diff options
536 files changed, 8519 insertions, 6055 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-watchdog b/Documentation/ABI/testing/sysfs-class-watchdog index 6317ade5ad19..675f9b537661 100644 --- a/Documentation/ABI/testing/sysfs-class-watchdog +++ b/Documentation/ABI/testing/sysfs-class-watchdog @@ -72,3 +72,37 @@ Description: It is a read/write file. When read, the currently assigned pretimeout governor is returned. When written, it sets the pretimeout governor. + +What: /sys/class/watchdog/watchdog1/access_cs0 +Date: August 2019 +Contact: Ivan Mikhaylov <i.mikhaylov@yadro.com>, + Alexander Amelkin <a.amelkin@yadro.com> +Description: + It is a read/write file. This attribute exists only if the + system has booted from the alternate flash chip due to + expiration of a watchdog timer of AST2400/AST2500 when + alternate boot function was enabled with 'aspeed,alt-boot' + devicetree option for that watchdog or with an appropriate + h/w strapping (for WDT2 only). + + At alternate flash the 'access_cs0' sysfs node provides: + ast2400: a way to get access to the primary SPI flash + chip at CS0 after booting from the alternate + chip at CS1. + ast2500: a way to restore the normal address mapping + from (CS0->CS1, CS1->CS0) to (CS0->CS0, + CS1->CS1). + + Clearing the boot code selection and timeout counter also + resets to the initial state the chip select line mapping. When + the SoC is in normal mapping state (i.e. booted from CS0), + clearing those bits does nothing for both versions of the SoC. + For alternate boot mode (booted from CS1 due to wdt2 + expiration) the behavior differs as described above. + + This option can be used with wdt2 (watchdog1) only. + + When read, the current status of the boot code selection is + shown. When written with any non-zero value, it clears + the boot code selection and the timeout counter, which results + in chipselect reset for AST2400/AST2500. diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 08af5caf036d..f77de49b1d51 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -42,6 +42,9 @@ String Manipulation .. kernel-doc:: lib/string.c :export: +.. kernel-doc:: include/linux/string.h + :internal: + .. kernel-doc:: mm/util.c :functions: kstrdup kstrdup_const kstrndup kmemdup kmemdup_nul memdup_user vmemdup_user strndup_user memdup_user_nul diff --git a/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt b/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt index 04cbb90a5d3e..28f2cbaf1702 100644 --- a/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt +++ b/Documentation/devicetree/bindings/thermal/qoriq-thermal.txt @@ -23,6 +23,7 @@ Required properties: Optional property: - little-endian : If present, the TMU registers are little endian. If absent, the default is big endian. +- clocks : the clock for clocking the TMU silicon. Example: diff --git a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml new file mode 100644 index 000000000000..3a54f58683a0 --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/watchdog/allwinner,sun4i-a10-wdt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Allwinner A10 Watchdog Device Tree Bindings + +allOf: + - $ref: "watchdog.yaml#" + +maintainers: + - Chen-Yu Tsai <wens@csie.org> + - Maxime Ripard <maxime.ripard@bootlin.com> + +properties: + compatible: + oneOf: + - const: allwinner,sun4i-a10-wdt + - const: allwinner,sun6i-a31-wdt + - items: + - const: allwinner,sun50i-a64-wdt + - const: allwinner,sun6i-a31-wdt + - items: + - const: allwinner,sun50i-h6-wdt + - const: allwinner,sun6i-a31-wdt + - items: + - const: allwinner,suniv-f1c100s-wdt + - const: allwinner,sun4i-a10-wdt + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - clocks + - interrupts + +unevaluatedProperties: false + +examples: + - | + wdt: watchdog@1c20c90 { + compatible = "allwinner,sun4i-a10-wdt"; + reg = <0x01c20c90 0x10>; + interrupts = <24>; + clocks = <&osc24M>; + timeout-sec = <10>; + }; + +... diff --git a/Documentation/devicetree/bindings/watchdog/aspeed-wdt.txt b/Documentation/devicetree/bindings/watchdog/aspeed-wdt.txt index c5077a1f5cb3..d78d4a8fb868 100644 --- a/Documentation/devicetree/bindings/watchdog/aspeed-wdt.txt +++ b/Documentation/devicetree/bindings/watchdog/aspeed-wdt.txt @@ -4,6 +4,7 @@ Required properties: - compatible: must be one of: - "aspeed,ast2400-wdt" - "aspeed,ast2500-wdt" + - "aspeed,ast2600-wdt" - reg: physical base address of the controller and length of memory mapped region diff --git a/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.txt b/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.txt new file mode 100644 index 000000000000..f902508d6cac --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.txt @@ -0,0 +1,22 @@ +* Freescale i.MX7ULP Watchdog Timer (WDT) Controller + +Required properties: +- compatible : Should be "fsl,imx7ulp-wdt" +- reg : Should contain WDT registers location and length +- interrupts : Should contain WDT interrupt +- clocks: Should contain a phandle pointing to the gated peripheral clock. + +Optional properties: +- timeout-sec : Contains the watchdog timeout in seconds + +Examples: + +wdog1: watchdog@403d0000 { + compatible = "fsl,imx7ulp-wdt"; + reg = <0x403d0000 0x10000>; + interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&pcc2 IMX7ULP_CLK_WDG1>; + assigned-clocks = <&pcc2 IMX7ULP_CLK_WDG1>; + assigned-clocks-parents = <&scg1 IMX7ULP_CLK_FIRC_BUS_CLK>; + timeout-sec = <40>; +}; diff --git a/Documentation/devicetree/bindings/watchdog/sunxi-wdt.txt b/Documentation/devicetree/bindings/watchdog/sunxi-wdt.txt deleted file mode 100644 index e65198d82a2b..000000000000 --- a/Documentation/devicetree/bindings/watchdog/sunxi-wdt.txt +++ /dev/null @@ -1,22 +0,0 @@ -Allwinner SoCs Watchdog timer - -Required properties: - -- compatible : should be one of - "allwinner,sun4i-a10-wdt" - "allwinner,sun6i-a31-wdt" - "allwinner,sun50i-a64-wdt","allwinner,sun6i-a31-wdt" - "allwinner,sun50i-h6-wdt","allwinner,sun6i-a31-wdt" - "allwinner,suniv-f1c100s-wdt", "allwinner,sun4i-a10-wdt" -- reg : Specifies base physical address and size of the registers. - -Optional properties: -- timeout-sec : Contains the watchdog timeout in seconds - -Example: - -wdt: watchdog@1c20c90 { - compatible = "allwinner,sun4i-a10-wdt"; - reg = <0x01c20c90 0x10>; - timeout-sec = <10>; -}; diff --git a/Documentation/devicetree/bindings/watchdog/watchdog.yaml b/Documentation/devicetree/bindings/watchdog/watchdog.yaml new file mode 100644 index 000000000000..187bf6cb62bf --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/watchdog.yaml @@ -0,0 +1,26 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/watchdog/watchdog.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Watchdog Generic Bindings + +maintainers: + - Guenter Roeck <linux@roeck-us.net> + - Wim Van Sebroeck <wim@linux-watchdog.org> + +description: | + This document describes generic bindings which can be used to + describe watchdog devices in a device tree. + +properties: + $nodename: + pattern: "^watchdog(@.*|-[0-9a-f])?$" + + timeout-sec: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Contains the watchdog timeout in seconds. + +... diff --git a/Documentation/vm/split_page_table_lock.rst b/Documentation/vm/split_page_table_lock.rst index 889b00be469f..ff51f4a5494d 100644 --- a/Documentation/vm/split_page_table_lock.rst +++ b/Documentation/vm/split_page_table_lock.rst @@ -54,9 +54,9 @@ Hugetlb-specific helpers: Support of split page table lock by an architecture =================================================== -There's no need in special enabling of PTE split page table lock: -everything required is done by pgtable_page_ctor() and pgtable_page_dtor(), -which must be called on PTE table allocation / freeing. +There's no need in special enabling of PTE split page table lock: everything +required is done by pgtable_pte_page_ctor() and pgtable_pte_page_dtor(), which +must be called on PTE table allocation / freeing. Make sure the architecture doesn't use slab allocator for page table allocation: slab uses page->slab_cache for its pages. @@ -74,7 +74,7 @@ paths: i.e X86_PAE preallocate few PMDs on pgd_alloc(). With everything in place you can set CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK. -NOTE: pgtable_page_ctor() and pgtable_pmd_page_ctor() can fail -- it must +NOTE: pgtable_pte_page_ctor() and pgtable_pmd_page_ctor() can fail -- it must be handled properly. page->ptl @@ -94,7 +94,7 @@ trick: split lock with enabled DEBUG_SPINLOCK or DEBUG_LOCK_ALLOC, but costs one more cache line for indirect access; -The spinlock_t allocated in pgtable_page_ctor() for PTE table and in +The spinlock_t allocated in pgtable_pte_page_ctor() for PTE table and in pgtable_pmd_page_ctor() for PMD table. Please, never access page->ptl directly -- use appropriate helper. diff --git a/Documentation/watchdog/watchdog-parameters.rst b/Documentation/watchdog/watchdog-parameters.rst index a3985cc5aeda..223c99361a30 100644 --- a/Documentation/watchdog/watchdog-parameters.rst +++ b/Documentation/watchdog/watchdog-parameters.rst @@ -301,15 +301,6 @@ ixp4xx_wdt: ------------------------------------------------- -ks8695_wdt: - wdt_time: - Watchdog time in seconds. (default=5) - nowayout: - Watchdog cannot be stopped once started - (default=kernel config parameter) - -------------------------------------------------- - machzwd: nowayout: Watchdog cannot be stopped once started @@ -375,16 +366,6 @@ nic7018_wdt: ------------------------------------------------- -nuc900_wdt: - heartbeat: - Watchdog heartbeats in seconds. - (default = 15) - nowayout: - Watchdog cannot be stopped once started - (default=kernel config parameter) - -------------------------------------------------- - omap_wdt: timer_margin: initial watchdog timeout (in seconds) diff --git a/MAINTAINERS b/MAINTAINERS index a97f1be63b9d..ee3971d8d335 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9060,6 +9060,7 @@ F: include/keys/trusted.h KEYS/KEYRINGS: M: David Howells <dhowells@redhat.com> +M: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com> L: keyrings@vger.kernel.org S: Maintained F: Documentation/security/keys/core.rst @@ -16071,6 +16072,7 @@ THERMAL M: Zhang Rui <rui.zhang@intel.com> M: Eduardo Valentin <edubezval@gmail.com> R: Daniel Lezcano <daniel.lezcano@linaro.org> +R: Amit Kucheria <amit.kucheria@verdurent.com> L: linux-pm@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index ac23379b7a87..a18ec7f63888 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -68,6 +68,9 @@ #define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ #define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ +#define MADV_COLD 20 /* deactivate these pages */ +#define MADV_PAGEOUT 21 /* reclaim these pages */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index 4751f2251cd9..b747f2ec2928 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -108,7 +108,7 @@ pte_alloc_one(struct mm_struct *mm) return 0; memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t)); page = virt_to_page(pte_pg); - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { __free_page(page); return 0; } @@ -123,7 +123,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline void pte_free(struct mm_struct *mm, pgtable_t ptep) { - pgtable_page_dtor(virt_to_page(ptep)); + pgtable_pte_page_dtor(virt_to_page(ptep)); free_pages((unsigned long)ptep, __get_order_pte()); } diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index b75ea15b85c0..669474add486 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -44,7 +44,7 @@ static inline void __tlb_remove_table(void *_table) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - pgtable_page_dtor(pte); + pgtable_pte_page_dtor(pte); #ifndef CONFIG_ARM_LPAE /* diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 25da9b2d9610..48c2888297dd 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -731,7 +731,7 @@ static void *__init late_alloc(unsigned long sz) { void *ptr = (void *)__get_free_pages(GFP_PGTABLE_KERNEL, get_order(sz)); - if (!ptr || !pgtable_page_ctor(virt_to_page(ptr))) + if (!ptr || !pgtable_pte_page_ctor(virt_to_page(ptr))) BUG(); return ptr; } diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index a95d1fcb7e21..b76df828e6b7 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -44,7 +44,7 @@ static inline void tlb_flush(struct mmu_gather *tlb) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - pgtable_page_dtor(pte); + pgtable_pte_page_dtor(pte); tlb_remove_table(tlb, pte); } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 53dc6f24cfb7..60c929f3683b 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -384,7 +384,7 @@ static phys_addr_t pgd_pgtable_alloc(int shift) * folded, and if so pgtable_pmd_page_ctor() becomes nop. */ if (shift == PAGE_SHIFT) - BUG_ON(!pgtable_page_ctor(phys_to_page(pa))); + BUG_ON(!pgtable_pte_page_ctor(phys_to_page(pa))); else if (shift == PMD_SHIFT) BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa))); diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index d089113fe41f..c7c1ed27e348 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -71,7 +71,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) #define __pte_free_tlb(tlb, pte, address) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page(tlb, pte); \ } while (0) diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h index 5a6e79e7926d..cc9be514a676 100644 --- a/arch/hexagon/include/asm/pgalloc.h +++ b/arch/hexagon/include/asm/pgalloc.h @@ -94,7 +94,7 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pgtable_page_dtor((pte)); \ + pgtable_pte_page_dtor((pte)); \ tlb_remove_page((tlb), (pte)); \ } while (0) diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index f1f6ebd537b7..c961773a6fff 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -71,19 +71,6 @@ void __init mem_init(void) init_mm.context.ptbase = __pa(init_mm.pgd); } -/* - * free_initrd_mem - frees... initrd memory. - * @start - start of init memory - * @end - end of init memory - * - * Apparently has to be passed the address of the initrd memory. - * - * Wrapped by #ifdef CONFIG_BLKDEV_INITRD - */ -void free_initrd_mem(unsigned long start, unsigned long end) -{ -} - void sync_icache_dcache(pte_t pte) { unsigned long addr; diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index 4399d712f6db..b34d44d666a4 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -41,7 +41,7 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page, unsigned long address) { - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); } @@ -54,7 +54,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm) if (!page) return NULL; - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { __free_page(page); return NULL; } @@ -73,7 +73,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm) static inline void pte_free(struct mm_struct *mm, struct page *page) { - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); } diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h index d04d9ba9b976..acab315c851f 100644 --- a/arch/m68k/include/asm/motorola_pgalloc.h +++ b/arch/m68k/include/asm/motorola_pgalloc.h @@ -36,7 +36,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0); if(!page) return NULL; - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { __free_page(page); return NULL; } @@ -51,7 +51,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) static inline void pte_free(struct mm_struct *mm, pgtable_t page) { - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); cache_page(kmap(page)); kunmap(page); __free_page(page); @@ -60,7 +60,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t page) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page, unsigned long address) { - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); cache_page(kmap(page)); kunmap(page); __free_page(page); diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 1a8ddbd0d23c..856121122b91 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -21,7 +21,7 @@ extern const char bad_pmd_string[]; #define __pte_free_tlb(tlb,pte,addr) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page((tlb), pte); \ } while (0) diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index aa73cb187a07..166842337eb2 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -54,7 +54,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) #define __pte_free_tlb(tlb,pte,address) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page((tlb), pte); \ } while (0) diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index c2b40969eb1f..57dc2ac4f8bd 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -95,6 +95,9 @@ #define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ #define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ +#define MADV_COLD 20 /* deactivate these pages */ +#define MADV_PAGEOUT 21 /* reclaim these pages */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index 750d18d5980b..0b146d773c85 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -41,7 +41,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page((tlb), (pte)); \ } while (0) diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index 787c1b9d2f6d..da12a4c38c4b 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -75,7 +75,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm) if (!pte) return NULL; clear_page(page_address(pte)); - if (!pgtable_page_ctor(pte)) { + if (!pgtable_pte_page_ctor(pte)) { __free_page(pte); return NULL; } @@ -89,13 +89,13 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline void pte_free(struct mm_struct *mm, struct page *pte) { - pgtable_page_dtor(pte); + pgtable_pte_page_dtor(pte); __free_page(pte); } #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page((tlb), (pte)); \ } while (0) diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index c98162f494db..6fd8871e4081 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -48,6 +48,9 @@ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ +#define MADV_COLD 20 /* deactivate these pages */ +#define MADV_PAGEOUT 21 /* reclaim these pages */ + #define MADV_MERGEABLE 65 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c index a7b05214760c..ee4bd6d38602 100644 --- a/arch/powerpc/mm/pgtable-frag.c +++ b/arch/powerpc/mm/pgtable-frag.c @@ -25,7 +25,7 @@ void pte_frag_destroy(void *pte_frag) count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); } } @@ -61,7 +61,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); if (!page) return NULL; - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { __free_page(page); return NULL; } @@ -113,7 +113,7 @@ void pte_fragment_free(unsigned long *table, int kernel) BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); if (atomic_dec_and_test(&page->pt_frag_refcount)) { if (!kernel) - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); } } diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index f66a00d8cb19..d59ea92285ec 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -78,7 +78,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) #define __pte_free_tlb(tlb, pte, buf) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page((tlb), pte); \ } while (0) diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index ae3e3221d4b5..ceeb552d3472 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -70,7 +70,7 @@ struct hws_qsi_info_block { /* Bit(s) */ unsigned long tear; /* 24-31: TEAR contents */ unsigned long dear; /* 32-39: DEAR contents */ unsigned int rsvrd0; /* 40-43: reserved */ - unsigned int cpu_speed; /* 44-47: CPU speed */ + unsigned int cpu_speed; /* 44-47: CPU speed */ unsigned long long rsvrd1; /* 48-55: reserved */ unsigned long long rsvrd2; /* 56-63: reserved */ } __packed; @@ -89,10 +89,10 @@ struct hws_lsctl_request_block { unsigned long tear; /* 16-23: TEAR contents */ unsigned long dear; /* 24-31: DEAR contents */ /* 32-63: */ - unsigned long rsvrd1; /* reserved */ - unsigned long rsvrd2; /* reserved */ - unsigned long rsvrd3; /* reserved */ - unsigned long rsvrd4; /* reserved */ + unsigned long rsvrd1; /* reserved */ + unsigned long rsvrd2; /* reserved */ + unsigned long rsvrd3; /* reserved */ + unsigned long rsvrd4; /* reserved */ } __packed; struct hws_basic_entry { diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index 560d8f766ddf..4652ffffe0b2 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -60,6 +60,7 @@ struct perf_sf_sde_regs { #define PERF_CPUM_SF_MODE_MASK (PERF_CPUM_SF_BASIC_MODE| \ PERF_CPUM_SF_DIAG_MODE) #define PERF_CPUM_SF_FULL_BLOCKS 0x0004 /* Process full SDBs only */ +#define PERF_CPUM_SF_FREQ_MODE 0x0008 /* Sampling with frequency */ #define REG_NONE 0 #define REG_OVERFLOW 1 @@ -70,5 +71,6 @@ struct perf_sf_sde_regs { #define SAMPL_FLAGS(hwc) ((hwc)->config_base) #define SAMPL_DIAG_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE) #define SDB_FULL_BLOCKS(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FULL_BLOCKS) +#define SAMPLE_FREQ_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FREQ_MODE) #endif /* _ASM_S390_PERF_EVENT_H */ diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h index 8c5755f41dde..f9e5e1f0821d 100644 --- a/arch/s390/include/uapi/asm/zcrypt.h +++ b/arch/s390/include/uapi/asm/zcrypt.h @@ -4,7 +4,7 @@ * * zcrypt 2.2.1 (user-visible header) * - * Copyright IBM Corp. 2001, 2018 + * Copyright IBM Corp. 2001, 2019 * Author(s): Robert Burroughs * Eric Rossman (edrossma@us.ibm.com) * @@ -286,7 +286,7 @@ struct zcrypt_device_matrix_ext { * 0x08: CEX3A * 0x0a: CEX4 * 0x0b: CEX5 - * 0x0c: CEX6 + * 0x0c: CEX6 and CEX7 * 0x0d: device is disabled * * ZCRYPT_QDEPTH_MASK diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 292a452cd1f3..544a02e944c6 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -673,13 +673,89 @@ out: rcu_read_unlock(); } +static unsigned long getrate(bool freq, unsigned long sample, + struct hws_qsi_info_block *si) +{ + unsigned long rate; + + if (freq) { + rate = freq_to_sample_rate(si, sample); + rate = hw_limit_rate(si, rate); + } else { + /* The min/max sampling rates specifies the valid range + * of sample periods. If the specified sample period is + * out of range, limit the period to the range boundary. + */ + rate = hw_limit_rate(si, sample); + + /* The perf core maintains a maximum sample rate that is + * configurable through the sysctl interface. Ensure the + * sampling rate does not exceed this value. This also helps + * to avoid throttling when pushing samples with + * perf_event_overflow(). + */ + if (sample_rate_to_freq(si, rate) > + sysctl_perf_event_sample_rate) { + debug_sprintf_event(sfdbg, 1, + "Sampling rate exceeds maximum " + "perf sample rate\n"); + rate = 0; + } + } + return rate; +} + +/* The sampling information (si) contains information about the + * min/max sampling intervals and the CPU speed. So calculate the + * correct sampling interval and avoid the whole period adjust + * feedback loop. + * + * Since the CPU Measurement sampling facility can not handle frequency + * calculate the sampling interval when frequency is specified using + * this formula: + * interval := cpu_speed * 1000000 / sample_freq + * + * Returns errno on bad input and zero on success with parameter interval + * set to the correct sampling rate. + * + * Note: This function turns off freq bit to avoid calling function + * perf_adjust_period(). This causes frequency adjustment in the common + * code part which causes tremendous variations in the counter values. + */ +static int __hw_perf_event_init_rate(struct perf_event *event, + struct hws_qsi_info_block *si) +{ + struct perf_event_attr *attr = &event->attr; + struct hw_perf_event *hwc = &event->hw; + unsigned long rate; + + if (attr->freq) { + if (!attr->sample_freq) + return -EINVAL; + rate = getrate(attr->freq, attr->sample_freq, si); + attr->freq = 0; /* Don't call perf_adjust_period() */ + SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FREQ_MODE; + } else { + rate = getrate(attr->freq, attr->sample_period, si); + if (!rate) + return -EINVAL; + } + attr->sample_period = rate; + SAMPL_RATE(hwc) = rate; + hw_init_period(hwc, SAMPL_RATE(hwc)); + debug_sprintf_event(sfdbg, 4, "__hw_perf_event_init_rate:" + "cpu:%d period:%llx freq:%d,%#lx\n", event->cpu, + event->attr.sample_period, event->attr.freq, + SAMPLE_FREQ_MODE(hwc)); + return 0; +} + static int __hw_perf_event_init(struct perf_event *event) { struct cpu_hw_sf *cpuhw; struct hws_qsi_info_block si; struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; - unsigned long rate; int cpu, err; /* Reserve CPU-measurement sampling facility */ @@ -745,43 +821,9 @@ static int __hw_perf_event_init(struct perf_event *event) if (attr->config1 & PERF_CPUM_SF_FULL_BLOCKS) SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FULL_BLOCKS; - /* The sampling information (si) contains information about the - * min/max sampling intervals and the CPU speed. So calculate the - * correct sampling interval and avoid the whole period adjust - * feedback loop. - */ - rate = 0; - if (attr->freq) { - if (!attr->sample_freq) { - err = -EINVAL; - goto out; - } - rate = freq_to_sample_rate(&si, attr->sample_freq); - rate = hw_limit_rate(&si, rate); - attr->freq = 0; - attr->sample_period = rate; - } else { - /* The min/max sampling rates specifies the valid range - * of sample periods. If the specified sample period is - * out of range, limit the period to the range boundary. - */ - rate = hw_limit_rate(&si, hwc->sample_period); - - /* The perf core maintains a maximum sample rate that is - * configurable through the sysctl interface. Ensure the - * sampling rate does not exceed this value. This also helps - * to avoid throttling when pushing samples with - * perf_event_overflow(). - */ - if (sample_rate_to_freq(&si, rate) > - sysctl_perf_event_sample_rate) { - err = -EINVAL; - debug_sprintf_event(sfdbg, 1, "Sampling rate exceeds maximum perf sample rate\n"); - goto out; - } - } - SAMPL_RATE(hwc) = rate; - hw_init_period(hwc, SAMPL_RATE(hwc)); + err = __hw_perf_event_init_rate(event, &si); + if (err) + goto out; /* Initialize sample data overflow accounting */ hwc->extra_reg.reg = REG_OVERFLOW; @@ -904,6 +946,8 @@ static void cpumsf_pmu_enable(struct pmu *pmu) if (sfb_has_pending_allocs(&cpuhw->sfb, hwc)) extend_sampling_buffer(&cpuhw->sfb, hwc); } + /* Rate may be adjusted with ioctl() */ + cpuhw->lsctl.interval = SAMPL_RATE(&cpuhw->event->hw); } /* (Re)enable the PMU and sampling facility */ @@ -922,8 +966,9 @@ static void cpumsf_pmu_enable(struct pmu *pmu) lpp(&S390_lowcore.lpp); debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i " - "tear=%p dear=%p\n", cpuhw->lsctl.es, - cpuhw->lsctl.cs, cpuhw->lsctl.ed, cpuhw->lsctl.cd, + "interval:%lx tear=%p dear=%p\n", + cpuhw->lsctl.es, cpuhw->lsctl.cs, cpuhw->lsctl.ed, + cpuhw->lsctl.cd, cpuhw->lsctl.interval, (void *) cpuhw->lsctl.tear, (void *) cpuhw->lsctl.dear); } @@ -1717,6 +1762,44 @@ static void cpumsf_pmu_read(struct perf_event *event) /* Nothing to do ... updates are interrupt-driven */ } +/* Check if the new sampling period/freqeuncy is appropriate. + * + * Return non-zero on error and zero on passed checks. + */ +static int cpumsf_pmu_check_period(struct perf_event *event, u64 value) +{ + struct hws_qsi_info_block si; + unsigned long rate; + bool do_freq; + + memset(&si, 0, sizeof(si)); + if (event->cpu == -1) { + if (qsi(&si)) + return -ENODEV; + } else { + /* Event is pinned to a particular CPU, retrieve the per-CPU + * sampling structure for accessing the CPU-specific QSI. + */ + struct cpu_hw_sf *cpuhw = &per_cpu(cpu_hw_sf, event->cpu); + + si = cpuhw->qsi; + } + + do_freq = !!SAMPLE_FREQ_MODE(&event->hw); + rate = getrate(do_freq, value, &si); + if (!rate) + return -EINVAL; + + event->attr.sample_period = rate; + SAMPL_RATE(&event->hw) = rate; + hw_init_period(&event->hw, SAMPL_RATE(&event->hw)); + debug_sprintf_event(sfdbg, 4, "cpumsf_pmu_check_period:" + "cpu:%d value:%llx period:%llx freq:%d\n", + event->cpu, value, + event->attr.sample_period, do_freq); + return 0; +} + /* Activate sampling control. * Next call of pmu_enable() starts sampling. */ @@ -1908,6 +1991,8 @@ static struct pmu cpumf_sampling = { .setup_aux = aux_buffer_setup, .free_aux = aux_buffer_free, + + .check_period = cpumsf_pmu_check_period, }; static void cpumf_measurement_alert(struct ext_code ext_code, diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 2db6fb405a9a..3627953007ed 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -311,7 +311,8 @@ int arch_update_cpu_topology(void) on_each_cpu(__arch_update_dedicated_flag, NULL, 0); for_each_online_cpu(cpu) { dev = get_cpu_device(cpu); - kobject_uevent(&dev->kobj, KOBJ_CHANGE); + if (dev) + kobject_uevent(&dev->kobj, KOBJ_CHANGE); } return rc; } diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 54fcdf66ae96..3dd253f81a77 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -210,7 +210,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) page = alloc_page(GFP_KERNEL); if (!page) return NULL; - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { __free_page(page); return NULL; } @@ -256,7 +256,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) atomic_xor_bits(&page->_refcount, 3U << 24); } - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); } @@ -308,7 +308,7 @@ void __tlb_remove_table(void *_table) case 3: /* 4K page table with pgstes */ if (mask & 3) atomic_xor_bits(&page->_refcount, 3 << 24); - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); break; } diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index 8c6341a4d807..22d968bfe9bb 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -29,7 +29,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, #define __pte_free_tlb(tlb,pte,addr) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page((tlb), (pte)); \ } while (0) diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index b57f9c631eca..6ae8016ef4ec 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -1078,7 +1078,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, } #define io_remap_pfn_range io_remap_pfn_range -static inline unsigned long untagged_addr(unsigned long start) +static inline unsigned long __untagged_addr(unsigned long start) { if (adi_capable()) { long addr = start; @@ -1098,7 +1098,8 @@ static inline unsigned long untagged_addr(unsigned long start) return start; } -#define untagged_addr untagged_addr +#define untagged_addr(addr) \ + ((__typeof__(addr))(__untagged_addr((unsigned long)(addr)))) static inline bool pte_access_permitted(pte_t pte, bool write) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 4b099dd7a767..e6d91819da92 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2903,7 +2903,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm) struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) return NULL; - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { free_unref_page(page); return NULL; } @@ -2919,7 +2919,7 @@ static void __pte_free(pgtable_t pte) { struct page *page = virt_to_page(pte); - pgtable_page_dtor(page); + pgtable_pte_page_dtor(page); __free_page(page); } diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index aaebbc00d262..cc3ad64479ac 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -378,7 +378,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm) if ((pte = (unsigned long)pte_alloc_one_kernel(mm)) == 0) return NULL; page = pfn_to_page(__nocache_pa(pte) >> PAGE_SHIFT); - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { __free_page(page); return NULL; } @@ -389,7 +389,7 @@ void pte_free(struct mm_struct *mm, pgtable_t pte) { unsigned long p; - pgtable_page_dtor(pte); + pgtable_pte_page_dtor(pte); p = (unsigned long)page_address(pte); /* Cached address (for test) */ if (p == 0) BUG(); diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 446e0c0f4018..881e76da1938 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -29,7 +29,7 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); #define __pte_free_tlb(tlb,pte, address) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page((tlb),(pte)); \ } while (0) diff --git a/arch/unicore32/include/asm/tlb.h b/arch/unicore32/include/asm/tlb.h index 10d2356bfddd..4663d8cc80ef 100644 --- a/arch/unicore32/include/asm/tlb.h +++ b/arch/unicore32/include/asm/tlb.h @@ -15,7 +15,7 @@ #define __pte_free_tlb(tlb, pte, addr) \ do { \ - pgtable_page_dtor(pte); \ + pgtable_pte_page_dtor(pte); \ tlb_remove_page((tlb), (pte)); \ } while (0) diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index fa16036fa592..65ebe4b88f7c 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -54,23 +54,10 @@ static u64 get_subtree_max_end(struct rb_node *node) return ret; } -static u64 compute_subtree_max_end(struct memtype *data) -{ - u64 max_end = data->end, child_max_end; - - child_max_end = get_subtree_max_end(data->rb.rb_right); - if (child_max_end > max_end) - max_end = child_max_end; - - child_max_end = get_subtree_max_end(data->rb.rb_left); - if (child_max_end > max_end) - max_end = child_max_end; - - return max_end; -} +#define NODE_END(node) ((node)->end) -RB_DECLARE_CALLBACKS(static, memtype_rb_augment_cb, struct memtype, rb, - u64, subtree_max_end, compute_subtree_max_end) +RB_DECLARE_CALLBACKS_MAX(static, memtype_rb_augment_cb, + struct memtype, rb, u64, subtree_max_end, NODE_END) /* Find the first (lowest start addr) overlapping range from rb tree */ static struct memtype *memtype_rb_lowest_match(struct rb_root *root, diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 463940faf52f..3e4b9035bb9a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -45,7 +45,7 @@ early_param("userpte", setup_userpte); void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { - pgtable_page_dtor(pte); + pgtable_pte_page_dtor(pte); paravirt_release_pte(page_to_pfn(pte)); paravirt_tlb_remove_table(tlb, pte); } diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h index dd744aa450fa..1d38f0e755ba 100644 --- a/arch/xtensa/include/asm/pgalloc.h +++ b/arch/xtensa/include/asm/pgalloc.h @@ -55,7 +55,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) if (!pte) return NULL; page = virt_to_page(pte); - if (!pgtable_page_ctor(page)) { + if (!pgtable_pte_page_ctor(page)) { __free_page(page); return NULL; } @@ -69,7 +69,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline void pte_free(struct mm_struct *mm, pgtable_t pte) { - pgtable_page_dtor(pte); + pgtable_pte_page_dtor(pte); __free_page(pte); } #define pmd_pgtable(pmd) pmd_page(pmd) diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index ebbb48842190..e5e643752947 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -103,6 +103,9 @@ #define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ #define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ +#define MADV_COLD 20 /* deactivate these pages */ +#define MADV_PAGEOUT 21 /* reclaim these pages */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c index c58986556161..651bd0236a99 100644 --- a/drivers/block/drbd/drbd_interval.c +++ b/drivers/block/drbd/drbd_interval.c @@ -13,33 +13,10 @@ sector_t interval_end(struct rb_node *node) return this->end; } -/** - * compute_subtree_last - compute end of @node - * - * The end of an interval is the highest (start + (size >> 9)) value of this - * node and of its children. Called for @node and its parents whenever the end - * may have changed. - */ -static inline sector_t -compute_subtree_last(struct drbd_interval *node) -{ - sector_t max = node->sector + (node->size >> 9); - - if (node->rb.rb_left) { - sector_t left = interval_end(node->rb.rb_left); - if (left > max) - max = left; - } - if (node->rb.rb_right) { - sector_t right = interval_end(node->rb.rb_right); - if (right > max) - max = right; - } - return max; -} +#define NODE_END(node) ((node)->sector + ((node)->size >> 9)) -RB_DECLARE_CALLBACKS(static, augment_callbacks, struct drbd_interval, rb, - sector_t, end, compute_subtree_last); +RB_DECLARE_CALLBACKS_MAX(static, augment_callbacks, + struct drbd_interval, rb, sector_t, end, NODE_END); /** * drbd_insert_interval - insert a new interval into a tree diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 42b936b6bbf1..6d021ecc8d59 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1103,7 +1103,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( alloc_flags = 0; if (!offset || !*offset) return -EINVAL; - user_addr = *offset; + user_addr = untagged_addr(*offset); } else if (flags & (ALLOC_MEM_FLAGS_DOORBELL | ALLOC_MEM_FLAGS_MMIO_REMAP)) { domain = AMDGPU_GEM_DOMAIN_GTT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c index 61bd10310604..5803fcbae22f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c @@ -948,6 +948,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block case AMD_IP_BLOCK_TYPE_UVD: case AMD_IP_BLOCK_TYPE_VCN: case AMD_IP_BLOCK_TYPE_VCE: + case AMD_IP_BLOCK_TYPE_SDMA: if (swsmu) ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate); else @@ -956,7 +957,6 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block break; case AMD_IP_BLOCK_TYPE_GMC: case AMD_IP_BLOCK_TYPE_ACP: - case AMD_IP_BLOCK_TYPE_SDMA: ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu( (adev)->powerplay.pp_handle, block_type, gate)); break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bdf849da32e4..264677ab248a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1012,11 +1012,16 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, /* Navi14 */ - {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, + {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, /* Renoir */ {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT}, + /* Navi12 */ + {0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT}, + {0, 0, 0} }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index b174bd5eb38e..8ceb44925947 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -291,6 +291,8 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, uint32_t handle; int r; + args->addr = untagged_addr(args->addr); + if (offset_in_page(args->addr | args->size)) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 7850084a05e3..60655834d649 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -143,7 +143,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, /* ring tests don't use a job */ if (job) { vm = job->vm; - fence_ctx = job->base.s_fence->scheduled.context; + fence_ctx = job->base.s_fence ? + job->base.s_fence->scheduled.context : 0; } else { vm = NULL; fence_ctx = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 0e2ec608530b..f6147528be64 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -677,6 +677,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) sh_num = 0xffffffff; + if (info->read_mmr_reg.count > 128) + return -EINVAL; + regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL); if (!regs) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index db28823891ac..638c821611ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -70,6 +70,11 @@ MODULE_FIRMWARE("amdgpu/navi10_mec.bin"); MODULE_FIRMWARE("amdgpu/navi10_mec2.bin"); MODULE_FIRMWARE("amdgpu/navi10_rlc.bin"); +MODULE_FIRMWARE("amdgpu/navi14_ce_wks.bin"); +MODULE_FIRMWARE("amdgpu/navi14_pfp_wks.bin"); +MODULE_FIRMWARE("amdgpu/navi14_me_wks.bin"); +MODULE_FIRMWARE("amdgpu/navi14_mec_wks.bin"); +MODULE_FIRMWARE("amdgpu/navi14_mec2_wks.bin"); MODULE_FIRMWARE("amdgpu/navi14_ce.bin"); MODULE_FIRMWARE("amdgpu/navi14_pfp.bin"); MODULE_FIRMWARE("amdgpu/navi14_me.bin"); @@ -594,7 +599,8 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev) static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) { const char *chip_name; - char fw_name[30]; + char fw_name[40]; + char wks[10]; int err; struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; @@ -607,12 +613,16 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) DRM_DEBUG("\n"); + memset(wks, 0, sizeof(wks)); switch (adev->asic_type) { case CHIP_NAVI10: chip_name = "navi10"; break; case CHIP_NAVI14: chip_name = "navi14"; + if (!(adev->pdev->device == 0x7340 && + adev->pdev->revision != 0x00)) + snprintf(wks, sizeof(wks), "_wks"); break; case CHIP_NAVI12: chip_name = "navi12"; @@ -621,7 +631,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) BUG(); } - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp%s.bin", chip_name, wks); err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); if (err) goto out; @@ -632,7 +642,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", chip_name, wks); err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); if (err) goto out; @@ -643,7 +653,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", chip_name, wks); err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); if (err) goto out; @@ -708,7 +718,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) if (adev->gfx.rlc.is_rlc_v2_1) gfx_v10_0_init_rlc_ext_microcode(adev); - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks); err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); if (err) goto out; @@ -719,7 +729,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", chip_name, wks); err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); if (!err) { err = amdgpu_ucode_validate(adev->gfx.mec2_fw); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 83d45f98a461..dcadc73bffd2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1650,7 +1650,6 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_RAVEN: - case CHIP_RENOIR: gfx_v9_0_init_lbpw(adev); break; case CHIP_VEGA20: @@ -3026,7 +3025,6 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_RAVEN: - case CHIP_RENOIR: if (amdgpu_lbpw == 0) gfx_v9_0_enable_lbpw(adev, false); else diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index ff18b3a57892..78452cf0115d 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1889,8 +1889,9 @@ static int sdma_v4_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs && - adev->powerplay.pp_funcs->set_powergating_by_smu) + if ((adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs && + adev->powerplay.pp_funcs->set_powergating_by_smu) || + adev->asic_type == CHIP_RENOIR) amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, false); if (!amdgpu_sriov_vf(adev)) @@ -1917,8 +1918,9 @@ static int sdma_v4_0_hw_fini(void *handle) sdma_v4_0_ctx_switch_enable(adev, false); sdma_v4_0_enable(adev, false); - if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs - && adev->powerplay.pp_funcs->set_powergating_by_smu) + if ((adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs + && adev->powerplay.pp_funcs->set_powergating_by_smu) || + adev->asic_type == CHIP_RENOIR) amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, true); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c index 4a5951036927..c44723c267c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c +++ b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c @@ -493,7 +493,15 @@ static void smu_v11_0_i2c_fini(struct i2c_adapter *control) } /* Restore clock gating */ - smu_v11_0_i2c_set_clock_gating(control, true); + + /* + * TODO Reenabling clock gating seems to break subsequent SMU operation + * on the I2C bus. My guess is that SMU doesn't disable clock gating like + * we do here before working with the bus. So for now just don't restore + * it but later work with SMU to see if they have this issue and can + * update their code appropriately + */ + /* smu_v11_0_i2c_set_clock_gating(control, true); */ } diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index a8cf82d46109..901fe3590165 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -694,10 +694,10 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x003f8000, 0x8f6f896f, 0x88776f77, 0x8a6eff6e, 0x023f8000, 0xb9eef807, - 0xb970f812, 0xb971f813, - 0x8ff08870, 0xf4051bb8, + 0xb97af812, 0xb97bf813, + 0x8ffa887a, 0xf4051bbd, 0xfa000000, 0xbf8cc07f, - 0xf4051c38, 0xfa000008, + 0xf4051ebd, 0xfa000008, 0xbf8cc07f, 0x87ee6e6e, 0xbf840001, 0xbe80206e, 0xb971f803, 0x8771ff71, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm index 35986219ce5f..cdaa523ce6be 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm @@ -187,12 +187,12 @@ L_FETCH_2ND_TRAP: // Read second-level TBA/TMA from first-level TMA and jump if available. // ttmp[2:5] and ttmp12 can be used (others hold SPI-initialized debug data) // ttmp12 holds SQ_WAVE_STATUS - s_getreg_b32 ttmp4, hwreg(HW_REG_SHADER_TMA_LO) - s_getreg_b32 ttmp5, hwreg(HW_REG_SHADER_TMA_HI) - s_lshl_b64 [ttmp4, ttmp5], [ttmp4, ttmp5], 0x8 - s_load_dwordx2 [ttmp2, ttmp3], [ttmp4, ttmp5], 0x0 glc:1 // second-level TBA + s_getreg_b32 ttmp14, hwreg(HW_REG_SHADER_TMA_LO) + s_getreg_b32 ttmp15, hwreg(HW_REG_SHADER_TMA_HI) + s_lshl_b64 [ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 + s_load_dwordx2 [ttmp2, ttmp3], [ttmp14, ttmp15], 0x0 glc:1 // second-level TBA s_waitcnt lgkmcnt(0) - s_load_dwordx2 [ttmp4, ttmp5], [ttmp4, ttmp5], 0x8 glc:1 // second-level TMA + s_load_dwordx2 [ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 glc:1 // second-level TMA s_waitcnt lgkmcnt(0) s_and_b64 [ttmp2, ttmp3], [ttmp2, ttmp3], [ttmp2, ttmp3] s_cbranch_scc0 L_NO_NEXT_TRAP // second-level trap handler not been set diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e1b09bb432bd..8cab6da512a0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2113,6 +2113,7 @@ static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd) } static const struct backlight_ops amdgpu_dm_backlight_ops = { + .options = BL_CORE_SUSPENDRESUME, .get_brightness = amdgpu_dm_backlight_get_brightness, .update_status = amdgpu_dm_backlight_update_status, }; @@ -2384,6 +2385,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY) dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true; + if (adev->asic_type == CHIP_RENOIR) + dm->dc->debug.disable_stutter = true; return 0; fail: @@ -5770,8 +5773,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * change FB pitch, DCC state, rotation or mirroing. */ bundle->flip_addrs[planes_count].flip_immediate = - (crtc->state->pageflip_flags & - DRM_MODE_PAGE_FLIP_ASYNC) != 0 && + crtc->state->async_flip && acrtc_state->update_type == UPDATE_TYPE_FAST; timestamp_ns = ktime_get_ns(); @@ -6348,7 +6350,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) amdgpu_dm_enable_crtc_interrupts(dev, state, true); for_each_new_crtc_in_state(state, crtc, new_crtc_state, j) - if (new_crtc_state->pageflip_flags & DRM_MODE_PAGE_FLIP_ASYNC) + if (new_crtc_state->async_flip) wait_for_vblank = false; /* update planes when needed per crtc*/ diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c index 383f4f8db8f4..9b2cb57bf2ba 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c @@ -708,6 +708,10 @@ static void hack_bounding_box(struct dcn_bw_internal_vars *v, unsigned int get_highest_allowed_voltage_level(uint32_t hw_internal_rev) { + /* for dali, the highest voltage level we want is 0 */ + if (ASICREV_IS_DALI(hw_internal_rev)) + return 0; + /* we are ok with all levels */ return 4; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c index 5cc3acccda2a..b1e657e137a9 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c @@ -98,11 +98,14 @@ uint32_t dce110_get_min_vblank_time_us(const struct dc_state *context) struct dc_stream_state *stream = context->streams[j]; uint32_t vertical_blank_in_pixels = 0; uint32_t vertical_blank_time = 0; + uint32_t vertical_total_min = stream->timing.v_total; + struct dc_crtc_timing_adjust adjust = stream->adjust; + if (adjust.v_total_max != adjust.v_total_min) + vertical_total_min = adjust.v_total_min; vertical_blank_in_pixels = stream->timing.h_total * - (stream->timing.v_total + (vertical_total_min - stream->timing.v_addressable); - vertical_blank_time = vertical_blank_in_pixels * 10000 / stream->timing.pix_clk_100hz; @@ -171,6 +174,10 @@ void dce11_pplib_apply_display_requirements( struct dc_state *context) { struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg; + int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ; + + if (dc->bw_vbios && dc->bw_vbios->memory_type == bw_def_hbm) + memory_type_multiplier = MEMORY_TYPE_HBM; pp_display_cfg->all_displays_in_sync = context->bw_ctx.bw.dce.all_displays_in_sync; @@ -183,8 +190,20 @@ void dce11_pplib_apply_display_requirements( pp_display_cfg->cpu_pstate_separation_time = context->bw_ctx.bw.dce.blackout_recovery_time_us; - pp_display_cfg->min_memory_clock_khz = context->bw_ctx.bw.dce.yclk_khz - / MEMORY_TYPE_MULTIPLIER_CZ; + /* + * TODO: determine whether the bandwidth has reached memory's limitation + * , then change minimum memory clock based on real-time bandwidth + * limitation. + */ + if (ASICREV_IS_VEGA20_P(dc->ctx->asic_id.hw_internal_rev) && (context->stream_count >= 2)) { + pp_display_cfg->min_memory_clock_khz = max(pp_display_cfg->min_memory_clock_khz, + (uint32_t) div64_s64( + div64_s64(dc->bw_vbios->high_yclk.value, + memory_type_multiplier), 10000)); + } else { + pp_display_cfg->min_memory_clock_khz = context->bw_ctx.bw.dce.yclk_khz + / memory_type_multiplier; + } pp_display_cfg->min_engine_clock_khz = determine_sclk_from_bounding_box( dc, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c index 1488ffddf4e3..31b698bf9cfc 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c @@ -148,7 +148,7 @@ static void dce_mi_program_pte_vm( pte->min_pte_before_flip_horiz_scan; REG_UPDATE(GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, - GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, 0xff); + GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, 0x7f); REG_UPDATE_3(DVMM_PTE_CONTROL, DVMM_PAGE_WIDTH, page_width, @@ -157,7 +157,7 @@ static void dce_mi_program_pte_vm( REG_UPDATE_2(DVMM_PTE_ARB_CONTROL, DVMM_PTE_REQ_PER_CHUNK, pte->pte_req_per_chunk, - DVMM_MAX_PTE_REQ_OUTSTANDING, 0xff); + DVMM_MAX_PTE_REQ_OUTSTANDING, 0x7f); } static void program_urgency_watermark( diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c index afc61055eca1..1787b9bf800a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c @@ -1091,6 +1091,7 @@ struct resource_pool *dce100_create_resource_pool( if (construct(num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index c66fe170e1e8..318e9c2e2ca8 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -1462,6 +1462,7 @@ struct resource_pool *dce110_create_resource_pool( if (construct(num_virtual_links, dc, pool, asic_id)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c index 3ac4c7e73050..83e1878161c9 100644 --- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c @@ -987,6 +987,10 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc) struct dm_pp_clock_levels_with_latency mem_clks = {0}; struct dm_pp_wm_sets_with_clock_ranges clk_ranges = {0}; struct dm_pp_clock_levels clks = {0}; + int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ; + + if (dc->bw_vbios && dc->bw_vbios->memory_type == bw_def_hbm) + memory_type_multiplier = MEMORY_TYPE_HBM; /*do system clock TODO PPLIB: after PPLIB implement, * then remove old way @@ -1026,12 +1030,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc) &clks); dc->bw_vbios->low_yclk = bw_frc_to_fixed( - clks.clocks_in_khz[0] * MEMORY_TYPE_MULTIPLIER_CZ, 1000); + clks.clocks_in_khz[0] * memory_type_multiplier, 1000); dc->bw_vbios->mid_yclk = bw_frc_to_fixed( - clks.clocks_in_khz[clks.num_levels>>1] * MEMORY_TYPE_MULTIPLIER_CZ, + clks.clocks_in_khz[clks.num_levels>>1] * memory_type_multiplier, 1000); dc->bw_vbios->high_yclk = bw_frc_to_fixed( - clks.clocks_in_khz[clks.num_levels-1] * MEMORY_TYPE_MULTIPLIER_CZ, + clks.clocks_in_khz[clks.num_levels-1] * memory_type_multiplier, 1000); return; @@ -1067,12 +1071,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc) * YCLK = UMACLK*m_memoryTypeMultiplier */ dc->bw_vbios->low_yclk = bw_frc_to_fixed( - mem_clks.data[0].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, 1000); + mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000); dc->bw_vbios->mid_yclk = bw_frc_to_fixed( - mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, + mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier, 1000); dc->bw_vbios->high_yclk = bw_frc_to_fixed( - mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, + mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier, 1000); /* Now notify PPLib/SMU about which Watermarks sets they should select @@ -1338,6 +1342,7 @@ struct resource_pool *dce112_create_resource_pool( if (construct(num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c index 7d08154e9662..8b85e5274bba 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c @@ -847,6 +847,8 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc) int i; unsigned int clk; unsigned int latency; + /*original logic in dal3*/ + int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ; /*do system clock*/ if (!dm_pp_get_clock_levels_by_type_with_latency( @@ -905,13 +907,16 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc) * ALSO always convert UMA clock (from PPLIB) to YCLK (HW formula): * YCLK = UMACLK*m_memoryTypeMultiplier */ + if (dc->bw_vbios->memory_type == bw_def_hbm) + memory_type_multiplier = MEMORY_TYPE_HBM; + dc->bw_vbios->low_yclk = bw_frc_to_fixed( - mem_clks.data[0].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, 1000); + mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000); dc->bw_vbios->mid_yclk = bw_frc_to_fixed( - mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, + mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier, 1000); dc->bw_vbios->high_yclk = bw_frc_to_fixed( - mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, + mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier, 1000); /* Now notify PPLib/SMU about which Watermarks sets they should select @@ -1203,6 +1208,7 @@ struct resource_pool *dce120_create_resource_pool( if (construct(num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 5a89e462e7cc..59305e411a66 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -1570,6 +1570,7 @@ struct resource_pool *dcn10_create_resource_pool( if (construct(init_data->num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 3ca5139f1273..de182185fe1f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -23,6 +23,8 @@ * */ +#include <linux/slab.h> + #include "dm_services.h" #include "dc.h" diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c index 34485d9de78a..8572678f8d4f 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c @@ -35,12 +35,10 @@ #include "hw_factory_dcn21.h" - #include "dcn/dcn_2_1_0_offset.h" #include "dcn/dcn_2_1_0_sh_mask.h" #include "renoir_ip_offset.h" - #include "reg_helper.h" #include "../hpd_regs.h" /* begin ********************* @@ -136,6 +134,39 @@ static const struct ddc_sh_mask ddc_mask[] = { DDC_MASK_SH_LIST_DCN2(_MASK, 6) }; +#include "../generic_regs.h" + +/* set field name */ +#define SF_GENERIC(reg_name, field_name, post_fix)\ + .field_name = reg_name ## __ ## field_name ## post_fix + +#define generic_regs(id) \ +{\ + GENERIC_REG_LIST(id)\ +} + +static const struct generic_registers generic_regs[] = { + generic_regs(A), +}; + +static const struct generic_sh_mask generic_shift[] = { + GENERIC_MASK_SH_LIST(__SHIFT, A), +}; + +static const struct generic_sh_mask generic_mask[] = { + GENERIC_MASK_SH_LIST(_MASK, A), +}; + +static void define_generic_registers(struct hw_gpio_pin *pin, uint32_t en) +{ + struct hw_generic *generic = HW_GENERIC_FROM_BASE(pin); + + generic->regs = &generic_regs[en]; + generic->shifts = &generic_shift[en]; + generic->masks = &generic_mask[en]; + generic->base.regs = &generic_regs[en].gpio; +} + static void define_ddc_registers( struct hw_gpio_pin *pin, uint32_t en) @@ -181,7 +212,8 @@ static const struct hw_factory_funcs funcs = { .get_hpd_pin = dal_hw_hpd_get_pin, .get_generic_pin = dal_hw_generic_get_pin, .define_hpd_registers = define_hpd_registers, - .define_ddc_registers = define_ddc_registers + .define_ddc_registers = define_ddc_registers, + .define_generic_registers = define_generic_registers }; /* * dal_hw_factory_dcn10_init diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c index ad7c43746291..fbb58fb8c318 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c @@ -58,7 +58,6 @@ #define SF_HPD(reg_name, field_name, post_fix)\ .field_name = reg_name ## __ ## field_name ## post_fix - /* macros to expend register list macro defined in HW object header file * end *********************/ @@ -71,7 +70,7 @@ static bool offset_to_id( { switch (offset) { /* GENERIC */ - case REG(DC_GENERICA): + case REG(DC_GPIO_GENERIC_A): *id = GPIO_ID_GENERIC; switch (mask) { case DC_GPIO_GENERIC_A__DC_GPIO_GENERICA_A_MASK: diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 1cc1c8ce633b..bef224bf803e 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -31,6 +31,8 @@ #include "dm_pp_smu.h" #define MEMORY_TYPE_MULTIPLIER_CZ 4 +#define MEMORY_TYPE_HBM 2 + enum dce_version resource_parse_asic_id( struct hw_asic_id asic_id); diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 1f16892f0add..1be6c44fd32f 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -137,10 +137,13 @@ #define RAVEN1_F0 0xF0 #define RAVEN_UNKNOWN 0xFF +#define PICASSO_15D8_REV_E3 0xE3 +#define PICASSO_15D8_REV_E4 0xE4 + #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN) #define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0)) -#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0)) - +#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < PICASSO_15D8_REV_E3)) +#define ASICREV_IS_DALI(eChipRev) ((eChipRev >= PICASSO_15D8_REV_E3) && (eChipRev < RAVEN1_F0)) #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN)) diff --git a/drivers/gpu/drm/amd/include/renoir_ip_offset.h b/drivers/gpu/drm/amd/include/renoir_ip_offset.h index 554714c8e000..094648cac392 100644 --- a/drivers/gpu/drm/amd/include/renoir_ip_offset.h +++ b/drivers/gpu/drm/amd/include/renoir_ip_offset.h @@ -155,7 +155,7 @@ static const struct IP_BASE MP0_BASE ={ { { { 0x00016000, 0x0243FC00, 0x00DC0000 { { 0, 0, 0, 0, 0 } }, { { 0, 0, 0, 0, 0 } }, { { 0, 0, 0, 0, 0 } } } }; -static const struct IP_BASE MP1_BASE ={ { { { 0x00016200, 0x02400400, 0x00E80000, 0x00EC0000, 0x00F00000 } }, +static const struct IP_BASE MP1_BASE ={ { { { 0x00016000, 0x02400400, 0x00E80000, 0x00EC0000, 0x00F00000 } }, { { 0, 0, 0, 0, 0 } }, { { 0, 0, 0, 0, 0 } }, { { 0, 0, 0, 0, 0 } }, diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index fa636cb462c1..fa8ad7db2b3a 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -1531,6 +1531,7 @@ static int pp_asic_reset_mode_2(void *handle) static int pp_smu_i2c_bus_access(void *handle, bool acquire) { struct pp_hwmgr *hwmgr = handle; + int ret = 0; if (!hwmgr || !hwmgr->pm_en) return -EINVAL; @@ -1540,7 +1541,11 @@ static int pp_smu_i2c_bus_access(void *handle, bool acquire) return -EINVAL; } - return hwmgr->hwmgr_func->smu_i2c_bus_access(hwmgr, acquire); + mutex_lock(&hwmgr->smu_lock); + ret = hwmgr->hwmgr_func->smu_i2c_bus_access(hwmgr, acquire); + mutex_unlock(&hwmgr->smu_lock); + + return ret; } static const struct amd_pm_funcs pp_dpm_funcs = { diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 22f3c60d380f..33960fb38a5d 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -354,6 +354,9 @@ int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type, case AMD_IP_BLOCK_TYPE_GFX: ret = smu_gfx_off_control(smu, gate); break; + case AMD_IP_BLOCK_TYPE_SDMA: + ret = smu_powergate_sdma(smu, gate); + break; default: break; } diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index 2a6da546fb55..e62bfba51562 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -177,12 +177,82 @@ static int renoir_get_dpm_uclk_limited(struct smu_context *smu, uint32_t *clock, } +static int renoir_print_clk_levels(struct smu_context *smu, + enum smu_clk_type clk_type, char *buf) +{ + int i, size = 0, ret = 0; + uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0; + DpmClocks_t *clk_table = smu->smu_table.clocks_table; + SmuMetrics_t metrics = {0}; + + if (!clk_table || clk_type >= SMU_CLK_COUNT) + return -EINVAL; + + ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, + (void *)&metrics, false); + if (ret) + return ret; + + switch (clk_type) { + case SMU_GFXCLK: + case SMU_SCLK: + /* retirve table returned paramters unit is MHz */ + cur_value = metrics.ClockFrequency[CLOCK_GFXCLK]; + ret = smu_get_dpm_freq_range(smu, SMU_GFXCLK, &min, &max); + if (!ret) { + /* driver only know min/max gfx_clk, Add level 1 for all other gfx clks */ + if (cur_value == max) + i = 2; + else if (cur_value == min) + i = 0; + else + i = 1; + + size += sprintf(buf + size, "0: %uMhz %s\n", min, + i == 0 ? "*" : ""); + size += sprintf(buf + size, "1: %uMhz %s\n", + i == 1 ? cur_value : RENOIR_UMD_PSTATE_GFXCLK, + i == 1 ? "*" : ""); + size += sprintf(buf + size, "2: %uMhz %s\n", max, + i == 2 ? "*" : ""); + } + return size; + case SMU_SOCCLK: + count = NUM_SOCCLK_DPM_LEVELS; + cur_value = metrics.ClockFrequency[CLOCK_SOCCLK]; + break; + case SMU_MCLK: + count = NUM_MEMCLK_DPM_LEVELS; + cur_value = metrics.ClockFrequency[CLOCK_UMCCLK]; + break; + case SMU_DCEFCLK: + count = NUM_DCFCLK_DPM_LEVELS; + cur_value = metrics.ClockFrequency[CLOCK_DCFCLK]; + break; + case SMU_FCLK: + count = NUM_FCLK_DPM_LEVELS; + cur_value = metrics.ClockFrequency[CLOCK_FCLK]; + break; + default: + return -EINVAL; + } + + for (i = 0; i < count; i++) { + GET_DPM_CUR_FREQ(clk_table, clk_type, i, value); + size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, + cur_value == value ? "*" : ""); + } + + return size; +} + static const struct pptable_funcs renoir_ppt_funcs = { .get_smu_msg_index = renoir_get_smu_msg_index, .get_smu_table_index = renoir_get_smu_table_index, .tables_init = renoir_tables_init, .set_power_state = NULL, .get_dpm_uclk_limited = renoir_get_dpm_uclk_limited, + .print_clk_levels = renoir_print_clk_levels, }; void renoir_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h index e9b7237c0f7f..2a390ddd37dd 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h @@ -25,4 +25,29 @@ extern void renoir_set_ppt_funcs(struct smu_context *smu); +/* UMD PState Renoir Msg Parameters in MHz */ +#define RENOIR_UMD_PSTATE_GFXCLK 700 +#define RENOIR_UMD_PSTATE_SOCCLK 678 +#define RENOIR_UMD_PSTATE_FCLK 800 + +#define GET_DPM_CUR_FREQ(table, clk_type, dpm_level, freq) \ + do { \ + switch (clk_type) { \ + case SMU_SOCCLK: \ + freq = table->SocClocks[dpm_level].Freq; \ + break; \ + case SMU_MCLK: \ + freq = table->MemClocks[dpm_level].Freq; \ + break; \ + case SMU_DCEFCLK: \ + freq = table->DcfClocks[dpm_level].Freq; \ + break; \ + case SMU_FCLK: \ + freq = table->FClocks[dpm_level].Freq; \ + break; \ + default: \ + break; \ + } \ + } while (0) + #endif diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 3d61c4fb4dec..9e13e466e72c 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -874,6 +874,9 @@ static int adv7511_bridge_attach(struct drm_bridge *bridge) &adv7511_connector_helper_funcs); drm_connector_attach_encoder(&adv->connector, bridge->encoder); + if (adv->type == ADV7533) + ret = adv7533_attach_dsi(adv); + if (adv->i2c_main->irq) regmap_write(adv->regmap, ADV7511_REG_INT_ENABLE(0), ADV7511_INT0_HPD); @@ -1219,17 +1222,8 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) drm_bridge_add(&adv7511->bridge); adv7511_audio_init(dev, adv7511); - - if (adv7511->type == ADV7533) { - ret = adv7533_attach_dsi(adv7511); - if (ret) - goto err_remove_bridge; - } - return 0; -err_remove_bridge: - drm_bridge_remove(&adv7511->bridge); err_unregister_cec: i2c_unregister_device(adv7511->i2c_cec); if (adv7511->cec_clk) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index aa16ea17ff9b..3ef2ac52ce94 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -26,6 +26,7 @@ */ #include <linux/dma-fence.h> +#include <linux/ktime.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> @@ -1580,9 +1581,23 @@ static void commit_tail(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; const struct drm_mode_config_helper_funcs *funcs; + ktime_t start; + s64 commit_time_ms; funcs = dev->mode_config.helper_private; + /* + * We're measuring the _entire_ commit, so the time will vary depending + * on how many fences and objects are involved. For the purposes of self + * refresh, this is desirable since it'll give us an idea of how + * congested things are. This will inform our decision on how often we + * should enter self refresh after idle. + * + * These times will be averaged out in the self refresh helpers to avoid + * overreacting over one outlier frame + */ + start = ktime_get(); + drm_atomic_helper_wait_for_fences(dev, old_state, false); drm_atomic_helper_wait_for_dependencies(old_state); @@ -1592,6 +1607,11 @@ static void commit_tail(struct drm_atomic_state *old_state) else drm_atomic_helper_commit_tail(old_state); + commit_time_ms = ktime_ms_delta(ktime_get(), start); + if (commit_time_ms > 0) + drm_self_refresh_helper_update_avg_times(old_state, + (unsigned long)commit_time_ms); + drm_atomic_helper_commit_cleanup_done(old_state); drm_atomic_state_put(old_state); @@ -3275,7 +3295,7 @@ static int page_flip_common(struct drm_atomic_state *state, return PTR_ERR(crtc_state); crtc_state->event = event; - crtc_state->pageflip_flags = flags; + crtc_state->async_flip = flags & DRM_MODE_PAGE_FLIP_ASYNC; plane_state = drm_atomic_get_plane_state(state, plane); if (IS_ERR(plane_state)) diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c index 46dc264a248b..d0a937fb0c56 100644 --- a/drivers/gpu/drm/drm_atomic_state_helper.c +++ b/drivers/gpu/drm/drm_atomic_state_helper.c @@ -128,7 +128,7 @@ void __drm_atomic_helper_crtc_duplicate_state(struct drm_crtc *crtc, state->zpos_changed = false; state->commit = NULL; state->event = NULL; - state->pageflip_flags = 0; + state->async_flip = false; /* Self refresh should be canceled when a new update is available */ state->active = drm_atomic_crtc_effectively_active(state); diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 5a5b42db6f2a..7a26bfb5329c 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -1305,8 +1305,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev, if (arg->reserved) return -EINVAL; - if ((arg->flags & DRM_MODE_PAGE_FLIP_ASYNC) && - !dev->mode_config.async_page_flip) + if (arg->flags & DRM_MODE_PAGE_FLIP_ASYNC) return -EINVAL; /* can't test and expect an event at the same time. */ diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index c456c3d3def2..769feefeeeef 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -976,14 +976,14 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) if (ret) goto err_minors; + dev->registered = true; + if (dev->driver->load) { ret = dev->driver->load(dev, flags); if (ret) goto err_minors; } - dev->registered = true; - if (drm_core_check_feature(dev, DRIVER_MODESET)) drm_modeset_register_all(dev); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index f675a3bb2c88..fcd728d7cf72 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -336,7 +336,12 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv) case DRM_CLIENT_CAP_ATOMIC: if (!drm_core_check_feature(dev, DRIVER_ATOMIC)) return -EOPNOTSUPP; - if (req->value > 1) + /* The modesetting DDX has a totally broken idea of atomic. */ + if (current->comm[0] == 'X' && req->value == 1) { + pr_info("broken atomic modeset userspace detected, disabling atomic\n"); + return -EOPNOTSUPP; + } + if (req->value > 2) return -EINVAL; file_priv->atomic = req->value; file_priv->universal_planes = req->value; diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c index c355ba8e6d5d..6a23e36ed4fe 100644 --- a/drivers/gpu/drm/drm_mode_object.c +++ b/drivers/gpu/drm/drm_mode_object.c @@ -42,7 +42,7 @@ int __drm_mode_object_add(struct drm_device *dev, struct drm_mode_object *obj, { int ret; - WARN_ON(dev->registered && !obj_free_cb); + WARN_ON(!dev->driver->load && dev->registered && !obj_free_cb); mutex_lock(&dev->mode_config.idr_mutex); ret = idr_alloc(&dev->mode_config.object_idr, register_obj ? obj : NULL, @@ -104,7 +104,7 @@ void drm_mode_object_register(struct drm_device *dev, void drm_mode_object_unregister(struct drm_device *dev, struct drm_mode_object *object) { - WARN_ON(dev->registered && !object->free_cb); + WARN_ON(!dev->driver->load && dev->registered && !object->free_cb); mutex_lock(&dev->mode_config.idr_mutex); if (object->id) { diff --git a/drivers/gpu/drm/drm_self_refresh_helper.c b/drivers/gpu/drm/drm_self_refresh_helper.c index 4b9424a8f1f1..68f4765a5896 100644 --- a/drivers/gpu/drm/drm_self_refresh_helper.c +++ b/drivers/gpu/drm/drm_self_refresh_helper.c @@ -5,6 +5,7 @@ * Authors: * Sean Paul <seanpaul@chromium.org> */ +#include <linux/average.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/workqueue.h> @@ -50,11 +51,17 @@ * atomic_check when &drm_crtc_state.self_refresh_active is true. */ +#define SELF_REFRESH_AVG_SEED_MS 200 + +DECLARE_EWMA(psr_time, 4, 4) + struct drm_self_refresh_data { struct drm_crtc *crtc; struct delayed_work entry_work; - struct drm_atomic_state *save_state; - unsigned int entry_delay_ms; + + struct mutex avg_mutex; + struct ewma_psr_time entry_avg_ms; + struct ewma_psr_time exit_avg_ms; }; static void drm_self_refresh_helper_entry_work(struct work_struct *work) @@ -123,6 +130,44 @@ out_drop_locks: } /** + * drm_self_refresh_helper_update_avg_times - Updates a crtc's SR time averages + * @state: the state which has just been applied to hardware + * @commit_time_ms: the amount of time in ms that this commit took to complete + * + * Called after &drm_mode_config_funcs.atomic_commit_tail, this function will + * update the average entry/exit self refresh times on self refresh transitions. + * These averages will be used when calculating how long to delay before + * entering self refresh mode after activity. + */ +void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state, + unsigned int commit_time_ms) +{ + struct drm_crtc *crtc; + struct drm_crtc_state *old_crtc_state, *new_crtc_state; + int i; + + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, + new_crtc_state, i) { + struct drm_self_refresh_data *sr_data = crtc->self_refresh_data; + struct ewma_psr_time *time; + + if (old_crtc_state->self_refresh_active == + new_crtc_state->self_refresh_active) + continue; + + if (new_crtc_state->self_refresh_active) + time = &sr_data->entry_avg_ms; + else + time = &sr_data->exit_avg_ms; + + mutex_lock(&sr_data->avg_mutex); + ewma_psr_time_add(time, commit_time_ms); + mutex_unlock(&sr_data->avg_mutex); + } +} +EXPORT_SYMBOL(drm_self_refresh_helper_update_avg_times); + +/** * drm_self_refresh_helper_alter_state - Alters the atomic state for SR exit * @state: the state currently being checked * @@ -153,6 +198,7 @@ void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state) for_each_new_crtc_in_state(state, crtc, crtc_state, i) { struct drm_self_refresh_data *sr_data; + unsigned int delay; /* Don't trigger the entry timer when we're already in SR */ if (crtc_state->self_refresh_active) @@ -162,8 +208,13 @@ void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state) if (!sr_data) continue; + mutex_lock(&sr_data->avg_mutex); + delay = (ewma_psr_time_read(&sr_data->entry_avg_ms) + + ewma_psr_time_read(&sr_data->exit_avg_ms)) * 2; + mutex_unlock(&sr_data->avg_mutex); + mod_delayed_work(system_wq, &sr_data->entry_work, - msecs_to_jiffies(sr_data->entry_delay_ms)); + msecs_to_jiffies(delay)); } } EXPORT_SYMBOL(drm_self_refresh_helper_alter_state); @@ -171,12 +222,10 @@ EXPORT_SYMBOL(drm_self_refresh_helper_alter_state); /** * drm_self_refresh_helper_init - Initializes self refresh helpers for a crtc * @crtc: the crtc which supports self refresh supported displays - * @entry_delay_ms: amount of inactivity to wait before entering self refresh * * Returns zero if successful or -errno on failure */ -int drm_self_refresh_helper_init(struct drm_crtc *crtc, - unsigned int entry_delay_ms) +int drm_self_refresh_helper_init(struct drm_crtc *crtc) { struct drm_self_refresh_data *sr_data = crtc->self_refresh_data; @@ -190,8 +239,18 @@ int drm_self_refresh_helper_init(struct drm_crtc *crtc, INIT_DELAYED_WORK(&sr_data->entry_work, drm_self_refresh_helper_entry_work); - sr_data->entry_delay_ms = entry_delay_ms; sr_data->crtc = crtc; + mutex_init(&sr_data->avg_mutex); + ewma_psr_time_init(&sr_data->entry_avg_ms); + ewma_psr_time_init(&sr_data->exit_avg_ms); + + /* + * Seed the averages so they're non-zero (and sufficiently large + * for even poorly performing panels). As time goes on, this will be + * averaged out and the values will trend to their true value. + */ + ewma_psr_time_add(&sr_data->entry_avg_ms, SELF_REFRESH_AVG_SEED_MS); + ewma_psr_time_add(&sr_data->exit_avg_ms, SELF_REFRESH_AVG_SEED_MS); crtc->self_refresh_data = sr_data; return 0; diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 2db029371c91..5193b6257061 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -267,7 +267,7 @@ nv50_wndw_atomic_check_acquire(struct nv50_wndw *wndw, bool modeset, asyw->image.pitch[0] = fb->base.pitches[0]; } - if (!(asyh->state.pageflip_flags & DRM_MODE_PAGE_FLIP_ASYNC)) + if (!asyh->state.async_flip) asyw->image.interval = 1; else asyw->image.interval = 0; @@ -383,7 +383,7 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw, } /* Can't do an immediate flip while changing the LUT. */ - asyh->state.pageflip_flags &= ~DRM_MODE_PAGE_FLIP_ASYNC; + asyh->state.async_flip = false; } static int diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c index a1f5fa6a742a..12ff77dacc95 100644 --- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c +++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c @@ -39,7 +39,7 @@ static int panfrost_devfreq_target(struct device *dev, unsigned long *freq, * If frequency scaling from low to high, adjust voltage first. * If frequency scaling from high to low, adjust frequency first. */ - if (old_clk_rate < target_rate && pfdev->regulator) { + if (old_clk_rate < target_rate) { err = regulator_set_voltage(pfdev->regulator, target_volt, target_volt); if (err) { @@ -53,14 +53,12 @@ static int panfrost_devfreq_target(struct device *dev, unsigned long *freq, if (err) { dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate, err); - if (pfdev->regulator) - regulator_set_voltage(pfdev->regulator, - pfdev->devfreq.cur_volt, - pfdev->devfreq.cur_volt); + regulator_set_voltage(pfdev->regulator, pfdev->devfreq.cur_volt, + pfdev->devfreq.cur_volt); return err; } - if (old_clk_rate > target_rate && pfdev->regulator) { + if (old_clk_rate > target_rate) { err = regulator_set_voltage(pfdev->regulator, target_volt, target_volt); if (err) diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c b/drivers/gpu/drm/panfrost/panfrost_device.c index 46b0b02e4289..238fb6d54df4 100644 --- a/drivers/gpu/drm/panfrost/panfrost_device.c +++ b/drivers/gpu/drm/panfrost/panfrost_device.c @@ -89,12 +89,9 @@ static int panfrost_regulator_init(struct panfrost_device *pfdev) { int ret; - pfdev->regulator = devm_regulator_get_optional(pfdev->dev, "mali"); + pfdev->regulator = devm_regulator_get(pfdev->dev, "mali"); if (IS_ERR(pfdev->regulator)) { ret = PTR_ERR(pfdev->regulator); - pfdev->regulator = NULL; - if (ret == -ENODEV) - return 0; dev_err(pfdev->dev, "failed to get regulator: %d\n", ret); return ret; } @@ -110,8 +107,7 @@ static int panfrost_regulator_init(struct panfrost_device *pfdev) static void panfrost_regulator_fini(struct panfrost_device *pfdev) { - if (pfdev->regulator) - regulator_disable(pfdev->regulator); + regulator_disable(pfdev->regulator); } int panfrost_device_init(struct panfrost_device *pfdev) diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 6010f9ee7c1f..bdd990568476 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -394,28 +394,40 @@ void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv) free_io_pgtable_ops(mmu->pgtbl_ops); } -static struct drm_mm_node *addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr) +static struct panfrost_gem_object * +addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr) { - struct drm_mm_node *node = NULL; + struct panfrost_gem_object *bo = NULL; + struct panfrost_file_priv *priv; + struct drm_mm_node *node; u64 offset = addr >> PAGE_SHIFT; struct panfrost_mmu *mmu; spin_lock(&pfdev->as_lock); list_for_each_entry(mmu, &pfdev->as_lru_list, list) { - struct panfrost_file_priv *priv; - if (as != mmu->as) - continue; + if (as == mmu->as) + break; + } + if (as != mmu->as) + goto out; + + priv = container_of(mmu, struct panfrost_file_priv, mmu); - priv = container_of(mmu, struct panfrost_file_priv, mmu); - drm_mm_for_each_node(node, &priv->mm) { - if (offset >= node->start && offset < (node->start + node->size)) - goto out; + spin_lock(&priv->mm_lock); + + drm_mm_for_each_node(node, &priv->mm) { + if (offset >= node->start && + offset < (node->start + node->size)) { + bo = drm_mm_node_to_panfrost_bo(node); + drm_gem_object_get(&bo->base.base); + break; } } + spin_unlock(&priv->mm_lock); out: spin_unlock(&pfdev->as_lock); - return node; + return bo; } #define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE) @@ -423,29 +435,28 @@ out: int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr) { int ret, i; - struct drm_mm_node *node; struct panfrost_gem_object *bo; struct address_space *mapping; pgoff_t page_offset; struct sg_table *sgt; struct page **pages; - node = addr_to_drm_mm_node(pfdev, as, addr); - if (!node) + bo = addr_to_drm_mm_node(pfdev, as, addr); + if (!bo) return -ENOENT; - bo = drm_mm_node_to_panfrost_bo(node); if (!bo->is_heap) { dev_WARN(pfdev->dev, "matching BO is not heap type (GPU VA = %llx)", - node->start << PAGE_SHIFT); - return -EINVAL; + bo->node.start << PAGE_SHIFT); + ret = -EINVAL; + goto err_bo; } WARN_ON(bo->mmu->as != as); /* Assume 2MB alignment and size multiple */ addr &= ~((u64)SZ_2M - 1); page_offset = addr >> PAGE_SHIFT; - page_offset -= node->start; + page_offset -= bo->node.start; mutex_lock(&bo->base.pages_lock); @@ -454,7 +465,8 @@ int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr) sizeof(struct sg_table), GFP_KERNEL | __GFP_ZERO); if (!bo->sgts) { mutex_unlock(&bo->base.pages_lock); - return -ENOMEM; + ret = -ENOMEM; + goto err_bo; } pages = kvmalloc_array(bo->base.base.size >> PAGE_SHIFT, @@ -463,7 +475,8 @@ int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr) kfree(bo->sgts); bo->sgts = NULL; mutex_unlock(&bo->base.pages_lock); - return -ENOMEM; + ret = -ENOMEM; + goto err_bo; } bo->base.pages = pages; bo->base.pages_use_count = 1; @@ -501,12 +514,16 @@ int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr) dev_dbg(pfdev->dev, "mapped page fault @ AS%d %llx", as, addr); + drm_gem_object_put_unlocked(&bo->base.base); + return 0; err_map: sg_free_table(sgt); err_pages: drm_gem_shmem_put_pages(&bo->base); +err_bo: + drm_gem_object_put_unlocked(&bo->base.base); return ret; } diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 431e6b64b77d..d0bc91ed7c90 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -324,8 +324,39 @@ bool radeon_device_is_virtual(void); static int radeon_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { + unsigned long flags = 0; int ret; + if (!ent) + return -ENODEV; /* Avoid NULL-ptr deref in drm_get_pci_dev */ + + flags = ent->driver_data; + + if (!radeon_si_support) { + switch (flags & RADEON_FAMILY_MASK) { + case CHIP_TAHITI: + case CHIP_PITCAIRN: + case CHIP_VERDE: + case CHIP_OLAND: + case CHIP_HAINAN: + dev_info(&pdev->dev, + "SI support disabled by module param\n"); + return -ENODEV; + } + } + if (!radeon_cik_support) { + switch (flags & RADEON_FAMILY_MASK) { + case CHIP_KAVERI: + case CHIP_BONAIRE: + case CHIP_HAWAII: + case CHIP_KABINI: + case CHIP_MULLINS: + dev_info(&pdev->dev, + "CIK support disabled by module param\n"); + return -ENODEV; + } + } + if (vga_switcheroo_client_probe_defer(pdev)) return -EPROBE_DEFER; diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 4cf58dbbe439..b2b076606f54 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -296,6 +296,8 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data, uint32_t handle; int r; + args->addr = untagged_addr(args->addr); + if (offset_in_page(args->addr | args->size)) return -EINVAL; diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 07f7ace42c4b..e85c554eeaa9 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -100,31 +100,6 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) struct radeon_device *rdev; int r, acpi_status; - if (!radeon_si_support) { - switch (flags & RADEON_FAMILY_MASK) { - case CHIP_TAHITI: - case CHIP_PITCAIRN: - case CHIP_VERDE: - case CHIP_OLAND: - case CHIP_HAINAN: - dev_info(dev->dev, - "SI support disabled by module param\n"); - return -ENODEV; - } - } - if (!radeon_cik_support) { - switch (flags & RADEON_FAMILY_MASK) { - case CHIP_KAVERI: - case CHIP_BONAIRE: - case CHIP_HAWAII: - case CHIP_KABINI: - case CHIP_MULLINS: - dev_info(dev->dev, - "CIK support disabled by module param\n"); - return -ENODEV; - } - } - rdev = kzalloc(sizeof(struct radeon_device), GFP_KERNEL); if (rdev == NULL) { return -ENOMEM; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 2f821c58007c..613404f86668 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -39,8 +39,6 @@ #include "rockchip_drm_vop.h" #include "rockchip_rgb.h" -#define VOP_SELF_REFRESH_ENTRY_DELAY_MS 100 - #define VOP_WIN_SET(vop, win, name, v) \ vop_reg_set(vop, &win->phy->name, win->base, ~0, v, #name) #define VOP_SCL_SET(vop, win, name, v) \ @@ -1563,8 +1561,7 @@ static int vop_create_crtc(struct vop *vop) init_completion(&vop->line_flag_completion); crtc->port = port; - ret = drm_self_refresh_helper_init(crtc, - VOP_SELF_REFRESH_ENTRY_DELAY_MS); + ret = drm_self_refresh_helper_init(crtc); if (ret) DRM_DEV_DEBUG_KMS(vop->dev, "Failed to init %s with SR helpers %d, ignoring\n", diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 9f53f63b1453..7bff0a1e713d 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -1041,7 +1041,7 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps, if (cb) iowait_pio_inc(&priv->s_iowait); pbuf = sc_buffer_alloc(sc, plen, cb, qp); - if (unlikely(IS_ERR_OR_NULL(pbuf))) { + if (IS_ERR_OR_NULL(pbuf)) { if (cb) verbs_pio_complete(qp, 0); if (IS_ERR(pbuf)) { diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c index 76b4ac7b1678..aeb2f497c683 100644 --- a/drivers/media/v4l2-core/videobuf-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf-dma-contig.c @@ -157,6 +157,7 @@ static void videobuf_dma_contig_user_put(struct videobuf_dma_contig_memory *mem) static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem, struct videobuf_buffer *vb) { + unsigned long untagged_baddr = untagged_addr(vb->baddr); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long prev_pfn, this_pfn; @@ -164,22 +165,22 @@ static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem, unsigned int offset; int ret; - offset = vb->baddr & ~PAGE_MASK; + offset = untagged_baddr & ~PAGE_MASK; mem->size = PAGE_ALIGN(vb->size + offset); ret = -EINVAL; down_read(&mm->mmap_sem); - vma = find_vma(mm, vb->baddr); + vma = find_vma(mm, untagged_baddr); if (!vma) goto out_up; - if ((vb->baddr + mem->size) > vma->vm_end) + if ((untagged_baddr + mem->size) > vma->vm_end) goto out_up; pages_done = 0; prev_pfn = 0; /* kill warning */ - user_address = vb->baddr; + user_address = untagged_baddr; while (pages_done < (mem->size >> PAGE_SHIFT)) { ret = follow_pfn(vma, user_address, &this_pfn); diff --git a/drivers/net/wimax/i2400m/tx.c b/drivers/net/wimax/i2400m/tx.c index ebd64e083726..1255302e251e 100644 --- a/drivers/net/wimax/i2400m/tx.c +++ b/drivers/net/wimax/i2400m/tx.c @@ -654,8 +654,7 @@ void i2400m_tx_close(struct i2400m *i2400m) padding = aligned_size - tx_msg_moved->size; if (padding > 0) { pad_buf = i2400m_tx_fifo_push(i2400m, padding, 0, 0); - if (unlikely(WARN_ON(pad_buf == NULL - || pad_buf == TAIL_FULL))) { + if (WARN_ON(pad_buf == NULL || pad_buf == TAIL_FULL)) { /* This should not happen -- append should verify * there is always space left at least to append * tx_block_size */ diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 2859cc99b73e..156c2a18a239 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -78,7 +78,7 @@ static int ndev_mw_to_bar(struct amd_ntb_dev *ndev, int idx) if (idx < 0 || idx > ndev->mw_count) return -EINVAL; - return 1 << idx; + return ndev->dev_data->mw_idx << idx; } static int amd_ntb_mw_count(struct ntb_dev *ntb, int pidx) @@ -909,7 +909,7 @@ static int amd_init_ntb(struct amd_ntb_dev *ndev) { void __iomem *mmio = ndev->self_mmio; - ndev->mw_count = AMD_MW_CNT; + ndev->mw_count = ndev->dev_data->mw_count; ndev->spad_count = AMD_SPADS_CNT; ndev->db_count = AMD_DB_CNT; @@ -1069,6 +1069,8 @@ static int amd_ntb_pci_probe(struct pci_dev *pdev, goto err_ndev; } + ndev->dev_data = (struct ntb_dev_data *)id->driver_data; + ndev_init_struct(ndev, pdev); rc = amd_ntb_init_pci(ndev, pdev); @@ -1123,9 +1125,21 @@ static const struct file_operations amd_ntb_debugfs_info = { .read = ndev_debugfs_read, }; +static const struct ntb_dev_data dev_data[] = { + { /* for device 145b */ + .mw_count = 3, + .mw_idx = 1, + }, + { /* for device 148b */ + .mw_count = 2, + .mw_idx = 2, + }, +}; + static const struct pci_device_id amd_ntb_pci_tbl[] = { - {PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_NTB)}, - {0} + { PCI_VDEVICE(AMD, 0x145b), (kernel_ulong_t)&dev_data[0] }, + { PCI_VDEVICE(AMD, 0x148b), (kernel_ulong_t)&dev_data[1] }, + { 0, } }; MODULE_DEVICE_TABLE(pci, amd_ntb_pci_tbl); diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.h b/drivers/ntb/hw/amd/ntb_hw_amd.h index 8f3617a46292..139a307147bc 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.h +++ b/drivers/ntb/hw/amd/ntb_hw_amd.h @@ -52,7 +52,6 @@ #include <linux/ntb.h> #include <linux/pci.h> -#define PCI_DEVICE_ID_AMD_NTB 0x145B #define AMD_LINK_HB_TIMEOUT msecs_to_jiffies(1000) #define AMD_LINK_STATUS_OFFSET 0x68 #define NTB_LIN_STA_ACTIVE_BIT 0x00000002 @@ -93,7 +92,6 @@ static inline void _write64(u64 val, void __iomem *mmio) enum { /* AMD NTB Capability */ - AMD_MW_CNT = 3, AMD_DB_CNT = 16, AMD_MSIX_VECTOR_CNT = 24, AMD_SPADS_CNT = 16, @@ -170,6 +168,11 @@ enum { AMD_PEER_OFFSET = 0x400, }; +struct ntb_dev_data { + const unsigned char mw_count; + const unsigned int mw_idx; +}; + struct amd_ntb_dev; struct amd_ntb_vec { @@ -185,6 +188,7 @@ struct amd_ntb_dev { u32 cntl_sta; u32 peer_sta; + struct ntb_dev_data *dev_data; unsigned char mw_count; unsigned char spad_count; unsigned char db_count; diff --git a/drivers/ntb/hw/idt/Kconfig b/drivers/ntb/hw/idt/Kconfig index bfc7cac94102..c79b54c1747d 100644 --- a/drivers/ntb/hw/idt/Kconfig +++ b/drivers/ntb/hw/idt/Kconfig @@ -4,11 +4,11 @@ config NTB_IDT depends on PCI select HWMON help - This driver supports NTB of cappable IDT PCIe-switches. + This driver supports NTB of capable IDT PCIe-switches. Some of the pre-initializations must be made before IDT PCIe-switch - exposes it NT-functions correctly. It should be done by either proper - initialisation of EEPROM connected to master smbus of the switch or + exposes its NT-functions correctly. It should be done by either proper + initialization of EEPROM connected to master SMbus of the switch or by BIOS using slave-SMBus interface changing corresponding registers value. Evidently it must be done before PCI bus enumeration is finished in Linux kernel. diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c index f4959458d909..86ffa716eaf2 100644 --- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c +++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c @@ -306,7 +306,7 @@ static int switchtec_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, if (rc) return rc; - if (addr == 0 || size == 0) { + if (size == 0) { if (widx < nr_direct_mw) switchtec_ntb_mw_clr_direct(sndev, widx); else diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 40c90ca10729..00a5d5764993 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -292,7 +292,7 @@ static int ntb_transport_bus_match(struct device *dev, static int ntb_transport_bus_probe(struct device *dev) { const struct ntb_transport_client *client; - int rc = -EINVAL; + int rc; get_device(dev); diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index d028331558ea..e9b7c2dfc730 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -1378,7 +1378,7 @@ static int perf_setup_peer_mw(struct perf_peer *peer) int ret; /* Get outbound MW parameters and map it */ - ret = ntb_peer_mw_get_addr(perf->ntb, peer->gidx, &phys_addr, + ret = ntb_peer_mw_get_addr(perf->ntb, perf->gidx, &phys_addr, &peer->outbuf_size); if (ret) return ret; diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index 0005ec9285aa..b42a93736668 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -372,7 +372,7 @@ int ccwgroup_create_dev(struct device *parent, struct ccwgroup_driver *gdrv, goto error; } /* Check for trailing stuff. */ - if (i == num_devices && strlen(buf) > 0) { + if (i == num_devices && buf && strlen(buf) > 0) { rc = -EINVAL; goto error; } diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 22c55816100b..1fbfb0a93f5f 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1388,6 +1388,8 @@ device_initcall(cio_settle_init); int sch_is_pseudo_sch(struct subchannel *sch) { + if (!sch->dev.parent) + return 0; return sch == to_css(sch->dev.parent)->pseudo_subchannel; } diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index d722458c5928..65841af15748 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -124,9 +124,7 @@ EXPORT_SYMBOL(ccw_device_is_multipath); /** * ccw_device_clear() - terminate I/O request processing * @cdev: target ccw device - * @intparm: interruption parameter; value is only used if no I/O is - * outstanding, otherwise the intparm associated with the I/O request - * is returned + * @intparm: interruption parameter to be returned upon conclusion of csch * * ccw_device_clear() calls csch on @cdev's subchannel. * Returns: @@ -179,6 +177,9 @@ int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm) * completed during the time specified by @expires. If a timeout occurs, the * channel program is terminated via xsch, hsch or csch, and the device's * interrupt handler will be called with an irb containing ERR_PTR(-%ETIMEDOUT). + * The interruption handler will echo back the @intparm specified here, unless + * another interruption parameter is specified by a subsequent invocation of + * ccw_device_halt() or ccw_device_clear(). * Returns: * %0, if the operation was successful; * -%EBUSY, if the device is busy, or status pending; @@ -256,6 +257,9 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, * Start a S/390 channel program. When the interrupt arrives, the * IRQ handler is called, either immediately, delayed (dev-end missing, * or sense required) or never (no IRQ handler registered). + * The interruption handler will echo back the @intparm specified here, unless + * another interruption parameter is specified by a subsequent invocation of + * ccw_device_halt() or ccw_device_clear(). * Returns: * %0, if the operation was successful; * -%EBUSY, if the device is busy, or status pending; @@ -287,6 +291,9 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, * Start a S/390 channel program. When the interrupt arrives, the * IRQ handler is called, either immediately, delayed (dev-end missing, * or sense required) or never (no IRQ handler registered). + * The interruption handler will echo back the @intparm specified here, unless + * another interruption parameter is specified by a subsequent invocation of + * ccw_device_halt() or ccw_device_clear(). * Returns: * %0, if the operation was successful; * -%EBUSY, if the device is busy, or status pending; @@ -322,6 +329,9 @@ int ccw_device_start(struct ccw_device *cdev, struct ccw1 *cpa, * completed during the time specified by @expires. If a timeout occurs, the * channel program is terminated via xsch, hsch or csch, and the device's * interrupt handler will be called with an irb containing ERR_PTR(-%ETIMEDOUT). + * The interruption handler will echo back the @intparm specified here, unless + * another interruption parameter is specified by a subsequent invocation of + * ccw_device_halt() or ccw_device_clear(). * Returns: * %0, if the operation was successful; * -%EBUSY, if the device is busy, or status pending; @@ -343,11 +353,12 @@ int ccw_device_start_timeout(struct ccw_device *cdev, struct ccw1 *cpa, /** * ccw_device_halt() - halt I/O request processing * @cdev: target ccw device - * @intparm: interruption parameter; value is only used if no I/O is - * outstanding, otherwise the intparm associated with the I/O request - * is returned + * @intparm: interruption parameter to be returned upon conclusion of hsch * * ccw_device_halt() calls hsch on @cdev's subchannel. + * The interruption handler will echo back the @intparm specified here, unless + * another interruption parameter is specified by a subsequent invocation of + * ccw_device_clear(). * Returns: * %0 on success, * -%ENODEV on device not operational, diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index a76b8a8bcbbb..a1915061932e 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1322,24 +1322,24 @@ static int ap_get_compatible_type(ap_qid_t qid, int rawtype, unsigned int func) /* < CEX2A is not supported */ if (rawtype < AP_DEVICE_TYPE_CEX2A) return 0; - /* up to CEX6 known and fully supported */ - if (rawtype <= AP_DEVICE_TYPE_CEX6) + /* up to CEX7 known and fully supported */ + if (rawtype <= AP_DEVICE_TYPE_CEX7) return rawtype; /* - * unknown new type > CEX6, check for compatibility + * unknown new type > CEX7, check for compatibility * to the highest known and supported type which is - * currently CEX6 with the help of the QACT function. + * currently CEX7 with the help of the QACT function. */ if (ap_qact_available()) { struct ap_queue_status status; union ap_qact_ap_info apinfo = {0}; apinfo.mode = (func >> 26) & 0x07; - apinfo.cat = AP_DEVICE_TYPE_CEX6; + apinfo.cat = AP_DEVICE_TYPE_CEX7; status = ap_qact(qid, 0, &apinfo); if (status.response_code == AP_RESPONSE_NORMAL && apinfo.cat >= AP_DEVICE_TYPE_CEX2A - && apinfo.cat <= AP_DEVICE_TYPE_CEX6) + && apinfo.cat <= AP_DEVICE_TYPE_CEX7) comp_type = apinfo.cat; } if (!comp_type) diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 6f3cf37776ca..433b7b64368d 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0+ */ /* - * Copyright IBM Corp. 2006, 2012 + * Copyright IBM Corp. 2006, 2019 * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> * Ralph Wuerthner <rwuerthn@de.ibm.com> @@ -63,6 +63,7 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr) #define AP_DEVICE_TYPE_CEX4 10 #define AP_DEVICE_TYPE_CEX5 11 #define AP_DEVICE_TYPE_CEX6 12 +#define AP_DEVICE_TYPE_CEX7 13 /* * Known function facilities diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index f76a1d0f54c4..9de3d46b3253 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -1363,9 +1363,122 @@ static struct attribute_group ccadata_attr_group = { .bin_attrs = ccadata_attrs, }; +#define CCACIPHERTOKENSIZE (sizeof(struct cipherkeytoken) + 80) + +/* + * Sysfs attribute read function for all secure key ccacipher binary attributes. + * The implementation can not deal with partial reads, because a new random + * secure key blob is generated with each read. In case of partial reads + * (i.e. off != 0 or count < key blob size) -EINVAL is returned. + */ +static ssize_t pkey_ccacipher_aes_attr_read(enum pkey_key_size keybits, + bool is_xts, char *buf, loff_t off, + size_t count) +{ + size_t keysize; + int rc; + + if (off != 0 || count < CCACIPHERTOKENSIZE) + return -EINVAL; + if (is_xts) + if (count < 2 * CCACIPHERTOKENSIZE) + return -EINVAL; + + keysize = CCACIPHERTOKENSIZE; + rc = cca_gencipherkey(-1, -1, keybits, 0, buf, &keysize); + if (rc) + return rc; + memset(buf + keysize, 0, CCACIPHERTOKENSIZE - keysize); + + if (is_xts) { + keysize = CCACIPHERTOKENSIZE; + rc = cca_gencipherkey(-1, -1, keybits, 0, + buf + CCACIPHERTOKENSIZE, &keysize); + if (rc) + return rc; + memset(buf + CCACIPHERTOKENSIZE + keysize, 0, + CCACIPHERTOKENSIZE - keysize); + + return 2 * CCACIPHERTOKENSIZE; + } + + return CCACIPHERTOKENSIZE; +} + +static ssize_t ccacipher_aes_128_read(struct file *filp, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return pkey_ccacipher_aes_attr_read(PKEY_SIZE_AES_128, false, buf, + off, count); +} + +static ssize_t ccacipher_aes_192_read(struct file *filp, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return pkey_ccacipher_aes_attr_read(PKEY_SIZE_AES_192, false, buf, + off, count); +} + +static ssize_t ccacipher_aes_256_read(struct file *filp, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return pkey_ccacipher_aes_attr_read(PKEY_SIZE_AES_256, false, buf, + off, count); +} + +static ssize_t ccacipher_aes_128_xts_read(struct file *filp, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return pkey_ccacipher_aes_attr_read(PKEY_SIZE_AES_128, true, buf, + off, count); +} + +static ssize_t ccacipher_aes_256_xts_read(struct file *filp, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return pkey_ccacipher_aes_attr_read(PKEY_SIZE_AES_256, true, buf, + off, count); +} + +static BIN_ATTR_RO(ccacipher_aes_128, CCACIPHERTOKENSIZE); +static BIN_ATTR_RO(ccacipher_aes_192, CCACIPHERTOKENSIZE); +static BIN_ATTR_RO(ccacipher_aes_256, CCACIPHERTOKENSIZE); +static BIN_ATTR_RO(ccacipher_aes_128_xts, 2 * CCACIPHERTOKENSIZE); +static BIN_ATTR_RO(ccacipher_aes_256_xts, 2 * CCACIPHERTOKENSIZE); + +static struct bin_attribute *ccacipher_attrs[] = { + &bin_attr_ccacipher_aes_128, + &bin_attr_ccacipher_aes_192, + &bin_attr_ccacipher_aes_256, + &bin_attr_ccacipher_aes_128_xts, + &bin_attr_ccacipher_aes_256_xts, + NULL +}; + +static struct attribute_group ccacipher_attr_group = { + .name = "ccacipher", + .bin_attrs = ccacipher_attrs, +}; + static const struct attribute_group *pkey_attr_groups[] = { &protkey_attr_group, &ccadata_attr_group, + &ccacipher_attr_group, NULL, }; diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index 003662aa8060..be2520cc010b 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -36,6 +36,8 @@ static struct ap_device_id ap_queue_ids[] = { .