte; @@ -425,198 +402,3 @@ static void __init __early_set_fixmap(enum fixed_addresses idx, pte_clear(&init_mm, addr, pte); __flush_tlb_one(addr); } - -static inline void __init early_set_fixmap(enum fixed_addresses idx, - phys_addr_t phys, pgprot_t prot) -{ - if (after_paging_init) - __set_fixmap(idx, phys, prot); - else - __early_set_fixmap(idx, phys, prot); -} - -static inline void __init early_clear_fixmap(enum fixed_addresses idx) -{ - if (after_paging_init) - clear_fixmap(idx); - else - __early_set_fixmap(idx, 0, __pgprot(0)); -} - -static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata; -static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; - -void __init fixup_early_ioremap(void) -{ - int i; - - for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { - if (prev_map[i]) { - WARN_ON(1); - break; - } - } - - early_ioremap_init(); -} - -static int __init check_early_ioremap_leak(void) -{ - int count = 0; - int i; - - for (i = 0; i < FIX_BTMAPS_SLOTS; i++) - if (prev_map[i]) - count++; - - if (!count) - return 0; - WARN(1, KERN_WARNING - "Debug warning: early ioremap leak of %d areas detected.\n", - count); - printk(KERN_WARNING - "please boot with early_ioremap_debug and report the dmesg.\n"); - - return 1; -} -late_initcall(check_early_ioremap_leak); - -static void __init __iomem * -__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) -{ - unsigned long offset; - resource_size_t last_addr; - unsigned int nrpages; - enum fixed_addresses idx; - int i, slot; - - WARN_ON(system_state != SYSTEM_BOOTING); - - slot = -1; - for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { - if (!prev_map[i]) { - slot = i; - break; - } - } - - if (slot < 0) { - printk(KERN_INFO "%s(%08llx, %08lx) not found slot\n", - __func__, (u64)phys_addr, size); - WARN_ON(1); - return NULL; - } - - if (early_ioremap_debug) { - printk(KERN_INFO "%s(%08llx, %08lx) [%d] => ", - __func__, (u64)phys_addr, size, slot); - dump_stack(); - } - - /* Don't allow wraparound or zero size */ - last_addr = phys_addr + size - 1; - if (!size || last_addr < phys_addr) { - WARN_ON(1); - return NULL; - } - - prev_size[slot] = size; - /* - * Mappings have to be page-aligned - */ - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - size = PAGE_ALIGN(last_addr + 1) - phys_addr; - - /* - * Mappings have to fit in the FIX_BTMAP area. - */ - nrpages = size >> PAGE_SHIFT; - if (nrpages > NR_FIX_BTMAPS) { - WARN_ON(1); - return NULL; - } - - /* - * Ok, go for it.. - */ - idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; - while (nrpages > 0) { - early_set_fixmap(idx, phys_addr, prot); - phys_addr += PAGE_SIZE; - --idx; - --nrpages; - } - if (early_ioremap_debug) - printk(KERN_CONT "%08lx + %08lx\n", offset, slot_virt[slot]); - - prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]); - return prev_map[slot]; -} - -/* Remap an IO device */ -void __init __iomem * -early_ioremap(resource_size_t phys_addr, unsigned long size) -{ - return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO); -} - -/* Remap memory */ -void __init __iomem * -early_memremap(resource_size_t phys_addr, unsigned long size) -{ - return __early_ioremap(phys_addr, size, PAGE_KERNEL); -} - -void __init early_iounmap(void __iomem *addr, unsigned long size) -{ - unsigned long virt_addr; - unsigned long offset; - unsigned int nrpages; - enum fixed_addresses idx; - int i, slot; - - slot = -1; - for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { - if (prev_map[i] == addr) { - slot = i; - break; - } - } - - if (slot < 0) { - printk(KERN_INFO "early_iounmap(%p, %08lx) not found slot\n", - addr, size); - WARN_ON(1); - return; - } - - if (prev_size[slot] != size) { - printk(KERN_INFO "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n", - addr, size, slot, prev_size[slot]); - WARN_ON(1); - return; - } - - if (early_ioremap_debug) { - printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr, - size, slot); - dump_stack(); - } - - virt_addr = (unsigned long)addr; - if (virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)) { - WARN_ON(1); - return; - } - offset = virt_addr & ~PAGE_MASK; - nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT; - - idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; - while (nrpages > 0) { - early_clear_fixmap(idx); - --idx; - --nrpages; - } - prev_map[slot] = NULL; -} diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index a69bcb8c7621..4dd8cf652579 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -127,7 +127,7 @@ static int __init parse_reservetop(char *arg) address = memparse(arg, &arg); reserve_top_address(address); - fixup_early_ioremap(); + early_ioremap_init(); return 0; } early_param("reservetop", parse_reservetop); diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index c87ae7c6e5f9..02d6d29a63c1 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -41,7 +41,7 @@ config ARCH_HAS_ILOG2_U32 config ARCH_HAS_ILOG2_U64 def_bool n -config NO_IOPORT +config NO_IOPORT_MAP def_bool n config HZ @@ -239,7 +239,7 @@ config XTENSA_PLATFORM_XT2000 config XTENSA_PLATFORM_S6105 bool "S6105" select SERIAL_CONSOLE - select NO_IOPORT + select NO_IOPORT_MAP config XTENSA_PLATFORM_XTFPGA bool "XTFPGA" diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig index 4f233204faf9..d57d917ff240 100644 --- a/arch/xtensa/configs/iss_defconfig +++ b/arch/xtensa/configs/iss_defconfig @@ -11,7 +11,7 @@ CONFIG_GENERIC_FIND_NEXT_BIT=y CONFIG_GENERIC_HWEIGHT=y # CONFIG_ARCH_HAS_ILOG2_U32 is not set # CONFIG_ARCH_HAS_ILOG2_U64 is not set -CONFIG_NO_IOPORT=y +CONFIG_NO_IOPORT_MAP=y CONFIG_HZ=100 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" CONFIG_CONSTRUCTORS=y diff --git a/arch/xtensa/configs/s6105_defconfig b/arch/xtensa/configs/s6105_defconfig index d929f77a0360..583c2b0974ca 100644 --- a/arch/xtensa/configs/s6105_defconfig +++ b/arch/xtensa/configs/s6105_defconfig @@ -11,7 +11,7 @@ CONFIG_GENERIC_FIND_NEXT_BIT=y CONFIG_GENERIC_HWEIGHT=y # CONFIG_ARCH_HAS_ILOG2_U32 is not set # CONFIG_ARCH_HAS_ILOG2_U64 is not set -CONFIG_NO_IOPORT=y +CONFIG_NO_IOPORT_MAP=y CONFIG_HZ=100 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig index 1a65838888cd..c54cac3f8bc8 100644 --- a/drivers/char/tpm/Kconfig +++ b/drivers/char/tpm/Kconfig @@ -74,7 +74,7 @@ config TCG_NSC config TCG_ATMEL tristate "Atmel TPM Interface" - depends on PPC64 || HAS_IOPORT + depends on PPC64 || HAS_IOPORT_MAP ---help--- If you have a TPM security chip from Atmel say Yes and it will be accessible from within Linux. To compile this driver diff --git a/drivers/gpio/gpio-zevio.c b/drivers/gpio/gpio-zevio.c index 9bf5034b6cdb..ed66cc616ec5 100644 --- a/drivers/gpio/gpio-zevio.c +++ b/drivers/gpio/gpio-zevio.c @@ -18,6 +18,10 @@ #include <linux/slab.h> #include <linux/gpio.h> +#ifndef IOMEM +#define IOMEM(x) ((void __force __iomem *)(x)) +#endif + /* * Memory layout: * This chip has four gpio sections, each controls 8 GPIOs. diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 10a69f1f642c..3577cfa16f74 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -937,7 +937,7 @@ config I2C_ACORN config I2C_ELEKTOR tristate "Elektor ISA card" - depends on ISA && HAS_IOPORT && BROKEN_ON_SMP + depends on ISA && HAS_IOPORT_MAP && BROKEN_ON_SMP select I2C_ALGOPCF help This supports the PCF8584 ISA bus I2C adapter. Say Y if you own diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig index 4b18b8765523..1e65cb6c2591 100644 --- a/drivers/net/can/sja1000/Kconfig +++ b/drivers/net/can/sja1000/Kconfig @@ -39,7 +39,7 @@ config CAN_EMS_PCI config CAN_PEAK_PCMCIA tristate "PEAK PCAN-PC Card" depends on PCMCIA - depends on HAS_IOPORT + depends on HAS_IOPORT_MAP ---help--- This driver is for the PCAN-PC Card PCMCIA adapter (1 or 2 channels) from PEAK-System (http://www.peak-system.com). To compile this diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig index 65b735d4a6ad..afaab4b2333f 100644 --- a/drivers/net/ethernet/3com/Kconfig +++ b/drivers/net/ethernet/3com/Kconfig @@ -66,7 +66,7 @@ config PCMCIA_3C589 config VORTEX tristate "3c590/3c900 series (592/595/597) \"Vortex/Boomerang\" support" - depends on (PCI || EISA) && HAS_IOPORT + depends on (PCI || EISA) && HAS_IOPORT_MAP select MII ---help--- This option enables driver support for a large number of 10Mbps and diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c index 9b084db739c7..3aaa15f6b7e9 100644 --- a/drivers/w1/w1_int.c +++ b/drivers/w1/w1_int.c @@ -92,9 +92,8 @@ static struct w1_master * w1_alloc_dev(u32 id, int slave_count, int slave_ttl, err = device_register(&dev->dev); if (err) { printk(KERN_ERR "Failed to register master device. err=%d\n", err); - memset(dev, 0, sizeof(struct w1_master)); - kfree(dev); - dev = NULL; + put_device(&dev->dev); + return NULL; } return dev; diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index a7ea492ae660..dd5d176c9c2f 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -38,7 +38,6 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) { struct super_block * sb; struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; struct ufs_cg_private_info * ucpi; struct ufs_cylinder_group * ucg; unsigned cgno, bit, end_bit, bbase, blkmap, i; @@ -46,7 +45,6 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(uspi); UFSD("ENTER, fragment %llu, count %u\n", (unsigned long long)fragment, count); @@ -54,7 +52,7 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) if (ufs_fragnum(fragment) + count > uspi->s_fpg) ufs_error (sb, "ufs_free_fragments", "internal error"); - mutex_lock(&UFS_SB(sb)->s_lock); + lock_ufs(sb); cgno = ufs_dtog(uspi, fragment); bit = ufs_dtogd(uspi, fragment); @@ -118,12 +116,12 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); UFSD("EXIT\n"); return; failed: - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); UFSD("EXIT (FAILED)\n"); return; } @@ -135,7 +133,6 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count) { struct super_block * sb; struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; struct ufs_cg_private_info * ucpi; struct ufs_cylinder_group * ucg; unsigned overflow, cgno, bit, end_bit, i; @@ -143,7 +140,6 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count) sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(uspi); UFSD("ENTER, fragment %llu, count %u\n", (unsigned long long)fragment, count); @@ -155,7 +151,7 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count) goto failed; } - mutex_lock(&UFS_SB(sb)->s_lock); + lock_ufs(sb); do_more: overflow = 0; @@ -215,12 +211,12 @@ do_more: } ufs_mark_sb_dirty(sb); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); UFSD("EXIT\n"); return; failed_unlock: - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); failed: UFSD("EXIT (FAILED)\n"); return; @@ -361,7 +357,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, usb1 = ubh_get_usb_first(uspi); *err = -ENOSPC; - mutex_lock(&UFS_SB(sb)->s_lock); + lock_ufs(sb); tmp = ufs_data_ptr_to_cpu(sb, p); if (count + ufs_fragnum(fragment) > uspi->s_fpb) { @@ -382,19 +378,19 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, "fragment %llu, tmp %llu\n", (unsigned long long)fragment, (unsigned long long)tmp); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); return INVBLOCK; } if (fragment < UFS_I(inode)->i_lastfrag) { UFSD("EXIT (ALREADY ALLOCATED)\n"); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); return 0; } } else { if (tmp) { UFSD("EXIT (ALREADY ALLOCATED)\n"); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); return 0; } } @@ -403,7 +399,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, * There is not enough space for user on the device */ if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) { - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); UFSD("EXIT (FAILED)\n"); return 0; } @@ -428,7 +424,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, ufs_clear_frags(inode, result + oldcount, newcount - oldcount, locked_page != NULL); } - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); UFSD("EXIT, result %llu\n", (unsigned long long)result); return result; } @@ -443,7 +439,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, fragment + count); ufs_clear_frags(inode, result + oldcount, newcount - oldcount, locked_page != NULL); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); UFSD("EXIT, result %llu\n", (unsigned long long)result); return result; } @@ -481,7 +477,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, *err = 0; UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag, fragment + count); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); if (newcount < request) ufs_free_fragments (inode, result + newcount, request - newcount); ufs_free_fragments (inode, tmp, oldcount); @@ -489,7 +485,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, return result; } - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); UFSD("EXIT (FAILED)\n"); return 0; } @@ -499,7 +495,6 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment, { struct super_block * sb; struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; struct ufs_cg_private_info * ucpi; struct ufs_cylinder_group * ucg; unsigned cgno, fragno, fragoff, count, fragsize, i; @@ -509,7 +504,6 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment, sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first (uspi); count = newcount - oldcount; cgno = ufs_dtog(uspi, fragment); @@ -577,7 +571,6 @@ static u64 ufs_alloc_fragments(struct inode *inode, unsigned cgno, { struct super_block * sb; struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; struct ufs_cg_private_info * ucpi; struct ufs_cylinder_group * ucg; unsigned oldcg, i, j, k, allocsize; @@ -588,7 +581,6 @@ static u64 ufs_alloc_fragments(struct inode *inode, unsigned cgno, sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(uspi); oldcg = cgno; /* @@ -690,7 +682,6 @@ static u64 ufs_alloccg_block(struct inode *inode, { struct super_block * sb; struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; struct ufs_cylinder_group * ucg; u64 result, blkno; @@ -698,7 +689,6 @@ static u64 ufs_alloccg_block(struct inode *inode, sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(uspi); ucg = ubh_get_ucg(UCPI_UBH(ucpi)); if (goal == 0) { @@ -794,7 +784,6 @@ static u64 ufs_bitmap_search(struct super_block *sb, 0x0, 0x2, 0x6, 0xe, 0x1e, 0x3e, 0x7e, 0xfe, 0x1fe }; struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; - struct ufs_super_block_first *usb1; struct ufs_cylinder_group *ucg; unsigned start, length, loc; unsigned pos, want, blockmap, mask, end; @@ -803,7 +792,6 @@ static u64 ufs_bitmap_search(struct super_block *sb, UFSD("ENTER, cg %u, goal %llu, count %u\n", ucpi->c_cgx, (unsigned long long)goal, count); - usb1 = ubh_get_usb_first (uspi); ucg = ubh_get_ucg(UCPI_UBH(ucpi)); if (goal) diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index d0426d74817b..a9cc75ffa925 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -57,7 +57,6 @@ void ufs_free_inode (struct inode * inode) { struct super_block * sb; struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; struct ufs_cg_private_info * ucpi; struct ufs_cylinder_group * ucg; int is_directory; @@ -67,15 +66,14 @@ void ufs_free_inode (struct inode * inode) sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(uspi); ino = inode->i_ino; - mutex_lock(&UFS_SB(sb)->s_lock); + lock_ufs(sb); if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) { ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); return; } @@ -83,7 +81,7 @@ void ufs_free_inode (struct inode * inode) bit = ufs_inotocgoff (ino); ucpi = ufs_load_cylinder (sb, cg); if (!ucpi) { - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); return; } ucg = ubh_get_ucg(UCPI_UBH(ucpi)); @@ -117,7 +115,7 @@ void ufs_free_inode (struct inode * inode) ubh_sync_block(UCPI_UBH(ucpi)); ufs_mark_sb_dirty(sb); - mutex_unlock(&UFS_SB(sb)->s_lock); + unlock_ufs(sb); UFSD("EXIT\n"); } @@ -175,7 +173,6 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode) struct super_block * sb; struct ufs_sb_info * sbi; struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; struct ufs_cg_private_info * ucpi; struct ufs_cylinder_group * ucg; struct inode * inode; @@ -195,9 +192,8 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode) ufsi = UFS_I(inode); sbi = UFS_SB(sb); uspi = sbi->s_uspi; - usb1 = ubh_get_usb_first(uspi); - mutex_lock(&sbi->s_lock); + lock_ufs(sb); /* * Try to place the inode in its parent directory @@ -332,21 +328,20 @@ cg_found: sync_dirty_buffer(bh); brelse(bh); } - - mutex_unlock(&sbi->s_lock); + unlock_ufs(sb); UFSD("allocating inode %lu\n", inode->i_ino); UFSD("EXIT\n"); return inode; fail_remove_inode: - mutex_unlock(&sbi->s_lock); + unlock_ufs(sb); clear_nlink(inode); iput(inode); UFSD("EXIT (FAILED): err %d\n", err); return ERR_PTR(err); failed: - mutex_unlock(&sbi->s_lock); + unlock_ufs(sb); make_bad_inode(inode); iput (inode); UFSD("EXIT (FAILED): err %d\n", err); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index b8c6791f046f..d05cf89accfb 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -524,11 +524,9 @@ static int ufs_read_cylinder_structures(struct super_block *sb) struct ufs_buffer_head * ubh; unsigned char * base, * space; unsigned size, blks, i; - struct ufs_super_block_third *usb3; UFSD("ENTER\n"); - usb3 = ubh_get_usb_third(uspi); /* * Read cs structures from (usually) first data block * on the device. @@ -699,7 +697,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait) unsigned flags; lock_ufs(sb); - mutex_lock(&UFS_SB(sb)->s_lock); UFSD("ENTER\n"); @@ -717,7 +714,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait) ufs_put_cstotal(sb); UFSD("EXIT\n"); - mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; @@ -762,6 +758,7 @@ static void ufs_put_super(struct super_block *sb) ubh_brelse_uspi (sbi->s_uspi); kfree (sbi->s_uspi); + mutex_destroy(&sbi->mutex); kfree (sbi); sb->s_fs_info = NULL; UFSD("EXIT\n"); @@ -805,7 +802,6 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) } #endif mutex_init(&sbi->mutex); - mutex_init(&sbi->s_lock); spin_lock_init(&sbi->work_lock); INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); /* @@ -1262,6 +1258,7 @@ failed: if (ubh) ubh_brelse_uspi (uspi); kfree (uspi); + mutex_destroy(&sbi->mutex); kfree(sbi); sb->s_fs_info = NULL; UFSD("EXIT (FAILED)\n"); @@ -1282,7 +1279,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) sync_filesystem(sb); lock_ufs(sb); - mutex_lock(&UFS_SB(sb)->s_lock); uspi = UFS_SB(sb)->s_uspi; flags = UFS_SB(sb)->s_flags; usb1 = ubh_get_usb_first(uspi); @@ -1296,7 +1292,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) new_mount_opt = 0; ufs_set_opt (new_mount_opt, ONERROR_LOCK); if (!ufs_parse_options (data, &new_mount_opt)) { - mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } @@ -1304,14 +1299,12 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) new_mount_opt |= ufstype; } else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) { printk("ufstype can't be changed during remount\n"); - mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) { UFS_SB(sb)->s_mount_opt = new_mount_opt; - mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; } @@ -1336,7 +1329,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) #ifndef CONFIG_UFS_FS_WRITE printk("ufs was compiled with read-only support, " "can't be mounted as read-write\n"); - mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; #else @@ -1346,13 +1338,11 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) ufstype != UFS_MOUNT_UFSTYPE_SUNx86 && ufstype != UFS_MOUNT_UFSTYPE_UFS2) { printk("this ufstype is read-only supported\n"); - mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EINVAL; } if (!ufs_read_cylinder_structures(sb)) { printk("failed during remounting\n"); - mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return -EPERM; } @@ -1360,7 +1350,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) #endif } UFS_SB(sb)->s_mount_opt = new_mount_opt; - mutex_unlock(&UFS_SB(sb)->s_lock); unlock_ufs(sb); return 0; } @@ -1390,15 +1379,11 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf) struct super_block *sb = dentry->d_sb; struct ufs_sb_private_info *uspi= UFS_SB(sb)->s_uspi; unsigned flags = UFS_SB(sb)->s_flags; - struct ufs_super_block_first *usb1; - struct ufs_super_block_second *usb2; struct ufs_super_block_third *usb3; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); lock_ufs(sb); - usb1 = ubh_get_usb_first(uspi); - usb2 = ubh_get_usb_second(uspi); usb3 = ubh_get_usb_third(uspi); if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) { @@ -1454,7 +1439,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -static int init_inodecache(void) +static int __init init_inodecache(void) { ufs_inode_cachep = kmem_cache_create("ufs_inode_cache", sizeof(struct ufs_inode_info), diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index ff2c15ab81aa..343e6fc571e5 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -24,7 +24,6 @@ struct ufs_sb_info { int work_queued; /* non-zero if the delayed work is queued */ struct delayed_work sync_work; /* FS sync delayed work */ spinlock_t work_lock; /* protects sync_work and work_queued */ - struct mutex s_lock; }; struct ufs_inode_info { diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h new file mode 100644 index 000000000000..a5de55c04fb2 --- /dev/null +++ b/include/asm-generic/early_ioremap.h @@ -0,0 +1,42 @@ +#ifndef _ASM_EARLY_IOREMAP_H_ +#define _ASM_EARLY_IOREMAP_H_ + +#include <linux/types.h> + +/* + * early_ioremap() and early_iounmap() are for temporary early boot-time + * mappings, before the real ioremap() is functional. + */ +extern void __iomem *early_ioremap(resource_size_t phys_addr, + unsigned long size); +extern void *early_memremap(resource_size_t phys_addr, + unsigned long size); +extern void early_iounmap(void __iomem *addr, unsigned long size); +extern void early_memunmap(void *addr, unsigned long size); + +/* + * Weak function called by early_ioremap_reset(). It does nothing, but + * architectures may provide their own version to do any needed cleanups. + */ +extern void early_ioremap_shutdown(void); + +#if defined(CONFIG_GENERIC_EARLY_IOREMAP) && defined(CONFIG_MMU) +/* Arch-specific initialization */ +extern void early_ioremap_init(void); + +/* Generic initialization called by architecture code */ +extern void early_ioremap_setup(void); + +/* + * Called as last step in paging_init() so library can act + * accordingly for subsequent map/unmap requests. + */ +extern void early_ioremap_reset(void); + +#else +static inline void early_ioremap_init(void) { } +static inline void early_ioremap_setup(void) { } +static inline void early_ioremap_reset(void) { } +#endif + +#endif /* _ASM_EARLY_IOREMAP_H_ */ diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index d5afe96adba6..975e1cc75edb 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -327,7 +327,7 @@ static inline void iounmap(void __iomem *addr) } #endif /* CONFIG_MMU */ -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP #ifndef CONFIG_GENERIC_IOMAP static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) { @@ -341,7 +341,7 @@ static inline void ioport_unmap(void __iomem *p) extern void __iomem *ioport_map(unsigned long port, unsigned int nr); extern void ioport_unmap(void __iomem *p); #endif /* CONFIG_GENERIC_IOMAP */ -#endif /* CONFIG_HAS_IOPORT */ +#endif /* CONFIG_HAS_IOPORT_MAP */ #ifndef xlate_dev_kmem_ptr #define xlate_dev_kmem_ptr(p) p diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 6afd7d6a9899..1b41011643a5 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -56,7 +56,7 @@ extern void iowrite8_rep(void __iomem *port, const void *buf, unsigned long coun extern void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count); extern void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count); -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP /* Create a virtual mapping cookie for an IO port range */ extern void __iomem *ioport_map(unsigned long port, unsigned int nr); extern void ioport_unmap(void __iomem *); diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index d17784ea37ff..0703aa75b5e8 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -56,17 +56,17 @@ extern unsigned long __per_cpu_offset[NR_CPUS]; #define per_cpu(var, cpu) \ (*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu))) -#ifndef __this_cpu_ptr -#define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset) +#ifndef raw_cpu_ptr +#define raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset) #endif #ifdef CONFIG_DEBUG_PREEMPT #define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset) #else -#define this_cpu_ptr(ptr) __this_cpu_ptr(ptr) +#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr) #endif #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) -#define __raw_get_cpu_var(var) (*__this_cpu_ptr(&(var))) +#define __raw_get_cpu_var(var) (*raw_cpu_ptr(&(var))) #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA extern void setup_per_cpu_areas(void); @@ -83,7 +83,7 @@ extern void setup_per_cpu_areas(void); #define __get_cpu_var(var) (*VERIFY_PERCPU_PTR(&(var))) #define __raw_get_cpu_var(var) (*VERIFY_PERCPU_PTR(&(var))) #define this_cpu_ptr(ptr) per_cpu_ptr(ptr, 0) -#define __this_cpu_ptr(ptr) this_cpu_ptr(ptr) +#define raw_cpu_ptr(ptr) this_cpu_ptr(ptr) #endif /* SMP */ @@ -122,4 +122,7 @@ extern void setup_per_cpu_areas(void); #define PER_CPU_DEF_ATTRIBUTES #endif +/* Keep until we have removed all uses of __this_cpu_ptr */ +#define __this_cpu_ptr raw_cpu_ptr + #endif /* _ASM_GENERIC_PERCPU_H_ */ diff --git a/include/linux/io.h b/include/linux/io.h index 8a18e75600cc..b76e6e545806 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -41,7 +41,7 @@ static inline int ioremap_page_range(unsigned long addr, unsigned long end, /* * Managed iomap interface */ -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP void __iomem * devm_ioport_map(struct device *dev, unsigned long port, unsigned int nr); void devm_ioport_unmap(struct device *dev, void __iomem *addr); diff --git a/include/linux/lglock.h b/include/linux/lglock.h index 96549abe8842..0081f000e34b 100644 --- a/include/linux/lglock.h +++ b/include/linux/lglock.h @@ -25,6 +25,8 @@ #include <linux/cpu.h> #include <linux/notifier.h> +#ifdef CONFIG_SMP + #ifdef CONFIG_DEBUG_LOCK_ALLOC #define LOCKDEP_INIT_MAP lockdep_init_map #else @@ -57,4 +59,18 @@ void lg_local_unlock_cpu(struct lglock *lg, int cpu); void lg_global_lock(struct lglock *lg); void lg_global_unlock(struct lglock *lg); +#else +/* When !CONFIG_SMP, map lglock to spinlock */ +#define lglock spinlock +#define DEFINE_LGLOCK(name) DEFINE_SPINLOCK(name) +#define DEFINE_STATIC_LGLOCK(name) static DEFINE_SPINLOCK(name) +#define lg_lock_init(lg, name) spin_lock_init(lg) +#define lg_local_lock spin_lock +#define lg_local_unlock spin_unlock +#define lg_local_lock_cpu(lg, cpu) spin_lock(lg) +#define lg_local_unlock_cpu(lg, cpu) spin_unlock(lg) +#define lg_global_lock spin_lock +#define lg_global_unlock spin_unlock +#endif + #endif diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c58736481e79..e9dfcdad24c5 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -497,6 +497,9 @@ void __memcg_kmem_commit_charge(struct page *page, void __memcg_kmem_uncharge_pages(struct page *page, int order); int memcg_cache_id(struct mem_cgroup *memcg); + +char *memcg_create_cache_name(struct mem_cgroup *memcg, + struct kmem_cache *root_cache); int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache); void memcg_free_cache_params(struct kmem_cache *s); @@ -510,7 +513,7 @@ struct kmem_cache * __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); void mem_cgroup_destroy_cache(struct kmem_cache *cachep); -void kmem_cache_destroy_memcg_children(struct kmem_cache *s); +int __kmem_cache_destroy_memcg_children(struct kmem_cache *s); /** * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed. @@ -664,10 +667,6 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { return cachep; } - -static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s) -{ -} #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/percpu.h b/include/linux/percpu.h index e3817d2441b6..e7a0b95ed527 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -173,6 +173,12 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr); extern void __bad_size_call_parameter(void); +#ifdef CONFIG_DEBUG_PREEMPT +extern void __this_cpu_preempt_check(const char *op); +#else +static inline void __this_cpu_preempt_check(const char *op) { } +#endif + #define __pcpu_size_call_return(stem, variable) \ ({ typeof(variable) pscr_ret__; \ __verify_pcpu_ptr(&(variable)); \ @@ -243,6 +249,8 @@ do { \ } while (0) /* + * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com> + * * Optimized manipulation for memory allocated through the per cpu * allocator or for addresses of per cpu variables. * @@ -296,7 +304,7 @@ do { \ do { \ unsigned long flags; \ raw_local_irq_save(flags); \ - *__this_cpu_ptr(&(pcp)) op val; \ + *raw_cpu_ptr(&(pcp)) op val; \ raw_local_irq_restore(flags); \ } while (0) @@ -381,8 +389,8 @@ do { \ typeof(pcp) ret__; \ unsigned long flags; \ raw_local_irq_save(flags); \ - __this_cpu_add(pcp, val); \ - ret__ = __this_cpu_read(pcp); \ + raw_cpu_add(pcp, val); \ + ret__ = raw_cpu_read(pcp); \ raw_local_irq_restore(flags); \ ret__; \ }) @@ -411,8 +419,8 @@ do { \ ({ typeof(pcp) ret__; \ unsigned long flags; \ raw_local_irq_save(flags); \ - ret__ = __this_cpu_read(pcp); \ - __this_cpu_write(pcp, nval); \ + ret__ = raw_cpu_read(pcp); \ + raw_cpu_write(pcp, nval); \ raw_local_irq_restore(flags); \ ret__; \ }) @@ -439,9 +447,9 @@ do { \ typeof(pcp) ret__; \ unsigned long flags; \ raw_local_irq_save(flags); \ - ret__ = __this_cpu_read(pcp); \ + ret__ = raw_cpu_read(pcp); \ if (ret__ == (oval)) \ - __this_cpu_write(pcp, nval); \ + raw_cpu_write(pcp, nval); \ raw_local_irq_restore(flags); \ ret__; \ }) @@ -476,7 +484,7 @@ do { \ int ret__; \ unsigned long flags; \ raw_local_irq_save(flags); \ - ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2, \ + ret__ = raw_cpu_generic_cmpxchg_double(pcp1, pcp2, \ oval1, oval2, nval1, nval2); \ raw_local_irq_restore(flags); \ ret__; \ @@ -504,12 +512,8 @@ do { \ #endif /* - * Generic percpu operations for context that are safe from preemption/interrupts. - * Either we do not care about races or the caller has the - * responsibility of handling preemption/interrupt issues. Arch code can still - * override these instructions since the arch per cpu code may be more - * efficient and may actually get race freeness for free (that is the - * case for x86 for example). + * Generic percpu operations for contexts where we do not want to do + * any checks for preemptiosn. * * If there is no other protection through preempt disable and/or * disabling interupts then one of these RMW operations can show unexpected @@ -517,211 +521,285 @@ do { \ * or an interrupt occurred and the same percpu variable was modified from * the interrupt context. */ -#ifndef __this_cpu_read -# ifndef __this_cpu_read_1 -# define __this_cpu_read_1(pcp) (*__this_cpu_ptr(&(pcp))) +#ifndef raw_cpu_read +# ifndef raw_cpu_read_1 +# define raw_cpu_read_1(pcp) (*raw_cpu_ptr(&(pcp))) # endif -# ifndef __this_cpu_read_2 -# define __this_cpu_read_2(pcp) (*__this_cpu_ptr(&(pcp))) +# ifndef raw_cpu_read_2 +# define raw_cpu_read_2(pcp) (*raw_cpu_ptr(&(pcp))) # endif -# ifndef __this_cpu_read_4 -# define __this_cpu_read_4(pcp) (*__this_cpu_ptr(&(pcp))) +# ifndef raw_cpu_read_4 +# define raw_cpu_read_4(pcp) (*raw_cpu_ptr(&(pcp))) # endif -# ifndef __this_cpu_read_8 -# define __this_cpu_read_8(pcp) (*__this_cpu_ptr(&(pcp))) +# ifndef raw_cpu_read_8 +# define raw_cpu_read_8(pcp) (*raw_cpu_ptr(&(pcp))) # endif -# define __this_cpu_read(pcp) __pcpu_size_call_return(__this_cpu_read_, (pcp)) +# define raw_cpu_read(pcp) __pcpu_size_call_return(raw_cpu_read_, (pcp)) #endif -#define __this_cpu_generic_to_op(pcp, val, op) \ +#define raw_cpu_generic_to_op(pcp, val, op) \ do { \ - *__this_cpu_ptr(&(pcp)) op val; \ + *raw_cpu_ptr(&(pcp)) op val; \ } while (0) -#ifndef __this_cpu_write -# ifndef __this_cpu_write_1 -# define __this_cpu_write_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), =) + +#ifndef raw_cpu_write +# ifndef raw_cpu_write_1 +# define raw_cpu_write_1(pcp, val) raw_cpu_generic_to_op((pcp), (val), =) # endif -# ifndef __this_cpu_write_2 -# define __this_cpu_write_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), =) +# ifndef