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE }, { .dev_type = AP_DEVICE_TYPE_CEX6, .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE }, + { .dev_type = AP_DEVICE_TYPE_CEX7, + .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE }, { /* end of sibling */ }, }; diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index 2d3f2732344f..d464618cd84f 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0+ */ /* - * Copyright IBM Corp. 2001, 2018 + * Copyright IBM Corp. 2001, 2019 * Author(s): Robert Burroughs * Eric Rossman (edrossma@us.ibm.com) * Cornelia Huck <cornelia.huck@de.ibm.com> @@ -29,6 +29,7 @@ #define ZCRYPT_CEX4 10 #define ZCRYPT_CEX5 11 #define ZCRYPT_CEX6 12 +#define ZCRYPT_CEX7 13 /** * Large random numbers are pulled in 4096 byte chunks from the crypto cards diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c index f58d8dec19dc..442e3d6162f7 100644 --- a/drivers/s390/crypto/zcrypt_cex4.c +++ b/drivers/s390/crypto/zcrypt_cex4.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright IBM Corp. 2012 + * Copyright IBM Corp. 2012, 2019 * Author(s): Holger Dengler <hd@linux.vnet.ibm.com> */ @@ -38,8 +38,8 @@ #define CEX4_CLEANUP_TIME (900*HZ) MODULE_AUTHOR("IBM Corporation"); -MODULE_DESCRIPTION("CEX4/CEX5/CEX6 Cryptographic Card device driver, " \ - "Copyright IBM Corp. 2018"); +MODULE_DESCRIPTION("CEX4/CEX5/CEX6/CEX7 Cryptographic Card device driver, " \ + "Copyright IBM Corp. 2019"); MODULE_LICENSE("GPL"); static struct ap_device_id zcrypt_cex4_card_ids[] = { @@ -49,6 +49,8 @@ static struct ap_device_id zcrypt_cex4_card_ids[] = { .match_flags = AP_DEVICE_ID_MATCH_CARD_TYPE }, { .dev_type = AP_DEVICE_TYPE_CEX6, .match_flags = AP_DEVICE_ID_MATCH_CARD_TYPE }, + { .dev_type = AP_DEVICE_TYPE_CEX7, + .match_flags = AP_DEVICE_ID_MATCH_CARD_TYPE }, { /* end of list */ }, }; @@ -61,6 +63,8 @@ static struct ap_device_id zcrypt_cex4_queue_ids[] = { .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE }, { .dev_type = AP_DEVICE_TYPE_CEX6, .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE }, + { .dev_type = AP_DEVICE_TYPE_CEX7, + .match_flags = AP_DEVICE_ID_MATCH_QUEUE_TYPE }, { /* end of list */ }, }; @@ -146,7 +150,7 @@ static const struct attribute_group cca_queue_attr_group = { }; /** - * Probe function for CEX4/CEX5/CEX6 card device. It always + * Probe function for CEX4/CEX5/CEX6/CEX7 card device. It always * accepts the AP device since the bus_match already checked * the hardware type. * @ap_dev: pointer to the AP device. @@ -158,25 +162,31 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) * MEX_1k, MEX_2k, MEX_4k, CRT_1k, CRT_2k, CRT_4k, RNG, SECKEY */ static const int CEX4A_SPEED_IDX[] = { - 14, 19, 249, 42, 228, 1458, 0, 0}; + 14, 19, 249, 42, 228, 1458, 0, 0}; static const int CEX5A_SPEED_IDX[] = { - 8, 9, 20, 18, 66, 458, 0, 0}; + 8, 9, 20, 18, 66, 458, 0, 0}; static const int CEX6A_SPEED_IDX[] = { - 6, 9, 20, 17, 65, 438, 0, 0}; + 6, 9, 20, 17, 65, 438, 0, 0}; + static const int CEX7A_SPEED_IDX[] = { + 6, 8, 17, 15, 54, 362, 0, 0}; static const int CEX4C_SPEED_IDX[] = { 59, 69, 308, 83, 278, 2204, 209, 40}; static const int CEX5C_SPEED_IDX[] = { - 24, 31, 50, 37, 90, 479, 27, 10}; + 24, 31, 50, 37, 90, 479, 27, 10}; static const int CEX6C_SPEED_IDX[] = { - 16, 20, 32, 27, 77, 455, 23, 9}; + 16, 20, 32, 27, 77, 455, 24, 9}; + static const int CEX7C_SPEED_IDX[] = { + 14, 16, 26, 23, 64, 376, 23, 8}; static const int CEX4P_SPEED_IDX[] = { - 224, 313, 3560, 359, 605, 2827, 0, 50}; + 0, 0, 0, 0, 0, 0, 0, 50}; static const int CEX5P_SPEED_IDX[] = { - 63, 84, 156, 83, 142, 533, 0, 10}; + 0, 0, 0, 0, 0, 0, 0, 10}; static const int CEX6P_SPEED_IDX[] = { - 55, 70, 121, 73, 129, 522, 0, 9}; + 0, 0, 0, 0, 0, 0, 0, 9}; + static const int CEX7P_SPEED_IDX[] = { + 0, 0, 0, 0, 0, 0, 0, 8}; struct ap_card *ac = to_ap_card(&ap_dev->device); struct zcrypt_card *zc; @@ -198,11 +208,19 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) zc->user_space_type = ZCRYPT_CEX5; memcpy(zc->speed_rating, CEX5A_SPEED_IDX, sizeof(CEX5A_SPEED_IDX)); - } else { + } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX6) { zc->type_string = "CEX6A"; zc->user_space_type = ZCRYPT_CEX6; memcpy(zc->speed_rating, CEX6A_SPEED_IDX, sizeof(CEX6A_SPEED_IDX)); + } else { + zc->type_string = "CEX7A"; + /* wrong user space type, just for compatibility + * with the ZCRYPT_STATUS_MASK ioctl. + */ + zc->user_space_type = ZCRYPT_CEX6; + memcpy(zc->speed_rating, CEX7A_SPEED_IDX, + sizeof(CEX7A_SPEED_IDX)); } zc->min_mod_size = CEX4A_MIN_MOD_SIZE; if (ap_test_bit(&ac->functions, AP_FUNC_MEX4K) && @@ -232,7 +250,7 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) zc->user_space_type = ZCRYPT_CEX3C; memcpy(zc->speed_rating, CEX5C_SPEED_IDX, sizeof(CEX5C_SPEED_IDX)); - } else { + } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX6) { zc->type_string = "CEX6C"; /* wrong user space type, must be CEX6 * just keep it for cca compatibility @@ -240,6 +258,14 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) zc->user_space_type = ZCRYPT_CEX3C; memcpy(zc->speed_rating, CEX6C_SPEED_IDX, sizeof(CEX6C_SPEED_IDX)); + } else { + zc->type_string = "CEX7C"; + /* wrong user space type, must be CEX7 + * just keep it for cca compatibility + */ + zc->user_space_type = ZCRYPT_CEX3C; + memcpy(zc->speed_rating, CEX7C_SPEED_IDX, + sizeof(CEX7C_SPEED_IDX)); } zc->min_mod_size = CEX4C_MIN_MOD_SIZE; zc->max_mod_size = CEX4C_MAX_MOD_SIZE; @@ -255,11 +281,19 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) zc->user_space_type = ZCRYPT_CEX5; memcpy(zc->speed_rating, CEX5P_SPEED_IDX, sizeof(CEX5P_SPEED_IDX)); - } else { + } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX6) { zc->type_string = "CEX6P"; zc->user_space_type = ZCRYPT_CEX6; memcpy(zc->speed_rating, CEX6P_SPEED_IDX, sizeof(CEX6P_SPEED_IDX)); + } else { + zc->type_string = "CEX7P"; + /* wrong user space type, just for compatibility + * with the ZCRYPT_STATUS_MASK ioctl. + */ + zc->user_space_type = ZCRYPT_CEX6; + memcpy(zc->speed_rating, CEX7P_SPEED_IDX, + sizeof(CEX7P_SPEED_IDX)); } zc->min_mod_size = CEX4C_MIN_MOD_SIZE; zc->max_mod_size = CEX4C_MAX_MOD_SIZE; @@ -289,8 +323,8 @@ out: } /** - * This is called to remove the CEX4/CEX5/CEX6 card driver information - * if an AP card device is removed. + * This is called to remove the CEX4/CEX5/CEX6/CEX7 card driver + * information if an AP card device is removed. */ static void zcrypt_cex4_card_remove(struct ap_device *ap_dev) { @@ -311,7 +345,7 @@ static struct ap_driver zcrypt_cex4_card_driver = { }; /** - * Probe function for CEX4/CEX5/CEX6 queue device. It always + * Probe function for CEX4/CEX5/CEX6/CEX7 queue device. It always * accepts the AP device since the bus_match already checked * the hardware type. * @ap_dev: pointer to the AP device. @@ -369,7 +403,7 @@ out: } /** - * This is called to remove the CEX4/CEX5/CEX6 queue driver + * This is called to remove the CEX4/CEX5/CEX6/CEX7 queue driver * information if an AP queue device is removed. */ static void zcrypt_cex4_queue_remove(struct ap_device *ap_dev) diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 2da026fd12c9..09ddcd06c715 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -254,6 +254,7 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, shm->teedev = teedev; shm->ctx = ctx; shm->id = -1; + addr = untagged_addr(addr); start = rounddown(addr, PAGE_SIZE); shm->offset = addr - start; shm->size = length; diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c index 8c07a393dc2e..709a22f455e9 100644 --- a/drivers/thermal/armada_thermal.c +++ b/drivers/thermal/armada_thermal.c @@ -53,7 +53,6 @@ #define CONTROL0_TSEN_MODE_EXTERNAL 0x2 #define CONTROL0_TSEN_MODE_MASK 0x3 -#define CONTROL1_TSEN_AVG_SHIFT 0 #define CONTROL1_TSEN_AVG_MASK 0x7 #define CONTROL1_EXT_TSEN_SW_RESET BIT(7) #define CONTROL1_EXT_TSEN_HW_RESETn BIT(8) @@ -267,8 +266,8 @@ static void armada_cp110_init(struct platform_device *pdev, /* Average the output value over 2^1 = 2 samples */ regmap_read(priv->syscon, data->syscon_control1_off, ®); - reg &= ~CONTROL1_TSEN_AVG_MASK << CONTROL1_TSEN_AVG_SHIFT; - reg |= 1 << CONTROL1_TSEN_AVG_SHIFT; + reg &= ~CONTROL1_TSEN_AVG_MASK; + reg |= 1; regmap_write(priv->syscon, data->syscon_control1_off, reg); } diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c index 9716bc3abaf9..7130e90773ed 100644 --- a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c +++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c @@ -77,9 +77,6 @@ int acpi_parse_trt(acpi_handle handle, int *trt_count, struct trt **trtp, struct acpi_buffer element = { 0, NULL }; struct acpi_buffer trt_format = { sizeof("RRNNNNNN"), "RRNNNNNN" }; - if (!acpi_has_method(handle, "_TRT")) - return -ENODEV; - status = acpi_evaluate_object(handle, "_TRT", NULL, &buffer); if (ACPI_FAILURE(status)) return -ENODEV; @@ -158,9 +155,6 @@ int acpi_parse_art(acpi_handle handle, int *art_count, struct art **artp, struct acpi_buffer art_format = { sizeof("RRNNNNNNNNNNN"), "RRNNNNNNNNNNN" }; - if (!acpi_has_method(handle, "_ART")) - return -ENODEV; - status = acpi_evaluate_object(handle, "_ART", NULL, &buffer); if (ACPI_FAILURE(status)) return -ENODEV; diff --git a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c index f5749d4418ae..a7bbd8584ae2 100644 --- a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c @@ -181,7 +181,7 @@ static int int3403_cdev_add(struct int3403_priv *priv) p = buf.pointer; if (!p || (p->type != ACPI_TYPE_PACKAGE)) { - printk(KERN_WARNING "Invalid PPSS data\n"); + pr_warn("Invalid PPSS data\n"); kfree(buf.pointer); return -EFAULT; } diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c index d3446acf9bbd..89a015387283 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c @@ -39,6 +39,9 @@ /* GeminiLake thermal reporting device */ #define PCI_DEVICE_ID_PROC_GLK_THERMAL 0x318C +/* IceLake thermal reporting device */ +#define PCI_DEVICE_ID_PROC_ICL_THERMAL 0x8a03 + #define DRV_NAME "proc_thermal" struct power_config { @@ -137,6 +140,72 @@ static const struct attribute_group power_limit_attribute_group = { .name = "power_limits" }; +static ssize_t tcc_offset_degree_celsius_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u64 val; + int err; + + err = rdmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, &val); + if (err) + return err; + + val = (val >> 24) & 0xff; + return sprintf(buf, "%d\n", (int)val); +} + +static int tcc_offset_update(int tcc) +{ + u64 val; + int err; + + if (!tcc) + return -EINVAL; + + err = rdmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, &val); + if (err) + return err; + + val &= ~GENMASK_ULL(31, 24); + val |= (tcc & 0xff) << 24; + + err = wrmsrl_safe(MSR_IA32_TEMPERATURE_TARGET, val); + if (err) + return err; + + return 0; +} + +static int tcc_offset_save; + +static ssize_t tcc_offset_degree_celsius_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + u64 val; + int tcc, err; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, &val); + if (err) + return err; + + if (!(val & BIT(30))) + return -EACCES; + + if (kstrtoint(buf, 0, &tcc)) + return -EINVAL; + + err = tcc_offset_update(tcc); + if (err) + return err; + + tcc_offset_save = tcc; + + return count; +} + +static DEVICE_ATTR_RW(tcc_offset_degree_celsius); + static int stored_tjmax; /* since it is fixed, we can have local storage */ static int get_tjmax(void) @@ -332,6 +401,7 @@ static void proc_thermal_remove(struct proc_thermal_device *proc_priv) acpi_remove_notify_handler(proc_priv->adev->handle, ACPI_DEVICE_NOTIFY, proc_thermal_notify); int340x_thermal_zone_remove(proc_priv->int340x_zone); + sysfs_remove_file(&proc_priv->dev->kobj, &dev_attr_tcc_offset_degree_celsius.attr); sysfs_remove_group(&proc_priv->dev->kobj, &power_limit_attribute_group); } @@ -355,8 +425,15 @@ static int int3401_add(struct platform_device *pdev) dev_info(&pdev->dev, "Creating sysfs group for PROC_THERMAL_PLATFORM_DEV\n"); - return sysfs_create_group(&pdev->dev.kobj, - &power_limit_attribute_group); + ret = sysfs_create_file(&pdev->dev.kobj, &dev_attr_tcc_offset_degree_celsius.attr); + if (ret) + return ret; + + ret = sysfs_create_group(&pdev->dev.kobj, &power_limit_attribute_group); + if (ret) + sysfs_remove_file(&pdev->dev.kobj, &dev_attr_tcc_offset_degree_celsius.attr); + + return ret; } static int int3401_remove(struct platform_device *pdev) @@ -588,8 +665,15 @@ static int proc_thermal_pci_probe(struct pci_dev *pdev, dev_info(&pdev->dev, "Creating sysfs group for PROC_THERMAL_PCI\n"); - return sysfs_create_group(&pdev->dev.kobj, - &power_limit_attribute_group); + ret = sysfs_create_file(&pdev->dev.kobj, &dev_attr_tcc_offset_degree_celsius.attr); + if (ret) + return ret; + + ret = sysfs_create_group(&pdev->dev.kobj, &power_limit_attribute_group); + if (ret) + sysfs_remove_file(&pdev->dev.kobj, &dev_attr_tcc_offset_degree_celsius.attr); + + return ret; } static void proc_thermal_pci_remove(struct pci_dev *pdev) @@ -615,6 +699,8 @@ static int proc_thermal_resume(struct device *dev) proc_dev = dev_get_drvdata(dev); proc_thermal_read_ppcc(proc_dev); + tcc_offset_update(tcc_offset_save); + return 0; } #else @@ -636,6 +722,8 @@ static const struct pci_device_id proc_thermal_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_CNL_THERMAL)}, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_CFL_THERMAL)}, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_GLK_THERMAL)}, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_ICL_THERMAL), + .driver_data = (kernel_ulong_t)&rapl_mmio_hsw, }, { 0, }, }; diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c index 99f8b2540f18..4f0bb8f502e1 100644 --- a/drivers/thermal/intel/intel_pch_thermal.c +++ b/drivers/thermal/intel/intel_pch_thermal.c @@ -371,16 +371,14 @@ static void intel_pch_thermal_remove(struct pci_dev *pdev) static int intel_pch_thermal_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct pch_thermal_device *ptd = pci_get_drvdata(pdev); + struct pch_thermal_device *ptd = dev_get_drvdata(device); return ptd->ops->suspend(ptd); } static int intel_pch_thermal_resume(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct pch_thermal_device *ptd = pci_get_drvdata(pdev); + struct pch_thermal_device *ptd = dev_get_drvdata(device); return ptd->ops->resume(ptd); } diff --git a/drivers/thermal/qcom/tsens-8960.c b/drivers/thermal/qcom/tsens-8960.c index 8d9b721dadb6..e46a4e3f25c4 100644 --- a/drivers/thermal/qcom/tsens-8960.c +++ b/drivers/thermal/qcom/tsens-8960.c @@ -229,6 +229,8 @@ static int calibrate_8960(struct tsens_priv *priv) for (i = 0; i < num_read; i++, s++) s->offset = data[i]; + kfree(data); + return 0; } diff --git a/drivers/thermal/qcom/tsens-v0_1.c b/drivers/thermal/qcom/tsens-v0_1.c index 6f26fadf4c27..055647bcee67 100644 --- a/drivers/thermal/qcom/tsens-v0_1.c +++ b/drivers/thermal/qcom/tsens-v0_1.c @@ -145,8 +145,10 @@ static int calibrate_8916(struct tsens_priv *priv) return PTR_ERR(qfprom_cdata); qfprom_csel = (u32 *)qfprom_read(priv->dev, "calib_sel"); - if (IS_ERR(qfprom_csel)) + if (IS_ERR(qfprom_csel)) { + kfree(qfprom_cdata); return PTR_ERR(qfprom_csel); + } mode = (qfprom_csel[0] & MSM8916_CAL_SEL_MASK) >> MSM8916_CAL_SEL_SHIFT; dev_dbg(priv->dev, "calibration mode is %d\n", mode); @@ -181,6 +183,8 @@ static int calibrate_8916(struct tsens_priv *priv) } compute_intercept_slope(priv, p1, p2, mode); + kfree(qfprom_cdata); + kfree(qfprom_csel); return 0; } @@ -198,8 +202,10 @@ static int calibrate_8974(struct tsens_priv *priv) return PTR_ERR(calib); bkp = (u32 *)qfprom_read(priv->dev, "calib_backup"); - if (IS_ERR(bkp)) + if (IS_ERR(bkp)) { + kfree(calib); return PTR_ERR(bkp); + } calib_redun_sel = bkp[1] & BKP_REDUN_SEL; calib_redun_sel >>= BKP_REDUN_SHIFT; @@ -313,6 +319,8 @@ static int calibrate_8974(struct tsens_priv *priv) } compute_intercept_slope(priv, p1, p2, mode); + kfree(calib); + kfree(bkp); return 0; } diff --git a/drivers/thermal/qcom/tsens-v1.c b/drivers/thermal/qcom/tsens-v1.c index 10b595d4f619..870f502f2cb6 100644 --- a/drivers/thermal/qcom/tsens-v1.c +++ b/drivers/thermal/qcom/tsens-v1.c @@ -138,6 +138,7 @@ static int calibrate_v1(struct tsens_priv *priv) } compute_intercept_slope(priv, p1, p2, mode); + kfree(qfprom_cdata); return 0; } diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h index 2fd94997245b..b89083b61c38 100644 --- a/drivers/thermal/qcom/tsens.h +++ b/drivers/thermal/qcom/tsens.h @@ -17,6 +17,7 @@ #include <linux/thermal.h> #include <linux/regmap.h> +#include <linux/slab.h> struct tsens_priv; diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c index 7b364933bfb1..39542c670301 100644 --- a/drivers/thermal/qoriq_thermal.c +++ b/drivers/thermal/qoriq_thermal.c @@ -2,6 +2,7 @@ // // Copyright 2016 Freescale Semiconductor, Inc. +#include <linux/clk.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/err.h> @@ -72,6 +73,7 @@ struct qoriq_sensor { struct qoriq_tmu_data { struct qoriq_tmu_regs __iomem *regs; + struct clk *clk; bool little_endian; struct qoriq_sensor *sensor[SITES_MAX]; }; @@ -202,32 +204,39 @@ static int qoriq_tmu_probe(struct platform_device *pdev) data->little_endian = of_property_read_bool(np, "little-endian"); - data->regs = of_iomap(np, 0); - if (!data->regs) { + data->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(data->regs)) { dev_err(&pdev->dev, "Failed to get memory region\n"); - ret = -ENODEV; - goto err_iomap; + return PTR_ERR(data->regs); + } + + data->clk = devm_clk_get_optional(&pdev->dev, NULL); + if (IS_ERR(data->clk)) + return PTR_ERR(data->clk); + + ret = clk_prepare_enable(data->clk); + if (ret) { + dev_err(&pdev->dev, "Failed to enable clock\n"); + return ret; } qoriq_tmu_init_device(data); /* TMU initialization */ ret = qoriq_tmu_calibration(pdev); /* TMU calibration */ if (ret < 0) - goto err_tmu; + goto err; ret = qoriq_tmu_register_tmu_zone(pdev); if (ret < 0) { dev_err(&pdev->dev, "Failed to register sensors\n"); ret = -ENODEV; - goto err_iomap; + goto err; } return 0; -err_tmu: - iounmap(data->regs); - -err_iomap: +err: + clk_disable_unprepare(data->clk); platform_set_drvdata(pdev, NULL); return ret; @@ -240,14 +249,14 @@ static int qoriq_tmu_remove(struct platform_device *pdev) /* Disable monitoring */ tmu_write(data, TMR_DISABLE, &data->regs->tmr); - iounmap(data->regs); + clk_disable_unprepare(data->clk); + platform_set_drvdata(pdev, NULL); return 0; } -#ifdef CONFIG_PM_SLEEP -static int qoriq_tmu_suspend(struct device *dev) +static int __maybe_unused qoriq_tmu_suspend(struct device *dev) { u32 tmr; struct qoriq_tmu_data *data = dev_get_drvdata(dev); @@ -257,14 +266,21 @@ static int qoriq_tmu_suspend(struct device *dev) tmr &= ~TMR_ME; tmu_write(data, tmr, &data->regs->tmr); + clk_disable_unprepare(data->clk); + return 0; } -static int qoriq_tmu_resume(struct device *dev) +static int __maybe_unused qoriq_tmu_resume(struct device *dev) { u32 tmr; + int ret; struct qoriq_tmu_data *data = dev_get_drvdata(dev); + ret = clk_prepare_enable(data->clk); + if (ret) + return ret; + /* Enable monitoring */ tmr = tmu_read(data, &data->regs->tmr); tmr |= TMR_ME; @@ -272,7 +288,6 @@ static int qoriq_tmu_resume(struct device *dev) return 0; } -#endif static SIMPLE_DEV_PM_OPS(qoriq_tmu_pm_ops, qoriq_tmu_suspend, qoriq_tmu_resume); diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c index a56463308694..755d2b5bd2c2 100644 --- a/drivers/thermal/rcar_gen3_thermal.c +++ b/drivers/thermal/rcar_gen3_thermal.c @@ -443,9 +443,8 @@ static int rcar_gen3_thermal_probe(struct platform_device *pdev) if (ret) goto error_unregister; - ret = devm_add_action(dev, rcar_gen3_hwmon_action, zone); + ret = devm_add_action_or_reset(dev, rcar_gen3_hwmon_action, zone); if (ret) { - rcar_gen3_hwmon_action(zone); goto error_unregister; } diff --git a/drivers/thermal/tegra/soctherm.c b/drivers/thermal/tegra/soctherm.c index 43941eb734eb..5acaad3a594f 100644 --- a/drivers/thermal/tegra/soctherm.c +++ b/drivers/thermal/tegra/soctherm.c @@ -202,7 +202,7 @@ /* get dividend from the depth */ #define THROT_DEPTH_DIVIDEND(depth) ((256 * (100 - (depth)) / 100) - 1) -/* gk20a nv_therm interface N:3 Mapping. Levels defined in tegra124-sochterm.h +/* gk20a nv_therm interface N:3 Mapping. Levels defined in tegra124-soctherm.h * level vector * NONE 3'b000 * LOW 3'b001 diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 6bab66e84eb5..d4481cc8958f 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -304,7 +304,7 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz, &tz->poll_queue, msecs_to_jiffies(delay)); else - cancel_delayed_work(&tz->poll_queue); + cancel_delayed_work_sync(&tz->poll_queue); } static void monitor_thermal_zone(struct thermal_zone_device *tz) @@ -985,7 +985,7 @@ __thermal_cooling_device_register(struct device_node *np, result = device_register(&cdev->device); if (result) { ida_simple_remove(&thermal_cdev_ida, cdev->id); - kfree(cdev); + put_device(&cdev->device); return ERR_PTR(result); } @@ -1240,21 +1240,31 @@ thermal_zone_device_register(const char *type, int trips, int mask, struct thermal_zone_device *tz; enum thermal_trip_type trip_type; int trip_temp; + int id; int result; int count; struct thermal_governor *governor; - if (!type || strlen(type) == 0) + if (!type || strlen(type) == 0) { + pr_err("Error: No thermal zone type defined\n"); return ERR_PTR(-EINVAL); + } - if (type && strlen(type) >= THERMAL_NAME_LENGTH) + if (type && strlen(type) >= THERMAL_NAME_LENGTH) { + pr_err("Error: Thermal zone name (%s) too long, should be under %d chars\n", + type, THERMAL_NAME_LENGTH); return ERR_PTR(-EINVAL); + } - if (trips > THERMAL_MAX_TRIPS || trips < 0 || mask >> trips) + if (trips > THERMAL_MAX_TRIPS || trips < 0 || mask >> trips) { + pr_err("Error: Incorrect number of thermal trips\n"); return ERR_PTR(-EINVAL); + } - if (!ops) + if (!ops) { + pr_err("Error: Thermal zone device ops not defined\n"); return ERR_PTR(-EINVAL); + } if (trips > 0 && (!ops->get_trip_type || !ops->get_trip_temp)) return ERR_PTR(-EINVAL); @@ -1266,11 +1276,13 @@ thermal_zone_device_register(const char *type, int trips, int mask, INIT_LIST_HEAD(&tz->thermal_instances); ida_init(&tz->ida); mutex_init(&tz->lock); - result = ida_simple_get(&thermal_tz_ida, 0, 0, GFP_KERNEL); - if (result < 0) + id = ida_simple_get(&thermal_tz_ida, 0, 0, GFP_KERNEL); + if (id < 0) { + result = id; goto free_tz; + } - tz->id = result; + tz->id = id; strlcpy(tz->type, type, sizeof(tz->type)); tz->ops = ops; tz->tzp = tzp; @@ -1292,7 +1304,7 @@ thermal_zone_device_register(const char *type, int trips, int mask, dev_set_name(&tz->device, "thermal_zone%d", tz->id); result = device_register(&tz->device); if (result) - goto remove_device_groups; + goto release_device; for (count = 0; count < trips; count++) { if (tz->ops->get_trip_type(tz, count, &trip_type)) @@ -1343,14 +1355,12 @@ thermal_zone_device_register(const char *type, int trips, int mask, return tz; unregister: - ida_simple_remove(&thermal_tz_ida, tz->id); - device_unregister(&tz->device); - return ERR_PTR(result); - -remove_device_groups: - thermal_zone_destroy_device_groups(tz); + device_del(&tz->device); +release_device: + put_device(&tz->device); + tz = NULL; remove_id: - ida_simple_remove(&thermal_tz_ida, tz->id); + ida_simple_remove(&thermal_tz_ida, id); free_tz: kfree(tz); return ERR_PTR(result); diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index 40c69a533b24..dd5d8ee37928 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -87,13 +87,17 @@ static struct thermal_hwmon_device * thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz) { struct thermal_hwmon_device *hwmon; + char type[THERMAL_NAME_LENGTH]; mutex_lock(&thermal_hwmon_list_lock); - list_for_each_entry(hwmon, &thermal_hwmon_list, node) - if (!strcmp(hwmon->type, tz->type)) { + list_for_each_entry(hwmon, &thermal_hwmon_list, node) { + strcpy(type, tz->type); + strreplace(type, '-', '_'); + if (!strcmp(hwmon->type, type)) { mutex_unlock(&thermal_hwmon_list_lock); return hwmon; } + } mutex_unlock(&thermal_hwmon_list_lock); return NULL; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 9a50b0558fa9..96fddc1dafc3 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -375,6 +375,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, down_read(&mm->mmap_sem); + vaddr = untagged_addr(vaddr); + vma = find_vma_intersection(mm, vaddr, vaddr + 1); if (vma && vma->vm_flags & VM_PFNMAP) { diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index a45f9e3e442b..58e7c100b6ad 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -477,13 +477,6 @@ config IXP4XX_WATCHDOG Say N if you are unsure. -config KS8695_WATCHDOG - tristate "KS8695 watchdog" - depends on ARCH_KS8695 - help - Watchdog timer embedded into KS8695 processor. This will reboot your - system when the timeout is reached. - config HAVE_S3C2410_WATCHDOG bool help @@ -662,15 +655,6 @@ config STMP3XXX_RTC_WATCHDOG To compile this driver as a module, choose M here: the module will be called stmp3xxx_rtc_wdt. -config NUC900_WATCHDOG - tristate "Nuvoton NUC900 watchdog" - depends on ARCH_W90X900 || COMPILE_TEST - help - Say Y here if to include support for the watchdog timer - for the Nuvoton NUC900 series SoCs. - To compile this driver as a module, choose M here: the - module will be called nuc900_wdt. - config TS4800_WATCHDOG tristate "TS-4800 Watchdog" depends on HAS_IOMEM && OF @@ -740,6 +724,19 @@ config IMX_SC_WDT To compile this driver as a module, choose M here: the module will be called imx_sc_wdt. +config IMX7ULP_WDT + tristate "IMX7ULP Watchdog" + depends on ARCH_MXC || COMPILE_TEST + select WATCHDOG_CORE + help + This is the driver for the hardware watchdog on the Freescale + IMX7ULP and later processors. If you have one of these + processors and wish to have watchdog support enabled, + say Y, otherwise say N. + + To compile this driver as a module, choose M here: the + module will be called imx7ulp_wdt. + config UX500_WATCHDOG tristate "ST-Ericsson Ux500 watchdog" depends on MFD_DB8500_PRCMU @@ -1046,8 +1043,8 @@ config F71808E_WDT depends on X86 help This is the driver for the hardware watchdog on the Fintek F71808E, - F71862FG, F71868, F71869, F71882FG, F71889FG, F81865 and F81866 - Super I/O controllers. + F71862FG, F71868, F71869, F71882FG, F71889FG, F81803, F81865, and + F81866 Super I/O controllers. You can compile this driver directly into the kernel, or use it as a module. The module will be called f71808e_wdt. diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index 7caa920e7e60..2ee352bf3372 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -49,7 +49,6 @@ obj-$(CONFIG_21285_WATCHDOG) += wdt285.o obj-$(CONFIG_977_WATCHDOG) += wdt977.o obj-$(CONFIG_FTWDT010_WATCHDOG) += ftwdt010_wdt.o obj-$(CONFIG_IXP4XX_WATCHDOG) += ixp4xx_wdt.o -obj-$(CONFIG_KS8695_WATCHDOG) += ks8695_wdt.o obj-$(CONFIG_S3C2410_WATCHDOG) += s3c2410_wdt.o obj-$(CONFIG_SA1100_WATCHDOG) += sa1100_wdt.o obj-$(CONFIG_SAMA5D4_WATCHDOG) += sama5d4_wdt.o @@ -64,11 +63,11 @@ obj-$(CONFIG_RN5T618_WATCHDOG) += rn5t618_wdt.o obj-$(CONFIG_COH901327_WATCHDOG) += coh901327_wdt.o obj-$(CONFIG_NPCM7XX_WATCHDOG) += npcm_wdt.o obj-$(CONFIG_STMP3XXX_RTC_WATCHDOG) += stmp3xxx_rtc_wdt.o -obj-$(CONFIG_NUC900_WATCHDOG) += nuc900_wdt.o obj-$(CONFIG_TS4800_WATCHDOG) += ts4800_wdt.o obj-$(CONFIG_TS72XX_WATCHDOG) += ts72xx_wdt.o obj-$(CONFIG_IMX2_WDT) += imx2_wdt.o obj-$(CONFIG_IMX_SC_WDT) += imx_sc_wdt.o +obj-$(CONFIG_IMX7ULP_WDT) += imx7ulp_wdt.o obj-$(CONFIG_UX500_WATCHDOG) += ux500_wdt.o obj-$(CONFIG_RETU_WATCHDOG) += retu_wdt.o obj-$(CONFIG_BCM2835_WDT) += bcm2835_wdt.o diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c index cc71861e033a..4ec0906bf12c 100644 --- a/drivers/watchdog/aspeed_wdt.c +++ b/drivers/watchdog/aspeed_wdt.c @@ -34,6 +34,7 @@ static const struct aspeed_wdt_config ast2500_config = { static const struct of_device_id aspeed_wdt_of_table[] = { { .compatible = "aspeed,ast2400-wdt", .data = &ast2400_config }, { .compatible = "aspeed,ast2500-wdt", .data = &ast2500_config }, + { .compatible = "aspeed,ast2600-wdt", .data = &ast2500_config }, { }, }; MODULE_DEVICE_TABLE(of, aspeed_wdt_of_table); @@ -53,6 +54,8 @@ MODULE_DEVICE_TABLE(of, aspeed_wdt_of_table); #define WDT_CTRL_ENABLE BIT(0) #define WDT_TIMEOUT_STATUS 0x10 #define WDT_TIMEOUT_STATUS_BOOT_SECONDARY BIT(1) +#define WDT_CLEAR_TIMEOUT_STATUS 0x14 +#define WDT_CLEAR_TIMEOUT_AND_BOOT_CODE_SELECTION BIT(0) /* * WDT_RESET_WIDTH controls the characteristics of the external pulse (if @@ -165,6 +168,60 @@ static int aspeed_wdt_restart(struct watchdog_device *wdd, return 0; } +/* access_cs0 shows if cs0 is accessible, hence the reverted bit */ +static ssize_t access_cs0_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct aspeed_wdt *wdt = dev_get_drvdata(dev); + u32 status = readl(wdt->base + WDT_TIMEOUT_STATUS); + + return sprintf(buf, "%u\n", + !(status & WDT_TIMEOUT_STATUS_BOOT_SECONDARY)); +} + +static ssize_t access_cs0_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t size) +{ + struct aspeed_wdt *wdt = dev_get_drvdata(dev); + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + if (val) + writel(WDT_CLEAR_TIMEOUT_AND_BOOT_CODE_SELECTION, + wdt->base + WDT_CLEAR_TIMEOUT_STATUS); + + return size; +} + +/* + * This attribute exists only if the system has booted from the alternate + * flash with 'alt-boot' option. + * + * At alternate flash the 'access_cs0' sysfs node provides: + * ast2400: a way to get access to the primary SPI flash chip at CS0 + * after booting from the alternate chip at CS1. + * ast2500: a way to restore the normal address mapping from + * (CS0->CS1, CS1->CS0) to (CS0->CS0, CS1->CS1). + * + * Clearing the boot code selection and timeout counter also resets to the + * initial state the chip select line mapping. When the SoC is in normal + * mapping state (i.e. booted from CS0), clearing those bits does nothing for + * both versions of the SoC. For alternate boot mode (booted from CS1 due to + * wdt2 expiration) the behavior differs as described above. + * + * This option can be used with wdt2 (watchdog1) only. + */ +static DEVICE_ATTR_RW(access_cs0); + +static struct attribute *bswitch_attrs[] = { + &dev_attr_access_cs0.attr, + NULL +}; +ATTRIBUTE_GROUPS(bswitch); + static const struct watchdog_ops aspeed_wdt_ops = { .start = aspeed_wdt_start, .stop = aspeed_wdt_stop, @@ -259,7 +316,8 @@ static int aspeed_wdt_probe(struct platform_device *pdev) set_bit(WDOG_HW_RUNNING, &wdt->wdd.status); } - if (of_device_is_compatible(np, "aspeed,ast2500-wdt")) { + if ((of_device_is_compatible(np, "aspeed,ast2500-wdt")) || + (of_device_is_compatible(np, "aspeed,ast2600-wdt"))) { u32 reg = readl(wdt->base + WDT_RESET_WIDTH); reg &= config->ext_pulse_width_mask; @@ -306,9 +364,16 @@ static int aspeed_wdt_probe(struct platform_device *pdev) } status = readl(wdt->base + WDT_TIMEOUT_STATUS); - if (status & WDT_TIMEOUT_STATUS_BOOT_SECONDARY) + if (status & WDT_TIMEOUT_STATUS_BOOT_SECONDARY) { wdt->wdd.bootstatus = WDIOF_CARDRESET; + if (of_device_is_compatible(np, "aspeed,ast2400-wdt") || + of_device_is_compatible(np, "aspeed,ast2500-wdt")) + wdt->wdd.groups = bswitch_groups; + } + + dev_set_drvdata(dev, wdt); + return devm_watchdog_register_device(dev, &wdt->wdd); } diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c index 2e09981fe978..75de664ef4b0 100644 --- a/drivers/watchdog/ath79_wdt.c +++ b/drivers/watchdog/ath79_wdt.c @@ -302,7 +302,7 @@ static int ath79_wdt_remove(struct platform_device *pdev) return 0; } -static void ath97_wdt_shutdown(struct platform_device *pdev) +static void ath79_wdt_shutdown(struct platform_device *pdev) { ath79_wdt_disable(); } @@ -318,7 +318,7 @@ MODULE_DEVICE_TABLE(of, ath79_wdt_match); static struct platform_driver ath79_wdt_driver = { .probe = ath79_wdt_probe, .remove = ath79_wdt_remove, - .shutdown = ath97_wdt_shutdown, + .shutdown = ath79_wdt_shutdown, .driver = { .name = DRIVER_NAME, .of_match_table = of_match_ptr(ath79_wdt_match), diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index b973b31179df..9393be584e72 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -473,29 +473,6 @@ static long cpwd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; } -static long cpwd_compat_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - int rval = -ENOIOCTLCMD; - - switch (cmd) { - /* solaris ioctls are specific to this driver */ - case WIOCSTART: - case WIOCSTOP: - case WIOCGSTAT: - mutex_lock(&cpwd_mutex); - rval = cpwd_ioctl(file, cmd, arg); - mutex_unlock(&cpwd_mutex); - break; - - /* everything else is handled by the generic compat layer */ - default: - break; - } - - return rval; -} - static ssize_t cpwd_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -520,7 +497,7 @@ static ssize_t cpwd_read(struct file *file, char __user *buffer, static const struct file_operations cpwd_fops = { .owner = THIS_MODULE, .unlocked_ioctl = cpwd_ioctl, - .compat_ioctl = cpwd_compat_ioctl, + .compat_ioctl = compat_ptr_ioctl, .open = cpwd_open, .write = cpwd_write, .read = cpwd_read, diff --git a/drivers/watchdog/diag288_wdt.c b/drivers/watchdog/diag288_wdt.c index 181440b7b4d0..aafc8d98bf9f 100644 --- a/drivers/watchdog/diag288_wdt.c +++ b/drivers/watchdog/diag288_wdt.c @@ -26,13 +26,11 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/slab.h> -#include <linux/miscdevice.h> #include <linux/watchdog.h> #include <linux/suspend.h> #include <asm/ebcdic.h> #include <asm/diag.h> #include <linux/io.h> -#include <linux/uaccess.h> #define MAX_CMDLEN 240 #define DEFAULT_CMD "SYSTEM RESTART" @@ -70,7 +68,6 @@ MODULE_PARM_DESC(conceal, "Enable the CONCEAL CP option while the watchdog is ac module_param_named(nowayout, nowayout_info, bool, 0444); MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default = CONFIG_WATCHDOG_NOWAYOUT)"); -MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR); MODULE_ALIAS("vmwatchdog"); static int __diag288(unsigned int func, unsigned int timeout, diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c index ff5cf1b48a4d..e46104c2fd94 100644 --- a/drivers/watchdog/f71808e_wdt.c +++ b/drivers/watchdog/f71808e_wdt.c @@ -31,8 +31,10 @@ #define SIO_REG_DEVID 0x20 /* Device ID (2 bytes) */ #define SIO_REG_DEVREV 0x22 /* Device revision */ #define SIO_REG_MANID 0x23 /* Fintek ID (2 bytes) */ +#define SIO_REG_CLOCK_SEL 0x26 /* Clock select */ #define SIO_REG_ROM_ADDR_SEL 0x27 /* ROM address select */ #define SIO_F81866_REG_PORT_SEL 0x27 /* F81866 Multi-Function Register */ +#define SIO_REG_TSI_LEVEL_SEL 0x28 /* TSI Level select */ #define SIO_REG_MFUNCT1 0x29 /* Multi function select 1 */ #define SIO_REG_MFUNCT2 0x2a /* Multi function select 2 */ #define SIO_REG_MFUNCT3 0x2b /* Multi function select 3 */ @@ -49,6 +51,7 @@ #define SIO_F71869A_ID 0x1007 /* Chipset ID */ #define SIO_F71882_ID 0x0541 /* Chipset ID */ #define SIO_F71889_ID 0x0723 /* Chipset ID */ +#define SIO_F81803_ID 0x1210 /* Chipset ID */ #define SIO_F81865_ID 0x0704 /* Chipset ID */ #define SIO_F81866_ID 0x1010 /* Chipset ID */ @@ -108,7 +111,7 @@ MODULE_PARM_DESC(start_withtimeout, "Start watchdog timer on module load with" " given initial timeout. Zero (default) disables this feature."); enum chips { f71808fg, f71858fg, f71862fg, f71868, f71869, f71882fg, f71889fg, - f81865, f81866}; + f81803, f81865, f81866}; static const char *f71808e_names[] = { "f71808fg", @@ -118,6 +121,7 @@ static const char *f71808e_names[] = { "f71869", "f71882fg", "f71889fg", + "f81803", "f81865", "f81866", }; @@ -370,6 +374,14 @@ static int watchdog_start(void) superio_inb(watchdog.sioaddr, SIO_REG_MFUNCT3) & 0xcf); break; + case f81803: + /* Enable TSI Level register bank */ + superio_clear_bit(watchdog.sioaddr, SIO_REG_CLOCK_SEL, 3); + /* Set pin 27 to WDTRST# */ + superio_outb(watchdog.sioaddr, SIO_REG_TSI_LEVEL_SEL, 0x5f & + superio_inb(watchdog.sioaddr, SIO_REG_TSI_LEVEL_SEL)); + break; + case f81865: /* Set pin 70 to WDTRST# */ superio_clear_bit(watchdog.sioaddr, SIO_REG_MFUNCT3, 5); @@ -809,6 +821,9 @@ static int __init f71808e_find(int sioaddr) /* Confirmed (by datasheet) not to have a watchdog. */ err = -ENODEV; goto exit; + case SIO_F81803_ID: + watchdog.type = f81803; + break; case SIO_F81865_ID: watchdog.type = f81865; break; diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c index 32af3974e6bb..8d019a961ccc 100644 --- a/drivers/watchdog/imx2_wdt.c +++ b/drivers/watchdog/imx2_wdt.c @@ -55,7 +55,7 @@ #define IMX2_WDT_WMCR 0x08 /* Misc Register */ -#define IMX2_WDT_MAX_TIME 128 +#define IMX2_WDT_MAX_TIME 128U #define IMX2_WDT_DEFAULT_TIME 60 /* in seconds */ #define WDOG_SEC_TO_COUNT(s) ((s * 2 - 1) << 8) @@ -180,7 +180,7 @@ static int imx2_wdt_set_timeout(struct watchdog_device *wdog, { unsigned int actual; - actual = min(new_timeout, wdog->max_hw_heartbeat_ms * 1000); + actual = min(new_timeout, IMX2_WDT_MAX_TIME); __imx2_wdt_set_timeout(wdog, actual); wdog->timeout = new_timeout; return 0; diff --git a/drivers/watchdog/imx7ulp_wdt.c b/drivers/watchdog/imx7ulp_wdt.c new file mode 100644 index 000000000000..5ce51026989a --- /dev/null +++ b/drivers/watchdog/imx7ulp_wdt.c @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 NXP. + */ + +#include <linux/clk.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/reboot.h> +#include <linux/watchdog.h> + +#define WDOG_CS 0x0 +#define WDOG_CS_CMD32EN BIT(13) +#define WDOG_CS_ULK BIT(11) +#define WDOG_CS_RCS BIT(10) +#define WDOG_CS_EN BIT(7) +#define WDOG_CS_UPDATE BIT(5) + +#define WDOG_CNT 0x4 +#define WDOG_TOVAL 0x8 + +#define REFRESH_SEQ0 0xA602 +#define REFRESH_SEQ1 0xB480 +#define REFRESH ((REFRESH_SEQ1 << 16) | REFRESH_SEQ0) + +#define UNLOCK_SEQ0 0xC520 +#define UNLOCK_SEQ1 0xD928 +#define UNLOCK ((UNLOCK_SEQ1 << 16) | UNLOCK_SEQ0) + +#define DEFAULT_TIMEOUT 60 +#define MAX_TIMEOUT 128 +#define WDOG_CLOCK_RATE 1000 + +static bool nowayout = WATCHDOG_NOWAYOUT; +module_param(nowayout, bool, 0000); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + +struct imx7ulp_wdt_device { + struct notifier_block restart_handler; + struct watchdog_device wdd; + void __iomem *base; + struct clk *clk; +}; + +static inline void imx7ulp_wdt_enable(void __iomem *base, bool enable) +{ + u32 val = readl(base + WDOG_CS); + + writel(UNLOCK, base + WDOG_CNT); + if (enable) + writel(val | WDOG_CS_EN, base + WDOG_CS); + else + writel(val & ~WDOG_CS_EN, base + WDOG_CS); +} + +static inline bool imx7ulp_wdt_is_enabled(void __iomem *base) +{ + u32 val = readl(base + WDOG_CS); + + return val & WDOG_CS_EN; +} + +static int imx7ulp_wdt_ping(struct watchdog_device *wdog) +{ + struct imx7ulp_wdt_device *wdt = watchdog_get_drvdata(wdog); + + writel(REFRESH, wdt->base + WDOG_CNT); + + return 0; +} + +static int imx7ulp_wdt_start(struct watchdog_device *wdog) +{ + struct imx7ulp_wdt_device *wdt = watchdog_get_drvdata(wdog); + + imx7ulp_wdt_enable(wdt->base, true); + + return 0; +} + +static int imx7ulp_wdt_stop(struct watchdog_device *wdog) +{ + struct imx7ulp_wdt_device *wdt = watchdog_get_drvdata(wdog); + + imx7ulp_wdt_enable(wdt->base, false); + + return 0; +} + +static int imx7ulp_wdt_set_timeout(struct watchdog_device *wdog, + unsigned int timeout) +{ + struct imx7ulp_wdt_device *wdt = watchdog_get_drvdata(wdog); + u32 val = WDOG_CLOCK_RATE * timeout; + + writel(UNLOCK, wdt->base + WDOG_CNT); + writel(val, wdt->base + WDOG_TOVAL); + + wdog->timeout = timeout; + + return 0; +} + +static const struct watchdog_ops imx7ulp_wdt_ops = { + .owner = THIS_MODULE, + .start = imx7ulp_wdt_start, + .stop = imx7ulp_wdt_stop, + .ping = imx7ulp_wdt_ping, + .set_timeout = imx7ulp_wdt_set_timeout, +}; + +static const struct watchdog_info imx7ulp_wdt_info = { + .identity = "i.MX7ULP watchdog timer", + .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | + WDIOF_MAGICCLOSE, +}; + +static inline void imx7ulp_wdt_init(void __iomem *base, unsigned int timeout) +{ + u32 val; + + /* unlock the wdog for reconfiguration */ + writel_relaxed(UNLOCK_SEQ0, base + WDOG_CNT); + writel_relaxed(UNLOCK_SEQ1, base + WDOG_CNT); + + /* set an initial timeout value in TOVAL */ + writel(timeout, base + WDOG_TOVAL); + /* enable 32bit command sequence and reconfigure */ + val = BIT(13) | BIT(8) | BIT(5); + writel(val, base + WDOG_CS); +} + +static void imx7ulp_wdt_action(void *data) +{ + clk_disable_unprepare(data); +} + +static int imx7ulp_wdt_probe(struct platform_device *pdev) +{ + struct imx7ulp_wdt_device *imx7ulp_wdt; + struct device *dev = &pdev->dev; + struct watchdog_device *wdog; + int ret; + + imx7ulp_wdt = devm_kzalloc(dev, sizeof(*imx7ulp_wdt), GFP_KERNEL); + if (!imx7ulp_wdt) + return -ENOMEM; + + platform_set_drvdata(pdev, imx7ulp_wdt); + + imx7ulp_wdt->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(imx7ulp_wdt->base)) + return PTR_ERR(imx7ulp_wdt->base); + + imx7ulp_wdt->clk = devm_clk_get(dev, NULL); + if (IS_ERR(imx7ulp_wdt->clk)) { + dev_err(dev, "Failed to get watchdog clock\n"); + return PTR_ERR(imx7ulp_wdt->clk); + } + + ret = clk_prepare_enable(imx7ulp_wdt->clk); + if (ret) + return ret; + + ret = devm_add_action_or_reset(dev, imx7ulp_wdt_action, imx7ulp_wdt->clk); + if (ret) + return ret; + + wdog = &imx7ulp_wdt->wdd; + wdog->info = &imx7ulp_wdt_info; + wdog->ops = &imx7ulp_wdt_ops; + wdog->min_timeout = 1; + wdog->max_timeout = MAX_TIMEOUT; + wdog->parent = dev; + wdog->timeout = DEFAULT_TIMEOUT; + + watchdog_init_timeout(wdog, 0, dev); + watchdog_stop_on_reboot(wdog); + watchdog_stop_on_unregister(wdog); + watchdog_set_drvdata(wdog, imx7ulp_wdt); + imx7ulp_wdt_init(imx7ulp_wdt->base, wdog->timeout * WDOG_CLOCK_RATE); + + return devm_watchdog_register_device(dev, wdog); +} + +static int __maybe_unused imx7ulp_wdt_suspend(struct device *dev) +{ + struct imx7ulp_wdt_device *imx7ulp_wdt = dev_get_drvdata(dev); + + if (watchdog_active(&imx7ulp_wdt->wdd)) + imx7ulp_wdt_stop(&imx7ulp_wdt->wdd); + + clk_disable_unprepare(imx7ulp_wdt->clk); + + return 0; +} + +static int __maybe_unused imx7ulp_wdt_resume(struct device *dev) +{ + struct imx7ulp_wdt_device *imx7ulp_wdt = dev_get_drvdata(dev); + u32 timeout = imx7ulp_wdt->wdd.timeout * WDOG_CLOCK_RATE; + int ret; + + ret = clk_prepare_enable(imx7ulp_wdt->clk); + if (ret) + return ret; + + if (imx7ulp_wdt_is_enabled(imx7ulp_wdt->base)) + imx7ulp_wdt_init(imx7ulp_wdt->base, timeout); + + if (watchdog_active(&imx7ulp_wdt->wdd)) + imx7ulp_wdt_start(&imx7ulp_wdt->wdd); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(imx7ulp_wdt_pm_ops, imx7ulp_wdt_suspend, + imx7ulp_wdt_resume); + +static const struct of_device_id imx7ulp_wdt_dt_ids[] = { + { .compatible = "fsl,imx7ulp-wdt", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, imx7ulp_wdt_dt_ids); + +static struct platform_driver imx7ulp_wdt_driver = { + .probe = imx7ulp_wdt_probe, + .driver = { + .name = "imx7ulp-wdt", + .pm = &imx7ulp_wdt_pm_ops, + .of_match_table = imx7ulp_wdt_dt_ids, + }, +}; +module_platform_driver(imx7ulp_wdt_driver); + +MODULE_AUTHOR("Anson Huang <Anson.Huang@nxp.com>"); +MODULE_DESCRIPTION("Freescale i.MX7ULP watchdog driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/watchdog/imx_sc_wdt.c b/drivers/watchdog/imx_sc_wdt.c index 78eaaf75a263..7ea5cf54e94a 100644 --- a/drivers/watchdog/imx_sc_wdt.c +++ b/drivers/watchdog/imx_sc_wdt.c @@ -175,12 +175,9 @@ static int imx_sc_wdt_probe(struct platform_device *pdev) watchdog_stop_on_unregister(wdog); ret = devm_watchdog_register_device(dev, wdog); - - if (ret) { - dev_err(dev, "Failed to register watchdog device\n"); - return ret; - } - + if (ret) + return ret; + ret = imx_scu_irq_group_enable(SC_IRQ_GROUP_WDOG, SC_IRQ_WDOG, true); diff --git a/drivers/watchdog/jz4740_wdt.c b/drivers/watchdog/jz4740_wdt.c index d4a90916dd38..c6052ae54f32 100644 --- a/drivers/watchdog/jz4740_wdt.c +++ b/drivers/watchdog/jz4740_wdt.c @@ -162,7 +162,6 @@ static int jz4740_wdt_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct jz4740_wdt_drvdata *drvdata; struct watchdog_device *jz4740_wdt; - int ret; drvdata = devm_kzalloc(dev, sizeof(struct jz4740_wdt_drvdata), GFP_KERNEL); diff --git a/drivers/watchdog/ks8695_wdt.c b/drivers/watchdog/ks8695_wdt.c deleted file mode 100644 index 1550ce3c5702..000000000000 --- a/drivers/watchdog/ks8695_wdt.c +++ /dev/null @@ -1,319 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Watchdog driver for Kendin/Micrel KS8695. - * - * (C) 2007 Andrew Victor - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/bitops.h> -#include <linux/errno.h> -#include <linux/fs.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/miscdevice.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/platform_device.h> -#include <linux/types.h> -#include <linux/watchdog.h> -#include <linux/io.h> -#include <linux/uaccess.h> -#include <mach/hardware.h> - -#define KS8695_TMR_OFFSET (0xF0000 + 0xE400) -#define KS8695_TMR_VA (KS8695_IO_VA + KS8695_TMR_OFFSET) - -/* - * Timer registers - */ -#define KS8695_TMCON (0x00) /* Timer Control Register */ -#define KS8695_T0TC (0x08) /* Timer 0 Timeout Count Register */ -#define TMCON_T0EN (1 << 0) /* Timer 0 Enable */ - -/* Timer0 Timeout Counter Register */ -#define T0TC_WATCHDOG (0xff) /* Enable watchdog mode */ - -#define WDT_DEFAULT_TIME 5 /* seconds */ -#define WDT_MAX_TIME 171 /* seconds */ - -static int wdt_time = WDT_DEFAULT_TIME; -static bool nowayout = WATCHDOG_NOWAYOUT; - -module_param(wdt_time, int, 0); -MODULE_PARM_DESC(wdt_time, "Watchdog time in seconds. (default=" - __MODULE_STRING(WDT_DEFAULT_TIME) ")"); - -#ifdef CONFIG_WATCHDOG_NOWAYOUT -module_param(nowayout, bool, 0); -MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" - __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); -#endif - - -static unsigned long ks8695wdt_busy; -static DEFINE_SPINLOCK(ks8695_lock); - -/* ......................................................................... */ - -/* - * Disable the watchdog. - */ -static inline void ks8695_wdt_stop(void) -{ - unsigned long tmcon; - - spin_lock(&ks8695_lock); - /* disable timer0 */ - tmcon = __raw_readl(KS8695_TMR_VA + KS8695_TMCON); - __raw_writel(tmcon & ~TMCON_T0EN, KS8695_TMR_VA + KS8695_TMCON); - spin_unlock(&ks8695_lock); -} - -/* - * Enable and reset the watchdog. - */ -static inline void ks8695_wdt_start(void) -{ - unsigned long tmcon; - unsigned long tval = wdt_time * KS8695_CLOCK_RATE; - - spin_lock(&ks8695_lock); - /* disable timer0 */ - tmcon = __raw_readl(KS8695_TMR_VA + KS8695_TMCON); - __raw_writel(tmcon & ~TMCON_T0EN, KS8695_TMR_VA + KS8695_TMCON); - - /* program timer0 */ - __raw_writel(tval | T0TC_WATCHDOG, KS8695_TMR_VA + KS8695_T0TC); - - /* re-enable timer0 */ - tmcon = __raw_readl(KS8695_TMR_VA + KS8695_TMCON); - __raw_writel(tmcon | TMCON_T0EN, KS8695_TMR_VA + KS8695_TMCON); - spin_unlock(&ks8695_lock); -} - -/* - * Reload the watchdog timer. (ie, pat the watchdog) - */ -static inline void ks8695_wdt_reload(void) -{ - unsigned long tmcon; - - spin_lock(&ks8695_lock); - /* disable, then re-enable timer0 */ - tmcon = __raw_readl(KS8695_TMR_VA + KS8695_TMCON); - __raw_writel(tmcon & ~TMCON_T0EN, KS8695_TMR_VA + KS8695_TMCON); - __raw_writel(tmcon | TMCON_T0EN, KS8695_TMR_VA + KS8695_TMCON); - spin_unlock(&ks8695_lock); -} - -/* - * Change the watchdog time interval. - */ -static int ks8695_wdt_settimeout(int new_time) -{ - /* - * All counting occurs at KS8695_CLOCK_RATE / 128 = 0.256 Hz - * - * Since WDV is a 16-bit counter, the maximum period is - * 65536 / 0.256 = 256 seconds. - */ - if ((new_time <= 0) || (new_time > WDT_MAX_TIME)) - return -EINVAL; - - /* Set new watchdog time. It will be used when - ks8695_wdt_start() is called. */ - wdt_time = new_time; - return 0; -} - -/* ......................................................................... */ - -/* - * Watchdog device is opened, and watchdog starts running. - */ -static int ks8695_wdt_open(struct inode *inode, struct file *file) -{ - if (test_and_set_bit(0, &ks8695wdt_busy)) - return -EBUSY; - - ks8695_wdt_start(); - return stream_open(inode, file); -} - -/* - * Close the watchdog device. - * If CONFIG_WATCHDOG_NOWAYOUT is NOT defined then the watchdog is also - * disabled. - */ -static int ks8695_wdt_close(struct inode *inode, struct file *file) -{ - /* Disable the watchdog when file is closed */ - if (!nowayout) - ks8695_wdt_stop(); - clear_bit(0, &ks8695wdt_busy); - return 0; -} - -static const struct watchdog_info ks8695_wdt_info = { - .identity = "ks8695 watchdog", - .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING, -}; - -/* - * Handle commands from user-space. - */ -static long ks8695_wdt_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - void __user *argp = (void __user *)arg; - int __user *p = argp; - int new_value; - - switch (cmd) { - case WDIOC_GETSUPPORT: - return copy_to_user(argp, &ks8695_wdt_info, - sizeof(ks8695_wdt_info)) ? -EFAULT : 0; - case WDIOC_GETSTATUS: - case WDIOC_GETBOOTSTATUS: - return put_user(0, p); - case WDIOC_SETOPTIONS: - if (get_user(new_value, p)) - return -EFAULT; - if (new_value & WDIOS_DISABLECARD) - ks8695_wdt_stop(); - if (new_value & WDIOS_ENABLECARD) - ks8695_wdt_start(); - return 0; - case WDIOC_KEEPALIVE: - ks8695_wdt_reload(); /* pat the watchdog */ - return 0; - case WDIOC_SETTIMEOUT: - if (get_user(new_value, p)) - return -EFAULT; - if (ks8695_wdt_settimeout(new_value)) - return -EINVAL; - /* Enable new time value */ - ks8695_wdt_start(); - /* Return current value */ - return put_user(wdt_time, p); - case WDIOC_GETTIMEOUT: - return put_user(wdt_time, p); - default: - return -ENOTTY; - } -} - -/* - * Pat the watchdog whenever device is written to. - */ -static ssize_t ks8695_wdt_write(struct file *file, const char *data, - size_t len, loff_t *ppos) -{ - ks8695_wdt_reload(); /* pat the watchdog */ - return len; -} - -/* ......................................................................... */ - -static const struct file_operations ks8695wdt_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .unlocked_ioctl = ks8695_wdt_ioctl, - .open = ks8695_wdt_open, - .release = ks8695_wdt_close, - .write = ks8695_wdt_write, -}; - -static struct miscdevice ks8695wdt_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &ks8695wdt_fops, -}; - -static int ks8695wdt_probe(struct platform_device *pdev) -{ - int res; - - if (ks8695wdt_miscdev.parent) - return -EBUSY; - ks8695wdt_miscdev.parent = &pdev->dev; - - res = misc_register(&ks8695wdt_miscdev); - if (res) - return res; - - pr_info("KS8695 Watchdog Timer enabled (%d seconds%s)\n", - wdt_time, nowayout ? ", nowayout" : ""); - return 0; -} - -static int ks8695wdt_remove(struct platform_device *pdev) -{ - misc_deregister(&ks8695wdt_miscdev); - ks8695wdt_miscdev.parent = NULL; - - return 0; -} - -static void ks8695wdt_shutdown(struct platform_device *pdev) -{ - ks8695_wdt_stop(); -} - -#ifdef CONFIG_PM - -static int ks8695wdt_suspend(struct platform_device *pdev, pm_message_t message) -{ - ks8695_wdt_stop(); - return 0; -} - -static int ks8695wdt_resume(struct platform_device *pdev) -{ - if (ks8695wdt_busy) - ks8695_wdt_start(); - return 0; -} - -#else -#define ks8695wdt_suspend NULL -#define ks8695wdt_resume NULL -#endif - -static struct platform_driver ks8695wdt_driver = { - .probe = ks8695wdt_probe, - .remove = ks8695wdt_remove, - .shutdown = ks8695wdt_shutdown, - .suspend = ks8695wdt_suspend, - .resume = ks8695wdt_resume, - .driver = { - .name = "ks8695_wdt", - }, -}; - -static int __init ks8695_wdt_init(void) -{ - /* Check that the heartbeat value is within range; - if not reset to the default */ - if (ks8695_wdt_settimeout(wdt_time)) { - ks8695_wdt_settimeout(WDT_DEFAULT_TIME); - pr_info("ks8695_wdt: wdt_time value must be 1 <= wdt_time <= %i" - ", using %d\n", wdt_time, WDT_MAX_TIME); - } - return platform_driver_register(&ks8695wdt_driver); -} - -static void __exit ks8695_wdt_exit(void) -{ - platform_driver_unregister(&ks8695wdt_driver); -} - -module_init(ks8695_wdt_init); -module_exit(ks8695_wdt_exit); - -MODULE_AUTHOR("Andrew Victor"); -MODULE_DESCRIPTION("Watchdog driver for KS8695"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:ks8695_wdt"); diff --git a/drivers/watchdog/nuc900_wdt.c b/drivers/watchdog/nuc900_wdt.c deleted file mode 100644 index db124cebe838..000000000000 --- a/drivers/watchdog/nuc900_wdt.c +++ /dev/null @@ -1,302 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2009 Nuvoton technology corporation. - * - * Wan ZongShun <mcuos.com@gmail.com> - */ - -#include <linux/bitops.h> -#include <linux/errno.h> -#include <linux/fs.h> -#include <linux/io.h> -#include <linux/clk.h> -#include <linux/kernel.h> -#include <linux/miscdevice.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/platform_device.h> -#include <linux/slab.h> -#include <linux/interrupt.h> -#include <linux/types.h> -#include <linux/watchdog.h> -#include <linux/uaccess.h> - -#define REG_WTCR 0x1c -#define WTCLK (0x01 << 10) -#define WTE (0x01 << 7) /*wdt enable*/ -#define WTIS (0x03 << 4) -#define WTIF (0x01 << 3) -#define WTRF (0x01 << 2) -#define WTRE (0x01 << 1) -#define WTR (0x01 << 0) -/* - * The watchdog time interval can be calculated via following formula: - * WTIS real time interval (formula) - * 0x00 ((2^ 14 ) * ((external crystal freq) / 256))seconds - * 0x01 ((2^ 16 ) * ((external crystal freq) / 256))seconds - * 0x02 ((2^ 18 ) * ((external crystal freq) / 256))seconds - * 0x03 ((2^ 20 ) * ((external crystal freq) / 256))seconds - * - * The external crystal freq is 15Mhz in the nuc900 evaluation board. - * So 0x00 = +-0.28 seconds, 0x01 = +-1.12 seconds, 0x02 = +-4.48 seconds, - * 0x03 = +- 16.92 seconds.. - */ -#define WDT_HW_TIMEOUT 0x02 -#define WDT_TIMEOUT (HZ/2) -#define WDT_HEARTBEAT 15 - -static int heartbeat = WDT_HEARTBEAT; -module_param(heartbeat, int, 0); -MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds. " - "(default = " __MODULE_STRING(WDT_HEARTBEAT) ")"); - -static bool nowayout = WATCHDOG_NOWAYOUT; -module_param(nowayout, bool, 0); -MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started " - "(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); - -struct nuc900_wdt { - struct clk *wdt_clock; - struct platform_device *pdev; - void __iomem *wdt_base; - char expect_close; - struct timer_list timer; - spinlock_t wdt_lock; - unsigned long next_heartbeat; -}; - -static unsigned long nuc900wdt_busy; -static struct nuc900_wdt *nuc900_wdt; - -static inline void nuc900_wdt_keepalive(void) -{ - unsigned int val; - - spin_lock(&nuc900_wdt->wdt_lock); - - val = __raw_readl(nuc900_wdt->wdt_base + REG_WTCR); - val |= (WTR | WTIF); - __raw_writel(val, nuc900_wdt->wdt_base + REG_WTCR); - - spin_unlock(&nuc900_wdt->wdt_lock); -} - -static inline void nuc900_wdt_start(void) -{ - unsigned int val; - - spin_lock(&nuc900_wdt->wdt_lock); - - val = __raw_readl(nuc900_wdt->wdt_base + REG_WTCR); - val |= (WTRE | WTE | WTR | WTCLK | WTIF); - val &= ~WTIS; - val |= (WDT_HW_TIMEOUT << 0x04); - __raw_writel(val, nuc900_wdt->wdt_base + REG_WTCR); - - spin_unlock(&nuc900_wdt->wdt_lock); - - nuc900_wdt->next_heartbeat = jiffies + heartbeat * HZ; - mod_timer(&nuc900_wdt->timer, jiffies + WDT_TIMEOUT); -} - -static inline void nuc900_wdt_stop(void) -{ - unsigned int val; - - del_timer(&nuc900_wdt->timer); - - spin_lock(&nuc900_wdt->wdt_lock); - - val = __raw_readl(nuc900_wdt->wdt_base + REG_WTCR); - val &= ~WTE; - __raw_writel(val, nuc900_wdt->wdt_base + REG_WTCR); - - spin_unlock(&nuc900_wdt->wdt_lock); -} - -static inline void nuc900_wdt_ping(void) -{ - nuc900_wdt->next_heartbeat = jiffies + heartbeat * HZ; -} - -static int nuc900_wdt_open(struct inode *inode, struct file *file) -{ - - if (test_and_set_bit(0, &nuc900wdt_busy)) - return -EBUSY; - - nuc900_wdt_start(); - - return stream_open(inode, file); -} - -static int nuc900_wdt_close(struct inode *inode, struct file *file) -{ - if (nuc900_wdt->expect_close == 42) - nuc900_wdt_stop(); - else { - dev_crit(&nuc900_wdt->pdev->dev, - "Unexpected close, not stopping watchdog!\n"); - nuc900_wdt_ping(); - } - - nuc900_wdt->expect_close = 0; - clear_bit(0, &nuc900wdt_busy); - return 0; -} - -static const struct watchdog_info nuc900_wdt_info = { - .identity = "nuc900 watchdog", - .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | - WDIOF_MAGICCLOSE, -}; - -static long nuc900_wdt_ioctl(struct file *file, - unsigned int cmd, unsigned long arg) -{ - void __user *argp = (void __user *)arg; - int __user *p = argp; - int new_value; - - switch (cmd) { - case WDIOC_GETSUPPORT: - return copy_to_user(argp, &nuc900_wdt_info, - sizeof(nuc900_wdt_info)) ? -EFAULT : 0; - case WDIOC_GETSTATUS: - case WDIOC_GETBOOTSTATUS: - return put_user(0, p); - - case WDIOC_KEEPALIVE: - nuc900_wdt_ping(); - return 0; - - case WDIOC_SETTIMEOUT: - if (get_user(new_value, p)) - return -EFAULT; - - heartbeat = new_value; - nuc900_wdt_ping(); - - return put_user(new_value, p); - case WDIOC_GETTIMEOUT: - return put_user(heartbeat, p); - default: - return -ENOTTY; - } -} - -static ssize_t nuc900_wdt_write(struct file *file, const char __user *data, - size_t len, loff_t *ppos) -{ - if (!len) - return 0; - - /* Scan for magic character */ - if (!nowayout) { - size_t i; - - nuc900_wdt->expect_close = 0; - - for (i = 0; i < len; i++) { - char c; - if (get_user(c, data + i)) - return -EFAULT; - if (c == 'V') { - nuc900_wdt->expect_close = 42; - break; - } - } - } - - nuc900_wdt_ping(); - return len; -} - -static void nuc900_wdt_timer_ping(struct timer_list *unused) -{ - if (time_before(jiffies, nuc900_wdt->next_heartbeat)) { - nuc900_wdt_keepalive(); - mod_timer(&nuc900_wdt->timer, jiffies + WDT_TIMEOUT); - } else - dev_warn(&nuc900_wdt->pdev->dev, "Will reset the machine !\n"); -} - -static const struct file_operations nuc900wdt_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .unlocked_ioctl = nuc900_wdt_ioctl, - .open = nuc900_wdt_open, - .release = nuc900_wdt_close, - .write = nuc900_wdt_write, -}; - -static struct miscdevice nuc900wdt_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &nuc900wdt_fops, -}; - -static int nuc900wdt_probe(struct platform_device *pdev) -{ - int ret = 0; - - nuc900_wdt = devm_kzalloc(&pdev->dev, sizeof(*nuc900_wdt), - GFP_KERNEL); - if (!nuc900_wdt) - return -ENOMEM; - - nuc900_wdt->pdev = pdev; - - spin_lock_init(&nuc900_wdt->wdt_lock); - - nuc900_wdt->wdt_base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(nuc900_wdt->wdt_base)) - return PTR_ERR(nuc900_wdt->wdt_base); - - nuc900_wdt->wdt_clock = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(nuc900_wdt->wdt_clock)) { - dev_err(&pdev->dev, "failed to find watchdog clock source\n"); - return PTR_ERR(nuc900_wdt->wdt_clock); - } - - clk_enable(nuc900_wdt->wdt_clock); - - timer_setup(&nuc900_wdt->timer, nuc900_wdt_timer_ping, 0); - - ret = misc_register(&nuc900wdt_miscdev); - if (ret) { - dev_err(&pdev->dev, "err register miscdev on minor=%d (%d)\n", - WATCHDOG_MINOR, ret); - goto err_clk; - } - - return 0; - -err_clk: - clk_disable(nuc900_wdt->wdt_clock); - return ret; -} - -static int nuc900wdt_remove(struct platform_device *pdev) -{ - misc_deregister(&nuc900wdt_miscdev); - - clk_disable(nuc900_wdt->wdt_clock); - - return 0; -} - -static struct platform_driver nuc900wdt_driver = { - .probe = nuc900wdt_probe, - .remove = nuc900wdt_remove, - .driver = { - .name = "nuc900-wdt", - }, -}; - -module_platform_driver(nuc900wdt_driver); - -MODULE_AUTHOR("Wan ZongShun <mcuos.com@gmail.com>"); -MODULE_DESCRIPTION("Watchdog driver for NUC900"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:nuc900-wdt"); diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c index cdb0d174c5e2..1cccf8eb1c5d 100644 --- a/drivers/watchdog/orion_wdt.c +++ b/drivers/watchdog/orion_wdt.c @@ -35,7 +35,15 @@ * Watchdog timer block registers. */ #define TIMER_CTRL 0x0000 -#define TIMER_A370_STATUS 0x04 +#define TIMER1_FIXED_ENABLE_BIT BIT(12) +#define WDT_AXP_FIXED_ENABLE_BIT BIT(10) +#define TIMER1_ENABLE_BIT BIT(2) + +#define TIMER_A370_STATUS 0x0004 +#define WDT_A370_EXPIRED BIT(31) +#define TIMER1_STATUS_BIT BIT(8) + +#define TIMER1_VAL_OFF 0x001c #define WDT_MAX_CYCLE_COUNT 0xffffffff @@ -43,9 +51,6 @@ #define WDT_A370_RATIO_SHIFT 5 #define WDT_A370_RATIO (1 << WDT_A370_RATIO_SHIFT) -#define WDT_AXP_FIXED_ENABLE_BIT BIT(10) -#define WDT_A370_EXPIRED BIT(31) - static bool nowayout = WATCHDOG_NOWAYOUT; static int heartbeat = -1; /* module parameter (seconds) */ @@ -158,6 +163,7 @@ static int armadaxp_wdt_clock_init(struct platform_device *pdev, struct orion_watchdog *dev) { int ret; + u32 val; dev->clk = of_clk_get_by_name(pdev->dev.of_node, "fixed"); if (IS_ERR(dev->clk)) @@ -168,10 +174,9 @@ static int armadaxp_wdt_clock_init(struct platform_device *pdev, return ret; } - /* Enable the fixed watchdog clock input */ - atomic_io_modify(dev->reg + TIMER_CTRL, - WDT_AXP_FIXED_ENABLE_BIT, - WDT_AXP_FIXED_ENABLE_BIT); + /* Fix the wdt and timer1 clock freqency to 25MHz */ + val = WDT_AXP_FIXED_ENABLE_BIT | TIMER1_FIXED_ENABLE_BIT; + atomic_io_modify(dev->reg + TIMER_CTRL, val, val); dev->clk_rate = clk_get_rate(dev->clk); return 0; @@ -183,6 +188,10 @@ static int orion_wdt_ping(struct watchdog_device *wdt_dev) /* Reload watchdog duration */ writel(dev->clk_rate * wdt_dev->timeout, dev->reg + dev->data->wdt_counter_offset); + if (dev->wdt.info->options & WDIOF_PRETIMEOUT) + writel(dev->clk_rate * (wdt_dev->timeout - wdt_dev->pretimeout), + dev->reg + TIMER1_VAL_OFF); + return 0; } @@ -194,13 +203,18 @@ static int armada375_start(struct watchdog_device *wdt_dev) /* Set watchdog duration */ writel(dev->clk_rate * wdt_dev->timeout, dev->reg + dev->data->wdt_counter_offset); + if (dev->wdt.info->options & WDIOF_PRETIMEOUT) + writel(dev->clk_rate * (wdt_dev->timeout - wdt_dev->pretimeout), + dev->reg + TIMER1_VAL_OFF); /* Clear the watchdog expiration bit */ atomic_io_modify(dev->reg + TIMER_A370_STATUS, WDT_A370_EXPIRED, 0); /* Enable watchdog timer */ - atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit, - dev->data->wdt_enable_bit); + reg = dev->data->wdt_enable_bit; + if (dev->wdt.info->options & WDIOF_PRETIMEOUT) + reg |= TIMER1_ENABLE_BIT; + atomic_io_modify(dev->reg + TIMER_CTRL, reg, reg); /* Enable reset on watchdog */ reg = readl(dev->rstout); @@ -277,7 +291,7 @@ static int orion_stop(struct watchdog_device *wdt_dev) static int armada375_stop(struct watchdog_device *wdt_dev) { struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev); - u32 reg; + u32 reg, mask; /* Disable reset on watchdog */ atomic_io_modify(dev->rstout_mask, dev->data->rstout_mask_bit, @@ -287,7 +301,10 @@ static int armada375_stop(struct watchdog_device *wdt_dev) writel(reg, dev->rstout); /* Disable watchdog timer */ - atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit, 0); + mask = dev->data->wdt_enable_bit; + if (wdt_dev->info->options & WDIOF_PRETIMEOUT) + mask |= TIMER1_ENABLE_BIT; + atomic_io_modify(dev->reg + TIMER_CTRL, mask, 0); return 0; } @@ -349,7 +366,7 @@ static unsigned int orion_wdt_get_timeleft(struct watchdog_device *wdt_dev) return readl(dev->reg + dev->data->wdt_counter_offset) / dev->clk_rate; } -static const struct watchdog_info orion_wdt_info = { +static struct watchdog_info orion_wdt_info = { .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE, .identity = "Orion Watchdog", }; @@ -368,6 +385,16 @@ static irqreturn_t orion_wdt_irq(int irq, void *devid) return IRQ_HANDLED; } +static irqreturn_t orion_wdt_pre_irq(int irq, void *devid) +{ + struct orion_watchdog *dev = devid; + + atomic_io_modify(dev->reg + TIMER_A370_STATUS, + TIMER1_STATUS_BIT, 0); + watchdog_notify_pretimeout(&dev->wdt); + return IRQ_HANDLED; +} + /* * The original devicetree binding for this driver specified only * one memory resource, so in order to keep DT backwards compatibility @@ -589,6 +616,19 @@ static int orion_wdt_probe(struct platform_device *pdev) } } + /* Optional 2nd interrupt for pretimeout */ + irq = platform_get_irq(pdev, 1); + if (irq > 0) { + orion_wdt_info.options |= WDIOF_PRETIMEOUT; + ret = devm_request_irq(&pdev->dev, irq, orion_wdt_pre_irq, + 0, pdev->name, dev); + if (ret < 0) { + dev_err(&pdev->dev, "failed to request IRQ\n"); + goto disable_clk; + } + } + + watchdog_set_nowayout(&dev->wdt, nowayout); ret = watchdog_register_device(&dev->wdt); if (ret) diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c index 7be7f87be28f..a494543d3ae1 100644 --- a/drivers/watchdog/qcom-wdt.c +++ b/drivers/watchdog/qcom-wdt.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2014, The Linux Foundation. All rights reserved. */ +#include <linux/bits.h> #include <linux/clk.h> #include <linux/delay.h> +#include <linux/interrupt.h> #include <linux/io.h> #include <linux/kernel.h> #include <linux/module.h> @@ -19,6 +21,9 @@ enum wdt_reg { WDT_BITE_TIME, }; +#define QCOM_WDT_ENABLE BIT(0) +#define QCOM_WDT_ENABLE_IRQ BIT(1) + static const u32 reg_offset_data_apcs_tmr[] = { [WDT_RST] = 0x38, [WDT_EN] = 0x40, @@ -37,7 +42,6 @@ static const u32 reg_offset_data_kpss[] = { struct qcom_wdt { struct watchdog_device wdd; - struct clk *clk; unsigned long rate; void __iomem *base; const u32 *layout; @@ -54,15 +58,35 @@ struct qcom_wdt *to_qcom_wdt(struct watchdog_device *wdd) return container_of(wdd, struct qcom_wdt, wdd); } +static inline int qcom_get_enable(struct watchdog_device *wdd) +{ + int enable = QCOM_WDT_ENABLE; + + if (wdd->pretimeout) + enable |= QCOM_WDT_ENABLE_IRQ; + + return enable; +} + +static irqreturn_t qcom_wdt_isr(int irq, void *arg) +{ + struct watchdog_device *wdd = arg; + + watchdog_notify_pretimeout(wdd); + + return IRQ_HANDLED; +} + static int qcom_wdt_start(struct watchdog_device *wdd) { struct qcom_wdt *wdt = to_qcom_wdt(wdd); + unsigned int bark = wdd->timeout - wdd->pretimeout; writel(0, wdt_addr(wdt, WDT_EN)); writel(1, wdt_addr(wdt, WDT_RST)); - writel(wdd->timeout * wdt->rate, wdt_addr(wdt, WDT_BARK_TIME)); + writel(bark * wdt->rate, wdt_addr(wdt, WDT_BARK_TIME)); writel(wdd->timeout * wdt->rate, wdt_addr(wdt, WDT_BITE_TIME)); - writel(1, wdt_addr(wdt, WDT_EN)); + writel(qcom_get_enable(wdd), wdt_addr(wdt, WDT_EN)); return 0; } @@ -89,6 +113,13 @@ static int qcom_wdt_set_timeout(struct watchdog_device *wdd, return qcom_wdt_start(wdd); } +static int qcom_wdt_set_pretimeout(struct watchdog_device *wdd, + unsigned int timeout) +{ + wdd->pretimeout = timeout; + return qcom_wdt_start(wdd); +} + static int qcom_wdt_restart(struct watchdog_device *wdd, unsigned long action, void *data) { @@ -105,7 +136,7 @@ static int qcom_wdt_restart(struct watchdog_device *wdd, unsigned long action, writel(1, wdt_addr(wdt, WDT_RST)); writel(timeout, wdt_addr(wdt, WDT_BARK_TIME)); writel(timeout, wdt_addr(wdt, WDT_BITE_TIME)); - writel(1, wdt_addr(wdt, WDT_EN)); + writel(QCOM_WDT_ENABLE, wdt_addr(wdt, WDT_EN)); /* * Actually make sure the above sequence hits hardware before sleeping. @@ -121,6 +152,7 @@ static const struct watchdog_ops qcom_wdt_ops = { .stop = qcom_wdt_stop, .ping = qcom_wdt_ping, .set_timeout = qcom_wdt_set_timeout, + .set_pretimeout = qcom_wdt_set_pretimeout, .restart = qcom_wdt_restart, .owner = THIS_MODULE, }; @@ -133,6 +165,15 @@ static const struct watchdog_info qcom_wdt_info = { .identity = KBUILD_MODNAME, }; +static const struct watchdog_info qcom_wdt_pt_info = { + .options = WDIOF_KEEPALIVEPING + | WDIOF_MAGICCLOSE + | WDIOF_SETTIMEOUT + | WDIOF_PRETIMEOUT + | WDIOF_CARDRESET, + .identity = KBUILD_MODNAME, +}; + static void qcom_clk_disable_unprepare(void *data) { clk_disable_unprepare(data); @@ -146,7 +187,8 @@ static int qcom_wdt_probe(struct platform_device *pdev) struct device_node *np = dev->of_node; const u32 *regs; u32 percpu_offset; - int ret; + int irq, ret; + struct clk *clk; regs = of_device_get_match_data(dev); if (!regs) { @@ -173,19 +215,18 @@ static int qcom_wdt_probe(struct platform_device *pdev) if (IS_ERR(wdt->base)) return PTR_ERR(wdt->base); - wdt->clk = devm_clk_get(dev, NULL); - if (IS_ERR(wdt->clk)) { + clk = devm_clk_get(dev, NULL); + if (IS_ERR(clk)) { dev_err(dev, "failed to get input clock\n"); - return PTR_ERR(wdt->clk); + return PTR_ERR(clk); } - ret = clk_prepare_enable(wdt->clk); + ret = clk_prepare_enable(clk); if (ret) { dev_err(dev, "failed to setup clock\n"); return ret; } - ret = devm_add_action_or_reset(dev, qcom_clk_disable_unprepare, - wdt->clk); + ret = devm_add_action_or_reset(dev, qcom_clk_disable_unprepare, clk); if (ret) return ret; @@ -197,14 +238,31 @@ static int qcom_wdt_probe(struct platform_device *pdev) * that it would bite before a second elapses it's usefulness is * limited. Bail if this is the case. */ - wdt->rate = clk_get_rate(wdt->clk); + wdt->rate = clk_get_rate(clk); if (wdt->rate == 0 || wdt->rate > 0x10000000U) { dev_err(dev, "invalid clock rate\n"); return -EINVAL; } - wdt->wdd.info = &qcom_wdt_info; + /* check if there is pretimeout support */ + irq = platform_get_irq(pdev, 0); + if (irq > 0) { + ret = devm_request_irq(dev, irq, qcom_wdt_isr, + IRQF_TRIGGER_RISING, + "wdt_bark", &wdt->wdd); + if (ret) + return ret; + + wdt->wdd.info = &qcom_wdt_pt_info; + wdt->wdd.pretimeout = 1; + } else { + if (irq == -EPROBE_DEFER) + return -EPROBE_DEFER; + + wdt->wdd.info = &qcom_wdt_info; + } + wdt->wdd.ops = &qcom_wdt_ops; wdt->wdd.min_timeout = 1; wdt->wdd.max_timeout = 0x10000000U / wdt->rate; diff --git a/drivers/watchdog/sprd_wdt.c b/drivers/watchdog/sprd_wdt.c index edba4e278685..0bb17b046140 100644 --- a/drivers/watchdog/sprd_wdt.c +++ b/drivers/watchdog/sprd_wdt.c @@ -284,10 +284,8 @@ static int sprd_wdt_probe(struct platform_device *pdev) } wdt->irq = platform_get_irq(pdev, 0); - if (wdt->irq < 0) { - dev_err(dev, "failed to get IRQ resource\n"); + if (wdt->irq < 0) return wdt->irq; - } ret = devm_request_irq(dev, wdt->irq, sprd_wdt_isr, IRQF_NO_SUSPEND, "sprd-wdt", (void *)wdt); diff --git a/drivers/watchdog/ziirave_wdt.c b/drivers/watchdog/ziirave_wdt.c index dec660c509b3..4a363a8b2d20 100644 --- a/drivers/watchdog/ziirave_wdt.c +++ b/drivers/watchdog/ziirave_wdt.c @@ -21,8 +21,11 @@ #include <linux/version.h> #include <linux/watchdog.h> +#include <asm/unaligned.h> + #define ZIIRAVE_TIMEOUT_MIN 3 #define ZIIRAVE_TIMEOUT_MAX 255 +#define ZIIRAVE_TIMEOUT_DEFAULT 30 #define ZIIRAVE_PING_VALUE 0x0 @@ -48,16 +51,12 @@ static char *ziirave_reasons[] = {"power cycle", "hw watchdog", NULL, NULL, #define ZIIRAVE_FIRM_PKT_TOTAL_SIZE 20 #define ZIIRAVE_FIRM_PKT_DATA_SIZE 16 -#define ZIIRAVE_FIRM_FLASH_MEMORY_START 0x1600 -#define ZIIRAVE_FIRM_FLASH_MEMORY_END 0x2bbf +#define ZIIRAVE_FIRM_FLASH_MEMORY_START (2 * 0x1600) +#define ZIIRAVE_FIRM_FLASH_MEMORY_END (2 * 0x2bbf) +#define ZIIRAVE_FIRM_PAGE_SIZE 128 /* Received and ready for next Download packet. */ #define ZIIRAVE_FIRM_DOWNLOAD_ACK 1 -/* Currently writing to flash. Retry Download status in a moment! */ -#define ZIIRAVE_FIRM_DOWNLOAD_BUSY 2 - -/* Wait for ACK timeout in ms */ -#define ZIIRAVE_FIRM_WAIT_FOR_ACK_TIMEOUT 50 /* Firmware commands */ #define ZIIRAVE_CMD_DOWNLOAD_START 0x10 @@ -68,6 +67,12 @@ static char *ziirave_reasons[] = {"power cycle", "hw watchdog", NULL, NULL, #define ZIIRAVE_CMD_JUMP_TO_BOOTLOADER 0x0c #define ZIIRAVE_CMD_DOWNLOAD_PACKET 0x0e +#define ZIIRAVE_CMD_JUMP_TO_BOOTLOADER_MAGIC 1 +#define ZIIRAVE_CMD_RESET_PROCESSOR_MAGIC 1 + +#define ZIIRAVE_FW_VERSION_FMT "02.%02u.%02u" +#define ZIIRAVE_BL_VERSION_FMT "01.%02u.%02u" + struct ziirave_wdt_rev { unsigned char major; unsigned char minor; @@ -165,67 +170,37 @@ static unsigned int ziirave_wdt_get_timeleft(struct watchdog_device *wdd) return ret; } -static int ziirave_firm_wait_for_ack(struct watchdog_device *wdd) +static int ziirave_firm_read_ack(struct watchdog_device *wdd) { struct i2c_client *client = to_i2c_client(wdd->parent); int ret; - unsigned long timeout; - timeout = jiffies + msecs_to_jiffies(ZIIRAVE_FIRM_WAIT_FOR_ACK_TIMEOUT); - do { - if (time_after(jiffies, timeout)) - return -ETIMEDOUT; - - usleep_range(5000, 10000); - - ret = i2c_smbus_read_byte(client); - if (ret < 0) { - dev_err(&client->dev, "Failed to read byte\n"); - return ret; - } - } while (ret == ZIIRAVE_FIRM_DOWNLOAD_BUSY); + ret = i2c_smbus_read_byte(client); + if (ret < 0) { + dev_err(&client->dev, "Failed to read status byte\n"); + return ret; + } return ret == ZIIRAVE_FIRM_DOWNLOAD_ACK ? 0 : -EIO; } -static int ziirave_firm_set_read_addr(struct watchdog_device *wdd, u16 addr) +static int ziirave_firm_set_read_addr(struct watchdog_device *wdd, u32 addr) { struct i2c_client *client = to_i2c_client(wdd->parent); + const u16 addr16 = (u16)addr / 2; u8 address[2]; - address[0] = addr & 0xff; - address[1] = (addr >> 8) & 0xff; + put_unaligned_le16(addr16, address); return i2c_smbus_write_block_data(client, ZIIRAVE_CMD_DOWNLOAD_SET_READ_ADDR, - ARRAY_SIZE(address), address); -} - -static int ziirave_firm_write_block_data(struct watchdog_device *wdd, - u8 command, u8 length, const u8 *data, - bool wait_for_ack) -{ - struct i2c_client *client = to_i2c_client(wdd->parent); - int ret; - - ret = i2c_smbus_write_block_data(client, command, length, data); - if (ret) { - dev_err(&client->dev, - "Failed to send command 0x%02x: %d\n", command, ret); - return ret; - } - - if (wait_for_ack) - ret = ziirave_firm_wait_for_ack(wdd); - - return ret; + sizeof(address), address); } -static int ziirave_firm_write_byte(struct watchdog_device *wdd, u8 command, - u8 byte, bool wait_for_ack) +static bool ziirave_firm_addr_readonly(u32 addr) { - return ziirave_firm_write_block_data(wdd, command, 1, &byte, - wait_for_ack); + return addr < ZIIRAVE_FIRM_FLASH_MEMORY_START || + addr > ZIIRAVE_FIRM_FLASH_MEMORY_END; } /* @@ -240,35 +215,53 @@ static int ziirave_firm_write_byte(struct watchdog_device *wdd, u8 command, * Data0 .. Data15: Array of 16 bytes of data. * Checksum: Checksum byte to verify data integrity. */ -static int ziirave_firm_write_pkt(struct watchdog_device *wdd, - const struct ihex_binrec *rec) +static int __ziirave_firm_write_pkt(struct watchdog_device *wdd, + u32 addr, const u8 *data, u8 len) { + const u16 addr16 = (u16)addr / 2; struct i2c_client *client = to_i2c_client(wdd->parent); u8 i, checksum = 0, packet[ZIIRAVE_FIRM_PKT_TOTAL_SIZE]; int ret; - u16 addr; - memset(packet, 0, ARRAY_SIZE(packet)); + /* Check max data size */ + if (len > ZIIRAVE_FIRM_PKT_DATA_SIZE) { + dev_err(&client->dev, "Firmware packet too long (%d)\n", + len); + return -EMSGSIZE; + } + + /* + * Ignore packets that are targeting program memory outisde of + * app partition, since they will be ignored by the + * bootloader. At the same time, we need to make sure we'll + * allow zero length packet that will be sent as the last step + * of firmware update + */ + if (len && ziirave_firm_addr_readonly(addr)) + return 0; /* Packet length */ - packet[0] = (u8)be16_to_cpu(rec->len); + packet[0] = len; /* Packet address */ - addr = (be32_to_cpu(rec->addr) & 0xffff) >> 1; - packet[1] = addr & 0xff; - packet[2] = (addr & 0xff00) >> 8; + put_unaligned_le16(addr16, packet + 1); - /* Packet data */ - if (be16_to_cpu(rec->len) > ZIIRAVE_FIRM_PKT_DATA_SIZE) - return -EMSGSIZE; - memcpy(packet + 3, rec->data, be16_to_cpu(rec->len)); + memcpy(packet + 3, data, len); + memset(packet + 3 + len, 0, ZIIRAVE_FIRM_PKT_DATA_SIZE - len); /* Packet checksum */ - for (i = 0; i < ZIIRAVE_FIRM_PKT_TOTAL_SIZE - 1; i++) + for (i = 0; i < len + 3; i++) checksum += packet[i]; packet[ZIIRAVE_FIRM_PKT_TOTAL_SIZE - 1] = checksum; - ret = ziirave_firm_write_block_data(wdd, ZIIRAVE_CMD_DOWNLOAD_PACKET, - ARRAY_SIZE(packet), packet, true); + ret = i2c_smbus_write_block_data(client, ZIIRAVE_CMD_DOWNLOAD_PACKET, + sizeof(packet), packet); + if (ret) { + dev_err(&client->dev, + "Failed to send DOWNLOAD_PACKET: %d\n", ret); + return ret; + } + + ret = ziirave_firm_read_ack(wdd); if (ret) dev_err(&client->dev, "Failed to write firmware packet at address 0x%04x: %d\n", @@ -277,6 +270,30 @@ static int ziirave_firm_write_pkt(struct watchdog_device *wdd, return ret; } +static int ziirave_firm_write_pkt(struct watchdog_device *wdd, + u32 addr, const u8 *data, u8 len) +{ + const u8 max_write_len = ZIIRAVE_FIRM_PAGE_SIZE - + (addr - ALIGN_DOWN(addr, ZIIRAVE_FIRM_PAGE_SIZE)); + int ret; + + if (len > max_write_len) { + /* + * If data crossed page boundary we need to split this + * write in two + */ + ret = __ziirave_firm_write_pkt(wdd, addr, data, max_write_len); + if (ret) + return ret; + + addr += max_write_len; + data += max_write_len; + len -= max_write_len; + } + + return __ziirave_firm_write_pkt(wdd, addr, data, len); +} + static int ziirave_firm_verify(struct watchdog_device *wdd, const struct firmware *fw) { @@ -284,16 +301,12 @@ static int ziirave_firm_verify(struct watchdog_device *wdd, const struct ihex_binrec *rec; int i, ret; u8 data[ZIIRAVE_FIRM_PKT_DATA_SIZE]; - u16 addr; for (rec = (void *)fw->data; rec; rec = ihex_next_binrec(rec)) { - /* Zero length marks end of records */ - if (!be16_to_cpu(rec->len)) - break; + const u16 len = be16_to_cpu(rec->len); + const u32 addr = be32_to_cpu(rec->addr); - addr = (be32_to_cpu(rec->addr) & 0xffff) >> 1; - if (addr < ZIIRAVE_FIRM_FLASH_MEMORY_START || - addr > ZIIRAVE_FIRM_FLASH_MEMORY_END) + if (ziirave_firm_addr_readonly(addr)) continue; ret = ziirave_firm_set_read_addr(wdd, addr); @@ -304,7 +317,7 @@ static int ziirave_firm_verify(struct watchdog_device *wdd, return ret; } - for (i = 0; i < ARRAY_SIZE(data); i++) { + for (i = 0; i < len; i++) { ret = i2c_smbus_read_byte_data(client, ZIIRAVE_CMD_DOWNLOAD_READ_BYTE); if (ret < 0) { @@ -315,7 +328,7 @@ static int ziirave_firm_verify(struct watchdog_device *wdd, data[i] = ret; } - if (memcmp(data, rec->data, be16_to_cpu(rec->len))) { + if (memcmp(data, rec->data, len)) { dev_err(&client->dev, "Firmware mismatch at address 0x%04x\n", addr); return -EINVAL; @@ -329,97 +342,45 @@ static int ziirave_firm_upload(struct watchdog_device *wdd, const struct firmware *fw) { struct i2c_client *client = to_i2c_client(wdd->parent); - int ret, words_till_page_break; const struct ihex_binrec *rec; - struct ihex_binrec *rec_new; + int ret; - ret = ziirave_firm_write_byte(wdd, ZIIRAVE_CMD_JUMP_TO_BOOTLOADER, 1, - false); - if (ret) + ret = i2c_smbus_write_byte_data(client, + ZIIRAVE_CMD_JUMP_TO_BOOTLOADER, + ZIIRAVE_CMD_JUMP_TO_BOOTLOADER_MAGIC); + if (ret) { + dev_err(&client->dev, "Failed to jump to bootloader\n"); return ret; + } msleep(500); - ret = ziirave_firm_write_byte(wdd, ZIIRAVE_CMD_DOWNLOAD_START, 1, true); - if (ret) + ret = i2c_smbus_write_byte(client, ZIIRAVE_CMD_DOWNLOAD_START); + if (ret) { + dev_err(&client->dev, "Failed to start download\n"); return ret; + } + + ret = ziirave_firm_read_ack(wdd); + if (ret) { + dev_err(&client->dev, "No ACK for start download\n"); + return ret; + } msleep(500); for (rec = (void *)fw->data; rec; rec = ihex_next_binrec(rec)) { - /* Zero length marks end of records */ - if (!be16_to_cpu(rec->len)) - break; - - /* Check max data size */ - if (be16_to_cpu(rec->len) > ZIIRAVE_FIRM_PKT_DATA_SIZE) { - dev_err(&client->dev, "Firmware packet too long (%d)\n", - be16_to_cpu(rec->len)); - return -EMSGSIZE; - } - - /* Calculate words till page break */ - words_till_page_break = (64 - ((be32_to_cpu(rec->addr) >> 1) & - 0x3f)); - if ((be16_to_cpu(rec->len) >> 1) > words_till_page_break) { - /* - * Data in passes page boundary, so we need to split in - * two blocks of data. Create a packet with the first - * block of data. - */ - rec_new = kzalloc(sizeof(struct ihex_binrec) + - (words_till_page_break << 1), - GFP_KERNEL); - if (!rec_new) - return -ENOMEM; - - rec_new->len = cpu_to_be16(words_till_page_break << 1); - rec_new->addr = rec->addr; - memcpy(rec_new->data, rec->data, - be16_to_cpu(rec_new->len)); - - ret = ziirave_firm_write_pkt(wdd, rec_new); - kfree(rec_new); - if (ret) - return ret; - - /* Create a packet with the second block of data */ - rec_new = kzalloc(sizeof(struct ihex_binrec) + - be16_to_cpu(rec->len) - - (words_till_page_break << 1), - GFP_KERNEL); - if (!rec_new) - return -ENOMEM; - - /* Remaining bytes */ - rec_new->len = rec->len - - cpu_to_be16(words_till_page_break << 1); - - rec_new->addr = cpu_to_be32(be32_to_cpu(rec->addr) + - (words_till_page_break << 1)); - - memcpy(rec_new->data, - rec->data + (words_till_page_break << 1), - be16_to_cpu(rec_new->len)); - - ret = ziirave_firm_write_pkt(wdd, rec_new); - kfree(rec_new); - if (ret) - return ret; - } else { - ret = ziirave_firm_write_pkt(wdd, rec); - if (ret) - return ret; - } + ret = ziirave_firm_write_pkt(wdd, be32_to_cpu(rec->addr), + rec->data, be16_to_cpu(rec->len)); + if (ret) + return ret; } - /* For end of download, the length field will be set to 0 */ - rec_new = kzalloc(sizeof(struct ihex_binrec) + 1, GFP_KERNEL); - if (!rec_new) - return -ENOMEM; - - ret = ziirave_firm_write_pkt(wdd, rec_new); - kfree(rec_new); + /* + * Finish firmware download process by sending a zero length + * payload + */ + ret = ziirave_firm_write_pkt(wdd, 0, NULL, 0); if (ret) { dev_err(&client->dev, "Failed to send EMPTY packet: %d\n", ret); return ret; @@ -437,15 +398,22 @@ static int ziirave_firm_upload(struct watchdog_device *wdd, } /* End download operation */ - ret = ziirave_firm_write_byte(wdd, ZIIRAVE_CMD_DOWNLOAD_END, 1, false); - if (ret) + ret = i2c_smbus_write_byte(client, ZIIRAVE_CMD_DOWNLOAD_END); + if (ret) { + dev_err(&client->dev, + "Failed to end firmware download: %d\n", ret); return ret; + } /* Reset the processor */ - ret = ziirave_firm_write_byte(wdd, ZIIRAVE_CMD_RESET_PROCESSOR, 1, - false); - if (ret) + ret = i2c_smbus_write_byte_data(client, + ZIIRAVE_CMD_RESET_PROCESSOR, + ZIIRAVE_CMD_RESET_PROCESSOR_MAGIC); + if (ret) { + dev_err(&client->dev, + "Failed to reset the watchdog: %d\n", ret); return ret; + } msleep(500); @@ -478,7 +446,7 @@ static ssize_t ziirave_wdt_sysfs_show_firm(struct device *dev, if (ret) return ret; - ret = sprintf(buf, "02.%02u.%02u", w_priv->firmware_rev.major, + ret = sprintf(buf, ZIIRAVE_FW_VERSION_FMT, w_priv->firmware_rev.major, w_priv->firmware_rev.minor); mutex_unlock(&w_priv->sysfs_mutex); @@ -501,7 +469,7 @@ static ssize_t ziirave_wdt_sysfs_show_boot(struct device *dev, if (ret) return ret; - ret = sprintf(buf, "01.%02u.%02u", w_priv->bootloader_rev.major, + ret = sprintf(buf, ZIIRAVE_BL_VERSION_FMT, w_priv->bootloader_rev.major, w_priv->bootloader_rev.minor); mutex_unlock(&w_priv->sysfs_mutex); @@ -568,7 +536,8 @@ static ssize_t ziirave_wdt_sysfs_store_firm(struct device *dev, goto unlock_mutex; } - dev_info(&client->dev, "Firmware updated to version 02.%02u.%02u\n", + dev_info(&client->dev, + "Firmware updated to version " ZIIRAVE_FW_VERSION_FMT "\n", w_priv->firmware_rev.major, w_priv->firmware_rev.minor); /* Restore the watchdog timeout */ @@ -611,7 +580,7 @@ static int ziirave_wdt_init_duration(struct i2c_client *client) &reset_duration); if (ret) { dev_info(&client->dev, - "Unable to set reset pulse duration, using default\n"); + "No reset pulse duration specified, using default\n"); return 0; } } @@ -633,7 +602,10 @@ static int ziirave_wdt_probe(struct i2c_client *client, struct ziirave_wdt_data *w_priv; int val; - if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA)) + if (!i2c_check_functionality(client->adapter, + I2C_FUNC_SMBUS_BYTE | + I2C_FUNC_SMBUS_BYTE_DATA | + I2C_FUNC_SMBUS_WRITE_BLOCK_DATA)) return -ENODEV; w_priv = devm_kzalloc(&client->dev, sizeof(*w_priv), GFP_KERNEL); @@ -658,57 +630,80 @@ static int ziirave_wdt_probe(struct i2c_client *client, */ if (w_priv->wdd.timeout == 0) { val = i2c_smbus_read_byte_data(client, ZIIRAVE_WDT_TIMEOUT); - if (val < 0) + if (val < 0) { + dev_err(&client->dev, "Failed to read timeout\n"); return val; + } - if (val < ZIIRAVE_TIMEOUT_MIN) - return -ENODEV; + if (val > ZIIRAVE_TIMEOUT_MAX || + val < ZIIRAVE_TIMEOUT_MIN) + val = ZIIRAVE_TIMEOUT_DEFAULT; w_priv->wdd.timeout = val; - } else { - ret = ziirave_wdt_set_timeout(&w_priv->wdd, - w_priv->wdd.timeout); - if (ret) - return ret; + } - dev_info(&client->dev, "Timeout set to %ds.", - w_priv->wdd.timeout); + ret = ziirave_wdt_set_timeout(&w_priv->wdd, w_priv->wdd.timeout); + if (ret) { + dev_err(&client->dev, "Failed to set timeout\n"); + return ret; } + dev_info(&client->dev, "Timeout set to %ds\n", w_priv->wdd.timeout); + watchdog_set_nowayout(&w_priv->wdd, nowayout); i2c_set_clientdata(client, w_priv); /* If in unconfigured state, set to stopped */ val = i2c_smbus_read_byte_data(client, ZIIRAVE_WDT_STATE); - if (val < 0) + if (val < 0) { + dev_err(&client->dev, "Failed to read state\n"); return val; + } if (val == ZIIRAVE_STATE_INITIAL) ziirave_wdt_stop(&w_priv->wdd); ret = ziirave_wdt_init_duration(client); - if (ret) + if (ret) { + dev_err(&client->dev, "Failed to init duration\n"); return ret; + } ret = ziirave_wdt_revision(client, &w_priv->firmware_rev, ZIIRAVE_WDT_FIRM_VER_MAJOR); - if (ret) + if (ret) { + dev_err(&client->dev, "Failed to read firmware version\n"); return ret; + } + + dev_info(&client->dev, + "Firmware version: " ZIIRAVE_FW_VERSION_FMT "\n", + w_priv->firmware_rev.major, w_priv->firmware_rev.minor); ret = ziirave_wdt_revision(client, &w_priv->bootloader_rev, ZIIRAVE_WDT_BOOT_VER_MAJOR); - if (ret) + if (ret) { + dev_err(&client->dev, "Failed to read bootloader version\n"); return ret; + } + + dev_info(&client->dev, + "Bootloader version: " ZIIRAVE_BL_VERSION_FMT "\n", + w_priv->bootloader_rev.major, w_priv->bootloader_rev.minor); w_priv->reset_reason = i2c_smbus_read_byte_data(client, ZIIRAVE_WDT_RESET_REASON); - if (w_priv->reset_reason < 0) + if (w_priv->reset_reason < 0) { + dev_err(&client->dev, "Failed to read reset reason\n"); return w_priv->reset_reason; + } if (w_priv->reset_reason >= ARRAY_SIZE(ziirave_reasons) || - !ziirave_reasons[w_priv->reset_reason]) + !ziirave_reasons[w_priv->reset_reason]) { + dev_err(&client->dev, "Invalid reset reason\n"); return -ENODEV; + } ret = watchdog_register_device(&w_priv->wdd); diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 2e8570c09789..6c8843968a52 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -247,7 +247,7 @@ static void xen_irq_info_cleanup(struct irq_info *info) */ unsigned int evtchn_from_irq(unsigned irq) { - if (unlikely(WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq))) + if (WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq)) return 0; return info_for_irq(irq)->evtchn; diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index 3eeb9bea7630..224df03ce42e 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -17,6 +17,8 @@ #include "../pci/pci.h" #ifdef CONFIG_PCI_MMCONFIG #include <asm/pci_x86.h> + +static int xen_mcfg_late(void); #endif static bool __read_mostly pci_seg_supported = true; @@ -28,7 +30,18 @@ static int xen_add_device(struct device *dev) #ifdef CONFIG_PCI_IOV struct pci_dev *physfn = pci_dev->physfn; #endif - +#ifdef CONFIG_PCI_MMCONFIG + static bool pci_mcfg_reserved = false; + /* + * Reserve MCFG areas in Xen on first invocation due to this being + * potentially called from inside of acpi_init immediately after + * MCFG table has been finally parsed. + */ + if (!pci_mcfg_reserved) { + xen_mcfg_late(); + pci_mcfg_reserved = true; + } +#endif if (pci_seg_supported) { struct { struct physdev_pci_device_add add; @@ -201,7 +214,7 @@ static int __init register_xen_pci_notifier(void) arch_initcall(register_xen_pci_notifier); #ifdef CONFIG_PCI_MMCONFIG -static int __init xen_mcfg_late(void) +static int xen_mcfg_late(void) { struct pci_mmcfg_region *cfg; int rc; @@ -240,8 +253,4 @@ static int __init xen_mcfg_late(void) } return 0; } -/* - * Needs to be done after acpi_init which are subsys_initcall. - */ -subsys_initcall_sync(xen_mcfg_late); #endif diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 58c9365fa217..bd3a10dfac15 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -39,6 +39,7 @@ #include <asm/xen/page-coherent.h> #include <trace/events/swiotlb.h> +#define MAX_DMA_BITS 32 /* * Used to do a quick range check in swiotlb_tbl_unmap_single and * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this @@ -115,8 +116,6 @@ static int is_xen_swiotlb_buffer(dma_addr_t dma_addr) return 0; } -static int max_dma_bits = 32; - static int xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs) { @@ -136,7 +135,7 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs) p + (i << IO_TLB_SHIFT), get_order(slabs << IO_TLB_SHIFT), dma_bits, &dma_handle); - } while (rc && dma_bits++ < max_dma_bits); + } while (rc && dma_bits++ < MAX_DMA_BITS); if (rc) return rc; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index cec3b4146440..ad4c6b1d5074 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1121,7 +1121,8 @@ out_free_interp: * (since it grows up, and may collide early with the stack * growing down), and into the unused ELF_ET_DYN_BASE region. */ - if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && !interpreter) + if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && + loc->elf_ex.e_type == ET_DYN && !interpreter) current->mm->brk = current->mm->start_brk = ELF_ET_DYN_BASE; diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 814ad2c2ba80..054acd9fd033 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -88,9 +88,7 @@ static int fat__get_entry(struct inode *dir, loff_t *pos, int err, offset; next: - if (*bh) - brelse(*bh); - + brelse(*bh); *bh = NULL; iblock = *pos >> sb->s_blocksize_bits; err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0, false); diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index cbe70637c117..0e6406c4f362 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -163,13 +163,11 @@ static const struct export_operations jffs2_export_ops = { * Opt_rp_size: size of reserved pool in KiB */ enum { - Opt_source, Opt_override_compr, Opt_rp_size, }; static const struct fs_parameter_spec jffs2_param_specs[] = { - fsparam_string ("source", Opt_source), fsparam_enum ("compr", Opt_override_compr), fsparam_u32 ("rp_size", Opt_rp_size), {} diff --git a/fs/namespace.c b/fs/namespace.c index b75d458f817d..fe0e9e1410fe 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3026,7 +3026,7 @@ void *copy_mount_options(const void __user * data) * the remainder of the page. */ /* copy_from_user cannot cross TASK_SIZE ! */ - size = TASK_SIZE - (unsigned long)data; + size = TASK_SIZE - (unsigned long)untagged_addr(data); if (size > PAGE_SIZE) size = PAGE_SIZE; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 0adfd8840110..e180033e35cf 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1669,10 +1669,8 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) #endif /* CONFIG_NFSV4 */ -/* - * Code common to create, mkdir, and mknod. - */ -int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, +struct dentry * +nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label) { @@ -1680,13 +1678,10 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, struct inode *dir = d_inode(parent); struct inode *inode; struct dentry *d; - int error = -EACCES; + int error; d_drop(dentry); - /* We may have been initialized further down */ - if (d_really_is_positive(dentry)) - goto out; if (fhandle->size == 0) { error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, NULL); if (error) @@ -1702,18 +1697,32 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, } inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label); d = d_splice_alias(inode, dentry); - if (IS_ERR(d)) { - error = PTR_ERR(d); - goto out_error; - } - dput(d); out: dput(parent); - return 0; + return d; out_error: nfs_mark_for_revalidate(dir); - dput(parent); - return error; + d = ERR_PTR(error); + goto out; +} +EXPORT_SYMBOL_GPL(nfs_add_or_obtain); + +/* + * Code common to create, mkdir, and mknod. + */ +int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, + struct nfs4_label *label) +{ + struct dentry *d; + + d = nfs_add_or_obtain(dentry, fhandle, fattr, label); + if (IS_ERR(d)) + return PTR_ERR(d); + + /* Callers don't care */ + dput(d); + return 0; } EXPORT_SYMBOL_GPL(nfs_instantiate); diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 3cb073c50fa6..c9b605f6c9cb 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -1164,6 +1164,7 @@ static struct pnfs_layoutdriver_type filelayout_type = { .id = LAYOUT_NFSV4_1_FILES, .name = "LAYOUT_NFSV4_1_FILES", .owner = THIS_MODULE, + .flags = PNFS_LAYOUTGET_ON_OPEN, .max_layoutget_response = 4096, /* 1 page or so... */ .alloc_layout_hdr = filelayout_alloc_layout_hdr, .free_layout_hdr = filelayout_free_layout_hdr, diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index e64f810223be..447a3c17fa8e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -16,14 +16,6 @@ extern const struct export_operations nfs_export_ops; struct nfs_string; -/* Maximum number of readahead requests - * FIXME: this should really be a sysctl so that users may tune it to suit - * their needs. People that do NFS over a slow network, might for - * instance want to reduce it to something closer to 1 for improved - * interactive response. - */ -#define NFS_MAX_READAHEAD (RPC_DEF_SLOT_TABLE - 1) - static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) { if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid)) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index a3ad2d46fd42..9eb2f1a503ab 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -279,15 +279,17 @@ static struct nfs3_createdata *nfs3_alloc_createdata(void) return data; } -static int nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata *data) +static struct dentry * +nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata *data) { int status; status = rpc_call_sync(NFS_CLIENT(dir), &data->msg, 0); nfs_post_op_update_inode(dir, data->res.dir_attr); - if (status == 0) - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); - return status; + if (status != 0) + return ERR_PTR(status); + + return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr, NULL); } static void nfs3_free_createdata(struct nfs3_createdata *data) @@ -304,6 +306,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, { struct posix_acl *default_acl, *acl; struct nfs3_createdata *data; + struct dentry *d_alias; int status = -ENOMEM; dprintk("NFS call create %pd\n", dentry); @@ -330,7 +333,8 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, goto out; for (;;) { - status = nfs3_do_create(dir, dentry, data); + d_alias = nfs3_do_create(dir, dentry, data); + status = PTR_ERR_OR_ZERO(d_alias); if (status != -ENOTSUPP) break; @@ -355,6 +359,9 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, if (status != 0) goto out_release_acls; + if (d_alias) + dentry = d_alias; + /* When we created the file with exclusive semantics, make * sure we set the attributes afterwards. */ if (data->arg.create.createmode == NFS3_CREATE_EXCLUSIVE) { @@ -372,11 +379,13 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, nfs_post_op_update_inode(d_inode(dentry), data->res.fattr); dprintk("NFS reply setattr (post-create): %d\n", status); if (status != 0) - goto out_release_acls; + goto out_dput; } status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl); +out_dput: + dput(d_alias); out_release_acls: posix_acl_release(acl); posix_acl_release(default_acl); @@ -504,6 +513,7 @@ nfs3_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page, unsigned int len, struct iattr *sattr) { struct nfs3_createdata *data; + struct dentry *d_alias; int status = -ENOMEM; if (len > NFS3_MAXPATHLEN) @@ -522,7 +532,11 @@ nfs3_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page, data->arg.symlink.pathlen = len; data->arg.symlink.sattr = sattr; - status = nfs3_do_create(dir, dentry, data); + d_alias = nfs3_do_create(dir, dentry, data); + status = PTR_ERR_OR_ZERO(d_alias); + + if (status == 0) + dput(d_alias); nfs3_free_createdata(data); out: @@ -535,6 +549,7 @@ nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) { struct posix_acl *default_acl, *acl; struct nfs3_createdata *data; + struct dentry *d_alias; int status = -ENOMEM; dprintk("NFS call mkdir %pd\n", dentry); @@ -553,12 +568,18 @@ nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) data->arg.mkdir.len = dentry->d_name.len; data->arg.mkdir.sattr = sattr; - status = nfs3_do_create(dir, dentry, data); + d_alias = nfs3_do_create(dir, dentry, data); + status = PTR_ERR_OR_ZERO(d_alias); + if (status != 0) goto out_release_acls; + if (d_alias) + dentry = d_alias; + status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl); + dput(d_alias); out_release_acls: posix_acl_release(acl); posix_acl_release(default_acl); @@ -660,6 +681,7 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, { struct posix_acl *default_acl, *acl; struct nfs3_createdata *data; + struct dentry *d_alias; int status = -ENOMEM; dprintk("NFS call mknod %pd %u:%u\n", dentry, @@ -698,12 +720,17 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, goto out; } - status = nfs3_do_create(dir, dentry, data); + d_alias = nfs3_do_create(dir, dentry, data); + status = PTR_ERR_OR_ZERO(d_alias); if (status != 0) goto out_release_acls; + if (d_alias) + dentry = d_alias; + status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl); + dput(d_alias); out_release_acls: posix_acl_release(acl); posix_acl_release(default_acl); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 3564da1ba8a1..16b2e5cc3e94 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -491,8 +491,6 @@ extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl); extern int nfs4_select_rw_stateid(struct nfs4_state *, fmode_t, const struct nfs_lock_context *, nfs4_stateid *, const struct cred **); -extern bool nfs4_refresh_open_stateid(nfs4_stateid *dst, - struct nfs4_state *state); extern bool nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state); @@ -574,6 +572,15 @@ static inline bool nfs4_stateid_is_newer(const nfs4_stateid *s1, const nfs4_stat return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0; } +static inline void nfs4_stateid_seqid_inc(nfs4_stateid *s1) +{ + u32 seqid = be32_to_cpu(s1->seqid); + + if (++seqid == 0) + ++seqid; + s1->seqid = cpu_to_be32(seqid); +} + static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state) { return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1406858bae6c..11eafcfc490b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1073,14 +1073,26 @@ static const struct rpc_call_ops nfs40_call_sync_ops = { .rpc_call_done = nfs40_call_sync_done, }; +static int nfs4_call_sync_custom(struct rpc_task_setup *task_setup) +{ + int ret; + struct rpc_task *task; + + task = rpc_run_task(task_setup); + if (IS_ERR(task)) + return PTR_ERR(task); + + ret = task->tk_status; + rpc_put_task(task); + return ret; +} + static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, struct nfs_server *server, struct rpc_message *msg, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res) { - int ret; - struct rpc_task *task; struct nfs_client *clp = server->nfs_client; struct nfs4_call_sync_data data = { .seq_server = server, @@ -1094,14 +1106,7 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, .callback_data = &data }; - task = rpc_run_task(&task_setup); - if (IS_ERR(task)) - ret = PTR_ERR(task); - else { - ret = task->tk_status; - rpc_put_task(task); - } - return ret; + return nfs4_call_sync_custom(&task_setup); } int nfs4_call_sync(struct rpc_clnt *clnt, @@ -3308,6 +3313,75 @@ nfs4_wait_on_layoutreturn(struct inode *inode, struct rpc_task *task) return pnfs_wait_on_layoutreturn(inode, task); } +/* + * Update the seqid of an open stateid + */ +static void nfs4_sync_open_stateid(nfs4_stateid *dst, + struct nfs4_state *state) +{ + __be32 seqid_open; + u32 dst_seqid; + int seq; + + for (;;) { + if (!nfs4_valid_open_stateid(state)) + break; + seq = read_seqbegin(&state->seqlock); + if (!nfs4_state_match_open_stateid_other(state, dst)) { + nfs4_stateid_copy(dst, &state->open_stateid); + if (read_seqretry(&state->seqlock, seq)) + continue; + break; + } + seqid_open = state->open_stateid.seqid; + if (read_seqretry(&state->seqlock, seq)) + continue; + + dst_seqid = be32_to_cpu(dst->seqid); + if ((s32)(dst_seqid - be32_to_cpu(seqid_open)) < 0) + dst->seqid = seqid_open; + break; + } +} + +/* + * Update the seqid of an open stateid after receiving + * NFS4ERR_OLD_STATEID + */ +static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst, + struct nfs4_state *state) +{ + __be32 seqid_open; + u32 dst_seqid; + bool ret; + int seq; + + for (;;) { + ret = false; + if (!nfs4_valid_open_stateid(state)) + break; + seq = read_seqbegin(&state->seqlock); + if (!nfs4_state_match_open_stateid_other(state, dst)) { + if (read_seqretry(&state->seqlock, seq)) + continue; + break; + } + seqid_open = state->open_stateid.seqid; + if (read_seqretry(&state->seqlock, seq)) + continue; + + dst_seqid = be32_to_cpu(dst->seqid); + if ((s32)(dst_seqid - be32_to_cpu(seqid_open)) >= 0) + dst->seqid = cpu_to_be32(dst_seqid + 1); + else + dst->seqid = seqid_open; + ret = true; + break; + } + + return ret; +} + struct nfs4_closedata { struct inode *inode; struct nfs4_state *state; @@ -3358,32 +3432,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data) trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status); /* Handle Layoutreturn errors */ - if (calldata->arg.lr_args && task->tk_status != 0) { - switch (calldata->res.lr_ret) { - default: - calldata->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT; - break; - case 0: - calldata->arg.lr_args = NULL; - calldata->res.lr_res = NULL; - break; - case -NFS4ERR_OLD_STATEID: - if (nfs4_layoutreturn_refresh_stateid(&calldata->arg.lr_args->stateid, - &calldata->arg.lr_args->range, - calldata->inode)) - goto lr_restart; - /* Fallthrough */ - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_EXPIRED: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_UNKNOWN_LAYOUTTYPE: - case -NFS4ERR_WRONG_CRED: - calldata->arg.lr_args = NULL; - calldata->res.lr_res = NULL; - goto lr_restart; - } - } + if (pnfs_roc_done(task, calldata->inode, + &calldata->arg.lr_args, + &calldata->res.lr_res, + &calldata->res.lr_ret) == -EAGAIN) + goto out_restart; /* hmm. we are done with the inode, and in the process of freeing * the state_owner. we keep this around to process errors @@ -3403,7 +3456,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data) break; case -NFS4ERR_OLD_STATEID: /* Did we race with OPEN? */ - if (nfs4_refresh_open_stateid(&calldata->arg.stateid, + if (nfs4_refresh_open_old_stateid(&calldata->arg.stateid, state)) goto out_restart; goto out_release; @@ -3415,7 +3468,9 @@ static void nfs4_close_done(struct rpc_task *task, void *data) task->tk_msg.rpc_cred); /* Fallthrough */ case -NFS4ERR_BAD_STATEID: - break; + if (calldata->arg.fmode == 0) + break; + /* Fallthrough */ default: task->tk_status = nfs4_async_handle_exception(task, server, task->tk_status, &exception); @@ -3430,8 +3485,6 @@ out_release: nfs_refresh_inode(calldata->inode, &calldata->fattr); dprintk("%s: done, ret = %d!\n", __func__, task->tk_status); return; -lr_restart: - calldata->res.lr_ret = 0; out_restart: task->tk_status = 0; rpc_restart_call_prepare(task); @@ -3472,8 +3525,8 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) } else if (is_rdwr) calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; - if (!nfs4_valid_open_stateid(state) || - !nfs4_refresh_open_stateid(&calldata->arg.stateid, state)) + nfs4_sync_open_stateid(&calldata->arg.stateid, state); + if (!nfs4_valid_open_stateid(state)) call_close = 0; spin_unlock(&state->owner->so_lock); @@ -6018,7 +6071,6 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, .rpc_resp = res, .rpc_cred = cred, }; - struct rpc_task *task; struct rpc_task_setup task_setup_data = { .rpc_client = clp->cl_rpcclient, .rpc_message = &msg, @@ -6051,17 +6103,12 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, dprintk("NFS call setclientid auth=%s, '%s'\n", clp->cl_rpcclient->cl_auth->au_ops->au_name, clp->cl_owner_id); - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) { - status = PTR_ERR(task); - goto out; - } - status = task->tk_status; + + status = nfs4_call_sync_custom(&task_setup_data); if (setclientid.sc_cred) { clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred); put_rpccred(setclientid.sc_cred); } - rpc_put_task(task); out: trace_nfs4_setclientid(clp, status); dprintk("NFS reply setclientid: %d\n", status); @@ -6129,32 +6176,11 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status); /* Handle Layoutreturn errors */ - if (data->args.lr_args && task->tk_status != 0) { - switch(data->res.lr_ret) { - default: - data->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT; - break; - case 0: - data->args.lr_args = NULL; - data->res.lr_res = NULL; - break; - case -NFS4ERR_OLD_STATEID: - if (nfs4_layoutreturn_refresh_stateid(&data->args.lr_args->stateid, - &data->args.lr_args->range, - data->inode)) - goto lr_restart; - /* Fallthrough */ - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_EXPIRED: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_UNKNOWN_LAYOUTTYPE: - case -NFS4ERR_WRONG_CRED: - data->args.lr_args = NULL; - data->res.lr_res = NULL; - goto lr_restart; - } - } + if (pnfs_roc_done(task, data->inode, + &data->args.lr_args, + &data->res.lr_res, + &data->res.lr_ret) == -EAGAIN) + goto out_restart; switch (task->tk_status) { case 0: @@ -6192,8 +6218,6 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) } data->rpc_status = task->tk_status; return; -lr_restart: - data->res.lr_ret = 0; out_restart: task->tk_status = 0; rpc_restart_call_prepare(task); @@ -6386,6 +6410,42 @@ static int nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock * return err; } +/* + * Update the seqid of a lock stateid after receiving + * NFS4ERR_OLD_STATEID + */ +static bool nfs4_refresh_lock_old_stateid(nfs4_stateid *dst, + struct nfs4_lock_state *lsp) +{ + struct nfs4_state *state = lsp->ls_state; + bool ret = false; + + spin_lock(&state->state_lock); + if (!nfs4_stateid_match_other(dst, &lsp->ls_stateid)) + goto out; + if (!nfs4_stateid_is_newer(&lsp->ls_stateid, dst)) + nfs4_stateid_seqid_inc(dst); + else + dst->seqid = lsp->ls_stateid.seqid; + ret = true; +out: + spin_unlock(&state->state_lock); + return ret; +} + +static bool nfs4_sync_lock_stateid(nfs4_stateid *dst, + struct nfs4_lock_state *lsp) +{ + struct nfs4_state *state = lsp->ls_state; + bool ret; + + spin_lock(&state->state_lock); + ret = !nfs4_stateid_match_other(dst, &lsp->ls_stateid); + nfs4_stateid_copy(dst, &lsp->ls_stateid); + spin_unlock(&state->state_lock); + return ret; +} + struct nfs4_unlockdata { struct nfs_locku_args arg; struct nfs_locku_res res; @@ -6403,7 +6463,8 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, struct nfs_seqid *seqid) { struct nfs4_unlockdata *p; - struct inode *inode = lsp->ls_state->inode; + struct nfs4_state *state = lsp->ls_state; + struct inode *inode = state->inode; p = kzalloc(sizeof(*p), GFP_NOFS); if (p == NULL) @@ -6419,6 +6480,9 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, locks_init_lock(&p->fl); locks_copy_lock(&p->fl, fl); p->server = NFS_SERVER(inode); + spin_lock(&state->state_lock); + nfs4_stateid_copy(&p->arg.stateid, &lsp->ls_stateid); + spin_unlock(&state->state_lock); return p; } @@ -6457,10 +6521,14 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) task->tk_msg.rpc_cred); /* Fall through */ case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: - if (!nfs4_stateid_match(&calldata->arg.stateid, - &calldata->lsp->ls_stateid)) + if (nfs4_sync_lock_stateid(&calldata->arg.stateid, + calldata->lsp)) + rpc_restart_call_prepare(task); + break; + case -NFS4ERR_OLD_STATEID: + if (nfs4_refresh_lock_old_stateid(&calldata->arg.stateid, + calldata->lsp)) rpc_restart_call_prepare(task); break; default: @@ -6483,7 +6551,6 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data) if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0) goto out_wait; - nfs4_stateid_copy(&calldata->arg.stateid, &calldata->lsp->ls_stateid); if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) { /* Note: exit _without_ running nfs4_locku_done */ goto out_no_action; @@ -7645,6 +7712,8 @@ int nfs4_proc_fsid_present(struct inode *inode, const struct cred *cred) static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors, bool use_integrity) { int status; + struct rpc_clnt *clnt = NFS_SERVER(dir)->client; + struct nfs_client *clp = NFS_SERVER(dir)->nfs_client; struct nfs4_secinfo_arg args = { .dir_fh = NFS_FH(dir), .name = name, @@ -7657,26 +7726,37 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct .rpc_argp = &args, .rpc_resp = &res, }; - struct rpc_clnt *clnt = NFS_SERVER(dir)->client; + struct nfs4_call_sync_data data = { + .seq_server = NFS_SERVER(dir), + .seq_args = &args.seq_args, + .seq_res = &res.seq_res, + }; + struct rpc_task_setup task_setup = { + .rpc_client = clnt, + .rpc_message = &msg, + .callback_ops = clp->cl_mvops->call_sync_ops, + .callback_data = &data, + .flags = RPC_TASK_NO_ROUND_ROBIN, + }; const struct cred *cred = NULL; if (use_integrity) { - clnt = NFS_SERVER(dir)->nfs_client->cl_rpcclient; - cred = nfs4_get_clid_cred(NFS_SERVER(dir)->nfs_client); + clnt = clp->cl_rpcclient; + task_setup.rpc_client = clnt; + + cred = nfs4_get_clid_cred(clp); msg.rpc_cred = cred; } dprintk("NFS call secinfo %s\n", name->name); - nfs4_state_protect(NFS_SERVER(dir)->nfs_client, - NFS_SP4_MACH_CRED_SECINFO, &clnt, &msg); + nfs4_state_protect(clp, NFS_SP4_MACH_CRED_SECINFO, &clnt, &msg); + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); + status = nfs4_call_sync_custom(&task_setup); - status = nfs4_call_sync(clnt, NFS_SERVER(dir), &msg, &args.seq_args, - &res.seq_res, RPC_TASK_NO_ROUND_ROBIN); dprintk("NFS reply secinfo: %d\n", status); put_cred(cred); - return status; } @@ -8344,7 +8424,6 @@ static const struct rpc_call_ops nfs4_get_lease_time_ops = { int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo) { - struct rpc_task *task; struct nfs4_get_lease_time_args args; struct nfs4_get_lease_time_res res = { .lr_fsinfo = fsinfo, @@ -8366,17 +8445,9 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo) .callback_data = &data, .flags = RPC_TASK_TIMEOUT, }; - int status; nfs4_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0, 1); - task = rpc_run_task(&task_setup); - - if (IS_ERR(task)) - return PTR_ERR(task); - - status = task->tk_status; - rpc_put_task(task); - return status; + return nfs4_call_sync_custom(&task_setup); } #ifdef CONFIG_NFS_V4_1 @@ -8845,7 +8916,6 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp, const struct cred *cred) { struct nfs4_reclaim_complete_data *calldata; - struct rpc_task *task; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RECLAIM_COMPLETE], .rpc_cred = cred, @@ -8854,7 +8924,7 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp, .rpc_client = clp->cl_rpcclient, .rpc_message = &msg, .callback_ops = &nfs4_reclaim_complete_call_ops, - .flags = RPC_TASK_ASYNC | RPC_TASK_NO_ROUND_ROBIN, + .flags = RPC_TASK_NO_ROUND_ROBIN, }; int status = -ENOMEM; @@ -8869,15 +8939,7 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp, msg.rpc_argp = &calldata->arg; msg.rpc_resp = &calldata->res; task_setup_data.callback_data = calldata; - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) { - status = PTR_ERR(task); - goto out; - } - status = rpc_wait_for_completion_task(task); - if (status == 0) - status = task->tk_status; - rpc_put_task(task); + status = nfs4_call_sync_custom(&task_setup_data); out: dprintk("<-- %s status=%d\n", __func__, status); return status; @@ -9103,10 +9165,19 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) if (!nfs41_sequence_process(task, &lrp->res.seq_res)) return; + /* + * Was there an RPC level error? Assume the call succeeded, + * and that we need to release the layout + */ + if (task->tk_rpc_status != 0 && RPC_WAS_SENT(task)) { + lrp->res.lrs_present = 0; + return; + } + server = NFS_SERVER(lrp->args.inode); switch (task->tk_status) { case -NFS4ERR_OLD_STATEID: - if (nfs4_layoutreturn_refresh_stateid(&lrp->args.stateid, + if (nfs4_layout_refresh_old_stateid(&lrp->args.stateid, &lrp->args.range, lrp->args.inode)) goto out_restart; @@ -9362,18 +9433,32 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_resp = &res, }; struct rpc_clnt *clnt = server->client; + struct nfs4_call_sync_data data = { + .seq_server = server, + .seq_args = &args.seq_args, + .seq_res = &res.seq_res, + }; + struct rpc_task_setup task_setup = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = server->nfs_client->cl_mvops->call_sync_ops, + .callback_data = &data, + .flags = RPC_TASK_NO_ROUND_ROBIN, + }; const struct cred *cred = NULL; int status; if (use_integrity) { clnt = server->nfs_client->cl_rpcclient; + task_setup.rpc_client = clnt; + cred = nfs4_get_clid_cred(server->nfs_client); msg.rpc_cred = cred; } dprintk("--> %s\n", __func__); - status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, - &res.seq_res, RPC_TASK_NO_ROUND_ROBIN); + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); + status = nfs4_call_sync_custom(&task_setup); dprintk("<-- %s status=%d\n", __func__, status); put_cred(cred); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index cad4e064b328..0c6d53dc3672 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1015,22 +1015,6 @@ out: return ret; } -bool nfs4_refresh_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) -{ - bool ret; - int seq; - - do { - ret = false; - seq = read_seqbegin(&state->seqlock); - if (nfs4_state_match_open_stateid_other(state, dst)) { - dst->seqid = state->open_stateid.seqid; - ret = true; - } - } while (read_seqretry(&state->seqlock, seq)); - return ret; -} - bool nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) { bool ret; @@ -2095,8 +2079,10 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred } status = nfs4_begin_drain_session(clp); - if (status != 0) - return status; + if (status != 0) { + result = status; + goto out; + } status = nfs4_replace_transport(server, locations); if (status != 0) { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 46a8d636d151..ab07db0f07cd 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1174,7 +1174,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, } else *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } - if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { + if (label && (bmval[2] & FATTR4_WORD2_SECURITY_LABEL)) { *p++ = cpu_to_be32(label->lfs); *p++ = cpu_to_be32(label->pi); *p++ = cpu_to_be32(label->len); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 4525d5acae38..bb80034a7661 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -359,9 +359,10 @@ pnfs_clear_lseg_state(struct pnfs_layout_segment *lseg, } /* - * Update the seqid of a layout stateid + * Update the seqid of a layout stateid after receiving + * NFS4ERR_OLD_STATEID */ -bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst, +bool nfs4_layout_refresh_old_stateid(nfs4_stateid *dst, struct pnfs_layout_range *dst_range, struct inode *inode) { @@ -377,7 +378,15 @@ bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst, spin_lock(&inode->i_lock); lo = NFS_I(inode)->layout; - if (lo && nfs4_stateid_match_other(dst, &lo->plh_stateid)) { + if (lo && pnfs_layout_is_valid(lo) && + nfs4_stateid_match_other(dst, &lo->plh_stateid)) { + /* Is our call using the most recent seqid? If so, bump it */ + if (!nfs4_stateid_is_newer(&lo->plh_stateid, dst)) { + nfs4_stateid_seqid_inc(dst); + ret = true; + goto out; + } + /* Try to update the seqid to the most recent */ err = pnfs_mark_matching_lsegs_return(lo, &head, &range, 0); if (err != -EBUSY) { dst->seqid = lo->plh_stateid.seqid; @@ -385,6 +394,7 @@ bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst, ret = true; } } +out: spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&head); return ret; @@ -1440,6 +1450,52 @@ out_noroc: return false; } +int pnfs_roc_done(struct rpc_task *task, struct inode *inode, + struct nfs4_layoutreturn_args **argpp, + struct nfs4_layoutreturn_res **respp, + int *ret) +{ + struct nfs4_layoutreturn_args *arg = *argpp; + int retval = -EAGAIN; + + if (!arg) + return 0; + /* Handle Layoutreturn errors */ + switch (*ret) { + case 0: + retval = 0; + break; + case -NFS4ERR_NOMATCHING_LAYOUT: + /* Was there an RPC level error? If not, retry */ + if (task->tk_rpc_status == 0) + break; + /* If the call was not sent, let caller handle it */ + if (!RPC_WAS_SENT(task)) + return 0; + /* + * Otherwise, assume the call succeeded and + * that we need to release the layout + */ + *ret = 0; + (*respp)->lrs_present = 0; + retval = 0; + break; + case -NFS4ERR_DELAY: + /* Let the caller handle the retry */ + *ret = -NFS4ERR_NOMATCHING_LAYOUT; + return 0; + case -NFS4ERR_OLD_STATEID: + if (!nfs4_layout_refresh_old_stateid(&arg->stateid, + &arg->range, inode)) + break; + *ret = -NFS4ERR_NOMATCHING_LAYOUT; + return -EAGAIN; + } + *argpp = NULL; + *respp = NULL; + return retval; +} + void pnfs_roc_release(struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, int ret) @@ -1449,10 +1505,15 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args, const nfs4_stateid *res_stateid = NULL; struct nfs4_xdr_opaque_data *ld_private = args->ld_private; - if (ret == 0) { - arg_stateid = &args->stateid; + switch (ret) { + case -NFS4ERR_NOMATCHING_LAYOUT: + break; + case 0: if (res->lrs_present) res_stateid = &res->stateid; + /* Fallthrough */ + default: + arg_stateid = &args->stateid; } pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range, res_stateid); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index f15609c003d8..f8a38065c7e4 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -261,7 +261,7 @@ int pnfs_destroy_layouts_byfsid(struct nfs_client *clp, bool is_recall); int pnfs_destroy_layouts_byclid(struct nfs_client *clp, bool is_recall); -bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst, +bool nfs4_layout_refresh_old_stateid(nfs4_stateid *dst, struct pnfs_layout_range *dst_range, struct inode *inode); void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo); @@ -282,6 +282,10 @@ bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, const struct cred *cred); +int pnfs_roc_done(struct rpc_task *task, struct inode *inode, + struct nfs4_layoutreturn_args **argpp, + struct nfs4_layoutreturn_res **respp, + int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, int ret); @@ -701,6 +705,15 @@ pnfs_roc(struct inode *ino, return false; } +static inline int +pnfs_roc_done(struct rpc_task *task, struct inode *inode, + struct nfs4_layoutreturn_args **argpp, + struct nfs4_layoutreturn_res **respp, + int *ret) +{ + return 0; +} + static inline void pnfs_roc_release(struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, @@ -785,7 +798,7 @@ static inline void nfs4_pnfs_v3_ds_connect_unload(void) { } -static inline bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst, +static inline bool nfs4_layout_refresh_old_stateid(nfs4_stateid *dst, struct pnfs_layout_range *dst_range, struct inode *inode) { diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 19a76cfa8b1f..a84df7d63403 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2645,6 +2645,13 @@ int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, } EXPORT_SYMBOL_GPL(nfs_clone_sb_security); +static void nfs_set_readahead(struct backing_dev_info *bdi, + unsigned long iomax_pages) +{ + bdi->ra_pages = VM_READAHEAD_PAGES; + bdi->io_pages = iomax_pages; +} + struct dentry *nfs_fs_mount_common(struct nfs_server *server, int flags, const char *dev_name, struct nfs_mount_info *mount_info, @@ -2687,7 +2694,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, mntroot = ERR_PTR(error); goto error_splat_super; } - s->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD; + nfs_set_readahead(s->s_bdi, server->rpages); server->super = s; } diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 20c841a906f2..3aac5c917afe 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -71,7 +71,7 @@ static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni) } /* Read, map, and pin the page. */ page = ntfs_map_page(mft_vi->i_mapping, index); - if (likely(!IS_ERR(page))) { + if (!IS_ERR(page)) { /* Catch multi sector transfer fixup errors. */ if (likely(ntfs_is_mft_recordp((le32*)(page_address(page) + ofs)))) { @@ -154,7 +154,7 @@ MFT_RECORD *map_mft_record(ntfs_inode *ni) mutex_lock(&ni->mrec_lock); m = map_mft_record_page(ni); - if (likely(!IS_ERR(m))) + if (!IS_ERR(m)) return m; mutex_unlock(&ni->mrec_lock); @@ -271,7 +271,7 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref, m = map_mft_record(ni); /* map_mft_record() has incremented this on success. */ atomic_dec(&ni->count); - if (likely(!IS_ERR(m))) { + if (!IS_ERR(m)) { /* Verify the sequence number. */ if (likely(le16_to_cpu(m->sequence_number) == seq_no)) { ntfs_debug("Done 1."); @@ -1303,7 +1303,7 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol) read_unlock_irqrestore(&mftbmp_ni->size_lock, flags); rl = ntfs_attr_find_vcn_nolock(mftbmp_ni, (ll - 1) >> vol->cluster_size_bits, NULL); - if (unlikely(IS_ERR(rl) || !rl->length || rl->lcn < 0)) { + if (IS_ERR(rl) || unlikely(!rl->length || rl->lcn < 0)) { up_write(&mftbmp_ni->runlist.lock); ntfs_error(vol->sb, "Failed to determine last allocated " "cluster of mft bitmap attribute."); @@ -1734,7 +1734,7 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol) read_unlock_irqrestore(&mft_ni->size_lock, flags); rl = ntfs_attr_find_vcn_nolock(mft_ni, (ll - 1) >> vol->cluster_size_bits, NULL); - if (unlikely(IS_ERR(rl) || !rl->length || rl->lcn < 0)) { + if (IS_ERR(rl) || unlikely(!rl->length || rl->lcn < 0)) { up_write(&mft_ni->runlist.lock); ntfs_error(vol->sb, "Failed to determine last allocated " "cluster of mft data attribute."); @@ -1776,7 +1776,7 @@ static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol) do { rl2 = ntfs_cluster_alloc(vol, old_last_vcn, nr, lcn, MFT_ZONE, true); - if (likely(!IS_ERR(rl2))) + if (!IS_ERR(rl2)) break; if (PTR_ERR(rl2) != -ENOSPC || nr == min_nr) { ntfs_error(vol->sb, "Failed to allocate the minimal " diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 2d3cc9e3395d..4e6a44bc654c 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -115,7 +115,7 @@ static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent, dent_ino = MREF(mref); ntfs_debug("Found inode 0x%lx. Calling ntfs_iget.", dent_ino); dent_inode = ntfs_iget(vol->sb, dent_ino); - if (likely(!IS_ERR(dent_inode))) { + if (!IS_ERR(dent_inode)) { /* Consistency check. */ if (is_bad_inode(dent_inode) || MSEQNO(mref) == NTFS_I(dent_inode)->seq_no || diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index 508744a93180..97932fb5179c 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -951,7 +951,7 @@ mpa_err: } /* Now combine the new and old runlists checking for overlaps. */ old_rl = ntfs_runlists_merge(old_rl, rl); - if (likely(!IS_ERR(old_rl))) + if (!IS_ERR(old_rl)) return old_rl; ntfs_free(rl); ntfs_error(vol->sb, "Failed to merge runlists."); diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 29621d40f448..7dc3bc604f78 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -1475,7 +1475,7 @@ not_enabled: kfree(name); /* Get the inode. */ tmp_ino = ntfs_iget(vol->sb, MREF(mref)); - if (unlikely(IS_ERR(tmp_ino) || is_bad_inode(tmp_ino))) { + if (IS_ERR(tmp_ino) || unlikely(is_bad_inode(tmp_ino))) { if (!IS_ERR(tmp_ino)) iput(tmp_ino); ntfs_error(vol->sb, "Failed to load $UsnJrnl."); diff --git a/fs/open.c b/fs/open.c index c60cd22cc052..b62f5c0923a8 100644 --- a/fs/open.c +++ b/fs/open.c @@ -776,7 +776,7 @@ static int do_dentry_open(struct file *f, f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop); - if (unlikely(WARN_ON(!f->f_op))) { + if (WARN_ON(!f->f_op)) { error = -ENODEV; goto cleanup_all; } diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c index 9c02d96d3a42..4075e41408b4 100644 --- a/fs/reiserfs/do_balan.c +++ b/fs/reiserfs/do_balan.c @@ -239,10 +239,8 @@ static int balance_leaf_when_delete_left(struct tree_balance *tb) static int balance_leaf_when_delete(struct tree_balance *tb, int flag) { struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path); - int item_pos = PATH_LAST_POSITION(tb->tb_path); struct buffer_info bi; int n; - struct item_head *ih; RFALSE(tb->FR[0] && B_LEVEL(tb->FR[0]) != DISK_LEAF_NODE_LEVEL + 1, "vs- 12000: level: wrong FR %z", tb->FR[0]); @@ -251,7 +249,6 @@ static int balance_leaf_when_delete(struct tree_balance *tb, int flag) RFALSE(!tb->blknum[0] && !PATH_H_PPARENT(tb->tb_path, 0), "PAP-12010: tree can not be empty"); - ih = item_head(tbS0, item_pos); buffer_info_init_tbS0(tb, &bi); /* Delete or truncate the item */ @@ -298,7 +295,6 @@ static unsigned int balance_leaf_insert_left(struct tree_balance *tb, if (tb->item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) { /* part of new item falls into L[0] */ int new_item_len, shift; - int version; ret = leaf_shift_left(tb, tb->lnum[0] - 1, -1); @@ -317,8 +313,6 @@ static unsigned int balance_leaf_insert_left(struct tree_balance *tb, leaf_insert_into_buf(&bi, n + tb->item_pos - ret, ih, body, min_t(int, tb->zeroes_num, ih_item_len(ih))); - version = ih_version(ih); - /* * Calculate key component, item length and body to * insert into S[0] @@ -632,7 +626,6 @@ static void balance_leaf_insert_right(struct tree_balance *tb, struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path); int n = B_NR_ITEMS(tbS0); struct buffer_info bi; - int ret; /* new item or part of it doesn't fall into R[0] */ if (n - tb->rnum[0] >= tb->item_pos) { @@ -646,13 +639,11 @@ static void balance_leaf_insert_right(struct tree_balance *tb, if (tb->item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1) { loff_t old_key_comp, old_len, r_zeroes_number; const char *r_body; - int version, shift; + int shift; loff_t offset; leaf_shift_right(tb, tb->rnum[0] - 1, -1); - version = ih_version(ih); - /* Remember key component and item length */ old_key_comp = le_ih_k_offset(ih); old_len = ih_item_len(ih); @@ -698,7 +689,7 @@ static void balance_leaf_insert_right(struct tree_balance *tb, /* whole new item falls into R[0] */ /* Shift rnum[0]-1 items to R[0] */ - ret = leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes); + leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes); /* Insert new item into R[0] */ buffer_info_init_right(tb, &bi); @@ -950,14 +941,12 @@ static void balance_leaf_new_nodes_insert(struct tree_balance *tb, if (tb->item_pos == n - tb->snum[i] + 1 && tb->sbytes[i] != -1) { int old_key_comp, old_len, r_zeroes_number; const char *r_body; - int version; /* Move snum[i]-1 items from S[0] to S_new[i] */ leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, tb->snum[i] - 1, -1, tb->S_new[i]); /* Remember key component and item length */ - version = ih_version(ih); old_key_comp = le_ih_k_offset(ih); old_len = ih_item_len(ih); diff --git a/fs/reiserfs/fix_node.c b/fs/reiserfs/fix_node.c index 6b0ddb2a9091..117092224111 100644 --- a/fs/reiserfs/fix_node.c +++ b/fs/reiserfs/fix_node.c @@ -376,7 +376,6 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h, int to, int to_bytes, short *snum012, int flow) { int i; - int cur_free; int units; struct virtual_node *vn = tb->tb_vn; int total_node_size, max_node_size, current_item_size; @@ -438,7 +437,6 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h, /* leaf level */ needed_nodes = 1; total_node_size = 0; - cur_free = max_node_size; /* start from 'from'-th item */ start_item = from; @@ -1734,14 +1732,12 @@ static int dc_check_balance_internal(struct tree_balance *tb, int h) * and Fh is its father. */ struct buffer_head *Sh, *Fh; - int maxsize, ret; + int ret; int lfree, rfree /* free space in L and R */ ; Sh = PATH_H_PBUFFER(tb->tb_path, h); Fh = PATH_H_PPARENT(tb->tb_path, h); - maxsize = MAX_CHILD_SIZE(Sh); - /* * using tb->insert_size[h], which is negative in this case, * create_virtual_node calculates: diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 4517a1394c6f..4b3e3e73b512 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -891,7 +891,6 @@ static int flush_older_commits(struct super_block *s, struct list_head *entry; unsigned int trans_id = jl->j_trans_id; unsigned int other_trans_id; - unsigned int first_trans_id; find_first: /* @@ -914,8 +913,6 @@ find_first: return 0; } - first_trans_id = first_jl->j_trans_id; - entry = &first_jl->j_list; while (1) { other_jl = JOURNAL_LIST_ENTRY(entry); @@ -1351,7 +1348,7 @@ static int flush_journal_list(struct super_block *s, struct reiserfs_journal_list *jl, int flushall) { struct reiserfs_journal_list *pjl; - struct reiserfs_journal_cnode *cn, *last; + struct reiserfs_journal_cnode *cn; int count; int was_jwait = 0; int was_dirty = 0; @@ -1509,7 +1506,6 @@ static int flush_journal_list(struct super_block *s, b_blocknr, __func__); } free_cnode: - last = cn; cn = cn->next; if (saved_bh) { /* @@ -1792,7 +1788,6 @@ static int flush_used_journal_lists(struct super_block *s, { unsigned long len = 0; unsigned long cur_len; - int ret; int i; int limit = 256; struct reiserfs_journal_list *tjl; @@ -1829,9 +1824,9 @@ static int flush_used_journal_lists(struct super_block *s, * transactions, but only bother if we've actually spanned * across multiple lists */ - if (flush_jl != jl) { - ret = kupdate_transactions(s, jl, &tjl, &trans_id, len, i); - } + if (flush_jl != jl) + kupdate_transactions(s, jl, &tjl, &trans_id, len, i); + flush_journal_list(s, flush_jl, 1); put_journal_list(s, flush_jl); put_journal_list(s, jl); @@ -1911,7 +1906,6 @@ static int do_journal_release(struct reiserfs_transaction_handle *th, struct super_block *sb, int error) { struct reiserfs_transaction_handle myth; - int flushed = 0; struct reiserfs_journal *journal = SB_JOURNAL(sb); /* @@ -1933,7 +1927,6 @@ static int do_journal_release(struct reiserfs_transaction_handle *th, 1); journal_mark_dirty(&myth, SB_BUFFER_WITH_SB(sb)); do_journal_end(&myth, FLUSH_ALL); - flushed = 1; } } @@ -3444,9 +3437,8 @@ static int remove_from_transaction(struct super_block *sb, if (cn == journal->j_last) { journal->j_last = cn->prev; } - if (bh) - remove_journal_hash(sb, journal->j_hash_table, NULL, - bh->b_blocknr, 0); + remove_journal_hash(sb, journal->j_hash_table, NULL, + bh->b_blocknr, 0); clear_buffer_journaled(bh); /* don't log this one */ if (!already_cleaned) { @@ -3988,7 +3980,6 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, int flags) struct buffer_head *c_bh; /* commit bh */ struct buffer_head *d_bh; /* desc bh */ int cur_write_start = 0; /* start index of current log write */ - int old_start; int i; int flush; int wait_on_commit; @@ -4245,7 +4236,6 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, int flags) journal->j_num_work_lists++; /* reset journal values for the next transaction */ - old_start = journal->j_start; journal->j_start = (journal->j_start + journal->j_len + 2) % SB_ONDISK_JOURNAL_SIZE(sb); diff --git a/fs/reiserfs/lbalance.c b/fs/reiserfs/lbalance.c index f5cebd70d903..7f868569d4d0 100644 --- a/fs/reiserfs/lbalance.c +++ b/fs/reiserfs/lbalance.c @@ -1322,7 +1322,7 @@ void leaf_paste_entries(struct buffer_info *bi, char *item; struct reiserfs_de_head *deh; char *insert_point; - int i, old_entry_num; + int i; struct buffer_head *bh = bi->bi_bh; if (new_entry_count == 0) @@ -1362,7 +1362,6 @@ void leaf_paste_entries(struct buffer_info *bi, put_deh_location(&deh[i], deh_location(&deh[i]) + paste_size); - old_entry_num = ih_entry_count(ih); put_ih_entry_count(ih, ih_entry_count(ih) + new_entry_count); /* prepare space for pasted records */ diff --git a/fs/reiserfs/objectid.c b/fs/reiserfs/objectid.c index 415d66ca87d1..34baf5c0f265 100644 --- a/fs/reiserfs/objectid.c +++ b/fs/reiserfs/objectid.c @@ -183,13 +183,12 @@ int reiserfs_convert_objectid_map_v1(struct super_block *s) int new_size = (s->s_blocksize - SB_SIZE) / sizeof(__u32) / 2 * 2; int old_max = sb_oid_maxsize(disk_sb); struct reiserfs_super_block_v1 *disk_sb_v1; - __le32 *objectid_map, *new_objectid_map; + __le32 *objectid_map; int i; disk_sb_v1 = (struct reiserfs_super_block_v1 *)(SB_BUFFER_WITH_SB(s)->b_data); objectid_map = (__le32 *) (disk_sb_v1 + 1); - new_objectid_map = (__le32 *) (disk_sb + 1); if (cur_size > new_size) { /* diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 9fed1c05f1f4..500f2000eb41 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -746,9 +746,6 @@ static void check_leaf_block_head(struct buffer_head *bh) static void check_internal_block_head(struct buffer_head *bh) { - struct block_head *blkh; - - blkh = B_BLK_HEAD(bh); if (!(B_LEVEL(bh) > DISK_LEAF_NODE_LEVEL && B_LEVEL(bh) <= MAX_HEIGHT)) reiserfs_panic(NULL, "vs-6025", "invalid level %z", bh); diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 0037aea97d39..da9ebe33882b 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -593,7 +593,6 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key, struct buffer_head *bh; struct path_element *last_element; int node_level, retval; - int right_neighbor_of_leaf_node; int fs_gen; struct buffer_head *reada_bh[SEARCH_BY_KEY_READA]; b_blocknr_t reada_blocks[SEARCH_BY_KEY_READA]; @@ -614,8 +613,6 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key, pathrelse(search_path); - right_neighbor_of_leaf_node = 0; - /* * With each iteration of this loop we search through the items in the * current node, and calculate the next current node(next path element) @@ -701,7 +698,6 @@ io_error: */ block_number = SB_ROOT_BLOCK(sb); expected_level = -1; - right_neighbor_of_leaf_node = 0; /* repeat search from the root */ continue; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index fe6d804a38dc..f9fd18670e22 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1272,21 +1272,23 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, } static __always_inline int validate_range(struct mm_struct *mm, - __u64 start, __u64 len) + __u64 *start, __u64 len) { __u64 task_size = mm->task_size; - if (start & ~PAGE_MASK) + *start = untagged_addr(*start); + + if (*start & ~PAGE_MASK) return -EINVAL; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; - if (start < mmap_min_addr) + if (*start < mmap_min_addr) return -EINVAL; - if (start >= task_size) + if (*start >= task_size) return -EINVAL; - if (len > task_size - start) + if (len > task_size - *start) return -EINVAL; return 0; } @@ -1336,7 +1338,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; } - ret = validate_range(mm, uffdio_register.range.start, + ret = validate_range(mm, &uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; @@ -1525,7 +1527,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; - ret = validate_range(mm, uffdio_unregister.start, + ret = validate_range(mm, &uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; @@ -1676,7 +1678,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; - ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); + ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len); if (ret) goto out; @@ -1716,7 +1718,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, sizeof(uffdio_copy)-sizeof(__s64))) goto out; - ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); + ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; /* @@ -1772,7 +1774,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; - ret = validate_range(ctx->mm, uffdio_zeropage.range.start, + ret = validate_range(ctx->mm, &uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 58fa85cec325..d6ed5d2c07c2 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -81,9 +81,10 @@ typedef struct xfs_alloc_arg { /* * Defines for datatype */ -#define XFS_ALLOC_INITIAL_USER_DATA (1 << 0)/* special case start of file */ -#define XFS_ALLOC_USERDATA_ZERO (1 << 1)/* zero extent on allocation */ -#define XFS_ALLOC_NOBUSY (1 << 2)/* Busy extents not allowed */ +#define XFS_ALLOC_USERDATA (1 << 0)/* allocation is for user data*/ +#define XFS_ALLOC_INITIAL_USER_DATA (1 << 1)/* special case start of file */ +#define XFS_ALLOC_USERDATA_ZERO (1 << 2)/* zero extent on allocation */ +#define XFS_ALLOC_NOBUSY (1 << 3)/* Busy extents not allowed */ static inline bool xfs_alloc_is_userdata(int datatype) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 054b4ce30033..4edc25a2ba80 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4042,8 +4042,12 @@ xfs_bmapi_allocate( */ if (!(bma->flags & XFS_BMAPI_METADATA)) { bma->datatype = XFS_ALLOC_NOBUSY; - if (whichfork == XFS_DATA_FORK && bma->offset == 0) - bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA; + if (whichfork == XFS_DATA_FORK) { + if (bma->offset == 0) + bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA; + else + bma->datatype |= XFS_ALLOC_USERDATA; + } if (bma->flags & XFS_BMAPI_ZERO) bma->datatype |= XFS_ALLOC_USERDATA_ZERO; } @@ -5621,6 +5625,11 @@ xfs_bmse_merge( if (error) return error; + /* change to extent format if required after extent removal */ + error = xfs_bmap_btree_to_extents(tp, ip, cur, logflags, whichfork); + if (error) + return error; + done: xfs_iext_remove(ip, icur, 0); xfs_iext_prev(XFS_IFORK_PTR(ip, whichfork), icur); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index a08dd8f40346..ac6cdca63e15 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -928,7 +928,7 @@ xfs_log_sb( xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb); xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); - xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb)); + xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb) - 1); } /* diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index a43d1813c4ff..5533e48e605d 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -97,7 +97,6 @@ xchk_allocbt_rec( xfs_agnumber_t agno = bs->cur->bc_private.a.agno; xfs_agblock_t bno; xfs_extlen_t len; - int error = 0; bno = be32_to_cpu(rec->alloc.ar_startblock); len = be32_to_cpu(rec->alloc.ar_blockcount); @@ -109,7 +108,7 @@ xchk_allocbt_rec( xchk_allocbt_xref(bs->sc, bno, len); - return error; + return 0; } /* Scrub the freespace btrees for some AG. */ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 120ef99d09e8..21c243622a79 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -2097,7 +2097,7 @@ xfs_verify_magic( int idx; idx = xfs_sb_version_hascrc(&mp->m_sb); - if (unlikely(WARN_ON(!bp->b_ops || !bp->b_ops->magic[idx]))) + if (WARN_ON(!bp->b_ops || !bp->b_ops->magic[idx])) return false; return dmagic == bp->b_ops->magic[idx]; } @@ -2115,7 +2115,7 @@ xfs_verify_magic16( int idx; idx = xfs_sb_version_hascrc(&mp->m_sb); - if (unlikely(WARN_ON(!bp->b_ops || !bp->b_ops->magic16[idx]))) + if (WARN_ON(!bp->b_ops || !bp->b_ops->magic16[idx])) return false; return dmagic == bp->b_ops->magic16[idx]; } diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index ddd0bf7a4740..f1bc88f4367c 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -63,19 +63,6 @@ static const struct sysfs_ops xfs_sysfs_ops = { .store = xfs_sysfs_object_store, }; -/* - * xfs_mount kobject. The mp kobject also serves as the per-mount parent object - * that is identified by the fsname under sysfs. - */ - -static inline struct xfs_mount * -to_mp(struct kobject *kobject) -{ - struct xfs_kobj *kobj = to_kobj(kobject); - - return container_of(kobj, struct xfs_mount, m_kobj); -} - static struct attribute *xfs_mp_attrs[] = { NULL, }; diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 7357a3c942a0..384b5c835ced 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -10,6 +10,7 @@ #define BUGFLAG_WARNING (1 << 0) #define BUGFLAG_ONCE (1 << 1) #define BUGFLAG_DONE (1 << 2) +#define BUGFLAG_NO_CUT_HERE (1 << 3) /* CUT_HERE already sent */ #define BUGFLAG_TAINT(taint) ((taint) << 8) #define BUG_GET_TAINT(bug) ((bug)->flags >> 8) #endif @@ -61,18 +62,6 @@ struct bug_entry { #define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0) #endif -#ifdef __WARN_FLAGS -#define __WARN_TAINT(taint) __WARN_FLAGS(BUGFLAG_TAINT(taint)) -#define __WARN_ONCE_TAINT(taint) __WARN_FLAGS(BUGFLAG_ONCE|BUGFLAG_TAINT(taint)) - -#define WARN_ON_ONCE(condition) ({ \ - int __ret_warn_on = !!(condition); \ - if (unlikely(__ret_warn_on)) \ - __WARN_ONCE_TAINT(TAINT_WARN); \ - unlikely(__ret_warn_on); \ -}) -#endif - /* * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report * significant kernel issues that need prompt attention if they should ever @@ -89,27 +78,27 @@ struct bug_entry { * * Use the versions with printk format strings to provide better diagnostics. */ -#ifndef __WARN_TAINT -extern __printf(3, 4) -void warn_slowpath_fmt(const char *file, const int line, - const char *fmt, ...); +#ifndef __WARN_FLAGS extern __printf(4, 5) -void warn_slowpath_fmt_taint(const char *file, const int line, unsigned taint, - const char *fmt, ...); -extern void warn_slowpath_null(const char *file, const int line); -#define WANT_WARN_ON_SLOWPATH -#define __WARN() warn_slowpath_null(__FILE__, __LINE__) -#define __WARN_printf(arg...) warn_slowpath_fmt(__FILE__, __LINE__, arg) -#define __WARN_printf_taint(taint, arg...) \ - warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg) +void warn_slowpath_fmt(const char *file, const int line, unsigned taint, + const char *fmt, ...); +#define __WARN() __WARN_printf(TAINT_WARN, NULL) +#define __WARN_printf(taint, arg...) \ + warn_slowpath_fmt(__FILE__, __LINE__, taint, arg) #else extern __printf(1, 2) void __warn_printk(const char *fmt, ...); -#define __WARN() do { \ - printk(KERN_WARNING CUT_HERE); __WARN_TAINT(TAINT_WARN); \ -} while (0) -#define __WARN_printf(arg...) __WARN_printf_taint(TAINT_WARN, arg) -#define __WARN_printf_taint(taint, arg...) \ - do { __warn_printk(arg); __WARN_TAINT(taint); } while (0) +#define __WARN() __WARN_FLAGS(BUGFLAG_TAINT(TAINT_WARN)) +#define __WARN_printf(taint, arg...) do { \ + __warn_printk(arg); \ + __WARN_FLAGS(BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\ + } while (0) +#define WARN_ON_ONCE(condition) ({ \ + int __ret_warn_on = !!(condition); \ + if (unlikely(__ret_warn_on)) \ + __WARN_FLAGS(BUGFLAG_ONCE | \ + BUGFLAG_TAINT(TAINT_WARN)); \ + unlikely(__ret_warn_on); \ +}) #endif /* used internally by panic.c */ @@ -132,7 +121,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, #define WARN(condition, format...) ({ \ int __ret_warn_on = !!(condition); \ if (unlikely(__ret_warn_on)) \ - __WARN_printf(format); \ + __WARN_printf(TAINT_WARN, format); \ unlikely(__ret_warn_on); \ }) #endif @@ -140,7 +129,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, #define WARN_TAINT(condition, taint, format...) ({ \ int __ret_warn_on = !!(condition); \ if (unlikely(__ret_warn_on)) \ - __WARN_printf_taint(taint, format); \ + __WARN_printf(taint, format); \ unlikely(__ret_warn_on); \ }) diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 6f8cc06ee44e..73f7421413cb 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -49,7 +49,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * - * Allocates a page and runs the pgtable_page_ctor(). + * Allocates a page and runs the pgtable_pte_page_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. @@ -63,7 +63,7 @@ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) pte = alloc_page(gfp); if (!pte) return NULL; - if (!pgtable_page_ctor(pte)) { + if (!pgtable_pte_page_ctor(pte)) { __free_page(pte); return NULL; } @@ -76,7 +76,7 @@ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * - * Allocates a page and runs the pgtable_page_ctor(). + * Allocates a page and runs the pgtable_pte_page_ctor(). * * Return: `struct page` initialized as page table or %NULL on error */ @@ -98,7 +98,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { - pgtable_page_dtor(pte_page); + pgtable_pte_page_dtor(pte_page); __free_page(pte_page); } diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 7d14c11bdc0a..408b6f4e63c0 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -285,12 +285,12 @@ struct drm_crtc_state { u32 target_vblank; /** - * @pageflip_flags: + * @async_flip: * - * DRM_MODE_PAGE_FLIP_* flags, as passed to the page flip ioctl. - * Zero in any other case. + * This is set when DRM_MODE_PAGE_FLIP_ASYNC is set in the legacy + * PAGE_FLIP IOCTL. It's not wired up for the atomic IOCTL itself yet. */ - u32 pageflip_flags; + bool async_flip; /** * @vrr_enabled: @@ -1108,7 +1108,7 @@ struct drm_crtc { /** * @self_refresh_data: Holds the state for the self refresh helpers * - * Initialized via drm_self_refresh_helper_register(). + * Initialized via drm_self_refresh_helper_init(). */ struct drm_self_refresh_data *self_refresh_data; }; diff --git a/include/drm/drm_self_refresh_helper.h b/include/drm/drm_self_refresh_helper.h index 397a583ccca7..5b79d253fb46 100644 --- a/include/drm/drm_self_refresh_helper.h +++ b/include/drm/drm_self_refresh_helper.h @@ -12,9 +12,9 @@ struct drm_atomic_state; struct drm_crtc; void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state); +void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state, + unsigned int commit_time_ms); -int drm_self_refresh_helper_init(struct drm_crtc *crtc, - unsigned int entry_delay_ms); - +int drm_self_refresh_helper_init(struct drm_crtc *crtc); void drm_self_refresh_helper_cleanup(struct drm_crtc *crtc); #endif diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b5a5a1ed9efd..78a73eba64dd 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -200,8 +200,8 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node) for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_wrap(cpu, mask, start) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start)) -#define for_each_cpu_and(cpu, mask, and) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)and) +#define for_each_cpu_and(cpu, mask1, mask2) \ + for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask1, (void)mask2) #else /** * cpumask_first - get the first cpu in a cpumask @@ -290,20 +290,20 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator - * @mask: the first cpumask pointer - * @and: the second cpumask pointer + * @mask1: the first cpumask pointer + * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; - * cpumask_and(&tmp, &mask, &and); + * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ -#define for_each_cpu_and(cpu, mask, and) \ +#define for_each_cpu_and(cpu, mask1, mask2) \ for ((cpu) = -1; \ - (cpu) = cpumask_next_and((cpu), (mask), (and)), \ + (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \ (cpu) < nr_cpu_ids;) #endif /* SMP */ diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h index 855476145fe1..aaa8a0767aa3 100644 --- a/include/linux/interval_tree_generic.h +++ b/include/linux/interval_tree_generic.h @@ -30,26 +30,8 @@ \ /* Callbacks for augmented rbtree insert and remove */ \ \ -static inline ITTYPE ITPREFIX ## _compute_subtree_last(ITSTRUCT *node) \ -{ \ - ITTYPE max = ITLAST(node), subtree_last; \ - if (node->ITRB.rb_left) { \ - subtree_last = rb_entry(node->ITRB.rb_left, \ - ITSTRUCT, ITRB)->ITSUBTREE; \ - if (max < subtree_last) \ - max = subtree_last; \ - } \ - if (node->ITRB.rb_right) { \ - subtree_last = rb_entry(node->ITRB.rb_right, \ - ITSTRUCT, ITRB)->ITSUBTREE; \ - if (max < subtree_last) \ - max = subtree_last; \ - } \ - return max; \ -} \ - \ -RB_DECLARE_CALLBACKS(static, ITPREFIX ## _augment, ITSTRUCT, ITRB, \ - ITTYPE, ITSUBTREE, ITPREFIX ## _compute_subtree_last) \ +RB_DECLARE_CALLBACKS_MAX(static, ITPREFIX ## _augment, \ + ITSTRUCT, ITRB, ITTYPE, ITSUBTREE, ITLAST) \ \ /* Insert / remove interval nodes from the tree */ \ \ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index f0b809258ed3..cc162f3e6461 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -183,6 +183,8 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, bool get_value); void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); +int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len); void * __weak arch_kexec_kernel_image_load(struct kimage *image); int __weak arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index fbf144aaa749..b072aeb1fd78 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -326,8 +326,10 @@ extern atomic_t kgdb_active; (raw_smp_processor_id() == atomic_read(&kgdb_active)) extern bool dbg_is_early; extern void __init dbg_late_init(void); +extern void kgdb_panic(const char *msg); #else /* ! CONFIG_KGDB */ #define in_dbg_master() (0) #define dbg_late_init() +static inline void kgdb_panic(const char *msg) {} #endif /* ! CONFIG_KGDB */ #endif /* _KGDB_H_ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 294a67b94147..cc292273e6ba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1949,7 +1949,7 @@ static inline void pgtable_init(void) pgtable_cache_init(); } -static inline bool pgtable_page_ctor(struct page *page) +static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) return false; @@ -1958,7 +1958,7 @@ static inline bool pgtable_page_ctor(struct page *page) return true; } -static inline void pgtable_page_dtor(struct page *page) +static inline void pgtable_pte_page_dtor(struct page *page) { ptlock_free(page); __ClearPageTable(page); diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index d7016dcb245e..c1bc6731125c 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -36,6 +36,10 @@ struct vmacache { struct vm_area_struct *vmas[VMACACHE_SIZE]; }; +/* + * When updating this, please also update struct resident_page_types[] in + * kernel/fork.c + */ enum { MM_FILEPAGES, /* Resident file mapping pages */ MM_ANONPAGES, /* Resident anonymous pages */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 0a11712a80e3..570a60c2f4f4 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -490,6 +490,9 @@ extern const struct file_operations nfs_dir_operations; extern const struct dentry_operations nfs_dentry_operations; extern void nfs_force_lookup_revalidate(struct inode *dir); +extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr, + struct nfs4_label *label); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); diff --git a/include/linux/printk.h b/include/linux/printk.h index cefd374c47b1..c09d67edda3a 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -488,13 +488,6 @@ extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, extern void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); -#if defined(CONFIG_DYNAMIC_DEBUG) -#define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \ - dynamic_hex_dump(prefix_str, prefix_type, 16, 1, buf, len, true) -#else -extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, - const void *buf, size_t len); -#endif /* defined(CONFIG_DYNAMIC_DEBUG) */ #else static inline void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, @@ -526,4 +519,19 @@ static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type, } #endif +/** + * print_hex_dump_bytes - shorthand form of print_hex_dump() with default params + * @prefix_str: string to prefix each line with; + * caller supplies trailing spaces for alignment if desired + * @prefix_type: controls whether prefix of an offset, address, or none + * is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE) + * @buf: data blob to dump + * @len: number of bytes in the @buf + * + * Calls print_hex_dump(), with log level of KERN_DEBUG, + * rowsize of 16, groupsize of 1, and ASCII output included. + */ +#define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \ + print_hex_dump_debug(prefix_str, prefix_type, 16, 1, buf, len, true) + #endif diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 179faab29f52..fdd421b8d9ae 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -60,41 +60,87 @@ rb_insert_augmented_cached(struct rb_node *node, rb_insert_augmented(node, &root->rb_root, augment); } -#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield, \ - rbtype, rbaugmented, rbcompute) \ +/* + * Template for declaring augmented rbtree callbacks (generic case) + * + * RBSTATIC: 'static' or empty + * RBNAME: name of the rb_augment_callbacks structure + * RBSTRUCT: struct type of the tree nodes + * RBFIELD: name of struct rb_node field within RBSTRUCT + * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree + * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data + */ + +#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ -rbname ## _propagate(struct rb_node *rb, struct rb_node *stop) \ +RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ - rbstruct *node = rb_entry(rb, rbstruct, rbfield); \ - rbtype augmented = rbcompute(node); \ - if (node->rbaugmented == augmented) \ + RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ + if (RBCOMPUTE(node, true)) \ break; \ - node->rbaugmented = augmented; \ - rb = rb_parent(&node->rbfield); \ + rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ -rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ +RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ - rbstruct *old = rb_entry(rb_old, rbstruct, rbfield); \ - rbstruct *new = rb_entry(rb_new, rbstruct, rbfield); \ - new->rbaugmented = old->rbaugmented; \ + RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ + RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ + new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ -rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ +RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ - rbstruct *old = rb_entry(rb_old, rbstruct, rbfield); \ - rbstruct *new = rb_entry(rb_new, rbstruct, rbfield); \ - new->rbaugmented = old->rbaugmented; \ - old->rbaugmented = rbcompute(old); \ + RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ + RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ + new->RBAUGMENTED = old->RBAUGMENTED; \ + RBCOMPUTE(old, false); \ } \ -rbstatic const struct rb_augment_callbacks rbname = { \ - .propagate = rbname ## _propagate, \ - .copy = rbname ## _copy, \ - .rotate = rbname ## _rotate \ +RBSTATIC const struct rb_augment_callbacks RBNAME = { \ + .propagate = RBNAME ## _propagate, \ + .copy = RBNAME ## _copy, \ + .rotate = RBNAME ## _rotate \ }; +/* + * Template for declaring augmented rbtree callbacks, + * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. + * + * RBSTATIC: 'static' or empty + * RBNAME: name of the rb_augment_callbacks structure + * RBSTRUCT: struct type of the tree nodes + * RBFIELD: name of struct rb_node field within RBSTRUCT + * RBTYPE: type of the RBAUGMENTED field + * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree + * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar + */ + +#define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ + RBTYPE, RBAUGMENTED, RBCOMPUTE) \ +static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ +{ \ + RBSTRUCT *child; \ + RBTYPE max = RBCOMPUTE(node); \ + if (node->RBFIELD.rb_left) { \ + child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ + if (child->RBAUGMENTED > max) \ + max = child->RBAUGMENTED; \ + } \ + if (node->RBFIELD.rb_right) { \ + child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ + if (child->RBAUGMENTED > max) \ + max = child->RBAUGMENTED; \ + } \ + if (exit && node->RBAUGMENTED == max) \ + return true; \ + node->RBAUGMENTED = max; \ + return false; \ +} \ +RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) + #define RB_RED 0 #define RB_BLACK 1 diff --git a/include/linux/string.h b/include/linux/string.h index 4deb11f7976b..b2f9df7f0761 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -474,8 +474,9 @@ static inline void memcpy_and_pad(void *dest, size_t dest_len, * But this can lead to bugs due to typos, or if prefix is a pointer * and not a constant. Instead use str_has_prefix(). * - * Returns: 0 if @str does not start with @prefix - strlen(@prefix) if @str does start with @prefix + * Returns: + * * strlen(@prefix) if @str starts with @prefix + * * 0 if @str does not start with @prefix */ static __always_inline size_t str_has_prefix(const char *str, const char *prefix) { diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 27536b961552..a6ef35184ef1 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -242,9 +242,6 @@ void rpc_sleep_on_priority_timeout(struct rpc_wait_queue *queue, void rpc_sleep_on_priority(struct rpc_wait_queue *, struct rpc_task *, int priority); -void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq, - struct rpc_wait_queue *queue, - struct rpc_task *task); void rpc_wake_up_queued_task(struct rpc_wait_queue *, struct rpc_task *); void rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *, diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 8a87d8bcb197..f33e5013bdfb 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -186,7 +186,7 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p) extern void xdr_shift_buf(struct xdr_buf *, size_t); extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *); extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); -extern int xdr_buf_read_netobj(struct xdr_buf *, struct xdr_netobj *, unsigned int); +extern int xdr_buf_read_mic(struct xdr_buf *, struct xdr_netobj *, unsigned int); extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 13e108bcc9eb..d783e15ba898 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -352,6 +352,7 @@ bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); +void xprt_request_dequeue_xprt(struct rpc_task *task); bool xprt_request_need_retransmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h index 86fc38ff0355..16c239e0d6dd 100644 --- a/include/linux/sunrpc/xprtrdma.h +++ b/include/linux/sunrpc/xprtrdma.h @@ -49,9 +49,9 @@ * fully-chunked NFS message (read chunks are the largest). Note only * a single chunk type per message is supported currently. */ -#define RPCRDMA_MIN_SLOT_TABLE (2U) +#define RPCRDMA_MIN_SLOT_TABLE (4U) #define RPCRDMA_DEF_SLOT_TABLE (128U) -#define RPCRDMA_MAX_SLOT_TABLE (256U) +#define RPCRDMA_MAX_SLOT_TABLE (16384U) #define RPCRDMA_MIN_INLINE (1024) /* min inline thresh */ #define RPCRDMA_DEF_INLINE (4096) /* default inline thresh */ diff --git a/include/linux/swap.h b/include/linux/swap.h index de2c67a33b7e..063c0c1e112b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -340,6 +340,7 @@ extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); +extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); @@ -364,6 +365,7 @@ extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); extern unsigned long vm_total_pages; +extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 8d8821b3689a..659a4400517b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -134,7 +134,7 @@ static inline void copy_overflow(int size, unsigned long count) WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } -static __always_inline bool +static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __compiletime_object_size(addr); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 34a038563d97..70bbdc38dc37 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -55,7 +55,7 @@ * as usual) and both source and destination can trigger faults. */ -static __always_inline unsigned long +static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); @@ -63,7 +63,7 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) return raw_copy_from_user(to, from, n); } -static __always_inline unsigned long +static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); @@ -85,7 +85,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ -static __always_inline unsigned long +static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); @@ -93,7 +93,7 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) return raw_copy_to_user(to, from, n); } -static __always_inline unsigned long +static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); @@ -103,7 +103,7 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) } #ifdef INLINE_COPY_FROM_USER -static inline unsigned long +static inline __must_check unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; @@ -117,12 +117,12 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return res; } #else -extern unsigned long +extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); #endif #ifdef INLINE_COPY_TO_USER -static inline unsigned long +static inline __must_check unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); @@ -133,7 +133,7 @@ _copy_to_user(void __user *to, const void *from, unsigned long n) return n; } #else -extern unsigned long +extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif @@ -222,8 +222,9 @@ static inline bool pagefault_disabled(void) #ifndef ARCH_HAS_NOCACHE_UACCESS -static inline unsigned long __copy_from_user_inatomic_nocache(void *to, - const void __user *from, unsigned long n) +static inline __must_check unsigned long +__copy_from_user_inatomic_nocache(void *to, const void __user *from, + unsigned long n) { return __copy_from_user_inatomic(to, from, n); } diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index f6a4eaa85a3e..a13830616107 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -451,20 +451,81 @@ TRACE_EVENT(xprtrdma_createmrs, TP_STRUCT__entry( __field(const void *, r_xprt) + __string(addr, rpcrdma_addrstr(r_xprt)) + __string(port, rpcrdma_portstr(r_xprt)) __field(unsigned int, count) ), TP_fast_assign( __entry->r_xprt = r_xprt; __entry->count = count; + __assign_str(addr, rpcrdma_addrstr(r_xprt)); + __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("r_xprt=%p: created %u MRs", - __entry->r_xprt, __entry->count + TP_printk("peer=[%s]:%s r_xprt=%p: created %u MRs", + __get_str(addr), __get_str(port), __entry->r_xprt, + __entry->count ) ); -DEFINE_RXPRT_EVENT(xprtrdma_nomrs); +TRACE_EVENT(xprtrdma_mr_get, + TP_PROTO( + const struct rpcrdma_req *req + ), + + TP_ARGS(req), + + TP_STRUCT__entry( + __field(const void *, req) + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(u32, xid) + ), + + TP_fast_assign( + const struct rpc_rqst *rqst = &req->rl_slot; + + __entry->req = req; + __entry->task_id = rqst->rq_task->tk_pid; + __entry->client_id = rqst->rq_task->tk_client->cl_clid; + __entry->xid = be32_to_cpu(rqst->rq_xid); + ), + + TP_printk("task:%u@%u xid=0x%08x req=%p", + __entry->task_id, __entry->client_id, __entry->xid, + __entry->req + ) +); + +TRACE_EVENT(xprtrdma_nomrs, + TP_PROTO( + const struct rpcrdma_req *req + ), + + TP_ARGS(req), + + TP_STRUCT__entry( + __field(const void *, req) + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(u32, xid) + ), + + TP_fast_assign( + const struct rpc_rqst *rqst = &req->rl_slot; + + __entry->req = req; + __entry->task_id = rqst->rq_task->tk_pid; + __entry->client_id = rqst->rq_task->tk_client->cl_clid; + __entry->xid = be32_to_cpu(rqst->rq_xid); + ), + + TP_printk("task:%u@%u xid=0x%08x req=%p", + __entry->task_id, __entry->client_id, __entry->xid, + __entry->req + ) +); DEFINE_RDCH_EVENT(read); DEFINE_WRCH_EVENT(write); @@ -623,21 +684,21 @@ TRACE_EVENT(xprtrdma_post_send, TRACE_EVENT(xprtrdma_post_recv, TP_PROTO( - const struct ib_cqe *cqe + const struct rpcrdma_rep *rep ), - TP_ARGS(cqe), + TP_ARGS(rep), TP_STRUCT__entry( - __field(const void *, cqe) + __field(const void *, rep) ), TP_fast_assign( - __entry->cqe = cqe; + __entry->rep = rep; ), - TP_printk("cqe=%p", - __entry->cqe + TP_printk("rep=%p", + __entry->rep ) ); @@ -715,14 +776,15 @@ TRACE_EVENT(xprtrdma_wc_receive, TP_ARGS(wc), TP_STRUCT__entry( - __field(const void *, cqe) + __field(const void *, rep) __field(u32, byte_len) __field(unsigned int, status) __field(u32, vendor_err) ), TP_fast_assign( - __entry->cqe = wc->wr_cqe; + __entry->rep = container_of(wc->wr_cqe, struct rpcrdma_rep, + rr_cqe); __entry->status = wc->status; if (wc->status) { __entry->byte_len = 0; @@ -733,8 +795,8 @@ TRACE_EVENT(xprtrdma_wc_receive, } ), - TP_printk("cqe=%p %u bytes: %s (%u/0x%x)", - __entry->cqe, __entry->byte_len, + TP_printk("rep=%p %u bytes: %s (%u/0x%x)", + __entry->rep, __entry->byte_len, rdma_show_wc_status(__entry->status), __entry->status, __entry->vendor_err ) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 3a27335fce2c..c2ce6480b4b1 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -66,8 +66,9 @@ DECLARE_EVENT_CLASS(writeback_page_template, ), TP_fast_assign( - strncpy(__entry->name, - mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", 32); + strscpy_pad(__entry->name, + mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", + 32); __entry->ino = mapping ? mapping->host->i_ino : 0; __entry->index = page->index; ), @@ -110,8 +111,8 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template, struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ - strncpy(__entry->name, - bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); + strscpy_pad(__entry->name, + bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; @@ -316,8 +317,8 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template, ), TP_fast_assign( - strncpy(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + strscpy_pad(__entry->name, + dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); @@ -360,8 +361,9 @@ DECLARE_EVENT_CLASS(writeback_work_class, __field(unsigned int, cgroup_ino) ), TP_fast_assign( - strncpy(__entry->name, - wb->bdi->dev ? dev_name(wb->bdi->dev) : "(unknown)", 32); + strscpy_pad(__entry->name, + wb->bdi->dev ? dev_name(wb->bdi->dev) : + "(unknown)", 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; @@ -414,7 +416,7 @@ DECLARE_EVENT_CLASS(writeback_class, __field(unsigned int, cgroup_ino) ), TP_fast_assign( - strncpy(__entry->name, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%u", @@ -436,7 +438,7 @@ TRACE_EVENT(writeback_bdi_register, __array(char, name, 32) ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strscpy_pad(__entry->name, dev_name(bdi->dev), 32); ), TP_printk("bdi %s", __entry->name @@ -461,7 +463,7 @@ DECLARE_EVENT_CLASS(wbc_class, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strscpy_pad(__entry->name, dev_name(bdi->dev), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; @@ -512,7 +514,7 @@ TRACE_EVENT(writeback_queue_io, ), TP_fast_assign( unsigned long *older_than_this = work->older_than_this; - strncpy(__entry->name, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32); __entry->older = older_than_this ? *older_than_this : 0; __entry->age = older_than_this ? (jiffies - *older_than_this) * 1000 / HZ : -1; @@ -598,7 +600,7 @@ TRACE_EVENT(bdi_dirty_ratelimit, ), TP_fast_assign( - strlcpy(__entry->bdi, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); @@ -663,7 +665,7 @@ TRACE_EVENT(balance_dirty_pages, TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; - strlcpy(__entry->bdi, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + @@ -723,8 +725,8 @@ TRACE_EVENT(writeback_sb_inodes_requeue, ), TP_fast_assign( - strncpy(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + strscpy_pad(__entry->name, + dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; @@ -797,8 +799,8 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, ), TP_fast_assign( - strncpy(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + strscpy_pad(__entry->name, + dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 63b1f506ea67..c160a5354eb6 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -67,6 +67,9 @@ #define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ #define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ +#define MADV_COLD 20 /* deactivate these pages */ +#define MADV_PAGEOUT 21 /* reclaim these pages */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/include/uapi/linux/coff.h b/include/uapi/linux/coff.h index e4a79f80b9a0..ab5c7e847eed 100644 --- a/include/uapi/linux/coff.h +++ b/include/uapi/linux/coff.h @@ -11,6 +11,9 @@ more information about COFF, then O'Reilly has a very excellent book. */ +#ifndef _UAPI_LINUX_COFF_H +#define _UAPI_LINUX_COFF_H + #define E_SYMNMLEN 8 /* Number of characters in a symbol name */ #define E_FILNMLEN 14 /* Number of characters in a file name */ #define E_DIMNUM 4 /* Number of array dimensions in auxiliary entry */ @@ -350,3 +353,5 @@ struct COFF_reloc { /* For new sections we haven't heard of before */ #define COFF_DEF_SECTION_ALIGNMENT 4 + +#endif /* _UAPI_LINUX_COFF_H */ diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 7c15729d9d25..3d920ff15c80 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1240,15 +1240,14 @@ static int do_mq_notify(mqd_t mqdes, const struct sigevent *notification) /* create the notify skb */ nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL); - if (!nc) { - ret = -ENOMEM; - goto out; - } + if (!nc) + return -ENOMEM; + if (copy_from_user(nc->data, notification->sigev_value.sival_ptr, NOTIFY_COOKIE_LEN)) { ret = -EFAULT; - goto out; + goto free_skb; } /* TODO: add a header? */ @@ -1264,8 +1263,7 @@ retry: fdput(f); if (IS_ERR(sock)) { ret = PTR_ERR(sock); - sock = NULL; - goto out; + goto free_skb; } timeo = MAX_SCHEDULE_TIMEOUT; @@ -1274,11 +1272,8 @@ retry: sock = NULL; goto retry; } - if (ret) { - sock = NULL; - nc = NULL; - goto out; - } + if (ret) + return ret; } } @@ -1333,7 +1328,8 @@ out_fput: out: if (sock) netlink_detachskb(sock, nc); - else if (nc) + else +free_skb: dev_kfree_skb(nc); return ret; diff --git a/ipc/sem.c b/ipc/sem.c index 7da4504bcc7c..ec97a7072413 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1852,7 +1852,8 @@ static struct sem_undo *__lookup_undo(struct sem_undo_list *ulp, int semid) { struct sem_undo *un; - list_for_each_entry_rcu(un, &ulp->list_proc, list_proc) { + list_for_each_entry_rcu(un, &ulp->list_proc, list_proc, + spin_is_locked(&ulp->lock)) { if (un->semid == semid) return un; } diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 10f1187b3907..f76d6f77dd5e 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -893,30 +893,25 @@ static struct sysrq_key_op sysrq_dbg_op = { }; #endif -static int kgdb_panic_event(struct notifier_block *self, - unsigned long val, - void *data) +void kgdb_panic(const char *msg) { + if (!kgdb_io_module_registered) + return; + /* - * Avoid entering the debugger if we were triggered due to a panic - * We don't want to get stuck waiting for input from user in such case. - * panic_timeout indicates the system should automatically + * We don't want to get stuck waiting for input from user if + * "panic_timeout" indicates the system should automatically * reboot on panic. */ if (panic_timeout) - return NOTIFY_DONE; + return; if (dbg_kdb_mode) - kdb_printf("PANIC: %s\n", (char *)data); + kdb_printf("PANIC: %s\n", msg); + kgdb_breakpoint(); - return NOTIFY_DONE; } -static struct notifier_block kgdb_panic_event_nb = { - .notifier_call = kgdb_panic_event, - .priority = INT_MAX, -}; - void __weak kgdb_arch_late(void) { } @@ -965,8 +960,6 @@ static void kgdb_register_callbacks(void) kgdb_arch_late(); register_module_notifier(&dbg_module_load_nb); register_reboot_notifier(&dbg_reboot_notifier); - atomic_notifier_chain_register(&panic_notifier_list, - &kgdb_panic_event_nb); #ifdef CONFIG_MAGIC_SYSRQ register_sysrq_key('g', &sysrq_dbg_op); #endif @@ -980,16 +973,14 @@ static void kgdb_register_callbacks(void) static void kgdb_unregister_callbacks(void) { /* - * When this routine is called KGDB should unregister from the - * panic handler and clean up, making sure it is not handling any + * When this routine is called KGDB should unregister from + * handlers and clean up, making sure it is not handling any * break exceptions at the time. */ if (kgdb_io_module_registered) { kgdb_io_module_registered = 0; unregister_reboot_notifier(&dbg_reboot_notifier); unregister_module_notifier(&dbg_module_load_nb); - atomic_notifier_chain_unregister(&panic_notifier_list, - &kgdb_panic_event_nb); kgdb_arch_exit(); #ifdef CONFIG_MAGIC_SYSRQ unregister_sysrq_key('g', &sysrq_dbg_op); diff --git a/kernel/elfcore.c b/kernel/elfcore.c index fc482c8e0bd8..57fb4dcff434 100644 --- a/kernel/elfcore.c +++ b/kernel/elfcore.c @@ -3,6 +3,7 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/binfmts.h> +#include <linux/elfcore.h> Elf_Half __weak elf_core_extra_phdrs(void) { diff --git a/kernel/events/core.c b/kernel/events/core.c index 4f08b17d6426..275eae05af20 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2239,7 +2239,7 @@ static void __perf_event_disable(struct perf_event *event, * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to - * remains valid. This condition is satisifed when called through + * remains valid. This condition is satisfied when called through * perf_event_for_each_child or perf_event_for_each because they * hold the top-level event's child_mutex, so any descendant that * goes to exit will block in perf_event_exit_event(). @@ -6054,7 +6054,7 @@ static void perf_sample_regs_intr(struct perf_regs *regs_intr, * Get remaining task size from user stack pointer. * * It'd be better to take stack vma map and limit this more - * precisly, but there's no way to get it safely under interrupt, + * precisely, but there's no way to get it safely under interrupt, * so using TASK_SIZE as limit. */ static u64 perf_ustack_task_size(struct pt_regs *regs) @@ -6616,7 +6616,7 @@ void perf_prepare_sample(struct perf_event_header *header, if (sample_type & PERF_SAMPLE_STACK_USER) { /* - * Either we need PERF_SAMPLE_STACK_USER bit to be allways + * Either we need PERF_SAMPLE_STACK_USER bit to be always * processed as the last one or have additional check added * in case new sample type is added, because we could eat * up the rest of the sample size. diff --git a/kernel/fork.c b/kernel/fork.c index 5a0fd518e04e..60763c043aa3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -125,6 +125,15 @@ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ +#define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) + +static const char * const resident_page_types[] = { + NAMED_ARRAY_INDEX(MM_FILEPAGES), + NAMED_ARRAY_INDEX(MM_ANONPAGES), + NAMED_ARRAY_INDEX(MM_SWAPENTS), + NAMED_ARRAY_INDEX(MM_SHMEMPAGES), +}; + DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ @@ -645,12 +654,15 @@ static void check_mm(struct mm_struct *mm) { int i; + BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, + "Please make sure 'struct resident_page_types[]' is updated as well"); + for (i = 0; i < NR_MM_COUNTERS; i++) { long x = atomic_long_read(&mm->rss_stat.count[i]); if (unlikely(x)) - printk(KERN_ALERT "BUG: Bad rss-counter state " - "mm:%p idx:%d val:%ld\n", mm, i, x); + pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", + mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d5870723b8ad..15d70a90b50d 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -300,6 +300,8 @@ static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order) { struct page *pages; + if (fatal_signal_pending(current)) + return NULL; pages = alloc_pages(gfp_mask & ~__GFP_ZERO, order); if (pages) { unsigned int count, i; diff --git a/kernel/panic.c b/kernel/panic.c index 057540b6eee9..47e8ebccc22b 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -12,6 +12,7 @@ #include <linux/debug_locks.h> #include <linux/sched/debug.h> #include <linux/interrupt.h> +#include <linux/kgdb.h> #include <linux/kmsg_dump.h> #include <linux/kallsyms.h> #include <linux/notifier.h> @@ -220,6 +221,13 @@ void panic(const char *fmt, ...) #endif /* + * If kgdb is enabled, give it a chance to run before we stop all + * the other CPUs or else we won't be able to debug processes left + * running on them. + */ + kgdb_panic(buf); + + /* * If we have crashed and we have a crash kernel loaded let it handle * everything else. * If we want to run this after calling panic_notifiers, pass @@ -551,9 +559,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, { disable_trace_on_warning(); - if (args) - pr_warn(CUT_HERE); - if (file) pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", raw_smp_processor_id(), current->pid, file, line, @@ -591,37 +596,26 @@ void __warn(const char *file, int line, void *caller, unsigned taint, add_taint(taint, LOCKDEP_STILL_OK); } -#ifdef WANT_WARN_ON_SLOWPATH -void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) +#ifndef __WARN_FLAGS +void warn_slowpath_fmt(const char *file, int line, unsigned taint, + const char *fmt, ...) { struct warn_args args; - args.fmt = fmt; - va_start(args.args, fmt); - __warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, - &args); - va_end(args.args); -} -EXPORT_SYMBOL(warn_slowpath_fmt); + pr_warn(CUT_HERE); -void warn_slowpath_fmt_taint(const char *file, int line, - unsigned taint, const char *fmt, ...) -{ - struct warn_args args; + if (!fmt) { + __warn(file, line, __builtin_return_address(0), taint, + NULL, NULL); + return; + } args.fmt = fmt; va_start(args.args, fmt); __warn(file, line, __builtin_return_address(0), taint, NULL, &args); va_end(args.args); } -EXPORT_SYMBOL(warn_slowpath_fmt_taint); - -void warn_slowpath_null(const char *file, int line) -{ - pr_warn(CUT_HERE); - __warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, NULL); -} -EXPORT_SYMBOL(warn_slowpath_null); +EXPORT_SYMBOL(warn_slowpath_fmt); #else void __warn_printk(const char *fmt, ...) { diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 0e315a2e77ae..4820823515e9 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1678,24 +1678,26 @@ void timer_clear_idle(void) static int collect_expired_timers(struct timer_base *base, struct hlist_head *heads) { + unsigned long now = READ_ONCE(jiffies); + /* * NOHZ optimization. After a long idle sleep we need to forward the * base to current jiffies. Avoid a loop by searching the bitfield for * the next expiring timer. */ - if ((long)(jiffies - base->clk) > 2) { + if ((long)(now - base->clk) > 2) { unsigned long next = __next_timer_interrupt(base); /* * If the next timer is ahead of time forward to current * jiffies, otherwise forward to the next expiry time: */ - if (time_after(next, jiffies)) { + if (time_after(next, now)) { /* * The call site will increment base->clk and then * terminate the expiry loop immediately. */ - base->clk = jiffies; + base->clk = now; return 0; } base->clk = next; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index a6697e28ddda..402dc3ce88d3 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -549,10 +549,11 @@ static bool trace_kprobe_has_same_kprobe(struct trace_kprobe *orig, for (i = 0; i < orig->tp.nr_args; i++) { if (strcmp(orig->tp.args[i].comm, comp->tp.args[i].comm)) - continue; + break; } - return true; + if (i == orig->tp.nr_args) + return true; } return false; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 34dd6d0016a3..dd884341f5c5 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -431,10 +431,11 @@ static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig, for (i = 0; i < orig->tp.nr_args; i++) { if (strcmp(orig->tp.args[i].comm, comp->tp.args[i].comm)) - continue; + break; } - return true; + if (i == orig->tp.nr_args) + return true; } return false; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6b1b1703a646..93d97f9b0157 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -311,7 +311,7 @@ config HEADERS_CHECK relevant for userspace, say 'Y'. config OPTIMIZE_INLINING - bool "Allow compiler to uninline functions marked 'inline'" + def_bool y help This option determines if the kernel forces gcc to inline the functions developers have marked 'inline'. Doing so takes away freedom from gcc to @@ -322,8 +322,6 @@ config OPTIMIZE_INLINING decision will become the default in the future. Until then this option is there to test gcc for this. - If unsure, say N. - config DEBUG_SECTION_MISMATCH bool "Enable full Section mismatch analysis" help diff --git a/lib/bug.c b/lib/bug.c index 1077366f496b..8c98af0bf585 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -181,6 +181,15 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) } } + /* + * BUG() and WARN_ON() families don't print a custom debug message + * before triggering the exception handler, so we must add the + * "cut here" line now. WARN() issues its own "cut here" before the + * extra debugging message it writes before triggering the handler. + */ + if ((bug->flags & BUGFLAG_NO_CUT_HERE) == 0) + printk(KERN_DEFAULT CUT_HERE); + if (warning) { /* this is a WARN_ON rather than BUG/BUG_ON */ __warn(file, line, (void *)bugaddr, BUG_GET_TAINT(bug), regs, @@ -188,8 +197,6 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) return BUG_TRAP_TYPE_WARN; } - printk(KERN_DEFAULT CUT_HERE); - if (file) pr_crit("kernel BUG at %s:%u!