raw_cpu_write_2 +# define raw_cpu_write_2(pcp, val) raw_cpu_generic_to_op((pcp), (val), =) # endif -# ifndef __this_cpu_write_4 -# define __this_cpu_write_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), =) +# ifndef raw_cpu_write_4 +# define raw_cpu_write_4(pcp, val) raw_cpu_generic_to_op((pcp), (val), =) # endif -# ifndef __this_cpu_write_8 -# define __this_cpu_write_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), =) +# ifndef raw_cpu_write_8 +# define raw_cpu_write_8(pcp, val) raw_cpu_generic_to_op((pcp), (val), =) # endif -# define __this_cpu_write(pcp, val) __pcpu_size_call(__this_cpu_write_, (pcp), (val)) +# define raw_cpu_write(pcp, val) __pcpu_size_call(raw_cpu_write_, (pcp), (val)) #endif -#ifndef __this_cpu_add -# ifndef __this_cpu_add_1 -# define __this_cpu_add_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=) +#ifndef raw_cpu_add +# ifndef raw_cpu_add_1 +# define raw_cpu_add_1(pcp, val) raw_cpu_generic_to_op((pcp), (val), +=) # endif -# ifndef __this_cpu_add_2 -# define __this_cpu_add_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=) +# ifndef raw_cpu_add_2 +# define raw_cpu_add_2(pcp, val) raw_cpu_generic_to_op((pcp), (val), +=) # endif -# ifndef __this_cpu_add_4 -# define __this_cpu_add_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=) +# ifndef raw_cpu_add_4 +# define raw_cpu_add_4(pcp, val) raw_cpu_generic_to_op((pcp), (val), +=) # endif -# ifndef __this_cpu_add_8 -# define __this_cpu_add_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), +=) +# ifndef raw_cpu_add_8 +# define raw_cpu_add_8(pcp, val) raw_cpu_generic_to_op((pcp), (val), +=) # endif -# define __this_cpu_add(pcp, val) __pcpu_size_call(__this_cpu_add_, (pcp), (val)) +# define raw_cpu_add(pcp, val) __pcpu_size_call(raw_cpu_add_, (pcp), (val)) #endif -#ifndef __this_cpu_sub -# define __this_cpu_sub(pcp, val) __this_cpu_add((pcp), -(typeof(pcp))(val)) +#ifndef raw_cpu_sub +# define raw_cpu_sub(pcp, val) raw_cpu_add((pcp), -(val)) #endif -#ifndef __this_cpu_inc -# define __this_cpu_inc(pcp) __this_cpu_add((pcp), 1) +#ifndef raw_cpu_inc +# define raw_cpu_inc(pcp) raw_cpu_add((pcp), 1) #endif -#ifndef __this_cpu_dec -# define __this_cpu_dec(pcp) __this_cpu_sub((pcp), 1) +#ifndef raw_cpu_dec +# define raw_cpu_dec(pcp) raw_cpu_sub((pcp), 1) #endif -#ifndef __this_cpu_and -# ifndef __this_cpu_and_1 -# define __this_cpu_and_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=) +#ifndef raw_cpu_and +# ifndef raw_cpu_and_1 +# define raw_cpu_and_1(pcp, val) raw_cpu_generic_to_op((pcp), (val), &=) # endif -# ifndef __this_cpu_and_2 -# define __this_cpu_and_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=) +# ifndef raw_cpu_and_2 +# define raw_cpu_and_2(pcp, val) raw_cpu_generic_to_op((pcp), (val), &=) # endif -# ifndef __this_cpu_and_4 -# define __this_cpu_and_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=) +# ifndef raw_cpu_and_4 +# define raw_cpu_and_4(pcp, val) raw_cpu_generic_to_op((pcp), (val), &=) # endif -# ifndef __this_cpu_and_8 -# define __this_cpu_and_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), &=) +# ifndef raw_cpu_and_8 +# define raw_cpu_and_8(pcp, val) raw_cpu_generic_to_op((pcp), (val), &=) # endif -# define __this_cpu_and(pcp, val) __pcpu_size_call(__this_cpu_and_, (pcp), (val)) +# define raw_cpu_and(pcp, val) __pcpu_size_call(raw_cpu_and_, (pcp), (val)) #endif -#ifndef __this_cpu_or -# ifndef __this_cpu_or_1 -# define __this_cpu_or_1(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=) +#ifndef raw_cpu_or +# ifndef raw_cpu_or_1 +# define raw_cpu_or_1(pcp, val) raw_cpu_generic_to_op((pcp), (val), |=) # endif -# ifndef __this_cpu_or_2 -# define __this_cpu_or_2(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=) +# ifndef raw_cpu_or_2 +# define raw_cpu_or_2(pcp, val) raw_cpu_generic_to_op((pcp), (val), |=) # endif -# ifndef __this_cpu_or_4 -# define __this_cpu_or_4(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=) +# ifndef raw_cpu_or_4 +# define raw_cpu_or_4(pcp, val) raw_cpu_generic_to_op((pcp), (val), |=) # endif -# ifndef __this_cpu_or_8 -# define __this_cpu_or_8(pcp, val) __this_cpu_generic_to_op((pcp), (val), |=) +# ifndef raw_cpu_or_8 +# define raw_cpu_or_8(pcp, val) raw_cpu_generic_to_op((pcp), (val), |=) # endif -# define __this_cpu_or(pcp, val) __pcpu_size_call(__this_cpu_or_, (pcp), (val)) +# define raw_cpu_or(pcp, val) __pcpu_size_call(raw_cpu_or_, (pcp), (val)) #endif -#define __this_cpu_generic_add_return(pcp, val) \ +#define raw_cpu_generic_add_return(pcp, val) \ ({ \ - __this_cpu_add(pcp, val); \ - __this_cpu_read(pcp); \ + raw_cpu_add(pcp, val); \ + raw_cpu_read(pcp); \ }) -#ifndef __this_cpu_add_return -# ifndef __this_cpu_add_return_1 -# define __this_cpu_add_return_1(pcp, val) __this_cpu_generic_add_return(pcp, val) +#ifndef raw_cpu_add_return +# ifndef raw_cpu_add_return_1 +# define raw_cpu_add_return_1(pcp, val) raw_cpu_generic_add_return(pcp, val) # endif -# ifndef __this_cpu_add_return_2 -# define __this_cpu_add_return_2(pcp, val) __this_cpu_generic_add_return(pcp, val) +# ifndef raw_cpu_add_return_2 +# define raw_cpu_add_return_2(pcp, val) raw_cpu_generic_add_return(pcp, val) # endif -# ifndef __this_cpu_add_return_4 -# define __this_cpu_add_return_4(pcp, val) __this_cpu_generic_add_return(pcp, val) +# ifndef raw_cpu_add_return_4 +# define raw_cpu_add_return_4(pcp, val) raw_cpu_generic_add_return(pcp, val) # endif -# ifndef __this_cpu_add_return_8 -# define __this_cpu_add_return_8(pcp, val) __this_cpu_generic_add_return(pcp, val) +# ifndef raw_cpu_add_return_8 +# define raw_cpu_add_return_8(pcp, val) raw_cpu_generic_add_return(pcp, val) # endif -# define __this_cpu_add_return(pcp, val) \ - __pcpu_size_call_return2(__this_cpu_add_return_, pcp, val) +# define raw_cpu_add_return(pcp, val) \ + __pcpu_size_call_return2(raw_add_return_, pcp, val) #endif -#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(typeof(pcp))(val)) -#define __this_cpu_inc_return(pcp) __this_cpu_add_return(pcp, 1) -#define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) +#define raw_cpu_sub_return(pcp, val) raw_cpu_add_return(pcp, -(typeof(pcp))(val)) +#define raw_cpu_inc_return(pcp) raw_cpu_add_return(pcp, 1) +#define raw_cpu_dec_return(pcp) raw_cpu_add_return(pcp, -1) -#define __this_cpu_generic_xchg(pcp, nval) \ +#define raw_cpu_generic_xchg(pcp, nval) \ ({ typeof(pcp) ret__; \ - ret__ = __this_cpu_read(pcp); \ - __this_cpu_write(pcp, nval); \ + ret__ = raw_cpu_read(pcp); \ + raw_cpu_write(pcp, nval); \ ret__; \ }) -#ifndef __this_cpu_xchg -# ifndef __this_cpu_xchg_1 -# define __this_cpu_xchg_1(pcp, nval) __this_cpu_generic_xchg(pcp, nval) +#ifndef raw_cpu_xchg +# ifndef raw_cpu_xchg_1 +# define raw_cpu_xchg_1(pcp, nval) raw_cpu_generic_xchg(pcp, nval) # endif -# ifndef __this_cpu_xchg_2 -# define __this_cpu_xchg_2(pcp, nval) __this_cpu_generic_xchg(pcp, nval) +# ifndef raw_cpu_xchg_2 +# define raw_cpu_xchg_2(pcp, nval) raw_cpu_generic_xchg(pcp, nval) # endif -# ifndef __this_cpu_xchg_4 -# define __this_cpu_xchg_4(pcp, nval) __this_cpu_generic_xchg(pcp, nval) +# ifndef raw_cpu_xchg_4 +# define raw_cpu_xchg_4(pcp, nval) raw_cpu_generic_xchg(pcp, nval) # endif -# ifndef __this_cpu_xchg_8 -# define __this_cpu_xchg_8(pcp, nval) __this_cpu_generic_xchg(pcp, nval) +# ifndef raw_cpu_xchg_8 +# define raw_cpu_xchg_8(pcp, nval) raw_cpu_generic_xchg(pcp, nval) # endif -# define __this_cpu_xchg(pcp, nval) \ - __pcpu_size_call_return2(__this_cpu_xchg_, (pcp), nval) +# define raw_cpu_xchg(pcp, nval) \ + __pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval) #endif -#define __this_cpu_generic_cmpxchg(pcp, oval, nval) \ +#define raw_cpu_generic_cmpxchg(pcp, oval, nval) \ ({ \ typeof(pcp) ret__; \ - ret__ = __this_cpu_read(pcp); \ + ret__ = raw_cpu_read(pcp); \ if (ret__ == (oval)) \ - __this_cpu_write(pcp, nval); \ + raw_cpu_write(pcp, nval); \ ret__; \ }) -#ifndef __this_cpu_cmpxchg -# ifndef __this_cpu_cmpxchg_1 -# define __this_cpu_cmpxchg_1(pcp, oval, nval) __this_cpu_generic_cmpxchg(pcp, oval, nval) +#ifndef raw_cpu_cmpxchg +# ifndef raw_cpu_cmpxchg_1 +# define raw_cpu_cmpxchg_1(pcp, oval, nval) raw_cpu_generic_cmpxchg(pcp, oval, nval) # endif -# ifndef __this_cpu_cmpxchg_2 -# define __this_cpu_cmpxchg_2(pcp, oval, nval) __this_cpu_generic_cmpxchg(pcp, oval, nval) +# ifndef raw_cpu_cmpxchg_2 +# define raw_cpu_cmpxchg_2(pcp, oval, nval) raw_cpu_generic_cmpxchg(pcp, oval, nval) # endif -# ifndef __this_cpu_cmpxchg_4 -# define __this_cpu_cmpxchg_4(pcp, oval, nval) __this_cpu_generic_cmpxchg(pcp, oval, nval) +# ifndef raw_cpu_cmpxchg_4 +# define raw_cpu_cmpxchg_4(pcp, oval, nval) raw_cpu_generic_cmpxchg(pcp, oval, nval) # endif -# ifndef __this_cpu_cmpxchg_8 -# define __this_cpu_cmpxchg_8(pcp, oval, nval) __this_cpu_generic_cmpxchg(pcp, oval, nval) +# ifndef raw_cpu_cmpxchg_8 +# define raw_cpu_cmpxchg_8(pcp, oval, nval) raw_cpu_generic_cmpxchg(pcp, oval, nval) # endif -# define __this_cpu_cmpxchg(pcp, oval, nval) \ - __pcpu_size_call_return2(__this_cpu_cmpxchg_, pcp, oval, nval) +# define raw_cpu_cmpxchg(pcp, oval, nval) \ + __pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval) #endif -#define __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ +#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ ({ \ int __ret = 0; \ - if (__this_cpu_read(pcp1) == (oval1) && \ - __this_cpu_read(pcp2) == (oval2)) { \ - __this_cpu_write(pcp1, (nval1)); \ - __this_cpu_write(pcp2, (nval2)); \ + if (raw_cpu_read(pcp1) == (oval1) && \ + raw_cpu_read(pcp2) == (oval2)) { \ + raw_cpu_write(pcp1, (nval1)); \ + raw_cpu_write(pcp2, (nval2)); \ __ret = 1; \ } \ (__ret); \ }) -#ifndef __this_cpu_cmpxchg_double -# ifndef __this_cpu_cmpxchg_double_1 -# define __this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) +#ifndef raw_cpu_cmpxchg_double +# ifndef raw_cpu_cmpxchg_double_1 +# define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \ + raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) # endif -# ifndef __this_cpu_cmpxchg_double_2 -# define __this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) +# ifndef raw_cpu_cmpxchg_double_2 +# define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \ + raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) # endif -# ifndef __this_cpu_cmpxchg_double_4 -# define __this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) +# ifndef raw_cpu_cmpxchg_double_4 +# define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \ + raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) # endif -# ifndef __this_cpu_cmpxchg_double_8 -# define __this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) +# ifndef raw_cpu_cmpxchg_double_8 +# define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \ + raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) # endif +# define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ + __pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)) +#endif + +/* + * Generic percpu operations for context that are safe from preemption/interrupts. + */ +#ifndef __this_cpu_read +# define __this_cpu_read(pcp) \ + (__this_cpu_preempt_check("read"),__pcpu_size_call_return(raw_cpu_read_, (pcp))) +#endif + +#ifndef __this_cpu_write +# define __this_cpu_write(pcp, val) \ +do { __this_cpu_preempt_check("write"); \ + __pcpu_size_call(raw_cpu_write_, (pcp), (val)); \ +} while (0) +#endif + +#ifndef __this_cpu_add +# define __this_cpu_add(pcp, val) \ +do { __this_cpu_preempt_check("add"); \ + __pcpu_size_call(raw_cpu_add_, (pcp), (val)); \ +} while (0) +#endif + +#ifndef __this_cpu_sub +# define __this_cpu_sub(pcp, val) __this_cpu_add((pcp), -(typeof(pcp))(val)) +#endif + +#ifndef __this_cpu_inc +# define __this_cpu_inc(pcp) __this_cpu_add((pcp), 1) +#endif + +#ifndef __this_cpu_dec +# define __this_cpu_dec(pcp) __this_cpu_sub((pcp), 1) +#endif + +#ifndef __this_cpu_and +# define __this_cpu_and(pcp, val) \ +do { __this_cpu_preempt_check("and"); \ + __pcpu_size_call(raw_cpu_and_, (pcp), (val)); \ +} while (0) + +#endif + +#ifndef __this_cpu_or +# define __this_cpu_or(pcp, val) \ +do { __this_cpu_preempt_check("or"); \ + __pcpu_size_call(raw_cpu_or_, (pcp), (val)); \ +} while (0) +#endif + +#ifndef __this_cpu_add_return +# define __this_cpu_add_return(pcp, val) \ + (__this_cpu_preempt_check("add_return"),__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val)) +#endif + +#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(typeof(pcp))(val)) +#define __this_cpu_inc_return(pcp) __this_cpu_add_return(pcp, 1) +#define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) + +#ifndef __this_cpu_xchg +# define __this_cpu_xchg(pcp, nval) \ + (__this_cpu_preempt_check("xchg"),__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval)) +#endif + +#ifndef __this_cpu_cmpxchg +# define __this_cpu_cmpxchg(pcp, oval, nval) \ + (__this_cpu_preempt_check("cmpxchg"),__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)) +#endif + +#ifndef __this_cpu_cmpxchg_double # define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - __pcpu_double_call_return_bool(__this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)) + (__this_cpu_preempt_check("cmpxchg_double"),__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))) #endif #endif /* __LINUX_PERCPU_H */ diff --git a/include/linux/slab.h b/include/linux/slab.h index b5b2df60299e..3dd389aa91c7 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -115,9 +115,9 @@ int slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *)); -struct kmem_cache * -kmem_cache_create_memcg(struct mem_cgroup *, const char *, size_t, size_t, - unsigned long, void (*)(void *), struct kmem_cache *); +#ifdef CONFIG_MEMCG_KMEM +void kmem_cache_create_memcg(struct mem_cgroup *, struct kmem_cache *); +#endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index f56bfa9e4526..f2f7398848cf 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -87,6 +87,9 @@ struct kmem_cache { #ifdef CONFIG_MEMCG_KMEM struct memcg_cache_params *memcg_params; int max_attr_size; /* for propagation, maximum size of a stored attr */ +#ifdef CONFIG_SYSFS + struct kset *memcg_kset; +#endif #endif #ifdef CONFIG_NUMA diff --git a/include/linux/topology.h b/include/linux/topology.h index 12ae6ce997d6..7062330a1329 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -188,7 +188,7 @@ DECLARE_PER_CPU(int, numa_node); /* Returns the number of the current Node. */ static inline int numa_node_id(void) { - return __this_cpu_read(numa_node); + return raw_cpu_read(numa_node); } #endif @@ -245,7 +245,7 @@ static inline void set_numa_mem(int node) /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { - return __this_cpu_read(_numa_mem_); + return raw_cpu_read(_numa_mem_); } #endif diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index ea4476157e00..45c9cd1daf7a 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -27,9 +27,13 @@ struct vm_event_state { DECLARE_PER_CPU(struct vm_event_state, vm_event_states); +/* + * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the + * local_irq_disable overhead. + */ static inline void __count_vm_event(enum vm_event_item item) { - __this_cpu_inc(vm_event_states.event[item]); + raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) @@ -39,7 +43,7 @@ static inline void count_vm_event(enum vm_event_item item) static inline void __count_vm_events(enum vm_event_item item, long delta) { - __this_cpu_add(vm_event_states.event[item], delta); + raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) diff --git a/kernel/fork.c b/kernel/fork.c index 0b65a2b0c426..312d5aed7ee9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -73,6 +73,7 @@ #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> +#include <linux/compiler.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -286,7 +287,7 @@ void __init fork_init(unsigned long mempages) init_task.signal->rlim[RLIMIT_NPROC]; } -int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst, +int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 3127ad52cdb2..cb0cf37dac3a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -23,6 +23,7 @@ #include <linux/mm.h> #include <linux/ctype.h> #include <linux/slab.h> +#include <linux/compiler.h> #include <asm/sections.h> @@ -36,8 +37,8 @@ * These will be re-linked against their real values * during the second link stage. */ -extern const unsigned long kallsyms_addresses[] __attribute__((weak)); -extern const u8 kallsyms_names[] __attribute__((weak)); +extern const unsigned long kallsyms_addresses[] __weak; +extern const u8 kallsyms_names[] __weak; /* * Tell the compiler that the count isn't in the small data section if the arch @@ -46,10 +47,10 @@ extern const u8 kallsyms_names[] __attribute__((weak)); extern const unsigned long kallsyms_num_syms __attribute__((weak, section(".rodata"))); -extern const u8 kallsyms_token_table[] __attribute__((weak)); -extern const u16 kallsyms_token_index[] __attribute__((weak)); +extern const u8 kallsyms_token_table[] __weak; +extern const u16 kallsyms_token_index[] __weak; -extern const unsigned long kallsyms_markers[] __attribute__((weak)); +extern const unsigned long kallsyms_markers[] __weak; static inline int is_kernel_inittext(unsigned long addr) { diff --git a/kernel/kexec.c b/kernel/kexec.c index c0d261c7db7b..c8380ad203bc 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -32,6 +32,7 @@ #include <linux/vmalloc.h> #include <linux/swap.h> #include <linux/syscore_ops.h> +#include <linux/compiler.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -1551,10 +1552,10 @@ void vmcoreinfo_append_str(const char *fmt, ...) * provide an empty default implementation here -- architecture * code may override this */ -void __attribute__ ((weak)) arch_crash_save_vmcoreinfo(void) +void __weak arch_crash_save_vmcoreinfo(void) {} -unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void) +unsigned long __weak paddr_vmcoreinfo_note(void) { return __pa((unsigned long)(char *)&vmcoreinfo_note); } diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index e660964086e2..2495a9b14ac8 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -18,6 +18,7 @@ #include <linux/stat.h> #include <linux/sched.h> #include <linux/capability.h> +#include <linux/compiler.h> #include <linux/rcupdate.h> /* rcu_expedited */ @@ -162,8 +163,8 @@ KERNEL_ATTR_RW(rcu_expedited); /* * Make /sys/kernel/notes give the raw contents of our kernel .notes section. */ -extern const void __start_notes __attribute__((weak)); -extern const void __stop_notes __attribute__((weak)); +extern const void __start_notes __weak; +extern const void __stop_notes __weak; #define notes_size (&__stop_notes - &__start_notes) static ssize_t notes_read(struct file *filp, struct kobject *kobj, diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 306a76b51e0f..b8bdcd4785b7 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,5 +1,5 @@ -obj-y += mutex.o semaphore.o rwsem.o lglock.o mcs_spinlock.o +obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = -pg @@ -14,6 +14,7 @@ ifeq ($(CONFIG_PROC_FS),y) obj-$(CONFIG_LOCKDEP) += lockdep_proc.o endif obj-$(CONFIG_SMP) += spinlock.o +obj-$(CONFIG_SMP) += lglock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o diff --git a/kernel/module.c b/kernel/module.c index 658c6746d051..28a3ad4df8e8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -640,7 +640,7 @@ static int module_unload_init(struct module *mod) INIT_LIST_HEAD(&mod->target_list); /* Hold reference count during initialization. */ - __this_cpu_write(mod->refptr->incs, 1); + raw_cpu_write(mod->refptr->incs, 1); return 0; } diff --git a/kernel/power/power.h b/kernel/power/power.h index 1ca753106557..15f37ea08719 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -2,6 +2,7 @@ #include <linux/suspend_ioctls.h> #include <linux/utsname.h> #include <linux/freezer.h> +#include <linux/compiler.h> struct swsusp_info { struct new_utsname uts; @@ -11,7 +12,7 @@ struct swsusp_info { unsigned long image_pages; unsigned long pages; unsigned long size; -} __attribute__((aligned(PAGE_SIZE))); +} __aligned(PAGE_SIZE); #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 149e745eaa52..18fb7a2fb14b 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -27,6 +27,7 @@ #include <linux/highmem.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/compiler.