\n", file, line); else diff --git a/lib/extable.c b/lib/extable.c index 25da4071122a..c3e59caf7ffa 100644 --- a/lib/extable.c +++ b/lib/extable.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/sort.h> #include <linux/uaccess.h> +#include <linux/extable.h> #ifndef ARCH_HAS_RELATIVE_EXTABLE #define ex_to_insn(x) ((x)->insn) diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c index a7bafc413730..ae25e2fa2187 100644 --- a/lib/generic-radix-tree.c +++ b/lib/generic-radix-tree.c @@ -36,12 +36,12 @@ static inline size_t genradix_depth_size(unsigned depth) #define GENRADIX_DEPTH_MASK \ ((unsigned long) (roundup_pow_of_two(GENRADIX_MAX_DEPTH + 1) - 1)) -unsigned genradix_root_to_depth(struct genradix_root *r) +static inline unsigned genradix_root_to_depth(struct genradix_root *r) { return (unsigned long) r & GENRADIX_DEPTH_MASK; } -struct genradix_node *genradix_root_to_node(struct genradix_root *r) +static inline struct genradix_node *genradix_root_to_node(struct genradix_root *r) { return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK); } diff --git a/lib/hexdump.c b/lib/hexdump.c index b1d55b669ae2..147133f8eb2f 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -270,25 +270,4 @@ void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, } EXPORT_SYMBOL(print_hex_dump); -#if !defined(CONFIG_DYNAMIC_DEBUG) -/** - * print_hex_dump_bytes - shorthand form of print_hex_dump() with default params - * @prefix_str: string to prefix each line with; - * caller supplies trailing spaces for alignment if desired - * @prefix_type: controls whether prefix of an offset, address, or none - * is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE) - * @buf: data blob to dump - * @len: number of bytes in the @buf - * - * Calls print_hex_dump(), with log level of KERN_DEBUG, - * rowsize of 16, groupsize of 1, and ASCII output included. - */ -void print_hex_dump_bytes(const char *prefix_str, int prefix_type, - const void *buf, size_t len) -{ - print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, 16, 1, - buf, len, true); -} -EXPORT_SYMBOL(print_hex_dump_bytes); -#endif /* !defined(CONFIG_DYNAMIC_DEBUG) */ #endif /* defined(CONFIG_PRINTK) */ diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c index ba16c08e8cb9..717c940112f9 100644 --- a/lib/lzo/lzo1x_compress.c +++ b/lib/lzo/lzo1x_compress.c @@ -83,17 +83,19 @@ next: ALIGN((uintptr_t)ir, 4)) && (ir < limit) && (*ir == 0)) ir++; - for (; (ir + 4) <= limit; ir += 4) { - dv = *((u32 *)ir); - if (dv) { + if (IS_ALIGNED((uintptr_t)ir, 4)) { + for (; (ir + 4) <= limit; ir += 4) { + dv = *((u32 *)ir); + if (dv) { # if defined(__LITTLE_ENDIAN) - ir += __builtin_ctz(dv) >> 3; + ir += __builtin_ctz(dv) >> 3; # elif defined(__BIG_ENDIAN) - ir += __builtin_clz(dv) >> 3; + ir += __builtin_clz(dv) >> 3; # else # error "missing endian definition" # endif - break; + break; + } } } #endif diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c index 62b8ee92643d..41ae3c7570d3 100644 --- a/lib/rbtree_test.c +++ b/lib/rbtree_test.c @@ -77,26 +77,10 @@ static inline void erase_cached(struct test_node *node, struct rb_root_cached *r } -static inline u32 augment_recompute(struct test_node *node) -{ - u32 max = node->val, child_augmented; - if (node->rb.rb_left) { - child_augmented = rb_entry(node->rb.rb_left, struct test_node, - rb)->augmented; - if (max < child_augmented) - max = child_augmented; - } - if (node->rb.rb_right) { - child_augmented = rb_entry(node->rb.rb_right, struct test_node, - rb)->augmented; - if (max < child_augmented) - max = child_augmented; - } - return max; -} +#define NODE_VAL(node) ((node)->val) -RB_DECLARE_CALLBACKS(static, augment_callbacks, struct test_node, rb, - u32, augmented, augment_recompute) +RB_DECLARE_CALLBACKS_MAX(static, augment_callbacks, + struct test_node, rb, u32, augmented, NODE_VAL) static void insert_augmented(struct test_node *node, struct rb_root_cached *root) @@ -238,7 +222,20 @@ static void check_augmented(int nr_nodes) check(nr_nodes); for (rb = rb_first(&root.rb_root); rb; rb = rb_next(rb)) { struct test_node *node = rb_entry(rb, struct test_node, rb); - WARN_ON_ONCE(node->augmented != augment_recompute(node)); + u32 subtree, max = node->val; + if (node->rb.rb_left) { + subtree = rb_entry(node->rb.rb_left, struct test_node, + rb)->augmented; + if (max < subtree) + max = subtree; + } + if (node->rb.rb_right) { + subtree = rb_entry(node->rb.rb_right, struct test_node, + rb)->augmented; + if (max < subtree) + max = subtree; + } + WARN_ON_ONCE(node->augmented != max); } } diff --git a/lib/string.c b/lib/string.c index 461fb620f85f..cd7a10c19210 100644 --- a/lib/string.c +++ b/lib/string.c @@ -173,8 +173,9 @@ EXPORT_SYMBOL(strlcpy); * doesn't unnecessarily force the tail of the destination buffer to be * zeroed. If zeroing is desired please use strscpy_pad(). * - * Return: The number of characters copied (not including the trailing - * %NUL) or -E2BIG if the destination buffer wasn't big enough. + * Returns: + * * The number of characters copied (not including the trailing %NUL) + * * -E2BIG if count is 0 or @src was truncated. */ ssize_t strscpy(char *dest, const char *src, size_t count) { @@ -182,7 +183,7 @@ ssize_t strscpy(char *dest, const char *src, size_t count) size_t max = count; long res = 0; - if (count == 0) + if (count == 0 || WARN_ON_ONCE(count > INT_MAX)) return -E2BIG; #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -253,8 +254,9 @@ EXPORT_SYMBOL(strscpy); * For full explanation of why you may want to consider using the * 'strscpy' functions please see the function docstring for strscpy(). * - * Return: The number of characters copied (not including the trailing - * %NUL) or -E2BIG if the destination buffer wasn't big enough. + * Returns: + * * The number of characters copied (not including the trailing %NUL) + * * -E2BIG if count is 0 or @src was truncated. */ ssize_t strscpy_pad(char *dest, const char *src, size_t count) { diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 023ba9f3b99f..dccb95af6003 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -6,6 +6,7 @@ #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> +#include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> @@ -108,7 +109,7 @@ long strncpy_from_user(char *dst, const char __user *src, long count) return 0; max_addr = user_addr_max(); - src_addr = (unsigned long)src; + src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 7f2db3fe311f..28ff554a1be8 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -2,6 +2,7 @@ #include <linux/kernel.h> #include <linux/export.h> #include <linux/uaccess.h> +#include <linux/mm.h> #include <asm/word-at-a-time.h> @@ -109,7 +110,7 @@ long strnlen_user(const char __user *str, long count) return 0; max_addr = user_addr_max(); - src_addr = (unsigned long)str; + src_addr = (unsigned long)untagged_addr(str); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; diff --git a/mm/frame_vector.c b/mm/frame_vector.c index c64dca6e27c2..c431ca81dad5 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -46,6 +46,8 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, if (WARN_ON_ONCE(nr_frames > vec->nr_allocated)) nr_frames = vec->nr_allocated; + start = untagged_addr(start); + down_read(&mm->mmap_sem); locked = 1; vma = find_vma_intersection(mm, start, start + 1); @@ -788,6 +788,8 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (!nr_pages) return 0; + start = untagged_addr(start); + VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); /* @@ -950,6 +952,8 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, struct vm_area_struct *vma; vm_fault_t ret, major = 0; + address = untagged_addr(address); + if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY; diff --git a/mm/internal.h b/mm/internal.h index e32390802fd3..0d5f720c75ab 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -39,7 +39,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); -static inline bool can_madv_dontneed_vma(struct vm_area_struct *vma) +static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); } diff --git a/mm/madvise.c b/mm/madvise.c index 68ab988ad433..2be9f3fdb05e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -11,6 +11,7 @@ #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> +#include <linux/page_idle.h> #include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> @@ -31,6 +32,11 @@ #include "internal.h" +struct madvise_walk_private { + struct mmu_gather *tlb; + bool pageout; +}; + /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_sem for writing. Others, which simply traverse vmas, need @@ -42,6 +48,8 @@ static int madvise_need_mmap_write(int behavior) case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: + case MADV_COLD: + case MADV_PAGEOUT: case MADV_FREE: return 0; default: @@ -289,6 +297,254 @@ static long madvise_willneed(struct vm_area_struct *vma, return 0; } +static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct madvise_walk_private *private = walk->private; + struct mmu_gather *tlb = private->tlb; + bool pageout = private->pageout; + struct mm_struct *mm = tlb->mm; + struct vm_area_struct *vma = walk->vma; + pte_t *orig_pte, *pte, ptent; + spinlock_t *ptl; + struct page *page = NULL; + LIST_HEAD(page_list); + + if (fatal_signal_pending(current)) + return -EINTR; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(*pmd)) { + pmd_t orig_pmd; + unsigned long next = pmd_addr_end(addr, end); + + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); + ptl = pmd_trans_huge_lock(pmd, vma); + if (!ptl) + return 0; + + orig_pmd = *pmd; + if (is_huge_zero_pmd(orig_pmd)) + goto huge_unlock; + + if (unlikely(!pmd_present(orig_pmd))) { + VM_BUG_ON(thp_migration_supported() && + !is_pmd_migration_entry(orig_pmd)); + goto huge_unlock; + } + + page = pmd_page(orig_pmd); + if (next - addr != HPAGE_PMD_SIZE) { + int err; + + if (page_mapcount(page) != 1) + goto huge_unlock; + + get_page(page); + spin_unlock(ptl); + lock_page(page); + err = split_huge_page(page); + unlock_page(page); + put_page(page); + if (!err) + goto regular_page; + return 0; + } + + if (pmd_young(orig_pmd)) { + pmdp_invalidate(vma, addr, pmd); + orig_pmd = pmd_mkold(orig_pmd); + + set_pmd_at(mm, addr, pmd, orig_pmd); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + } + + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (pageout) { + if (!isolate_lru_page(page)) + list_add(&page->lru, &page_list); + } else + deactivate_page(page); +huge_unlock: + spin_unlock(ptl); + if (pageout) + reclaim_pages(&page_list); + return 0; + } + + if (pmd_trans_unstable(pmd)) + return 0; +regular_page: +#endif + tlb_change_page_size(tlb, PAGE_SIZE); + orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + flush_tlb_batched_pending(mm); + arch_enter_lazy_mmu_mode(); + for (; addr < end; pte++, addr += PAGE_SIZE) { + ptent = *pte; + + if (pte_none(ptent)) + continue; + + if (!pte_present(ptent)) + continue; + + page = vm_normal_page(vma, addr, ptent); + if (!page) + continue; + + /* + * Creating a THP page is expensive so split it only if we + * are sure it's worth. Split it if we are only owner. + */ + if (PageTransCompound(page)) { + if (page_mapcount(page) != 1) + break; + get_page(page); + if (!trylock_page(page)) { + put_page(page); + break; + } + pte_unmap_unlock(orig_pte, ptl); + if (split_huge_page(page)) { + unlock_page(page); + put_page(page); + pte_offset_map_lock(mm, pmd, addr, &ptl); + break; + } + unlock_page(page); + put_page(page); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte--; + addr -= PAGE_SIZE; + continue; + } + + VM_BUG_ON_PAGE(PageTransCompound(page), page); + + if (pte_young(ptent)) { + ptent = ptep_get_and_clear_full(mm, addr, pte, + tlb->fullmm); + ptent = pte_mkold(ptent); + set_pte_at(mm, addr, pte, ptent); + tlb_remove_tlb_entry(tlb, pte, addr); + } + + /* + * We are deactivating a page for accelerating reclaiming. + * VM couldn't reclaim the page unless we clear PG_young. + * As a side effect, it makes confuse idle-page tracking + * because they will miss recent referenced history. + */ + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (pageout) { + if (!isolate_lru_page(page)) + list_add(&page->lru, &page_list); + } else + deactivate_page(page); + } + + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(orig_pte, ptl); + if (pageout) + reclaim_pages(&page_list); + cond_resched(); + + return 0; +} + +static const struct mm_walk_ops cold_walk_ops = { + .pmd_entry = madvise_cold_or_pageout_pte_range, +}; + +static void madvise_cold_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + struct madvise_walk_private walk_private = { + .pageout = false, + .tlb = tlb, + }; + + tlb_start_vma(tlb, vma); + walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); + tlb_end_vma(tlb, vma); +} + +static long madvise_cold(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start_addr, unsigned long end_addr) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + + *prev = vma; + if (!can_madv_lru_vma(vma)) + return -EINVAL; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, start_addr, end_addr); + madvise_cold_page_range(&tlb, vma, start_addr, end_addr); + tlb_finish_mmu(&tlb, start_addr, end_addr); + + return 0; +} + +static void madvise_pageout_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + struct madvise_walk_private walk_private = { + .pageout = true, + .tlb = tlb, + }; + + tlb_start_vma(tlb, vma); + walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); + tlb_end_vma(tlb, vma); +} + +static inline bool can_do_pageout(struct vm_area_struct *vma) +{ + if (vma_is_anonymous(vma)) + return true; + if (!vma->vm_file) + return false; + /* + * paging out pagecache only for non-anonymous mappings that correspond + * to the files the calling process could (if tried) open for writing; + * otherwise we'd be including shared non-exclusive mappings, which + * opens a side channel. + */ + return inode_owner_or_capable(file_inode(vma->vm_file)) || + inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; +} + +static long madvise_pageout(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start_addr, unsigned long end_addr) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + + *prev = vma; + if (!can_madv_lru_vma(vma)) + return -EINVAL; + + if (!can_do_pageout(vma)) + return 0; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, start_addr, end_addr); + madvise_pageout_page_range(&tlb, vma, start_addr, end_addr); + tlb_finish_mmu(&tlb, start_addr, end_addr); + + return 0; +} + static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -493,7 +749,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, int behavior) { *prev = vma; - if (!can_madv_dontneed_vma(vma)) + if (!can_madv_lru_vma(vma)) return -EINVAL; if (!userfaultfd_remove(vma, start, end)) { @@ -515,7 +771,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, */ return -ENOMEM; } - if (!can_madv_dontneed_vma(vma)) + if (!can_madv_lru_vma(vma)) return -EINVAL; if (end > vma->vm_end) { /* @@ -669,6 +925,10 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, return madvise_remove(vma, prev, start, end); case MADV_WILLNEED: return madvise_willneed(vma, prev, start, end); + case MADV_COLD: + return madvise_cold(vma, prev, start, end); + case MADV_PAGEOUT: + return madvise_pageout(vma, prev, start, end); case MADV_FREE: case MADV_DONTNEED: return madvise_dontneed_free(vma, prev, start, end, behavior); @@ -690,6 +950,8 @@ madvise_behavior_valid(int behavior) case MADV_WILLNEED: case MADV_DONTNEED: case MADV_FREE: + case MADV_COLD: + case MADV_PAGEOUT: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: @@ -784,6 +1046,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) size_t len; struct blk_plug plug; + start = untagged_addr(start); + if (!madvise_behavior_valid(behavior)) return error; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2156ef775d04..c313c49074ca 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2943,6 +2943,16 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) { + + /* + * Enforce __GFP_NOFAIL allocation because callers are not + * prepared to see failures and likely do not have any failure + * handling code. + */ + if (gfp & __GFP_NOFAIL) { + page_counter_charge(&memcg->kmem, nr_pages); + return 0; + } cancel_charge(memcg, nr_pages); return -ENOMEM; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 464406e8da91..de27d08b1ff8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1405,6 +1405,7 @@ static long kernel_mbind(unsigned long start, unsigned long len, int err; unsigned short mode_flags; + start = untagged_addr(start); mode_flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if (mode >= MPOL_MAX) @@ -1558,6 +1559,8 @@ static int kernel_get_mempolicy(int __user *policy, int uninitialized_var(pval); nodemask_t nodes; + addr = untagged_addr(addr); + if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; diff --git a/mm/migrate.c b/mm/migrate.c index 73d476d690b1..4fe45d1428c8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1612,7 +1612,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, goto out_flush; if (get_user(node, nodes + i)) goto out_flush; - addr = (unsigned long)p; + addr = (unsigned long)untagged_addr(p); err = -ENODEV; if (node < 0 || node >= MAX_NUMNODES) diff --git a/mm/mincore.c b/mm/mincore.c index f9a9dbe8cd33..49b6fa2f6aa1 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -256,6 +256,8 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len, unsigned long pages; unsigned char *tmp; + start = untagged_addr(start); + /* Check the start address: needs to be page-aligned.. */ if (start & ~PAGE_MASK) return -EINVAL; diff --git a/mm/mlock.c b/mm/mlock.c index a90099da4fb4..a72c1eeded77 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -674,6 +674,8 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla unsigned long lock_limit; int error = -ENOMEM; + start = untagged_addr(start); + if (!can_do_mlock()) return -EPERM; @@ -735,6 +737,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; + start = untagged_addr(start); + len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; diff --git a/mm/mmap.c b/mm/mmap.c index f1e8c7f93e04..a7d8c84d19b7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -201,6 +201,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) bool downgraded = false; LIST_HEAD(uf); + brk = untagged_addr(brk); + if (down_write_killable(&mm->mmap_sem)) return -EINTR; @@ -289,9 +291,9 @@ out: return retval; } -static long vma_compute_subtree_gap(struct vm_area_struct *vma) +static inline unsigned long vma_compute_gap(struct vm_area_struct *vma) { - unsigned long max, prev_end, subtree_gap; + unsigned long gap, prev_end; /* * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we @@ -299,14 +301,21 @@ static long vma_compute_subtree_gap(struct vm_area_struct *vma) * an unmapped area; whereas when expanding we only require one. * That's a little inconsistent, but keeps the code here simpler. */ - max = vm_start_gap(vma); + gap = vm_start_gap(vma); if (vma->vm_prev) { prev_end = vm_end_gap(vma->vm_prev); - if (max > prev_end) - max -= prev_end; + if (gap > prev_end) + gap -= prev_end; else - max = 0; + gap = 0; } + return gap; +} + +#ifdef CONFIG_DEBUG_VM_RB +static unsigned long vma_compute_subtree_gap(struct vm_area_struct *vma) +{ + unsigned long max = vma_compute_gap(vma), subtree_gap; if (vma->vm_rb.rb_left) { subtree_gap = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb)->rb_subtree_gap; @@ -322,7 +331,6 @@ static long vma_compute_subtree_gap(struct vm_area_struct *vma) return max; } -#ifdef CONFIG_DEBUG_VM_RB static int browse_rb(struct mm_struct *mm) { struct rb_root *root = &mm->mm_rb; @@ -428,8 +436,9 @@ static void validate_mm(struct mm_struct *mm) #define validate_mm(mm) do { } while (0) #endif -RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, - unsigned long, rb_subtree_gap, vma_compute_subtree_gap) +RB_DECLARE_CALLBACKS_MAX(static, vma_gap_callbacks, + struct vm_area_struct, vm_rb, + unsigned long, rb_subtree_gap, vma_compute_gap) /* * Update augmented rbtree rb_subtree_gap values after vma->vm_start or @@ -439,8 +448,8 @@ RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, static void vma_gap_update(struct vm_area_struct *vma) { /* - * As it turns out, RB_DECLARE_CALLBACKS() already created a callback - * function that does exactly what we want. + * As it turns out, RB_DECLARE_CALLBACKS_MAX() already created + * a callback function that does exactly what we want. */ vma_gap_callbacks_propagate(&vma->vm_rb, NULL); } @@ -1580,6 +1589,8 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, struct file *file = NULL; unsigned long retval; + addr = untagged_addr(addr); + if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); @@ -2878,6 +2889,7 @@ EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { + addr = untagged_addr(addr); profile_munmap(addr); return __vm_munmap(addr, len, true); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 675e5d34a507..7967825f6d33 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -459,6 +459,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len, const bool rier = (current->personality & READ_IMPLIES_EXEC) && (prot & PROT_READ); + start = untagged_addr(start); + prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP); if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */ return -EINVAL; diff --git a/mm/mremap.c b/mm/mremap.c index fc241d23cd97..1fc8a29fbe3f 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -606,6 +606,9 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, LIST_HEAD(uf_unmap_early); LIST_HEAD(uf_unmap); + addr = untagged_addr(addr); + new_addr = untagged_addr(new_addr); + if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE)) return ret; diff --git a/mm/msync.c b/mm/msync.c index ef30a429623a..c3bd3e75f687 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -37,6 +37,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) int unmapped_error = 0; int error = -EINVAL; + start = untagged_addr(start); + if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC)) goto out; if (offset_in_page(start)) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c1d9496b4c43..71e3acea7817 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -523,7 +523,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm) set_bit(MMF_UNSTABLE, &mm->flags); for (vma = mm->mmap ; vma; vma = vma->vm_next) { - if (!can_madv_dontneed_vma(vma)) + if (!can_madv_lru_vma(vma)) continue; /* diff --git a/mm/swap.c b/mm/swap.c index 784dc1620620..38c3fa4308e2 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -47,6 +47,7 @@ int page_cluster; static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); +static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs); #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); @@ -538,6 +539,22 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, update_page_reclaim_stat(lruvec, file, 0); } +static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, + void *arg) +{ + if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { + int file = page_is_file_cache(page); + int lru = page_lru_base_type(page); + + del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); + ClearPageActive(page); + ClearPageReferenced(page); + add_page_to_lru_list(page, lruvec, lru); + + __count_vm_events(PGDEACTIVATE, hpage_nr_pages(page)); + update_page_reclaim_stat(lruvec, file, 0); + } +} static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) @@ -590,6 +607,10 @@ void lru_add_drain_cpu(int cpu) if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); + pvec = &per_cpu(lru_deactivate_pvecs, cpu); + if (pagevec_count(pvec)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + pvec = &per_cpu(lru_lazyfree_pvecs, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); @@ -623,6 +644,26 @@ void deactivate_file_page(struct page *page) } } +/* + * deactivate_page - deactivate a page + * @page: page to deactivate + * + * deactivate_page() moves @page to the inactive list if @page was on the active + * list and was not an unevictable page. This is done to accelerate the reclaim + * of @page. + */ +void deactivate_page(struct page *page) +{ + if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { + struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + put_cpu_var(lru_deactivate_pvecs); + } +} + /** * mark_page_lazyfree - make an anon page lazyfree * @page: page to deactivate @@ -687,6 +728,7 @@ void lru_add_drain_all(void) if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); diff --git a/mm/usercopy.c b/mm/usercopy.c index 98e924864554..660717a1ea5c 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> +#include <linux/highmem.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> @@ -227,7 +228,12 @@ static inline void check_heap_object(const void *ptr, unsigned long n, if (!virt_addr_valid(ptr)) return; - page = virt_to_head_page(ptr); + /* + * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the + * highmem page or fallback to virt_to_page(). The following + * is effectively a highmem-aware virt_to_head_page(). + */ + page = compound_head(kmap_to_page((void *)ptr)); if (PageSlab(page)) { /* Check slab allocator for flags and size. */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index fcadd3e25c0c..a3c70e275f4e 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -396,9 +396,8 @@ compute_subtree_max_size(struct vmap_area *va) get_subtree_max_size(va->rb_node.rb_right)); } -RB_DECLARE_CALLBACKS(static, free_vmap_area_rb_augment_cb, - struct vmap_area, rb_node, unsigned long, subtree_max_size, - compute_subtree_max_size) +RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, + struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) static void purge_vmap_area_lazy(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); diff --git a/mm/vmscan.c b/mm/vmscan.c index 4911754c93b7..e5d52d6a24af 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1123,7 +1123,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct scan_control *sc, enum ttu_flags ttu_flags, struct reclaim_stat *stat, - bool force_reclaim) + bool ignore_references) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); @@ -1137,7 +1137,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct address_space *mapping; struct page *page; int may_enter_fs; - enum page_references references = PAGEREF_RECLAIM_CLEAN; + enum page_references references = PAGEREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; @@ -1268,7 +1268,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } - if (!force_reclaim) + if (!ignore_references) references = page_check_references(page, sc); switch (references) { @@ -2145,6 +2145,62 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_deactivate, nr_rotated, sc->priority, file); } +unsigned long reclaim_pages(struct list_head *page_list) +{ + int nid = -1; + unsigned long nr_reclaimed = 0; + LIST_HEAD(node_page_list); + struct reclaim_stat dummy_stat; + struct page *page; + struct scan_control sc = { + .gfp_mask = GFP_KERNEL, + .priority = DEF_PRIORITY, + .may_writepage = 1, + .may_unmap = 1, + .may_swap = 1, + }; + + while (!list_empty(page_list)) { + page = lru_to_page(page_list); + if (nid == -1) { + nid = page_to_nid(page); + INIT_LIST_HEAD(&node_page_list); + } + + if (nid == page_to_nid(page)) { + ClearPageActive(page); + list_move(&page->lru, &node_page_list); + continue; + } + + nr_reclaimed += shrink_page_list(&node_page_list, + NODE_DATA(nid), + &sc, 0, + &dummy_stat, false); + while (!list_empty(&node_page_list)) { + page = lru_to_page(&node_page_list); + list_del(&page->lru); + putback_lru_page(page); + } + + nid = -1; + } + + if (!list_empty(&node_page_list)) { + nr_reclaimed += shrink_page_list(&node_page_list, + NODE_DATA(nid), + &sc, 0, + &dummy_stat, false); + while (!list_empty(&node_page_list)) { + page = lru_to_page(&node_page_list); + list_del(&page->lru); + putback_lru_page(page); + } + } + + return nr_reclaimed; +} + /* * The inactive anon list should be small enough that the VM never has * to do too much work. diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 4ce42c62458e..d75fddca44c9 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1960,7 +1960,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred, if (xdr_buf_subsegment(rcv_buf, &integ_buf, data_offset, integ_len)) goto unwrap_failed; - if (xdr_buf_read_netobj(rcv_buf, &mic, mic_offset)) + if (xdr_buf_read_mic(rcv_buf, &mic, mic_offset)) goto unwrap_failed; maj_stat = gss_verify_mic(ctx->gc_gss_ctx, &integ_buf, &mic); if (maj_stat == GSS_S_CONTEXT_EXPIRED) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index a07b516e503a..f7f78566be46 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1837,7 +1837,7 @@ call_allocate(struct rpc_task *task) return; } - rpc_exit(task, -ERESTARTSYS); + rpc_call_rpcerror(task, -ERESTARTSYS); } static int @@ -1862,6 +1862,7 @@ rpc_xdr_encode(struct rpc_task *task) req->rq_rbuffer, req->rq_rcvsize); + req->rq_reply_bytes_recvd = 0; req->rq_snd_buf.head[0].iov_len = 0; xdr_init_encode(&xdr, &req->rq_snd_buf, req->rq_snd_buf.head[0].iov_base, req); @@ -1881,6 +1882,8 @@ call_encode(struct rpc_task *task) if (!rpc_task_need_encode(task)) goto out; dprint_status(task); + /* Dequeue task from the receive queue while we're encoding */ + xprt_request_dequeue_xprt(task); /* Encode here so that rpcsec_gss can use correct sequence number. */ rpc_xdr_encode(task); /* Did the encode result in an error condition? */ @@ -2479,6 +2482,7 @@ call_decode(struct rpc_task *task) struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; struct xdr_stream xdr; + int err; dprint_status(task); @@ -2501,6 +2505,15 @@ call_decode(struct rpc_task *task) * before it changed req->rq_reply_bytes_recvd. */ smp_rmb(); + + /* + * Did we ever call xprt_complete_rqst()? If not, we should assume + * the message is incomplete. + */ + err = -EAGAIN; + if (!req->rq_reply_bytes_recvd) + goto out; + req->rq_rcv_buf.len = req->rq_private_buf.len; /* Check that the softirq receive buffer is valid */ @@ -2509,7 +2522,9 @@ call_decode(struct rpc_task *task) xdr_init_decode(&xdr, &req->rq_rcv_buf, req->rq_rcv_buf.head[0].iov_base, req); - switch (rpc_decode_header(task, &xdr)) { + err = rpc_decode_header(task, &xdr); +out: + switch (err) { case 0: task->tk_action = rpc_exit_task; task->tk_status = rpcauth_unwrap_resp(task, &xdr); @@ -2518,9 +2533,6 @@ call_decode(struct rpc_task *task) return; case -EAGAIN: task->tk_status = 0; - xdr_free_bvec(&req->rq_rcv_buf); - req->rq_reply_bytes_recvd = 0; - req->rq_rcv_buf.len = 0; if (task->tk_client->cl_discrtry) xprt_conditional_disconnect(req->rq_xprt, req->rq_connect_cookie); @@ -2561,7 +2573,7 @@ rpc_encode_header(struct rpc_task *task, struct xdr_stream *xdr) return 0; out_fail: trace_rpc_bad_callhdr(task); - rpc_exit(task, error); + rpc_call_rpcerror(task, error); return error; } @@ -2628,7 +2640,7 @@ out_garbage: return -EAGAIN; } out_err: - rpc_exit(task, error); + rpc_call_rpcerror(task, error); return error; out_unparsable: diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 1f275aba786f..360afe153193 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -541,33 +541,14 @@ rpc_wake_up_task_on_wq_queue_action_locked(struct workqueue_struct *wq, return NULL; } -static void -rpc_wake_up_task_on_wq_queue_locked(struct workqueue_struct *wq, - struct rpc_wait_queue *queue, struct rpc_task *task) -{ - rpc_wake_up_task_on_wq_queue_action_locked(wq, queue, task, NULL, NULL); -} - /* * Wake up a queued task while the queue lock is being held */ -static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct rpc_task *task) -{ - rpc_wake_up_task_on_wq_queue_locked(rpciod_workqueue, queue, task); -} - -/* - * Wake up a task on a specific queue - */ -void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq, - struct rpc_wait_queue *queue, - struct rpc_task *task) +static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, + struct rpc_task *task) { - if (!RPC_IS_QUEUED(task)) - return; - spin_lock(&queue->lock); - rpc_wake_up_task_on_wq_queue_locked(wq, queue, task); - spin_unlock(&queue->lock); + rpc_wake_up_task_on_wq_queue_action_locked(rpciod_workqueue, queue, + task, NULL, NULL); } /* @@ -930,8 +911,10 @@ static void __rpc_execute(struct rpc_task *task) /* * Signalled tasks should exit rather than sleep. */ - if (RPC_SIGNALLED(task)) + if (RPC_SIGNALLED(task)) { + task->tk_rpc_status = -ERESTARTSYS; rpc_exit(task, -ERESTARTSYS); + } /* * The queue->lock protects against races with @@ -967,6 +950,7 @@ static void __rpc_execute(struct rpc_task *task) */ dprintk("RPC: %5u got signal\n", task->tk_pid); set_bit(RPC_TASK_SIGNALLED, &task->tk_runstate); + task->tk_rpc_status = -ERESTARTSYS; rpc_exit(task, -ERESTARTSYS); } dprintk("RPC: %5u sync task resuming\n", task->tk_pid); diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 48c93b9e525e..14ba9e72a204 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -560,7 +560,7 @@ EXPORT_SYMBOL_GPL(xdr_init_encode); * required at the end of encoding, or any other time when the xdr_buf * data might be read. */ -void xdr_commit_encode(struct xdr_stream *xdr) +inline void xdr_commit_encode(struct xdr_stream *xdr) { int shift = xdr->scratch.iov_len; void *page; @@ -1236,43 +1236,60 @@ xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj) } EXPORT_SYMBOL_GPL(xdr_encode_word); -/* If the netobj starting offset bytes from the start of xdr_buf is contained - * entirely in the head or the tail, set object to point to it; otherwise - * try to find space for it at the end of the tail, copy it there, and - * set obj to point to it. */ -int xdr_buf_read_netobj(struct xdr_buf *buf, struct xdr_netobj *obj, unsigned int offset) +/** + * xdr_buf_read_mic() - obtain the address of the GSS mic from xdr buf + * @buf: pointer to buffer containing a mic + * @mic: on success, returns the address of the mic + * @offset: the offset in buf where mic may be found + * + * This function may modify the xdr buf if the mic is found to be straddling + * a boundary between head, pages, and tail. On success the mic can be read + * from the address returned. There is no need to free the mic. + * + * Return: Success returns 0, otherwise an integer error. + */ +int xdr_buf_read_mic(struct xdr_buf *buf, struct xdr_netobj *mic, unsigned int offset) { struct xdr_buf subbuf; + unsigned int boundary; - if (xdr_decode_word(buf, offset, &obj->len)) + if (xdr_decode_word(buf, offset, &mic->len)) return -EFAULT; - if (xdr_buf_subsegment(buf, &subbuf, offset + 4, obj->len)) + offset += 4; + + /* Is the mic partially in the head? */ + boundary = buf->head[0].iov_len; + if (offset < boundary && (offset + mic->len) > boundary) + xdr_shift_buf(buf, boundary - offset); + + /* Is the mic partially in the pages? */ + boundary += buf->page_len; + if (offset < boundary && (offset + mic->len) > boundary) + xdr_shrink_pagelen(buf, boundary - offset); + + if (xdr_buf_subsegment(buf, &subbuf, offset, mic->len)) return -EFAULT; - /* Is the obj contained entirely in the head? */ - obj->data = subbuf.head[0].iov_base; - if (subbuf.head[0].iov_len == obj->len) + /* Is the mic contained entirely in the head? */ + mic->data = subbuf.head[0].iov_base; + if (subbuf.head[0].iov_len == mic->len) return 0; - /* ..or is the obj contained entirely in the tail? */ - obj->data = subbuf.tail[0].iov_base; - if (subbuf.tail[0].iov_len == obj->len) + /* ..or is the mic contained entirely in the tail? */ + mic->data = subbuf.tail[0].iov_base; + if (subbuf.tail[0].iov_len == mic->len) return 0; - /* use end of tail as storage for obj: - * (We don't copy to the beginning because then we'd have - * to worry about doing a potentially overlapping copy. - * This assumes the object is at most half the length of the - * tail.) */ - if (obj->len > buf->buflen - buf->len) + /* Find a contiguous area in @buf to hold all of @mic */ + if (mic->len > buf->buflen - buf->len) return -ENOMEM; if (buf->tail[0].iov_len != 0) - obj->data = buf->tail[0].iov_base + buf->tail[0].iov_len; + mic->data = buf->tail[0].iov_base + buf->tail[0].iov_len; else - obj->data = buf->head[0].iov_base + buf->head[0].iov_len; - __read_bytes_from_xdr_buf(&subbuf, obj->data, obj->len); + mic->data = buf->head[0].iov_base + buf->head[0].iov_len; + __read_bytes_from_xdr_buf(&subbuf, mic->data, mic->len); return 0; } -EXPORT_SYMBOL_GPL(xdr_buf_read_netobj); +EXPORT_SYMBOL_GPL(xdr_buf_read_mic); /* Returns 0 on success, or else a negative error code. */ static int diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 2e71f5455c6c..8a45b3ccc313 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -456,6 +456,12 @@ void xprt_release_rqst_cong(struct rpc_task *task) } EXPORT_SYMBOL_GPL(xprt_release_rqst_cong); +static void xprt_clear_congestion_window_wait_locked(struct rpc_xprt *xprt) +{ + if (test_and_clear_bit(XPRT_CWND_WAIT, &xprt->state)) + __xprt_lock_write_next_cong(xprt); +} + /* * Clear the congestion window wait flag and wake up the next * entry on xprt->sending @@ -671,6 +677,7 @@ void xprt_disconnect_done(struct rpc_xprt *xprt) spin_lock(&xprt->transport_lock); xprt_clear_connected(xprt); xprt_clear_write_space_locked(xprt); + xprt_clear_congestion_window_wait_locked(xprt); xprt_wake_pending_tasks(xprt, -ENOTCONN); spin_unlock(&xprt->transport_lock); } @@ -1324,6 +1331,36 @@ xprt_request_dequeue_transmit(struct rpc_task *task) } /** + * xprt_request_dequeue_xprt - remove a task from the transmit+receive queue + * @task: pointer to rpc_task + * + * Remove a task from the transmit and receive queues, and ensure that + * it is not pinned by the receive work item. + */ +void +xprt_request_dequeue_xprt(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + struct rpc_xprt *xprt = req->rq_xprt; + + if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate) || + test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) || + xprt_is_pinned_rqst(req)) { + spin_lock(&xprt->queue_lock); + xprt_request_dequeue_transmit_locked(task); + xprt_request_dequeue_receive_locked(task); + while (xprt_is_pinned_rqst(req)) { + set_bit(RPC_TASK_MSG_PIN_WAIT, &task->tk_runstate); + spin_unlock(&xprt->queue_lock); + xprt_wait_on_pinned_rqst(req); + spin_lock(&xprt->queue_lock); + clear_bit(RPC_TASK_MSG_PIN_WAIT, &task->tk_runstate); + } + spin_unlock(&xprt->queue_lock); + } +} + +/** * xprt_request_prepare - prepare an encoded request for transport * @req: pointer to rpc_rqst * @@ -1747,28 +1784,6 @@ void xprt_retry_reserve(struct rpc_task *task) xprt_do_reserve(xprt, task); } -static void -xprt_request_dequeue_all(struct rpc_task *task, struct rpc_rqst *req) -{ - struct rpc_xprt *xprt = req->rq_xprt; - - if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate) || - test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) || - xprt_is_pinned_rqst(req)) { - spin_lock(&xprt->queue_lock); - xprt_request_dequeue_transmit_locked(task); - xprt_request_dequeue_receive_locked(task); - while (xprt_is_pinned_rqst(req)) { - set_bit(RPC_TASK_MSG_PIN_WAIT, &task->tk_runstate); - spin_unlock(&xprt->queue_lock); - xprt_wait_on_pinned_rqst(req); - spin_lock(&xprt->queue_lock); - clear_bit(RPC_TASK_MSG_PIN_WAIT, &task->tk_runstate); - } - spin_unlock(&xprt->queue_lock); - } -} - /** * xprt_release - release an RPC request slot * @task: task which is finished with the slot @@ -1788,7 +1803,7 @@ void xprt_release(struct rpc_task *task) } xprt = req->rq_xprt; - xprt_request_dequeue_all(task, req); + xprt_request_dequeue_xprt(task); spin_lock(&xprt->transport_lock); xprt->ops->release_xprt(xprt, task); if (xprt->ops->release_request) diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 59e624b1d7a0..50e075fcdd8f 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -54,9 +54,7 @@ size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *xprt) unsigned int xprt_rdma_bc_max_slots(struct rpc_xprt *xprt) { - struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); - - return r_xprt->rx_buf.rb_bc_srv_max_requests; + return RPCRDMA_BACKWARD_WRS >> 1; } static int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 0b6dad7580a1..30065a28628c 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -7,67 +7,37 @@ /* Lightweight memory registration using Fast Registration Work * Requests (FRWR). * - * FRWR features ordered asynchronous registration and deregistration - * of arbitrarily sized memory regions. This is the fastest and safest + * FRWR features ordered asynchronous registration and invalidation + * of arbitrarily-sized memory regions. This is the fastest and safest * but most complex memory registration mode. */ /* Normal operation * - * A Memory Region is prepared for RDMA READ or WRITE using a FAST_REG + * A Memory Region is prepared for RDMA Read or Write using a FAST_REG * Work Request (frwr_map). When the RDMA operation is finished, this * Memory Region is invalidated using a LOCAL_INV Work Request - * (frwr_unmap_sync). + * (frwr_unmap_async and frwr_unmap_sync). * - * Typically these Work Requests are not signaled, and neither are RDMA - * SEND Work Requests (with the exception of signaling occasionally to - * prevent provider work queue overflows). This greatly reduces HCA + * Typically FAST_REG Work Requests are not signaled, and neither are + * RDMA Send Work Requests (with the exception of signaling occasionally + * to prevent provider work queue overflows). This greatly reduces HCA * interrupt workload. - * - * As an optimization, frwr_unmap marks MRs INVALID before the - * LOCAL_INV WR is posted. If posting succeeds, the MR is placed on - * rb_mrs immediately so that no work (like managing a linked list - * under a spinlock) is needed in the completion upcall. - * - * But this means that frwr_map() can occasionally encounter an MR - * that is INVALID but the LOCAL_INV WR has not completed. Work Queue - * ordering prevents a subsequent FAST_REG WR from executing against - * that MR while it is still being invalidated. */ /* Transport recovery * - * ->op_map and the transport connect worker cannot run at the same - * time, but ->op_unmap can fire while the transport connect worker - * is running. Thus MR recovery is handled in ->op_map, to guarantee - * that recovered MRs are owned by a sending RPC, and not one where - * ->op_unmap could fire at the same time transport reconnect is - * being done. - * - * When the underlying transport disconnects, MRs are left in one of - * four states: - * - * INVALID: The MR was not in use before the QP entered ERROR state. - * - * VALID: The MR was registered before the QP entered ERROR state. - * - * FLUSHED_FR: The MR was being registered when the QP entered ERROR - * state, and the pending WR was flushed. - * - * FLUSHED_LI: The MR was being invalidated when the QP entered ERROR - * state, and the pending WR was flushed. - * - * When frwr_map encounters FLUSHED and VALID MRs, they are recovered - * with ib_dereg_mr and then are re-initialized. Because MR recovery - * allocates fresh resources, it is deferred to a workqueue, and the - * recovered MRs are placed back on the rb_mrs list when recovery is - * complete. frwr_map allocates another MR for the current RPC while - * the broken MR is reset. - * - * To ensure that frwr_map doesn't encounter an MR that is marked - * INVALID but that is about to be flushed due to a previous transport - * disconnect, the transport connect worker attempts to drain all - * pending send queue WRs before the transport is reconnected. + * frwr_map and frwr_unmap_* cannot run at the same time the transport + * connect worker is running. The connect worker holds the transport + * send lock, just as ->send_request does. This prevents frwr_map and + * the connect worker from running concurrently. When a connection is + * closed, the Receive completion queue is drained before the allowing + * the connect worker to get control. This prevents frwr_unmap and the + * connect worker from running concurrently. + * + * When the underlying transport disconnects, MRs that are in flight + * are flushed and are likely unusable. Thus all flushed MRs are + * destroyed. New MRs are created on demand. */ #include <linux/sunrpc/rpc_rdma.h> @@ -118,15 +88,8 @@ void frwr_release_mr(struct rpcrdma_mr *mr) kfree(mr); } -/* MRs are dynamically allocated, so simply clean up and release the MR. - * A replacement MR will subsequently be allocated on demand. - */ -static void -frwr_mr_recycle_worker(struct work_struct *work) +static void frwr_mr_recycle(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) { - struct rpcrdma_mr *mr = container_of(work, struct rpcrdma_mr, mr_recycle); - struct rpcrdma_xprt *r_xprt = mr->mr_xprt; - trace_xprtrdma_mr_recycle(mr); if (mr->mr_dir != DMA_NONE) { @@ -136,14 +99,40 @@ frwr_mr_recycle_worker(struct work_struct *work) mr->mr_dir = DMA_NONE; } - spin_lock(&r_xprt->rx_buf.rb_mrlock); + spin_lock(&r_xprt->rx_buf.rb_lock); list_del(&mr->mr_all); r_xprt->rx_stats.mrs_recycled++; - spin_unlock(&r_xprt->rx_buf.rb_mrlock); + spin_unlock(&r_xprt->rx_buf.rb_lock); frwr_release_mr(mr); } +/* MRs are dynamically allocated, so simply clean up and release the MR. + * A replacement MR will subsequently be allocated on demand. + */ +static void +frwr_mr_recycle_worker(struct work_struct *work) +{ + struct rpcrdma_mr *mr = container_of(work, struct rpcrdma_mr, + mr_recycle); + + frwr_mr_recycle(mr->mr_xprt, mr); +} + +/* frwr_recycle - Discard MRs + * @req: request to reset + * + * Used after a reconnect. These MRs could be in flight, we can't + * tell. Safe thing to do is release them. + */ +void frwr_recycle(struct rpcrdma_req *req) +{ + struct rpcrdma_mr *mr; + + while ((mr = rpcrdma_mr_pop(&req->rl_registered))) + frwr_mr_recycle(mr->mr_xprt, mr); +} + /* frwr_reset - Place MRs back on the free list * @req: request to reset * @@ -156,12 +145,10 @@ frwr_mr_recycle_worker(struct work_struct *work) */ void frwr_reset(struct rpcrdma_req *req) { - while (!list_empty(&req->rl_registered)) { - struct rpcrdma_mr *mr; + struct rpcrdma_mr *mr; - mr = rpcrdma_mr_pop(&req->rl_registered); - rpcrdma_mr_unmap_and_put(mr); - } + while ((mr = rpcrdma_mr_pop(&req->rl_registered))) + rpcrdma_mr_put(mr); } /** @@ -179,11 +166,14 @@ int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) struct ib_mr *frmr; int rc; + /* NB: ib_alloc_mr and device drivers typically allocate + * memory with GFP_KERNEL. + */ frmr = ib_alloc_mr(ia->ri_pd, ia->ri_mrtype, depth); if (IS_ERR(frmr)) goto out_mr_err; - sg = kcalloc(depth, sizeof(*sg), GFP_KERNEL); + sg = kcalloc(depth, sizeof(*sg), GFP_NOFS); if (!sg) goto out_list_err; @@ -203,8 +193,6 @@ out_mr_err: return rc; out_list_err: - dprintk("RPC: %s: sg allocation failure\n", - __func__); ib_dereg_mr(frmr); return -ENOMEM; } @@ -290,8 +278,8 @@ int frwr_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep) ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS; ep->rep_attr.cap.max_recv_wr += 1; /* for ib_drain_rq */ - ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS / - ia->ri_max_frwr_depth); + ia->ri_max_segs = + DIV_ROUND_UP(RPCRDMA_MAX_DATA_SEGS, ia->ri_max_frwr_depth); /* Reply chunks require segments for head and tail buffers */ ia->ri_max_segs += 2; if (ia->ri_max_segs > RPCRDMA_MAX_HDR_SEGS) @@ -323,31 +311,25 @@ size_t frwr_maxpages(struct rpcrdma_xprt *r_xprt) * @nsegs: number of segments remaining * @writing: true when RDMA Write will be used * @xid: XID of RPC using the registered memory - * @out: initialized MR + * @mr: MR to fill in * * Prepare a REG_MR Work Request to register a memory region * for remote access via RDMA READ or RDMA WRITE. * * Returns the next segment or a negative errno pointer. - * On success, the prepared MR is planted in @out. + * On success, @mr is filled in. */ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, int nsegs, bool writing, __be32 xid, - struct rpcrdma_mr **out) + struct rpcrdma_mr *mr) { struct rpcrdma_ia *ia = &r_xprt->rx_ia; - bool holes_ok = ia->ri_mrtype == IB_MR_TYPE_SG_GAPS; - struct rpcrdma_mr *mr; - struct ib_mr *ibmr; struct ib_reg_wr *reg_wr; + struct ib_mr *ibmr; int i, n; u8 key; - mr = rpcrdma_mr_get(r_xprt); - if (!mr) - goto out_getmr_err; - if (nsegs > ia->ri_max_frwr_depth) nsegs = ia->ri_max_frwr_depth; for (i = 0; i < nsegs;) { @@ -362,7 +344,7 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, ++seg; ++i; - if (holes_ok) + if (ia->ri_mrtype == IB_MR_TYPE_SG_GAPS) continue; if ((i < nsegs && offset_in_page(seg->mr_offset)) || offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) @@ -397,22 +379,15 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, mr->mr_offset = ibmr->iova; trace_xprtrdma_mr_map(mr); - *out = mr; return seg; -out_getmr_err: - xprt_wait_for_buffer_space(&r_xprt->rx_xprt); - return ERR_PTR(-EAGAIN); - out_dmamap_err: mr->mr_dir = DMA_NONE; trace_xprtrdma_frwr_sgerr(mr, i); - rpcrdma_mr_put(mr); return ERR_PTR(-EIO); out_mapmr_err: trace_xprtrdma_frwr_maperr(mr, n); - rpcrdma_mr_recycle(mr); return ERR_PTR(-EIO); } @@ -485,7 +460,7 @@ void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) if (mr->mr_handle == rep->rr_inv_rkey) { list_del_init(&mr->mr_list); trace_xprtrdma_mr_remoteinv(mr); - rpcrdma_mr_unmap_and_put(mr); + rpcrdma_mr_put(mr); break; /* only one invalidated MR per RPC */ } } @@ -495,7 +470,7 @@ static void __frwr_release_mr(struct ib_wc *wc, struct rpcrdma_mr *mr) if (wc->status != IB_WC_SUCCESS) rpcrdma_mr_recycle(mr); else - rpcrdma_mr_unmap_and_put(mr); + rpcrdma_mr_put(mr); } /** @@ -532,8 +507,8 @@ static void frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) /* WARNING: Only wr_cqe and status are reliable at this point */ trace_xprtrdma_wc_li_wake(wc, frwr); - complete(&frwr->fr_linv_done); __frwr_release_mr(wc, mr); + complete(&frwr->fr_linv_done); } /** @@ -562,8 +537,7 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ frwr = NULL; prev = &first; - while (!list_empty(&req->rl_registered)) { - mr = rpcrdma_mr_pop(&req->rl_registered); + while ((mr = rpcrdma_mr_pop(&req->rl_registered))) { trace_xprtrdma_mr_localinv(mr); r_xprt->rx_stats.local_inv_needed++; @@ -632,11 +606,15 @@ static void frwr_wc_localinv_done(struct ib_cq *cq, struct ib_wc *wc) struct rpcrdma_frwr *frwr = container_of(cqe, struct rpcrdma_frwr, fr_cqe); struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr); + struct rpcrdma_rep *rep = mr->mr_req->rl_reply; /* WARNING: Only wr_cqe and status are reliable at this point */ trace_xprtrdma_wc_li_done(wc, frwr); - rpcrdma_complete_rqst(frwr->fr_req->rl_reply); __frwr_release_mr(wc, mr); + + /* Ensure @rep is generated before __frwr_release_mr */ + smp_rmb(); + rpcrdma_complete_rqst(rep); } /** @@ -662,15 +640,13 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ frwr = NULL; prev = &first; - while (!list_empty(&req->rl_registered)) { - mr = rpcrdma_mr_pop(&req->rl_registered); + while ((mr = rpcrdma_mr_pop(&req->rl_registered))) { trace_xprtrdma_mr_localinv(mr); r_xprt->rx_stats.local_inv_needed++; frwr = &mr->frwr; frwr->fr_cqe.done = frwr_wc_localinv; - frwr->fr_req = req; last = &frwr->fr_invwr; last->next = NULL; last->wr_cqe = &frwr->fr_cqe; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 4345e6912392..b86b5fd62d9f 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -342,6 +342,32 @@ encode_read_segment(struct xdr_stream *xdr, struct rpcrdma_mr *mr, return 0; } +static struct rpcrdma_mr_seg *rpcrdma_mr_prepare(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct rpcrdma_mr_seg *seg, + int nsegs, bool writing, + struct rpcrdma_mr **mr) +{ + *mr = rpcrdma_mr_pop(&req->rl_free_mrs); + if (!*mr) { + *mr = rpcrdma_mr_get(r_xprt); + if (!*mr) + goto out_getmr_err; + trace_xprtrdma_mr_get(req); + (*mr)->mr_req = req; + } + + rpcrdma_mr_push(*mr, &req->rl_registered); + return frwr_map(r_xprt, seg, nsegs, writing, req->rl_slot.rq_xid, *mr); + +out_getmr_err: + trace_xprtrdma_nomrs(req); + xprt_wait_for_buffer_space(&r_xprt->rx_xprt); + if (r_xprt->rx_ep.rep_connected != -ENODEV) + schedule_work(&r_xprt->rx_buf.rb_refresh_worker); + return ERR_PTR(-EAGAIN); +} + /* Register and XDR encode the Read list. Supports encoding a list of read * segments that belong to a single read chunk. * @@ -356,9 +382,10 @@ encode_read_segment(struct xdr_stream *xdr, struct rpcrdma_mr *mr, * * Only a single @pos value is currently supported. */ -static noinline int -rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, - struct rpc_rqst *rqst, enum rpcrdma_chunktype rtype) +static int rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct rpc_rqst *rqst, + enum rpcrdma_chunktype rtype) { struct xdr_stream *xdr = &req->rl_stream; struct rpcrdma_mr_seg *seg; @@ -379,10 +406,9 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, return nsegs; do { - seg = frwr_map(r_xprt, seg, nsegs, false, rqst->rq_xid, &mr); + seg = rpcrdma_mr_prepare(r_xprt, req, seg, nsegs, false, &mr); if (IS_ERR(seg)) return PTR_ERR(seg); - rpcrdma_mr_push(mr, &req->rl_registered); if (encode_read_segment(xdr, mr, pos) < 0) return -EMSGSIZE; @@ -411,9 +437,10 @@ done: * * Only a single Write chunk is currently supported. */ -static noinline int -rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, - struct rpc_rqst *rqst, enum rpcrdma_chunktype wtype) +static int rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct rpc_rqst *rqst, + enum rpcrdma_chunktype wtype) { struct xdr_stream *xdr = &req->rl_stream; struct rpcrdma_mr_seg *seg; @@ -440,10 +467,9 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, nchunks = 0; do { - seg = frwr_map(r_xprt, seg, nsegs, true, rqst->rq_xid, &mr); + seg = rpcrdma_mr_prepare(r_xprt, req, seg, nsegs, true, &mr); if (IS_ERR(seg)) return PTR_ERR(seg); - rpcrdma_mr_push(mr, &req->rl_registered); if (encode_rdma_segment(xdr, mr) < 0) return -EMSGSIZE; @@ -474,9 +500,10 @@ done: * Returns zero on success, or a negative errno if a failure occurred. * @xdr is advanced to the next position in the stream. */ -static noinline int -rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, - struct rpc_rqst *rqst, enum rpcrdma_chunktype wtype) +static int rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, + struct rpc_rqst *rqst, + enum rpcrdma_chunktype wtype) { struct xdr_stream *xdr = &req->rl_stream; struct rpcrdma_mr_seg *seg; @@ -501,10 +528,9 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, nchunks = 0; do { - seg = frwr_map(r_xprt, seg, nsegs, true, rqst->rq_xid, &mr); + seg = rpcrdma_mr_prepare(r_xprt, req, seg, nsegs, true, &mr); if (IS_ERR(seg)) return PTR_ERR(seg); - rpcrdma_mr_push(mr, &req->rl_registered); if (encode_rdma_segment(xdr, mr) < 0) return -EMSGSIZE; @@ -841,12 +867,7 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) * chunks. Very likely the connection has been replaced, * so these registrations are invalid and unusable. */ - while (unlikely(!list_empty(&req->rl_registered))) { - struct rpcrdma_mr *mr; - - mr = rpcrdma_mr_pop(&req->rl_registered); - rpcrdma_mr_recycle(mr); - } + frwr_recycle(req); /* This implementation supports the following combinations * of chunk lists in one RPC-over-RDMA Call message: @@ -1240,8 +1261,6 @@ void rpcrdma_complete_rqst(struct rpcrdma_rep *rep) struct rpc_rqst *rqst = rep->rr_rqst; int status; - xprt->reestablish_timeout = 0; - switch (rep->rr_proc) { case rdma_msg: status = rpcrdma_decode_msg(r_xprt, rep, rqst); @@ -1300,6 +1319,12 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) u32 credits; __be32 *p; + /* Any data means we had a useful conversation, so + * then we don't need to delay the next reconnect. + */ + if (xprt->reestablish_timeout) + xprt->reestablish_timeout = 0; + /* Fixed transport header fields */ xdr_init_decode(&rep->rr_stream, &rep->rr_hdrbuf, rep->rr_hdrbuf.head[0].iov_base, NULL); diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 2ec349ed4770..160558b4135e 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -423,8 +423,6 @@ void xprt_rdma_close(struct rpc_xprt *xprt) if (ep->rep_connected == -ENODEV) return; - if (ep->rep_connected > 0) - xprt->reestablish_timeout = 0; rpcrdma_ep_disconnect(ep, ia); /* Prepare @xprt for the next connection by reinitializing @@ -434,6 +432,7 @@ void xprt_rdma_close(struct rpc_xprt *xprt) xprt->cwnd = RPC_CWNDSHIFT; out: + xprt->reestablish_timeout = 0; ++xprt->connect_cookie; xprt_disconnect_done(xprt); } @@ -494,9 +493,9 @@ xprt_rdma_timer(struct rpc_xprt *xprt, struct rpc_task *task) * @reconnect_timeout: reconnect timeout after server disconnects * */ -static void xprt_rdma_tcp_set_connect_timeout(struct rpc_xprt *xprt, - unsigned long connect_timeout, - unsigned long reconnect_timeout) +static void xprt_rdma_set_connect_timeout(struct rpc_xprt *xprt, + unsigned long connect_timeout, + unsigned long reconnect_timeout) { struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); @@ -571,6 +570,7 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) return; out_sleep: + set_bit(XPRT_CONGESTED, &xprt->state); rpc_sleep_on(&xprt->backlog, task, NULL); task->tk_status = -EAGAIN; } @@ -589,7 +589,8 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst) memset(rqst, 0, sizeof(*rqst)); rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); - rpc_wake_up_next(&xprt->backlog); + if (unlikely(!rpc_wake_up_next(&xprt->backlog))) + clear_bit(XPRT_CONGESTED, &xprt->state); } static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt, @@ -803,7 +804,7 @@ static const struct rpc_xprt_ops xprt_rdma_procs = { .send_request = xprt_rdma_send_request, .close = xprt_rdma_close, .destroy = xprt_rdma_destroy, - .set_connect_timeout = xprt_rdma_tcp_set_connect_timeout, + .set_connect_timeout = xprt_rdma_set_connect_timeout, .print_stats = xprt_rdma_print_stats, .enable_swap = xprt_rdma_enable_swap, .disable_swap = xprt_rdma_disable_swap, diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index b10aa16557f0..3a907537e2cf 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -53,6 +53,7 @@ #include <linux/slab.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/svc_rdma.h> +#include <linux/log2.h> #include <asm-generic/barrier.h> #include <asm/bitops.h> @@ -74,8 +75,10 @@ * internal functions */ static void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc); +static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf); static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf); +static void rpcrdma_mr_free(struct rpcrdma_mr *mr); static struct rpcrdma_regbuf * rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction, gfp_t flags); @@ -405,9 +408,8 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) struct rpcrdma_ep *ep = &r_xprt->rx_ep; struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_req *req; - struct rpcrdma_rep *rep; - cancel_delayed_work_sync(&buf->rb_refresh_worker); + cancel_work_sync(&buf->rb_refresh_worker); /* This is similar to rpcrdma_ep_destroy, but: * - Don't cancel the connect worker. @@ -429,8 +431,7 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) /* The ULP is responsible for ensuring all DMA * mappings and MRs are gone. */ - list_for_each_entry(rep, &buf->rb_recv_bufs, rr_list) - rpcrdma_regbuf_dma_unmap(rep->rr_rdmabuf); + rpcrdma_reps_destroy(buf); list_for_each_entry(req, &buf->rb_allreqs, rl_all) { rpcrdma_regbuf_dma_unmap(req->rl_rdmabuf); rpcrdma_regbuf_dma_unmap(req->rl_sendbuf); @@ -604,10 +605,10 @@ void rpcrdma_ep_destroy(struct rpcrdma_xprt *r_xprt) * Unlike a normal reconnection, a fresh PD and a new set * of MRs and buffers is needed. */ -static int -rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, - struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) +static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, + struct ib_qp_init_attr *qp_init_attr) { + struct rpcrdma_ia *ia = &r_xprt->rx_ia; int rc, err; trace_xprtrdma_reinsert(r_xprt); @@ -624,7 +625,7 @@ rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, } rc = -ENETUNREACH; - err = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr); + err = rdma_create_qp(ia->ri_id, ia->ri_pd, qp_init_attr); if (err) { pr_err("rpcrdma: rdma_create_qp returned %d\n", err); goto out3; @@ -641,16 +642,16 @@ out1: return rc; } -static int -rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, struct rpcrdma_ep *ep, - struct rpcrdma_ia *ia) +static int rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, + struct ib_qp_init_attr *qp_init_attr) { + struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rdma_cm_id *id, *old; int err, rc; trace_xprtrdma_reconnect(r_xprt); - rpcrdma_ep_disconnect(ep, ia); + rpcrdma_ep_disconnect(&r_xprt->rx_ep, ia); rc = -EHOSTUNREACH; id = rpcrdma_create_id(r_xprt, ia); @@ -672,7 +673,7 @@ rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, struct rpcrdma_ep *ep, goto out_destroy; } - err = rdma_create_qp(id, ia->ri_pd, &ep->rep_attr); + err = rdma_create_qp(id, ia->ri_pd, qp_init_attr); if (err) goto out_destroy; @@ -697,25 +698,27 @@ rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) struct rpcrdma_xprt *r_xprt = container_of(ia, struct rpcrdma_xprt, rx_ia); struct rpc_xprt *xprt = &r_xprt->rx_xprt; + struct ib_qp_init_attr qp_init_attr; int rc; retry: + memcpy(&qp_init_attr, &ep->rep_attr, sizeof(qp_init_attr)); switch (ep->rep_connected) { case 0: dprintk("RPC: %s: connecting...\n", __func__); - rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr); + rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &qp_init_attr); if (rc) { rc = -ENETUNREACH; goto out_noupdate; } break; case -ENODEV: - rc = rpcrdma_ep_recreate_xprt(r_xprt, ep, ia); + rc = rpcrdma_ep_recreate_xprt(r_xprt, &qp_init_attr); if (rc) goto out_noupdate; break; default: - rc = rpcrdma_ep_reconnect(r_xprt, ep, ia); + rc = rpcrdma_ep_reconnect(r_xprt, &qp_init_attr); if (rc) goto out; } @@ -729,6 +732,8 @@ retry: if (rc) goto out; + if (xprt->reestablish_timeout < RPCRDMA_INIT_REEST_TO) + xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO; wait_event_interruptible(ep->rep_connect_wait, ep->rep_connected != 0); if (ep->rep_connected <= 0) { if (ep->rep_connected == -EAGAIN) @@ -942,14 +947,12 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt) struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_ia *ia = &r_xprt->rx_ia; unsigned int count; - LIST_HEAD(free); - LIST_HEAD(all); for (count = 0; count < ia->ri_max_segs; count++) { struct rpcrdma_mr *mr; int rc; - mr = kzalloc(sizeof(*mr), GFP_KERNEL); + mr = kzalloc(sizeof(*mr), GFP_NOFS); if (!mr) break; @@ -961,15 +964,13 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt) mr->mr_xprt = r_xprt; - list_add(&mr->mr_list, &free); - list_add(&mr->mr_all, &all); + spin_lock(&buf->rb_lock); + list_add(&mr->mr_list, &buf->rb_mrs); + list_add(&mr->mr_all, &buf->rb_all_mrs); + spin_unlock(&buf->rb_lock); } - spin_lock(&buf->rb_mrlock); - list_splice(&free, &buf->rb_mrs); - list_splice(&all, &buf->rb_all); r_xprt->rx_stats.mrs_allocated += count; - spin_unlock(&buf->rb_mrlock); trace_xprtrdma_createmrs(r_xprt, count); } @@ -977,7 +978,7 @@ static void rpcrdma_mr_refresh_worker(struct work_struct *work) { struct rpcrdma_buffer *buf = container_of(work, struct rpcrdma_buffer, - rb_refresh_worker.work); + rb_refresh_worker); struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt, rx_buf); @@ -999,12 +1000,18 @@ struct rpcrdma_req *rpcrdma_req_create(struct rpcrdma_xprt *r_xprt, size_t size, struct rpcrdma_buffer *buffer = &r_xprt->rx_buf; struct rpcrdma_regbuf *rb; struct rpcrdma_req *req; + size_t maxhdrsize; req = kzalloc(sizeof(*req), flags); if (req == NULL) goto out1; - rb = rpcrdma_regbuf_alloc(RPCRDMA_HDRBUF_SIZE, DMA_TO_DEVICE, flags); + /* Compute maximum header buffer size in bytes */ + maxhdrsize = rpcrdma_fixed_maxsz + 3 + + r_xprt->rx_ia.ri_max_segs * rpcrdma_readchunk_maxsz; + maxhdrsize *= sizeof(__be32); + rb = rpcrdma_regbuf_alloc(__roundup_pow_of_two(maxhdrsize), + DMA_TO_DEVICE, flags); if (!rb) goto out2; req->rl_rdmabuf = rb; @@ -1018,6 +1025,7 @@ struct rpcrdma_req *rpcrdma_req_create(struct rpcrdma_xprt *r_xprt, size_t size, if (!req->rl_recvbuf) goto out4; + INIT_LIST_HEAD(&req->rl_free_mrs); INIT_LIST_HEAD(&req->rl_registered); spin_lock(&buffer->rb_lock); list_add(&req->rl_all, &buffer->rb_allreqs); @@ -1065,6 +1073,40 @@ out: return NULL; } +static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep) +{ + rpcrdma_regbuf_free(rep->rr_rdmabuf); + kfree(rep); +} + +static struct rpcrdma_rep *rpcrdma_rep_get_locked(struct rpcrdma_buffer *buf) +{ + struct llist_node *node; + + /* Calls to llist_del_first are required to be serialized */ + node = llist_del_first(&buf->rb_free_reps); + if (!node) + return NULL; + return llist_entry(node, struct rpcrdma_rep, rr_node); +} + +static void rpcrdma_rep_put(struct rpcrdma_buffer *buf, + struct rpcrdma_rep *rep) +{ + if (!rep->rr_temp) + llist_add(&rep->rr_node, &buf->rb_free_reps); + else + rpcrdma_rep_destroy(rep); +} + +static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf) +{ + struct rpcrdma_rep *rep; + + while ((rep = rpcrdma_rep_get_locked(buf)) != NULL) + rpcrdma_rep_destroy(rep); +} + /** * rpcrdma_buffer_create - Create initial set of req/rep objects * @r_xprt: transport instance to (re)initialize @@ -1078,12 +1120,10 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) buf->rb_max_requests = r_xprt->rx_ep.rep_max_requests; buf->rb_bc_srv_max_requests = 0; - spin_lock_init(&buf->rb_mrlock); spin_lock_init(&buf->rb_lock); INIT_LIST_HEAD(&buf->rb_mrs); - INIT_LIST_HEAD(&buf->rb_all); - INIT_DELAYED_WORK(&buf->rb_refresh_worker, - rpcrdma_mr_refresh_worker); + INIT_LIST_HEAD(&buf->rb_all_mrs); + INIT_WORK(&buf->rb_refresh_worker, rpcrdma_mr_refresh_worker); rpcrdma_mrs_create(r_xprt); @@ -1102,7 +1142,7 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) } buf->rb_credits = 1; - INIT_LIST_HEAD(&buf->rb_recv_bufs); + init_llist_head(&buf->rb_free_reps); rc = rpcrdma_sendctxs_create(r_xprt); if (rc) @@ -1114,12 +1154,6 @@ out: return rc; } -static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep) -{ - rpcrdma_regbuf_free(rep->rr_rdmabuf); - kfree(rep); -} - /** * rpcrdma_req_destroy - Destroy an rpcrdma_req object * @req: unused object to be destroyed @@ -1127,11 +1161,13 @@ static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep) * This function assumes that the caller prevents concurrent device * unload and transport tear-down. */ -void -rpcrdma_req_destroy(struct rpcrdma_req *req) +void rpcrdma_req_destroy(struct rpcrdma_req *req) { list_del(&req->rl_all); + while (!list_empty(&req->rl_free_mrs)) + rpcrdma_mr_free(rpcrdma_mr_pop(&req->rl_free_mrs)); + rpcrdma_regbuf_free(req->rl_recvbuf); rpcrdma_regbuf_free(req->rl_sendbuf); rpcrdma_regbuf_free(req->rl_rdmabuf); @@ -1147,25 +1183,19 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) unsigned int count; count = 0; - spin_lock(&buf->rb_mrlock); - while (!list_empty(&buf->rb_all)) { - mr = list_entry(buf->rb_all.next, struct rpcrdma_mr, mr_all); + spin_lock(&buf->rb_lock); + while ((mr = list_first_entry_or_null(&buf->rb_all_mrs, + struct rpcrdma_mr, + mr_all)) != NULL) { list_del(&mr->mr_all); - - spin_unlock(&buf->rb_mrlock); - - /* Ensure MW is not on any rl_registered list */ - if (!list_empty(&mr->mr_list)) - list_del(&mr->mr_list); + spin_unlock(&buf->rb_lock); frwr_release_mr(mr); count++; - spin_lock(&buf->rb_mrlock); + spin_lock(&buf->rb_lock); } - spin_unlock(&buf->rb_mrlock); + spin_unlock(&buf->rb_lock); r_xprt->rx_stats.mrs_allocated = 0; - - dprintk("RPC: %s: released %u MRs\n", __func__, count); } /** @@ -1179,18 +1209,10 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) void rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) { - cancel_delayed_work_sync(&buf->rb_refresh_worker); + cancel_work_sync(&buf->rb_refresh_worker); rpcrdma_sendctxs_destroy(buf); - - while (!list_empty(&buf->rb_recv_bufs)) { - struct rpcrdma_rep *rep; - - rep = list_first_entry(&buf->rb_recv_bufs, - struct rpcrdma_rep, rr_list); - list_del(&rep->rr_list); - rpcrdma_rep_destroy(rep); - } + rpcrdma_reps_destroy(buf); while (!list_empty(&buf->rb_send_bufs)) { struct rpcrdma_req *req; @@ -1215,54 +1237,20 @@ struct rpcrdma_mr * rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct rpcrdma_mr *mr = NULL; - - spin_lock(&buf->rb_mrlock); - if (!list_empty(&buf->rb_mrs)) - mr = rpcrdma_mr_pop(&buf->rb_mrs); - spin_unlock(&buf->rb_mrlock); + struct rpcrdma_mr *mr; - if (!mr) - goto out_nomrs; + spin_lock(&buf->rb_lock); + mr = rpcrdma_mr_pop(&buf->rb_mrs); + spin_unlock(&buf->rb_lock); return mr; - -out_nomrs: - trace_xprtrdma_nomrs(r_xprt); - if (r_xprt->rx_ep.rep_connected != -ENODEV) - schedule_delayed_work(&buf->rb_refresh_worker, 0); - - /* Allow the reply handler and refresh worker to run */ - cond_resched(); - - return NULL; -} - -static void -__rpcrdma_mr_put(struct rpcrdma_buffer *buf, struct rpcrdma_mr *mr) -{ - spin_lock(&buf->rb_mrlock); - rpcrdma_mr_push(mr, &buf->rb_mrs); - spin_unlock(&buf->rb_mrlock); -} - -/** - * rpcrdma_mr_put - Release an rpcrdma_mr object - * @mr: object to release - * - */ -void -rpcrdma_mr_put(struct rpcrdma_mr *mr) -{ - __rpcrdma_mr_put(&mr->mr_xprt->rx_buf, mr); } /** - * rpcrdma_mr_unmap_and_put - DMA unmap an MR and release it - * @mr: object to release + * rpcrdma_mr_put - DMA unmap an MR and release it + * @mr: MR to release * */ -void -rpcrdma_mr_unmap_and_put(struct rpcrdma_mr *mr) +void rpcrdma_mr_put(struct rpcrdma_mr *mr) { struct rpcrdma_xprt *r_xprt = mr->mr_xprt; @@ -1272,7 +1260,19 @@ rpcrdma_mr_unmap_and_put(struct rpcrdma_mr *mr) mr->mr_sg, mr->mr_nents, mr->mr_dir); mr->mr_dir = DMA_NONE; } - __rpcrdma_mr_put(&r_xprt->rx_buf, mr); + + rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs); +} + +static void rpcrdma_mr_free(struct rpcrdma_mr *mr) +{ + struct rpcrdma_xprt *r_xprt = mr->mr_xprt; + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + + mr->mr_req = NULL; + spin_lock(&buf->rb_lock); + rpcrdma_mr_push(mr, &buf->rb_mrs); + spin_unlock(&buf->rb_lock); } /** @@ -1303,39 +1303,24 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) */ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) { - struct rpcrdma_rep *rep = req->rl_reply; - + if (req->rl_reply) + rpcrdma_rep_put(buffers, req->rl_reply); req->rl_reply = NULL; spin_lock(&buffers->rb_lock); list_add(&req->rl_list, &buffers->rb_send_bufs); - if (rep) { - if (!rep->rr_temp) { - list_add(&rep->rr_list, &buffers->rb_recv_bufs); - rep = NULL; - } - } spin_unlock(&buffers->rb_lock); - if (rep) - rpcrdma_rep_destroy(rep); } -/* - * Put reply buffers back into pool when not attached to - * request. This happens in error conditions. +/** + * rpcrdma_recv_buffer_put - Release rpcrdma_rep back to free list + * @rep: rep to release + * + * Used after error conditions. */ -void -rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep) +void rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep) { - struct rpcrdma_buffer *buffers = &rep->rr_rxprt->rx_buf; - - if (!rep->rr_temp) { - spin_lock(&buffers->rb_lock); - list_add(&rep->rr_list, &buffers->rb_recv_bufs); - spin_unlock(&buffers->rb_lock); - } else { - rpcrdma_rep_destroy(rep); - } + rpcrdma_rep_put(&rep->rr_rxprt->rx_buf, rep); } /* Returns a pointer to a rpcrdma_regbuf object, or NULL. @@ -1483,7 +1468,7 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) count = 0; needed = buf->rb_credits + (buf->rb_bc_srv_max_requests << 1); - if (ep->rep_receive_count > needed) + if (likely(ep->rep_receive_count > needed)) goto out; needed -= ep->rep_receive_count; if (!temp) @@ -1491,22 +1476,10 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) /* fast path: all needed reps can be found on the free list */ wr = NULL; - spin_lock(&buf->rb_lock); while (needed) { - rep = list_first_entry_or_null(&buf->rb_recv_bufs, - struct rpcrdma_rep, rr_list); + rep = rpcrdma_rep_get_locked(buf); if (!rep) - break; - - list_del(&rep->rr_list); - rep->rr_recv_wr.next = wr; - wr = &rep->rr_recv_wr; - --needed; - } - spin_unlock(&buf->rb_lock); - - while (needed) { - rep = rpcrdma_rep_create(r_xprt, temp); + rep = rpcrdma_rep_create(r_xprt, temp); if (!rep) break; @@ -1523,7 +1496,7 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) goto release_wrs; - trace_xprtrdma_post_recv(rep->rr_recv_wr.wr_cqe); + trace_xprtrdma_post_recv(rep); ++count; } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 92ce09fcea74..65e6b0eb862e 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -47,6 +47,7 @@ #include <linux/atomic.h> /* atomic_t, etc */ #include <linux/kref.h> /* struct kref */ #include <linux/workqueue.h> /* struct work_struct */ +#include <linux/llist.h> #include <rdma/rdma_cm.h> /* RDMA connection api */ #include <rdma/ib_verbs.h> /* RDMA verbs api */ @@ -117,9 +118,6 @@ struct rpcrdma_ep { #endif /* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV - * - * The below structure appears at the front of a large region of kmalloc'd - * memory, which always starts on a good alignment boundary. */ struct rpcrdma_regbuf { @@ -158,25 +156,22 @@ static inline void *rdmab_data(const struct rpcrdma_regbuf *rb) /* To ensure a transport can always make forward progress, * the number of RDMA segments allowed in header chunk lists - * is capped at 8. This prevents less-capable devices and - * memory registrations from overrunning the Send buffer - * while building chunk lists. + * is capped at 16. This prevents less-capable devices from + * overrunning the Send buffer while building chunk lists. * * Elements of the Read list take up more room than the - * Write list or Reply chunk. 8 read segments means the Read - * list (or Write list or Reply chunk) cannot consume more - * than - * - * ((8 + 2) * read segment size) + 1 XDR words, or 244 bytes. + * Write list or Reply chunk. 16 read segments means the + * chunk lists cannot consume more than * - * And the fixed part of the header is another 24 bytes. + * ((16 + 2) * read segment size) + 1 XDR words, * - * The smallest inline threshold is 1024 bytes, ensuring that - * at least 750 bytes are available for RPC messages. + * or about 400 bytes. The fixed part of the header is + * another 24 bytes. Thus when the inline threshold is + * 1024 bytes, at least 600 bytes are available for RPC + * message bodies. */ enum { - RPCRDMA_MAX_HDR_SEGS = 8, - RPCRDMA_HDRBUF_SIZE = 256, + RPCRDMA_MAX_HDR_SEGS = 16, }; /* @@ -206,7 +201,7 @@ struct rpcrdma_rep { struct rpc_rqst *rr_rqst; struct xdr_buf rr_hdrbuf; struct xdr_stream rr_stream; - struct list_head rr_list; + struct llist_node rr_node; struct ib_recv_wr rr_recv_wr; }; @@ -240,20 +235,20 @@ struct rpcrdma_sendctx { * An external memory region is any buffer or page that is registered * on the fly (ie, not pre-registered). */ -struct rpcrdma_req; struct rpcrdma_frwr { struct ib_mr *fr_mr; struct ib_cqe fr_cqe; struct completion fr_linv_done; - struct rpcrdma_req *fr_req; union { struct ib_reg_wr fr_regwr; struct ib_send_wr fr_invwr; }; }; +struct rpcrdma_req; struct rpcrdma_mr { struct list_head mr_list; + struct rpcrdma_req *mr_req; struct scatterlist *mr_sg; int mr_nents; enum dma_data_direction mr_dir; @@ -331,7 +326,8 @@ struct rpcrdma_req { struct list_head rl_all; struct kref rl_kref; - struct list_head rl_registered; /* registered segments */ + struct list_head rl_free_mrs; + struct list_head rl_registered; struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; }; @@ -344,7 +340,7 @@ rpcr_to_rdmar(const struct rpc_rqst *rqst) static inline void rpcrdma_mr_push(struct rpcrdma_mr *mr, struct list_head *list) { - list_add_tail(&mr->mr_list, list); + list_add(&mr->mr_list, list); } static inline struct rpcrdma_mr * @@ -352,8 +348,9 @@ rpcrdma_mr_pop(struct list_head *list) { struct rpcrdma_mr *mr; - mr = list_first_entry(list, struct rpcrdma_mr, mr_list); - list_del_init(&mr->mr_list); + mr = list_first_entry_or_null(list, struct rpcrdma_mr, mr_list); + if (mr) + list_del_init(&mr->mr_list); return mr; } @@ -364,19 +361,19 @@ rpcrdma_mr_pop(struct list_head *list) * One of these is associated with a transport instance */ struct rpcrdma_buffer { - spinlock_t rb_mrlock; /* protect rb_mrs list */ + spinlock_t rb_lock; + struct list_head rb_send_bufs; struct list_head rb_mrs; - struct list_head rb_all; unsigned long rb_sc_head; unsigned long rb_sc_tail; unsigned long rb_sc_last; struct rpcrdma_sendctx **rb_sc_ctxs; - spinlock_t rb_lock; /* protect buf lists */ - struct list_head rb_send_bufs; - struct list_head rb_recv_bufs; struct list_head rb_allreqs; + struct list_head rb_all_mrs; + + struct llist_head rb_free_reps; u32 rb_max_requests; u32 rb_credits; /* most recent credit grant */ @@ -384,7 +381,7 @@ struct rpcrdma_buffer { u32 rb_bc_srv_max_requests; u32 rb_bc_max_requests; - struct delayed_work rb_refresh_worker; + struct work_struct rb_refresh_worker; }; /* @@ -490,7 +487,6 @@ struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_xprt *r_xprt); struct rpcrdma_mr *rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt); void rpcrdma_mr_put(struct rpcrdma_mr *mr); -void rpcrdma_mr_unmap_and_put(struct rpcrdma_mr *mr); static inline void rpcrdma_mr_recycle(struct rpcrdma_mr *mr) @@ -546,6 +542,7 @@ rpcrdma_data_dir(bool writing) /* Memory registration calls xprtrdma/frwr_ops.c */ bool frwr_is_supported(struct ib_device *device); +void frwr_recycle(struct rpcrdma_req *req); void frwr_reset(struct rpcrdma_req *req); int frwr_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep); int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr); @@ -554,7 +551,7 @@ size_t frwr_maxpages(struct rpcrdma_xprt *r_xprt); struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, int nsegs, bool writing, __be32 xid, - struct rpcrdma_mr **mr); + struct rpcrdma_mr *mr); int frwr_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req); void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs); void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e2176c167a57..9ac88722fa83 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -562,10 +562,14 @@ xs_read_stream_call(struct sock_xprt *transport, struct msghdr *msg, int flags) printk(KERN_WARNING "Callback slot table overflowed\n"); return -ESHUTDOWN; } + if (transport->recv.copied && !req->rq_private_buf.len) + return -ESHUTDOWN; ret = xs_read_stream_request(transport, msg, flags, req); if (msg->msg_flags & (MSG_EOR|MSG_TRUNC)) xprt_complete_bc_request(req, transport->recv.copied); + else + req->rq_private_buf.len = transport->recv.copied; return ret; } @@ -587,7 +591,7 @@ xs_read_stream_reply(struct sock_xprt *transport, struct msghdr *msg, int flags) /* Look up and lock the request corresponding to the given XID */ spin_lock(&xprt->queue_lock); req = xprt_lookup_rqst(xprt, transport->recv.xid); - if (!req) { + if (!req || (transport->recv.copied && !req->rq_private_buf.len)) { msg->msg_flags |= MSG_TRUNC; goto out; } @@ -599,6 +603,8 @@ xs_read_stream_reply(struct sock_xprt *transport, struct msghdr *msg, int flags) spin_lock(&xprt->queue_lock); if (msg->msg_flags & (MSG_EOR|MSG_TRUNC)) xprt_complete_rqst(req->rq_task, transport->recv.copied); + else + req->rq_private_buf.len = transport->recv.copied; xprt_unpin_rqst(req); out: spin_unlock(&xprt->queue_lock); diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 93a7edfe0f05..6fcc66afb088 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -62,6 +62,8 @@ my $conststructsfile = "$D/const_structs.checkpatch"; my $typedefsfile = ""; my $color = "auto"; my $allow_c99_comments = 1; # Can be overridden by --ignore C99_COMMENT_TOLERANCE +# git output parsing needs US English output, so first set backtick child process LANGUAGE +my $git_command ='export LANGUAGE=en_US.UTF-8; git'; sub help { my ($exitcode) = @_; @@ -904,7 +906,7 @@ sub seed_camelcase_includes { $camelcase_seeded = 1; if (-e ".git") { - my $git_last_include_commit = `git log --no-merges --pretty=format:"%h%n" -1 -- include`; + my $git_last_include_commit = `${git_command} log --no-merges --pretty=format:"%h%n" -1 -- include`; chomp $git_last_include_commit; $camelcase_cache = ".checkpatch-camelcase.git.$git_last_include_commit"; } else { @@ -932,7 +934,7 @@ sub seed_camelcase_includes { } if (-e ".git") { - $files = `git ls-files "include/*.h"`; + $files = `${git_command} ls-files "include/*.h"`; @include_files = split('\n', $files); } @@ -956,13 +958,13 @@ sub git_commit_info { return ($id, $desc) if ((which("git") eq "") || !(-e ".git")); - my $output = `git log --no-color --format='%H %s' -1 $commit 2>&1`; + my $output = `${git_command} log --no-color --format='%H %s' -1 $commit 2>&1`; $output =~ s/^\s*//gm; my @lines = split("\n", $output); return ($id, $desc) if ($#lines < 0); - if ($lines[0] =~ /^error: short SHA1 $commit is ambiguous\./) { + if ($lines[0] =~ /^error: short SHA1 $commit is ambiguous/) { # Maybe one day convert this block of bash into something that returns # all matching commit ids, but it's very slow... # @@ -1006,7 +1008,7 @@ if ($git) { } else { $git_range = "-1 $commit_expr"; } - my $lines = `git log --no-color --no-merges --pretty=format:'%H %s' $git_range`; + my $lines = `${git_command} log --no-color --no-merges --pretty=format:'%H %s' $git_range`; foreach my $line (split(/\n/, $lines)) { $line =~ /^([0-9a-fA-F]{40,40}) (.*)$/; next if (!defined($1) || !defined($2)); @@ -2725,8 +2727,10 @@ sub process { ($line =~ /^\s*(?:WARNING:|BUG:)/ || $line =~ /^\s*\[\s*\d+\.\d{6,6}\s*\]/ || # timestamp - $line =~ /^\s*\[\<[0-9a-fA-F]{8,}\>\]/)) { - # stack dump address + $line =~ /^\s*\[\<[0-9a-fA-F]{8,}\>\]/) || + $line =~ /^(?:\s+\w+:\s+[0-9a-fA-F]+){3,3}/ || + $line =~ /^\s*\#\d+\s*\[[0-9a-fA-F]+\]\s*\w+ at [0-9a-fA-F]+/) { + # stack dump address styles $commit_log_possible_stack_dump = 1; } @@ -2898,6 +2902,17 @@ sub process { } } +# check for invalid commit id + if ($in_commit_log && $line =~ /(^fixes:|\bcommit)\s+([0-9a-f]{6,40})\b/i) { + my $id; + my $description; + ($id, $description) = git_commit_info($2, undef, undef); + if (!defined($id)) { + WARN("UNKNOWN_COMMIT_ID", + "Unknown commit id '$2', maybe rebased or not pulled?\n" . $herecurr); + } + } + # ignore non-hunk lines and lines being removed next if (!$hunk_line || $line =~ /^-/); @@ -3069,21 +3084,21 @@ sub process { # check SPDX comment style for .[chsS] files if ($realfile =~ /\.[chsS]$/ && $rawline =~ /SPDX-License-Identifier:/ && - $rawline !~ /^\+\s*\Q$comment\E\s*/) { + $rawline !~ m@^\+\s*\Q$comment\E\s*@) { WARN("SPDX_LICENSE_TAG", "Improper SPDX comment style for '$realfile', please use '$comment' instead\n" . $herecurr); } if ($comment !~ /^$/ && - $rawline !~ /^\+\Q$comment\E SPDX-License-Identifier: /) { - WARN("SPDX_LICENSE_TAG", - "Missing or malformed SPDX-License-Identifier tag in line $checklicenseline\n" . $herecurr); + $rawline !~ m@^\+\Q$comment\E SPDX-License-Identifier: @) { + WARN("SPDX_LICENSE_TAG", + "Missing or malformed SPDX-License-Identifier tag in line $checklicenseline\n" . $herecurr); } elsif ($rawline =~ /(SPDX-License-Identifier: .*)/) { - my $spdx_license = $1; - if (!is_SPDX_License_valid($spdx_license)) { - WARN("SPDX_LICENSE_TAG", - "'$spdx_license' is not supported in LICENSES/...\n" . $herecurr); - } + my $spdx_license = $1; + if (!is_SPDX_License_valid($spdx_license)) { + WARN("SPDX_LICENSE_TAG", + "'$spdx_license' is not supported in LICENSES/...\n" . $herecurr); + } } } } @@ -4660,7 +4675,7 @@ sub process { # closing brace should have a space following it when it has anything # on the line - if ($line =~ /}(?!(?:,|;|\)))\S/) { + if ($line =~ /}(?!(?:,|;|\)|\}))\S/) { if (ERROR("SPACING", "space required after that close brace '}'\n" . $herecurr) && $fix) { @@ -5191,7 +5206,7 @@ sub process { next if ($arg =~ /\.\.\./); next if ($arg =~ /^type$/i); my $tmp_stmt = $define_stmt; - $tmp_stmt =~ s/\b(typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; + $tmp_stmt =~ s/\b(sizeof|typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; $tmp_stmt =~ s/\#+\s*$arg\b//g; $tmp_stmt =~ s/\b$arg\s*\#\#//g; my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g; @@ -5873,6 +5888,18 @@ sub process { "__aligned(size) is preferred over __attribute__((aligned(size)))\n" . $herecurr); } +# Check for __attribute__ section, prefer __section + if ($realfile !~ m@\binclude/uapi/@ && + $line =~ /\b__attribute__\s*\(\s*\(.*_*section_*\s*\(\s*("[^"]*")/) { + my $old = substr($rawline, $-[1], $+[1] - $-[1]); + my $new = substr($old, 1, -1); + if (WARN("PREFER_SECTION", + "__section($new) is preferred over __attribute__((section($old)))\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*_*section_*\s*\(\s*\Q$old\E\s*\)\s*\)\s*\)/__section($new)/; + } + } + # Check for __attribute__ format(printf, prefer __printf if ($realfile !~ m@\binclude/uapi/@ && $line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf/) { @@ -6480,6 +6507,12 @@ sub process { "Using $1 should generally have parentheses around the comparison\n" . $herecurr); } +# nested likely/unlikely calls + if ($line =~ /\b(?:(?:un)?likely)\s*\(\s*!?\s*(IS_ERR(?:_OR_NULL|_VALUE)?|WARN)/) { + WARN("LIKELY_MISUSE", + "nested (un)?likely() calls, $1 already uses unlikely() internally\n" . $herecurr); + } + # whine mightly about in_atomic if ($line =~ /\bin_atomic\s*\(/) { if ($realfile =~ m@^drivers/@) { diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 2f5b95f09fa0..34e40e96dee2 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -77,12 +77,12 @@ lx-symbols command.""" gdb.write("scanning for modules in {0}\n".format(path)) for root, dirs, files in os.walk(path): for name in files: - if name.endswith(".ko"): + if name.endswith(".ko") or name.endswith(".ko.debug"): self.module_files.append(root + "/" + name) self.module_files_updated = True def _get_module_file(self, module_name): - module_pattern = ".*/{0}\.ko$".format( + module_pattern = ".*/{0}\.ko(?:.debug)?$".format( module_name.replace("_", r"[_\-]")) for name in self.module_files: if re.match(module_pattern, name) and os.path.exists(name): diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 5171b9c7ca3e..0652d3eed9bd 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -231,6 +231,8 @@ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ +#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ +#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -354,6 +356,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ diff --git a/tools/arch/x86/include/uapi/asm/unistd.h b/tools/arch/x86/include/uapi/asm/unistd.h index 30d7d04d72d6..196fdd02b8b1 100644 --- a/tools/arch/x86/include/uapi/asm/unistd.h +++ b/tools/arch/x86/include/uapi/asm/unistd.h @@ -3,7 +3,7 @@ #define _UAPI_ASM_X86_UNISTD_H /* x32 syscall flag bit */ -#define __X32_SYSCALL_BIT 0x40000000 +#define __X32_SYSCALL_BIT 0x40000000UL #ifndef __KERNEL__ # ifdef __i386__ diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h index bbd75ac8b202..550223f0a6e6 100644 --- a/tools/include/asm/bug.h +++ b/tools/include/asm/bug.h @@ -3,6 +3,7 @@ #define _TOOLS_ASM_BUG_H #include <linux/compiler.h> +#include <stdio.h> #define __WARN_printf(arg...) do { fprintf(stderr, arg); } while (0) diff --git a/tools/include/linux/rbtree.h b/tools/include/linux/rbtree.h index d83763a5327c..e03b1ea23e0e 100644 --- a/tools/include/linux/rbtree.h +++ b/tools/include/linux/rbtree.h @@ -31,25 +31,9 @@ struct rb_root { struct rb_node *rb_node; }; -/* - * Leftmost-cached rbtrees. - * - * We do not cache the rightmost node based on footprint - * size vs number of potential users that could benefit - * from O(1) rb_last(). Just not worth it, users that want - * this feature can always implement the logic explicitly. - * Furthermore, users that want to cache both pointers may - * find it a bit asymmetric, but that's ok. - */ -struct rb_root_cached { - struct rb_root rb_root; - struct rb_node *rb_leftmost; -}; - #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define RB_ROOT (struct rb_root) { NULL, } -#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) @@ -71,12 +55,6 @@ extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); -extern void rb_insert_color_cached(struct rb_node *, - struct rb_root_cached *, bool); -extern void rb_erase_cached(struct rb_node *node, struct rb_root_cached *); -/* Same as rb_first(), but O(1) */ -#define rb_first_cached(root) (root)->rb_leftmost - /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); @@ -84,8 +62,6 @@ extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); -extern void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, - struct rb_root_cached *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) @@ -129,4 +105,51 @@ static inline void rb_erase_init(struct rb_node *n, struct rb_root *root) rb_erase(n, root); RB_CLEAR_NODE(n); } + +/* + * Leftmost-cached rbtrees. + * + * We do not cache the rightmost node based on footprint + * size vs number of potential users that could benefit + * from O(1) rb_last(). Just not worth it, users that want + * this feature can always implement the logic explicitly. + * Furthermore, users that want to cache both pointers may + * find it a bit asymmetric, but that's ok. + */ +struct rb_root_cached { + struct rb_root rb_root; + struct rb_node *rb_leftmost; +}; + +#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } + +/* Same as rb_first(), but O(1) */ +#define rb_first_cached(root) (root)->rb_leftmost + +static inline void rb_insert_color_cached(struct rb_node *node, + struct rb_root_cached *root, + bool leftmost) +{ + if (leftmost) + root->rb_leftmost = node; + rb_insert_color(node, &root->rb_root); +} + +static inline void rb_erase_cached(struct rb_node *node, + struct rb_root_cached *root) +{ + if (root->rb_leftmost == node) + root->rb_leftmost = rb_next(node); + rb_erase(node, &root->rb_root); +} + +static inline void rb_replace_node_cached(struct rb_node *victim, + struct rb_node *new, + struct rb_root_cached *root) +{ + if (root->rb_leftmost == victim) + root->rb_leftmost = new; + rb_replace_node(victim, new, &root->rb_root); +} + #endif /* __TOOLS_LINUX_PERF_RBTREE_H */ diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h index ddd01006ece5..381aa948610d 100644 --- a/tools/include/linux/rbtree_augmented.h +++ b/tools/include/linux/rbtree_augmented.h @@ -32,17 +32,16 @@ struct rb_augment_callbacks { void (*rotate)(struct rb_node *old, struct rb_node *new); }; -extern void __rb_insert_augmented(struct rb_node *node, - struct rb_root *root, - bool newleft, struct rb_node **leftmost, +extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); + /* * Fixup the rbtree and update the augmented information when rebalancing. * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and - * rb_augment_inserted() instead of the usual rb_insert_color() call. - * If rb_augment_inserted() rebalances the rbtree, it will callback into + * rb_insert_augmented() instead of the usual rb_insert_color() call. + * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ @@ -50,7 +49,7 @@ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - __rb_insert_augmented(node, root, false, NULL, augment->rotate); + __rb_insert_augmented(node, root, augment->rotate); } static inline void @@ -58,45 +57,92 @@ rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { - __rb_insert_augmented(node, &root->rb_root, - newleft, &root->rb_leftmost, augment->rotate); + if (newleft) + root->rb_leftmost = node; + rb_insert_augmented(node, &root->rb_root, augment); } -#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield, \ - rbtype, rbaugmented, rbcompute) \ +/* + * Template for declaring augmented rbtree callbacks (generic case) + * + * RBSTATIC: 'static' or empty + * RBNAME: name of the rb_augment_callbacks structure + * RBSTRUCT: struct type of the tree nodes + * RBFIELD: name of struct rb_node field within RBSTRUCT + * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree + * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data + */ + +#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ -rbname ## _propagate(struct rb_node *rb, struct rb_node *stop) \ +RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ - rbstruct *node = rb_entry(rb, rbstruct, rbfield); \ - rbtype augmented = rbcompute(node); \ - if (node->rbaugmented == augmented) \ + RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ + if (RBCOMPUTE(node, true)) \ break; \ - node->rbaugmented = augmented; \ - rb = rb_parent(&node->rbfield); \ + rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ -rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ +RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ - rbstruct *old = rb_entry(rb_old, rbstruct, rbfield); \ - rbstruct *new = rb_entry(rb_new, rbstruct, rbfield); \ - new->rbaugmented = old->rbaugmented; \ + RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ + RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ + new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ -rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ +RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ - rbstruct *old = rb_entry(rb_old, rbstruct, rbfield); \ - rbstruct *new = rb_entry(rb_new, rbstruct, rbfield); \ - new->rbaugmented = old->rbaugmented; \ - old->rbaugmented = rbcompute(old); \ + RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ + RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ + new->RBAUGMENTED = old->RBAUGMENTED; \ + RBCOMPUTE(old, false); \ } \ -rbstatic const struct rb_augment_callbacks rbname = { \ - .propagate = rbname ## _propagate, \ - .copy = rbname ## _copy, \ - .rotate = rbname ## _rotate \ +RBSTATIC const struct rb_augment_callbacks RBNAME = { \ + .propagate = RBNAME ## _propagate, \ + .copy = RBNAME ## _copy, \ + .rotate = RBNAME ## _rotate \ }; +/* + * Template for declaring augmented rbtree callbacks, + * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. + * + * RBSTATIC: 'static' or empty + * RBNAME: name of the rb_augment_callbacks structure + * RBSTRUCT: struct type of the tree nodes + * RBFIELD: name of struct rb_node field within RBSTRUCT + * RBTYPE: type of the RBAUGMENTED field + * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree + * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar + */ + +#define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ + RBTYPE, RBAUGMENTED, RBCOMPUTE) \ +static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ +{ \ + RBSTRUCT *child; \ + RBTYPE max = RBCOMPUTE(node); \ + if (node->RBFIELD.rb_left) { \ + child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ + if (child->RBAUGMENTED > max) \ + max = child->RBAUGMENTED; \ + } \ + if (node->RBFIELD.rb_right) { \ + child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ + if (child->RBAUGMENTED > max) \ + max = child->RBAUGMENTED; \ + } \ + if (exit && node->RBAUGMENTED == max) \ + return true; \ + node->RBAUGMENTED = max; \ + return false; \ +} \ +RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) + #define RB_RED 0 #define RB_BLACK 1 @@ -139,7 +185,6 @@ extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, - struct rb_node **leftmost, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; @@ -147,9 +192,6 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, struct rb_node *parent, *rebalance; unsigned long pc; - if (leftmost && node == *leftmost) - *leftmost = rb_next(node); - if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) @@ -249,8 +291,7 @@ static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - struct rb_node *rebalance = __rb_erase_augmented(node, root, - NULL, augment); + struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } @@ -259,11 +300,9 @@ static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { - struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root, - &root->rb_leftmost, - augment); - if (rebalance) - __rb_erase_color(rebalance, &root->rb_root, augment->rotate); + if (root->rb_leftmost == node) + root->rb_leftmost = rb_next(node); + rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _TOOLS_LINUX_RBTREE_AUGMENTED_H */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 1be0e798e362..1fc8faa6e973 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -569,7 +569,7 @@ __SYSCALL(__NR_semget, sys_semget) __SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl) #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 #define __NR_semtimedop 192 -__SC_COMP(__NR_semtimedop, sys_semtimedop, sys_semtimedop_time32) +__SC_3264(__NR_semtimedop, sys_semtimedop_time32, sys_semtimedop) #endif #define __NR_semop 193 __SYSCALL(__NR_semop, sys_semop) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 094bb03b9cc2..7da1b37b27aa 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -181,7 +181,7 @@ struct prctl_mm_map { #define PR_GET_THP_DISABLE 42 /* - * Tell the kernel to start/stop helping userspace manage bounds tables. + * No longer implemented, but left here to ensure the numbers stay reserved: */ #define PR_MPX_ENABLE_MANAGEMENT 43 #define PR_MPX_DISABLE_MANAGEMENT 44 @@ -229,4 +229,9 @@ struct prctl_mm_map { # define PR_PAC_APDBKEY (1UL << 3) # define PR_PAC_APGAKEY (1UL << 4) +/* Tagged user address controls for arm64 */ +#define PR_SET_TAGGED_ADDR_CTRL 55 +#define PR_GET_TAGGED_ADDR_CTRL 56 +# define PR_TAGGED_ADDR_ENABLE (1UL << 0) + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c index 804f145e3113..2548ff8c4d9c 100644 --- a/tools/lib/rbtree.c +++ b/tools/lib/rbtree.c @@ -83,14 +83,10 @@ __rb_rotate_set_parents(struct rb_node *old, struct rb_node *new, static __always_inline void __rb_insert(struct rb_node *node, struct rb_root *root, - bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) { struct rb_node *parent = rb_red_parent(node), *gparent, *tmp; - if (newleft) - *leftmost = node; - while (true) { /* * Loop invariant: node is red. @@ -436,34 +432,17 @@ static const struct rb_augment_callbacks dummy_callbacks = { void rb_insert_color(struct rb_node *node, struct rb_root *root) { - __rb_insert(node, root, false, NULL, dummy_rotate); + __rb_insert(node, root, dummy_rotate); } void rb_erase(struct rb_node *node, struct rb_root *root) { struct rb_node *rebalance; - rebalance = __rb_erase_augmented(node, root, - NULL, &dummy_callbacks); + rebalance = __rb_erase_augmented(node, root, &dummy_callbacks); if (rebalance) ____rb_erase_color(rebalance, root, dummy_rotate); } -void rb_insert_color_cached(struct rb_node *node, - struct rb_root_cached *root, bool leftmost) -{ - __rb_insert(node, &root->rb_root, leftmost, - &root->rb_leftmost, dummy_rotate); -} - -void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) -{ - struct rb_node *rebalance; - rebalance = __rb_erase_augmented(node, &root->rb_root, - &root->rb_leftmost, &dummy_callbacks); - if (rebalance) - ____rb_erase_color(rebalance, &root->rb_root, dummy_rotate); -} - /* * Augmented rbtree manipulation functions. * @@ -472,10 +451,9 @@ void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) */ void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, - bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) { - __rb_insert(node, root, newleft, leftmost, augment_rotate); + __rb_insert(node, root, augment_rotate); } /* @@ -580,15 +558,6 @@ void rb_replace_node(struct rb_node *victim, struct rb_node *new, __rb_change_child(victim, new, parent, root); } -void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, - struct rb_root_cached *root) -{ - rb_replace_node(victim, new, &root->rb_root); - - if (root->rb_leftmost == victim) - root->rb_leftmost = new; -} - static struct rb_node *rb_left_deepest_node(const struct rb_node *node) { for (;;) { diff --git a/tools/lib/traceevent/Build b/tools/lib/traceevent/Build index ba54bfce0b0b..f9a5d79578f5 100644 --- a/tools/lib/traceevent/Build +++ b/tools/lib/traceevent/Build @@ -6,14 +6,3 @@ libtraceevent-y += parse-utils.o libtraceevent-y += kbuffer-parse.o libtraceevent-y += tep_strerror.o libtraceevent-y += event-parse-api.o - -plugin_jbd2-y += plugin_jbd2.o -plugin_hrtimer-y += plugin_hrtimer.o -plugin_kmem-y += plugin_kmem.o -plugin_kvm-y += plugin_kvm.o -plugin_mac80211-y += plugin_mac80211.o -plugin_sched_switch-y += plugin_sched_switch.o -plugin_function-y += plugin_function.o -plugin_xen-y += plugin_xen.o -plugin_scsi-y += plugin_scsi.o -plugin_cfg80211-y += plugin_cfg80211.o diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt new file mode 100644 index 000000000000..2c6a61811118 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt @@ -0,0 +1,130 @@ +libtraceevent(3) +================ + +NAME +---- +tep_print_event - Writes event information into a trace sequence. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* +*#include <trace-seq.h>* + +void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seqpass:[*]_s_, struct tep_record pass:[*]_record_, const char pass:[*]_fmt_, _..._) +-- + +DESCRIPTION +----------- + +The _tep_print_event()_ function parses the event information of the given +_record_ and writes it into the trace sequence _s_, according to the format +string _fmt_. The desired information is specified after the format string. +The _fmt_ is printf-like format string, following arguments are supported: +[verse] +-- + TEP_PRINT_PID, "%d" - PID of the event. + TEP_PRINT_CPU, "%d" - Event CPU. + TEP_PRINT_COMM, "%s" - Event command string. + TEP_PRINT_NAME, "%s" - Event name. + TEP_PRINT_LATENCY, "%s" - Latency of the event. It prints 4 or more + fields - interrupt state, scheduling state, + current context, and preemption count. + Field 1 is the interrupt enabled state: + d : Interrupts are disabled + . : Interrupts are enabled + X : The architecture does not support this + information + Field 2 is the "need resched" state. + N : The task is set to call the scheduler when + possible, as another higher priority task + may need to be scheduled in. + . : The task is not set to call the scheduler. + Field 3 is the context state. + . : Normal context + s : Soft interrupt context + h : Hard interrupt context + H : Hard interrupt context which triggered + during soft interrupt context. + z : NMI context + Z : NMI context which triggered during hard + interrupt context + Field 4 is the preemption count. + . : The preempt count is zero. + On preemptible kernels (where the task can be scheduled + out in arbitrary locations while in kernel context), the + preempt count, when non zero, will prevent the kernel + from scheduling out the current task. The preempt count + number is displayed when it is not zero. + Depending on the kernel, it may show other fields + (lock depth, or migration disabled, which are unique to + specialized kernels). + TEP_PRINT_TIME, %d - event time stamp. A divisor and precision can be + specified as part of this format string: + "%precision.divisord". Example: + "%3.1000d" - divide the time by 1000 and print the first + 3 digits before the dot. Thus, the time stamp + "123456000" will be printed as "123.456" + TEP_PRINT_INFO, "%s" - event information. + TEP_PRINT_INFO_RAW, "%s" - event information, in raw format. + +-- +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct trace_seq seq; +trace_seq_init(&seq); +struct tep_handle *tep = tep_alloc(); +... +void print_my_event(struct tep_record *record) +{ + trace_seq_reset(&seq); + tep_print_event(tep, s, record, "%16s-%-5d [%03d] %s %6.1000d %s %s", + TEP_PRINT_COMM, TEP_PRINT_PID, TEP_PRINT_CPU, + TEP_PRINT_LATENCY, TEP_PRINT_TIME, TEP_PRINT_NAME, + TEP_PRINT_INFO); +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*trace-seq.h* + Header file to include in order to have access to trace sequences related APIs. + Trace sequences are used to allow a function to call several other functions + to create a string of data to use. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt index 38bfea30a5f6..f6aca0df2151 100644 --- a/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt +++ b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt @@ -59,12 +59,12 @@ parser context. The _tep_register_function()_ function registers a function name mapped to an address and (optional) module. This mapping is used in case the function tracer -or events have "%pF" or "%pS" parameter in its format string. It is common to -pass in the kallsyms function names with their corresponding addresses with this +or events have "%pS" parameter in its format string. It is common to pass in +the kallsyms function names with their corresponding addresses with this function. The _tep_ argument is the trace event parser context. The _name_ is -the name of the function, the string is copied internally. The _addr_ is -the start address of the function. The _mod_ is the kernel module -the function may be in (NULL for none). +the name of the function, the string is copied internally. The _addr_ is the +start address of the function. The _mod_ is the kernel module the function may +be in (NULL for none). The _tep_register_print_string()_ function registers a string by the address it was stored in the kernel. Some strings internal to the kernel with static diff --git a/tools/lib/traceevent/Documentation/libtraceevent-handle.txt b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt index 8d568316847d..45b20172e262 100644 --- a/tools/lib/traceevent/Documentation/libtraceevent-handle.txt +++ b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt @@ -3,7 +3,7 @@ libtraceevent(3) NAME ---- -tep_alloc, tep_free,tep_ref, tep_unref,tep_ref_get - Create, destroy, manage +tep_alloc, tep_free,tep_ref, tep_unref,tep_get_ref - Create, destroy, manage references of trace event parser context. SYNOPSIS @@ -16,7 +16,7 @@ struct tep_handle pass:[*]*tep_alloc*(void); void *tep_free*(struct tep_handle pass:[*]_tep_); void *tep_ref*(struct tep_handle pass:[*]_tep_); void *tep_unref*(struct tep_handle pass:[*]_tep_); -int *tep_ref_get*(struct tep_handle pass:[*]_tep_); +int *tep_get_ref*(struct tep_handle pass:[*]_tep_); -- DESCRIPTION @@ -57,9 +57,9 @@ EXAMPLE ... struct tep_handle *tep = tep_alloc(); ... -int ref = tep_ref_get(tep); +int ref = tep_get_ref(tep); tep_ref(tep); -if ( (ref+1) != tep_ref_get(tep)) { +if ( (ref+1) != tep_get_ref(tep)) { /* Something wrong happened, the counter is not incremented by 1 */ } tep_unref(tep); diff --git a/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt b/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt new file mode 100644 index 000000000000..596032ade31f --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt @@ -0,0 +1,99 @@ +libtraceevent(3) +================ + +NAME +---- +tep_load_plugins, tep_unload_plugins - Load / unload traceevent plugins. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_plugin_list pass:[*]*tep_load_plugins*(struct tep_handle pass:[*]_tep_); +void *tep_unload_plugins*(struct tep_plugin_list pass:[*]_plugin_list_, struct tep_handle pass:[*]_tep_); +-- + +DESCRIPTION +----------- +The _tep_load_plugins()_ function loads all plugins, located in the plugin +directories. The _tep_ argument is trace event parser context. +The plugin directories are : +[verse] +-- + - System's plugin directory, defined at the library compile time. It + depends on the library installation prefix and usually is + _(install_preffix)/lib/traceevent/plugins_ + - Directory, defined by the environment variable _TRACEEVENT_PLUGIN_DIR_ + - User's plugin directory, located at _~/.local/lib/traceevent/plugins_ +-- +Loading of plugins can be controlled by the _tep_flags_, using the +_tep_set_flag()_ API: +[verse] +-- + _TEP_DISABLE_SYS_PLUGINS_ - do not load plugins, located in + the system's plugin directory. + _TEP_DISABLE_PLUGINS_ - do not load any plugins. +-- +The _tep_set_flag()_ API needs to be called before _tep_load_plugins()_, if +loading of all plugins is not the desired case. + +The _tep_unload_plugins()_ function unloads the plugins, previously loaded by +_tep_load_plugins()_. The _tep_ argument is trace event parser context. The +_plugin_list_ is the list of loaded plugins, returned by +the _tep_load_plugins()_ function. + +RETURN VALUE +------------ +The _tep_load_plugins()_ function returns a list of successfully loaded plugins, +or NULL in case no plugins are loaded. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct tep_plugin_list *plugins = tep_load_plugins(tep); +if (plugins == NULL) { + /* no plugins are loaded */ +} +... +tep_unload_plugins(plugins, tep); +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_, _tep_set_flag(3)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent.txt b/tools/lib/traceevent/Documentation/libtraceevent.txt index fbd977b47de1..d530a7ce8fb2 100644 --- a/tools/lib/traceevent/Documentation/libtraceevent.txt +++ b/tools/lib/traceevent/Documentation/libtraceevent.txt @@ -16,7 +16,7 @@ Management of tep handler data structure and access of its members: void *tep_free*(struct tep_handle pass:[*]_tep_); void *tep_ref*(struct tep_handle pass:[*]_tep_); void *tep_unref*(struct tep_handle pass:[*]_tep_); - int *tep_ref_get*(struct tep_handle pass:[*]_tep_); + int *tep_get_ref*(struct tep_handle pass:[*]_tep_); void *tep_set_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); void *tep_clear_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); bool *tep_test_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flags_); @@ -26,15 +26,12 @@ Management of tep handler data structure and access of its members: void *tep_set_long_size*(struct tep_handle pass:[*]_tep_, int _long_size_); int *tep_get_page_size*(struct tep_handle pass:[*]_tep_); void *tep_set_page_size*(struct tep_handle pass:[*]_tep_, int _page_size_); - bool *tep_is_latency_format*(struct tep_handle pass:[*]_tep_); - void *tep_set_latency_format*(struct tep_handle pass:[*]_tep_, int _lat_); int *tep_get_header_page_size*(struct tep_handle pass:[*]_tep_); int *tep_get_header_timestamp_size*(struct tep_handle pass:[*]_tep_); bool *tep_is_old_format*(struct tep_handle pass:[*]_tep_); int *tep_strerror*(struct tep_handle pass:[*]_tep_, enum tep_errno _errnum_, char pass:[*]_buf_, size_t _buflen_); Register / unregister APIs: - int *tep_register_trace_clock*(struct tep_handle pass:[*]_tep_, const char pass:[*]_trace_clock_); int *tep_register_function*(struct tep_handle pass:[*]_tep_, char pass:[*]_name_, unsigned long long _addr_, char pass:[*]_mod_); int *tep_register_event_handler*(struct tep_handle pass:[*]_tep_, int _id_, const char pass:[*]_sys_name_, const char pass:[*]_event_name_, tep_event_handler_func _func_, void pass:[*]_context_); int *tep_unregister_event_handler*(struct tep_handle pass:[*]tep, int id, const char pass:[*]sys_name, const char pass:[*]event_name, tep_event_handler_func func, void pass:[*]_context_); @@ -57,14 +54,7 @@ Event related APIs: int *tep_get_events_count*(struct tep_handle pass:[*]_tep_); struct tep_event pass:[*]pass:[*]*tep_list_events*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_); struct tep_event pass:[*]pass:[*]*tep_list_events_copy*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_); - -Event printing: - void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_, bool _use_trace_clock_); - void *tep_print_event_data*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); - void *tep_event_info*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); - void *tep_print_event_task*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); - void *tep_print_event_time*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]record, bool _use_trace_clock_); - void *tep_set_print_raw*(struct tep_handle pass:[*]_tep_, int _print_raw_); + void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_, const char pass:[*]_fmt_, _..._); Event finding: struct tep_event pass:[*]*tep_find_event*(struct tep_handle pass:[*]_tep_, int _id_); @@ -116,7 +106,6 @@ Filter management: int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_); Parsing various data from the records: - void *tep_data_latency_format*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_); int *tep_data_type*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); int *tep_data_pid*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); int *tep_data_preempt_count*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index a39cdd0d890d..5315f3787f8d 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -58,30 +58,6 @@ export man_dir man_dir_SQ INSTALL export DESTDIR DESTDIR_SQ export EVENT_PARSE_VERSION -set_plugin_dir := 1 - -# Set plugin_dir to preffered global plugin location -# If we install under $HOME directory we go under -# $(HOME)/.local/lib/traceevent/plugins -# -# We dont set PLUGIN_DIR in case we install under $HOME -# directory, because by default the code looks under: -# $(HOME)/.local/lib/traceevent/plugins by default. -# -ifeq ($(plugin_dir),) -ifeq ($(prefix),$(HOME)) -override plugin_dir = $(HOME)/.local/lib/traceevent/plugins -set_plugin_dir := 0 -else -override plugin_dir = $(libdir)/traceevent/plugins -endif -endif - -ifeq ($(set_plugin_dir),1) -PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)" -PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))' -endif - include ../../scripts/Makefile.include # copy a bit from Linux kbuild @@ -105,7 +81,6 @@ export prefix libdir src obj # Shell quotes libdir_SQ = $(subst ','\'',$(libdir)) libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) -plugin_dir_SQ = $(subst ','\'',$(plugin_dir)) CONFIG_INCLUDES = CONFIG_LIBS = @@ -151,29 +126,14 @@ MAKEOVERRIDES= export srctree OUTPUT CC LD CFLAGS V build := -f $(srctree)/tools/build/Makefile.build dir=. obj -PLUGINS = plugin_jbd2.so -PLUGINS += plugin_hrtimer.so -PLUGINS += plugin_kmem.so -PLUGINS += plugin_kvm.so -PLUGINS += plugin_mac80211.so -PLUGINS += plugin_sched_switch.so -PLUGINS += plugin_function.so -PLUGINS += plugin_xen.so -PLUGINS += plugin_scsi.so -PLUGINS += plugin_cfg80211.so - -PLUGINS := $(addprefix $(OUTPUT),$(PLUGINS)) -PLUGINS_IN := $(PLUGINS:.so=-in.o) - TE_IN := $(OUTPUT)libtraceevent-in.o LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) -DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list -CMD_TARGETS = $(LIB_TARGET) $(PLUGINS) $(DYNAMIC_LIST_FILE) +CMD_TARGETS = $(LIB_TARGET) TARGETS = $(CMD_TARGETS) -all: all_cmd +all: all_cmd plugins all_cmd: $(CMD_TARGETS) @@ -188,17 +148,6 @@ $(OUTPUT)libtraceevent.so.$(EVENT_PARSE_VERSION): $(TE_IN) $(OUTPUT)libtraceevent.a: $(TE_IN) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ -$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS) - $(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@) - -plugins: $(PLUGINS) - -__plugin_obj = $(notdir $@) - plugin_obj = $(__plugin_obj:-in.o=) - -$(PLUGINS_IN): force - $(Q)$(MAKE) $(build)=$(plugin_obj) - $(OUTPUT)%.so: $(OUTPUT)%-in.o $(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^ @@ -258,25 +207,6 @@ define do_install $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' endef -define do_install_plugins - for plugin in $1; do \ - $(call do_install,$$plugin,$(plugin_dir_SQ)); \ - done -endef - -define do_generate_dynamic_list_file - symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \ - xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ - if [ "$$symbol_type" = "U W" ];then \ - (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ - echo '};'; \ - ) > $2; \ - else \ - (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\ - fi -endef - PKG_CONFIG_FILE = libtraceevent.pc define do_install_pkgconfig_file if [ -n "${pkgconfig_dir}" ]; then \ @@ -296,10 +226,6 @@ install_lib: all_cmd install_plugins install_headers install_pkgconfig $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_INSTALL) $(DESTDIR)$(libdir_SQ) -install_plugins: $(PLUGINS) - $(call QUIET_INSTALL, trace_plugins) \ - $(call do_install_plugins, $(PLUGINS)) - install_pkgconfig: $(call QUIET_INSTALL, $(PKG_CONFIG_FILE)) \ $(call do_install_pkgconfig_file,$(prefix)) @@ -313,7 +239,7 @@ install_headers: install: install_lib -clean: +clean: clean_plugins $(call QUIET_CLEAN, libtraceevent) \ $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \ $(RM) TRACEEVENT-CFLAGS tags TAGS; \ @@ -351,7 +277,19 @@ help: @echo ' doc-install - install the man pages' @echo ' doc-uninstall - uninstall the man pages' @echo'' -PHONY += force plugins + +PHONY += plugins +plugins: + $(call descend,plugins) + +PHONY += install_plugins +install_plugins: + $(call descend,plugins,install) + +PHONY += clean_plugins +clean_plugins: + $(call descend,plugins,clean) + force: # Declare the contents of the .PHONY variable as phony. We keep that diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index bb22238debfe..d948475585ce 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4367,10 +4367,20 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s switch (*ptr) { case 's': case 'S': - case 'f': - case 'F': case 'x': break; + case 'f': + case 'F': + /* + * Pre-5.5 kernels use %pf and + * %pF for printing symbols + * while kernels since 5.5 use + * %pfw for fwnodes. So check + * %p[fF] isn't followed by 'w'. + */ + if (ptr[1] != 'w') + break; + /* fall through */ default: /* * Older kernels do not process @@ -4487,12 +4497,12 @@ get_bprint_format(void *data, int size __maybe_unused, printk = find_printk(tep, addr); if (!printk) { - if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0) + if (asprintf(&format, "%%ps: (NO FORMAT FOUND at %llx)\n", addr) < 0) return NULL; return format; } - if (asprintf(&format, "%s: %s", "%pf", printk->printk) < 0) + if (asprintf(&format, "%s: %s", "%ps", printk->printk) < 0) return NULL; return format; @@ -5517,8 +5527,10 @@ static void print_event_time(struct tep_handle *tep, struct trace_seq *s, if (divstr && isdigit(*(divstr + 1))) div = atoi(divstr + 1); time = record->ts; - if (div) + if (div) { + time += div / 2; time /= div; + } pr = prec; while (pr--) p10 *= 10; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index d438ee44289f..b77837f75a0d 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -441,6 +441,8 @@ int tep_register_print_string(struct tep_handle *tep, const char *fmt, unsigned long long addr); bool tep_is_pid_registered(struct tep_handle *tep, int pid); +struct tep_event *tep_get_event(struct tep_handle *tep, int index); + #define TEP_PRINT_INFO "INFO" #define TEP_PRINT_INFO_RAW "INFO_RAW" #define TEP_PRINT_COMM "COMM" diff --git a/tools/lib/traceevent/plugins/Build b/tools/lib/traceevent/plugins/Build new file mode 100644 index 000000000000..210d26910613 --- /dev/null +++ b/tools/lib/traceevent/plugins/Build @@ -0,0 +1,10 @@ +plugin_jbd2-y += plugin_jbd2.o +plugin_hrtimer-y += plugin_hrtimer.o +plugin_kmem-y += plugin_kmem.o +plugin_kvm-y += plugin_kvm.o +plugin_mac80211-y += plugin_mac80211.o +plugin_sched_switch-y += plugin_sched_switch.o +plugin_function-y += plugin_function.o +plugin_xen-y += plugin_xen.o +plugin_scsi-y += plugin_scsi.o +plugin_cfg80211-y += plugin_cfg80211.o diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile new file mode 100644 index 000000000000..f440989fa55e --- /dev/null +++ b/tools/lib/traceevent/plugins/Makefile @@ -0,0 +1,222 @@ +# SPDX-License-Identifier: GPL-2.0 + +#MAKEFLAGS += --no-print-directory + + +# Makefiles suck: This macro sets a default value of $(2) for the +# variable named by $(1), unless the variable has been set by +# environment or command line. This is necessary for CC and AR +# because make sets default values, so the simpler ?= approach +# won't work as expected. +define allow-override + $(if $(or $(findstring environment,$(origin $(1))),\ + $(findstring command line,$(origin $(1)))),,\ + $(eval $(1) = $(2))) +endef + +# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix. +$(call allow-override,CC,$(CROSS_COMPILE)gcc) +$(call allow-override,AR,$(CROSS_COMPILE)ar) +$(call allow-override,NM,$(CROSS_COMPILE)nm) +$(call allow-override,PKG_CONFIG,pkg-config) + +EXT = -std=gnu99 +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= /usr/local +libdir = $(prefix)/$(libdir_relative) + +set_plugin_dir := 1 + +# Set plugin_dir to preffered global plugin location +# If we install under $HOME directory we go under +# $(HOME)/.local/lib/traceevent/plugins +# +# We dont set PLUGIN_DIR in case we install under $HOME +# directory, because by default the code looks under: +# $(HOME)/.local/lib/traceevent/plugins by default. +# +ifeq ($(plugin_dir),) +ifeq ($(prefix),$(HOME)) +override plugin_dir = $(HOME)/.local/lib/traceevent/plugins +set_plugin_dir := 0 +else +override plugin_dir = $(libdir)/traceevent/plugins +endif +endif + +ifeq ($(set_plugin_dir),1) +PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)" +PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))' +endif + +include ../../../scripts/Makefile.include + +# copy a bit from Linux kbuild + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +export prefix libdir src obj + +# Shell quotes +plugin_dir_SQ = $(subst ','\'',$(plugin_dir)) + +CONFIG_INCLUDES = +CONFIG_LIBS = +CONFIG_FLAGS = + +OBJ = $@ +N = + +INCLUDES = -I. -I.. -I $(srctree)/tools/include $(CONFIG_INCLUDES) + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +# Append required CFLAGS +override CFLAGS += -fPIC +override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ) +override CFLAGS += $(udis86-flags) -D_GNU_SOURCE + +ifeq ($(VERBOSE),1) + Q = +else + Q = @ +endif + +# Disable command line variables (CFLAGS) override from top +# level Makefile (perf), otherwise build Makefile will get +# the same command line setup. +MAKEOVERRIDES= + +export srctree OUTPUT CC LD CFLAGS V + +build := -f $(srctree)/tools/build/Makefile.build dir=. obj + +DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list + +PLUGINS = plugin_jbd2.so +PLUGINS += plugin_hrtimer.so +PLUGINS += plugin_kmem.so +PLUGINS += plugin_kvm.so +PLUGINS += plugin_mac80211.so +PLUGINS += plugin_sched_switch.so +PLUGINS += plugin_function.so +PLUGINS += plugin_xen.so +PLUGINS += plugin_scsi.so +PLUGINS += plugin_cfg80211.so + +PLUGINS := $(addprefix $(OUTPUT),$(PLUGINS)) +PLUGINS_IN := $(PLUGINS:.so=-in.o) + +plugins: $(PLUGINS) $(DYNAMIC_LIST_FILE) + +__plugin_obj = $(notdir $@) + plugin_obj = $(__plugin_obj:-in.o=) + +$(PLUGINS_IN): force + $(Q)$(MAKE) $(build)=$(plugin_obj) + +$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS) + $(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@) + +$(OUTPUT)%.so: $(OUTPUT)%-in.o + $(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^ + +define update_dir + (echo $1 > $@.tmp; \ + if [ -r $@ ] && cmp -s $@ $@.tmp; then \ + rm -f $@.tmp; \ + else \ + echo ' UPDATE $@'; \ + mv -f $@.tmp $@; \ + fi); +endef + +tags: force + $(RM) tags + find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \ + --regex-c++='/_PE\(([^,)]*).*/TEP_ERRNO__\1/' + +TAGS: force + $(RM) TAGS + find . -name '*.[ch]' | xargs etags \ + --regex='/_PE(\([^,)]*\).*/TEP_ERRNO__\1/' + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + $(call do_install_mkdir,$2); \ + $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' +endef + +define do_install_plugins + for plugin in $1; do \ + $(call do_install,$$plugin,$(plugin_dir_SQ)); \ + done +endef + +define do_generate_dynamic_list_file + symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \ + xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ + if [ "$$symbol_type" = "U W" ];then \ + (echo '{'; \ + $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + echo '};'; \ + ) > $2; \ + else \ + (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\ + fi +endef + +install: $(PLUGINS) + $(call QUIET_INSTALL, trace_plugins) \ + $(call do_install_plugins, $(PLUGINS)) + +clean: + $(call QUIET_CLEAN, trace_plugins) \ + $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \ + $(RM) $(OUTPUT)libtraceevent-dynamic-list \ + $(RM) TRACEEVENT-CFLAGS tags TAGS; + +PHONY += force plugins +force: + +# Declare the contents of the .PHONY variable as phony. We keep that +# information in a variable so we can use it in if_changed and friends. +.PHONY: $(PHONY) diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugins/plugin_cfg80211.c index 3d43b56a6c98..3d43b56a6c98 100644 --- a/tools/lib/traceevent/plugin_cfg80211.c +++ b/tools/lib/traceevent/plugins/plugin_cfg80211.c diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugins/plugin_function.c index 7770fcb78e0f..7770fcb78e0f 100644 --- a/tools/lib/traceevent/plugin_function.c +++ b/tools/lib/traceevent/plugins/plugin_function.c diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugins/plugin_hrtimer.c index bb434e0ed03a..bb434e0ed03a 100644 --- a/tools/lib/traceevent/plugin_hrtimer.c +++ b/tools/lib/traceevent/plugins/plugin_hrtimer.c diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugins/plugin_jbd2.c index 04fc125f38cb..04fc125f38cb 100644 --- a/tools/lib/traceevent/plugin_jbd2.c +++ b/tools/lib/traceevent/plugins/plugin_jbd2.c diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugins/plugin_kmem.c index edaec5d962c3..edaec5d962c3 100644 --- a/tools/lib/traceevent/plugin_kmem.c +++ b/tools/lib/traceevent/plugins/plugin_kmem.c diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugins/plugin_kvm.c index c8e623065a7e..c8e623065a7e 100644 --- a/tools/lib/traceevent/plugin_kvm.c +++ b/tools/lib/traceevent/plugins/plugin_kvm.c diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugins/plugin_mac80211.c index 884303c26b5c..884303c26b5c 100644 --- a/tools/lib/traceevent/plugin_mac80211.c +++ b/tools/lib/traceevent/plugins/plugin_mac80211.c diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugins/plugin_sched_switch.c index 957389a0ff7a..957389a0ff7a 100644 --- a/tools/lib/traceevent/plugin_sched_switch.c +++ b/tools/lib/traceevent/plugins/plugin_sched_switch.c diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugins/plugin_scsi.c index 5d0387a4b65a..5d0387a4b65a 100644 --- a/tools/lib/traceevent/plugin_scsi.c +++ b/tools/lib/traceevent/plugins/plugin_scsi.c diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugins/plugin_xen.c index 993b208d0323..993b208d0323 100644 --- a/tools/lib/traceevent/plugin_xen.c +++ b/tools/lib/traceevent/plugins/plugin_xen.c diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index a269d78456b6..46f7fba2306c 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -924,7 +924,7 @@ ifndef NO_JVMTI JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}') else ifneq (,$(wildcard /usr/sbin/alternatives)) - JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g') + JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed -e 's%/jre/bin/java.%%g' -e 's%/bin/java.%%g') endif endif ifndef JDIR diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index f9807d8c005b..902c792f326a 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -292,7 +292,7 @@ endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a export LIBTRACEEVENT -LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list +LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)plugins/libtraceevent-dynamic-list # # The static build has no dynsym table, so this does not work for @@ -567,7 +567,7 @@ all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) # Create python binding output directory if not already present _dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python') -$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST) +$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST) $(LIBPERF) $(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \ CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \ $(PYTHON_WORD) util/setup.py \ @@ -737,7 +737,7 @@ libtraceevent_plugins: FORCE $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) plugins $(LIBTRACEEVENT_DYNAMIC_LIST): libtraceevent_plugins - $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent-dynamic-list + $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)plugins/libtraceevent-dynamic-list $(LIBTRACEEVENT)-clean: $(call QUIET_CLEAN, libtraceevent) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index c32db09baf0d..ede040cf82ad 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -23,9 +23,10 @@ #include "../../util/event.h" #include "../../util/evlist.h" #include "../../util/evsel.h" +#include "../../util/evsel_config.h" #include "../../util/pmu.h" #include "../../util/cs-etm.h" -#include "../../util/util.h" +#include <internal/lib.h> // page_size #include "../../util/session.h" #include <errno.h> @@ -416,7 +417,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, if (err) goto out; - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; @@ -648,7 +649,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, if (priv_size != cs_etm_info_priv_size(itr, session->evlist)) return -EINVAL; - if (!session->evlist->nr_mmaps) + if (!session->evlist->core.nr_mmaps) return -EINVAL; /* If the cpu_map is empty all online CPUs are involved */ diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 4b364692da67..eba6541ec0f1 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -16,7 +16,7 @@ #include "../../util/evsel.h" #include "../../util/evlist.h" #include "../../util/session.h" -#include "../../util/util.h" +#include <internal/lib.h> // page_size #include "../../util/pmu.h" #include "../../util/debug.h" #include "../../util/auxtrace.h" @@ -51,7 +51,7 @@ static int arm_spe_info_fill(struct auxtrace_record *itr, if (priv_size != ARM_SPE_AUXTRACE_PRIV_SIZE) return -EINVAL; - if (!session->evlist->nr_mmaps) + if (!session->evlist->core.nr_mmaps) return -EINVAL; auxtrace_info->type = PERF_AUXTRACE_ARM_SPE; @@ -129,7 +129,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, if (err) return err; - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c index b047b882c5b1..917b97d7c5d3 100644 --- a/tools/perf/arch/arm64/util/dwarf-regs.c +++ b/tools/perf/arch/arm64/util/dwarf-regs.c @@ -11,7 +11,6 @@ #include <dwarf-regs.h> #include <linux/ptrace.h> /* for struct user_pt_regs */ #include <linux/stringify.h> -#include "util.h" struct pt_regs_dwarfnum { const char *name; diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index e41defaaa2e6..a32e4b72a98f 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -1,5 +1,7 @@ #include <stdio.h> #include <stdlib.h> +#include <perf/cpumap.h> +#include <internal/cpumap.h> #include <api/fs/fs.h> #include "debug.h" #include "header.h" @@ -29,7 +31,7 @@ char *get_cpuid_str(struct perf_pmu *pmu) /* read midr from list of cpus mapped to this pmu */ cpus = perf_cpu_map__get(pmu->cpus); - for (cpu = 0; cpu < cpus->nr; cpu++) { + for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) { scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, sysfs, cpus->map[cpu]); diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c index 002520d4036b..1495a9523a23 100644 --- a/tools/perf/arch/arm64/util/unwind-libunwind.c +++ b/tools/perf/arch/arm64/util/unwind-libunwind.c @@ -5,8 +5,8 @@ #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" -#include "../../util/debug.h" #endif +#include "../../util/debug.h" int LIBUNWIND__ARCH_REG_ID(int regnum) { diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c index 4952890b9428..0c4f4caf53ac 100644 --- a/tools/perf/arch/powerpc/util/dwarf-regs.c +++ b/tools/perf/arch/powerpc/util/dwarf-regs.c @@ -12,7 +12,6 @@ #include <linux/ptrace.h> #include <linux/kernel.h> #include <linux/stringify.h> -#include "util.h" struct pt_regs_dwarfnum { const char *name; diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 0b242664f5ea..b6b7bc7e31a1 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -6,7 +6,6 @@ #include <string.h> #include <linux/stringify.h> #include "header.h" -#include "util.h" #define mfspr(rn) ({unsigned long rval; \ asm volatile("mfspr %0," __stringify(rn) \ diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index f0dbf7b075c8..9cc1c4a9dec4 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -5,9 +5,11 @@ #include "util/debug.h" #include "util/evsel.h" #include "util/evlist.h" +#include "util/pmu.h" #include "book3s_hv_exits.h" #include "book3s_hcalls.h" +#include <subcmd/parse-options.h> #define NR_TPS 4 @@ -172,3 +174,46 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) return ret; } + +/* + * Incase of powerpc architecture, pmu registers are programmable + * by guest kernel. So monitoring guest via host may not provide + * valid samples with default 'cycles' event. It is better to use + * 'trace_imc/trace_cycles' event for guest profiling, since it + * can track the guest instruction pointer in the trace-record. + * + * Function to parse the arguments and return appropriate values. + */ +int kvm_add_default_arch_event(int *argc, const char **argv) +{ + const char **tmp; + bool event = false; + int i, j = *argc; + + const struct option event_options[] = { + OPT_BOOLEAN('e', "event", &event, NULL), + OPT_END() + }; + + tmp = calloc(j + 1, sizeof(char *)); + if (!tmp) + return -EINVAL; + + for (i = 0; i < j; i++) + tmp[i] = argv[i]; + + parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN); + if (!event) { + if (pmu_have_event("trace_imc", "trace_cycles")) { + argv[j++] = strdup("-e"); + argv[j++] = strdup("trace_imc/trace_cycles/"); + *argc += 2; + } else { + free(tmp); + return -EINVAL; + } + } + + free(tmp); + return 0; +} diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index fc9c2f5fcd52..3018a054526a 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -13,6 +13,7 @@ #include "util/callchain.h" #include "util/debug.h" #include "util/dso.h" +#include "util/event.h" // struct ip_callchain #include "util/map.h" #include "util/symbol.h" diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 8a4b717e0a53..abb7a12d8f93 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -4,7 +4,6 @@ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation */ -#include "debug.h" #include "dso.h" #include "symbol.h" #include "map.h" diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index cb198787570a..6ac8887be7c9 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -4,6 +4,7 @@ PERF_HAVE_DWARF_REGS := 1 endif HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 +PERF_HAVE_JITDUMP := 1 # # Syscall table generation for perf diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index b0fb70e38960..0db5c58c98e8 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -1,4 +1,5 @@ #include <stdbool.h> +#include <stdlib.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bitops.h> diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index c8c86a0c9b79..724efb2d842d 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -2,7 +2,7 @@ #include <unistd.h> #include <stdio.h> #include <string.h> -#include "util.h" +#include <internal/lib.h> // page_size #include "machine.h" #include "api/fs/fs.h" #include "debug.h" diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 3b5cc3373821..3ec562a2aaba 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -5,7 +5,7 @@ #include "evlist.h" #include "evsel.h" #include "arch-tests.h" -#include "util.h" +#include <internal/lib.h> // page_size #include <signal.h> #include <sys/mman.h> @@ -63,9 +63,9 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt goto out; } - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); if (!evsel) { - pr_debug("perf_evlist__first failed\n"); + pr_debug("evlist__first failed\n"); goto out; } diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index eb3635941c2b..fa947952c16a 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -15,9 +15,9 @@ #include "evlist.h" #include "evsel.h" #include "thread_map.h" -#include "cpumap.h" #include "record.h" #include "tsc.h" +#include "util/mmap.h" #include "tests/tests.h" #include "arch-tests.h" @@ -66,7 +66,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe union perf_event *event; u64 test_tsc, comm1_tsc, comm2_tsc; u64 test_time, comm1_time = 0, comm2_time = 0; - struct perf_mmap *md; + struct mmap *md; threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -83,7 +83,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe perf_evlist__config(evlist, &opts, NULL); - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); evsel->core.attr.comm = 1; evsel->core.attr.disabled = 1; @@ -91,9 +91,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe CHECK__(evlist__open(evlist)); - CHECK__(perf_evlist__mmap(evlist, UINT_MAX)); + CHECK__(evlist__mmap(evlist, UINT_MAX)); - pc = evlist->mmap[0].base; + pc = evlist->mmap[0].core.base; ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { @@ -115,7 +115,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe evlist__disable(evlist); - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { md = &evlist->mmap[i]; if (perf_mmap__read_init(md) < 0) continue; diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c index 6e67cee792b1..1ea916656a2d 100644 --- a/tools/perf/arch/x86/tests/rdpmc.c +++ b/tools/perf/arch/x86/tests/rdpmc.c @@ -13,7 +13,7 @@ #include "tests/tests.h" #include "cloexec.h" #include "event.h" -#include "util.h" +#include <internal/lib.h> // page_size #include "arch-tests.h" static u64 rdpmc(unsigned int counter) diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c index 9876c7a7ed7c..3e6791531ca5 100644 --- a/tools/perf/arch/x86/util/archinsn.c +++ b/tools/perf/arch/x86/util/archinsn.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "../../../../arch/x86/include/asm/insn.h" #include "archinsn.h" +#include "event.h" #include "machine.h" #include "thread.h" #include "symbol.h" diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index a3a0b6884779..d357c625c09f 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -3,6 +3,8 @@ #include <linux/string.h> #include <linux/zalloc.h> +#include "../../util/event.h" +#include "../../util/synthetic-events.h" #include "../../util/machine.h" #include "../../util/tool.h" #include "../../util/map.h" diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index d263430c045f..f7f68a50a5cd 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -15,6 +15,7 @@ #include "../../util/event.h" #include "../../util/evsel.h" #include "../../util/evlist.h" +#include "../../util/mmap.h" #include "../../util/session.h" #include "../../util/pmu.h" #include "../../util/debug.h" @@ -22,7 +23,7 @@ #include "../../util/tsc.h" #include "../../util/auxtrace.h" #include "../../util/intel-bts.h" -#include "../../util/util.h" +#include <internal/lib.h> // page_size #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -74,10 +75,10 @@ static int intel_bts_info_fill(struct auxtrace_record *itr, if (priv_size != INTEL_BTS_AUXTRACE_PRIV_SIZE) return -EINVAL; - if (!session->evlist->nr_mmaps) + if (!session->evlist->core.nr_mmaps) return -EINVAL; - pc = session->evlist->mmap[0].base; + pc = session->evlist->mmap[0].core.base; if (pc) { err = perf_read_tsc_conversion(pc, &tc); if (err) { @@ -230,7 +231,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, if (err) return err; - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index cb7cf16af79c..d6d26256915f 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -18,6 +18,7 @@ #include "../../util/evlist.h" #include "../../util/evsel.h" #include "../../util/cpumap.h" +#include "../../util/mmap.h" #include <subcmd/parse-options.h> #include "../../util/parse-events.h" #include "../../util/pmu.h" @@ -26,7 +27,7 @@ #include "../../util/record.h" #include "../../util/target.h" #include "../../util/tsc.h" -#include "../../util/util.h" +#include <internal/lib.h> // page_size #include "../../util/intel-pt.h" #define KiB(x) ((x) * 1024) @@ -351,10 +352,10 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, filter = intel_pt_find_filter(session->evlist, ptr->intel_pt_pmu); filter_str_len = filter ? strlen(filter) : 0; - if (!session->evlist->nr_mmaps) + if (!session->evlist->core.nr_mmaps) return -EINVAL; - pc = session->evlist->mmap[0].base; + pc = session->evlist->mmap[0].core.base; if (pc) { err = perf_read_tsc_conversion(pc, &tc); if (err) { @@ -416,12 +417,12 @@ static int intel_pt_track_switches(struct evlist *evlist) return err; } - evsel = perf_evlist__last(evlist); + evsel = evlist__last(evlist); perf_evsel__set_sample_bit(evsel, CPU); perf_evsel__set_sample_bit(evsel, TIME); - evsel->system_wide = true; + evsel->core.system_wide = true; evsel->no_aux_samples = true; evsel->immediate = true; @@ -716,13 +717,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, if (err) return err; - switch_evsel = perf_evlist__last(evlist); + switch_evsel = evlist__last(evlist); switch_evsel->core.attr.freq = 0; switch_evsel->core.attr.sample_period = 1; switch_evsel->core.attr.context_switch = 1; - switch_evsel->system_wide = true; + switch_evsel->core.system_wide = true; switch_evsel->no_aux_samples = true; switch_evsel->immediate = true; @@ -774,7 +775,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, if (err) return err; - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c index 1e9ec783b9a1..e17e080e76f4 100644 --- a/tools/perf/arch/x86/util/machine.c +++ b/tools/perf/arch/x86/util/machine.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/string.h> +#include <limits.h> #include <stdlib.h> -#include "../../util/util.h" +#include <internal/lib.h> // page_size #include "../../util/machine.h" #include "../../util/map.h" #include "../../util/symbol.h" diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index c5197a15119b..2f55afb14e1f 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -8,6 +8,8 @@ #include <linux/types.h> #include <asm/barrier.h> #include "../../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/synthetic-events.h" #include "../../../util/tsc.h" int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 05920e3edf7a..47357973b55b 100644 --- a/tools/perf/arch/x86/util/unwind-libunwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include "../../util/debug.h" #ifndef REMOTE_UNWIND_LIBUNWIND #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" -#include "../../util/debug.h" #endif #ifdef HAVE_ARCH_X86_64_SUPPORT diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index d1caa4a0a12a..bb617e568841 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -21,12 +21,12 @@ #include <sys/resource.h> #include <sys/epoll.h> #include <sys/eventfd.h> +#include <internal/cpumap.h> #include <perf/cpumap.h> #include "../util/stat.h" #include <subcmd/parse-options.h> #include "bench.h" -#include "cpumap.h" #include <err.h> diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index f6b4472847d2..7af694437f4e 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -76,12 +76,12 @@ #include <sys/epoll.h> #include <sys/eventfd.h> #include <sys/types.h> +#include <internal/cpumap.h> #include <perf/cpumap.h> #include "../util/stat.h" #include <subcmd/parse-options.h> #include "bench.h" -#include "cpumap.h" #include <err.h> diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index 80e138904c66..8ba0c3330a9a 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -20,13 +20,13 @@ #include <linux/kernel.h> #include <linux/zalloc.h> #include <sys/time.h> +#include <internal/cpumap.h> #include <perf/cpumap.h> #include "../util/stat.h" #include <subcmd/parse-options.h> #include "bench.h" #include "futex.h" -#include "cpumap.h" #include <err.h> diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index c5d6d0abbaa9..d0cae8125423 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -14,10 +14,10 @@ #include <linux/kernel.h> #include <linux/zalloc.h> #include <errno.h> +#include <internal/cpumap.h> #include <perf/cpumap.h> #include "bench.h" #include "futex.h" -#include "cpumap.h" #include <err.h> #include <stdlib.h> diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 75d3418c1a88..a00a6891447a 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -20,10 +20,10 @@ #include <linux/kernel.h> #include <linux/time64.h> #include <errno.h> +#include <internal/cpumap.h> #include <perf/cpumap.h> #include "bench.h" #include "futex.h" -#include "cpumap.h" #include <err.h> #include <stdlib.h> diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 163fe16c275a..a053cf2b7039 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -29,7 +29,8 @@ int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe #include <linux/time64.h> #include <errno.h> #include "futex.h" -#include "cpumap.h" +#include <internal/cpumap.h> +#include <perf/cpumap.h> #include <err.h> #include <stdlib.h> diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 77dcdc13618a..df810096abfe 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -20,10 +20,10 @@ #include <linux/kernel.h> #include <linux/time64.h> #include <errno.h> +#include <internal/cpumap.h> #include <perf/cpumap.h> #include "bench.h" #include "futex.h" -#include "cpumap.h" #include <err.h> #include <stdlib.h> diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 62b8ef4bcb1f..5797253b9700 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -9,7 +9,6 @@ /* For the CLR_() macros */ #include <pthread.h> -#include "../builtin.h" #include <subcmd/parse-options.h> #include "../util/cloexec.h" diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index c63eb9a46346..97e4a4fb3362 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -10,9 +10,7 @@ * */ -#include "../util/util.h" #include <subcmd/parse-options.h> -#include "../builtin.h" #include "bench.h" /* Test groups of 20 processes spraying to 20 receivers */ diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 35b07f197d48..3c88d1f201f1 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -9,9 +9,7 @@ * http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> */ -#include "../util/util.h" #include <subcmd/parse-options.h> -#include "../builtin.h" #include "bench.h" #include <unistd.h> diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 4e4d2e76232e..8db8fc9bddef 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -27,6 +27,7 @@ #include "util/sort.h" #include "util/hist.h" #include "util/dso.h" +#include "util/machine.h" #include "util/map.h" #include "util/session.h" #include "util/tool.h" @@ -39,6 +40,7 @@ #include <dlfcn.h> #include <errno.h> #include <linux/bitmap.h> +#include <linux/err.h> struct perf_annotate { struct perf_tool tool; @@ -583,8 +585,8 @@ int cmd_annotate(int argc, const char **argv) data.path = input_name; annotate.session = perf_session__new(&data, false, &annotate.tool); - if (annotate.session == NULL) - return -1; + if (IS_ERR(annotate.session)) + return PTR_ERR(annotate.session); annotate.has_br_stack = perf_header__has_feat(&annotate.session->header, HEADER_BRANCH_STACK); diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 1a69eb565dc0..39efa51d7fb3 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -28,6 +28,7 @@ #include "util/util.h" #include "util/probe-file.h" #include <linux/string.h> +#include <linux/err.h> static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid) { @@ -422,8 +423,8 @@ int cmd_buildid_cache(int argc, const char **argv) data.force = force; session = perf_session__new(&data, false, NULL); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); } if (symbol__init(session ? &session->header.env : NULL) < 0) diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 5a0d8b378cb5..e3ef75583514 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -18,6 +18,7 @@ #include "util/symbol.h" #include "util/data.h" #include <errno.h> +#include <linux/err.h> static int sysfs__fprintf_build_id(FILE *fp) { @@ -65,8 +66,8 @@ static int perf_session__list_build_ids(bool force, bool with_hits) goto out; session = perf_session__new(&data, false, &build_id__mark_dso_hit_ops); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); /* * We take all buildids when the file contains AUX area tracing data diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index b09b12e0976b..3542b6ab9813 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -13,6 +13,7 @@ #include <errno.h> #include <inttypes.h> #include <linux/compiler.h> +#include <linux/err.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/zalloc.h> @@ -20,6 +21,7 @@ #include <sys/param.h> #include "debug.h" #include "builtin.h" +#include <perf/cpumap.h> #include <subcmd/pager.h> #include <subcmd/parse-options.h> #include "map_symbol.h" @@ -2780,8 +2782,9 @@ static int perf_c2c__report(int argc, const char **argv) } session = perf_session__new(&data, 0, &c2c.tool); - if (session == NULL) { - pr_debug("No memory for session\n"); + if (IS_ERR(session)) { + err = PTR_ERR(session); + pr_debug("Error creating perf session\n"); goto out; } diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 42d8157e047a..2603015f98be 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -9,7 +9,6 @@ #include "util/cache.h" #include <subcmd/parse-options.h> -#include "util/util.h" #include "util/debug.h" #include "util/config.h" #include <linux/string.h> diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 827e4800d862..c37a78677955 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -23,6 +23,7 @@ #include "util/time-utils.h" #include "util/annotate.h" #include "util/map.h" +#include <linux/err.h> #include <linux/zalloc.h> #include <subcmd/pager.h> #include <subcmd/parse-options.h> @@ -1153,9 +1154,9 @@ static int check_file_brstack(void) data__for_each_file(i, d) { d->session = perf_session__new(&d->data, false, &pdiff.tool); - if (!d->session) { + if (IS_ERR(d->session)) { pr_err("Failed to open %s\n", d->data.path); - return -1; + return PTR_ERR(d->session); } has_br_stack = perf_header__has_feat(&d->session->header, @@ -1185,9 +1186,9 @@ static int __cmd_diff(void) data__for_each_file(i, d) { d->session = perf_session__new(&d->data, false, &pdiff.tool); - if (!d->session) { + if (IS_ERR(d->session)) { + ret = PTR_ERR(d->session); pr_err("Failed to open %s\n", d->data.path); - ret = -1; goto out_delete; } diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 238fa3876805..440501994931 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -5,18 +5,18 @@ */ #include "builtin.h" -#include "util/util.h" - #include <linux/list.h> #include "perf.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/evsel_fprintf.h" #include "util/parse-events.h" #include <subcmd/parse-options.h> #include "util/session.h" #include "util/data.h" #include "util/debug.h" +#include <linux/err.h> static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { @@ -30,8 +30,8 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details bool has_tracepoint = false; session = perf_session__new(&data, 0, NULL); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); evlist__for_each_entry(session->evlist, pos) { perf_evsel__fprintf(pos, details, stdout); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index c14f40b858bc..372ecb3e2c06 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -21,7 +21,9 @@ #include "util/auxtrace.h" #include "util/jit.h" #include "util/symbol.h" +#include "util/synthetic-events.h" #include "util/thread.h" +#include <linux/err.h> #include <subcmd/parse-options.h> @@ -834,8 +836,8 @@ int cmd_inject(int argc, const char **argv) data.path = inject.input_name; inject.session = perf_session__new(&data, true, &inject.tool); - if (inject.session == NULL) - return -1; + if (IS_ERR(inject.session)) + return PTR_ERR(inject.session); if (zstd_init(&(inject.session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed.\n"); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index b5682beaad72..1e61e353f579 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -14,6 +14,7 @@ #include "util/tool.h" #include "util/callchain.h" #include "util/time-utils.h" +#include <linux/err.h> #include <subcmd/pager.h> #include <subcmd/parse-options.h> @@ -1956,8 +1957,8 @@ int cmd_kmem(int argc, const char **argv) data.path = input_name; kmem_session = session = perf_session__new(&data, false, &perf_kmem); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); ret = -1; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 0a4fcbe32bf6..2227e2f42c09 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -5,6 +5,7 @@ #include "util/build-id.h" #include "util/evsel.h" #include "util/evlist.h" +#include "util/mmap.h" #include "util/term.h" #include "util/symbol.h" #include "util/thread.h" @@ -17,9 +18,11 @@ #include "util/debug.h" #include "util/tool.h" #include "util/stat.h" +#include "util/synthetic-events.h" #include "util/top.h" #include "util/data.h" #include "util/ordered-events.h" +#include "util/kvm-stat.h" #include "ui/ui.h" #include <sys/prctl.h> @@ -31,6 +34,7 @@ #include <sys/stat.h> #include <fcntl.h> +#include <linux/err.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/time64.h> @@ -58,7 +62,6 @@ static const char *get_filename_for_perf_kvm(void) } #ifdef HAVE_KVM_STAT_SUPPORT -#include "util/kvm-stat.h" void exit_event_get_key(struct evsel *evsel, struct perf_sample *sample, @@ -748,7 +751,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, { struct evlist *evlist = kvm->evlist; union perf_event *event; - struct perf_mmap *md; + struct mmap *md; u64 timestamp; s64 n = 0; int err; @@ -799,7 +802,7 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm) s64 n, ntotal = 0; u64 flush_time = ULLONG_MAX, mmap_time; - for (i = 0; i < kvm->evlist->nr_mmaps; i++) { + for (i = 0; i < kvm->evlist->core.nr_mmaps; i++) { n = perf_kvm__mmap_read_idx(kvm, i, &mmap_time); if (n < 0) return -1; @@ -964,10 +967,10 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) goto out; } - if (perf_evlist__add_pollfd(kvm->evlist, kvm->timerfd) < 0) + if (evlist__add_pollfd(kvm->evlist, kvm->timerfd) < 0) goto out; - nr_stdin = perf_evlist__add_pollfd(kvm->evlist, fileno(stdin)); + nr_stdin = evlist__add_pollfd(kvm->evlist, fileno(stdin)); if (nr_stdin < 0) goto out; @@ -978,7 +981,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) evlist__enable(kvm->evlist); while (!done) { - struct fdarray *fda = &kvm->evlist->pollfd; + struct fdarray *fda = &kvm->evlist->core.pollfd; int rc; rc = perf_kvm__mmap_read(kvm); @@ -1058,7 +1061,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) goto out; } - if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) { + if (evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) { ui__error("Failed to mmap the events: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); evlist__close(evlist); @@ -1090,9 +1093,9 @@ static int read_events(struct perf_kvm_stat *kvm) kvm->tool = eops; kvm->session = perf_session__new(&file, false, &kvm->tool); - if (!kvm->session) { + if (IS_ERR(kvm->session)) { pr_err("Initializing perf session failed\n"); - return -1; + return PTR_ERR(kvm->session); } symbol__init(&kvm->session->header.env); @@ -1445,8 +1448,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, * perf session */ kvm->session = perf_session__new(&data, false, &kvm->tool); - if (kvm->session == NULL) { - err = -1; + if (IS_ERR(kvm->session)) { + err = PTR_ERR(kvm->session); goto out; } kvm->session->evlist = kvm->evlist; @@ -1513,11 +1516,21 @@ perf_stat: } #endif /* HAVE_KVM_STAT_SUPPORT */ +int __weak kvm_add_default_arch_event(int *argc __maybe_unused, + const char **argv __maybe_unused) +{ + return 0; +} + static int __cmd_record(const char *file_name, int argc, const char **argv) { - int rec_argc, i = 0, j; + int rec_argc, i = 0, j, ret; const char **rec_argv; + ret = kvm_add_default_arch_event(&argc, argv); + if (ret) + return -EINVAL; + rec_argc = argc + 2; rec_argv = calloc(rec_argc + 1, sizeof(char *)); rec_argv[i++] = strdup("record"); diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index e290f6b348d8..08e62ae9d37e 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -81,9 +81,9 @@ int cmd_list(int argc, const char **argv) long_desc_flag, details_flag); else if (strcmp(argv[i], "sdt") == 0) print_sdt_events(NULL, NULL, raw_dump); - else if (strcmp(argv[i], "metric") == 0) + else if (strcmp(argv[i], "metric") == 0 || strcmp(argv[i], "metrics") == 0) metricgroup__print(true, false, NULL, raw_dump, details_flag); - else if (strcmp(argv[i], "metricgroup") == 0) + else if (strcmp(argv[i], "metricgroup") == 0 || strcmp(argv[i], "metricgroups") == 0) metricgroup__print(false, true, NULL, raw_dump, details_flag); else if ((sep = strchr(argv[i], ':')) != NULL) { int sep_idx; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 4c2b7f437cdf..474dfd59d7eb 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -30,6 +30,7 @@ #include <linux/hash.h> #include <linux/kernel.h> #include <linux/zalloc.h> +#include <linux/err.h> static struct perf_session *session; @@ -872,9 +873,9 @@ static int __cmd_report(bool display_info) }; session = perf_session__new(&data, false, &eops); - if (!session) { + if (IS_ERR(session)) { pr_err("Initializing perf session failed\n"); - return -1; + return PTR_ERR(session); } symbol__init(&session->header.env); diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 27d2bde943a8..a13f5817d6fc 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -17,6 +17,7 @@ #include "util/dso.h" #include "util/map.h" #include "util/symbol.h" +#include <linux/err.h> #define MEM_OPERATION_LOAD 0x1 #define MEM_OPERATION_STORE 0x2 @@ -249,8 +250,8 @@ static int report_raw_events(struct perf_mem *mem) struct perf_session *session = perf_session__new(&data, false, &mem->tool); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); if (mem->cpu_list) { ret = perf_session__cpu_bitmap(session, mem->cpu_list, diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 1447004eee8a..23332861de6e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -20,6 +20,7 @@ #include "util/evlist.h" #include "util/evsel.h" #include "util/debug.h" +#include "util/mmap.h" #include "util/target.h" #include "util/session.h" #include "util/tool.h" @@ -38,6 +39,7 @@ #include "util/trigger.h" #include "util/perf-hooks.h" #include "util/cpu-set-sched.h" +#include "util/synthetic-events.h" #include "util/time-utils.h" #include "util/units.h" #include "util/bpf-event.h" @@ -53,6 +55,7 @@ #include <signal.h> #include <sys/mman.h> #include <sys/wait.h> +#include <linux/err.h> #include <linux/string.h> #include <linux/time64.h> #include <linux/zalloc.h> @@ -117,7 +120,7 @@ static bool switch_output_time(struct record *rec) trigger_is_ready(&switch_output_trigger); } -static int record__write(struct record *rec, struct perf_mmap *map __maybe_unused, +static int record__write(struct record *rec, struct mmap *map __maybe_unused, void *bf, size_t size) { struct perf_data_file *file = &rec->session->data->file; @@ -166,7 +169,7 @@ static int record__aio_write(struct aiocb *cblock, int trace_fd, return rc; } -static int record__aio_complete(struct perf_mmap *md, struct aiocb *cblock) +static int record__aio_complete(struct mmap *md, struct aiocb *cblock) { void *rem_buf; off_t rem_off; @@ -212,7 +215,7 @@ static int record__aio_complete(struct perf_mmap *md, struct aiocb *cblock) return rc; } -static int record__aio_sync(struct perf_mmap *md, bool sync_all) +static int record__aio_sync(struct mmap *md, bool sync_all) { struct aiocb **aiocb = md->aio.aiocb; struct aiocb *cblocks = md->aio.cblocks; @@ -253,12 +256,12 @@ struct record_aio { size_t size; }; -static int record__aio_pushfn(struct perf_mmap *map, void *to, void *buf, size_t size) +static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size) { struct record_aio *aio = to; /* - * map->base data pointed by buf is copied into free map->aio.data[] buffer + * map->core.base data pointed by buf is copied into free map->aio.data[] buffer * to release space in the kernel buffer as fast as possible, calling * perf_mmap__consume() from perf_mmap__push() function. * @@ -298,7 +301,7 @@ static int record__aio_pushfn(struct perf_mmap *map, void *to, void *buf, size_t return size; } -static int record__aio_push(struct record *rec, struct perf_mmap *map, off_t *off) +static int record__aio_push(struct record *rec, struct mmap *map, off_t *off) { int ret, idx; int trace_fd = rec->session->data->file.fd; @@ -349,15 +352,15 @@ static void record__aio_mmap_read_sync(struct record *rec) { int i; struct evlist *evlist = rec->evlist; - struct perf_mmap *maps = evlist->mmap; + struct mmap *maps = evlist->mmap; if (!record__aio_enabled(rec)) return; - for (i = 0; i < evlist->nr_mmaps; i++) { - struct perf_mmap *map = &maps[i]; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + struct mmap *map = &maps[i]; - if (map->base) + if (map->core.base) record__aio_sync(map, true); } } @@ -385,7 +388,7 @@ static int record__aio_parse(const struct option *opt, #else /* HAVE_AIO_SUPPORT */ static int nr_cblocks_max = 0; -static int record__aio_push(struct record *rec __maybe_unused, struct perf_mmap *map __maybe_unused, +static int record__aio_push(struct record *rec __maybe_unused, struct mmap *map __maybe_unused, off_t *off __maybe_unused) { return -1; @@ -437,7 +440,7 @@ static int record__mmap_flush_parse(const struct option *opt, if (!opts->mmap_flush) opts->mmap_flush = MMAP_FLUSH_DEFAULT; - flush_max = perf_evlist__mmap_size(opts->mmap_pages); + flush_max = evlist__mmap_size(opts->mmap_pages); flush_max /= 4; if (opts->mmap_flush > flush_max) opts->mmap_flush = flush_max; @@ -480,7 +483,7 @@ static int process_synthesized_event(struct perf_tool *tool, return record__write(rec, NULL, event, event->header.size); } -static int record__pushfn(struct perf_mmap *map, void *to, void *bf, size_t size) +static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size) { struct record *rec = to; @@ -525,7 +528,7 @@ static void record__sig_exit(void) #ifdef HAVE_AUXTRACE_SUPPORT static int record__process_auxtrace(struct perf_tool *tool, - struct perf_mmap *map, + struct mmap *map, union perf_event *event, void *data1, size_t len1, void *data2, size_t len2) { @@ -563,7 +566,7 @@ static int record__process_auxtrace(struct perf_tool *tool, } static int record__auxtrace_mmap_read(struct record *rec, - struct perf_mmap *map) + struct mmap *map) { int ret; @@ -579,7 +582,7 @@ static int record__auxtrace_mmap_read(struct record *rec, } static int record__auxtrace_mmap_read_snapshot(struct record *rec, - struct perf_mmap *map) + struct mmap *map) { int ret; @@ -600,8 +603,8 @@ static int record__auxtrace_read_snapshot_all(struct record *rec) int i; int rc = 0; - for (i = 0; i < rec->evlist->nr_mmaps; i++) { - struct perf_mmap *map = &rec->evlist->mmap[i]; + for (i = 0; i < rec->evlist->core.nr_mmaps; i++) { + struct mmap *map = &rec->evlist->mmap[i]; if (!map->auxtrace_mmap.base) continue; @@ -666,7 +669,7 @@ static int record__auxtrace_init(struct record *rec) static inline int record__auxtrace_mmap_read(struct record *rec __maybe_unused, - struct perf_mmap *map __maybe_unused) + struct mmap *map __maybe_unused) { return 0; } @@ -705,7 +708,7 @@ static int record__mmap_evlist(struct record *rec, if (opts->affinity != PERF_AFFINITY_SYS) cpu__setup_cpunode_map(); - if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, + if (evlist__mmap_ex(evlist, opts->mmap_pages, opts->auxtrace_mmap_pages, opts->auxtrace_snapshot_mode, opts->nr_cblocks, opts->affinity, @@ -753,9 +756,9 @@ static int record__open(struct record *rec) if (perf_evlist__add_dummy(evlist)) return -ENOMEM; - pos = perf_evlist__first(evlist); + pos = evlist__first(evlist); pos->tracking = 0; - pos = perf_evlist__last(evlist); + pos = evlist__last(evlist); pos->tracking = 1; pos->core.attr.enable_on_exec = 1; } @@ -786,6 +789,17 @@ try_again: pos->supported = true; } + if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(evlist)) { + pr_warning( +"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n" +"check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n" +"Samples in kernel functions may not be resolved if a suitable vmlinux\n" +"file is not found in the buildid cache or in the vmlinux path.\n\n" +"Samples in kernel modules won't be resolved at all.\n\n" +"If some relocation was applied (e.g. kexec) symbols may be misresolved\n" +"even with a suitable vmlinux or kallsyms file.\n\n"); + } + if (perf_evlist__apply_filters(evlist, &pos)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", pos->filter, perf_evsel__name(pos), errno, @@ -888,7 +902,7 @@ static struct perf_event_header finished_round_event = { .type = PERF_RECORD_FINISHED_ROUND, }; -static void record__adjust_affinity(struct record *rec, struct perf_mmap *map) +static void record__adjust_affinity(struct record *rec, struct mmap *map) { if (rec->opts.affinity != PERF_AFFINITY_SYS && !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) { @@ -935,7 +949,7 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist, u64 bytes_written = rec->bytes_written; int i; int rc = 0; - struct perf_mmap *maps; + struct mmap *maps; int trace_fd = rec->data.file.fd; off_t off = 0; @@ -952,20 +966,20 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist, if (record__aio_enabled(rec)) off = record__aio_get_pos(trace_fd); - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { u64 flush = 0; - struct perf_mmap *map = &maps[i]; + struct mmap *map = &maps[i]; - if (map->base) { + if (map->core.base) { record__adjust_affinity(rec, map); if (synch) { - flush = map->flush; - map->flush = 1; + flush = map->core.flush; + map->core.flush = 1; } if (!record__aio_enabled(rec)) { if (perf_mmap__push(map, rec, record__pushfn) < 0) { if (synch) - map->flush = flush; + map->core.flush = flush; rc = -1; goto out; } @@ -973,13 +987,13 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist, if (record__aio_push(rec, map, &off) < 0) { record__aio_set_pos(trace_fd, off); if (synch) - map->flush = flush; + map->core.flush = flush; rc = -1; goto out; } } if (synch) - map->flush = flush; + map->core.flush = flush; } if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode && @@ -1180,23 +1194,14 @@ static void workload_exec_failed_signal(int signo __maybe_unused, static void snapshot_sig_handler(int sig); static void alarm_sig_handler(int sig); -int __weak -perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, - struct perf_tool *tool __maybe_unused, - perf_event__handler_t process __maybe_unused, - struct machine *machine __maybe_unused) -{ - return 0; -} - static const struct perf_event_mmap_page * perf_evlist__pick_pc(struct evlist *evlist) { if (evlist) { - if (evlist->mmap && evlist->mmap[0].base) - return evlist->mmap[0].base; - if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base) - return evlist->overwrite_mmap[0].base; + if (evlist->mmap && evlist->mmap[0].core.base) + return evlist->mmap[0].core.base; + if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].core.base) + return evlist->overwrite_mmap[0].core.base; } return NULL; } @@ -1362,9 +1367,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } session = perf_session__new(data, false, tool); - if (session == NULL) { + if (IS_ERR(session)) { pr_err("Perf session creation failed.\n"); - return -1; + return PTR_ERR(session); } fd = perf_data__fd(data); @@ -1407,7 +1412,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = -1; goto out_child; } - session->header.env.comp_mmap_len = session->evlist->mmap_len; + session->header.env.comp_mmap_len = session->evlist->core.mmap_len; err = bpf__apply_obj_config(); if (err) { @@ -1610,7 +1615,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (hits == rec->samples) { if (done || draining) break; - err = perf_evlist__poll(rec->evlist, -1); + err = evlist__poll(rec->evlist, -1); /* * Propagate error, only if there's any. Ignore positive * number of returned events and interrupt error. @@ -1619,7 +1624,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = 0; waking++; - if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0) + if (evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0) draining = true; } @@ -1976,7 +1981,7 @@ out_free: static void switch_output_size_warn(struct record *rec) { - u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages); + u64 wakeup_size = evlist__mmap_size(rec->opts.mmap_pages); struct switch_output *s = &rec->switch_output; wakeup_size /= 2; @@ -2371,16 +2376,6 @@ int cmd_record(int argc, const char **argv) err = -ENOMEM; - if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist)) - pr_warning( -"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n" -"check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n" -"Samples in kernel functions may not be resolved if a suitable vmlinux\n" -"file is not found in the buildid cache or in the vmlinux path.\n\n" -"Samples in kernel modules won't be resolved at all.\n\n" -"If some relocation was applied (e.g. kexec) symbols may be misresolved\n" -"even with a suitable vmlinux or kallsyms file.\n\n"); - if (rec->no_buildid_cache || rec->no_buildid) { disable_buildid_cache(); } else if (rec->switch_output.enabled) { diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index b18fab94d38d..aae0e57c60fb 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -48,7 +48,7 @@ #include "util/auxtrace.h" #include "util/units.h" #include "util/branch.h" -#include "util/util.h" +#include "util/util.h" // perf_tip() #include "ui/ui.h" #include "ui/progress.h" @@ -1269,8 +1269,8 @@ int cmd_report(int argc, const char **argv) repeat: session = perf_session__new(&data, false, &report.tool); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); ret = evswitch__init(&report.evswitch, session->evlist, stderr); if (ret) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index ec96d64aec69..5cacc4f84c8d 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3,8 +3,10 @@ #include "perf.h" #include "perf-sys.h" +#include "util/cpumap.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/evsel_fprintf.h" #include "util/symbol.h" #include "util/thread.h" #include "util/header.h" @@ -23,6 +25,7 @@ #include "util/trace-event.h" #include "util/debug.h" +#include "util/event.h" #include <linux/kernel.h> #include <linux/log2.h> @@ -36,7 +39,9 @@ #include <pthread.h> #include <math.h> #include <api/fs/fs.h> +#include <perf/cpumap.h> #include <linux/time64.h> +#include <linux/err.h> #include <linux/ctype.h> @@ -1794,9 +1799,9 @@ static int perf_sched__read_events(struct perf_sched *sched) int rc = -1; session = perf_session__new(&data, false, &sched->tool); - if (session == NULL) { - pr_debug("No Memory for session\n"); - return -1; + if (IS_ERR(session)) { + pr_debug("Error creating perf session"); + return PTR_ERR(session); } symbol__init(&session->header.env); @@ -2051,7 +2056,7 @@ static void timehist_print_sample(struct perf_sched *sched, EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE | EVSEL__PRINT_CALLCHAIN_ARROW | EVSEL__PRINT_SKIP_IGNORED, - &callchain_cursor, stdout); + &callchain_cursor, symbol_conf.bt_stop_list, stdout); out: printf("\n"); @@ -2986,8 +2991,8 @@ static int perf_sched__timehist(struct perf_sched *sched) symbol_conf.use_callchain = sched->show_callchain; session = perf_session__new(&data, false, &sched->tool); - if (session == NULL) - return -ENOMEM; + if (IS_ERR(session)) + return PTR_ERR(session); evlist = session->evlist; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index e079b34201f2..286fc70d7402 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -17,6 +17,7 @@ #include "util/trace-event.