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -155,7 +156,7 @@ static inline void free_image_page(void *addr, int clear_nosave_free) struct linked_page { struct linked_page *next; char data[LINKED_PAGE_DATA_SIZE]; -} __attribute__((packed)); +} __packed; static inline void free_list_of_pages(struct linked_page *list, int clear_page_nosave) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 90b3d9366d1a..c3ad9cafe930 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -26,6 +26,7 @@ #include <linux/syscore_ops.h> #include <linux/ftrace.h> #include <trace/events/power.h> +#include <linux/compiler.h> #include "power.h" @@ -156,13 +157,13 @@ static int suspend_prepare(suspend_state_t state) } /* default implementation */ -void __attribute__ ((weak)) arch_suspend_disable_irqs(void) +void __weak arch_suspend_disable_irqs(void) { local_irq_disable(); } /* default implementation */ -void __attribute__ ((weak)) arch_suspend_enable_irqs(void) +void __weak arch_suspend_enable_irqs(void) { local_irq_enable(); } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 7c33ed200410..8c9a4819f798 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -101,7 +101,7 @@ struct swsusp_header { unsigned int flags; /* Flags to pass to the "boot" kernel */ char orig_sig[10]; char sig[10]; -} __attribute__((packed)); +} __packed; static struct swsusp_header *swsusp_header; diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index b30a2924ef14..3ef6451e972e 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -60,13 +60,14 @@ #include <linux/sched.h> #include <linux/static_key.h> #include <linux/workqueue.h> +#include <linux/compiler.h> /* * Scheduler clock - returns current time in nanosec units. * This is default implementation. * Architectures and sub-architectures can override this. */ -unsigned long long __attribute__((weak)) sched_clock(void) +unsigned long long __weak sched_clock(void) { return (unsigned long long)(jiffies - INITIAL_JIFFIES) * (NSEC_PER_SEC / HZ); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1d1b87b36778..80bd491b718c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -73,6 +73,7 @@ #include <linux/init_task.h> #include <linux/binfmts.h> #include <linux/context_tracking.h> +#include <linux/compiler.h> #include <asm/switch_to.h> #include <asm/tlb.h> @@ -6498,7 +6499,7 @@ static cpumask_var_t fallback_doms; * cpu core maps. It is supposed to return 1 if the topology changed * or 0 if it stayed the same. */ -int __attribute__((weak)) arch_update_cpu_topology(void) +int __weak arch_update_cpu_topology(void) { return 0; } diff --git a/kernel/signal.c b/kernel/signal.c index 5d4b05a229a6..6ea13c09ae56 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -33,6 +33,8 @@ #include <linux/uprobes.h> #include <linux/compat.h> #include <linux/cn_proc.h> +#include <linux/compiler.h> + #define CREATE_TRACE_POINTS #include <trace/events/signal.h> @@ -3618,7 +3620,7 @@ SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask) } #endif -__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma) +__weak const char *arch_vma_name(struct vm_area_struct *vma) { return NULL; } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0aa4ce81bc16..8c367e1a12d3 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -22,6 +22,7 @@ #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> +#include <linux/compiler.h> #include "tick-internal.h" #include "ntp_internal.h" @@ -760,7 +761,7 @@ u64 timekeeping_max_deferment(void) * * XXX - Do be sure to remove it once all arches implement it. */ -void __attribute__((weak)) read_persistent_clock(struct timespec *ts) +void __weak read_persistent_clock(struct timespec *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; @@ -775,7 +776,7 @@ void __attribute__((weak)) read_persistent_clock(struct timespec *ts) * * XXX - Do be sure to remove it once all arches implement it. */ -void __attribute__((weak)) read_boot_clock(struct timespec *ts) +void __weak read_boot_clock(struct timespec *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ffc314b7e92b..2e29d7ba5a52 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -13,6 +13,7 @@ #include <linux/hw_breakpoint.h> #include <linux/trace_seq.h> #include <linux/ftrace_event.h> +#include <linux/compiler.h> #ifdef CONFIG_FTRACE_SYSCALLS #include <asm/unistd.h> /* For NR_SYSCALLS */ @@ -1279,7 +1280,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ - __attribute__((__aligned__(4))) event_##call; + __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ diff --git a/lib/Kconfig b/lib/Kconfig index ea321564b2b7..507ad6489f1f 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -358,9 +358,9 @@ config HAS_IOMEM select GENERIC_IO default y -config HAS_IOPORT +config HAS_IOPORT_MAP boolean - depends on HAS_IOMEM && !NO_IOPORT + depends on HAS_IOMEM && !NO_IOPORT_MAP default y config HAS_DMA diff --git a/lib/devres.c b/lib/devres.c index 48cb3c7bd7de..2f16c133fd36 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -170,7 +170,7 @@ void __iomem *devm_request_and_ioremap(struct device *device, } EXPORT_SYMBOL(devm_request_and_ioremap); -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP /* * Generic iomap devres */ @@ -229,7 +229,7 @@ void devm_ioport_unmap(struct device *dev, void __iomem *addr) devm_ioport_map_match, (__force void *)addr)); } EXPORT_SYMBOL(devm_ioport_unmap); -#endif /* CONFIG_HAS_IOPORT */ +#endif /* CONFIG_HAS_IOPORT_MAP */ #ifdef CONFIG_PCI /* diff --git a/lib/iomap.c b/lib/iomap.c index 2c08f36862eb..fc3dcb4b238e 100644 --- a/lib/iomap.c +++ b/lib/iomap.c @@ -224,7 +224,7 @@ EXPORT_SYMBOL(iowrite8_rep); EXPORT_SYMBOL(iowrite16_rep); EXPORT_SYMBOL(iowrite32_rep); -#ifdef CONFIG_HAS_IOPORT +#ifdef CONFIG_HAS_IOPORT_MAP /* Create a virtual mapping cookie for an IO port range */ void __iomem *ioport_map(unsigned long port, unsigned int nr) { @@ -239,7 +239,7 @@ void ioport_unmap(void __iomem *addr) } EXPORT_SYMBOL(ioport_map); EXPORT_SYMBOL(ioport_unmap); -#endif /* CONFIG_HAS_IOPORT */ +#endif /* CONFIG_HAS_IOPORT_MAP */ #ifdef CONFIG_PCI /* Hide the details if this is a MMIO or PIO address space and just do what diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 04abe53f12a1..1afec32de6f2 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -7,7 +7,8 @@ #include <linux/kallsyms.h> #include <linux/sched.h> -notrace unsigned int debug_smp_processor_id(void) +notrace static unsigned int check_preemption_disabled(const char *what1, + const char *what2) { int this_cpu = raw_smp_processor_id(); @@ -38,9 +39,9 @@ notrace unsigned int debug_smp_processor_id(void) if (!printk_ratelimit()) goto out_enable; - printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] " - "code: %s/%d\n", - preempt_count() - 1, current->comm, current->pid); + printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n", + what1, what2, preempt_count() - 1, current->comm, current->pid); + print_symbol("caller is %s\n", (long)__builtin_return_address(0)); dump_stack(); @@ -50,5 +51,14 @@ out: return this_cpu; } +notrace unsigned int debug_smp_processor_id(void) +{ + return check_preemption_disabled("smp_processor_id", ""); +} EXPORT_SYMBOL(debug_smp_processor_id); +notrace void __this_cpu_preempt_check(const char *op) +{ + check_preemption_disabled("__this_cpu_", op); +} +EXPORT_SYMBOL(__this_cpu_preempt_check); diff --git a/mm/Kconfig b/mm/Kconfig index 37fbe1ef5239..ebe5880c29d6 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -578,3 +578,6 @@ config PGTABLE_MAPPING You can check speed with zsmalloc benchmark: https://github.com/spartacus06/zsmapbench + +config GENERIC_EARLY_IOREMAP + bool diff --git a/mm/Makefile b/mm/Makefile index 23a6f7e23019..9e5aaf92197d 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -61,3 +61,4 @@ obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o obj-$(CONFIG_ZBUD) += zbud.o obj-$(CONFIG_ZSMALLOC) += zsmalloc.o +obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 09d9591b7708..5ab9a49ce037 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -234,11 +234,46 @@ static ssize_t stable_pages_required_show(struct device *dev, } static DEVICE_ATTR_RO(stable_pages_required); +static ssize_t strictlimit_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + unsigned int val; + ssize_t ret; + + ret = kstrtouint(buf, 10, &val); + if (ret < 0) + return ret; + + switch (val) { + case 0: + bdi->capabilities &= ~BDI_CAP_STRICTLIMIT; + break; + case 1: + bdi->capabilities |= BDI_CAP_STRICTLIMIT; + break; + default: + return -EINVAL; + } + + return count; +} +static ssize_t strictlimit_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + + return snprintf(page, PAGE_SIZE-1, "%d\n", + !!(bdi->capabilities & BDI_CAP_STRICTLIMIT)); +} +static DEVICE_ATTR_RW(strictlimit); + static struct attribute *bdi_dev_attrs[] = { &dev_attr_read_ahead_kb.attr, &dev_attr_min_ratio.attr, &dev_attr_max_ratio.attr, &dev_attr_stable_pages_required.attr, + &dev_attr_strictlimit.attr, NULL, }; ATTRIBUTE_GROUPS(bdi_dev); diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c new file mode 100644 index 000000000000..e10ccd299d66 --- /dev/null +++ b/mm/early_ioremap.c @@ -0,0 +1,245 @@ +/* + * Provide common bits of early_ioremap() support for architectures needing + * temporary mappings during boot before ioremap() is available. + * + * This is mostly a direct copy of the x86 early_ioremap implementation. + * + * (C) Copyright 1995 1996, 2014 Linus Torvalds + * + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> +#include <asm/fixmap.h> + +#ifdef CONFIG_MMU +static int early_ioremap_debug __initdata; + +static int __init early_ioremap_debug_setup(char *str) +{ + early_ioremap_debug = 1; + + return 0; +} +early_param("early_ioremap_debug", early_ioremap_debug_setup); + +static int after_paging_init __initdata; + +void __init __weak early_ioremap_shutdown(void) +{ +} + +void __init early_ioremap_reset(void) +{ + early_ioremap_shutdown(); + after_paging_init = 1; +} + +/* + * Generally, ioremap() is available after paging_init() has been called. + * Architectures wanting to allow early_ioremap after paging_init() can + * define __late_set_fixmap and __late_clear_fixmap to do the right thing. + */ +#ifndef __late_set_fixmap +static inline void __init __late_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t prot) +{ + BUG(); +} +#endif + +#ifndef __late_clear_fixmap +static inline void __init __late_clear_fixmap(enum fixed_addresses idx) +{ + BUG(); +} +#endif + +static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata; + +void __init early_ioremap_setup(void) +{ + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (WARN_ON(prev_map[i])) + break; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i); +} + +static int __init check_early_ioremap_leak(void) +{ + int count = 0; + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (prev_map[i]) + count++; + + if (WARN(count, KERN_WARNING + "Debug warning: early ioremap leak of %d areas detected.\n" + "please boot with early_ioremap_debug and report the dmesg.