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/evsel_fprintf.h" #include "util/evswitch.h" #include "util/sort.h" #include "util/data.h" @@ -52,6 +53,7 @@ #include <unistd.h> #include <subcmd/pager.h> #include <perf/evlist.h> +#include <linux/err.h> #include "util/record.h" #include "util/util.h" #include "perf.h" @@ -1324,7 +1326,8 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, } else printed += fprintf(fp, "\n"); - printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, fp); + printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, + symbol_conf.bt_stop_list, fp); } /* print branch_to information */ @@ -1866,7 +1869,8 @@ static void process_event(struct perf_script *script, cursor = &callchain_cursor; fputc(cursor ? '\n' : ' ', fp); - sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, fp); + sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, + symbol_conf.bt_stop_list, fp); } if (PRINT_FIELD(IREGS)) @@ -1915,7 +1919,7 @@ static void __process_stat(struct evsel *counter, u64 tstamp) int cpu, thread; static int header_printed; - if (counter->system_wide) + if (counter->core.system_wide) nthreads = 1; if (!header_printed) { @@ -2042,7 +2046,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, return err; evlist = *pevlist; - evsel = perf_evlist__last(*pevlist); + evsel = evlist__last(*pevlist); if (!evsel->priv) { if (scr->per_event_dump) { @@ -3083,8 +3087,8 @@ int find_scripts(char **scripts_array, char **scripts_path_array, int num, int i = 0; session = perf_session__new(&data, false, NULL); - if (!session) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); @@ -3754,8 +3758,8 @@ int cmd_script(int argc, const char **argv) } session = perf_session__new(&data, false, &script.tool); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); if (header || header_only) { script.tool.show_feat_hdr = SHOW_FEAT_HEADER; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7e17bf9f700a..468fc49420ce 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -61,6 +61,7 @@ #include "util/tool.h" #include "util/string2.h" #include "util/metricgroup.h" +#include "util/synthetic-events.h" #include "util/target.h" #include "util/time-utils.h" #include "util/top.h" @@ -82,6 +83,7 @@ #include <unistd.h> #include <sys/time.h> #include <sys/resource.h> +#include <linux/err.h> #include <linux/ctype.h> #include <perf/evlist.h> @@ -233,7 +235,7 @@ static int write_stat_round_event(u64 tm, u64 type) #define WRITE_STAT_ROUND_EVENT(time, interval) \ write_stat_round_event(time, PERF_STAT_ROUND_TYPE__ ## interval) -#define SID(e, x, y) xyarray__entry(e->sample_id, x, y) +#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y) static int perf_evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread, @@ -276,7 +278,7 @@ static int read_counter(struct evsel *counter, struct timespec *rs) if (!counter->supported) return -ENOENT; - if (counter->system_wide) + if (counter->core.system_wide) nthreads = 1; for (thread = 0; thread < nthreads; thread++) { @@ -540,8 +542,8 @@ try_again: if (err < 0) return err; - err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list, - process_synthesized_event, is_pipe); + err = perf_event__synthesize_stat_events(&stat_config, NULL, evsel_list, + process_synthesized_event, is_pipe); if (err < 0) return err; } @@ -822,18 +824,6 @@ static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused, return cpu_map__get_core(map, cpu, NULL); } -static int cpu_map__get_max(struct perf_cpu_map *map) -{ - int i, max = -1; - - for (i = 0; i < map->nr; i++) { - if (map->map[i] > max) - max = map->map[i]; - } - - return max; -} - static int perf_stat__get_aggr(struct perf_stat_config *config, aggr_get_id_t get_id, struct perf_cpu_map *map, int idx) { @@ -928,7 +918,7 @@ static int perf_stat_init_aggr_mode(void) * taking the highest cpu number to be the size of * the aggregation translate cpumap. */ - nr = cpu_map__get_max(evsel_list->core.cpus); + nr = perf_cpu_map__max(evsel_list->core.cpus); stat_config.cpus_aggr_map = perf_cpu_map__empty_new(nr + 1); return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } @@ -1447,9 +1437,9 @@ static int __cmd_record(int argc, const char **argv) } session = perf_session__new(data, false, NULL); - if (session == NULL) { - pr_err("Perf session creation failed.\n"); - return -1; + if (IS_ERR(session)) { + pr_err("Perf session creation failed\n"); + return PTR_ERR(session); } init_features(session); @@ -1646,8 +1636,8 @@ static int __cmd_report(int argc, const char **argv) perf_stat.data.mode = PERF_DATA_MODE_READ; session = perf_session__new(&perf_stat.data, false, &perf_stat.tool); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); perf_stat.session = session; stat_config.output = stderr; @@ -1681,7 +1671,7 @@ static void setup_system_wide(int forks) struct evsel *counter; evlist__for_each_entry(evsel_list, counter) { - if (!counter->system_wide) + if (!counter->core.system_wide) return; } @@ -1963,8 +1953,11 @@ int cmd_stat(int argc, const char **argv) fprintf(output, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); + if (run_idx != 0) + perf_evlist__reset_prev_raw_counts(evsel_list); + status = run_perf_stat(argc, argv, run_idx); - if (forever && status != -1) { + if (forever && status != -1 && !interval) { print_counters(NULL, argc, argv); perf_stat__reset_stats(); } diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index e0e822695a29..9e84fae9b096 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -35,6 +35,7 @@ #include "util/tool.h" #include "util/data.h" #include "util/debug.h" +#include <linux/err.h> #ifdef LACKS_OPEN_MEMSTREAM_PROTOTYPE FILE *open_memstream(char **ptr, size_t *sizeloc); @@ -1601,8 +1602,8 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name) &tchart->tool); int ret = -EINVAL; - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); symbol__init(&session->header.env); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 726e3f2dd8c7..1f60124eb19b 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -27,11 +27,14 @@ #include "util/dso.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/evsel_config.h" #include "util/event.h" #include "util/machine.h" #include "util/map.h" +#include "util/mmap.h" #include "util/session.h" #include "util/symbol.h" +#include "util/synthetic-events.h" #include "util/top.h" #include "util/util.h" #include <linux/rbtree.h> @@ -76,6 +79,7 @@ #include <linux/stringify.h> #include <linux/time64.h> #include <linux/types.h> +#include <linux/err.h> #include <linux/ctype.h> @@ -528,7 +532,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) prompt_integer(&counter, "Enter details event counter"); if (counter >= top->evlist->core.nr_entries) { - top->sym_evsel = perf_evlist__first(top->evlist); + top->sym_evsel = evlist__first(top->evlist); fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel)); sleep(1); break; @@ -537,7 +541,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) if (top->sym_evsel->idx == counter) break; } else - top->sym_evsel = perf_evlist__first(top->evlist); + top->sym_evsel = evlist__first(top->evlist); break; case 'f': prompt_integer(&top->count_filter, "Enter display event count filter"); @@ -861,7 +865,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) { struct record_opts *opts = &top->record_opts; struct evlist *evlist = top->evlist; - struct perf_mmap *md; + struct mmap *md; union perf_event *event; md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx]; @@ -901,7 +905,7 @@ static void perf_top__mmap_read(struct perf_top *top) if (overwrite) perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); - for (i = 0; i < top->evlist->nr_mmaps; i++) + for (i = 0; i < top->evlist->core.nr_mmaps; i++) perf_top__mmap_read_idx(top, i); if (overwrite) { @@ -959,7 +963,7 @@ static int perf_top__overwrite_check(struct perf_top *top) /* has term for current event */ if ((overwrite < 0) && (set >= 0)) { /* if it's first event, set overwrite */ - if (evsel == perf_evlist__first(evlist)) + if (evsel == evlist__first(evlist)) overwrite = set; else return -1; @@ -983,7 +987,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top, return 0; /* only fall back when first event fails */ - if (evsel != perf_evlist__first(evlist)) + if (evsel != evlist__first(evlist)) return 0; evlist__for_each_entry(evlist, counter) @@ -1040,7 +1044,7 @@ try_again: } } - if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) { + if (evlist__mmap(evlist, opts->mmap_pages) < 0) { ui__error("Failed to mmap with %d (%s)\n", errno, str_error_r(errno, msg, sizeof(msg))); goto out_err; @@ -1304,7 +1308,7 @@ static int __cmd_top(struct perf_top *top) } /* Wait for a minimal set of events before starting the snapshot */ - perf_evlist__poll(top->evlist, 100); + evlist__poll(top->evlist, 100); perf_top__mmap_read(top); @@ -1314,7 +1318,7 @@ static int __cmd_top(struct perf_top *top) perf_top__mmap_read(top); if (opts->overwrite || (hits == top->samples)) - ret = perf_evlist__poll(top->evlist, 100); + ret = evlist__poll(top->evlist, 100); if (resize) { perf_top__resize(top); @@ -1641,7 +1645,7 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } - top.sym_evsel = perf_evlist__first(top.evlist); + top.sym_evsel = evlist__first(top.evlist); if (!callchain_param.enabled) { symbol_conf.cumulate_callchain = false; @@ -1671,8 +1675,8 @@ int cmd_top(int argc, const char **argv) } top.session = perf_session__new(NULL, false, NULL); - if (top.session == NULL) { - status = -1; + if (IS_ERR(top.session)) { + status = PTR_ERR(top.session); goto out_delete_evlist; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 0f633f0d6be8..bb5130d02155 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -28,8 +28,12 @@ #include "util/dso.h" #include "util/env.h" #include "util/event.h" +#include "util/evsel.h" +#include "util/evsel_fprintf.h" +#include "util/synthetic-events.h" #include "util/evlist.h" #include "util/evswitch.h" +#include "util/mmap.h" #include <subcmd/pager.h> #include <subcmd/exec-cmd.h> #include "util/machine.h" @@ -2074,7 +2078,7 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam EVSEL__PRINT_DSO | EVSEL__PRINT_UNKNOWN_AS_ADDR; - return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output); + return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, symbol_conf.bt_stop_list, trace->output); } static const char *errno_to_name(struct evsel *evsel, int err) @@ -3408,7 +3412,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->dump.map) bpf_map__fprintf(trace->dump.map, trace->output); - err = perf_evlist__mmap(evlist, trace->opts.mmap_pages); + err = evlist__mmap(evlist, trace->opts.mmap_pages); if (err < 0) goto out_error_mmap; @@ -3425,7 +3429,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) trace->multiple_threads = perf_thread_map__pid(evlist->core.threads, 0) == -1 || evlist->core.threads->nr > 1 || - perf_evlist__first(evlist)->core.attr.inherit; + evlist__first(evlist)->core.attr.inherit; /* * Now that we already used evsel->core.attr to ask the kernel to setup the @@ -3441,9 +3445,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv) again: before = trace->nr_events; - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { union perf_event *event; - struct perf_mmap *md; + struct mmap *md; md = &evlist->mmap[i]; if (perf_mmap__read_init(md) < 0) @@ -3472,8 +3476,8 @@ again: if (trace->nr_events == before) { int timeout = done ? 100 : -1; - if (!draining && perf_evlist__poll(evlist, timeout) > 0) { - if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0) + if (!draining && evlist__poll(evlist, timeout) > 0) { + if (evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0) draining = true; goto again; @@ -3584,8 +3588,8 @@ static int trace__replay(struct trace *trace) trace->multiple_threads = true; session = perf_session__new(&data, false, &trace->tool); - if (session == NULL) - return -1; + if (IS_ERR(session)) + return PTR_ERR(session); if (trace->opts.target.pid) symbol_conf.pid_list_str = strdup(trace->opts.target.pid); diff --git a/tools/perf/jvmti/Build b/tools/perf/jvmti/Build index eaeb8cb5379b..1e148bbdf820 100644 --- a/tools/perf/jvmti/Build +++ b/tools/perf/jvmti/Build @@ -1,8 +1,17 @@ jvmti-y += libjvmti.o jvmti-y += jvmti_agent.o +# For strlcpy +jvmti-y += libstring.o + CFLAGS_jvmti = -fPIC -DPIC -I$(JDIR)/include -I$(JDIR)/include/linux CFLAGS_REMOVE_jvmti = -Wmissing-declarations CFLAGS_REMOVE_jvmti += -Wstrict-prototypes CFLAGS_REMOVE_jvmti += -Wextra CFLAGS_REMOVE_jvmti += -Wwrite-strings + +CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" + +$(OUTPUT)jvmti/libstring.o: ../lib/string.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/lib/Makefile b/tools/perf/lib/Makefile index a67efb8d9d39..85ccb8c439a4 100644 --- a/tools/perf/lib/Makefile +++ b/tools/perf/lib/Makefile @@ -59,7 +59,13 @@ else CFLAGS := -g -Wall endif -INCLUDES = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/ -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi +INCLUDES = \ +-I$(srctree)/tools/perf/lib/include \ +-I$(srctree)/tools/lib/ \ +-I$(srctree)/tools/include \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/ \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \ +-I$(srctree)/tools/include/uapi # Append required CFLAGS override CFLAGS += $(EXTRA_WARNINGS) @@ -88,13 +94,34 @@ LIBPERF_PC := $(OUTPUT)libperf.pc LIBPERF_ALL := $(LIBPERF_A) $(OUTPUT)libperf.so* +LIB_DIR := $(srctree)/tools/lib/api/ + +ifneq ($(OUTPUT),) +ifneq ($(subdir),) + API_PATH=$(OUTPUT)/../lib/api/ +else + API_PATH=$(OUTPUT) +endif +else + API_PATH=$(LIB_DIR) +endif + +LIBAPI = $(API_PATH)libapi.a + +$(LIBAPI): FORCE + $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) $(OUTPUT)libapi.a + +$(LIBAPI)-clean: + $(call QUIET_CLEAN, libapi) + $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null + $(LIBPERF_IN): FORCE $(Q)$(MAKE) $(build)=libperf $(LIBPERF_A): $(LIBPERF_IN) $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) -$(LIBPERF_SO): $(LIBPERF_IN) +$(LIBPERF_SO): $(LIBPERF_IN) $(LIBAPI) $(QUIET_LINK)$(CC) --shared -Wl,-soname,libperf.so \ -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@ @ln -sf $(@F) $(OUTPUT)libperf.so @@ -106,12 +133,12 @@ libs: $(LIBPERF_A) $(LIBPERF_SO) $(LIBPERF_PC) all: fixdep $(Q)$(MAKE) libs -clean: +clean: $(LIBAPI)-clean $(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \ *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd LIBPERF-CFLAGS $(LIBPERF_PC) $(Q)$(MAKE) -C tests clean -tests: +tests: libs $(Q)$(MAKE) -C tests $(Q)$(MAKE) -C tests run @@ -146,6 +173,7 @@ install_headers: $(call do_install,include/perf/threadmap.h,$(prefix)/include/perf,644); \ $(call do_install,include/perf/evlist.h,$(prefix)/include/perf,644); \ $(call do_install,include/perf/evsel.h,$(prefix)/include/perf,644); + $(call do_install,include/perf/event.h,$(prefix)/include/perf,644); install_pkgconfig: $(LIBPERF_PC) $(call QUIET_INSTALL, $(LIBPERF_PC)) \ diff --git a/tools/perf/lib/core.c b/tools/perf/lib/core.c index 29d5e3348718..d0b9ae422b9f 100644 --- a/tools/perf/lib/core.c +++ b/tools/perf/lib/core.c @@ -4,7 +4,9 @@ #include <stdio.h> #include <stdarg.h> +#include <unistd.h> #include <perf/core.h> +#include <internal/lib.h> #include "internal.h" static int __base_pr(enum libperf_print_level level, const char *format, @@ -15,11 +17,6 @@ static int __base_pr(enum libperf_print_level level, const char *format, static libperf_print_fn_t __libperf_pr = __base_pr; -void libperf_set_print(libperf_print_fn_t fn) -{ - __libperf_pr = fn; -} - __printf(2, 3) void libperf_print(enum libperf_print_level level, const char *format, ...) { @@ -32,3 +29,9 @@ void libperf_print(enum libperf_print_level level, const char *format, ...) __libperf_pr(level, format, args); va_end(args); } + +void libperf_init(libperf_print_fn_t fn) +{ + page_size = sysconf(_SC_PAGE_SIZE); + __libperf_pr = fn; +} diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c index 1f0e6f334237..2ca1fafa620d 100644 --- a/tools/perf/lib/cpumap.c +++ b/tools/perf/lib/cpumap.c @@ -260,3 +260,15 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu) return -1; } + +int perf_cpu_map__max(struct perf_cpu_map *map) +{ + int i, max = -1; + + for (i = 0; i < map->nr; i++) { + if (map->map[i] > max) + max = map->map[i]; + } + + return max; +} diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c index f4dc9a208332..d1496fee810c 100644 --- a/tools/perf/lib/evlist.c +++ b/tools/perf/lib/evlist.c @@ -1,16 +1,30 @@ // SPDX-License-Identifier: GPL-2.0 #include <perf/evlist.h> #include <perf/evsel.h> +#include <linux/bitops.h> #include <linux/list.h> +#include <linux/hash.h> +#include <sys/ioctl.h> #include <internal/evlist.h> #include <internal/evsel.h> +#include <internal/xyarray.h> #include <linux/zalloc.h> #include <stdlib.h> +#include <errno.h> +#include <unistd.h> +#include <fcntl.h> +#include <signal.h> +#include <poll.h> #include <perf/cpumap.h> #include <perf/threadmap.h> +#include <api/fd/array.h> void perf_evlist__init(struct perf_evlist *evlist) { + int i; + + for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i) + INIT_HLIST_HEAD(&evlist->heads[i]); INIT_LIST_HEAD(&evlist->entries); evlist->nr_entries = 0; } @@ -157,3 +171,113 @@ void perf_evlist__disable(struct perf_evlist *evlist) perf_evlist__for_each_entry(evlist, evsel) perf_evsel__disable(evsel); } + +u64 perf_evlist__read_format(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + + return first->attr.read_format; +} + +#define SID(e, x, y) xyarray__entry(e->sample_id, x, y) + +static void perf_evlist__id_hash(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, u64 id) +{ + int hash; + struct perf_sample_id *sid = SID(evsel, cpu, thread); + + sid->id = id; + sid->evsel = evsel; + hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS); + hlist_add_head(&sid->node, &evlist->heads[hash]); +} + +void perf_evlist__id_add(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, u64 id) +{ + perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + evsel->id[evsel->ids++] = id; +} + +int perf_evlist__id_add_fd(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, int fd) +{ + u64 read_data[4] = { 0, }; + int id_idx = 1; /* The first entry is the counter value */ + u64 id; + int ret; + + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); + if (!ret) + goto add; + + if (errno != ENOTTY) + return -1; + + /* Legacy way to get event id.. All hail to old kernels! */ + + /* + * This way does not work with group format read, so bail + * out in that case. + */ + if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP) + return -1; + + if (!(evsel->attr.read_format & PERF_FORMAT_ID) || + read(fd, &read_data, sizeof(read_data)) == -1) + return -1; + + if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + ++id_idx; + if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + ++id_idx; + + id = read_data[id_idx]; + +add: + perf_evlist__id_add(evlist, evsel, cpu, thread, id); + return 0; +} + +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) +{ + int nr_cpus = perf_cpu_map__nr(evlist->cpus); + int nr_threads = perf_thread_map__nr(evlist->threads); + int nfds = 0; + struct perf_evsel *evsel; + + perf_evlist__for_each_entry(evlist, evsel) { + if (evsel->system_wide) + nfds += nr_cpus; + else + nfds += nr_cpus * nr_threads; + } + + if (fdarray__available_entries(&evlist->pollfd) < nfds && + fdarray__grow(&evlist->pollfd, nfds) < 0) + return -ENOMEM; + + return 0; +} + +int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, + void *ptr, short revent) +{ + int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP); + + if (pos >= 0) { + evlist->pollfd.priv[pos].ptr = ptr; + fcntl(fd, F_SETFL, O_NONBLOCK); + } + + return pos; +} + +int perf_evlist__poll(struct perf_evlist *evlist, int timeout) +{ + return fdarray__poll(&evlist->pollfd, timeout); +} diff --git a/tools/perf/lib/evsel.c b/tools/perf/lib/evsel.c index 24abc80dd767..a8cb582e2721 100644 --- a/tools/perf/lib/evsel.c +++ b/tools/perf/lib/evsel.c @@ -230,3 +230,33 @@ struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel) { return &evsel->attr; } + +int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + if (ncpus == 0 || nthreads == 0) + return 0; + + if (evsel->system_wide) + nthreads = 1; + + evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); + if (evsel->sample_id == NULL) + return -ENOMEM; + + evsel->id = zalloc(ncpus * nthreads * sizeof(u64)); + if (evsel->id == NULL) { + xyarray__delete(evsel->sample_id); + evsel->sample_id = NULL; + return -ENOMEM; + } + + return 0; +} + +void perf_evsel__free_id(struct perf_evsel *evsel) +{ + xyarray__delete(evsel->sample_id); + evsel->sample_id = NULL; + zfree(&evsel->id); + evsel->ids = 0; +} diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h index 448891f06e3e..9f440ab12b76 100644 --- a/tools/perf/lib/include/internal/evlist.h +++ b/tools/perf/lib/include/internal/evlist.h @@ -3,6 +3,11 @@ #define __LIBPERF_INTERNAL_EVLIST_H #include <linux/list.h> +#include <api/fd/array.h> +#include <internal/evsel.h> + +#define PERF_EVLIST__HLIST_BITS 8 +#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) struct perf_cpu_map; struct perf_thread_map; @@ -13,8 +18,16 @@ struct perf_evlist { bool has_user_cpus; struct perf_cpu_map *cpus; struct perf_thread_map *threads; + int nr_mmaps; + size_t mmap_len; + struct fdarray pollfd; + struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; }; +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); +int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, + void *ptr, short revent); + /** * __perf_evlist__for_each_entry - iterate thru all the evsels * @list: list_head instance to iterate @@ -47,4 +60,24 @@ struct perf_evlist { #define perf_evlist__for_each_entry_reverse(evlist, evsel) \ __perf_evlist__for_each_entry_reverse(&(evlist)->entries, evsel) +static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) +{ + return list_entry(evlist->entries.next, struct perf_evsel, node); +} + +static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) +{ + return list_entry(evlist->entries.prev, struct perf_evsel, node); +} + +u64 perf_evlist__read_format(struct perf_evlist *evlist); + +void perf_evlist__id_add(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, u64 id); + +int perf_evlist__id_add_fd(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, int fd); + #endif /* __LIBPERF_INTERNAL_EVLIST_H */ diff --git a/tools/perf/lib/include/internal/evsel.h b/tools/perf/lib/include/internal/evsel.h index 8b854d1c9b45..a69b8299c36f 100644 --- a/tools/perf/lib/include/internal/evsel.h +++ b/tools/perf/lib/include/internal/evsel.h @@ -4,9 +4,35 @@ #include <linux/types.h> #include <linux/perf_event.h> +#include <stdbool.h> +#include <sys/types.h> struct perf_cpu_map; struct perf_thread_map; +struct xyarray; + +/* + * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are + * more than one entry in the evlist. + */ +struct perf_sample_id { + struct hlist_node node; + u64 id; + struct perf_evsel *evsel; + /* + * 'idx' will be used for AUX area sampling. A sample will have AUX area + * data that will be queued for decoding, where there are separate + * queues for each CPU (per-cpu tracing) or task (per-thread tracing). + * The sample ID can be used to lookup 'idx' which is effectively the + * queue number. + */ + int idx; + int cpu; + pid_t tid; + + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ + u64 period; +}; struct perf_evsel { struct list_head node; @@ -15,9 +41,13 @@ struct perf_evsel { struct perf_cpu_map *own_cpus; struct perf_thread_map *threads; struct xyarray *fd; + struct xyarray *sample_id; + u64 *id; + u32 ids; /* parse modifier helper */ int nr_members; + bool system_wide; }; int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); @@ -26,4 +56,7 @@ void perf_evsel__free_fd(struct perf_evsel *evsel); int perf_evsel__read_size(struct perf_evsel *evsel); int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter); +int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__free_id(struct perf_evsel *evsel); + #endif /* __LIBPERF_INTERNAL_EVSEL_H */ diff --git a/tools/perf/lib/include/internal/lib.h b/tools/perf/lib/include/internal/lib.h index 0b56f1201dc9..5175d491b2d4 100644 --- a/tools/perf/lib/include/internal/lib.h +++ b/tools/perf/lib/include/internal/lib.h @@ -2,7 +2,9 @@ #ifndef __LIBPERF_INTERNAL_LIB_H #define __LIBPERF_INTERNAL_LIB_H -#include <unistd.h> +#include <sys/types.h> + +extern unsigned int page_size; ssize_t readn(int fd, void *buf, size_t n); ssize_t writen(int fd, const void *buf, size_t n); diff --git a/tools/perf/lib/include/internal/mmap.h b/tools/perf/lib/include/internal/mmap.h new file mode 100644 index 000000000000..ba1e519c15b9 --- /dev/null +++ b/tools/perf/lib/include/internal/mmap.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_MMAP_H +#define __LIBPERF_INTERNAL_MMAP_H + +#include <linux/compiler.h> +#include <linux/refcount.h> +#include <linux/types.h> +#include <stdbool.h> + +/* perf sample has 16 bits size limit */ +#define PERF_SAMPLE_MAX_SIZE (1 << 16) + +/** + * struct perf_mmap - perf's ring buffer mmap details + * + * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this + */ +struct perf_mmap { + void *base; + int mask; + int fd; + int cpu; + refcount_t refcnt; + u64 prev; + u64 start; + u64 end; + bool overwrite; + u64 flush; + char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); +}; + +#endif /* __LIBPERF_INTERNAL_MMAP_H */ diff --git a/tools/perf/lib/include/perf/core.h b/tools/perf/lib/include/perf/core.h index c341a7b2c874..cfd70e720c1c 100644 --- a/tools/perf/lib/include/perf/core.h +++ b/tools/perf/lib/include/perf/core.h @@ -17,6 +17,6 @@ enum libperf_print_level { typedef int (*libperf_print_fn_t)(enum libperf_print_level level, const char *, va_list ap); -LIBPERF_API void libperf_set_print(libperf_print_fn_t fn); +LIBPERF_API void libperf_init(libperf_print_fn_t fn); #endif /* __LIBPERF_CORE_H */ diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h index 8aa995c59498..ac9aa497f84a 100644 --- a/tools/perf/lib/include/perf/cpumap.h +++ b/tools/perf/lib/include/perf/cpumap.h @@ -16,6 +16,7 @@ LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); +LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map); #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \ for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \ diff --git a/tools/perf/lib/include/perf/evlist.h b/tools/perf/lib/include/perf/evlist.h index 38365f8f3fba..8a2ce0757ab2 100644 --- a/tools/perf/lib/include/perf/evlist.h +++ b/tools/perf/lib/include/perf/evlist.h @@ -31,5 +31,6 @@ LIBPERF_API void perf_evlist__disable(struct perf_evlist *evlist); LIBPERF_API void perf_evlist__set_maps(struct perf_evlist *evlist, struct perf_cpu_map *cpus, struct perf_thread_map *threads); +LIBPERF_API int perf_evlist__poll(struct perf_evlist *evlist, int timeout); #endif /* __LIBPERF_EVLIST_H */ diff --git a/tools/perf/lib/lib.c b/tools/perf/lib/lib.c index 2a81819c3b8c..18658931fc71 100644 --- a/tools/perf/lib/lib.c +++ b/tools/perf/lib/lib.c @@ -5,6 +5,8 @@ #include <linux/kernel.h> #include <internal/lib.h> +unsigned int page_size; + static ssize_t ion(bool is_read, int fd, void *buf, size_t n) { void *buf_start = buf; diff --git a/tools/perf/lib/libperf.map b/tools/perf/lib/libperf.map index dc4d66363bc4..ab8dbde1136c 100644 --- a/tools/perf/lib/libperf.map +++ b/tools/perf/lib/libperf.map @@ -1,6 +1,6 @@ LIBPERF_0.0.1 { global: - libperf_set_print; + libperf_init; perf_cpu_map__dummy_new; perf_cpu_map__get; perf_cpu_map__put; @@ -9,6 +9,7 @@ LIBPERF_0.0.1 { perf_cpu_map__nr; perf_cpu_map__cpu; perf_cpu_map__empty; + perf_cpu_map__max; perf_thread_map__new_dummy; perf_thread_map__set_pid; perf_thread_map__comm; @@ -38,6 +39,7 @@ LIBPERF_0.0.1 { perf_evlist__remove; perf_evlist__next; perf_evlist__set_maps; + perf_evlist__poll; local: *; }; diff --git a/tools/perf/lib/tests/test-cpumap.c b/tools/perf/lib/tests/test-cpumap.c index 76a43cfb83a1..aa34c20df07e 100644 --- a/tools/perf/lib/tests/test-cpumap.c +++ b/tools/perf/lib/tests/test-cpumap.c @@ -1,13 +1,23 @@ // SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> #include <perf/cpumap.h> #include <internal/tests.h> +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + int main(int argc, char **argv) { struct perf_cpu_map *cpus; __T_START; + libperf_init(libperf_print); + cpus = perf_cpu_map__dummy_new(); if (!cpus) return -1; diff --git a/tools/perf/lib/tests/test-evlist.c b/tools/perf/lib/tests/test-evlist.c index 4e1407f20ffd..e6b2ab2e2bde 100644 --- a/tools/perf/lib/tests/test-evlist.c +++ b/tools/perf/lib/tests/test-evlist.c @@ -1,4 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdarg.h> #include <linux/perf_event.h> #include <perf/cpumap.h> #include <perf/threadmap.h> @@ -6,6 +8,12 @@ #include <perf/evsel.h> #include <internal/tests.h> +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + static int test_stat_cpu(void) { struct perf_cpu_map *cpus; @@ -177,6 +185,8 @@ int main(int argc, char **argv) { __T_START; + libperf_init(libperf_print); + test_stat_cpu(); test_stat_thread(); test_stat_thread_enable(); diff --git a/tools/perf/lib/tests/test-evsel.c b/tools/perf/lib/tests/test-evsel.c index 2c648fe5617e..1b6c4285ac2b 100644 --- a/tools/perf/lib/tests/test-evsel.c +++ b/tools/perf/lib/tests/test-evsel.c @@ -1,10 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> #include <linux/perf_event.h> #include <perf/cpumap.h> #include <perf/threadmap.h> #include <perf/evsel.h> #include <internal/tests.h> +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + static int test_stat_cpu(void) { struct perf_cpu_map *cpus; @@ -116,6 +124,8 @@ int main(int argc, char **argv) { __T_START; + libperf_init(libperf_print); + test_stat_cpu(); test_stat_thread(); test_stat_thread_enable(); diff --git a/tools/perf/lib/tests/test-threadmap.c b/tools/perf/lib/tests/test-threadmap.c index 10a4f4cbbdd5..8c5f47247d9e 100644 --- a/tools/perf/lib/tests/test-threadmap.c +++ b/tools/perf/lib/tests/test-threadmap.c @@ -1,13 +1,23 @@ // SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> #include <perf/threadmap.h> #include <internal/tests.h> +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + int main(int argc, char **argv) { struct perf_thread_map *threads; __T_START; + libperf_init(libperf_print); + threads = perf_thread_map__new_dummy(); if (!threads) return -1; diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 1193b923e801..27f94b0bb874 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -12,6 +12,7 @@ #include "util/build-id.h" #include "util/cache.h" #include "util/env.h" +#include <internal/lib.h> // page_size #include <subcmd/exec-cmd.h> #include "util/config.h" #include <subcmd/run-command.h> @@ -20,11 +21,12 @@ #include "util/bpf-loader.h" #include "util/debug.h" #include "util/event.h" -#include "util/util.h" +#include "util/util.h" // usage() #include "ui/ui.h" #include "perf-sys.h" #include <api/fs/fs.h> #include <api/fs/tracing_path.h> +#include <perf/core.h> #include <errno.h> #include <pthread.h> #include <signal.h> @@ -428,6 +430,12 @@ void pthread__unblock_sigwinch(void) pthread_sigmask(SIG_UNBLOCK, &set, NULL); } +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return eprintf(level, verbose, fmt, ap); +} + int main(int argc, const char **argv) { int err; @@ -438,8 +446,7 @@ int main(int argc, const char **argv) exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); pager_init(PERF_PAGER_ENVIRONMENT); - /* The page_size is placed in util object. */ - page_size = sysconf(_SC_PAGE_SIZE); + libperf_init(libperf_print); cmd = extract_argv0_path(argv[0]); if (!cmd) diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README index e62b09b6a844..de7efa2cebd1 100644 --- a/tools/perf/pmu-events/README +++ b/tools/perf/pmu-events/README @@ -30,9 +30,9 @@ the topic. Eg: "Floating-point.json". All the topic JSON files for a CPU model/family should be in a separate sub directory. Thus for the Silvermont X86 CPU: - $ ls tools/perf/pmu-events/arch/x86/Silvermont_core - Cache.json Memory.json Virtual-Memory.json - Frontend.json Pipeline.json + $ ls tools/perf/pmu-events/arch/x86/silvermont + cache.json memory.json virtual-memory.json + frontend.json pipeline.json The JSONs folder for a CPU model/family may be placed in the root arch folder, or may be placed in a vendor sub-folder under the arch folder @@ -94,7 +94,7 @@ users to specify events by their name: where 'pm_1plus_ppc_cmpl' is a Power8 PMU event. -However some errors in processing may cause the perf build to fail. +However some errors in processing may cause the alias build to fail. Mapfile format =============== @@ -119,7 +119,7 @@ where: Header line The header line is the first line in the file, which is - always _IGNORED_. It can empty. + always _IGNORED_. It can be empty. CPUID: CPUID is an arch-specific char string, that can be used @@ -138,15 +138,15 @@ where: files, relative to the directory containing the mapfile.csv Type: - indicates whether the events or "core" or "uncore" events. + indicates whether the events are "core" or "uncore" events. Eg: - $ grep Silvermont tools/perf/pmu-events/arch/x86/mapfile.csv - GenuineIntel-6-37,V13,Silvermont_core,core - GenuineIntel-6-4D,V13,Silvermont_core,core - GenuineIntel-6-4C,V13,Silvermont_core,core + $ grep silvermont tools/perf/pmu-events/arch/x86/mapfile.csv + GenuineIntel-6-37,v13,silvermont,core + GenuineIntel-6-4D,v13,silvermont,core + GenuineIntel-6-4C,v13,silvermont,core i.e the three CPU models use the JSON files (i.e PMU events) listed - in the directory 'tools/perf/pmu-events/arch/x86/Silvermont_core'. + in the directory 'tools/perf/pmu-events/arch/x86/silvermont'. diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json new file mode 100644 index 000000000000..b5e5d055c70d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json @@ -0,0 +1,14 @@ +[ + { + "PublicDescription": "Mispredicted or not predicted branch speculatively executed. This event counts any predictable branch instruction which is mispredicted either due to dynamic misprediction or because the MMU is off and the branches are statically predicted not taken.", + "EventCode": "0x10", + "EventName": "BR_MIS_PRED", + "BriefDescription": "Mispredicted or not predicted branch speculatively executed." + }, + { + "PublicDescription": "Predictable branch speculatively executed. This event counts all predictable branches.", + "EventCode": "0x12", + "EventName": "BR_PRED", + "BriefDescription": "Predictable branch speculatively executed." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json new file mode 100644 index 000000000000..fce7309ae624 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json @@ -0,0 +1,24 @@ +[ + { + "EventCode": "0x11", + "EventName": "CPU_CYCLES", + "BriefDescription": "The number of core clock cycles." + }, + { + "PublicDescription": "Bus access. This event counts for every beat of data transferred over the data channels between the core and the SCU. If both read and write data beats are transferred on a given cycle, this event is counted twice on that cycle. This event counts the sum of BUS_ACCESS_RD and BUS_ACCESS_WR.", + "EventCode": "0x19", + "EventName": "BUS_ACCESS", + "BriefDescription": "Bus access." + }, + { + "EventCode": "0x1D", + "EventName": "BUS_CYCLES", + "BriefDescription": "Bus cycles. This event duplicates CPU_CYCLES." + }, + { + "ArchStdEvent": "BUS_ACCESS_RD" + }, + { + "ArchStdEvent": "BUS_ACCESS_WR" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json new file mode 100644 index 000000000000..24594081c199 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json @@ -0,0 +1,207 @@ +[ + { + "PublicDescription": "L1 instruction cache refill. This event counts any instruction fetch which misses in the cache.", + "EventCode": "0x01", + "EventName": "L1I_CACHE_REFILL", + "BriefDescription": "L1 instruction cache refill" + }, + { + "PublicDescription": "L1 instruction TLB refill. This event counts any refill of the instruction L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", + "EventCode": "0x02", + "EventName": "L1I_TLB_REFILL", + "BriefDescription": "L1 instruction TLB refill" + }, + { + "PublicDescription": "L1 data cache refill. This event counts any load or store operation or page table walk access which causes data to be read from outside the L1, including accesses which do not allocate into L1.", + "EventCode": "0x03", + "EventName": "L1D_CACHE_REFILL", + "BriefDescription": "L1 data cache refill" + }, + { + "PublicDescription": "L1 data cache access. This event counts any load or store operation or page table walk access which looks up in the L1 data cache. In particular, any access which could count the L1D_CACHE_REFILL event causes this event to count.", + "EventCode": "0x04", + "EventName": "L1D_CACHE", + "BriefDescription": "L1 data cache access" + }, + { + "PublicDescription": "L1 data TLB refill. This event counts any refill of the data L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", + "EventCode": "0x05", + "EventName": "L1D_TLB_REFILL", + "BriefDescription": "L1 data TLB refill" + }, + { + "PublicDescription": "Level 1 instruction cache access or Level 0 Macro-op cache access. This event counts any instruction fetch which accesses the L1 instruction cache or L0 Macro-op cache.", + "EventCode": "0x14", + "EventName": "L1I_CACHE", + "BriefDescription": "L1 instruction cache access" + }, + { + "PublicDescription": "L1 data cache Write-Back. This event counts any write-back of data from the L1 data cache to L2 or L3. This counts both victim line evictions and snoops, including cache maintenance operations.", + "EventCode": "0x15", + "EventName": "L1D_CACHE_WB", + "BriefDescription": "L1 data cache Write-Back" + }, + { + "PublicDescription": "L2 data cache access. This event counts any transaction from L1 which looks up in the L2 cache, and any write-back from the L1 to the L2. Snoops from outside the core and cache maintenance operations are not counted.", + "EventCode": "0x16", + "EventName": "L2D_CACHE", + "BriefDescription": "L2 data cache access" + }, + { + "PublicDescription": "L2 data cache refill. This event counts any cacheable transaction from L1 which causes data to be read from outside the core. L2 refills caused by stashes into L2 should not be counted", + "EventCode": "0x17", + "EventName": "L2D_CACHE_REFILL", + "BriefDescription": "L2 data cache refill" + }, + { + "PublicDescription": "L2 data cache write-back. This event counts any write-back of data from the L2 cache to outside the core. This includes snoops to the L2 which return data, regardless of whether they cause an invalidation. Invalidations from the L2 which do not write data outside of the core and snoops which return data from the L1 are not counted", + "EventCode": "0x18", + "EventName": "L2D_CACHE_WB", + "BriefDescription": "L2 data cache write-back" + }, + { + "PublicDescription": "L2 data cache allocation without refill. This event counts any full cache line write into the L2 cache which does not cause a linefill, including write-backs from L1 to L2 and full-line writes which do not allocate into L1.", + "EventCode": "0x20", + "EventName": "L2D_CACHE_ALLOCATE", + "BriefDescription": "L2 data cache allocation without refill" + }, + { + "PublicDescription": "Level 1 data TLB access. This event counts any load or store operation which accesses the data L1 TLB. If both a load and a store are executed on a cycle, this event counts twice. This event counts regardless of whether the MMU is enabled.", + "EventCode": "0x25", + "EventName": "L1D_TLB", + "BriefDescription": "Level 1 data TLB access." + }, + { + "PublicDescription": "Level 1 instruction TLB access. This event counts any instruction fetch which accesses the instruction L1 TLB.This event counts regardless of whether the MMU is enabled.", + "EventCode": "0x26", + "EventName": "L1I_TLB", + "BriefDescription": "Level 1 instruction TLB access" + }, + { + "PublicDescription": "This event counts any full cache line write into the L3 cache which does not cause a linefill, including write-backs from L2 to L3 and full-line writes which do not allocate into L2", + "EventCode": "0x29", + "EventName": "L3D_CACHE_ALLOCATE", + "BriefDescription": "Allocation without refill" + }, + { + "PublicDescription": "Attributable Level 3 unified cache refill. This event counts for any cacheable read transaction returning datafrom the SCU for which the data source was outside the cluster. Transactions such as ReadUnique are counted here as 'read' transactions, even though they can be generated by store instructions.", + "EventCode": "0x2A", + "EventName": "L3D_CACHE_REFILL", + "BriefDescription": "Attributable Level 3 unified cache refill." + }, + { + "PublicDescription": "Attributable Level 3 unified cache access. This event counts for any cacheable read transaction returning datafrom the SCU, or for any cacheable write to the SCU.", + "EventCode": "0x2B", + "EventName": "L3D_CACHE", + "BriefDescription": "Attributable Level 3 unified cache access." + }, + { + "PublicDescription": "Attributable L2 data or unified TLB refill. This event counts on anyrefill of the L2 TLB, caused by either an instruction or data access.This event does not count if the MMU is disabled.", + "EventCode": "0x2D", + "EventName": "L2D_TLB_REFILL", + "BriefDescription": "Attributable L2 data or unified TLB refill" + }, + { + "PublicDescription": "Attributable L2 data or unified TLB access. This event counts on any access to the L2 TLB (caused by a refill of any of the L1 TLBs). This event does not count if the MMU is disabled.", + "EventCode": "0x2F", + "EventName": "L2D_TLB", + "BriefDescription": "Attributable L2 data or unified TLB access" + }, + { + "PublicDescription": "Access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count.", + "EventCode": "0x34", + "EventName": "DTLB_WALK", + "BriefDescription": "Access to data TLB that caused a page table walk." + }, + { + "PublicDescription": "Access to instruction TLB that caused a page table walk. This event counts on any instruction access which causes L2D_TLB_REFILL to count.", + "EventCode": "0x35", + "EventName": "ITLB_WALK", + "BriefDescription": "Access to instruction TLB that caused a page table walk." + }, + { + "EventCode": "0x36", + "EventName": "LL_CACHE_RD", + "BriefDescription": "Last level cache access, read" + }, + { + "EventCode": "0x37", + "EventName": "LL_CACHE_MISS_RD", + "BriefDescription": "Last level cache miss, read" + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L1D_CACHE_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L1D_CACHE_WR" + }, + { + "ArchStdEvent": "L1D_TLB_RD" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_TLB_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L2D_CACHE_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L2D_CACHE_WR" + }, + { + "ArchStdEvent": "L2D_TLB_RD" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_TLB_WR" + }, + { + "ArchStdEvent": "L3D_CACHE_RD" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json new file mode 100644 index 000000000000..98d29c862320 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json @@ -0,0 +1,52 @@ +[ + { + "EventCode": "0x09", + "EventName": "EXC_TAKEN", + "BriefDescription": "Exception taken." + }, + { + "PublicDescription": "Local memory error. This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", + "EventCode": "0x1A", + "EventName": "MEMORY_ERROR", + "BriefDescription": "Local memory error." + }, + { + "ArchStdEvent": "EXC_DABORT" + }, + { + "ArchStdEvent": "EXC_FIQ" + }, + { + "ArchStdEvent": "EXC_HVC" + }, + { + "ArchStdEvent": "EXC_IRQ" + }, + { + "ArchStdEvent": "EXC_PABORT" + }, + { + "ArchStdEvent": "EXC_SMC" + }, + { + "ArchStdEvent": "EXC_SVC" + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ" + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ" + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER" + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT" + }, + { + "ArchStdEvent": "EXC_UNDEF" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json new file mode 100644 index 000000000000..c153ac706d8d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json @@ -0,0 +1,108 @@ +[ + { + "PublicDescription": "Software increment. Instruction architecturally executed (condition code check pass).", + "EventCode": "0x00", + "EventName": "SW_INCR", + "BriefDescription": "Software increment." + }, + { + "PublicDescription": "Instruction architecturally executed. This event counts all retired instructions, including those that fail their condition check.", + "EventCode": "0x08", + "EventName": "INST_RETIRED", + "BriefDescription": "Instruction architecturally executed." + }, + { + "EventCode": "0x0A", + "EventName": "EXC_RETURN", + "BriefDescription": "Instruction architecturally executed, condition code check pass, exception return." + }, + { + "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR. This event only counts writes to CONTEXTIDR in AArch32 state, and via the CONTEXTIDR_EL1 mnemonic in AArch64 state.", + "EventCode": "0x0B", + "EventName": "CID_WRITE_RETIRED", + "BriefDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR." + }, + { + "EventCode": "0x1B", + "EventName": "INST_SPEC", + "BriefDescription": "Operation speculatively executed" + }, + { + "PublicDescription": "Instruction architecturally executed, condition code check pass, write to TTBR. This event only counts writes to TTBR0/TTBR1 in AArch32 state and TTBR0_EL1/TTBR1_EL1 in AArch64 state.", + "EventCode": "0x1C", + "EventName": "TTBR_WRITE_RETIRED", + "BriefDescription": "Instruction architecturally executed, condition code check pass, write to TTBR" + }, + { + "PublicDescription": "Instruction architecturally executed, branch. This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches.", + "EventCode": "0x21", + "EventName": "BR_RETIRED", + "BriefDescription": "Instruction architecturally executed, branch." + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted branch. This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush.", + "EventCode": "0x22", + "EventName": "BR_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted branch." + }, + { + "ArchStdEvent": "ASE_SPEC" + }, + { + "ArchStdEvent": "BR_IMMED_SPEC" + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC" + }, + { + "ArchStdEvent": "BR_RETURN_SPEC" + }, + { + "ArchStdEvent": "CRYPTO_SPEC" + }, + { + "ArchStdEvent": "DMB_SPEC" + }, + { + "ArchStdEvent": "DP_SPEC" + }, + { + "ArchStdEvent": "DSB_SPEC" + }, + { + "ArchStdEvent": "ISB_SPEC" + }, + { + "ArchStdEvent": "LDREX_SPEC" + }, + { + "ArchStdEvent": "LDST_SPEC" + }, + { + "ArchStdEvent": "LD_SPEC" + }, + { + "ArchStdEvent": "PC_WRITE_SPEC" + }, + { + "ArchStdEvent": "RC_LD_SPEC" + }, + { + "ArchStdEvent": "RC_ST_SPEC" + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC" + }, + { + "ArchStdEvent": "STREX_SPEC" + }, + { + "ArchStdEvent": "ST_SPEC" + }, + { + "ArchStdEvent": "VFP_SPEC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json new file mode 100644 index 000000000000..b86643253f19 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json @@ -0,0 +1,23 @@ +[ + { + "PublicDescription": "Data memory access. This event counts memory accesses due to load or store instructions. This event counts the sum of MEM_ACCESS_RD and MEM_ACCESS_WR.", + "EventCode": "0x13", + "EventName": "MEM_ACCESS", + "BriefDescription": "Data memory access" + }, + { + "ArchStdEvent": "MEM_ACCESS_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_WR" + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json new file mode 100644 index 000000000000..8bde029a62d5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json @@ -0,0 +1,7 @@ +[ + { + "EventCode": "0x31", + "EventName": "REMOTE_ACCESS", + "BriefDescription": "Access to another socket in a multi-socket system" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json new file mode 100644 index 000000000000..010a647f9d02 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json @@ -0,0 +1,14 @@ +[ + { + "PublicDescription": "No operation issued because of the frontend. The counter counts on any cycle when there are no fetched instructions available to dispatch.", + "EventCode": "0x23", + "EventName": "STALL_FRONTEND", + "BriefDescription": "No operation issued because of the frontend." + }, + { + "PublicDescription": "No operation issued because of the backend. The counter counts on any cycle fetched instructions are not dispatched due to resource constraints.", + "EventCode": "0x24", + "EventName": "STALL_BACKEND", + "BriefDescription": "No operation issued because of the backend." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 927fcddcb4aa..0d609149b82a 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -16,6 +16,8 @@ 0x00000000420f1000,v1,arm/cortex-a53,core 0x00000000410fd070,v1,arm/cortex-a57-a72,core 0x00000000410fd080,v1,arm/cortex-a57-a72,core +0x00000000410fd0b0,v1,arm/cortex-a76-n1,core +0x00000000410fd0c0,v1,arm/cortex-a76-n1,core 0x00000000420f5160,v1,cavium/thunderx2,core 0x00000000430f0af0,v1,cavium/thunderx2,core 0x00000000480fd010,v1,hisilicon/hip08,core diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json index 9dc2f6b70354..b2a3df07fbc4 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json @@ -1776,30 +1776,6 @@ "PublicDescription": "" }, {, - "EventCode": "0xa29084", - "EventName": "PM_L3_P0_GRP_PUMP", - "BriefDescription": "L3 pf sent with grp scope port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0x528084", - "EventName": "PM_L3_P0_LCO_DATA", - "BriefDescription": "lco sent with data port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0x518080", - "EventName": "PM_L3_P0_LCO_NO_DATA", - "BriefDescription": "dataless l3 lco sent port 0", - "PublicDescription": "" - }, - {, - "EventCode": "0xa4908c", - "EventName": "PM_L3_P0_LCO_RTY", - "BriefDescription": "L3 LCO received retry port 0", - "PublicDescription": "" - }, - {, "EventCode": "0x84908d", "EventName": "PM_L3_PF0_ALLOC", "BriefDescription": "lifetime, sample of PF machine 0 valid", diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json index fad4af9142cb..6221a840fcea 100644 --- a/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json @@ -283,5 +283,47 @@ "BriefDescription": "Total cycles spent with one or more fill requests in flight from L2.", "PublicDescription": "Total cycles spent with one or more fill requests in flight from L2.", "UMask": "0x1" + }, + { + "EventName": "l3_request_g1.caching_l3_cache_accesses", + "EventCode": "0x01", + "BriefDescription": "Caching: L3 cache accesses", + "UMask": "0x80", + "Unit": "L3PMC" + }, + { + "EventName": "l3_lookup_state.all_l3_req_typs", + "EventCode": "0x04", + "BriefDescription": "All L3 Request Types", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_comb_clstr_state.other_l3_miss_typs", + "EventCode": "0x06", + "BriefDescription": "Other L3 Miss Request Types", + "UMask": "0xfe", + "Unit": "L3PMC" + }, + { + "EventName": "l3_comb_clstr_state.request_miss", + "EventCode": "0x06", + "BriefDescription": "L3 cache misses", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "EventName": "xi_sys_fill_latency", + "EventCode": "0x90", + "BriefDescription": "L3 Cache Miss Latency. Total cycles for all transactions divided by 16. Ignores SliceMask and ThreadMask.", + "UMask": "0x00", + "Unit": "L3PMC" + }, + { + "EventName": "xi_ccx_sdp_req1.all_l3_miss_req_typs", + "EventCode": "0x9a", + "BriefDescription": "All L3 Miss Request Types. Ignores SliceMask and ThreadMask.", + "UMask": "0x3f", + "Unit": "L3PMC" } ] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/core.json b/tools/perf/pmu-events/arch/x86/amdfam17h/core.json index 7b285b0a7f35..1079544eeed5 100644 --- a/tools/perf/pmu-events/arch/x86/amdfam17h/core.json +++ b/tools/perf/pmu-events/arch/x86/amdfam17h/core.json @@ -13,7 +13,7 @@ { "EventName": "ex_ret_brn", "EventCode": "0xc2", - "BriefDescription": "[Retired Branch Instructions.", + "BriefDescription": "Retired Branch Instructions.", "PublicDescription": "The number of branch instructions retired. This includes all types of architectural control flow changes, including exceptions and interrupts." }, { diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index d413761621b0..9e37287da924 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -239,6 +239,7 @@ static struct map { { "hisi_sccl,ddrc", "hisi_sccl,ddrc" }, { "hisi_sccl,hha", "hisi_sccl,hha" }, { "hisi_sccl,l3c", "hisi_sccl,l3c" }, + { "L3PMC", "amd_l3" }, {} }; diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index a637a4a90760..338cd9faa835 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -10,6 +10,7 @@ #include "tests.h" #include "debug.h" #include "parse-events.h" +#include "util/mmap.h" #include <errno.h> #include <linux/string.h> @@ -32,8 +33,8 @@ static int count_samples(struct evlist *evlist, int *sample_count, { int i; - for (i = 0; i < evlist->nr_mmaps; i++) { - struct perf_mmap *map = &evlist->overwrite_mmap[i]; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + struct mmap *map = &evlist->overwrite_mmap[i]; union perf_event *event; perf_mmap__read_init(map); @@ -63,9 +64,9 @@ static int do_test(struct evlist *evlist, int mmap_pages, int err; char sbuf[STRERR_BUFSIZE]; - err = perf_evlist__mmap(evlist, mmap_pages); + err = evlist__mmap(evlist, mmap_pages); if (err < 0) { - pr_debug("perf_evlist__mmap: %s\n", + pr_debug("evlist__mmap: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); return TEST_FAIL; } @@ -75,7 +76,7 @@ static int do_test(struct evlist *evlist, int mmap_pages, evlist__disable(evlist); err = count_samples(evlist, sample_count, comm_count); - perf_evlist__munmap(evlist); + evlist__munmap(evlist); return err; } diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index db2aadff3708..96c137360918 100644 --- a/tools/perf/tests/bitmap.c +++ b/tools/perf/tests/bitmap.c @@ -2,8 +2,8 @@ #include <linux/compiler.h> #include <linux/bitmap.h> #include <perf/cpumap.h> +#include <internal/cpumap.h> #include "tests.h" -#include "cpumap.h" #include "debug.h" #define NBITS 100 diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index fc102e4f403e..1eb0bffaed6c 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -19,6 +19,7 @@ #include "llvm.h" #include "debug.h" #include "parse-events.h" +#include "util/mmap.h" #define NR_ITERS 111 #define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test" @@ -167,9 +168,9 @@ static int do_test(struct bpf_object *obj, int (*func)(void), goto out_delete_evlist; } - err = perf_evlist__mmap(evlist, opts.mmap_pages); + err = evlist__mmap(evlist, opts.mmap_pages); if (err < 0) { - pr_debug("perf_evlist__mmap: %s\n", + pr_debug("evlist__mmap: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -178,9 +179,9 @@ static int do_test(struct bpf_object *obj, int (*func)(void), (*func)(); evlist__disable(evlist); - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { union perf_event *event; - struct perf_mmap *md; + struct mmap *md; md = &evlist->mmap[i]; if (perf_mmap__read_init(md) < 0) diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c index f45fe11dcf50..2577d3ed1531 100644 --- a/tools/perf/tests/clang.c +++ b/tools/perf/tests/clang.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include "tests.h" -#include "debug.h" -#include "util.h" #include "c++/clang-c.h" #include <linux/kernel.h> diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index c1c29e08e7fb..f5764a3890b9 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -19,12 +19,13 @@ #include "evlist.h" #include "evsel.h" #include "thread_map.h" -#include "cpumap.h" #include "machine.h" #include "map.h" #include "symbol.h" #include "event.h" #include "record.h" +#include "util/mmap.h" +#include "util/synthetic-events.h" #include "thread.h" #include "tests.h" @@ -419,10 +420,10 @@ static int process_events(struct machine *machine, struct evlist *evlist, struct state *state) { union perf_event *event; - struct perf_mmap *md; + struct mmap *md; int i, ret; - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { md = &evlist->mmap[i]; if (perf_mmap__read_init(md) < 0) continue; @@ -651,7 +652,7 @@ static int do_test_code_reading(bool try_kcore) perf_evlist__config(evlist, &opts, NULL); - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); evsel->core.attr.comm = 1; evsel->core.attr.disabled = 1; @@ -685,9 +686,9 @@ static int do_test_code_reading(bool try_kcore) break; } - ret = perf_evlist__mmap(evlist, UINT_MAX); + ret = evlist__mmap(evlist, UINT_MAX); if (ret < 0) { - pr_debug("perf_evlist__mmap failed\n"); + pr_debug("evlist__mmap failed\n"); goto out_put; } diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 39493de50117..8a0d236202b0 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -3,6 +3,7 @@ #include <stdio.h> #include "cpumap.h" #include "event.h" +#include "util/synthetic-events.h" #include <string.h> #include <linux/bitops.h> #include <perf/cpumap.h> diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index a4874d4ce7ef..627c1aaf1c9e 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -10,7 +10,6 @@ #include <sys/resource.h> #include <api/fs/fs.h> #include "dso.h" -#include "util.h" #include "machine.h" #include "symbol.h" #include "tests.h" diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 4125255ff637..4f4ecbcbe87e 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -15,6 +15,7 @@ #include "symbol.h" #include "thread.h" #include "callchain.h" +#include "util/synthetic-events.h" #if defined (__x86_64__) || defined (__i386__) || defined (__powerpc__) #include "arch-tests.h" diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index d824a726906c..1ee8704e2284 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -9,7 +9,6 @@ #include "tests.h" #include "evlist.h" #include "evsel.h" -#include "util.h" #include "debug.h" #include "parse-events.h" #include "thread_map.h" @@ -17,7 +16,7 @@ static int attach__enable_on_exec(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__last(evlist); + struct evsel *evsel = evlist__last(evlist); struct target target = { .uid = UINT_MAX, }; @@ -59,7 +58,7 @@ static int detach__enable_on_exec(struct evlist *evlist) static int attach__current_disabled(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__last(evlist); + struct evsel *evsel = evlist__last(evlist); struct perf_thread_map *threads; int err; @@ -85,7 +84,7 @@ static int attach__current_disabled(struct evlist *evlist) static int attach__current_enabled(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__last(evlist); + struct evsel *evsel = evlist__last(evlist); struct perf_thread_map *threads; int err; @@ -105,14 +104,14 @@ static int attach__current_enabled(struct evlist *evlist) static int detach__disable(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__last(evlist); + struct evsel *evsel = evlist__last(evlist); return evsel__enable(evsel); } static int attach__cpu_disabled(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__last(evlist); + struct evsel *evsel = evlist__last(evlist); struct perf_cpu_map *cpus; int err; @@ -141,7 +140,7 @@ static int attach__cpu_disabled(struct evlist *evlist) static int attach__cpu_enabled(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__last(evlist); + struct evsel *evsel = evlist__last(evlist); struct perf_cpu_map *cpus; int err; @@ -181,7 +180,7 @@ static int test_times(int (attach)(struct evlist *), goto out_err; } - evsel = perf_evlist__last(evlist); + evsel = evlist__last(evlist); evsel->core.attr.read_format |= PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index cac4290e233a..c727379cf20e 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -2,10 +2,12 @@ #include <linux/compiler.h> #include <perf/cpumap.h> #include <string.h> +#include "cpumap.h" #include "evlist.h" #include "evsel.h" #include "header.h" #include "machine.h" +#include "util/synthetic-events.h" #include "tool.h" #include "tests.h" #include "debug.h" @@ -90,12 +92,12 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu evlist = perf_evlist__new_default(); TEST_ASSERT_VAL("failed to get evlist", evlist); - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); - TEST_ASSERT_VAL("failed to allos ids", - !perf_evsel__alloc_id(evsel, 1, 1)); + TEST_ASSERT_VAL("failed to allocate ids", + !perf_evsel__alloc_id(&evsel->core, 1, 1)); - perf_evlist__id_add(evlist, evsel, 0, 0, 123); + perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123); evsel->unit = strdup("KRAVA"); diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 5330f106a6ee..956205bf9326 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -34,7 +34,7 @@ static int perf_evsel__roundtrip_cache_name_test(void) } idx = 0; - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index de110d8f169b..6f34d08b84e5 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -2,6 +2,7 @@ #include <inttypes.h> #include "util/debug.h" #include "util/dso.h" +#include "util/event.h" // struct perf_sample #include "util/map.h" #include "util/symbol.h" #include "util/sort.h" @@ -10,6 +11,7 @@ #include "util/thread.h" #include "tests/hists_common.h" #include <linux/kernel.h> +#include <linux/perf_event.h> static struct { u32 pid; diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index fa55b7bad3af..6367c8f6ca22 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -721,7 +721,7 @@ int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_u if (verbose > 1) machine__fprintf(machine, stderr); - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); for (i = 0; i < ARRAY_SIZE(testcases); i++) { err = testcases[i](evsel, machine); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 8be4d0b61e3a..a024d3f3a412 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -8,6 +8,7 @@ #include "machine.h" #include "parse-events.h" #include "hists_common.h" +#include "util/mmap.h" #include <errno.h> #include <linux/kernel.h> @@ -310,8 +311,8 @@ int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unuse print_hists_in(hists); } - first = perf_evlist__first(evlist); - evsel = perf_evlist__last(evlist); + first = evlist__first(evlist); + evsel = evlist__last(evlist); first_hists = evsel__hists(first); hists = evsel__hists(evsel); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 3f6dfa212260..38f804ff6452 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -608,7 +608,7 @@ int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unu if (verbose > 1) machine__fprintf(machine, stderr); - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); for (i = 0; i < ARRAY_SIZE(testcases); i++) { err = testcases[i](evsel, machine); diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 9f0762d987fa..92c7d591bcac 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -12,8 +12,8 @@ #include "evsel.h" #include "record.h" #include "thread_map.h" -#include "cpumap.h" #include "tests.h" +#include "util/mmap.h" #define CHECK__(x) { \ while ((x) < 0) { \ @@ -32,11 +32,11 @@ static int find_comm(struct evlist *evlist, const char *comm) { union perf_event *event; - struct perf_mmap *md; + struct mmap *md; int i, found; found = 0; - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { md = &evlist->mmap[i]; if (perf_mmap__read_init(md) < 0) continue; @@ -93,7 +93,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un perf_evlist__config(evlist, &opts, NULL); - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); evsel->core.attr.comm = 1; evsel->core.attr.disabled = 1; @@ -105,7 +105,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un goto out_err; } - CHECK__(perf_evlist__mmap(evlist, UINT_MAX)); + CHECK__(evlist__mmap(evlist, UINT_MAX)); /* * First, test that a 'comm' event can be found when the event is @@ -132,7 +132,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un evlist__enable(evlist); - evsel = perf_evlist__last(evlist); + evsel = evlist__last(evlist); CHECK__(evsel__disable(evsel)); @@ -143,7 +143,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un found = find_comm(evlist, comm); if (found != 1) { - pr_debug("Seconf time, failed to find tracking event.\n"); + pr_debug("Second time, failed to find tracking event.\n"); goto out_err; } diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 022e4c9cf092..ae6cda81c209 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -7,7 +7,6 @@ #include "llvm.h" #include "tests.h" #include "debug.h" -#include "util.h" #ifdef HAVE_LIBBPF_SUPPORT static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 70c48475896d..c850d1664c56 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -100,7 +100,7 @@ make_install_info := install-info make_install_pdf := install-pdf make_install_prefix := install prefix=/tmp/krava make_install_prefix_slash := install prefix=/tmp/krava/ -make_static := LDFLAGS=-static +make_static := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 # all the NO_* variable combined make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 @@ -327,6 +327,10 @@ make_kernelsrc_tools: (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \ test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false) +make_libperf: + @echo "- make -C lib"; + make -C lib clean >$@ 2>&1; make -C lib >>$@ 2>&1 && rm $@ + FEATURES_DUMP_FILE := $(FULL_O)/BUILD_TEST_FEATURE_DUMP FEATURES_DUMP_FILE_STATIC := $(FULL_O)/BUILD_TEST_FEATURE_DUMP_STATIC @@ -365,5 +369,5 @@ $(foreach t,$(run),$(if $(findstring make_static,$(t)),\ $(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE)))) endif -.PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools +.PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools make_libperf endif # ifndef MK diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c index 7672ade70f20..a258bd51f1a4 100644 --- a/tools/perf/tests/mem2node.c +++ b/tools/perf/tests/mem2node.c @@ -4,7 +4,7 @@ #include <linux/kernel.h> #include <linux/zalloc.h> #include <perf/cpumap.h> -#include "cpumap.h" +#include <internal/cpumap.h> #include "debug.h" #include "env.h" #include "mem2node.h" diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 85e1d7337dc0..3a22dce991ba 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -10,8 +10,8 @@ #include "evlist.h" #include "evsel.h" #include "thread_map.h" -#include "cpumap.h" #include "tests.h" +#include "util/mmap.h" #include <linux/err.h> #include <linux/kernel.h> #include <linux/string.h> @@ -43,7 +43,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse expected_nr_events[nsyscalls], i, j; struct evsel *evsels[nsyscalls], *evsel; char sbuf[STRERR_BUFSIZE]; - struct perf_mmap *md; + struct mmap *md; threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { @@ -53,7 +53,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse cpus = perf_cpu_map__new(NULL); if (cpus == NULL) { - pr_debug("cpu_map__new\n"); + pr_debug("perf_cpu_map__new\n"); goto out_free_threads; } @@ -100,7 +100,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse expected_nr_events[i] = 1 + rand() % 127; } - if (perf_evlist__mmap(evlist, 128) < 0) { + if (evlist__mmap(evlist, 128) < 0) { pr_debug("failed to mmap events: %d (%s)\n", errno, str_error_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 360d70deb855..8d9d4cbff76d 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -8,13 +8,15 @@ #include <stdlib.h> #include <stdio.h> #include "debug.h" +#include "event.h" #include "tests.h" #include "machine.h" #include "thread_map.h" #include "map.h" #include "symbol.h" +#include "util/synthetic-events.h" #include "thread.h" -#include "util.h" +#include <internal/lib.h> // page_size #define THREADS 4 diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index 9171f77cd9cd..93c176523e38 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -14,7 +14,8 @@ #include "evsel.h" #include "tests.h" #include "thread_map.h" -#include "cpumap.h" +#include <perf/cpumap.h> +#include <internal/cpumap.h> #include "debug.h" #include "stat.h" #include "util/counts.h" @@ -37,7 +38,7 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int cpus = perf_cpu_map__new(NULL); if (cpus == NULL) { - pr_debug("cpu_map__new\n"); + pr_debug("perf_cpu_map__new\n"); goto out_thread_map_delete; } diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index b71167b43dda..2b5c46813053 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -11,6 +11,7 @@ #include "record.h" #include "tests.h" #include "debug.h" +#include "util/mmap.h" #include <errno.h> #ifndef O_DIRECTORY @@ -69,9 +70,9 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest goto out_delete_evlist; } - err = perf_evlist__mmap(evlist, UINT_MAX); + err = evlist__mmap(evlist, UINT_MAX); if (err < 0) { - pr_debug("perf_evlist__mmap: %s\n", + pr_debug("evlist__mmap: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -86,9 +87,9 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest while (1) { int before = nr_events; - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { union perf_event *event; - struct perf_mmap *md; + struct mmap *md; md = &evlist->mmap[i]; if (perf_mmap__read_init(md) < 0) @@ -126,7 +127,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest } if (nr_events == before) - perf_evlist__poll(evlist, 10); + evlist__poll(evlist, 10); if (++nr_polls > 5) { pr_debug("%s: no events!\n", __func__); diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 02ba696fb87f..25e0ed2eedfc 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -6,7 +6,6 @@ #include "tests.h" #include "debug.h" #include "pmu.h" -#include "util.h" #include <dirent.h> #include <errno.h> #include <sys/types.h> @@ -47,7 +46,7 @@ static bool kvm_s390_create_vm_valid(void) static int test__checkevent_tracepoint(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups); @@ -78,7 +77,7 @@ static int test__checkevent_tracepoint_multi(struct evlist *evlist) static int test__checkevent_raw(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); @@ -88,7 +87,7 @@ static int test__checkevent_raw(struct evlist *evlist) static int test__checkevent_numeric(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type); @@ -98,7 +97,7 @@ static int test__checkevent_numeric(struct evlist *evlist) static int test__checkevent_symbolic_name(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); @@ -109,7 +108,7 @@ static int test__checkevent_symbolic_name(struct evlist *evlist) static int test__checkevent_symbolic_name_config(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); @@ -130,7 +129,7 @@ static int test__checkevent_symbolic_name_config(struct evlist *evlist) static int test__checkevent_symbolic_alias(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); @@ -141,7 +140,7 @@ static int test__checkevent_symbolic_alias(struct evlist *evlist) static int test__checkevent_genhw(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); @@ -151,7 +150,7 @@ static int test__checkevent_genhw(struct evlist *evlist) static int test__checkevent_breakpoint(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); @@ -165,7 +164,7 @@ static int test__checkevent_breakpoint(struct evlist *evlist) static int test__checkevent_breakpoint_x(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); @@ -178,7 +177,7 @@ static int test__checkevent_breakpoint_x(struct evlist *evlist) static int test__checkevent_breakpoint_r(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", @@ -193,7 +192,7 @@ static int test__checkevent_breakpoint_r(struct evlist *evlist) static int test__checkevent_breakpoint_w(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", @@ -208,7 +207,7 @@ static int test__checkevent_breakpoint_w(struct evlist *evlist) static int test__checkevent_breakpoint_rw(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", @@ -223,7 +222,7 @@ static int test__checkevent_breakpoint_rw(struct evlist *evlist) static int test__checkevent_tracepoint_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); @@ -254,7 +253,7 @@ test__checkevent_tracepoint_multi_modifier(struct evlist *evlist) static int test__checkevent_raw_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); @@ -266,7 +265,7 @@ static int test__checkevent_raw_modifier(struct evlist *evlist) static int test__checkevent_numeric_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); @@ -278,7 +277,7 @@ static int test__checkevent_numeric_modifier(struct evlist *evlist) static int test__checkevent_symbolic_name_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); @@ -290,7 +289,7 @@ static int test__checkevent_symbolic_name_modifier(struct evlist *evlist) static int test__checkevent_exclude_host_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); @@ -300,7 +299,7 @@ static int test__checkevent_exclude_host_modifier(struct evlist *evlist) static int test__checkevent_exclude_guest_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); @@ -310,7 +309,7 @@ static int test__checkevent_exclude_guest_modifier(struct evlist *evlist) static int test__checkevent_symbolic_alias_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); @@ -322,7 +321,7 @@ static int test__checkevent_symbolic_alias_modifier(struct evlist *evlist) static int test__checkevent_genhw_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); @@ -334,7 +333,7 @@ static int test__checkevent_genhw_modifier(struct evlist *evlist) static int test__checkevent_exclude_idle_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude idle", evsel->core.attr.exclude_idle); TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); @@ -349,7 +348,7 @@ static int test__checkevent_exclude_idle_modifier(struct evlist *evlist) static int test__checkevent_exclude_idle_modifier_1(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude idle", evsel->core.attr.exclude_idle); TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); @@ -364,7 +363,7 @@ static int test__checkevent_exclude_idle_modifier_1(struct evlist *evlist) static int test__checkevent_breakpoint_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); @@ -379,7 +378,7 @@ static int test__checkevent_breakpoint_modifier(struct evlist *evlist) static int test__checkevent_breakpoint_x_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); @@ -393,7 +392,7 @@ static int test__checkevent_breakpoint_x_modifier(struct evlist *evlist) static int test__checkevent_breakpoint_r_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); @@ -407,7 +406,7 @@ static int test__checkevent_breakpoint_r_modifier(struct evlist *evlist) static int test__checkevent_breakpoint_w_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); @@ -421,7 +420,7 @@ static int test__checkevent_breakpoint_w_modifier(struct evlist *evlist) static int test__checkevent_breakpoint_rw_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); @@ -436,7 +435,7 @@ static int test__checkevent_breakpoint_rw_modifier(struct evlist *evlist) static int test__checkevent_pmu(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); @@ -454,7 +453,7 @@ static int test__checkevent_pmu(struct evlist *evlist) static int test__checkevent_list(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); @@ -493,7 +492,7 @@ static int test__checkevent_list(struct evlist *evlist) static int test__checkevent_pmu_name(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); /* cpu/config=1,name=krava/u */ TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); @@ -514,7 +513,7 @@ static int test__checkevent_pmu_name(struct evlist *evlist) static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); /* cpu/config=1,call-graph=fp,time,period=100000/ */ TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); @@ -547,7 +546,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) static int test__checkevent_pmu_events(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); @@ -565,7 +564,7 @@ static int test__checkevent_pmu_events(struct evlist *evlist) static int test__checkevent_pmu_events_mix(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); /* pmu-event:u */ TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); @@ -643,7 +642,7 @@ static int test__group1(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* instructions:k */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); @@ -685,7 +684,7 @@ static int test__group2(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* faults + :ku modifier */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_SW_PAGE_FAULTS == evsel->core.attr.config); @@ -740,7 +739,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups); /* group1 syscalls:sys_enter_openat:H */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->core.attr.type); TEST_ASSERT_VAL("wrong sample_type", PERF_TP_SAMPLE_TYPE == evsel->core.attr.sample_type); @@ -832,7 +831,7 @@ static int test__group4(struct evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles:u + p */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); @@ -876,7 +875,7 @@ static int test__group5(struct evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups); /* cycles + G */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); @@ -962,7 +961,7 @@ static int test__group_gh1(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles + :H group modifier */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); @@ -1002,7 +1001,7 @@ static int test__group_gh2(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles + :G group modifier */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); @@ -1042,7 +1041,7 @@ static int test__group_gh3(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles:G + :u group modifier */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); @@ -1082,7 +1081,7 @@ static int test__group_gh4(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles:G + :uG group modifier */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); @@ -1121,7 +1120,7 @@ static int test__leader_sample1(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); /* cycles - sampling group leader */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); @@ -1174,7 +1173,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); /* instructions - sampling group leader */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); @@ -1208,7 +1207,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused) static int test__checkevent_pinned_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); @@ -1226,7 +1225,7 @@ static int test__pinned_group(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); /* cycles - group leader */ - evsel = leader = perf_evlist__first(evlist); + evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); @@ -1252,7 +1251,7 @@ static int test__pinned_group(struct evlist *evlist) static int test__checkevent_breakpoint_len(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); @@ -1267,7 +1266,7 @@ static int test__checkevent_breakpoint_len(struct evlist *evlist) static int test__checkevent_breakpoint_len_w(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); @@ -1283,7 +1282,7 @@ static int test__checkevent_breakpoint_len_w(struct evlist *evlist) static int test__checkevent_breakpoint_len_rw_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); @@ -1295,7 +1294,7 @@ test__checkevent_breakpoint_len_rw_modifier(struct evlist *evlist) static int test__checkevent_precise_max_modifier(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); @@ -1306,7 +1305,7 @@ static int test__checkevent_precise_max_modifier(struct evlist *evlist) static int test__checkevent_config_symbol(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0); return 0; @@ -1314,7 +1313,7 @@ static int test__checkevent_config_symbol(struct evlist *evlist) static int test__checkevent_config_raw(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0); return 0; @@ -1322,7 +1321,7 @@ static int test__checkevent_config_raw(struct evlist *evlist) static int test__checkevent_config_num(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0); return 0; @@ -1330,7 +1329,7 @@ static int test__checkevent_config_num(struct evlist *evlist) static int test__checkevent_config_cache(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0); return 0; @@ -1343,7 +1342,7 @@ static bool test__intel_pt_valid(void) static int test__intel_pt(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0); return 0; @@ -1351,7 +1350,7 @@ static int test__intel_pt(struct evlist *evlist) static int test__checkevent_complex_name(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0); return 0; @@ -1359,7 +1358,7 @@ static int test__checkevent_complex_name(struct evlist *evlist) static int test__sym_event_slash(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES); @@ -1369,7 +1368,7 @@ static int test__sym_event_slash(struct evlist *evlist) static int test__sym_event_dc(struct evlist *evlist) { - struct evsel *evsel = perf_evlist__first(evlist); + struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES); diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 8284752a60c8..adf3c9c4a416 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -1,4 +1,3 @@ -// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/types.h> #include <stddef.h> @@ -8,7 +7,6 @@ #include "event.h" #include "evlist.h" #include "header.h" -#include "util.h" #include "debug.h" static int process_event(struct evlist **pevlist, union perf_event *event) diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c index a693bcf017ea..dbc27199c65e 100644 --- a/tools/perf/tests/perf-hooks.c +++ b/tools/perf/tests/perf-hooks.c @@ -4,7 +4,6 @@ #include "tests.h" #include "debug.h" -#include "util.h" #include "perf-hooks.h" static void sigsegv_handler(int sig __maybe_unused) diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index e1b42292cf7f..437426be29e9 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -11,6 +11,7 @@ #include "debug.h" #include "record.h" #include "tests.h" +#include "util/mmap.h" static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp) { @@ -103,7 +104,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus /* * Config the evsels, setting attr->comm on the first one, etc. */ - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); perf_evsel__set_sample_bit(evsel, CPU); perf_evsel__set_sample_bit(evsel, TID); perf_evsel__set_sample_bit(evsel, TIME); @@ -143,9 +144,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus * fds in the same CPU to be injected in the same mmap ring buffer * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)). */ - err = perf_evlist__mmap(evlist, opts.mmap_pages); + err = evlist__mmap(evlist, opts.mmap_pages); if (err < 0) { - pr_debug("perf_evlist__mmap: %s\n", + pr_debug("evlist__mmap: %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; } @@ -164,9 +165,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus while (1) { int before = total_events; - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { union perf_event *event; - struct perf_mmap *md; + struct mmap *md; md = &evlist->mmap[i]; if (perf_mmap__read_init(md) < 0) @@ -286,7 +287,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does. */ if (total_events == before && false) - perf_evlist__poll(evlist, -1); + evlist__poll(evlist, -1); sleep(1); if (++wakeups > 5) { diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 14a78898d79e..74379ff1f7fa 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "parse-events.h" #include "pmu.h" -#include "util.h" #include "tests.h" #include <errno.h> #include <stdio.h> diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 5fcc06817076..3a02426db9a6 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -9,10 +9,10 @@ #include "map_symbol.h" #include "branch.h" -#include "util.h" #include "event.h" #include "evsel.h" #include "debug.h" +#include "util/synthetic-events.h" #include "tests.h" diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index cf1bd57d3023..60f0e9ee04fb 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -3,6 +3,7 @@ #include <limits.h> #include <stdio.h> #include <stdlib.h> +#include <unistd.h> #include <sys/epoll.h> #include <util/symbol.h> #include <linux/filter.h> diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index cc10b4116c9f..c1911501c39c 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -5,6 +5,7 @@ #include "stat.h" #include "counts.h" #include "debug.h" +#include "util/synthetic-events.h" static bool has_term(struct perf_record_stat_config *config, u64 tag, u64 val) diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 97694a040986..84519df87f30 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -12,6 +12,7 @@ #include "util/evsel.h" #include "util/evlist.h" #include "util/cpumap.h" +#include "util/mmap.h" #include "util/thread_map.h" #include <perf/evlist.h> @@ -42,7 +43,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) }; struct perf_cpu_map *cpus; struct perf_thread_map *threads; - struct perf_mmap *md; + struct mmap *md; attr.sample_freq = 500; @@ -82,7 +83,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) goto out_delete_evlist; } - err = perf_evlist__mmap(evlist, 128); + err = evlist__mmap(evlist, 128); if (err < 0) { pr_debug("failed to mmap event: %d (%s)\n", errno, str_error_r(errno, sbuf, sizeof(sbuf))); diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 1a60fa1219f5..ffa592e0020e 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -14,9 +14,9 @@ #include "evlist.h" #include "evsel.h" #include "thread_map.h" -#include "cpumap.h" #include "record.h" #include "tests.h" +#include "util/mmap.h" static int spin_sleep(void) { @@ -144,7 +144,7 @@ static int process_sample_event(struct evlist *evlist, return err; /* * Check for no missing sched_switch events i.e. that the - * evsel->system_wide flag has worked. + * evsel->core.system_wide flag has worked. */ if (switch_tracking->tids[cpu] != -1 && switch_tracking->tids[cpu] != prev_tid) { @@ -264,10 +264,10 @@ static int process_events(struct evlist *evlist, unsigned pos, cnt = 0; LIST_HEAD(events); struct event_node *events_array, *node; - struct perf_mmap *md; + struct mmap *md; int i, ret; - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { md = &evlist->mmap[i]; if (perf_mmap__read_init(md) < 0) continue; @@ -316,7 +316,7 @@ out_free_nodes: * * This function implements a test that checks that sched_switch events and * tracking events can be recorded for a workload (current process) using the - * evsel->system_wide and evsel->tracking flags (respectively) with other events + * evsel->core.system_wide and evsel->tracking flags (respectively) with other events * sometimes enabled or disabled. */ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) @@ -367,7 +367,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - cpu_clocks_evsel = perf_evlist__last(evlist); + cpu_clocks_evsel = evlist__last(evlist); /* Second event */ err = parse_events(evlist, "cycles:u", NULL); @@ -376,7 +376,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - cycles_evsel = perf_evlist__last(evlist); + cycles_evsel = evlist__last(evlist); /* Third event */ if (!perf_evlist__can_select_event(evlist, sched_switch)) { @@ -391,22 +391,22 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - switch_evsel = perf_evlist__last(evlist); + switch_evsel = evlist__last(evlist); perf_evsel__set_sample_bit(switch_evsel, CPU); perf_evsel__set_sample_bit(switch_evsel, TIME); - switch_evsel->system_wide = true; + switch_evsel->core.system_wide = true; switch_evsel->no_aux_samples = true; switch_evsel->immediate = true; /* Test moving an event to the front */ - if (cycles_evsel == perf_evlist__first(evlist)) { + if (cycles_evsel == evlist__first(evlist)) { pr_debug("cycles event already at front"); goto out_err; } perf_evlist__to_front(evlist, cycles_evsel); - if (cycles_evsel != perf_evlist__first(evlist)) { + if (cycles_evsel != evlist__first(evlist)) { pr_debug("Failed to move cycles event to front"); goto out_err; } @@ -421,7 +421,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out_err; } - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); @@ -434,7 +434,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ perf_evlist__config(evlist, &opts, NULL); /* Check moved event is still at the front */ - if (cycles_evsel != perf_evlist__first(evlist)) { + if (cycles_evsel != evlist__first(evlist)) { pr_debug("Front event no longer at front"); goto out_err; } @@ -461,9 +461,9 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ goto out; } - err = perf_evlist__mmap(evlist, UINT_MAX); + err = evlist__mmap(evlist, UINT_MAX); if (err) { - pr_debug("perf_evlist__mmap failed!\n"); + pr_debug("evlist__mmap failed!\n"); goto out_err; } diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index f610e8c0a083..bce3a4cb4c89 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -4,12 +4,13 @@ #include "evsel.h" #include "target.h" #include "thread_map.h" -#include "cpumap.h" #include "tests.h" +#include "util/mmap.h" #include <errno.h> #include <signal.h> #include <linux/string.h> +#include <perf/cpumap.h> #include <perf/evlist.h> static int exited; @@ -51,7 +52,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused char sbuf[STRERR_BUFSIZE]; struct perf_cpu_map *cpus; struct perf_thread_map *threads; - struct perf_mmap *md; + struct mmap *md; signal(SIGCHLD, sig_handler); @@ -87,7 +88,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused goto out_delete_evlist; } - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); evsel->core.attr.task = 1; #ifdef __s390x__ evsel->core.attr.sample_freq = 1000000; @@ -106,7 +107,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused goto out_delete_evlist; } - if (perf_evlist__mmap(evlist, 128) < 0) { + if (evlist__mmap(evlist, 128) < 0) { pr_debug("failed to mmap events: %d (%s)\n", errno, str_error_r(errno, sbuf, sizeof(sbuf))); goto out_delete_evlist; @@ -129,7 +130,7 @@ retry: out_init: if (!exited || !nr_exit) { - perf_evlist__poll(evlist, -1); + evlist__poll(evlist, -1); goto retry; } diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index 39168c57943b..28f51c4bd373 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -8,6 +8,7 @@ #include "thread_map.h" #include "debug.h" #include "event.h" +#include "util/synthetic-events.h" #include <linux/zalloc.h> #include <perf/event.h> diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index a4f9f5182b47..4a800499d7c3 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -3,11 +3,12 @@ #include <stdlib.h> #include <stdio.h> #include <perf/cpumap.h> +#include "cpumap.h" #include "tests.h" -#include "util.h" #include "session.h" #include "evlist.h" #include "debug.h" +#include <linux/err.h> #define TEMPL "/tmp/perf-test-XXXXXX" #define DATA_SIZE 10 @@ -39,7 +40,7 @@ static int session_write_header(char *path) }; session = perf_session__new(&data, false, NULL); - TEST_ASSERT_VAL("can't get session", session); + TEST_ASSERT_VAL("can't get session", !IS_ERR(session)); session->evlist = perf_evlist__new_default(); TEST_ASSERT_VAL("can't get evlist", session->evlist); @@ -70,7 +71,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) int i; session = perf_session__new(&data, false, NULL); - TEST_ASSERT_VAL("can't get session", session); + TEST_ASSERT_VAL("can't get session", !IS_ERR(session)); /* On platforms with large numbers of CPUs process_cpu_topology() * might issue an error while reading the perf.data file section diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 01f434c067c6..aa296ffea6d1 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -7,7 +7,7 @@ #include "dso.h" #include "map.h" #include "symbol.h" -#include "util.h" +#include <internal/lib.h> // page_size #include "tests.h" #include "debug.h" #include "machine.h" diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index f93d40b1c203..781afe42e90e 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../util/util.h" #include "../util/string2.h" #include "../util/config.h" #include "libslang.h" diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ac74ed2c23a0..82207db8f97c 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -2,7 +2,6 @@ #include "../browser.h" #include "../helpline.h" #include "../ui.h" -#include "../util.h" #include "../../util/annotate.h" #include "../../util/debug.h" #include "../../util/dso.h" diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c index 0f59a7001479..57e6e4332f74 100644 --- a/tools/perf/ui/browsers/header.c +++ b/tools/perf/ui/browsers/header.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include "util/debug.h" #include "ui/browser.h" #include "ui/keysyms.h" #include "ui/ui.h" diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 589168ca9f62..7a7187e069b4 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -3319,13 +3319,13 @@ browse_hists: switch (key) { case K_TAB: if (pos->core.node.next == &evlist->core.entries) - pos = perf_evlist__first(evlist); + pos = evlist__first(evlist); else pos = perf_evsel__next(pos); goto browse_hists; case K_UNTAB: if (pos->core.node.prev == &evlist->core.entries) - pos = perf_evlist__last(evlist); + pos = evlist__last(evlist); else pos = perf_evsel__prev(pos); goto browse_hists; @@ -3417,7 +3417,7 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, single_entry: if (nr_entries == 1) { - struct evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); return perf_evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index 893b065971f6..3d49b916c9e4 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -5,7 +5,6 @@ #include <stdlib.h> #include <string.h> #include <linux/bitops.h> -#include "../../util/util.h" #include "../../util/debug.h" #include "../../util/map.h" #include "../../util/dso.h" diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c index f16a38fea45e..76d356a18790 100644 --- a/tools/perf/ui/browsers/res_sample.c +++ b/tools/perf/ui/browsers/res_sample.c @@ -7,7 +7,7 @@ #include "config.h" #include "time-utils.h" #include "../util.h" -#include "../../util/util.h" +#include "../../util/util.h" // perf_exe() #include "../../perf.h" #include <stdlib.h> #include <string.h> diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index 586a21acc13d..fc733a6354d4 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include "../../builtin.h" #include "../../perf.h" -#include "../../util/util.h" +#include "../../util/util.h" // perf_exe() +#include "../util.h" #include "../../util/hist.h" #include "../../util/debug.h" #include "../../util/symbol.h" diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c index e166da9ec767..e40a006aead8 100644 --- a/tools/perf/ui/gtk/helpline.c +++ b/tools/perf/ui/gtk/helpline.c @@ -6,7 +6,6 @@ #include "gtk.h" #include "../ui.h" #include "../helpline.h" -#include "../../util/debug.h" static void gtk_helpline_pop(void) { diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 6c2efc10bf5c..ed1a97b2c4b0 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -8,6 +8,7 @@ #include "../string2.h" #include "gtk.h" #include <signal.h> +#include <stdlib.h> #include <linux/string.h> #define MAX_COLUMNS 32 diff --git a/tools/perf/ui/gtk/progress.c b/tools/perf/ui/gtk/progress.c index b6ad8857da78..eea6fcde518a 100644 --- a/tools/perf/ui/gtk/progress.c +++ b/tools/perf/ui/gtk/progress.c @@ -3,7 +3,6 @@ #include "gtk.h" #include "../progress.h" -#include "util.h" static GtkWidget *dialog; static GtkWidget *progress; diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c index 1a2616b97b5c..f5eee4d66873 100644 --- a/tools/perf/ui/gtk/setup.c +++ b/tools/perf/ui/gtk/setup.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "gtk.h" -#include "../../util/debug.h" +#include <linux/compiler.h> +#include "../util.h" extern struct perf_error_ops perf_gtk_eops; diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c index c2c558958b9c..c47f5c387838 100644 --- a/tools/perf/ui/gtk/util.c +++ b/tools/perf/ui/gtk/util.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include "../util.h" -#include "../../util/debug.h" #include "gtk.h" #include <stdlib.h> diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c index 54bcd08df87e..911182b3f5e6 100644 --- a/tools/perf/ui/helpline.c +++ b/tools/perf/ui/helpline.c @@ -3,10 +3,8 @@ #include <stdlib.h> #include <string.h> -#include "../util/debug.h" #include "helpline.h" #include "ui.h" -#include "../util/util.h" char ui_helpline__current[512]; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 3e533de7d852..f73675500061 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -8,7 +8,6 @@ #include "../util/callchain.h" #include "../util/debug.h" #include "../util/hist.h" -#include "../util/util.h" #include "../util/sort.h" #include "../util/evsel.h" #include "../util/evlist.h" diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index c7a86b4be9f5..700335cde618 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <pthread.h> #include <dlfcn.h> +#include <unistd.h> #include <subcmd/pager.h> #include "../util/debug.h" #include "../util/hist.h" -#include "../util/util.h" #include "ui.h" pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 832ca6cfbe30..5365606e9dad 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -5,6 +5,7 @@ #include "../../util/callchain.h" #include "../../util/debug.h" +#include "../../util/event.h" #include "../../util/hist.h" #include "../../util/map.h" #include "../../util/map_groups.h" diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c index 5f188f678c55..298d6af82fdd 100644 --- a/tools/perf/ui/tui/helpline.c +++ b/tools/perf/ui/tui/helpline.c @@ -6,7 +6,6 @@ #include <linux/kernel.h> #include <linux/string.h> -#include "../../util/debug.h" #include "../helpline.h" #include "../ui.h" #include "../libslang.h" diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index 56651a4f5aa0..e9bfe856a5de 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -2,13 +2,13 @@ #include <signal.h> #include <stdbool.h> #include <stdlib.h> +#include <unistd.h> #include <linux/kernel.h> #ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #endif #include "../../util/debug.h" -#include "../../util/util.h" #include "../../perf.h" #include "../browser.h" #include "../helpline.h" diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c index 087d9ab054c8..b98dd0e31dc1 100644 --- a/tools/perf/ui/tui/util.c +++ b/tools/perf/ui/tui/util.c @@ -5,7 +5,6 @@ #include <stdlib.h> #include <sys/ttydefaults.h> -#include "../../util/debug.h" #include "../browser.h" #include "../keysyms.h" #include "../helpline.h" diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 0b4d8e0d474c..8dcfca1a882f 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -3,6 +3,7 @@ perf-y += block-range.o perf-y += build-id.o perf-y += cacheline.o perf-y += config.o +perf-y += copyfile.o perf-y += ctype.o perf-y += db-export.o perf-y += env.o @@ -10,6 +11,7 @@ perf-y += event.o perf-y += evlist.o perf-y += evsel.o perf-y += evsel_fprintf.o +perf-y += perf_event_attr_fprintf.o perf-y += evswitch.o perf-y += find_bit.o perf-y += get_current_dir_name.o @@ -86,6 +88,7 @@ perf-y += stat-display.o perf-y += record.o perf-y += srcline.o perf-y += srccode.o +perf-y += synthetic-events.o perf-y += data.o perf-y += tsc.o perf-y += cloexec.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 1748f528b6e9..e830eadfca2a 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -14,7 +14,7 @@ #include <bpf/btf.h> #include <bpf/libbpf.h> #include <linux/btf.h> -#include "util.h" +#include "util.h" // hex_width() #include "ui/ui.h" #include "sort.h" #include "build-id.h" @@ -34,6 +34,7 @@ #include "bpf-event.h" #include "block-range.h" #include "string2.h" +#include "util/event.h" #include "arch/common.h" #include <regex.h> #include <pthread.h> diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 8a7340f6a2a2..53be12b23ff4 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -16,7 +16,6 @@ #include <linux/log2.h> #include <linux/zalloc.h> -#include "cpumap.h" #include "color.h" #include "evsel.h" #include "machine.h" diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 6f25224a3def..8470dfe9fe97 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -31,8 +31,8 @@ #include "map.h" #include "pmu.h" #include "evsel.h" -#include "cpumap.h" #include "symbol.h" +#include "util/synthetic-events.h" #include "thread_map.h" #include "asm/bug.h" #include "auxtrace.h" @@ -50,10 +50,12 @@ #include "intel-bts.h" #include "arm-spe.h" #include "s390-cpumsf.h" -#include "util.h" +#include "util/mmap.h" #include <linux/ctype.h> +#include <linux/kernel.h> #include "symbol/kallsyms.h" +#include <internal/lib.h> static bool auxtrace__dont_decode(struct perf_session *session) { @@ -1226,7 +1228,7 @@ int perf_event__process_auxtrace_error(struct perf_session *session, return 0; } -static int __auxtrace_mmap__read(struct perf_mmap *map, +static int __auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, bool snapshot, size_t snapshot_size) @@ -1337,13 +1339,13 @@ static int __auxtrace_mmap__read(struct perf_mmap *map, return 1; } -int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr, +int auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn) { return __auxtrace_mmap__read(map, itr, tool, fn, false, 0); } -int auxtrace_mmap__read_snapshot(struct perf_mmap *map, +int auxtrace_mmap__read_snapshot(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, size_t snapshot_size) diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 37e70dc01436..f201f36bc35f 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -11,21 +11,22 @@ #include <errno.h> #include <stdbool.h> #include <stddef.h> +#include <stdio.h> // FILE #include <linux/list.h> #include <linux/perf_event.h> #include <linux/types.h> #include <asm/bitsperlong.h> #include <asm/barrier.h> -#include "event.h" - union perf_event; struct perf_session; struct evlist; struct perf_tool; -struct perf_mmap; +struct mmap; +struct perf_sample; struct option; struct record_opts; +struct perf_record_auxtrace_error; struct perf_record_auxtrace_info; struct events_stats; @@ -444,14 +445,14 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, bool per_cpu); typedef int (*process_auxtrace_t)(struct perf_tool *tool, - struct perf_mmap *map, + struct mmap *map, union perf_event *event, void *data1, size_t len1, void *data2, size_t len2); -int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr, +int auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn); -int auxtrace_mmap__read_snapshot(struct perf_mmap *map, +int auxtrace_mmap__read_snapshot(struct mmap *map, struct auxtrace_record *itr, struct perf_tool *tool, process_auxtrace_t fn, size_t snapshot_size); @@ -524,10 +525,6 @@ void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int int code, int cpu, pid_t pid, pid_t tid, u64 ip, const char *msg, u64 timestamp); -int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, - struct perf_tool *tool, - struct perf_session *session, - perf_event__handler_t process); int perf_event__process_auxtrace_info(struct perf_session *session, union perf_event *event); s64 perf_event__process_auxtrace(struct perf_session *session, @@ -604,15 +601,6 @@ void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused) { } -static inline int -perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused, - struct perf_tool *tool __maybe_unused, - struct perf_session *session __maybe_unused, - perf_event__handler_t process __maybe_unused) -{ - return -EINVAL; -} - static inline int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused, struct evlist *evlist __maybe_unused, diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 7a3d4b125323..f7ed5d122e22 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -16,6 +16,7 @@ #include "map.h" #include "evlist.h" #include "record.h" +#include "util/synthetic-events.h" #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index a01c2fd68c03..81fdc88e6c1a 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -6,9 +6,9 @@ #include <linux/rbtree.h> #include <pthread.h> #include <api/fd/array.h> -#include "event.h" #include <stdio.h> +struct bpf_prog_info; struct machine; union perf_event; struct perf_env; @@ -33,11 +33,6 @@ struct btf_node { #ifdef HAVE_LIBBPF_SUPPORT int machine__process_bpf(struct machine *machine, union perf_event *event, struct perf_sample *sample); - -int perf_event__synthesize_bpf_events(struct perf_session *session, - perf_event__handler_t process, - struct machine *machine, - struct record_opts *opts); int bpf_event__add_sb_event(struct evlist **evlist, struct perf_env *env); void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, @@ -51,14 +46,6 @@ static inline int machine__process_bpf(struct machine *machine __maybe_unused, return 0; } -static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused, - perf_event__handler_t process __maybe_unused, - struct machine *machine __maybe_unused, - struct record_opts *opts __maybe_unused) -{ - return 0; -} - static inline int bpf_event__add_sb_event(struct evlist **evlist __maybe_unused, struct perf_env *env __maybe_unused) { diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 37283e865352..10c187b8b8ea 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -1568,7 +1568,7 @@ struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name) return ERR_PTR(-err); } - evsel = perf_evlist__last(evlist); + evsel = evlist__last(evlist); } bpf__for_each_map_named(map, obj, tmp, name) { diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c index 9d1e090084a2..2285b1eb3128 100644 --- a/tools/perf/util/branch.c +++ b/tools/perf/util/branch.c @@ -1,5 +1,3 @@ -#include "util/util.h" -#include "util/debug.h" #include "util/map_symbol.h" #include "util/branch.h" #include <linux/kernel.h> diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h index 06f66dad0b79..88e00d268f6f 100644 --- a/tools/perf/util/branch.h +++ b/tools/perf/util/branch.h @@ -1,8 +1,15 @@ #ifndef _PERF_BRANCH_H #define _PERF_BRANCH_H 1 - +/* + * The linux/stddef.h isn't need here, but is needed for __always_inline used + * in files included from uapi/linux/perf_event.h such as + * /usr/include/linux/swab.h and /usr/include/linux/byteorder/little_endian.h, + * detected in at least musl libc, used in Alpine Linux. -acme + */ #include <stdio.h> #include <stdint.h> +#include <linux/compiler.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include <linux/types.h> diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e5fb77755d9e..c076fc7fe025 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -7,12 +7,13 @@ * Copyright (C) 2009, 2010 Red Hat Inc. * Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com> */ -#include "util.h" +#include "util.h" // lsdir(), mkdir_p(), rm_rf() #include <dirent.h> #include <errno.h> #include <stdio.h> #include <sys/stat.h> #include <sys/types.h> +#include "util/copyfile.h" #include "dso.h" #include "build-id.h" #include "event.h" diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index c14646c1f2eb..9a9b56ed3f0a 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -23,6 +23,7 @@ #include "debug.h" #include "dso.h" +#include "event.h" #include "hist.h" #include "sort.h" #include "machine.h" diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index b042ceef4114..83398e5bbe4b 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -4,12 +4,15 @@ #include <linux/list.h> #include <linux/rbtree.h> -#include "event.h" #include "map_symbol.h" #include "branch.h" +struct addr_location; struct evsel; +struct ip_callchain; struct map; +struct perf_sample; +struct thread; #define HELP_PAD "\t\t\t\t" diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 4e904fcb2783..a12872f2856a 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <sched.h> -#include "util.h" +#include "util.h" // for sched_getcpu() #include "../perf-sys.h" #include "cloexec.h" #include "event.h" diff --git a/tools/perf/util/copyfile.c b/tools/perf/util/copyfile.c new file mode 100644 index 000000000000..3fa0db136667 --- /dev/null +++ b/tools/perf/util/copyfile.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "util/copyfile.h" +#include "util/namespaces.h" +#include <internal/lib.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi) +{ + int err = -1; + char *line = NULL; + size_t n; + FILE *from_fp, *to_fp; + struct nscookie nsc; + + nsinfo__mountns_enter(nsi, &nsc); + from_fp = fopen(from, "r"); + nsinfo__mountns_exit(&nsc); + if (from_fp == NULL) + goto out; + + to_fp = fopen(to, "w"); + if (to_fp == NULL) + goto out_fclose_from; + + while (getline(&line, &n, from_fp) > 0) + if (fputs(line, to_fp) == EOF) + goto out_fclose_to; + err = 0; +out_fclose_to: + fclose(to_fp); + free(line); +out_fclose_from: + fclose(from_fp); +out: + return err; +} + +int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) +{ + void *ptr; + loff_t pgoff; + + pgoff = off_in & ~(page_size - 1); + off_in -= pgoff; + + ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff); + if (ptr == MAP_FAILED) + return -1; + + while (size) { + ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out); + if (ret < 0 && errno == EINTR) + continue; + if (ret <= 0) + break; + + size -= ret; + off_in += ret; + off_out += ret; + } + munmap(ptr, off_in + size); + + return size ? -1 : 0; +} + +static int copyfile_mode_ns(const char *from, const char *to, mode_t mode, + struct nsinfo *nsi) +{ + int fromfd, tofd; + struct stat st; + int err; + char *tmp = NULL, *ptr = NULL; + struct nscookie nsc; + + nsinfo__mountns_enter(nsi, &nsc); + err = stat(from, &st); + nsinfo__mountns_exit(&nsc); + if (err) + goto out; + err = -1; + + /* extra 'x' at the end is to reserve space for '.' */ + if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) { + tmp = NULL; + goto out; + } + ptr = strrchr(tmp, '/'); + if (!ptr) + goto out; + ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1); + *ptr = '.'; + + tofd = mkstemp(tmp); + if (tofd < 0) + goto out; + + if (fchmod(tofd, mode)) + goto out_close_to; + + if (st.st_size == 0) { /* /proc? do it slowly... */ + err = slow_copyfile(from, tmp, nsi); + goto out_close_to; + } + + nsinfo__mountns_enter(nsi, &nsc); + fromfd = open(from, O_RDONLY); + nsinfo__mountns_exit(&nsc); + if (fromfd < 0) + goto out_close_to; + + err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size); + + close(fromfd); +out_close_to: + close(tofd); + if (!err) + err = link(tmp, to); + unlink(tmp); +out: + free(tmp); + return err; +} + +int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi) +{ + return copyfile_mode_ns(from, to, 0755, nsi); +} + +int copyfile_mode(const char *from, const char *to, mode_t mode) +{ + return copyfile_mode_ns(from, to, mode, NULL); +} + +int copyfile(const char *from, const char *to) +{ + return copyfile_mode(from, to, 0755); +} diff --git a/tools/perf/util/copyfile.h b/tools/perf/util/copyfile.h new file mode 100644 index 000000000000..e85d2f22f3cc --- /dev/null +++ b/tools/perf/util/copyfile.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef PERF_COPYFILE_H_ +#define PERF_COPYFILE_H_ + +#include <linux/types.h> +#include <sys/types.h> +#include <fcntl.h> + +struct nsinfo; + +int copyfile(const char *from, const char *to); +int copyfile_mode(const char *from, const char *to, mode_t mode); +int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); +int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size); + +#endif // PERF_COPYFILE_H_ diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 37d7c492b155..cd92a99eb89d 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -17,7 +17,6 @@ #include "cs-etm.h" #include "cs-etm-decoder.h" #include "intlist.h" -#include "util.h" /* use raw logging */ #ifdef CS_DEBUG_RAW diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 707afdbd9529..4ba0f871f086 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -35,7 +35,7 @@ #include "thread.h" #include "thread-stack.h" #include <tools/libc_compat.h> -#include "util.h" +#include "util/synthetic-events.h" #define MAX_TIMESTAMP (~0ULL) @@ -1298,7 +1298,7 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, attr.read_format = evsel->core.attr.read_format; /* create new id val to be a fixed offset from evsel id */ - id = evsel->id[0] + 1000000000; + id = evsel->core.id[0] + 1000000000; if (!id) id = 1; diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 0c268449959c..dbc772bfb04e 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -30,6 +30,7 @@ #include "machine.h" #include "config.h" #include <linux/ctype.h> +#include <linux/err.h> #define pr_N(n, fmt, ...) \ eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) @@ -1619,8 +1620,10 @@ int bt_convert__perf2ctf(const char *input, const char *path, err = -1; /* perf.data session */ session = perf_session__new(&data, 0, &c.tool); - if (!session) + if (IS_ERR(session)) { + err = PTR_ERR(session); goto free_writer; + } if (c.queue_size) { ordered_events__set_alloc_size(&session->ordered_events, diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index e75c3a279fe8..88fba2ba549f 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -13,9 +13,10 @@ #include <dirent.h> #include "data.h" -#include "util.h" +#include "util.h" // rm_rf_perf_data() #include "debug.h" #include "header.h" +#include <internal/lib.h> static void close_dir(struct perf_data_file *files, int nr) { diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index a1b59bd35519..e55114f0336f 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -17,7 +17,6 @@ #include "event.h" #include "debug.h" #include "print_binary.h" -#include "util.h" #include "target.h" #include "ui/helpline.h" #include "ui/ui.h" diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index b2deee987ffa..d25ae1c4cee9 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -3,9 +3,9 @@ #ifndef __PERF_DEBUG_H #define __PERF_DEBUG_H +#include <stdarg.h> #include <stdbool.h> #include <linux/compiler.h> -#include "../ui/util.h" extern int verbose; extern bool quiet, dump_trace; diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c index 763328c151e9..6fb7f34c0814 100644 --- a/tools/perf/util/demangle-java.c +++ b/tools/perf/util/demangle-java.c @@ -3,7 +3,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include "debug.h" #include "symbol.h" #include "demangle-java.h" diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c index 423afbbd386b..a659fc69f73a 100644 --- a/tools/perf/util/demangle-rust.c +++ b/tools/perf/util/demangle-rust.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> -#include "util.h" #include "debug.h" #include "demangle-rust.h" diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index db55eddce8cd..1b49ecee5aff 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -5,7 +5,6 @@ * Written by: Masami Hiramatsu <mhiramat@kernel.org> */ -#include <util.h> #include <debug.h> #include <dwarf-regs.h> #include <elf.h> diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index d8e083d42610..db40906e2937 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -4,9 +4,10 @@ #include <linux/types.h> #include <linux/rbtree.h> -#include "cpumap.h" #include "rwsem.h" +struct perf_cpu_map; + struct cpu_topology_map { int socket_id; int die_id; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index f4afbb858ebb..fc1e5a991008 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,16 +1,16 @@ -#include <dirent.h> #include <errno.h> #include <fcntl.h> #include <inttypes.h> #include <linux/kernel.h> #include <linux/types.h> +#include <perf/cpumap.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ -#include <api/fs/fs.h> #include <linux/perf_event.h> #include <linux/zalloc.h> +#include "cpumap.h" #include "dso.h" #include "event.h" #include "debug.h" @@ -24,6 +24,7 @@ #include "time-utils.h" #include <linux/ctype.h> #include "map.h" +#include "util/namespaces.h" #include "symbol.h" #include "symbol/kallsyms.h" #include "asm/bug.h" @@ -33,8 +34,6 @@ #include "tool.h" #include "../perf.h" -#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500 - static const char *perf_event__names[] = { [0] = "TOTAL", [PERF_RECORD_MMAP] = "MMAP", @@ -75,18 +74,6 @@ static const char *perf_event__names[] = { [PERF_RECORD_COMPRESSED] = "COMPRESSED", }; -static const char *perf_ns__names[] = { - [NET_NS_INDEX] = "net", - [UTS_NS_INDEX] = "uts", - [IPC_NS_INDEX] = "ipc", - [PID_NS_INDEX] = "pid", - [USER_NS_INDEX] = "user", - [MNT_NS_INDEX] = "mnt", - [CGROUP_NS_INDEX] = "cgroup", -}; - -unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT; - const char *perf_event__name(unsigned int id) { if (id >= ARRAY_SIZE(perf_event__names)) @@ -96,775 +83,6 @@ const char *perf_event__name(unsigned int id) return perf_event__names[id]; } -static const char *perf_ns__name(unsigned int id) -{ - if (id >= ARRAY_SIZE(perf_ns__names)) - return "UNKNOWN"; - return perf_ns__names[id]; -} - -int perf_tool__process_synth_event(struct perf_tool *tool, - union perf_event *event, - struct machine *machine, - perf_event__handler_t process) -{ - struct perf_sample synth_sample = { - .pid = -1, - .tid = -1, - .time = -1, - .stream_id = -1, - .cpu = -1, - .period = 1, - .cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK, - }; - - return process(tool, event, &synth_sample, machine); -}; - -/* - * Assumes that the first 4095 bytes of /proc/pid/stat contains - * the comm, tgid and ppid. - */ -static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, - pid_t *tgid, pid_t *ppid) -{ - char filename[PATH_MAX]; - char bf[4096]; - int fd; - size_t size = 0; - ssize_t n; - char *name, *tgids, *ppids; - - *tgid = -1; - *ppid = -1; - - snprintf(filename, sizeof(filename), "/proc/%d/status", pid); - - fd = open(filename, O_RDONLY); - if (fd < 0) { - pr_debug("couldn't open %s\n", filename); - return -1; - } - - n = read(fd, bf, sizeof(bf) - 1); - close(fd); - if (n <= 0) { - pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n", - pid); - return -1; - } - bf[n] = '\0'; - - name = strstr(bf, "Name:"); - tgids = strstr(bf, "Tgid:"); - ppids = strstr(bf, "PPid:"); - - if (name) { - char *nl; - - name = skip_spaces(name + 5); /* strlen("Name:") */ - nl = strchr(name, '\n'); - if (nl) - *nl = '\0'; - - size = strlen(name); - if (size >= len) - size = len - 1; - memcpy(comm, name, size); - comm[size] = '\0'; - } else { - pr_debug("Name: string not found for pid %d\n", pid); - } - - if (tgids) { - tgids += 5; /* strlen("Tgid:") */ - *tgid = atoi(tgids); - } else { - pr_debug("Tgid: string not found for pid %d\n", pid); - } - - if (ppids) { - ppids += 5; /* strlen("PPid:") */ - *ppid = atoi(ppids); - } else { - pr_debug("PPid: string not found for pid %d\n", pid); - } - - return 0; -} - -static int perf_event__prepare_comm(union perf_event *event, pid_t pid, - struct machine *machine, - pid_t *tgid, pid_t *ppid) -{ - size_t size; - - *ppid = -1; - - memset(&event->comm, 0, sizeof(event->comm)); - - if (machine__is_host(machine)) { - if (perf_event__get_comm_ids(pid, event->comm.comm, - sizeof(event->comm.comm), - tgid, ppid) != 0) { - return -1; - } - } else { - *tgid = machine->pid; - } - - if (*tgid < 0) - return -1; - - event->comm.pid = *tgid; - event->comm.header.type = PERF_RECORD_COMM; - - size = strlen(event->comm.comm) + 1; - size = PERF_ALIGN(size, sizeof(u64)); - memset(event->comm.comm + size, 0, machine->id_hdr_size); - event->comm.header.size = (sizeof(event->comm) - - (sizeof(event->comm.comm) - size) + - machine->id_hdr_size); - event->comm.tid = pid; - - return 0; -} - -pid_t perf_event__synthesize_comm(struct perf_tool *tool, - union perf_event *event, pid_t pid, - perf_event__handler_t process, - struct machine *machine) -{ - pid_t tgid, ppid; - - if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0) - return -1; - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) - return -1; - - return tgid; -} - -static void perf_event__get_ns_link_info(pid_t pid, const char *ns, - struct perf_ns_link_info *ns_link_info) -{ - struct stat64 st; - char proc_ns[128]; - - sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns); - if (stat64(proc_ns, &st) == 0) { - ns_link_info->dev = st.st_dev; - ns_link_info->ino = st.st_ino; - } -} - -int perf_event__synthesize_namespaces(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, - perf_event__handler_t process, - struct machine *machine) -{ - u32 idx; - struct perf_ns_link_info *ns_link_info; - - if (!tool || !tool->namespace_events) - return 0; - - memset(&event->namespaces, 0, (sizeof(event->namespaces) + - (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + - machine->id_hdr_size)); - - event->namespaces.pid = tgid; - event->namespaces.tid = pid; - - event->namespaces.nr_namespaces = NR_NAMESPACES; - - ns_link_info = event->namespaces.link_info; - - for (idx = 0; idx < event->namespaces.nr_namespaces; idx++) - perf_event__get_ns_link_info(pid, perf_ns__name(idx), - &ns_link_info[idx]); - - event->namespaces.header.type = PERF_RECORD_NAMESPACES; - - event->namespaces.header.size = (sizeof(event->namespaces) + - (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + - machine->id_hdr_size); - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) - return -1; - - return 0; -} - -static int perf_event__synthesize_fork(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, pid_t ppid, - perf_event__handler_t process, - struct machine *machine) -{ - memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - - /* - * for main thread set parent to ppid from status file. For other - * threads set parent pid to main thread. ie., assume main thread - * spawns all threads in a process - */ - if (tgid == pid) { - event->fork.ppid = ppid; - event->fork.ptid = ppid; - } else { - event->fork.ppid = tgid; - event->fork.ptid = tgid; - } - event->fork.pid = tgid; - event->fork.tid = pid; - event->fork.header.type = PERF_RECORD_FORK; - event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC; - - event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size); - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) - return -1; - - return 0; -} - -int perf_event__synthesize_mmap_events(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data) -{ - char filename[PATH_MAX]; - FILE *fp; - unsigned long long t; - bool truncation = false; - unsigned long long timeout = proc_map_timeout * 1000000ULL; - int rc = 0; - const char *hugetlbfs_mnt = hugetlbfs__mountpoint(); - int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0; - - if (machine__is_default_guest(machine)) - return 0; - - snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps", - machine->root_dir, pid, pid); - - fp = fopen(filename, "r"); - if (fp == NULL) { - /* - * We raced with a task exiting - just return: - */ - pr_debug("couldn't open %s\n", filename); - return -1; - } - - event->header.type = PERF_RECORD_MMAP2; - t = rdclock(); - - while (1) { - char bf[BUFSIZ]; - char prot[5]; - char execname[PATH_MAX]; - char anonstr[] = "//anon"; - unsigned int ino; - size_t size; - ssize_t n; - - if (fgets(bf, sizeof(bf), fp) == NULL) - break; - - if ((rdclock() - t) > timeout) { - pr_warning("Reading %s time out. " - "You may want to increase " - "the time limit by --proc-map-timeout\n", - filename); - truncation = true; - goto out; - } - - /* ensure null termination since stack will be reused. */ - strcpy(execname, ""); - - /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n", - &event->mmap2.start, &event->mmap2.len, prot, - &event->mmap2.pgoff, &event->mmap2.maj, - &event->mmap2.min, - &ino, execname); - - /* - * Anon maps don't have the execname. - */ - if (n < 7) - continue; - - event->mmap2.ino = (u64)ino; - - /* - * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c - */ - if (machine__is_host(machine)) - event->header.misc = PERF_RECORD_MISC_USER; - else - event->header.misc = PERF_RECORD_MISC_GUEST_USER; - - /* map protection and flags bits */ - event->mmap2.prot = 0; - event->mmap2.flags = 0; - if (prot[0] == 'r') - event->mmap2.prot |= PROT_READ; - if (prot[1] == 'w') - event->mmap2.prot |= PROT_WRITE; - if (prot[2] == 'x') - event->mmap2.prot |= PROT_EXEC; - - if (prot[3] == 's') - event->mmap2.flags |= MAP_SHARED; - else - event->mmap2.flags |= MAP_PRIVATE; - - if (prot[2] != 'x') { - if (!mmap_data || prot[0] != 'r') - continue; - - event->header.misc |= PERF_RECORD_MISC_MMAP_DATA; - } - -out: - if (truncation) - event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT; - - if (!strcmp(execname, "")) - strcpy(execname, anonstr); - - if (hugetlbfs_mnt_len && - !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) { - strcpy(execname, anonstr); - event->mmap2.flags |= MAP_HUGETLB; - } - - size = strlen(execname) + 1; - memcpy(event->mmap2.filename, execname, size); - size = PERF_ALIGN(size, sizeof(u64)); - event->mmap2.len -= event->mmap.start; - event->mmap2.header.size = (sizeof(event->mmap2) - - (sizeof(event->mmap2.filename) - size)); - memset(event->mmap2.filename + size, 0, machine->id_hdr_size); - event->mmap2.header.size += machine->id_hdr_size; - event->mmap2.pid = tgid; - event->mmap2.tid = pid; - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { - rc = -1; - break; - } - - if (truncation) - break; - } - - fclose(fp); - return rc; -} - -int perf_event__synthesize_modules(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - int rc = 0; - struct map *pos; - struct maps *maps = machine__kernel_maps(machine); - union perf_event *event = zalloc((sizeof(event->mmap) + - machine->id_hdr_size)); - if (event == NULL) { - pr_debug("Not enough memory synthesizing mmap event " - "for kernel modules\n"); - return -1; - } - - event->header.type = PERF_RECORD_MMAP; - - /* - * kernel uses 0 for user space maps, see kernel/perf_event.c - * __perf_event_mmap - */ - if (machine__is_host(machine)) - event->header.misc = PERF_RECORD_MISC_KERNEL; - else - event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - - for (pos = maps__first(maps); pos; pos = map__next(pos)) { - size_t size; - - if (!__map__is_kmodule(pos)) - continue; - - size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); - event->mmap.header.type = PERF_RECORD_MMAP; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, machine->id_hdr_size); - event->mmap.header.size += machine->id_hdr_size; - event->mmap.start = pos->start; - event->mmap.len = pos->end - pos->start; - event->mmap.pid = machine->pid; - - memcpy(event->mmap.filename, pos->dso->long_name, - pos->dso->long_name_len + 1); - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { - rc = -1; - break; - } - } - - free(event); - return rc; -} - -static int __event__synthesize_thread(union perf_event *comm_event, - union perf_event *mmap_event, - union perf_event *fork_event, - union perf_event *namespaces_event, - pid_t pid, int full, - perf_event__handler_t process, - struct perf_tool *tool, - struct machine *machine, - bool mmap_data) -{ - char filename[PATH_MAX]; - DIR *tasks; - struct dirent *dirent; - pid_t tgid, ppid; - int rc = 0; - - /* special case: only send one comm event using passed in pid */ - if (!full) { - tgid = perf_event__synthesize_comm(tool, comm_event, pid, - process, machine); - - if (tgid == -1) - return -1; - - if (perf_event__synthesize_namespaces(tool, namespaces_event, pid, - tgid, process, machine) < 0) - return -1; - - /* - * send mmap only for thread group leader - * see thread__init_map_groups - */ - if (pid == tgid && - perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, - process, machine, mmap_data)) - return -1; - - return 0; - } - - if (machine__is_default_guest(machine)) - return 0; - - snprintf(filename, sizeof(filename), "%s/proc/%d/task", - machine->root_dir, pid); - - tasks = opendir(filename); - if (tasks == NULL) { - pr_debug("couldn't open %s\n", filename); - return 0; - } - - while ((dirent = readdir(tasks)) != NULL) { - char *end; - pid_t _pid; - - _pid = strtol(dirent->d_name, &end, 10); - if (*end) - continue; - - rc = -1; - if (perf_event__prepare_comm(comm_event, _pid, machine, - &tgid, &ppid) != 0) - break; - - if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, - ppid, process, machine) < 0) - break; - - if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid, - tgid, process, machine) < 0) - break; - - /* - * Send the prepared comm event - */ - if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0) - break; - - rc = 0; - if (_pid == pid) { - /* process the parent's maps too */ - rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, - process, machine, mmap_data); - if (rc) - break; - } - } - - closedir(tasks); - return rc; -} - -int perf_event__synthesize_thread_map(struct perf_tool *tool, - struct perf_thread_map *threads, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data) -{ - union perf_event *comm_event, *mmap_event, *fork_event; - union perf_event *namespaces_event; - int err = -1, thread, j; - - comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); - if (comm_event == NULL) - goto out; - - mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); - if (mmap_event == NULL) - goto out_free_comm; - - fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); - if (fork_event == NULL) - goto out_free_mmap; - - namespaces_event = malloc(sizeof(namespaces_event->namespaces) + - (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + - machine->id_hdr_size); - if (namespaces_event == NULL) - goto out_free_fork; - - err = 0; - for (thread = 0; thread < threads->nr; ++thread) { - if (__event__synthesize_thread(comm_event, mmap_event, - fork_event, namespaces_event, - perf_thread_map__pid(threads, thread), 0, - process, tool, machine, - mmap_data)) { - err = -1; - break; - } - - /* - * comm.pid is set to thread group id by - * perf_event__synthesize_comm - */ - if ((int) comm_event->comm.pid != perf_thread_map__pid(threads, thread)) { - bool need_leader = true; - - /* is thread group leader in thread_map? */ - for (j = 0; j < threads->nr; ++j) { - if ((int) comm_event->comm.pid == perf_thread_map__pid(threads, j)) { - need_leader = false; - break; - } - } - - /* if not, generate events for it */ - if (need_leader && - __event__synthesize_thread(comm_event, mmap_event, - fork_event, namespaces_event, - comm_event->comm.pid, 0, - process, tool, machine, - mmap_data)) { - err = -1; - break; - } - } - } - free(namespaces_event); -out_free_fork: - free(fork_event); -out_free_mmap: - free(mmap_event); -out_free_comm: - free(comm_event); -out: - return err; -} - -static int __perf_event__synthesize_threads(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data, - struct dirent **dirent, - int start, - int num) -{ - union perf_event *comm_event, *mmap_event, *fork_event; - union perf_event *namespaces_event; - int err = -1; - char *end; - pid_t pid; - int i; - - comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); - if (comm_event == NULL) - goto out; - - mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); - if (mmap_event == NULL) - goto out_free_comm; - - fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); - if (fork_event == NULL) - goto out_free_mmap; - - namespaces_event = malloc(sizeof(namespaces_event->namespaces) + - (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + - machine->id_hdr_size); - if (namespaces_event == NULL) - goto out_free_fork; - - for (i = start; i < start + num; i++) { - if (!isdigit(dirent[i]->d_name[0])) - continue; - - pid = (pid_t)strtol(dirent[i]->d_name, &end, 10); - /* only interested in proper numerical dirents */ - if (*end) - continue; - /* - * We may race with exiting thread, so don't stop just because - * one thread couldn't be synthesized. - */ - __event__synthesize_thread(comm_event, mmap_event, fork_event, - namespaces_event, pid, 1, process, - tool, machine, mmap_data); - } - err = 0; - - free(namespaces_event); -out_free_fork: - free(fork_event); -out_free_mmap: - free(mmap_event); -out_free_comm: - free(comm_event); -out: - return err; -} - -struct synthesize_threads_arg { - struct perf_tool *tool; - perf_event__handler_t process; - struct machine *machine; - bool mmap_data; - struct dirent **dirent; - int num; - int start; -}; - -static void *synthesize_threads_worker(void *arg) -{ - struct synthesize_threads_arg *args = arg; - - __perf_event__synthesize_threads(args->tool, args->process, - args->machine, args->mmap_data, - args->dirent, - args->start, args->num); - return NULL; -} - -int perf_event__synthesize_threads(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data, - unsigned int nr_threads_synthesize) -{ - struct synthesize_threads_arg *args = NULL; - pthread_t *synthesize_threads = NULL; - char proc_path[PATH_MAX]; - struct dirent **dirent; - int num_per_thread; - int m, n, i, j; - int thread_nr; - int base = 0; - int err = -1; - - - if (machine__is_default_guest(machine)) - return 0; - - snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); - n = scandir(proc_path, &dirent, 0, alphasort); - if (n < 0) - return err; - - if (nr_threads_synthesize == UINT_MAX) - thread_nr = sysconf(_SC_NPROCESSORS_ONLN); - else - thread_nr = nr_threads_synthesize; - - if (thread_nr <= 1) { - err = __perf_event__synthesize_threads(tool, process, - machine, mmap_data, - dirent, base, n); - goto free_dirent; - } - if (thread_nr > n) - thread_nr = n; - - synthesize_threads = calloc(sizeof(pthread_t), thread_nr); - if (synthesize_threads == NULL) - goto free_dirent; - - args = calloc(sizeof(*args), thread_nr); - if (args == NULL) - goto free_threads; - - num_per_thread = n / thread_nr; - m = n % thread_nr; - for (i = 0; i < thread_nr; i++) { - args[i].tool = tool; - args[i].process = process; - args[i].machine = machine; - args[i].mmap_data = mmap_data; - args[i].dirent = dirent; - } - for (i = 0; i < m; i++) { - args[i].num = num_per_thread + 1; - args[i].start = i * args[i].num; - } - if (i != 0) - base = args[i-1].start + args[i-1].num; - for (j = i; j < thread_nr; j++) { - args[j].num = num_per_thread; - args[j].start = base + (j - i) * args[i].num; - } - - for (i = 0; i < thread_nr; i++) { - if (pthread_create(&synthesize_threads[i], NULL, - synthesize_threads_worker, &args[i])) - goto out_join; - } - err = 0; -out_join: - for (i = 0; i < thread_nr; i++) - pthread_join(synthesize_threads[i], NULL); - free(args); -free_threads: - free(synthesize_threads); -free_dirent: - for (i = 0; i < n; i++) - zfree(&dirent[i]); - free(dirent); - - return err; -} - struct process_symbol_args { const char *name; u64 start; @@ -899,327 +117,6 @@ int kallsyms__get_function_start(const char *kallsyms_filename, return 0; } -int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused, - perf_event__handler_t process __maybe_unused, - struct machine *machine __maybe_unused) -{ - return 0; -} - -static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - size_t size; - struct map *map = machine__kernel_map(machine); - struct kmap *kmap; - int err; - union perf_event *event; - - if (map == NULL) - return -1; - - kmap = map__kmap(map); - if (!kmap->ref_reloc_sym) - return -1; - - /* - * We should get this from /sys/kernel/sections/.text, but till that is - * available use this, and after it is use this as a fallback for older - * kernels. - */ - event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); - if (event == NULL) { - pr_debug("Not enough memory synthesizing mmap event " - "for kernel modules\n"); - return -1; - } - - if (machine__is_host(machine)) { - /* - * kernel uses PERF_RECORD_MISC_USER for user space maps, - * see kernel/perf_event.c __perf_event_mmap - */ - event->header.misc = PERF_RECORD_MISC_KERNEL; - } else { - event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - } - - size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), - "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; - size = PERF_ALIGN(size, sizeof(u64)); - event->mmap.header.type = PERF_RECORD_MMAP; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); - event->mmap.pgoff = kmap->ref_reloc_sym->addr; - event->mmap.start = map->start; - event->mmap.len = map->end - event->mmap.start; - event->mmap.pid = machine->pid; - - err = perf_tool__process_synth_event(tool, event, machine, process); - free(event); - - return err; -} - -int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - int err; - - err = __perf_event__synthesize_kernel_mmap(tool, process, machine); - if (err < 0) - return err; - - return perf_event__synthesize_extra_kmaps(tool, process, machine); -} - -int perf_event__synthesize_thread_map2(struct perf_tool *tool, - struct perf_thread_map *threads, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event *event; - int i, err, size; - - size = sizeof(event->thread_map); - size += threads->nr * sizeof(event->thread_map.entries[0]); - - event = zalloc(size); - if (!event) - return -ENOMEM; - - event->header.type = PERF_RECORD_THREAD_MAP; - event->header.size = size; - event->thread_map.nr = threads->nr; - - for (i = 0; i < threads->nr; i++) { - struct perf_record_thread_map_entry *entry = &event->thread_map.entries[i]; - char *comm = perf_thread_map__comm(threads, i); - - if (!comm) - comm = (char *) ""; - - entry->pid = perf_thread_map__pid(threads, i); - strncpy((char *) &entry->comm, comm, sizeof(entry->comm)); - } - - err = process(tool, event, NULL, machine); - - free(event); - return err; -} - -static void synthesize_cpus(struct cpu_map_entries *cpus, - struct perf_cpu_map *map) -{ - int i; - - cpus->nr = map->nr; - - for (i = 0; i < map->nr; i++) - cpus->cpu[i] = map->map[i]; -} - -static void synthesize_mask(struct perf_record_record_cpu_map *mask, - struct perf_cpu_map *map, int max) -{ - int i; - - mask->nr = BITS_TO_LONGS(max); - mask->long_size = sizeof(long); - - for (i = 0; i < map->nr; i++) - set_bit(map->map[i], mask->mask); -} - -static size_t cpus_size(struct perf_cpu_map *map) -{ - return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16); -} - -static size_t mask_size(struct perf_cpu_map *map, int *max) -{ - int i; - - *max = 0; - - for (i = 0; i < map->nr; i++) { - /* bit possition of the cpu is + 1 */ - int bit = map->map[i] + 1; - - if (bit > *max) - *max = bit; - } - - return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long); -} - -void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max) -{ - size_t size_cpus, size_mask; - bool is_dummy = perf_cpu_map__empty(map); - - /* - * Both array and mask data have variable size based - * on the number of cpus and their actual values. - * The size of the 'struct perf_record_cpu_map_data' is: - * - * array = size of 'struct cpu_map_entries' + - * number of cpus * sizeof(u64) - * - * mask = size of 'struct perf_record_record_cpu_map' + - * maximum cpu bit converted to size of longs - * - * and finaly + the size of 'struct perf_record_cpu_map_data'. - */ - size_cpus = cpus_size(map); - size_mask = mask_size(map, max); - - if (is_dummy || (size_cpus < size_mask)) { - *size += size_cpus; - *type = PERF_CPU_MAP__CPUS; - } else { - *size += size_mask; - *type = PERF_CPU_MAP__MASK; - } - - *size += sizeof(struct perf_record_cpu_map_data); - *size = PERF_ALIGN(*size, sizeof(u64)); - return zalloc(*size); -} - -void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map, - u16 type, int max) -{ - data->type = type; - - switch (type) { - case PERF_CPU_MAP__CPUS: - synthesize_cpus((struct cpu_map_entries *) data->data, map); - break; - case PERF_CPU_MAP__MASK: - synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max); - default: - break; - }; -} - -static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map) -{ - size_t size = sizeof(struct perf_record_cpu_map); - struct perf_record_cpu_map *event; - int max; - u16 type; - - event = cpu_map_data__alloc(map, &size, &type, &max); - if (!event) - return NULL; - - event->header.type = PERF_RECORD_CPU_MAP; - event->header.size = size; - event->data.type = type; - - cpu_map_data__synthesize(&event->data, map, type, max); - return event; -} - -int perf_event__synthesize_cpu_map(struct perf_tool *tool, - struct perf_cpu_map *map, - perf_event__handler_t process, - struct machine *machine) -{ - struct perf_record_cpu_map *event; - int err; - - event = cpu_map_event__new(map); - if (!event) - return -ENOMEM; - - err = process(tool, (union perf_event *) event, NULL, machine); - - free(event); - return err; -} - -int perf_event__synthesize_stat_config(struct perf_tool *tool, - struct perf_stat_config *config, - perf_event__handler_t process, - struct machine *machine) -{ - struct perf_record_stat_config *event; - int size, i = 0, err; - - size = sizeof(*event); - size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0])); - - event = zalloc(size); - if (!event) - return -ENOMEM; - - event->header.type = PERF_RECORD_STAT_CONFIG; - event->header.size = size; - event->nr = PERF_STAT_CONFIG_TERM__MAX; - -#define ADD(__term, __val) \ - event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term; \ - event->data[i].val = __val; \ - i++; - - ADD(AGGR_MODE, config->aggr_mode) - ADD(INTERVAL, config->interval) - ADD(SCALE, config->scale) - - WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX, - "stat config terms unbalanced\n"); -#undef ADD - - err = process(tool, (union perf_event *) event, NULL, machine); - - free(event); - return err; -} - -int perf_event__synthesize_stat(struct perf_tool *tool, - u32 cpu, u32 thread, u64 id, - struct perf_counts_values *count, - perf_event__handler_t process, - struct machine *machine) -{ - struct perf_record_stat event; - - event.header.type = PERF_RECORD_STAT; - event.header.size = sizeof(event); - event.header.misc = 0; - - event.id = id; - event.cpu = cpu; - event.thread = thread; - event.val = count->val; - event.ena = count->ena; - event.run = count->run; - - return process(tool, (union perf_event *) &event, NULL, machine); -} - -int perf_event__synthesize_stat_round(struct perf_tool *tool, - u64 evtime, u64 type, - perf_event__handler_t process, - struct machine *machine) -{ - struct perf_record_stat_round event; - - event.header.type = PERF_RECORD_STAT_ROUND; - event.header.size = sizeof(event); - event.header.misc = 0; - - event.time = evtime; - event.type = type; - - return process(tool, (union perf_event *) &event, NULL, machine); -} - void perf_event__read_stat_config(struct perf_stat_config *config, struct perf_record_stat_config *event) { diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 47ad81d47b1a..a0a0c91cde4a 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -279,54 +279,13 @@ enum { void perf_event__print_totals(void); -struct perf_tool; -struct perf_thread_map; struct perf_cpu_map; +struct perf_record_stat_config; struct perf_stat_config; -struct perf_counts_values; - -typedef int (*perf_event__handler_t)(struct perf_tool *tool, - union perf_event *event, - struct perf_sample *sample, - struct machine *machine); +struct perf_tool; -int perf_event__synthesize_thread_map(struct perf_tool *tool, - struct perf_thread_map *threads, - perf_event__handler_t process, - struct machine *machine, bool mmap_data); -int perf_event__synthesize_thread_map2(struct perf_tool *tool, - struct perf_thread_map *threads, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_cpu_map(struct perf_tool *tool, - struct perf_cpu_map *cpus, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_threads(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine, bool mmap_data, - unsigned int nr_threads_synthesize); -int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_stat_config(struct perf_tool *tool, - struct perf_stat_config *config, - perf_event__handler_t process, - struct machine *machine); void perf_event__read_stat_config(struct perf_stat_config *config, struct perf_record_stat_config *event); -int perf_event__synthesize_stat(struct perf_tool *tool, - u32 cpu, u32 thread, u64 id, - struct perf_counts_values *count, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_stat_round(struct perf_tool *tool, - u64 time, u64 type, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_modules(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); int perf_event__process_comm(struct perf_tool *tool, union perf_event *event, @@ -380,10 +339,6 @@ int perf_event__process_bpf(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); -int perf_tool__process_synth_event(struct perf_tool *tool, - union perf_event *event, - struct machine *machine, - perf_event__handler_t process); int perf_event__process(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -405,34 +360,6 @@ void thread__resolve(struct thread *thread, struct addr_location *al, const char *perf_event__name(unsigned int id); -size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, - u64 read_format); -int perf_event__synthesize_sample(union perf_event *event, u64 type, - u64 read_format, - const struct perf_sample *sample); - -pid_t perf_event__synthesize_comm(struct perf_tool *tool, - union perf_event *event, pid_t pid, - perf_event__handler_t process, - struct machine *machine); - -int perf_event__synthesize_namespaces(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, - perf_event__handler_t process, - struct machine *machine); - -int perf_event__synthesize_mmap_events(struct perf_tool *tool, - union perf_event *event, - pid_t pid, pid_t tgid, - perf_event__handler_t process, - struct machine *machine, - bool mmap_data); - -int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); - size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp); size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp); size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 095924aa186b..d277a98e62df 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -10,13 +10,14 @@ #include <inttypes.h> #include <poll.h> #include "cpumap.h" +#include "util/mmap.h" #include "thread_map.h" #include "target.h" #include "evlist.h" #include "evsel.h" #include "debug.h" #include "units.h" -#include "util.h" +#include <internal/lib.h> // page_size #include "../perf.h" #include "asm/bug.h" #include "bpf-event.h" @@ -49,18 +50,14 @@ int sigqueue(pid_t pid, int sig, const union sigval value); #endif #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) -#define SID(e, x, y) xyarray__entry(e->sample_id, x, y) +#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y) void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, struct perf_thread_map *threads) { - int i; - - for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i) - INIT_HLIST_HEAD(&evlist->heads[i]); perf_evlist__init(&evlist->core); perf_evlist__set_maps(&evlist->core, cpus, threads); - fdarray__init(&evlist->pollfd, 64); + fdarray__init(&evlist->core.pollfd, 64); evlist->workload.pid = -1; evlist->bkw_mmap_state = BKW_MMAP_NOTREADY; } @@ -108,7 +105,7 @@ struct evlist *perf_evlist__new_dummy(void) */ void perf_evlist__set_id_pos(struct evlist *evlist) { - struct evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); evlist->id_pos = first->id_pos; evlist->is_pos = first->is_pos; @@ -124,7 +121,7 @@ static void perf_evlist__update_id_pos(struct evlist *evlist) perf_evlist__set_id_pos(evlist); } -static void perf_evlist__purge(struct evlist *evlist) +static void evlist__purge(struct evlist *evlist) { struct evsel *pos, *n; @@ -137,11 +134,11 @@ static void perf_evlist__purge(struct evlist *evlist) evlist->core.nr_entries = 0; } -void perf_evlist__exit(struct evlist *evlist) +void evlist__exit(struct evlist *evlist) { zfree(&evlist->mmap); zfree(&evlist->overwrite_mmap); - fdarray__exit(&evlist->pollfd); + fdarray__exit(&evlist->core.pollfd); } void evlist__delete(struct evlist *evlist) @@ -149,14 +146,14 @@ void evlist__delete(struct evlist *evlist) if (evlist == NULL) return; - perf_evlist__munmap(evlist); + evlist__munmap(evlist); evlist__close(evlist); perf_cpu_map__put(evlist->core.cpus); perf_thread_map__put(evlist->core.threads); evlist->core.cpus = NULL; evlist->core.threads = NULL; - perf_evlist__purge(evlist); - perf_evlist__exit(evlist); + evlist__purge(evlist); + evlist__exit(evlist); free(evlist); } @@ -318,7 +315,7 @@ int perf_evlist__add_newtp(struct evlist *evlist, static int perf_evlist__nr_threads(struct evlist *evlist, struct evsel *evsel) { - if (evsel->system_wide) + if (evsel->core.system_wide) return 1; else return perf_thread_map__nr(evlist->core.threads); @@ -401,128 +398,29 @@ int perf_evlist__enable_event_idx(struct evlist *evlist, return perf_evlist__enable_event_thread(evlist, evsel, idx); } -int perf_evlist__alloc_pollfd(struct evlist *evlist) +int evlist__add_pollfd(struct evlist *evlist, int fd) { - int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); - int nr_threads = perf_thread_map__nr(evlist->core.threads); - int nfds = 0; - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) { - if (evsel->system_wide) - nfds += nr_cpus; - else - nfds += nr_cpus * nr_threads; - } - - if (fdarray__available_entries(&evlist->pollfd) < nfds && - fdarray__grow(&evlist->pollfd, nfds) < 0) - return -ENOMEM; - - return 0; -} - -static int __perf_evlist__add_pollfd(struct evlist *evlist, int fd, - struct perf_mmap *map, short revent) -{ - int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP); - /* - * Save the idx so that when we filter out fds POLLHUP'ed we can - * close the associated evlist->mmap[] entry. - */ - if (pos >= 0) { - evlist->pollfd.priv[pos].ptr = map; - - fcntl(fd, F_SETFL, O_NONBLOCK); - } - - return pos; -} - -int perf_evlist__add_pollfd(struct evlist *evlist, int fd) -{ - return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN); + return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN); } static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd, void *arg __maybe_unused) { - struct perf_mmap *map = fda->priv[fd].ptr; + struct mmap *map = fda->priv[fd].ptr; if (map) perf_mmap__put(map); } -int perf_evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask) +int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask) { - return fdarray__filter(&evlist->pollfd, revents_and_mask, + return fdarray__filter(&evlist->core.pollfd, revents_and_mask, perf_evlist__munmap_filtered, NULL); } -int perf_evlist__poll(struct evlist *evlist, int timeout) +int evlist__poll(struct evlist *evlist, int timeout) { - return fdarray__poll(&evlist->pollfd, timeout); -} - -static void perf_evlist__id_hash(struct evlist *evlist, - struct evsel *evsel, - int cpu, int thread, u64 id) -{ - int hash; - struct perf_sample_id *sid = SID(evsel, cpu, thread); - - sid->id = id; - sid->evsel = evsel; - hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS); - hlist_add_head(&sid->node, &evlist->heads[hash]); -} - -void perf_evlist__id_add(struct evlist *evlist, struct evsel *evsel, - int cpu, int thread, u64 id) -{ - perf_evlist__id_hash(evlist, evsel, cpu, thread, id); - evsel->id[evsel->ids++] = id; -} - -int perf_evlist__id_add_fd(struct evlist *evlist, - struct evsel *evsel, - int cpu, int thread, int fd) -{ - u64 read_data[4] = { 0, }; - int id_idx = 1; /* The first entry is the counter value */ - u64 id; - int ret; - - ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); - if (!ret) - goto add; - - if (errno != ENOTTY) - return -1; - - /* Legacy way to get event id.. All hail to old kernels! */ - - /* - * This way does not work with group format read, so bail - * out in that case. - */ - if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP) - return -1; - - if (!(evsel->core.attr.read_format & PERF_FORMAT_ID) || - read(fd, &read_data, sizeof(read_data)) == -1) - return -1; - - if (evsel->core.attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - ++id_idx; - if (evsel->core.attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - ++id_idx; - - id = read_data[id_idx]; - - add: - perf_evlist__id_add(evlist, evsel, cpu, thread, id); - return 0; + return perf_evlist__poll(&evlist->core, timeout); } static void perf_evlist__set_sid_idx(struct evlist *evlist, @@ -535,7 +433,7 @@ static void perf_evlist__set_sid_idx(struct evlist *evlist, sid->cpu = evlist->core.cpus->map[cpu]; else sid->cpu = -1; - if (!evsel->system_wide && evlist->core.threads && thread >= 0) + if (!evsel->core.system_wide && evlist->core.threads && thread >= 0) sid->tid = perf_thread_map__pid(evlist->core.threads, thread); else sid->tid = -1; @@ -548,7 +446,7 @@ struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id) int hash; hash = hash_64(id, PERF_EVLIST__HLIST_BITS); - head = &evlist->heads[hash]; + head = &evlist->core.heads[hash]; hlist_for_each_entry(sid, head, node) if (sid->id == id) @@ -562,14 +460,14 @@ struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id) struct perf_sample_id *sid; if (evlist->core.nr_entries == 1 || !id) - return perf_evlist__first(evlist); + return evlist__first(evlist); sid = perf_evlist__id2sid(evlist, id); if (sid) - return sid->evsel; + return container_of(sid->evsel, struct evsel, core); if (!perf_evlist__sample_id_all(evlist)) - return perf_evlist__first(evlist); + return evlist__first(evlist); return NULL; } @@ -584,7 +482,7 @@ struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, sid = perf_evlist__id2sid(evlist, id); if (sid) - return sid->evsel; + return container_of(sid->evsel, struct evsel, core); return NULL; } @@ -613,7 +511,7 @@ static int perf_evlist__event2id(struct evlist *evlist, struct evsel *perf_evlist__event2evsel(struct evlist *evlist, union perf_event *event) { - struct evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); struct hlist_head *head; struct perf_sample_id *sid; int hash; @@ -634,11 +532,11 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist, return first; hash = hash_64(id, PERF_EVLIST__HLIST_BITS); - head = &evlist->heads[hash]; + head = &evlist->core.heads[hash]; hlist_for_each_entry(sid, head, node) { if (sid->id == id) - return sid->evsel; + return container_of(sid->evsel, struct evsel, core); } return NULL; } @@ -650,8 +548,8 @@ static int perf_evlist__set_paused(struct evlist *evlist, bool value) if (!evlist->overwrite_mmap) return 0; - for (i = 0; i < evlist->nr_mmaps; i++) { - int fd = evlist->overwrite_mmap[i].fd; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + int fd = evlist->overwrite_mmap[i].core.fd; int err; if (fd < 0) @@ -673,42 +571,42 @@ static int perf_evlist__resume(struct evlist *evlist) return perf_evlist__set_paused(evlist, false); } -static void perf_evlist__munmap_nofree(struct evlist *evlist) +static void evlist__munmap_nofree(struct evlist *evlist) { int i; if (evlist->mmap) - for (i = 0; i < evlist->nr_mmaps; i++) + for (i = 0; i < evlist->core.nr_mmaps; i++) perf_mmap__munmap(&evlist->mmap[i]); if (evlist->overwrite_mmap) - for (i = 0; i < evlist->nr_mmaps; i++) + for (i = 0; i < evlist->core.nr_mmaps; i++) perf_mmap__munmap(&evlist->overwrite_mmap[i]); } -void perf_evlist__munmap(struct evlist *evlist) +void evlist__munmap(struct evlist *evlist) { - perf_evlist__munmap_nofree(evlist); + evlist__munmap_nofree(evlist); zfree(&evlist->mmap); zfree(&evlist->overwrite_mmap); } -static struct perf_mmap *perf_evlist__alloc_mmap(struct evlist *evlist, - bool overwrite) +static struct mmap *evlist__alloc_mmap(struct evlist *evlist, + bool overwrite) { int i; - struct perf_mmap *map; + struct mmap *map; - evlist->nr_mmaps = perf_cpu_map__nr(evlist->core.cpus); + evlist->core.nr_mmaps = perf_cpu_map__nr(evlist->core.cpus); if (perf_cpu_map__empty(evlist->core.cpus)) - evlist->nr_mmaps = perf_thread_map__nr(evlist->core.threads); - map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); + evlist->core.nr_mmaps = perf_thread_map__nr(evlist->core.threads); + map = zalloc(evlist->core.nr_mmaps * sizeof(struct mmap)); if (!map) return NULL; - for (i = 0; i < evlist->nr_mmaps; i++) { - map[i].fd = -1; - map[i].overwrite = overwrite; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + map[i].core.fd = -1; + map[i].core.overwrite = overwrite; /* * When the perf_mmap() call is made we grab one refcount, plus * one extra to let perf_mmap__consume() get the last @@ -718,7 +616,7 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct evlist *evlist, * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and * thus does perf_mmap__get() on it. */ - refcount_set(&map[i].refcnt, 0); + refcount_set(&map[i].core.refcnt, 0); } return map; } @@ -732,7 +630,7 @@ perf_evlist__should_poll(struct evlist *evlist __maybe_unused, return true; } -static int perf_evlist__mmap_per_evsel(struct evlist *evlist, int idx, +static int evlist__mmap_per_evsel(struct evlist *evlist, int idx, struct mmap_params *mp, int cpu_idx, int thread, int *_output, int *_output_overwrite) { @@ -741,7 +639,7 @@ static int perf_evlist__mmap_per_evsel(struct evlist *evlist, int idx, int evlist_cpu = cpu_map__cpu(evlist->core.cpus, cpu_idx); evlist__for_each_entry(evlist, evsel) { - struct perf_mmap *maps = evlist->mmap; + struct mmap *maps = evlist->mmap; int *output = _output; int fd; int cpu; @@ -752,7 +650,7 @@ static int perf_evlist__mmap_per_evsel(struct evlist *evlist, int idx, maps = evlist->overwrite_mmap; if (!maps) { - maps = perf_evlist__alloc_mmap(evlist, true); + maps = evlist__alloc_mmap(evlist, true); if (!maps) return -1; evlist->overwrite_mmap = maps; @@ -762,7 +660,7 @@ static int perf_evlist__mmap_per_evsel(struct evlist *evlist, int idx, mp->prot &= ~PROT_WRITE; } - if (evsel->system_wide && thread) + if (evsel->core.system_wide && thread) continue; cpu = perf_cpu_map__idx(evsel->core.cpus, evlist_cpu); @@ -792,14 +690,14 @@ static int perf_evlist__mmap_per_evsel(struct evlist *evlist, int idx, * other events, so it should not need to be polled anyway. * Therefore don't add it for polling. */ - if (!evsel->system_wide && - __perf_evlist__add_pollfd(evlist, fd, &maps[idx], revent) < 0) { + if (!evsel->core.system_wide && + perf_evlist__add_pollfd(&evlist->core, fd, &maps[idx], revent) < 0) { perf_mmap__put(&maps[idx]); return -1; } if (evsel->core.attr.read_format & PERF_FORMAT_ID) { - if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread, + if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, cpu, thread, fd) < 0) return -1; perf_evlist__set_sid_idx(evlist, evsel, idx, cpu, @@ -810,7 +708,7 @@ static int perf_evlist__mmap_per_evsel(struct evlist *evlist, int idx, return 0; } -static int perf_evlist__mmap_per_cpu(struct evlist *evlist, +static int evlist__mmap_per_cpu(struct evlist *evlist, struct mmap_params *mp) { int cpu, thread; @@ -826,7 +724,7 @@ static int perf_evlist__mmap_per_cpu(struct evlist *evlist, true); for (thread = 0; thread < nr_threads; thread++) { - if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu, + if (evlist__mmap_per_evsel(evlist, cpu, mp, cpu, thread, &output, &output_overwrite)) goto out_unmap; } @@ -835,11 +733,11 @@ static int perf_evlist__mmap_per_cpu(struct evlist *evlist, return 0; out_unmap: - perf_evlist__munmap_nofree(evlist); + evlist__munmap_nofree(evlist); return -1; } -static int perf_evlist__mmap_per_thread(struct evlist *evlist, +static int evlist__mmap_per_thread(struct evlist *evlist, struct mmap_params *mp) { int thread; @@ -853,7 +751,7 @@ static int perf_evlist__mmap_per_thread(struct evlist *evlist, auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread, false); - if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread, + if (evlist__mmap_per_evsel(evlist, thread, mp, 0, thread, &output, &output_overwrite)) goto out_unmap; } @@ -861,7 +759,7 @@ static int perf_evlist__mmap_per_thread(struct evlist *evlist, return 0; out_unmap: - perf_evlist__munmap_nofree(evlist); + evlist__munmap_nofree(evlist); return -1; } @@ -888,7 +786,7 @@ unsigned long perf_event_mlock_kb_in_pages(void) return pages; } -size_t perf_evlist__mmap_size(unsigned long pages) +size_t evlist__mmap_size(unsigned long pages) { if (pages == UINT_MAX) pages = perf_event_mlock_kb_in_pages(); @@ -971,7 +869,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, } /** - * perf_evlist__mmap_ex - Create mmaps to receive events. + * evlist__mmap_ex - Create mmaps to receive events. * @evlist: list of events * @pages: map length in pages * @overwrite: overwrite older events? @@ -979,7 +877,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, * @auxtrace_overwrite - overwrite older auxtrace data? * * If @overwrite is %false the user needs to signal event consumption using - * perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this + * perf_mmap__write_tail(). Using evlist__mmap_read() does this * automatically. * * Similarly, if @auxtrace_overwrite is %false the user needs to signal data @@ -987,7 +885,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, * * Return: %0 on success, negative error code otherwise. */ -int perf_evlist__mmap_ex(struct evlist *evlist, unsigned int pages, +int evlist__mmap_ex(struct evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush, int comp_level) @@ -1004,36 +902,36 @@ int perf_evlist__mmap_ex(struct evlist *evlist, unsigned int pages, .comp_level = comp_level }; if (!evlist->mmap) - evlist->mmap = perf_evlist__alloc_mmap(evlist, false); + evlist->mmap = evlist__alloc_mmap(evlist, false); if (!evlist->mmap) return -ENOMEM; - if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) + if (evlist->core.pollfd.entries == NULL && perf_evlist__alloc_pollfd(&evlist->core) < 0) return -ENOMEM; - evlist->mmap_len = perf_evlist__mmap_size(pages); - pr_debug("mmap size %zuB\n", evlist->mmap_len); - mp.mask = evlist->mmap_len - page_size - 1; + evlist->core.mmap_len = evlist__mmap_size(pages); + pr_debug("mmap size %zuB\n", evlist->core.mmap_len); + mp.mask = evlist->core.mmap_len - page_size - 1; - auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len, + auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->core.mmap_len, auxtrace_pages, auxtrace_overwrite); evlist__for_each_entry(evlist, evsel) { if ((evsel->core.attr.read_format & PERF_FORMAT_ID) && - evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) + evsel->core.sample_id == NULL && + perf_evsel__alloc_id(&evsel->core, perf_cpu_map__nr(cpus), threads->nr) < 0) return -ENOMEM; } if (perf_cpu_map__empty(cpus)) - return perf_evlist__mmap_per_thread(evlist, &mp); + return evlist__mmap_per_thread(evlist, &mp); - return perf_evlist__mmap_per_cpu(evlist, &mp); + return evlist__mmap_per_cpu(evlist, &mp); } -int perf_evlist__mmap(struct evlist *evlist, unsigned int pages) +int evlist__mmap(struct evlist *evlist, unsigned int pages) { - return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0); + return evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0); } int perf_evlist__create_maps(struct evlist *evlist, struct target *target) @@ -1225,7 +1123,7 @@ u64 perf_evlist__combined_branch_type(struct evlist *evlist) bool perf_evlist__valid_read_format(struct evlist *evlist) { - struct evsel *first = perf_evlist__first(evlist), *pos = first; + struct evsel *first = evlist__first(evlist), *pos = first; u64 read_format = first->core.attr.read_format; u64 sample_type = first->core.attr.sample_type; @@ -1243,15 +1141,9 @@ bool perf_evlist__valid_read_format(struct evlist *evlist) return true; } -u64 perf_evlist__read_format(struct evlist *evlist) -{ - struct evsel *first = perf_evlist__first(evlist); - return first->core.attr.read_format; -} - u16 perf_evlist__id_hdr_size(struct evlist *evlist) { - struct evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); struct perf_sample *data; u64 sample_type; u16 size = 0; @@ -1284,7 +1176,7 @@ out: bool perf_evlist__valid_sample_id_all(struct evlist *evlist) { - struct evsel *first = perf_evlist__first(evlist), *pos = first; + struct evsel *first = evlist__first(evlist), *pos = first; evlist__for_each_entry_continue(evlist, pos) { if (first->core.attr.sample_id_all != pos->core.attr.sample_id_all) @@ -1296,7 +1188,7 @@ bool perf_evlist__valid_sample_id_all(struct evlist *evlist) bool perf_evlist__sample_id_all(struct evlist *evlist) { - struct evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); return first->core.attr.sample_id_all; } @@ -1529,19 +1421,6 @@ int perf_evlist__parse_sample_timestamp(struct evlist *evlist, return perf_evsel__parse_sample_timestamp(evsel, event, timestamp); } -size_t perf_evlist__fprintf(struct evlist *evlist, FILE *fp) -{ - struct evsel *evsel; - size_t printed = 0; - - evlist__for_each_entry(evlist, evsel) { - printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "", - perf_evsel__name(evsel)); - } - - return printed + fprintf(fp, "\n"); -} - int perf_evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size) { @@ -1571,7 +1450,7 @@ int perf_evlist__strerror_open(struct evlist *evlist, "Hint:\tThe current value is %d.", value); break; case EINVAL: { - struct evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); int max_freq; if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0) @@ -1599,7 +1478,7 @@ out_default: int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size) { char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); - int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0; + int pages_attempted = evlist->core.mmap_len / 1024, pages_max_per_user, printed = 0; switch (err) { case EPERM: @@ -1633,7 +1512,7 @@ void perf_evlist__to_front(struct evlist *evlist, struct evsel *evsel, *n; LIST_HEAD(move); - if (move_evsel == perf_evlist__first(evlist)) + if (move_evsel == evlist__first(evlist)) return; evlist__for_each_entry_safe(evlist, n, evsel) { @@ -1754,7 +1633,7 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist) void perf_evlist__force_leader(struct evlist *evlist) { if (!evlist->nr_groups) { - struct evsel *leader = perf_evlist__first(evlist); + struct evsel *leader = evlist__first(evlist); perf_evlist__set_leader(evlist); leader->forced_leader = true; @@ -1780,7 +1659,7 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, is_open = false; if (c2->leader == leader) { if (is_open) - evsel__close(c2); + perf_evsel__close(&evsel->core); c2->leader = c2; c2->core.nr_members = 0; } @@ -1844,10 +1723,10 @@ static void *perf_evlist__poll_thread(void *arg) draining = true; if (!draining) - perf_evlist__poll(evlist, 1000); + evlist__poll(evlist, 1000); - for (i = 0; i < evlist->nr_mmaps; i++) { - struct perf_mmap *map = &evlist->mmap[i]; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + struct mmap *map = &evlist->mmap[i]; union perf_event *event; if (perf_mmap__read_init(map)) @@ -1889,7 +1768,7 @@ int perf_evlist__start_sb_thread(struct evlist *evlist, goto out_delete_evlist; } - if (perf_evlist__mmap(evlist, UINT_MAX)) + if (evlist__mmap(evlist, UINT_MAX)) goto out_delete_evlist; evlist__for_each_entry(evlist, counter) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index a55f0f2546e5..7cfe75522ba5 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -7,11 +7,11 @@ #include <linux/refcount.h> #include <linux/list.h> #include <api/fd/array.h> -#include <stdio.h> #include <internal/evlist.h> +#include <internal/evsel.h> #include "events_stats.h" #include "evsel.h" -#include "mmap.h" +#include <pthread.h> #include <signal.h> #include <unistd.h> @@ -20,16 +20,38 @@ struct thread_map; struct perf_cpu_map; struct record_opts; -#define PERF_EVLIST__HLIST_BITS 8 -#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) +/* + * State machine of bkw_mmap_state: + * + * .