\n", + count)) + return 1; + return 0; +} +late_initcall(check_early_ioremap_leak); + +static void __init __iomem * +__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) +{ + unsigned long offset; + resource_size_t last_addr; + unsigned int nrpages; + enum fixed_addresses idx; + int i, slot; + + WARN_ON(system_state != SYSTEM_BOOTING); + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (!prev_map[i]) { + slot = i; + break; + } + } + + if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n", + __func__, (u64)phys_addr, size)) + return NULL; + + /* Don't allow wraparound or zero size */ + last_addr = phys_addr + size - 1; + if (WARN_ON(!size || last_addr < phys_addr)) + return NULL; + + prev_size[slot] = size; + /* + * Mappings have to be page-aligned + */ + offset = phys_addr & ~PAGE_MASK; + phys_addr &= PAGE_MASK; + size = PAGE_ALIGN(last_addr + 1) - phys_addr; + + /* + * Mappings have to fit in the FIX_BTMAP area. + */ + nrpages = size >> PAGE_SHIFT; + if (WARN_ON(nrpages > NR_FIX_BTMAPS)) + return NULL; + + /* + * Ok, go for it.. + */ + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; + while (nrpages > 0) { + if (after_paging_init) + __late_set_fixmap(idx, phys_addr, prot); + else + __early_set_fixmap(idx, phys_addr, prot); + phys_addr += PAGE_SIZE; + --idx; + --nrpages; + } + WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n", + __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]); + + prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]); + return prev_map[slot]; +} + +void __init early_iounmap(void __iomem *addr, unsigned long size) +{ + unsigned long virt_addr; + unsigned long offset; + unsigned int nrpages; + enum fixed_addresses idx; + int i, slot; + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (prev_map[i] == addr) { + slot = i; + break; + } + } + + if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n", + addr, size)) + return; + + if (WARN(prev_size[slot] != size, + "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n", + addr, size, slot, prev_size[slot])) + return; + + WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n", + addr, size, slot); + + virt_addr = (unsigned long)addr; + if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN))) + return; + + offset = virt_addr & ~PAGE_MASK; + nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT; + + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; + while (nrpages > 0) { + if (after_paging_init) + __late_clear_fixmap(idx); + else + __early_set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR); + --idx; + --nrpages; + } + prev_map[slot] = NULL; +} + +/* Remap an IO device */ +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) +{ + return __early_ioremap(phys_addr, size, FIXMAP_PAGE_IO); +} + +/* Remap memory */ +void __init * +early_memremap(resource_size_t phys_addr, unsigned long size) +{ + return (__force void *)__early_ioremap(phys_addr, size, + FIXMAP_PAGE_NORMAL); +} +#else /* CONFIG_MMU */ + +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) +{ + return (__force void __iomem *)phys_addr; +} + +/* Remap memory */ +void __init * +early_memremap(resource_size_t phys_addr, unsigned long size) +{ + return (void *)phys_addr; +} + +void __init early_iounmap(void __iomem *addr, unsigned long size) +{ +} + +#endif /* CONFIG_MMU */ + + +void __init early_memunmap(void *addr, unsigned long size) +{ + early_iounmap((__force void __iomem *)addr, size); +} diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ef00c57fe6bb..b4b6aef562fa 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3094,6 +3094,29 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) return 0; } +char *memcg_create_cache_name(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) +{ + static char *buf = NULL; + + /* + * We need a mutex here to protect the shared buffer. Since this is + * expected to be called only on cache creation, we can employ the + * slab_mutex for that purpose. + */ + lockdep_assert_held(&slab_mutex); + + if (!buf) { + buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!buf) + return NULL; + } + + cgroup_name(memcg->css.cgroup, buf, NAME_MAX + 1); + return kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, + memcg_cache_id(memcg), buf); +} + int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache) { @@ -3117,6 +3140,7 @@ int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, s->memcg_params->root_cache = root_cache; INIT_WORK(&s->memcg_params->destroy, kmem_cache_destroy_work_func); + css_get(&memcg->css); } else s->memcg_params->is_root_cache = true; @@ -3125,6 +3149,10 @@ int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, void memcg_free_cache_params(struct kmem_cache *s) { + if (!s->memcg_params) + return; + if (!s->memcg_params->is_root_cache) + css_put(&s->memcg_params->memcg->css); kfree(s->memcg_params); } @@ -3147,9 +3175,6 @@ void memcg_register_cache(struct kmem_cache *s) memcg = s->memcg_params->memcg; id = memcg_cache_id(memcg); - css_get(&memcg->css); - - /* * Since readers won't lock (see cache_from_memcg_idx()), we need a * barrier here to ensure nobody will see the kmem_cache partially @@ -3198,10 +3223,8 @@ void memcg_unregister_cache(struct kmem_cache *s) * after removing it from the memcg_slab_caches list, otherwise we can * fail to convert memcg_params_to_cache() while traversing the list. */ - VM_BUG_ON(!root->memcg_params->memcg_caches[id]); + VM_BUG_ON(root->memcg_params->memcg_caches[id] != s); root->memcg_params->memcg_caches[id] = NULL; - - css_put(&memcg->css); } /* @@ -3298,55 +3321,10 @@ void mem_cgroup_destroy_cache(struct kmem_cache *cachep) schedule_work(&cachep->memcg_params->destroy); } -static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *s) -{ - struct kmem_cache *new = NULL; - static char *tmp_path = NULL, *tmp_name = NULL; - static DEFINE_MUTEX(mutex); /* protects tmp_name */ - - BUG_ON(!memcg_can_account_kmem(memcg)); - - mutex_lock(&mutex); - /* - * kmem_cache_create_memcg duplicates the given name and - * cgroup_name for this name requires RCU context. - * This static temporary buffer is used to prevent from - * pointless shortliving allocation. - */ - if (!tmp_path || !tmp_name) { - if (!tmp_path) - tmp_path = kmalloc(PATH_MAX, GFP_KERNEL); - if (!tmp_name) - tmp_name = kmalloc(NAME_MAX + 1, GFP_KERNEL); - if (!tmp_path || !tmp_name) - goto out; - } - - cgroup_name(memcg->css.cgroup, tmp_name, NAME_MAX + 1); - snprintf(tmp_path, PATH_MAX, "%s(%d:%s)", s->name, - memcg_cache_id(memcg), tmp_name); - - new = kmem_cache_create_memcg(memcg, tmp_path, s->object_size, s->align, - (s->flags & ~SLAB_PANIC), s->ctor, s); - if (new) - new->allocflags |= __GFP_KMEMCG; - else - new = s; -out: - mutex_unlock(&mutex); - return new; -} - -void kmem_cache_destroy_memcg_children(struct kmem_cache *s) +int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) { struct kmem_cache *c; - int i; - - if (!s->memcg_params) - return; - if (!s->memcg_params->is_root_cache) - return; + int i, failed = 0; /* * If the cache is being destroyed, we trust that there is no one else @@ -3380,16 +3358,14 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s) c->memcg_params->dead = false; cancel_work_sync(&c->memcg_params->destroy); kmem_cache_destroy(c); + + if (cache_from_memcg_idx(s, i)) + failed++; } mutex_unlock(&activate_kmem_mutex); + return failed; } -struct create_work { - struct mem_cgroup *memcg; - struct kmem_cache *cachep; - struct work_struct work; -}; - static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) { struct kmem_cache *cachep; @@ -3407,13 +3383,20 @@ static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) mutex_unlock(&memcg->slab_caches_mutex); } +struct create_work { + struct mem_cgroup *memcg; + struct kmem_cache *cachep; + struct work_struct work; +}; + static void memcg_create_cache_work_func(struct work_struct *w) { - struct create_work *cw; + struct create_work *cw = container_of(w, struct create_work, work); + struct mem_cgroup *memcg = cw->memcg; + struct kmem_cache *cachep = cw->cachep; - cw = container_of(w, struct create_work, work); - memcg_create_kmem_cache(cw->memcg, cw->cachep); - css_put(&cw->memcg->css); + kmem_cache_create_memcg(memcg, cachep); + css_put(&memcg->css); kfree(cw); } diff --git a/mm/slab.h b/mm/slab.h index 8184a7cde272..3045316b7c9d 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -55,12 +55,12 @@ extern void create_boot_cache(struct kmem_cache *, const char *name, struct mem_cgroup; #ifdef CONFIG_SLUB struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)); +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)); #else static inline struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)) +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { return NULL; } #endif @@ -119,13 +119,6 @@ static inline bool is_root_cache(struct kmem_cache *s) return !s->memcg_params || s->memcg_params->is_root_cache; } -static inline bool cache_match_memcg(struct kmem_cache *cachep, - struct mem_cgroup *memcg) -{ - return (is_root_cache(cachep) && !memcg) || - (cachep->memcg_params->memcg == memcg); -} - static inline void memcg_bind_pages(struct kmem_cache *s, int order) { if (!is_root_cache(s)) @@ -204,12 +197,6 @@ static inline bool is_root_cache(struct kmem_cache *s) return true; } -static inline bool cache_match_memcg(struct kmem_cache *cachep, - struct mem_cgroup *memcg) -{ - return true; -} - static inline void memcg_bind_pages(struct kmem_cache *s, int order) { } diff --git a/mm/slab_common.c b/mm/slab_common.c index 1ec3c619ba04..f3cfccf76dda 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -29,8 +29,7 @@ DEFINE_MUTEX(slab_mutex); struct kmem_cache *kmem_cache; #ifdef CONFIG_DEBUG_VM -static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, - size_t size) +static int kmem_cache_sanity_check(const char *name, size_t size) { struct kmem_cache *s = NULL; @@ -57,13 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, } #if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON) - /* - * For simplicity, we won't check this in the list of memcg - * caches. We have control over memcg naming, and if there - * aren't duplicates in the global list, there won't be any - * duplicates in the memcg lists as well. - */ - if (!memcg && !strcmp(s->name, name)) { + if (!strcmp(s->name, name)) { pr_err("%s (%s): Cache name already exists.\n", __func__, name); dump_stack(); @@ -77,8 +70,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, return 0; } #else -static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg, - const char *name, size_t size) +static inline int kmem_cache_sanity_check(const char *name, size_t size) { return 0; } @@ -139,6 +131,46 @@ unsigned long calculate_alignment(unsigned long flags, return ALIGN(align, sizeof(void *)); } +static struct kmem_cache * +do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *), + struct mem_cgroup *memcg, struct kmem_cache *root_cache) +{ + struct kmem_cache *s; + int err; + + err = -ENOMEM; + s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); + if (!s) + goto out; + + s->name = name; + s->object_size = object_size; + s->size = size; + s->align = align; + s->ctor = ctor; + + err = memcg_alloc_cache_params(memcg, s, root_cache); + if (err) + goto out_free_cache; + + err = __kmem_cache_create(s, flags); + if (err) + goto out_free_cache; + + s->refcount = 1; + list_add(&s->list, &slab_caches); + memcg_register_cache(s); +out: + if (err) + return ERR_PTR(err); + return s; + +out_free_cache: + memcg_free_cache_params(s); + kfree(s); + goto out; +} /* * kmem_cache_create - Create a cache. @@ -164,34 +196,21 @@ unsigned long calculate_alignment(unsigned long flags, * cacheline. This can be beneficial if you're counting cycles as closely * as davem. */ - struct kmem_cache * -kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *), - struct kmem_cache *parent_cache) +kmem_cache_create(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { - struct kmem_cache *s = NULL; + struct kmem_cache *s; + char *cache_name; int err; get_online_cpus(); mutex_lock(&slab_mutex); - err = kmem_cache_sanity_check(memcg, name, size); + err = kmem_cache_sanity_check(name, size); if (err) goto out_unlock; - if (memcg) { - /* - * Since per-memcg caches are created asynchronously on first - * allocation (see memcg_kmem_get_cache()), several threads can - * try to create the same cache, but only one of them may - * succeed. Therefore if we get here and see the cache has - * already been created, we silently return NULL. - */ - if (cache_from_memcg_idx(parent_cache, memcg_cache_id(memcg))) - goto out_unlock; - } - /* * Some allocators will constraint the set of valid flags to a subset * of all flags. We expect them to define CACHE_CREATE_MASK in this @@ -200,50 +219,29 @@ kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size, */ flags &= CACHE_CREATE_MASK; - s = __kmem_cache_alias(memcg, name, size, align, flags, ctor); + s = __kmem_cache_alias(name, size, align, flags, ctor); if (s) goto out_unlock; - err = -ENOMEM; - s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); - if (!s) + cache_name = kstrdup(name, GFP_KERNEL); + if (!cache_name) { + err = -ENOMEM; goto out_unlock; + } - s->object_size = s->size = size; - s->align = calculate_alignment(flags, align, size); - s->ctor = ctor; - - s->name = kstrdup(name, GFP_KERNEL); - if (!s->name) - goto out_free_cache; - - err = memcg_alloc_cache_params(memcg, s, parent_cache); - if (err) - goto out_free_cache; - - err = __kmem_cache_create(s, flags); - if (err) - goto out_free_cache; - - s->refcount = 1; - list_add(&s->list, &slab_caches); - memcg_register_cache(s); + s = do_kmem_cache_create(cache_name, size, size, + calculate_alignment(flags, align, size), + flags, ctor, NULL, NULL); + if (IS_ERR(s)) { + err = PTR_ERR(s); + kfree(cache_name); + } out_unlock: mutex_unlock(&slab_mutex); put_online_cpus(); if (err) { - /* - * There is no point in flooding logs with warnings or - * especially crashing the system if we fail to create a cache - * for a memcg. In this case we will be accounting the memcg - * allocation to the root cgroup until we succeed to create its - * own cache, but it isn't that critical. - */ - if (!memcg) - return NULL; - if (flags & SLAB_PANIC) panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n", name, err); @@ -255,52 +253,112 @@ out_unlock: return NULL; } return s; +} +EXPORT_SYMBOL(kmem_cache_create); -out_free_cache: - memcg_free_cache_params(s); - kfree(s->name); - kmem_cache_free(kmem_cache, s); - goto out_unlock; +#ifdef CONFIG_MEMCG_KMEM +/* + * kmem_cache_create_memcg - Create a cache for a memory cgroup. + * @memcg: The memory cgroup the new cache is for. + * @root_cache: The parent of the new cache. + * + * This function attempts to create a kmem cache that will serve allocation + * requests going from @memcg to @root_cache. The new cache inherits properties + * from its parent. + */ +void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_cache) +{ + struct kmem_cache *s; + char *cache_name; + + get_online_cpus(); + mutex_lock(&slab_mutex); + + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (cache_from_memcg_idx(root_cache, memcg_cache_id(memcg))) + goto out_unlock; + + cache_name = memcg_create_cache_name(memcg, root_cache); + if (!cache_name) + goto out_unlock; + + s = do_kmem_cache_create(cache_name, root_cache->object_size, + root_cache->size, root_cache->align, + root_cache->flags, root_cache->ctor, + memcg, root_cache); + if (IS_ERR(s)) { + kfree(cache_name); + goto out_unlock; + } + + s->allocflags |= __GFP_KMEMCG; + +out_unlock: + mutex_unlock(&slab_mutex); + put_online_cpus(); } -struct kmem_cache * -kmem_cache_create(const char *name, size_t size, size_t align, - unsigned long flags, void (*ctor)(void *)) +static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) { - return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL); + int rc; + + if (!s->memcg_params || + !s->memcg_params->is_root_cache) + return 0; + + mutex_unlock(&slab_mutex); + rc = __kmem_cache_destroy_memcg_children(s); + mutex_lock(&slab_mutex); + + return rc; } -EXPORT_SYMBOL(kmem_cache_create); +#else +static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) +{ + return 0; +} +#endif /* CONFIG_MEMCG_KMEM */ void kmem_cache_destroy(struct kmem_cache *s) { - /* Destroy all the children caches if we aren't a memcg cache */ - kmem_cache_destroy_memcg_children(s); - get_online_cpus(); mutex_lock(&slab_mutex); + s->refcount--; - if (!s->refcount) { - list_del(&s->list); - - if (!__kmem_cache_shutdown(s)) { - memcg_unregister_cache(s); - mutex_unlock(&slab_mutex); - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); - - memcg_free_cache_params(s); - kfree(s->name); - kmem_cache_free(kmem_cache, s); - } else { - list_add(&s->list, &slab_caches); - mutex_unlock(&slab_mutex); - printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n", - s->name); - dump_stack(); - } - } else { - mutex_unlock(&slab_mutex); + if (s->refcount) + goto out_unlock; + + if (kmem_cache_destroy_memcg_children(s) != 0) + goto out_unlock; + + list_del(&s->list); + memcg_unregister_cache(s); + + if (__kmem_cache_shutdown(s) != 0) { + list_add(&s->list, &slab_caches); + memcg_register_cache(s); + printk(KERN_ERR "kmem_cache_destroy %s: " + "Slab cache still has objects\n", s->name); + dump_stack(); + goto out_unlock; } + + mutex_unlock(&slab_mutex); + if (s->flags & SLAB_DESTROY_BY_RCU) + rcu_barrier(); + + memcg_free_cache_params(s); + kfree(s->name); + kmem_cache_free(kmem_cache, s); + goto out_put_cpus; + +out_unlock: + mutex_unlock(&slab_mutex); +out_put_cpus: put_online_cpus(); } EXPORT_SYMBOL(kmem_cache_destroy); diff --git a/mm/slub.c b/mm/slub.c index 93a5bd096ac7..5e234f1f8853 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -224,7 +224,11 @@ static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { } static inline void stat(const struct kmem_cache *s, enum stat_item si) { #ifdef CONFIG_SLUB_STATS - __this_cpu_inc(s->cpu_slab->stat[si]); + /* + * The rmw is racy on a preemptible kernel but this is acceptable, so + * avoid this_cpu_add()'s irq-disable overhead. + */ + raw_cpu_inc(s->cpu_slab->stat[si]); #endif } @@ -3686,6 +3690,9 @@ static int slab_unmergeable(struct kmem_cache *s) if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE)) return 1; + if (!is_root_cache(s)) + return 1; + if (s->ctor) return 1; @@ -3698,9 +3705,8 @@ static int slab_unmergeable(struct kmem_cache *s) return 0; } -static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, - size_t align, unsigned long flags, const char *name, - void (*ctor)(void *)) +static struct kmem_cache *find_mergeable(size_t size, size_t align, + unsigned long flags, const char *name, void (*ctor)(void *)) { struct kmem_cache *s; @@ -3723,7 +3729,7 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, continue; if ((flags & SLUB_MERGE_SAME) != (s->flags & SLUB_MERGE_SAME)) - continue; + continue; /* * Check if alignment is compatible. * Courtesy of Adrian Drzewiecki @@ -3734,23 +3740,24 @@ static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size, if (s->size - size >= sizeof(void *)) continue; - if (!cache_match_memcg(s, memcg)) - continue; - return s; } return NULL; } struct kmem_cache * -__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, - size_t align, unsigned long flags, void (*ctor)(void *)) +__kmem_cache_alias(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *s; - s = find_mergeable(memcg, size, align, flags, name, ctor); + s = find_mergeable(size, align, flags, name, ctor); if (s) { + int i; + struct kmem_cache *c; + s->refcount++; + /* * Adjust the object sizes so that we clear * the complete object on kzalloc. @@ -3758,6 +3765,15 @@ __kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size, s->object_size = max(s->object_size, (int)size); s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *))); + for_each_memcg_cache_index(i) { + c = cache_from_memcg_idx(s, i); + if (!c) + continue; + c->object_size = s->object_size; + c->inuse = max_t(int, c->inuse, + ALIGN(size, sizeof(void *))); + } + if (sysfs_slab_alias(s, name)) { s->refcount--; s = NULL; @@ -5127,6 +5143,15 @@ static const struct kset_uevent_ops slab_uevent_ops = { static struct kset *slab_kset; +static inline struct kset *cache_kset(struct kmem_cache *s) +{ +#ifdef CONFIG_MEMCG_KMEM + if (!is_root_cache(s)) + return s->memcg_params->root_cache->memcg_kset; +#endif + return slab_kset; +} + #define ID_STR_LENGTH 64 /* Create a unique string id for a slab cache: @@ -5192,26 +5217,39 @@ static int sysfs_slab_add(struct kmem_cache *s) name = create_unique_id(s); } - s->kobj.kset = slab_kset; + s->kobj.kset = cache_kset(s); err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); - if (err) { - kobject_put(&s->kobj); - return err; - } + if (err) + goto out_put_kobj; err = sysfs_create_group(&s->kobj, &slab_attr_group); - if (err) { - kobject_del(&s->kobj); - kobject_put(&s->kobj); - return err; + if (err) + goto out_del_kobj; + +#ifdef CONFIG_MEMCG_KMEM + if (is_root_cache(s)) { + s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj); + if (!s->memcg_kset) { + err = -ENOMEM; + goto out_del_kobj; + } } +#endif + kobject_uevent(&s->kobj, KOBJ_ADD); if (!unmergeable) { /* Setup first alias */ sysfs_slab_alias(s, s->name); - kfree(name); } - return 0; +out: + if (!unmergeable) + kfree(name); + return err; +out_del_kobj: + kobject_del(&s->kobj); +out_put_kobj: + kobject_put(&s->kobj); + goto out; } static void sysfs_slab_remove(struct kmem_cache *s) @@ -5223,6 +5261,9 @@ static void sysfs_slab_remove(struct kmem_cache *s) */ return; +#ifdef CONFIG_MEMCG_KMEM + kset_unregister(s->memcg_kset); +#endif kobject_uevent(&s->kobj, KOBJ_REMOVE); kobject_del(&s->kobj); kobject_put(&s->kobj); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1be9e990514d..34d094cadb11 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -188,7 +188,7 @@ const __u8 ip_tos2prio[16] = { EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); -#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field) +#define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig index affa13480659..0216475fc759 100644 --- a/sound/isa/Kconfig +++ b/sound/isa/Kconfig @@ -191,7 +191,7 @@ config SND_ES18XX config SND_SC6000 tristate "Gallant SC-6000/6600/7000 and Audio Excel DSP 16" - depends on HAS_IOPORT + depends on HAS_IOPORT_MAP select SND_WSS_LIB select SND_OPL3_LIB select SND_MPU401_UART diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig index 0b0c0cf13f74..3a3a3a71088b 100644 --- a/sound/pci/Kconfig +++ b/sound/pci/Kconfig @@ -688,7 +688,7 @@ config SND_LOLA config SND_LX6464ES tristate "Digigram LX6464ES" - depends on HAS_IOPORT + depends on HAS_IOPORT_MAP select SND_PCM help Say Y here to include support for Digigram LX6464ES boards. |