________________(forbid)_____________. + * | V + * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY + * ^ ^ | ^ | + * | |__(forbid)____/ |___(forbid)___/| + * | | + * \_________________(3)_______________/ + * + * NOTREADY : Backward ring buffers are not ready + * RUNNING : Backward ring buffers are recording + * DATA_PENDING : We are required to collect data from backward ring buffers + * EMPTY : We have collected data from backward ring buffers. + * + * (0): Setup backward ring buffer + * (1): Pause ring buffers for reading + * (2): Read from ring buffers + * (3): Resume ring buffers for recording + */ +enum bkw_mmap_state { + BKW_MMAP_NOTREADY, + BKW_MMAP_RUNNING, + BKW_MMAP_DATA_PENDING, + BKW_MMAP_EMPTY, +}; struct evlist { struct perf_evlist core; - struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; int nr_groups; - int nr_mmaps; bool enabled; - size_t mmap_len; int id_pos; int is_pos; u64 combined_sample_type; @@ -38,9 +60,8 @@ struct evlist { int cork_fd; pid_t pid; } workload; - struct fdarray pollfd; - struct perf_mmap *mmap; - struct perf_mmap *overwrite_mmap; + struct mmap *mmap; + struct mmap *overwrite_mmap; struct evsel *selected; struct events_stats stats; struct perf_env *env; @@ -65,7 +86,7 @@ struct evlist *perf_evlist__new_default(void); struct evlist *perf_evlist__new_dummy(void); void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, struct perf_thread_map *threads); -void perf_evlist__exit(struct evlist *evlist); +void evlist__exit(struct evlist *evlist); void evlist__delete(struct evlist *evlist); void evlist__add(struct evlist *evlist, struct evsel *entry); @@ -119,17 +140,10 @@ struct evsel * perf_evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name); -void perf_evlist__id_add(struct evlist *evlist, struct evsel *evsel, - int cpu, int thread, u64 id); -int perf_evlist__id_add_fd(struct evlist *evlist, - struct evsel *evsel, - int cpu, int thread, int fd); - -int perf_evlist__add_pollfd(struct evlist *evlist, int fd); -int perf_evlist__alloc_pollfd(struct evlist *evlist); -int perf_evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask); +int evlist__add_pollfd(struct evlist *evlist, int fd); +int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask); -int perf_evlist__poll(struct evlist *evlist, int timeout); +int evlist__poll(struct evlist *evlist, int timeout); struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id); struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, @@ -139,7 +153,7 @@ struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id); void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state); -void perf_evlist__mmap_consume(struct evlist *evlist, int idx); +void evlist__mmap_consume(struct evlist *evlist, int idx); int evlist__open(struct evlist *evlist); void evlist__close(struct evlist *evlist); @@ -170,14 +184,14 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, unsigned long perf_event_mlock_kb_in_pages(void); -int perf_evlist__mmap_ex(struct evlist *evlist, unsigned int pages, +int evlist__mmap_ex(struct evlist *evlist, unsigned int pages, unsigned int auxtrace_pages, bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush, int comp_level); -int perf_evlist__mmap(struct evlist *evlist, unsigned int pages); -void perf_evlist__munmap(struct evlist *evlist); +int evlist__mmap(struct evlist *evlist, unsigned int pages); +void evlist__munmap(struct evlist *evlist); -size_t perf_evlist__mmap_size(unsigned long pages); +size_t evlist__mmap_size(unsigned long pages); void evlist__disable(struct evlist *evlist); void evlist__enable(struct evlist *evlist); @@ -195,7 +209,6 @@ int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); void __perf_evlist__set_leader(struct list_head *list); void perf_evlist__set_leader(struct evlist *evlist); -u64 perf_evlist__read_format(struct evlist *evlist); u64 __perf_evlist__combined_sample_type(struct evlist *evlist); u64 perf_evlist__combined_sample_type(struct evlist *evlist); u64 perf_evlist__combined_branch_type(struct evlist *evlist); @@ -221,17 +234,19 @@ static inline bool perf_evlist__empty(struct evlist *evlist) return list_empty(&evlist->core.entries); } -static inline struct evsel *perf_evlist__first(struct evlist *evlist) +static inline struct evsel *evlist__first(struct evlist *evlist) { - return list_entry(evlist->core.entries.next, struct evsel, core.node); + struct perf_evsel *evsel = perf_evlist__first(&evlist->core); + + return container_of(evsel, struct evsel, core); } -static inline struct evsel *perf_evlist__last(struct evlist *evlist) +static inline struct evsel *evlist__last(struct evlist *evlist) { - return list_entry(evlist->core.entries.prev, struct evsel, core.node); -} + struct perf_evsel *evsel = perf_evlist__last(&evlist->core); -size_t perf_evlist__fprintf(struct evlist *evlist, FILE *fp); + return container_of(evsel, struct evsel, core); +} int perf_evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 85825384f9e8..5591af81a070 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -30,8 +30,10 @@ #include "counts.h" #include "event.h" #include "evsel.h" +#include "util/evsel_config.h" +#include "util/evsel_fprintf.h" #include "evlist.h" -#include "cpumap.h" +#include <perf/cpumap.h> #include "thread_map.h" #include "target.h" #include "perf_regs.h" @@ -45,6 +47,7 @@ #include "../perf-sys.h" #include "util/parse-branch-options.h" #include <internal/xyarray.h> +#include <internal/lib.h> #include <linux/ctype.h> @@ -1226,36 +1229,6 @@ int evsel__disable(struct evsel *evsel) return err; } -int perf_evsel__alloc_id(struct evsel *evsel, int ncpus, int nthreads) -{ - if (ncpus == 0 || nthreads == 0) - return 0; - - if (evsel->system_wide) - nthreads = 1; - - evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); - if (evsel->sample_id == NULL) - return -ENOMEM; - - evsel->id = zalloc(ncpus * nthreads * sizeof(u64)); - if (evsel->id == NULL) { - xyarray__delete(evsel->sample_id); - evsel->sample_id = NULL; - return -ENOMEM; - } - - return 0; -} - -static void perf_evsel__free_id(struct evsel *evsel) -{ - xyarray__delete(evsel->sample_id); - evsel->sample_id = NULL; - zfree(&evsel->id); - evsel->ids = 0; -} - static void perf_evsel__free_config_terms(struct evsel *evsel) { struct perf_evsel_config_term *term, *h; @@ -1272,7 +1245,7 @@ void perf_evsel__exit(struct evsel *evsel) assert(evsel->evlist == NULL); perf_evsel__free_counts(evsel); perf_evsel__free_fd(&evsel->core); - perf_evsel__free_id(evsel); + perf_evsel__free_id(&evsel->core); perf_evsel__free_config_terms(evsel); cgroup__put(evsel->cgrp); perf_cpu_map__put(evsel->core.cpus); @@ -1472,152 +1445,6 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread) return fd; } -struct bit_names { - int bit; - const char *name; -}; - -static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits) -{ - bool first_bit = true; - int i = 0; - - do { - if (value & bits[i].bit) { - buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name); - first_bit = false; - } - } while (bits[++i].name != NULL); -} - -static void __p_sample_type(char *buf, size_t size, u64 value) -{ -#define bit_name(n) { PERF_SAMPLE_##n, #n } - struct bit_names bits[] = { - bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), - bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), - bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), - bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), - bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), - bit_name(WEIGHT), bit_name(PHYS_ADDR), - { .name = NULL, } - }; -#undef bit_name - __p_bits(buf, size, value, bits); -} - -static void __p_branch_sample_type(char *buf, size_t size, u64 value) -{ -#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n } - struct bit_names bits[] = { - bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY), - bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL), - bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX), - bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), - bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), - { .name = NULL, } - }; -#undef bit_name - __p_bits(buf, size, value, bits); -} - -static void __p_read_format(char *buf, size_t size, u64 value) -{ -#define bit_name(n) { PERF_FORMAT_##n, #n } - struct bit_names bits[] = { - bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), - bit_name(ID), bit_name(GROUP), - { .name = NULL, } - }; -#undef bit_name - __p_bits(buf, size, value, bits); -} - -#define BUF_SIZE 1024 - -#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val)) -#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val)) -#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val)) -#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) -#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val) -#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) - -#define PRINT_ATTRn(_n, _f, _p) \ -do { \ - if (attr->_f) { \ - _p(attr->_f); \ - ret += attr__fprintf(fp, _n, buf, priv);\ - } \ -} while (0) - -#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p) - -int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, - attr__fprintf_f attr__fprintf, void *priv) -{ - char buf[BUF_SIZE]; - int ret = 0; - - PRINT_ATTRf(type, p_unsigned); - PRINT_ATTRf(size, p_unsigned); - PRINT_ATTRf(config, p_hex); - PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned); - PRINT_ATTRf(sample_type, p_sample_type); - PRINT_ATTRf(read_format, p_read_format); - - PRINT_ATTRf(disabled, p_unsigned); - PRINT_ATTRf(inherit, p_unsigned); - PRINT_ATTRf(pinned, p_unsigned); - PRINT_ATTRf(exclusive, p_unsigned); - PRINT_ATTRf(exclude_user, p_unsigned); - PRINT_ATTRf(exclude_kernel, p_unsigned); - PRINT_ATTRf(exclude_hv, p_unsigned); - PRINT_ATTRf(exclude_idle, p_unsigned); - PRINT_ATTRf(mmap, p_unsigned); - PRINT_ATTRf(comm, p_unsigned); - PRINT_ATTRf(freq, p_unsigned); - PRINT_ATTRf(inherit_stat, p_unsigned); - PRINT_ATTRf(enable_on_exec, p_unsigned); - PRINT_ATTRf(task, p_unsigned); - PRINT_ATTRf(watermark, p_unsigned); - PRINT_ATTRf(precise_ip, p_unsigned); - PRINT_ATTRf(mmap_data, p_unsigned); - PRINT_ATTRf(sample_id_all, p_unsigned); - PRINT_ATTRf(exclude_host, p_unsigned); - PRINT_ATTRf(exclude_guest, p_unsigned); - PRINT_ATTRf(exclude_callchain_kernel, p_unsigned); - PRINT_ATTRf(exclude_callchain_user, p_unsigned); - PRINT_ATTRf(mmap2, p_unsigned); - PRINT_ATTRf(comm_exec, p_unsigned); - PRINT_ATTRf(use_clockid, p_unsigned); - PRINT_ATTRf(context_switch, p_unsigned); - PRINT_ATTRf(write_backward, p_unsigned); - PRINT_ATTRf(namespaces, p_unsigned); - PRINT_ATTRf(ksymbol, p_unsigned); - PRINT_ATTRf(bpf_event, p_unsigned); - PRINT_ATTRf(aux_output, p_unsigned); - - PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); - PRINT_ATTRf(bp_type, p_unsigned); - PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex); - PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex); - PRINT_ATTRf(branch_sample_type, p_branch_sample_type); - PRINT_ATTRf(sample_regs_user, p_hex); - PRINT_ATTRf(sample_stack_user, p_unsigned); - PRINT_ATTRf(clockid, p_signed); - PRINT_ATTRf(sample_regs_intr, p_hex); - PRINT_ATTRf(aux_watermark, p_unsigned); - PRINT_ATTRf(sample_max_stack, p_unsigned); - - return ret; -} - -static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, - void *priv __maybe_unused) -{ - return fprintf(fp, " %-32s %s\n", name, val); -} - static void perf_evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) @@ -1662,7 +1489,7 @@ static bool ignore_missing_thread(struct evsel *evsel, return false; /* The system wide setup does not work with threads. */ - if (evsel->system_wide) + if (evsel->core.system_wide) return false; /* The -ESRCH is perf event syscall errno for pid's not found. */ @@ -1688,6 +1515,12 @@ static bool ignore_missing_thread(struct evsel *evsel, return true; } +static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, + void *priv __maybe_unused) +{ + return fprintf(fp, " %-32s %s\n", name, val); +} + static void display_attr(struct perf_event_attr *attr) { if (verbose >= 2) { @@ -1771,7 +1604,7 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, threads = empty_thread_map; } - if (evsel->system_wide) + if (evsel->core.system_wide) nthreads = 1; else nthreads = threads->nr; @@ -1818,7 +1651,7 @@ retry_sample_id: for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; - if (!evsel->cgrp && !evsel->system_wide) + if (!evsel->cgrp && !evsel->core.system_wide) pid = perf_thread_map__pid(threads, thread); group_fd = get_group_fd(evsel, cpu, thread); @@ -1991,7 +1824,7 @@ out_close: void evsel__close(struct evsel *evsel) { perf_evsel__close(&evsel->core); - perf_evsel__free_id(evsel); + perf_evsel__free_id(&evsel->core); } int perf_evsel__open_per_cpu(struct evsel *evsel, @@ -2419,283 +2252,6 @@ int perf_evsel__parse_sample_timestamp(struct evsel *evsel, return 0; } -size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, - u64 read_format) -{ - size_t sz, result = sizeof(struct perf_record_sample); - - if (type & PERF_SAMPLE_IDENTIFIER) - result += sizeof(u64); - - if (type & PERF_SAMPLE_IP) - result += sizeof(u64); - - if (type & PERF_SAMPLE_TID) - result += sizeof(u64); - - if (type & PERF_SAMPLE_TIME) - result += sizeof(u64); - - if (type & PERF_SAMPLE_ADDR) - result += sizeof(u64); - - if (type & PERF_SAMPLE_ID) - result += sizeof(u64); - - if (type & PERF_SAMPLE_STREAM_ID) - result += sizeof(u64); - - if (type & PERF_SAMPLE_CPU) - result += sizeof(u64); - - if (type & PERF_SAMPLE_PERIOD) - result += sizeof(u64); - - if (type & PERF_SAMPLE_READ) { - result += sizeof(u64); - if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - result += sizeof(u64); - if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - result += sizeof(u64); - /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ - if (read_format & PERF_FORMAT_GROUP) { - sz = sample->read.group.nr * - sizeof(struct sample_read_value); - result += sz; - } else { - result += sizeof(u64); - } - } - - if (type & PERF_SAMPLE_CALLCHAIN) { - sz = (sample->callchain->nr + 1) * sizeof(u64); - result += sz; - } - - if (type & PERF_SAMPLE_RAW) { - result += sizeof(u32); - result += sample->raw_size; - } - - if (type & PERF_SAMPLE_BRANCH_STACK) { - sz = sample->branch_stack->nr * sizeof(struct branch_entry); - sz += sizeof(u64); - result += sz; - } - - if (type & PERF_SAMPLE_REGS_USER) { - if (sample->user_regs.abi) { - result += sizeof(u64); - sz = hweight64(sample->user_regs.mask) * sizeof(u64); - result += sz; - } else { - result += sizeof(u64); - } - } - - if (type & PERF_SAMPLE_STACK_USER) { - sz = sample->user_stack.size; - result += sizeof(u64); - if (sz) { - result += sz; - result += sizeof(u64); - } - } - - if (type & PERF_SAMPLE_WEIGHT) - result += sizeof(u64); - - if (type & PERF_SAMPLE_DATA_SRC) - result += sizeof(u64); - - if (type & PERF_SAMPLE_TRANSACTION) - result += sizeof(u64); - - if (type & PERF_SAMPLE_REGS_INTR) { - if (sample->intr_regs.abi) { - result += sizeof(u64); - sz = hweight64(sample->intr_regs.mask) * sizeof(u64); - result += sz; - } else { - result += sizeof(u64); - } - } - - if (type & PERF_SAMPLE_PHYS_ADDR) - result += sizeof(u64); - - return result; -} - -int perf_event__synthesize_sample(union perf_event *event, u64 type, - u64 read_format, - const struct perf_sample *sample) -{ - __u64 *array; - size_t sz; - /* - * used for cross-endian analysis. See git commit 65014ab3 - * for why this goofiness is needed. - */ - union u64_swap u; - - array = event->sample.array; - - if (type & PERF_SAMPLE_IDENTIFIER) { - *array = sample->id; - array++; - } - - if (type & PERF_SAMPLE_IP) { - *array = sample->ip; - array++; - } - - if (type & PERF_SAMPLE_TID) { - u.val32[0] = sample->pid; - u.val32[1] = sample->tid; - *array = u.val64; - array++; - } - - if (type & PERF_SAMPLE_TIME) { - *array = sample->time; - array++; - } - - if (type & PERF_SAMPLE_ADDR) { - *array = sample->addr; - array++; - } - - if (type & PERF_SAMPLE_ID) { - *array = sample->id; - array++; - } - - if (type & PERF_SAMPLE_STREAM_ID) { - *array = sample->stream_id; - array++; - } - - if (type & PERF_SAMPLE_CPU) { - u.val32[0] = sample->cpu; - u.val32[1] = 0; - *array = u.val64; - array++; - } - - if (type & PERF_SAMPLE_PERIOD) { - *array = sample->period; - array++; - } - - if (type & PERF_SAMPLE_READ) { - if (read_format & PERF_FORMAT_GROUP) - *array = sample->read.group.nr; - else - *array = sample->read.one.value; - array++; - - if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { - *array = sample->read.time_enabled; - array++; - } - - if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { - *array = sample->read.time_running; - array++; - } - - /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ - if (read_format & PERF_FORMAT_GROUP) { - sz = sample->read.group.nr * - sizeof(struct sample_read_value); - memcpy(array, sample->read.group.values, sz); - array = (void *)array + sz; - } else { - *array = sample->read.one.id; - array++; - } - } - - if (type & PERF_SAMPLE_CALLCHAIN) { - sz = (sample->callchain->nr + 1) * sizeof(u64); - memcpy(array, sample->callchain, sz); - array = (void *)array + sz; - } - - if (type & PERF_SAMPLE_RAW) { - u.val32[0] = sample->raw_size; - *array = u.val64; - array = (void *)array + sizeof(u32); - - memcpy(array, sample->raw_data, sample->raw_size); - array = (void *)array + sample->raw_size; - } - - if (type & PERF_SAMPLE_BRANCH_STACK) { - sz = sample->branch_stack->nr * sizeof(struct branch_entry); - sz += sizeof(u64); - memcpy(array, sample->branch_stack, sz); - array = (void *)array + sz; - } - - if (type & PERF_SAMPLE_REGS_USER) { - if (sample->user_regs.abi) { - *array++ = sample->user_regs.abi; - sz = hweight64(sample->user_regs.mask) * sizeof(u64); - memcpy(array, sample->user_regs.regs, sz); - array = (void *)array + sz; - } else { - *array++ = 0; - } - } - - if (type & PERF_SAMPLE_STACK_USER) { - sz = sample->user_stack.size; - *array++ = sz; - if (sz) { - memcpy(array, sample->user_stack.data, sz); - array = (void *)array + sz; - *array++ = sz; - } - } - - if (type & PERF_SAMPLE_WEIGHT) { - *array = sample->weight; - array++; - } - - if (type & PERF_SAMPLE_DATA_SRC) { - *array = sample->data_src; - array++; - } - - if (type & PERF_SAMPLE_TRANSACTION) { - *array = sample->transaction; - array++; - } - - if (type & PERF_SAMPLE_REGS_INTR) { - if (sample->intr_regs.abi) { - *array++ = sample->intr_regs.abi; - sz = hweight64(sample->intr_regs.mask) * sizeof(u64); - memcpy(array, sample->intr_regs.regs, sz); - array = (void *)array + sz; - } else { - *array++ = 0; - } - } - - if (type & PERF_SAMPLE_PHYS_ADDR) { - *array = sample->phys_addr; - array++; - } - - return 0; -} - struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name) { return tep_find_field(evsel->tp_format, name); @@ -2811,9 +2367,11 @@ bool perf_evsel__fallback(struct evsel *evsel, int err, if (evsel->name) free(evsel->name); evsel->name = new_name; - scnprintf(msg, msgsize, -"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid); + scnprintf(msg, msgsize, "kernel.perf_event_paranoid=%d, trying " + "to fall back to excluding kernel and hypervisor " + " samples", paranoid); evsel->core.attr.exclude_kernel = 1; + evsel->core.attr.exclude_hv = 1; return true; } @@ -2966,7 +2524,7 @@ static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) thread++) { int fd = FD(evsel, cpu, thread); - if (perf_evlist__id_add_fd(evlist, evsel, + if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, cpu, thread, fd) < 0) return -1; } @@ -2980,7 +2538,7 @@ int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist) struct perf_cpu_map *cpus = evsel->core.cpus; struct perf_thread_map *threads = evsel->core.threads; - if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr)) + if (perf_evsel__alloc_id(&evsel->core, cpus->nr, threads->nr)) return -ENOMEM; return store_evsel_ids(evsel, evlist); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 68321d10eb2d..ddc5ee6f6592 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -4,7 +4,6 @@ #include <linux/list.h> #include <stdbool.h> -#include <stdio.h> #include <sys/types.h> #include <linux/perf_event.h> #include <linux/types.h> @@ -13,79 +12,11 @@ #include "symbol_conf.h" #include <internal/cpumap.h> -struct addr_location; -struct evsel; -union perf_event; - -/* - * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are - * more than one entry in the evlist. - */ -struct perf_sample_id { - struct hlist_node node; - u64 id; - struct evsel *evsel; - /* - * 'idx' will be used for AUX area sampling. A sample will have AUX area - * data that will be queued for decoding, where there are separate - * queues for each CPU (per-cpu tracing) or task (per-thread tracing). - * The sample ID can be used to lookup 'idx' which is effectively the - * queue number. - */ - int idx; - int cpu; - pid_t tid; - - /* Holds total ID period value for PERF_SAMPLE_READ processing. */ - u64 period; -}; - +struct bpf_object; struct cgroup; - -/* - * The 'struct perf_evsel_config_term' is used to pass event - * specific configuration data to perf_evsel__config routine. - * It is allocated within event parsing and attached to - * perf_evsel::config_terms list head. -*/ -enum term_type { - PERF_EVSEL__CONFIG_TERM_PERIOD, - PERF_EVSEL__CONFIG_TERM_FREQ, - PERF_EVSEL__CONFIG_TERM_TIME, - PERF_EVSEL__CONFIG_TERM_CALLGRAPH, - PERF_EVSEL__CONFIG_TERM_STACK_USER, - PERF_EVSEL__CONFIG_TERM_INHERIT, - PERF_EVSEL__CONFIG_TERM_MAX_STACK, - PERF_EVSEL__CONFIG_TERM_MAX_EVENTS, - PERF_EVSEL__CONFIG_TERM_OVERWRITE, - PERF_EVSEL__CONFIG_TERM_DRV_CFG, - PERF_EVSEL__CONFIG_TERM_BRANCH, - PERF_EVSEL__CONFIG_TERM_PERCORE, - PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT, -}; - -struct perf_evsel_config_term { - struct list_head list; - enum term_type type; - union { - u64 period; - u64 freq; - bool time; - char *callgraph; - char *drv_cfg; - u64 stack_user; - int max_stack; - bool inherit; - bool overwrite; - char *branch; - unsigned long max_events; - bool percore; - bool aux_output; - } val; - bool weak; -}; - +struct perf_counts; struct perf_stat_evsel; +union perf_event; typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data); @@ -94,10 +25,6 @@ enum perf_tool_event { PERF_TOOL_DURATION_TIME = 1, }; -struct bpf_object; -struct perf_counts; -struct xyarray; - /** struct evsel - event selector * * @evlist - evlist this evsel is in, if it is in one. @@ -117,12 +44,9 @@ struct evsel { struct perf_evsel core; struct evlist *evlist; char *filter; - struct xyarray *sample_id; - u64 *id; struct perf_counts *counts; struct perf_counts *prev_raw_counts; int idx; - u32 ids; unsigned long max_events; unsigned long nr_events_printed; char *name; @@ -146,7 +70,6 @@ struct evsel { bool disabled; bool no_aux_samples; bool immediate; - bool system_wide; bool tracking; bool per_pkg; bool precise_max; @@ -179,11 +102,6 @@ struct evsel { } side_band; }; -union u64_swap { - u64 val64; - u32 val32[2]; -}; - struct perf_missing_features { bool sample_id_all; bool exclude_guest; @@ -282,8 +200,6 @@ const char *perf_evsel__name(struct evsel *evsel); const char *perf_evsel__group_name(struct evsel *evsel); int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size); -int perf_evsel__alloc_id(struct evsel *evsel, int ncpus, int nthreads); - void __perf_evsel__set_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit); void __perf_evsel__reset_sample_bit(struct evsel *evsel, @@ -439,37 +355,6 @@ static inline bool perf_evsel__is_clock(struct evsel *evsel) perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); } -struct perf_attr_details { - bool freq; - bool verbose; - bool event_group; - bool force; - bool trace_fields; -}; - -int perf_evsel__fprintf(struct evsel *evsel, - struct perf_attr_details *details, FILE *fp); - -#define EVSEL__PRINT_IP (1<<0) -#define EVSEL__PRINT_SYM (1<<1) -#define EVSEL__PRINT_DSO (1<<2) -#define EVSEL__PRINT_SYMOFFSET (1<<3) -#define EVSEL__PRINT_ONELINE (1<<4) -#define EVSEL__PRINT_SRCLINE (1<<5) -#define EVSEL__PRINT_UNKNOWN_AS_ADDR (1<<6) -#define EVSEL__PRINT_CALLCHAIN_ARROW (1<<7) -#define EVSEL__PRINT_SKIP_IGNORED (1<<8) - -struct callchain_cursor; - -int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, - unsigned int print_opts, - struct callchain_cursor *cursor, FILE *fp); - -int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, - int left_alignment, unsigned int print_opts, - struct callchain_cursor *cursor, FILE *fp); - bool perf_evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize); int perf_evsel__open_strerror(struct evsel *evsel, struct target *target, @@ -502,11 +387,6 @@ static inline bool evsel__has_callchain(const struct evsel *evsel) return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; } -typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); - -int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, - attr__fprintf_f attr__fprintf, void *priv); - struct perf_env *perf_evsel__env(struct evsel *evsel); int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist); diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h new file mode 100644 index 000000000000..8a7648037c18 --- /dev/null +++ b/tools/perf/util/evsel_config.h @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __PERF_EVSEL_CONFIG_H +#define __PERF_EVSEL_CONFIG_H 1 + +#include <linux/types.h> +#include <stdbool.h> + +/* + * The 'struct perf_evsel_config_term' is used to pass event + * specific configuration data to perf_evsel__config routine. + * It is allocated within event parsing and attached to + * perf_evsel::config_terms list head. +*/ +enum evsel_term_type { + PERF_EVSEL__CONFIG_TERM_PERIOD, + PERF_EVSEL__CONFIG_TERM_FREQ, + PERF_EVSEL__CONFIG_TERM_TIME, + PERF_EVSEL__CONFIG_TERM_CALLGRAPH, + PERF_EVSEL__CONFIG_TERM_STACK_USER, + PERF_EVSEL__CONFIG_TERM_INHERIT, + PERF_EVSEL__CONFIG_TERM_MAX_STACK, + PERF_EVSEL__CONFIG_TERM_MAX_EVENTS, + PERF_EVSEL__CONFIG_TERM_OVERWRITE, + PERF_EVSEL__CONFIG_TERM_DRV_CFG, + PERF_EVSEL__CONFIG_TERM_BRANCH, + PERF_EVSEL__CONFIG_TERM_PERCORE, + PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT, +}; + +struct perf_evsel_config_term { + struct list_head list; + enum evsel_term_type type; + union { + u64 period; + u64 freq; + bool time; + char *callgraph; + char *drv_cfg; + u64 stack_user; + int max_stack; + bool inherit; + bool overwrite; + char *branch; + unsigned long max_events; + bool percore; + bool aux_output; + } val; + bool weak; +}; +#endif // __PERF_EVSEL_CONFIG_H diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 496fec01f5d1..028df7afb0dc 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -4,6 +4,8 @@ #include <stdbool.h> #include <traceevent/event-parse.h> #include "evsel.h" +#include "util/evsel_fprintf.h" +#include "util/event.h" #include "callchain.h" #include "map.h" #include "strlist.h" @@ -101,7 +103,7 @@ out: int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, unsigned int print_opts, struct callchain_cursor *cursor, - FILE *fp) + struct strlist *bt_stop_list, FILE *fp) { int printed = 0; struct callchain_cursor_node *node; @@ -174,10 +176,8 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, printed += fprintf(fp, "\n"); /* Add srccode here too? */ - if (symbol_conf.bt_stop_list && - node->sym && - strlist__has_entry(symbol_conf.bt_stop_list, - node->sym->name)) { + if (bt_stop_list && node->sym && + strlist__has_entry(bt_stop_list, node->sym->name)) { break; } @@ -192,7 +192,7 @@ next: int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, int left_alignment, unsigned int print_opts, - struct callchain_cursor *cursor, FILE *fp) + struct callchain_cursor *cursor, struct strlist *bt_stop_list, FILE *fp) { int printed = 0; int print_ip = print_opts & EVSEL__PRINT_IP; @@ -203,8 +203,8 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR; if (cursor != NULL) { - printed += sample__fprintf_callchain(sample, left_alignment, - print_opts, cursor, fp); + printed += sample__fprintf_callchain(sample, left_alignment, print_opts, + cursor, bt_stop_list, fp); } else { printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); diff --git a/tools/perf/util/evsel_fprintf.h b/tools/perf/util/evsel_fprintf.h new file mode 100644 index 000000000000..47e6c8456bb1 --- /dev/null +++ b/tools/perf/util/evsel_fprintf.h @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __PERF_EVSEL_FPRINTF_H +#define __PERF_EVSEL_FPRINTF_H 1 + +#include <stdio.h> +#include <stdbool.h> + +struct evsel; + +struct perf_attr_details { + bool freq; + bool verbose; + bool event_group; + bool force; + bool trace_fields; +}; + +int perf_evsel__fprintf(struct evsel *evsel, + struct perf_attr_details *details, FILE *fp); + +#define EVSEL__PRINT_IP (1<<0) +#define EVSEL__PRINT_SYM (1<<1) +#define EVSEL__PRINT_DSO (1<<2) +#define EVSEL__PRINT_SYMOFFSET (1<<3) +#define EVSEL__PRINT_ONELINE (1<<4) +#define EVSEL__PRINT_SRCLINE (1<<5) +#define EVSEL__PRINT_UNKNOWN_AS_ADDR (1<<6) +#define EVSEL__PRINT_CALLCHAIN_ARROW (1<<7) +#define EVSEL__PRINT_SKIP_IGNORED (1<<8) + +struct addr_location; +struct perf_event_attr; +struct perf_sample; +struct callchain_cursor; +struct strlist; + +int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, + unsigned int print_opts, struct callchain_cursor *cursor, + struct strlist *bt_stop_list, FILE *fp); + +int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, + int left_alignment, unsigned int print_opts, + struct callchain_cursor *cursor, + struct strlist *bt_stop_list, FILE *fp); + +typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); + +int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, + attr__fprintf_f attr__fprintf, void *priv); +#endif // __PERF_EVSEL_H diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index b72440bf9a79..d4137559be05 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -35,6 +35,9 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #elif defined(__sparc__) #define GEN_ELF_ARCH EM_SPARC #define GEN_ELF_CLASS ELFCLASS32 +#elif defined(__s390x__) +#define GEN_ELF_ARCH EM_S390 +#define GEN_ELF_CLASS ELFCLASS64 #else #error "unsupported architecture" #endif diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b0c34dda30a0..86d9396cb131 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -25,6 +25,7 @@ #include "dso.h" #include "evlist.h" #include "evsel.h" +#include "util/evsel_fprintf.h" #include "header.h" #include "memswap.h" #include "trace-event.h" @@ -42,11 +43,12 @@ #include "tool.h" #include "time-utils.h" #include "units.h" -#include "util.h" +#include "util/util.h" // perf_exe() #include "cputopo.h" #include "bpf-event.h" #include <linux/ctype.h> +#include <internal/lib.h> /* * magic2 = "PERFILE2" @@ -70,15 +72,6 @@ struct perf_file_attr { struct perf_file_section ids; }; -struct feat_fd { - struct perf_header *ph; - int fd; - void *buf; /* Either buf != NULL or fd >= 0 */ - ssize_t offset; - size_t size; - struct evsel *events; -}; - void perf_header__set_feat(struct perf_header *header, int feat) { set_bit(feat, header->adds_features); @@ -524,7 +517,7 @@ static int write_event_desc(struct feat_fd *ff, * copy into an nri to be independent of the * type of ids, */ - nri = evsel->ids; + nri = evsel->core.ids; ret = do_write(ff, &nri, sizeof(nri)); if (ret < 0) return ret; @@ -538,7 +531,7 @@ static int write_event_desc(struct feat_fd *ff, /* * write unique ids for this event */ - ret = do_write(ff, evsel->id, evsel->ids * sizeof(u64)); + ret = do_write(ff, evsel->core.id, evsel->core.ids * sizeof(u64)); if (ret < 0) return ret; } @@ -1081,7 +1074,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path); if (sysfs__read_str(file, &cache->map, &len)) { - zfree(&cache->map); + zfree(&cache->size); zfree(&cache->type); return -1; } @@ -1598,7 +1591,7 @@ static void free_event_desc(struct evsel *events) for (evsel = events; evsel->core.attr.size; evsel++) { zfree(&evsel->name); - zfree(&evsel->id); + zfree(&evsel->core.id); } free(events); @@ -1664,8 +1657,8 @@ static struct evsel *read_event_desc(struct feat_fd *ff) id = calloc(nr, sizeof(*id)); if (!id) goto error; - evsel->ids = nr; - evsel->id = id; + evsel->core.ids = nr; + evsel->core.id = id; for (j = 0 ; j < nr; j++) { if (do_read_u64(ff, id)) @@ -1707,9 +1700,9 @@ static void print_event_desc(struct feat_fd *ff, FILE *fp) for (evsel = events; evsel->core.attr.size; evsel++) { fprintf(fp, "# event : name = %s, ", evsel->name); - if (evsel->ids) { + if (evsel->core.ids) { fprintf(fp, ", id = {"); - for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) { + for (j = 0, id = evsel->core.id; j < evsel->core.ids; j++, id++) { if (j) fputc(',', fp); fprintf(fp, " %"PRIu64, *id); @@ -2823,15 +2816,6 @@ static int process_compressed(struct feat_fd *ff, return 0; } -struct feature_ops { - int (*write)(struct feat_fd *ff, struct evlist *evlist); - void (*print)(struct feat_fd *ff, FILE *fp); - int (*process)(struct feat_fd *ff, void *data); - const char *name; - bool full_only; - bool synthesize; -}; - #define FEAT_OPR(n, func, __full_only) \ [HEADER_##n] = { \ .name = __stringify(n), \ @@ -2858,8 +2842,10 @@ struct feature_ops { #define process_branch_stack NULL #define process_stat NULL +// Only used in util/synthetic-events.c +const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE]; -static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { +const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPN(TRACING_DATA, tracing_data, false), FEAT_OPN(BUILD_ID, build_id, false), FEAT_OPR(HOSTNAME, hostname, false), @@ -3083,7 +3069,7 @@ int perf_session__write_header(struct perf_session *session, evlist__for_each_entry(session->evlist, evsel) { evsel->id_offset = lseek(fd, 0, SEEK_CUR); - err = do_write(&ff, evsel->id, evsel->ids * sizeof(u64)); + err = do_write(&ff, evsel->core.id, evsel->core.ids * sizeof(u64)); if (err < 0) { pr_debug("failed to write perf header\n"); return err; @@ -3097,7 +3083,7 @@ int perf_session__write_header(struct perf_session *session, .attr = evsel->core.attr, .ids = { .offset = evsel->id_offset, - .size = evsel->ids * sizeof(u64), + .size = evsel->core.ids * sizeof(u64), } }; err = do_write(&ff, &f_attr, sizeof(f_attr)); @@ -3624,7 +3610,7 @@ int perf_session__read_header(struct perf_session *session) * for allocating the perf_sample_id table we fake 1 cpu and * hattr->ids threads. */ - if (perf_evsel__alloc_id(evsel, 1, nr_ids)) + if (perf_evsel__alloc_id(&evsel->core, 1, nr_ids)) goto out_delete_evlist; lseek(fd, f_attr.ids.offset, SEEK_SET); @@ -3633,7 +3619,7 @@ int perf_session__read_header(struct perf_session *session) if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id))) goto out_errno; - perf_evlist__id_add(session->evlist, evsel, 0, j, f_id); + perf_evlist__id_add(&session->evlist->core, &evsel->core, 0, j, f_id); } lseek(fd, tmp, SEEK_SET); @@ -3656,105 +3642,6 @@ out_delete_evlist: return -ENOMEM; } -int perf_event__synthesize_attr(struct perf_tool *tool, - struct perf_event_attr *attr, u32 ids, u64 *id, - perf_event__handler_t process) -{ - union perf_event *ev; - size_t size; - int err; - - size = sizeof(struct perf_event_attr); - size = PERF_ALIGN(size, sizeof(u64)); - size += sizeof(struct perf_event_header); - size += ids * sizeof(u64); - - ev = zalloc(size); - - if (ev == NULL) - return -ENOMEM; - - ev->attr.attr = *attr; - memcpy(ev->attr.id, id, ids * sizeof(u64)); - - ev->attr.header.type = PERF_RECORD_HEADER_ATTR; - ev->attr.header.size = (u16)size; - - if (ev->attr.header.size == size) - err = process(tool, ev, NULL, NULL); - else - err = -E2BIG; - - free(ev); - - return err; -} - -int perf_event__synthesize_features(struct perf_tool *tool, - struct perf_session *session, - struct evlist *evlist, - perf_event__handler_t process) -{ - struct perf_header *header = &session->header; - struct feat_fd ff; - struct perf_record_header_feature *fe; - size_t sz, sz_hdr; - int feat, ret; - - sz_hdr = sizeof(fe->header); - sz = sizeof(union perf_event); - /* get a nice alignment */ - sz = PERF_ALIGN(sz, page_size); - - memset(&ff, 0, sizeof(ff)); - - ff.buf = malloc(sz); - if (!ff.buf) - return -ENOMEM; - - ff.size = sz - sz_hdr; - ff.ph = &session->header; - - for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { - if (!feat_ops[feat].synthesize) { - pr_debug("No record header feature for header :%d\n", feat); - continue; - } - - ff.offset = sizeof(*fe); - - ret = feat_ops[feat].write(&ff, evlist); - if (ret || ff.offset <= (ssize_t)sizeof(*fe)) { - pr_debug("Error writing feature\n"); - continue; - } - /* ff.buf may have changed due to realloc in do_write() */ - fe = ff.buf; - memset(fe, 0, sizeof(*fe)); - - fe->feat_id = feat; - fe->header.type = PERF_RECORD_HEADER_FEATURE; - fe->header.size = ff.offset; - - ret = process(tool, ff.buf, NULL, NULL); - if (ret) { - free(ff.buf); - return ret; - } - } - - /* Send HEADER_LAST_FEATURE mark. */ - fe = ff.buf; - fe->feat_id = HEADER_LAST_FEATURE; - fe->header.type = PERF_RECORD_HEADER_FEATURE; - fe->header.size = sizeof(*fe); - - ret = process(tool, ff.buf, NULL, NULL); - - free(ff.buf); - return ret; -} - int perf_event__process_feature(struct perf_session *session, union perf_event *event) { @@ -3797,113 +3684,6 @@ int perf_event__process_feature(struct perf_session *session, return 0; } -static struct perf_record_event_update * -event_update_event__new(size_t size, u64 type, u64 id) -{ - struct perf_record_event_update *ev; - - size += sizeof(*ev); - size = PERF_ALIGN(size, sizeof(u64)); - - ev = zalloc(size); - if (ev) { - ev->header.type = PERF_RECORD_EVENT_UPDATE; - ev->header.size = (u16)size; - ev->type = type; - ev->id = id; - } - return ev; -} - -int -perf_event__synthesize_event_update_unit(struct perf_tool *tool, - struct evsel *evsel, - perf_event__handler_t process) -{ - struct perf_record_event_update *ev; - size_t size = strlen(evsel->unit); - int err; - - ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]); - if (ev == NULL) - return -ENOMEM; - - strlcpy(ev->data, evsel->unit, size + 1); - err = process(tool, (union perf_event *)ev, NULL, NULL); - free(ev); - return err; -} - -int -perf_event__synthesize_event_update_scale(struct perf_tool *tool, - struct evsel *evsel, - perf_event__handler_t process) -{ - struct perf_record_event_update *ev; - struct perf_record_event_update_scale *ev_data; - int err; - - ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]); - if (ev == NULL) - return -ENOMEM; - - ev_data = (struct perf_record_event_update_scale *)ev->data; - ev_data->scale = evsel->scale; - err = process(tool, (union perf_event*) ev, NULL, NULL); - free(ev); - return err; -} - -int -perf_event__synthesize_event_update_name(struct perf_tool *tool, - struct evsel *evsel, - perf_event__handler_t process) -{ - struct perf_record_event_update *ev; - size_t len = strlen(evsel->name); - int err; - - ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]); - if (ev == NULL) - return -ENOMEM; - - strlcpy(ev->data, evsel->name, len + 1); - err = process(tool, (union perf_event*) ev, NULL, NULL); - free(ev); - return err; -} - -int -perf_event__synthesize_event_update_cpus(struct perf_tool *tool, - struct evsel *evsel, - perf_event__handler_t process) -{ - size_t size = sizeof(struct perf_record_event_update); - struct perf_record_event_update *ev; - int max, err; - u16 type; - - if (!evsel->core.own_cpus) - return 0; - - ev = cpu_map_data__alloc(evsel->core.own_cpus, &size, &type, &max); - if (!ev) - return -ENOMEM; - - ev->header.type = PERF_RECORD_EVENT_UPDATE; - ev->header.size = (u16)size; - ev->type = PERF_EVENT_UPDATE__CPUS; - ev->id = evsel->id[0]; - - cpu_map_data__synthesize((struct perf_record_cpu_map_data *)ev->data, - evsel->core.own_cpus, - type, max); - - err = process(tool, (union perf_event*) ev, NULL, NULL); - free(ev); - return err; -} - size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) { struct perf_record_event_update *ev = &event->event_update; @@ -3943,93 +3723,6 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) return ret; } -int perf_event__synthesize_attrs(struct perf_tool *tool, - struct evlist *evlist, - perf_event__handler_t process) -{ - struct evsel *evsel; - int err = 0; - - evlist__for_each_entry(evlist, evsel) { - err = perf_event__synthesize_attr(tool, &evsel->core.attr, evsel->ids, - evsel->id, process); - if (err) { - pr_debug("failed to create perf header attribute\n"); - return err; - } - } - - return err; -} - -static bool has_unit(struct evsel *counter) -{ - return counter->unit && *counter->unit; -} - -static bool has_scale(struct evsel *counter) -{ - return counter->scale != 1; -} - -int perf_event__synthesize_extra_attr(struct perf_tool *tool, - struct evlist *evsel_list, - perf_event__handler_t process, - bool is_pipe) -{ - struct evsel *counter; - int err; - - /* - * Synthesize other events stuff not carried within - * attr event - unit, scale, name - */ - evlist__for_each_entry(evsel_list, counter) { - if (!counter->supported) - continue; - - /* - * Synthesize unit and scale only if it's defined. - */ - if (has_unit(counter)) { - err = perf_event__synthesize_event_update_unit(tool, counter, process); - if (err < 0) { - pr_err("Couldn't synthesize evsel unit.\n"); - return err; - } - } - - if (has_scale(counter)) { - err = perf_event__synthesize_event_update_scale(tool, counter, process); - if (err < 0) { - pr_err("Couldn't synthesize evsel counter.\n"); - return err; - } - } - - if (counter->core.own_cpus) { - err = perf_event__synthesize_event_update_cpus(tool, counter, process); - if (err < 0) { - pr_err("Couldn't synthesize evsel cpus.\n"); - return err; - } - } - - /* - * Name is needed only for pipe output, - * perf.data carries event names. - */ - if (is_pipe) { - err = perf_event__synthesize_event_update_name(tool, counter, process); - if (err < 0) { - pr_err("Couldn't synthesize evsel name.\n"); - return err; - } - } - } - return 0; -} - int perf_event__process_attr(struct perf_tool *tool __maybe_unused, union perf_event *event, struct evlist **pevlist) @@ -4058,11 +3751,11 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, * for allocating the perf_sample_id table we fake 1 cpu and * hattr->ids threads. */ - if (perf_evsel__alloc_id(evsel, 1, n_ids)) + if (perf_evsel__alloc_id(&evsel->core, 1, n_ids)) return -ENOMEM; for (i = 0; i < n_ids; i++) { - perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]); + perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]); } return 0; @@ -4114,55 +3807,6 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, return 0; } -int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, - struct evlist *evlist, - perf_event__handler_t process) -{ - union perf_event ev; - struct tracing_data *tdata; - ssize_t size = 0, aligned_size = 0, padding; - struct feat_fd ff; - int err __maybe_unused = 0; - - /* - * We are going to store the size of the data followed - * by the data contents. Since the fd descriptor is a pipe, - * we cannot seek back to store the size of the data once - * we know it. Instead we: - * - * - write the tracing data to the temp file - * - get/write the data size to pipe - * - write the tracing data from the temp file - * to the pipe - */ - tdata = tracing_data_get(&evlist->core.entries, fd, true); - if (!tdata) - return -1; - - memset(&ev, 0, sizeof(ev)); - - ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; - size = tdata->size; - aligned_size = PERF_ALIGN(size, sizeof(u64)); - padding = aligned_size - size; - ev.tracing_data.header.size = sizeof(ev.tracing_data); - ev.tracing_data.size = aligned_size; - - process(tool, &ev, NULL, NULL); - - /* - * The put function will copy all the tracing data - * stored in temp file to the pipe. - */ - tracing_data_put(tdata); - - ff = (struct feat_fd){ .fd = fd }; - if (write_padded(&ff, NULL, 0, padding)) - return -1; - - return aligned_size; -} - int perf_event__process_tracing_data(struct perf_session *session, union perf_event *event) { @@ -4202,34 +3846,6 @@ int perf_event__process_tracing_data(struct perf_session *session, return size_read + padding; } -int perf_event__synthesize_build_id(struct perf_tool *tool, - struct dso *pos, u16 misc, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event ev; - size_t len; - int err = 0; - - if (!pos->hit) - return err; - - memset(&ev, 0, sizeof(ev)); - - len = pos->long_name_len + 1; - len = PERF_ALIGN(len, NAME_ALIGN); - memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); - ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; - ev.build_id.header.misc = misc; - ev.build_id.pid = machine->pid; - ev.build_id.header.size = sizeof(ev.build_id) + len; - memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); - - err = process(tool, &ev, NULL, machine); - - return err; -} - int perf_event__process_build_id(struct perf_session *session, union perf_event *event) { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 3e48ae3c49b1..ca53a929e9fd 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -5,10 +5,10 @@ #include <linux/stddef.h> #include <linux/perf_event.h> #include <sys/types.h> +#include <stdio.h> // FILE #include <stdbool.h> #include <linux/bitmap.h> #include <linux/types.h> -#include "event.h" #include "env.h" #include "pmu.h" @@ -92,8 +92,28 @@ struct perf_header { struct perf_env env; }; +struct feat_fd { + struct perf_header *ph; + int fd; + void *buf; /* Either buf != NULL or fd >= 0 */ + ssize_t offset; + size_t size; + struct evsel *events; +}; + +struct perf_header_feature_ops { + int (*write)(struct feat_fd *ff, struct evlist *evlist); + void (*print)(struct feat_fd *ff, FILE *fp); + int (*process)(struct feat_fd *ff, void *data); + const char *name; + bool full_only; + bool synthesize; +}; + struct evlist; struct perf_session; +struct perf_tool; +union perf_event; int perf_session__read_header(struct perf_session *session); int perf_session__write_header(struct perf_session *session, @@ -115,54 +135,16 @@ int perf_header__process_sections(struct perf_header *header, int fd, int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); -int perf_event__synthesize_features(struct perf_tool *tool, - struct perf_session *session, - struct evlist *evlist, - perf_event__handler_t process); - -int perf_event__synthesize_extra_attr(struct perf_tool *tool, - struct evlist *evsel_list, - perf_event__handler_t process, - bool is_pipe); - int perf_event__process_feature(struct perf_session *session, union perf_event *event); - -int perf_event__synthesize_attr(struct perf_tool *tool, - struct perf_event_attr *attr, u32 ids, u64 *id, - perf_event__handler_t process); -int perf_event__synthesize_attrs(struct perf_tool *tool, - struct evlist *evlist, - perf_event__handler_t process); -int perf_event__synthesize_event_update_unit(struct perf_tool *tool, - struct evsel *evsel, - perf_event__handler_t process); -int perf_event__synthesize_event_update_scale(struct perf_tool *tool, - struct evsel *evsel, - perf_event__handler_t process); -int perf_event__synthesize_event_update_name(struct perf_tool *tool, - struct evsel *evsel, - perf_event__handler_t process); -int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, - struct evsel *evsel, - perf_event__handler_t process); int perf_event__process_attr(struct perf_tool *tool, union perf_event *event, struct evlist **pevlist); int perf_event__process_event_update(struct perf_tool *tool, union perf_event *event, struct evlist **pevlist); size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp); - -int perf_event__synthesize_tracing_data(struct perf_tool *tool, - int fd, struct evlist *evlist, - perf_event__handler_t process); int perf_event__process_tracing_data(struct perf_session *session, union perf_event *event); - -int perf_event__synthesize_build_id(struct perf_tool *tool, - struct dso *pos, u16 misc, - perf_event__handler_t process, - struct machine *machine); int perf_event__process_build_id(struct perf_session *session, union perf_event *event); bool is_perf_magic(u64 magic); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 34803e33dc80..6a186b668303 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -15,6 +15,7 @@ struct addr_location; struct map_symbol; struct mem_info; struct branch_info; +struct branch_stack; struct block_info; struct symbol; struct ui_progress; diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index aacffa2b0362..34cb380d19a3 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -14,7 +14,6 @@ #include <linux/log2.h> #include <linux/zalloc.h> -#include "cpumap.h" #include "color.h" #include "evsel.h" #include "evlist.h" @@ -29,6 +28,7 @@ #include "auxtrace.h" #include "intel-pt-decoder/intel-pt-insn-decoder.h" #include "intel-bts.h" +#include "util/synthetic-events.h" #define MAX_TIMESTAMP (~0ULL) @@ -768,7 +768,7 @@ static int intel_bts_synth_events(struct intel_bts *bts, int err; evlist__for_each_entry(evlist, evsel) { - if (evsel->core.attr.type == bts->pmu_type && evsel->ids) { + if (evsel->core.attr.type == bts->pmu_type && evsel->core.ids) { found = true; break; } @@ -795,7 +795,7 @@ static int intel_bts_synth_events(struct intel_bts *bts, attr.sample_id_all = evsel->core.attr.sample_id_all; attr.read_format = evsel->core.attr.read_format; - id = evsel->id[0] + 1000000000; + id = evsel->core.id[0] + 1000000000; if (!id) id = 1; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 9b56fb74bedf..a1c9eb6d4f40 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -33,6 +33,7 @@ #include "tsc.h" #include "intel-pt.h" #include "config.h" +#include "util/synthetic-events.h" #include "time-utils.h" #include "../arch/x86/include/uapi/asm/perf_regs.h" @@ -1704,7 +1705,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) struct intel_pt *pt = ptq->pt; struct evsel *evsel = pt->pebs_evsel; u64 sample_type = evsel->core.attr.sample_type; - u64 id = evsel->id[0]; + u64 id = evsel->core.id[0]; u8 cpumode; if (intel_pt_skip_event(pt)) @@ -2719,7 +2720,7 @@ static void intel_pt_set_event_name(struct evlist *evlist, u64 id, struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->id && evsel->id[0] == id) { + if (evsel->core.id && evsel->core.id[0] == id) { if (evsel->name) zfree(&evsel->name); evsel->name = strdup(name); @@ -2734,7 +2735,7 @@ static struct evsel *intel_pt_evsel(struct intel_pt *pt, struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->core.attr.type == pt->pmu_type && evsel->ids) + if (evsel->core.attr.type == pt->pmu_type && evsel->core.ids) return evsel; } @@ -2775,7 +2776,7 @@ static int intel_pt_synth_events(struct intel_pt *pt, attr.sample_id_all = evsel->core.attr.sample_id_all; attr.read_format = evsel->core.attr.read_format; - id = evsel->id[0] + 1000000000; + id = evsel->core.id[0] + 1000000000; if (!id) id = 1; @@ -2902,7 +2903,7 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt) return; evlist__for_each_entry(pt->session->evlist, evsel) { - if (evsel->core.attr.aux_output && evsel->id) { + if (evsel->core.attr.aux_output && evsel->core.id) { pt->sample_pebs = true; pt->pebs_evsel = evsel; return; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index b80f29bfc7bb..1bdf4c6ea3e5 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -15,7 +15,6 @@ #include <linux/stringify.h> #include "build-id.h" -#include "util.h" #include "event.h" #include "debug.h" #include "evlist.h" @@ -27,7 +26,6 @@ #include "jit.h" #include "jitdump.h" #include "genelf.h" -#include "../builtin.h" #include <linux/ctype.h> #include <linux/zalloc.h> @@ -779,7 +777,7 @@ jit_process(struct perf_session *session, * track sample_type to compute id_all layout * perf sets the same sample type to all events as of now */ - first = perf_evlist__first(session->evlist); + first = evlist__first(session->evlist); jd.sample_type = first->core.attr.sample_type; *nbytes = 0; diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 46913637085b..6f0fa05b62b6 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -2,6 +2,8 @@ #ifndef __PERF_KVM_STAT_H #define __PERF_KVM_STAT_H +#ifdef HAVE_KVM_STAT_SUPPORT + #include "tool.h" #include "stat.h" #include "record.h" @@ -144,5 +146,7 @@ extern const int decode_str_len; extern const char *kvm_exit_reason; extern const char *kvm_entry_trace; extern const char *kvm_exit_trace; +#endif /* HAVE_KVM_STAT_SUPPORT */ +extern int kvm_add_default_arch_event(int *argc, const char **argv); #endif /* __PERF_KVM_STAT_H */ diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c index 66756e6be111..6b4e5a0892f8 100644 --- a/tools/perf/util/libunwind/arm64.c +++ b/tools/perf/util/libunwind/arm64.c @@ -22,7 +22,6 @@ #define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP #include "unwind.h" -#include "debug.h" #include "libunwind-aarch64.h" #include <../../../../arch/arm64/include/uapi/asm/perf_regs.h> #include "../../arch/arm64/util/unwind-libunwind.c" diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c index c5e568188e19..21c216c40a3b 100644 --- a/tools/perf/util/libunwind/x86_32.c +++ b/tools/perf/util/libunwind/x86_32.c @@ -22,7 +22,6 @@ #define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP #include "unwind.h" -#include "debug.h" #include "libunwind-x86.h" #include <../../../../arch/x86/include/uapi/asm/perf_regs.h> diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 55fb4b3b1157..8d04e3d070b1 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -8,6 +8,7 @@ #include <limits.h> #include <stdio.h> #include <stdlib.h> +#include <unistd.h> #include <linux/err.h> #include <linux/string.h> #include <linux/zalloc.h> diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 397447066033..39062df02629 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -7,10 +7,10 @@ #include <sys/stat.h> #include <fcntl.h> #include "compress.h" -#include "util.h" #include "debug.h" #include <string.h> #include <unistd.h> +#include <internal/lib.h> #define BUFSIZE 8192 diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b4749d3eed08..70a9f8716a4b 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -32,6 +32,7 @@ #include "linux/hash.h" #include "asm/bug.h" #include "bpf-event.h" +#include <internal/lib.h> // page_size #include <linux/ctype.h> #include <symbol/kallsyms.h> @@ -2609,21 +2610,6 @@ int machines__for_each_thread(struct machines *machines, return rc; } -int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, - struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, - unsigned int nr_threads_synthesize) -{ - if (target__has_task(target)) - return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap); - else if (target__has_cpu(target)) - return perf_event__synthesize_threads(tool, process, - machine, data_mmap, - nr_threads_synthesize); - /* command specified */ - return 0; -} - pid_t machine__get_current_tid(struct machine *machine, int cpu) { int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index ffd391a925a6..18e13c0ccd6a 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -6,7 +6,6 @@ #include <linux/rbtree.h> #include "map_groups.h" #include "dsos.h" -#include "event.h" #include "rwsem.h" struct addr_location; @@ -252,20 +251,6 @@ int machines__for_each_thread(struct machines *machines, int (*fn)(struct thread *thread, void *p), void *priv); -int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, - struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, - unsigned int nr_threads_synthesize); -static inline -int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, - unsigned int nr_threads_synthesize) -{ - return __machine__synthesize_threads(machine, NULL, target, threads, - perf_event__process, data_mmap, - nr_threads_synthesize); -} - pid_t machine__get_current_tid(struct machine *machine, int cpu); int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, pid_t tid); diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h index 1e29ff903ca9..2c38e8c2d548 100644 --- a/tools/perf/util/memswap.h +++ b/tools/perf/util/memswap.h @@ -2,6 +2,13 @@ #ifndef PERF_MEMSWAP_H_ #define PERF_MEMSWAP_H_ +#include <linux/types.h> + +union u64_swap { + u64 val64; + u32 val32[2]; +}; + void mem_bswap_64(void *src, int byte_size); void mem_bswap_32(void *src, int byte_size); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 33c5b5495482..a35dc57d5995 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -12,6 +12,7 @@ #include <linux/zalloc.h> #include <stdlib.h> #include <string.h> +#include <unistd.h> // sysconf() #ifdef HAVE_LIBNUMA_SUPPORT #include <numaif.h> #endif @@ -20,25 +21,25 @@ #include "event.h" #include "mmap.h" #include "../perf.h" -#include "util.h" /* page_size */ +#include <internal/lib.h> /* page_size */ -size_t perf_mmap__mmap_len(struct perf_mmap *map) +size_t perf_mmap__mmap_len(struct mmap *map) { - return map->mask + 1 + page_size; + return map->core.mask + 1 + page_size; } /* When check_messup is true, 'end' must points to a good entry */ -static union perf_event *perf_mmap__read(struct perf_mmap *map, +static union perf_event *perf_mmap__read(struct mmap *map, u64 *startp, u64 end) { - unsigned char *data = map->base + page_size; + unsigned char *data = map->core.base + page_size; union perf_event *event = NULL; int diff = end - *startp; if (diff >= (int)sizeof(event->header)) { size_t size; - event = (union perf_event *)&data[*startp & map->mask]; + event = (union perf_event *)&data[*startp & map->core.mask]; size = event->header.size; if (size < sizeof(event->header) || diff < (int)size) @@ -48,20 +49,20 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, * Event straddles the mmap boundary -- header should always * be inside due to u64 alignment of output. */ - if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) { + if ((*startp & map->core.mask) + size != ((*startp + size) & map->core.mask)) { unsigned int offset = *startp; unsigned int len = min(sizeof(*event), size), cpy; - void *dst = map->event_copy; + void *dst = map->core.event_copy; do { - cpy = min(map->mask + 1 - (offset & map->mask), len); - memcpy(dst, &data[offset & map->mask], cpy); + cpy = min(map->core.mask + 1 - (offset & map->core.mask), len); + memcpy(dst, &data[offset & map->core.mask], cpy); offset += cpy; dst += cpy; len -= cpy; } while (len); - event = (union perf_event *)map->event_copy; + event = (union perf_event *)map->core.event_copy; } *startp += size; @@ -82,55 +83,55 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, * } * perf_mmap__read_done() */ -union perf_event *perf_mmap__read_event(struct perf_mmap *map) +union perf_event *perf_mmap__read_event(struct mmap *map) { union perf_event *event; /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!refcount_read(&map->refcnt)) + if (!refcount_read(&map->core.refcnt)) return NULL; /* non-overwirte doesn't pause the ringbuffer */ - if (!map->overwrite) - map->end = perf_mmap__read_head(map); + if (!map->core.overwrite) + map->core.end = perf_mmap__read_head(map); - event = perf_mmap__read(map, &map->start, map->end); + event = perf_mmap__read(map, &map->core.start, map->core.end); - if (!map->overwrite) - map->prev = map->start; + if (!map->core.overwrite) + map->core.prev = map->core.start; return event; } -static bool perf_mmap__empty(struct perf_mmap *map) +static bool perf_mmap__empty(struct mmap *map) { - return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base; + return perf_mmap__read_head(map) == map->core.prev && !map->auxtrace_mmap.base; } -void perf_mmap__get(struct perf_mmap *map) +void perf_mmap__get(struct mmap *map) { - refcount_inc(&map->refcnt); + refcount_inc(&map->core.refcnt); } -void perf_mmap__put(struct perf_mmap *map) +void perf_mmap__put(struct mmap *map) { - BUG_ON(map->base && refcount_read(&map->refcnt) == 0); + BUG_ON(map->core.base && refcount_read(&map->core.refcnt) == 0); - if (refcount_dec_and_test(&map->refcnt)) + if (refcount_dec_and_test(&map->core.refcnt)) perf_mmap__munmap(map); } -void perf_mmap__consume(struct perf_mmap *map) +void perf_mmap__consume(struct mmap *map) { - if (!map->overwrite) { - u64 old = map->prev; + if (!map->core.overwrite) { + u64 old = map->core.prev; perf_mmap__write_tail(map, old); } - if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map)) + if (refcount_read(&map->core.refcnt) == 1 && perf_mmap__empty(map)) perf_mmap__put(map); } @@ -161,13 +162,13 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb } #ifdef HAVE_AIO_SUPPORT -static int perf_mmap__aio_enabled(struct perf_mmap *map) +static int perf_mmap__aio_enabled(struct mmap *map) { return map->aio.nr_cblocks > 0; } #ifdef HAVE_LIBNUMA_SUPPORT -static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) +static int perf_mmap__aio_alloc(struct mmap *map, int idx) { map->aio.data[idx] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, 0, 0); @@ -179,7 +180,7 @@ static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) return 0; } -static void perf_mmap__aio_free(struct perf_mmap *map, int idx) +static void perf_mmap__aio_free(struct mmap *map, int idx) { if (map->aio.data[idx]) { munmap(map->aio.data[idx], perf_mmap__mmap_len(map)); @@ -187,7 +188,7 @@ static void perf_mmap__aio_free(struct perf_mmap *map, int idx) } } -static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affinity) +static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity) { void *data; size_t mmap_len; @@ -207,7 +208,7 @@ static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affi return 0; } #else /* !HAVE_LIBNUMA_SUPPORT */ -static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) +static int perf_mmap__aio_alloc(struct mmap *map, int idx) { map->aio.data[idx] = malloc(perf_mmap__mmap_len(map)); if (map->aio.data[idx] == NULL) @@ -216,19 +217,19 @@ static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx) return 0; } -static void perf_mmap__aio_free(struct perf_mmap *map, int idx) +static void perf_mmap__aio_free(struct mmap *map, int idx) { zfree(&(map->aio.data[idx])); } -static int perf_mmap__aio_bind(struct perf_mmap *map __maybe_unused, int idx __maybe_unused, +static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused, int cpu __maybe_unused, int affinity __maybe_unused) { return 0; } #endif -static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp) +static int perf_mmap__aio_mmap(struct mmap *map, struct mmap_params *mp) { int delta_max, i, prio, ret; @@ -256,7 +257,7 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp) pr_debug2("failed to allocate data buffer area, error %m"); return -1; } - ret = perf_mmap__aio_bind(map, i, map->cpu, mp->affinity); + ret = perf_mmap__aio_bind(map, i, map->core.cpu, mp->affinity); if (ret == -1) return -1; /* @@ -282,7 +283,7 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp) return 0; } -static void perf_mmap__aio_munmap(struct perf_mmap *map) +static void perf_mmap__aio_munmap(struct mmap *map) { int i; @@ -294,34 +295,34 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map) zfree(&map->aio.aiocb); } #else /* !HAVE_AIO_SUPPORT */ -static int perf_mmap__aio_enabled(struct perf_mmap *map __maybe_unused) +static int perf_mmap__aio_enabled(struct mmap *map __maybe_unused) { return 0; } -static int perf_mmap__aio_mmap(struct perf_mmap *map __maybe_unused, +static int perf_mmap__aio_mmap(struct mmap *map __maybe_unused, struct mmap_params *mp __maybe_unused) { return 0; } -static void perf_mmap__aio_munmap(struct perf_mmap *map __maybe_unused) +static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused) { } #endif -void perf_mmap__munmap(struct perf_mmap *map) +void perf_mmap__munmap(struct mmap *map) { perf_mmap__aio_munmap(map); if (map->data != NULL) { munmap(map->data, perf_mmap__mmap_len(map)); map->data = NULL; } - if (map->base != NULL) { - munmap(map->base, perf_mmap__mmap_len(map)); - map->base = NULL; - map->fd = -1; - refcount_set(&map->refcnt, 0); + if (map->core.base != NULL) { + munmap(map->core.base, perf_mmap__mmap_len(map)); + map->core.base = NULL; + map->core.fd = -1; + refcount_set(&map->core.refcnt, 0); } auxtrace_mmap__munmap(&map->auxtrace_mmap); } @@ -343,16 +344,16 @@ static void build_node_mask(int node, cpu_set_t *mask) } } -static void perf_mmap__setup_affinity_mask(struct perf_mmap *map, struct mmap_params *mp) +static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) { CPU_ZERO(&map->affinity_mask); if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) - build_node_mask(cpu__get_node(map->cpu), &map->affinity_mask); + build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask); else if (mp->affinity == PERF_AFFINITY_CPU) - CPU_SET(map->cpu, &map->affinity_mask); + CPU_SET(map->core.cpu, &map->affinity_mask); } -int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu) +int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) { /* * The last one will be done at perf_mmap__consume(), so that we @@ -367,23 +368,23 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c * evlist layer can't just drop it when filtering events in * perf_evlist__filter_pollfd(). */ - refcount_set(&map->refcnt, 2); - map->prev = 0; - map->mask = mp->mask; - map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, + refcount_set(&map->core.refcnt, 2); + map->core.prev = 0; + map->core.mask = mp->mask; + map->core.base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, MAP_SHARED, fd, 0); - if (map->base == MAP_FAILED) { + if (map->core.base == MAP_FAILED) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", errno); - map->base = NULL; + map->core.base = NULL; return -1; } - map->fd = fd; - map->cpu = cpu; + map->core.fd = fd; + map->core.cpu = cpu; perf_mmap__setup_affinity_mask(map, mp); - map->flush = mp->flush; + map->core.flush = mp->flush; map->comp_level = mp->comp_level; @@ -399,7 +400,7 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c } if (auxtrace_mmap__mmap(&map->auxtrace_mmap, - &mp->auxtrace_mp, map->base, fd)) + &mp->auxtrace_mp, map->core.base, fd)) return -1; return perf_mmap__aio_mmap(map, mp); @@ -440,25 +441,25 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end) /* * Report the start and end of the available data in ringbuffer */ -static int __perf_mmap__read_init(struct perf_mmap *md) +static int __perf_mmap__read_init(struct mmap *md) { u64 head = perf_mmap__read_head(md); - u64 old = md->prev; - unsigned char *data = md->base + page_size; + u64 old = md->core.prev; + unsigned char *data = md->core.base + page_size; unsigned long size; - md->start = md->overwrite ? head : old; - md->end = md->overwrite ? old : head; + md->core.start = md->core.overwrite ? head : old; + md->core.end = md->core.overwrite ? old : head; - if ((md->end - md->start) < md->flush) + if ((md->core.end - md->core.start) < md->core.flush) return -EAGAIN; - size = md->end - md->start; - if (size > (unsigned long)(md->mask) + 1) { - if (!md->overwrite) { + size = md->core.end - md->core.start; + if (size > (unsigned long)(md->core.mask) + 1) { + if (!md->core.overwrite) { WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); - md->prev = head; + md->core.prev = head; perf_mmap__consume(md); return -EAGAIN; } @@ -467,29 +468,29 @@ static int __perf_mmap__read_init(struct perf_mmap *md) * Backward ring buffer is full. We still have a chance to read * most of data from it. */ - if (overwrite_rb_find_range(data, md->mask, &md->start, &md->end)) + if (overwrite_rb_find_range(data, md->core.mask, &md->core.start, &md->core.end)) return -EINVAL; } return 0; } -int perf_mmap__read_init(struct perf_mmap *map) +int perf_mmap__read_init(struct mmap *map) { /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!refcount_read(&map->refcnt)) + if (!refcount_read(&map->core.refcnt)) return -ENOENT; return __perf_mmap__read_init(map); } -int perf_mmap__push(struct perf_mmap *md, void *to, - int push(struct perf_mmap *map, void *to, void *buf, size_t size)) +int perf_mmap__push(struct mmap *md, void *to, + int push(struct mmap *map, void *to, void *buf, size_t size)) { u64 head = perf_mmap__read_head(md); - unsigned char *data = md->base + page_size; + unsigned char *data = md->core.base + page_size; unsigned long size; void *buf; int rc = 0; @@ -498,12 +499,12 @@ int perf_mmap__push(struct perf_mmap *md, void *to, if (rc < 0) return (rc == -EAGAIN) ? 1 : -1; - size = md->end - md->start; + size = md->core.end - md->core.start; - if ((md->start & md->mask) + size != (md->end & md->mask)) { - buf = &data[md->start & md->mask]; - size = md->mask + 1 - (md->start & md->mask); - md->start += size; + if ((md->core.start & md->core.mask) + size != (md->core.end & md->core.mask)) { + buf = &data[md->core.start & md->core.mask]; + size = md->core.mask + 1 - (md->core.start & md->core.mask); + md->core.start += size; if (push(md, to, buf, size) < 0) { rc = -1; @@ -511,16 +512,16 @@ int perf_mmap__push(struct perf_mmap *md, void *to, } } - buf = &data[md->start & md->mask]; - size = md->end - md->start; - md->start += size; + buf = &data[md->core.start & md->core.mask]; + size = md->core.end - md->core.start; + md->core.start += size; if (push(md, to, buf, size) < 0) { rc = -1; goto out; } - md->prev = head; + md->core.prev = head; perf_mmap__consume(md); out: return rc; @@ -529,16 +530,16 @@ out: /* * Mandatory for overwrite mode * The direction of overwrite mode is backward. - * The last perf_mmap__read() will set tail to map->prev. - * Need to correct the map->prev to head which is the end of next read. + * The last perf_mmap__read() will set tail to map->core.prev. + * Need to correct the map->core.prev to head which is the end of next read. */ -void perf_mmap__read_done(struct perf_mmap *map) +void perf_mmap__read_done(struct mmap *map) { /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!refcount_read(&map->refcnt)) + if (!refcount_read(&map->core.refcnt)) return; - map->prev = perf_mmap__read_head(map); + map->core.prev = perf_mmap__read_head(map); } diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index 3857a49e8f96..e567c1c875bd 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -1,6 +1,7 @@ #ifndef __PERF_MMAP_H #define __PERF_MMAP_H 1 +#include <internal/mmap.h> #include <linux/compiler.h> #include <linux/refcount.h> #include <linux/types.h> @@ -15,22 +16,13 @@ struct aiocb; /** - * struct perf_mmap - perf's ring buffer mmap details + * struct mmap - perf's ring buffer mmap details * * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this */ -struct perf_mmap { - void *base; - int mask; - int fd; - int cpu; - refcount_t refcnt; - u64 prev; - u64 start; - u64 end; - bool overwrite; +struct mmap { + struct perf_mmap core; struct auxtrace_mmap auxtrace_mmap; - char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); #ifdef HAVE_AIO_SUPPORT struct { void **data; @@ -40,71 +32,42 @@ struct perf_mmap { } aio; #endif cpu_set_t affinity_mask; - u64 flush; void *data; int comp_level; }; -/* - * State machine of bkw_mmap_state: - * - * .________________(forbid)_____________. - * | V - * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY - * ^ ^ | ^ | - * | |__(forbid)____/ |___(forbid)___/| - * | | - * \_________________(3)_______________/ - * - * NOTREADY : Backward ring buffers are not ready - * RUNNING : Backward ring buffers are recording - * DATA_PENDING : We are required to collect data from backward ring buffers - * EMPTY : We have collected data from backward ring buffers. - * - * (0): Setup backward ring buffer - * (1): Pause ring buffers for reading - * (2): Read from ring buffers - * (3): Resume ring buffers for recording - */ -enum bkw_mmap_state { - BKW_MMAP_NOTREADY, - BKW_MMAP_RUNNING, - BKW_MMAP_DATA_PENDING, - BKW_MMAP_EMPTY, -}; - struct mmap_params { int prot, mask, nr_cblocks, affinity, flush, comp_level; struct auxtrace_mmap_params auxtrace_mp; }; -int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu); -void perf_mmap__munmap(struct perf_mmap *map); +int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu); +void perf_mmap__munmap(struct mmap *map); -void perf_mmap__get(struct perf_mmap *map); -void perf_mmap__put(struct perf_mmap *map); +void perf_mmap__get(struct mmap *map); +void perf_mmap__put(struct mmap *map); -void perf_mmap__consume(struct perf_mmap *map); +void perf_mmap__consume(struct mmap *map); -static inline u64 perf_mmap__read_head(struct perf_mmap *mm) +static inline u64 perf_mmap__read_head(struct mmap *mm) { - return ring_buffer_read_head(mm->base); + return ring_buffer_read_head(mm->core.base); } -static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) +static inline void perf_mmap__write_tail(struct mmap *md, u64 tail) { - ring_buffer_write_tail(md->base, tail); + ring_buffer_write_tail(md->core.base, tail); } -union perf_event *perf_mmap__read_forward(struct perf_mmap *map); +union perf_event *perf_mmap__read_forward(struct mmap *map); -union perf_event *perf_mmap__read_event(struct perf_mmap *map); +union perf_event *perf_mmap__read_event(struct mmap *map); -int perf_mmap__push(struct perf_mmap *md, void *to, - int push(struct perf_mmap *map, void *to, void *buf, size_t size)); +int perf_mmap__push(struct mmap *md, void *to, + int push(struct mmap *map, void *to, void *buf, size_t size)); -size_t perf_mmap__mmap_len(struct perf_mmap *map); +size_t perf_mmap__mmap_len(struct mmap *map); -int perf_mmap__read_init(struct perf_mmap *md); -void perf_mmap__read_done(struct perf_mmap *map); +int perf_mmap__read_init(struct mmap *md); +void perf_mmap__read_done(struct mmap *map); #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 99be15dd2b6b..285d6f30d912 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -17,8 +17,26 @@ #include <string.h> #include <unistd.h> #include <asm/bug.h> +#include <linux/kernel.h> #include <linux/zalloc.h> +static const char *perf_ns__names[] = { + [NET_NS_INDEX] = "net", + [UTS_NS_INDEX] = "uts", + [IPC_NS_INDEX] = "ipc", + [PID_NS_INDEX] = "pid", + [USER_NS_INDEX] = "user", + [MNT_NS_INDEX] = "mnt", + [CGROUP_NS_INDEX] = "cgroup", +}; + +const char *perf_ns__name(unsigned int id) +{ + if (id >= ARRAY_SIZE(perf_ns__names)) + return "UNKNOWN"; + return perf_ns__names[id]; +} + struct namespaces *namespaces__new(struct perf_record_namespaces *event) { struct namespaces *namespaces; diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 40edef56cb52..4b33f684eddd 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -66,4 +66,6 @@ static inline void __nsinfo__zput(struct nsinfo **nsip) #define nsinfo__zput(nsi) __nsinfo__zput(&nsi) +const char *perf_ns__name(unsigned int id); + #endif /* __PERF_NAMESPACES_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5ec21d21113c..b5e2adef49de 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -30,11 +30,12 @@ #include "parse-events-flex.h" #include "pmu.h" #include "thread_map.h" -#include "cpumap.h" #include "probe-file.h" #include "asm/bug.h" #include "util/parse-branch-options.h" #include "metricgroup.h" +#include "util/evsel_config.h" +#include "util/event.h" #define MAX_NAME_LEN 100 @@ -335,7 +336,7 @@ __add_event(struct list_head *list, int *idx, (*idx)++; evsel->core.cpus = perf_cpu_map__get(cpus); evsel->core.own_cpus = perf_cpu_map__get(cpus); - evsel->system_wide = pmu ? pmu->is_uncore : false; + evsel->core.system_wide = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats; if (name) @@ -1936,7 +1937,7 @@ int parse_events(struct evlist *evlist, const char *str, perf_evlist__splice_list_tail(evlist, &parse_state.list); evlist->nr_groups += parse_state.nr_groups; - last = perf_evlist__last(evlist); + last = evlist__last(evlist); last->cmdline_group_boundary = true; return 0; @@ -2050,7 +2051,7 @@ foreach_evsel_in_last_glob(struct evlist *evlist, * So no need to WARN here, let *func do this. */ if (evlist->core.nr_entries > 0) - last = perf_evlist__last(evlist); + last = evlist__last(evlist); do { err = (*func)(last, arg); diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index f1c36ed1cf36..48126ae4cd13 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -9,13 +9,11 @@ #define YYDEBUG 1 #include <fnmatch.h> +#include <stdio.h> #include <linux/compiler.h> -#include <linux/list.h> #include <linux/types.h> -#include "util.h" #include "pmu.h" #include "evsel.h" -#include "debug.h" #include "parse-events.h" #include "parse-events-bison.h" diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c index e635c594f773..7a0ab3507bd5 100644 --- a/tools/perf/util/perf-hooks.c +++ b/tools/perf/util/perf-hooks.c @@ -12,7 +12,6 @@ #include <setjmp.h> #include <linux/err.h> #include <linux/kernel.h> -#include "util/util.h" #include "util/debug.h" #include "util/perf-hooks.h" diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c new file mode 100644 index 000000000000..d4ad3f04923a --- /dev/null +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <inttypes.h> +#include <stdio.h> +#include <stdbool.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/perf_event.h> +#include "util/evsel_fprintf.h" + +struct bit_names { + int bit; + const char *name; +}; + +static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits) +{ + bool first_bit = true; + int i = 0; + + do { + if (value & bits[i].bit) { + buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name); + first_bit = false; + } + } while (bits[++i].name != NULL); +} + +static void __p_sample_type(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_##n, #n } + struct bit_names bits[] = { + bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), + bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), + bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), + bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), + bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), + bit_name(WEIGHT), bit_name(PHYS_ADDR), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +static void __p_branch_sample_type(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n } + struct bit_names bits[] = { + bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY), + bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL), + bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX), + bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), + bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +static void __p_read_format(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_FORMAT_##n, #n } + struct bit_names bits[] = { + bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), + bit_name(ID), bit_name(GROUP), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +#define BUF_SIZE 1024 + +#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val)) +#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val)) +#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val)) +#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) +#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val) +#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) + +#define PRINT_ATTRn(_n, _f, _p) \ +do { \ + if (attr->_f) { \ + _p(attr->_f); \ + ret += attr__fprintf(fp, _n, buf, priv);\ + } \ +} while (0) + +#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p) + +int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, + attr__fprintf_f attr__fprintf, void *priv) +{ + char buf[BUF_SIZE]; + int ret = 0; + + PRINT_ATTRf(type, p_unsigned); + PRINT_ATTRf(size, p_unsigned); + PRINT_ATTRf(config, p_hex); + PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned); + PRINT_ATTRf(sample_type, p_sample_type); + PRINT_ATTRf(read_format, p_read_format); + + PRINT_ATTRf(disabled, p_unsigned); + PRINT_ATTRf(inherit, p_unsigned); + PRINT_ATTRf(pinned, p_unsigned); + PRINT_ATTRf(exclusive, p_unsigned); + PRINT_ATTRf(exclude_user, p_unsigned); + PRINT_ATTRf(exclude_kernel, p_unsigned); + PRINT_ATTRf(exclude_hv, p_unsigned); + PRINT_ATTRf(exclude_idle, p_unsigned); + PRINT_ATTRf(mmap, p_unsigned); + PRINT_ATTRf(comm, p_unsigned); + PRINT_ATTRf(freq, p_unsigned); + PRINT_ATTRf(inherit_stat, p_unsigned); + PRINT_ATTRf(enable_on_exec, p_unsigned); + PRINT_ATTRf(task, p_unsigned); + PRINT_ATTRf(watermark, p_unsigned); + PRINT_ATTRf(precise_ip, p_unsigned); + PRINT_ATTRf(mmap_data, p_unsigned); + PRINT_ATTRf(sample_id_all, p_unsigned); + PRINT_ATTRf(exclude_host, p_unsigned); + PRINT_ATTRf(exclude_guest, p_unsigned); + PRINT_ATTRf(exclude_callchain_kernel, p_unsigned); + PRINT_ATTRf(exclude_callchain_user, p_unsigned); + PRINT_ATTRf(mmap2, p_unsigned); + PRINT_ATTRf(comm_exec, p_unsigned); + PRINT_ATTRf(use_clockid, p_unsigned); + PRINT_ATTRf(context_switch, p_unsigned); + PRINT_ATTRf(write_backward, p_unsigned); + PRINT_ATTRf(namespaces, p_unsigned); + PRINT_ATTRf(ksymbol, p_unsigned); + PRINT_ATTRf(bpf_event, p_unsigned); + PRINT_ATTRf(aux_output, p_unsigned); + + PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); + PRINT_ATTRf(bp_type, p_unsigned); + PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex); + PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex); + PRINT_ATTRf(branch_sample_type, p_branch_sample_type); + PRINT_ATTRf(sample_regs_user, p_hex); + PRINT_ATTRf(sample_stack_user, p_unsigned); + PRINT_ATTRf(clockid, p_signed); + PRINT_ATTRf(sample_regs_intr, p_hex); + PRINT_ATTRf(aux_watermark, p_unsigned); + PRINT_ATTRf(sample_max_stack, p_unsigned); + + return ret; +} diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index fb597fa94234..5608da82ad23 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -20,7 +20,6 @@ #include "debug.h" #include "pmu.h" #include "parse-events.h" -#include "cpumap.h" #include "header.h" #include "pmu-events/pmu-events.h" #include "string2.h" diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index b8e0967c5c21..91cab5f669d2 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2331,6 +2331,7 @@ void clear_probe_trace_event(struct probe_trace_event *tev) } } zfree(&tev->args); + tev->nargs = 0; } struct kprobe_blacklist_node { diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index d13db55a2feb..b659466ea498 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -16,6 +16,7 @@ #include "strlist.h" #include "strfilter.h" #include "debug.h" +#include "build-id.h" #include "dso.h" #include "color.h" #include "symbol.h" diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 505905fc21c5..cd9f95e5044e 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1245,6 +1245,17 @@ static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf, return n; } +static bool trace_event_finder_overlap(struct trace_event_finder *tf) +{ + int i; + + for (i = 0; i < tf->ntevs; i++) { + if (tf->pf.addr == tf->tevs[i].point.address) + return true; + } + return false; +} + /* Add a found probe point into trace event list */ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) { @@ -1255,6 +1266,14 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) struct perf_probe_arg *args = NULL; int ret, i; + /* + * For some reason (e.g. different column assigned to same address) + * This callback can be called with the address which already passed. + * Ignore it first. + */ + if (trace_event_finder_overlap(tf)) + return 0; + /* Check number of tevs */ if (tf->ntevs == tf->max_tevs) { pr_warning("Too many( > %d) probe point found.\n", diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index c6dd478956f1..9af183860fbd 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,6 +10,7 @@ util/python.c util/cap.c util/evlist.c util/evsel.c +util/perf_event_attr_fprintf.c util/cpumap.c util/memswap.c util/mmap.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 07ca4535e6f7..53f31053a27a 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -6,17 +6,15 @@ #include <linux/err.h> #include <perf/cpumap.h> #include <traceevent/event-parse.h> -#include "debug.h" #include "evlist.h" #include "callchain.h" #include "evsel.h" #include "event.h" -#include "cpumap.h" #include "print_binary.h" #include "thread_map.h" #include "trace-event.h" #include "mmap.h" -#include "util.h" +#include <internal/lib.h> #include "../perf-sys.h" #if PY_MAJOR_VERSION < 3 @@ -61,6 +59,8 @@ int parse_callchain_record(const char *arg __maybe_unused, */ int verbose; +int eprintf(int level, int var, const char *fmt, ...); + int eprintf(int level, int var, const char *fmt, ...) { va_list args; @@ -884,7 +884,7 @@ static int pyrf_evlist__init(struct pyrf_evlist *pevlist, static void pyrf_evlist__delete(struct pyrf_evlist *pevlist) { - perf_evlist__exit(&pevlist->evlist); + evlist__exit(&pevlist->evlist); Py_TYPE(pevlist)->tp_free((PyObject*)pevlist); } @@ -899,7 +899,7 @@ static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, &pages, &overwrite)) return NULL; - if (perf_evlist__mmap(evlist, pages) < 0) { + if (evlist__mmap(evlist, pages) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -918,7 +918,7 @@ static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist, if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout)) return NULL; - n = perf_evlist__poll(evlist, timeout); + n = evlist__poll(evlist, timeout); if (n < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; @@ -935,17 +935,17 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, PyObject *list = PyList_New(0); int i; - for (i = 0; i < evlist->pollfd.nr; ++i) { + for (i = 0; i < evlist->core.pollfd.nr; ++i) { PyObject *file; #if PY_MAJOR_VERSION < 3 - FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r"); + FILE *fp = fdopen(evlist->core.pollfd.entries[i].fd, "r"); if (fp == NULL) goto free_list; file = PyFile_FromFile(fp, "perf", "r", NULL); #else - file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, + file = PyFile_FromFd(evlist->core.pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 0); #endif if (file == NULL) @@ -984,14 +984,14 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, return Py_BuildValue("i", evlist->core.nr_entries); } -static struct perf_mmap *get_md(struct evlist *evlist, int cpu) +static struct mmap *get_md(struct evlist *evlist, int cpu) { int i; - for (i = 0; i < evlist->nr_mmaps; i++) { - struct perf_mmap *md = &evlist->mmap[i]; + for (i = 0; i < evlist->core.nr_mmaps; i++) { + struct mmap *md = &evlist->mmap[i]; - if (md->cpu == cpu) + if (md->core.cpu == cpu) return md; } @@ -1005,7 +1005,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, union perf_event *event; int sample_id_all = 1, cpu; static char *kwlist[] = { "cpu", "sample_id_all", NULL }; - struct perf_mmap *md; + struct mmap *md; int err; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist, diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 286fe816c0f3..8579505c29a4 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -2,7 +2,6 @@ #include "debug.h" #include "evlist.h" #include "evsel.h" -#include "cpumap.h" #include "parse-events.h" #include <errno.h> #include <limits.h> @@ -10,7 +9,6 @@ #include <api/fs/fs.h> #include <subcmd/parse-options.h> #include <perf/cpumap.h> -#include "util.h" #include "cloexec.h" #include "record.h" #include "../perf-sys.h" @@ -32,7 +30,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) if (parse_events(evlist, str, NULL)) goto out_delete; - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); while (1) { fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); @@ -173,7 +171,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, use_sample_identifier = perf_can_sample_identifier(); sample_id = true; } else if (evlist->core.nr_entries > 1) { - struct evsel *first = perf_evlist__first(evlist); + struct evsel *first = evlist__first(evlist); evlist__for_each_entry(evlist, evsel) { if (evsel->core.attr.sample_type == first->core.attr.sample_type) @@ -278,7 +276,7 @@ bool perf_evlist__can_select_event(struct evlist *evlist, const char *str) if (err) goto out_delete; - evsel = perf_evlist__last(temp_evlist); + evsel = evlist__last(temp_evlist); if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) { struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c index 5e52e7baa7b6..f3d29d8ddc99 100644 --- a/tools/perf/util/rwsem.c +++ b/tools/perf/util/rwsem.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "util.h" #include "rwsem.h" diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index 24a99909d8b3..6785cd87aa4d 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -151,7 +151,6 @@ #include <sys/stat.h> #include <sys/types.h> -#include "cpumap.h" #include "color.h" #include "evsel.h" #include "evlist.h" diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index 4d9593e331ea..05b43ab4eeef 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -22,7 +22,6 @@ #include <asm/byteorder.h> #include "debug.h" -#include "util.h" #include "session.h" #include "evlist.h" #include "color.h" diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 666a56e88d8e..5d341efc3237 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -37,7 +37,6 @@ #include "../dso.h" #include "../callchain.h" #include "../evsel.h" -#include "../util.h" #include "../event.h" #include "../thread.h" #include "../comm.h" @@ -49,7 +48,6 @@ #include "map.h" #include "symbol.h" #include "thread_map.h" -#include "cpumap.h" #include "print_binary.h" #include "stat.h" #include "mem-events.h" diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index e9e4a04f15db..061bb4d6a3f5 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -22,7 +22,6 @@ #include "symbol.h" #include "session.h" #include "tool.h" -#include "cpumap.h" #include "perf_regs.h" #include "asm/bug.h" #include "auxtrace.h" @@ -30,10 +29,11 @@ #include "thread-stack.h" #include "sample-raw.h" #include "stat.h" -#include "util.h" #include "ui/progress.h" #include "../perf.h" #include "arch/common.h" +#include <internal/lib.h> +#include <linux/err.h> #ifdef HAVE_ZSTD_SUPPORT static int perf_session__process_compressed_event(struct perf_session *session, @@ -187,6 +187,7 @@ static int ordered_events__deliver_event(struct ordered_events *oe, struct perf_session *perf_session__new(struct perf_data *data, bool repipe, struct perf_tool *tool) { + int ret = -ENOMEM; struct perf_session *session = zalloc(sizeof(*session)); if (!session) @@ -201,13 +202,15 @@ struct perf_session *perf_session__new(struct perf_data *data, perf_env__init(&session->header.env); if (data) { - if (perf_data__open(data)) + ret = perf_data__open(data); + if (ret < 0) goto out_delete; session->data = data; if (perf_data__is_read(data)) { - if (perf_session__open(session) < 0) + ret = perf_session__open(session); + if (ret < 0) goto out_delete; /* @@ -222,8 +225,11 @@ struct perf_session *perf_session__new(struct perf_data *data, perf_evlist__init_trace_event_sample_raw(session->evlist); /* Open the directory data. */ - if (data->is_dir && perf_data__open_dir(data)) + if (data->is_dir) { + ret = perf_data__open_dir(data); + if (ret) goto out_delete; + } } } else { session->machines.host.env = &perf_env; @@ -256,7 +262,7 @@ struct perf_session *perf_session__new(struct perf_data *data, out_delete: perf_session__delete(session); out: - return NULL; + return ERR_PTR(ret); } static void perf_session__delete_threads(struct perf_session *session) @@ -1317,6 +1323,7 @@ static int deliver_sample_value(struct evlist *evlist, struct machine *machine) { struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id); + struct evsel *evsel; if (sid) { sample->id = v->id; @@ -1336,7 +1343,8 @@ static int deliver_sample_value(struct evlist *evlist, if (!sample->period) return 0; - return tool->sample(tool, event, sample, sid->evsel, machine); + evsel = container_of(sid->evsel, struct evsel, core); + return tool->sample(tool, event, sample, evsel, machine); } static int deliver_sample_group(struct evlist *evlist, @@ -2412,73 +2420,3 @@ int perf_event__process_id_index(struct perf_session *session, } return 0; } - -int perf_event__synthesize_id_index(struct perf_tool *tool, - perf_event__handler_t process, - struct evlist *evlist, - struct machine *machine) -{ - union perf_event *ev; - struct evsel *evsel; - size_t nr = 0, i = 0, sz, max_nr, n; - int err; - - pr_debug2("Synthesizing id index\n"); - - max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) / - sizeof(struct id_index_entry); - - evlist__for_each_entry(evlist, evsel) - nr += evsel->ids; - - n = nr > max_nr ? max_nr : nr; - sz = sizeof(struct perf_record_id_index) + n * sizeof(struct id_index_entry); - ev = zalloc(sz); - if (!ev) - return -ENOMEM; - - ev->id_index.header.type = PERF_RECORD_ID_INDEX; - ev->id_index.header.size = sz; - ev->id_index.nr = n; - - evlist__for_each_entry(evlist, evsel) { - u32 j; - - for (j = 0; j < evsel->ids; j++) { - struct id_index_entry *e; - struct perf_sample_id *sid; - - if (i >= n) { - err = process(tool, ev, NULL, machine); - if (err) - goto out_err; - nr -= n; - i = 0; - } - - e = &ev->id_index.entries[i++]; - - e->id = evsel->id[j]; - - sid = perf_evlist__id2sid(evlist, e->id); - if (!sid) { - free(ev); - return -ENOENT; - } - - e->idx = sid->idx; - e->cpu = sid->cpu; - e->tid = sid->tid; - } - } - - sz = sizeof(struct perf_record_id_index) + nr * sizeof(struct id_index_entry); - ev->id_index.header.size = sz; - ev->id_index.nr = nr; - - err = process(tool, ev, NULL, machine); -out_err: - free(ev); - - return err; -} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index b7aa076ab6fd..b4c9428c18f0 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -138,9 +138,4 @@ int perf_session__deliver_synth_event(struct perf_session *session, int perf_event__process_id_index(struct perf_session *session, union perf_event *event); -int perf_event__synthesize_id_index(struct perf_tool *tool, - perf_event__handler_t process, - struct evlist *evlist, - struct machine *machine); - #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index a2308eb77681..43d1d410854a 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2329,7 +2329,7 @@ static struct evsel *find_evsel(struct evlist *evlist, char *event_name) if (nr > evlist->core.nr_entries) return NULL; - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); while (--nr > 0) evsel = perf_evsel__next(evsel); diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c index adfcf1ff464c..d84ed8b6caaa 100644 --- a/tools/perf/util/srccode.c +++ b/tools/perf/util/srccode.c @@ -15,7 +15,7 @@ #include <string.h> #include "srccode.h" #include "debug.h" -#include "util.h" +#include <internal/lib.h> // page_size #define MAXSRCCACHE (32*1024*1024) #define MAXSRCFILES 64 diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 70c87fdb2a43..2c41d47f6f83 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -738,6 +738,8 @@ static void generic_metric(struct perf_stat_config *config, char *n, *pn; expr__ctx_init(&pctx); + /* Must be first id entry */ + expr__add_id(&pctx, name, avg); for (i = 0; metric_events[i]; i++) { struct saved_value *v; struct stats *stats; @@ -776,8 +778,6 @@ static void generic_metric(struct perf_stat_config *config, expr__add_id(&pctx, n, avg_stats(stats)*scale); } - expr__add_id(&pctx, name, avg); - if (!metric_events[i]) { const char *p = metric_expr; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 8f1ea27f976f..ebdd130557fb 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -4,6 +4,7 @@ #include <math.h> #include <string.h> #include "counts.h" +#include "cpumap.h" #include "debug.h" #include "header.h" #include "stat.h" @@ -161,6 +162,15 @@ static void perf_evsel__free_prev_raw_counts(struct evsel *evsel) evsel->prev_raw_counts = NULL; } +static void perf_evsel__reset_prev_raw_counts(struct evsel *evsel) +{ + if (evsel->prev_raw_counts) { + evsel->prev_raw_counts->aggr.val = 0; + evsel->prev_raw_counts->aggr.ena = 0; + evsel->prev_raw_counts->aggr.run = 0; + } +} + static int perf_evsel__alloc_stats(struct evsel *evsel, bool alloc_raw) { int ncpus = perf_evsel__nr_cpus(evsel); @@ -211,6 +221,14 @@ void perf_evlist__reset_stats(struct evlist *evlist) } } +void perf_evlist__reset_prev_raw_counts(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) + perf_evsel__reset_prev_raw_counts(evsel); +} + static void zero_per_pkg(struct evsel *counter) { if (counter->per_pkg_mask) @@ -318,7 +336,7 @@ static int process_counter_maps(struct perf_stat_config *config, int ncpus = perf_evsel__nr_cpus(counter); int cpu, thread; - if (counter->system_wide) + if (counter->core.system_wide) nthreads = 1; for (thread = 0; thread < nthreads; thread++) { @@ -493,45 +511,3 @@ int create_perf_stat_counter(struct evsel *evsel, return perf_evsel__open_per_thread(evsel, evsel->core.threads); } - -int perf_stat_synthesize_config(struct perf_stat_config *config, - struct perf_tool *tool, - struct evlist *evlist, - perf_event__handler_t process, - bool attrs) -{ - int err; - - if (attrs) { - err = perf_event__synthesize_attrs(tool, evlist, process); - if (err < 0) { - pr_err("Couldn't synthesize attrs.\n"); - return err; - } - } - - err = perf_event__synthesize_extra_attr(tool, evlist, process, - attrs); - - err = perf_event__synthesize_thread_map2(tool, evlist->core.threads, - process, NULL); - if (err < 0) { - pr_err("Couldn't synthesize thread map.\n"); - return err; - } - - err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, - process, NULL); - if (err < 0) { - pr_err("Couldn't synthesize thread map.\n"); - return err; - } - - err = perf_event__synthesize_stat_config(tool, config, process, NULL); - if (err < 0) { - pr_err("Couldn't synthesize config.\n"); - return err; - } - - return 0; -} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 14fe3e548229..edbeb2f63e8d 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -7,8 +7,9 @@ #include <sys/types.h> #include <sys/resource.h> #include "rblist.h" -#include "event.h" +struct perf_cpu_map; +struct perf_stat_config; struct timespec; struct stats { @@ -192,6 +193,7 @@ void perf_stat__collect_metric_expr(struct evlist *); int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw); void perf_evlist__free_stats(struct evlist *evlist); void perf_evlist__reset_stats(struct evlist *evlist); +void perf_evlist__reset_prev_raw_counts(struct evlist *evlist); int perf_stat_process_counter(struct perf_stat_config *config, struct evsel *counter); @@ -210,11 +212,6 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target); -int perf_stat_synthesize_config(struct perf_stat_config *config, - struct perf_tool *tool, - struct evlist *evlist, - perf_event__handler_t process, - bool attrs); void perf_evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 582f4a69cd48..96f941e01681 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -17,11 +17,11 @@ #include <linux/string.h> #include <linux/time64.h> #include <linux/zalloc.h> +#include <internal/cpumap.h> #include <perf/cpumap.h> #include "env.h" #include "svghelper.h" -#include "cpumap.h" static u64 first_time, last_time; static u64 turbo_frequency, max_freq; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 9428639872a6..66f4be1df573 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -7,6 +7,7 @@ #include <unistd.h> #include <inttypes.h> +#include "dso.h" #include "map.h" #include "map_groups.h" #include "symbol.h" @@ -16,10 +17,12 @@ #include "machine.h" #include "vdso.h" #include "debug.h" -#include "util.h" +#include "util/copyfile.h" #include <linux/ctype.h> +#include <linux/kernel.h> #include <linux/zalloc.h> #include <symbol/kallsyms.h> +#include <internal/lib.h> #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 7e2813ec9498..d6e99af263ec 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -1,8 +1,6 @@ -// SPDX-License-Identifier: GPL-2.0 #include "dso.h" #include "symbol.h" #include "symsrc.h" -#include "util.h" #include <errno.h> #include <unistd.h> @@ -13,6 +11,7 @@ #include <byteswap.h> #include <sys/stat.h> #include <linux/zalloc.h> +#include <internal/lib.h> static bool check_need_swap(int file_endian) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 765c75df2904..a8f80e427674 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -19,7 +19,7 @@ #include "build-id.h" #include "cap.h" #include "dso.h" -#include "util.h" +#include "util.h" // lsdir() #include "debug.h" #include "event.h" #include "machine.h" diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c new file mode 100644 index 000000000000..807cbca403a7 --- /dev/null +++ b/tools/perf/util/synthetic-events.c @@ -0,0 +1,1884 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "util/debug.h" +#include "util/dso.h" +#include "util/event.h" +#include "util/evlist.h" +#include "util/machine.h" +#include "util/map.h" +#include "util/map_symbol.h" +#include "util/branch.h" +#include "util/memswap.h" +#include "util/namespaces.h" +#include "util/session.h" +#include "util/stat.h" +#include "util/symbol.h" +#include "util/synthetic-events.h" +#include "util/target.h" +#include "util/time-utils.h" +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/zalloc.h> +#include <linux/perf_event.h> +#include <asm/bug.h> +#include <perf/evsel.h> +#include <internal/cpumap.h> +#include <perf/cpumap.h> +#include <internal/lib.h> // page_size +#include <internal/threadmap.h> +#include <perf/threadmap.h> +#include <symbol/kallsyms.h> +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <stdio.h> +#include <string.h> +#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ +#include <api/fs/fs.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> + +#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500 + +unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT; + +int perf_tool__process_synth_event(struct perf_tool *tool, + union perf_event *event, + struct machine *machine, + perf_event__handler_t process) +{ + struct perf_sample synth_sample = { + .pid = -1, + .tid = -1, + .time = -1, + .stream_id = -1, + .cpu = -1, + .period = 1, + .cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK, + }; + + return process(tool, event, &synth_sample, machine); +}; + +/* + * Assumes that the first 4095 bytes of /proc/pid/stat contains + * the comm, tgid and ppid. + */ +static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, + pid_t *tgid, pid_t *ppid) +{ + char filename[PATH_MAX]; + char bf[4096]; + int fd; + size_t size = 0; + ssize_t n; + char *name, *tgids, *ppids; + + *tgid = -1; + *ppid = -1; + + snprintf(filename, sizeof(filename), "/proc/%d/status", pid); + + fd = open(filename, O_RDONLY); + if (fd < 0) { + pr_debug("couldn't open %s\n", filename); + return -1; + } + + n = read(fd, bf, sizeof(bf) - 1); + close(fd); + if (n <= 0) { + pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n", + pid); + return -1; + } + bf[n] = '\0'; + + name = strstr(bf, "Name:"); + tgids = strstr(bf, "Tgid:"); + ppids = strstr(bf, "PPid:"); + + if (name) { + char *nl; + + name = skip_spaces(name + 5); /* strlen("Name:") */ + nl = strchr(name, '\n'); + if (nl) + *nl = '\0'; + + size = strlen(name); + if (size >= len) + size = len - 1; + memcpy(comm, name, size); + comm[size] = '\0'; + } else { + pr_debug("Name: string not found for pid %d\n", pid); + } + + if (tgids) { + tgids += 5; /* strlen("Tgid:") */ + *tgid = atoi(tgids); + } else { + pr_debug("Tgid: string not found for pid %d\n", pid); + } + + if (ppids) { + ppids += 5; /* strlen("PPid:") */ + *ppid = atoi(ppids); + } else { + pr_debug("PPid: string not found for pid %d\n", pid); + } + + return 0; +} + +static int perf_event__prepare_comm(union perf_event *event, pid_t pid, + struct machine *machine, + pid_t *tgid, pid_t *ppid) +{ + size_t size; + + *ppid = -1; + + memset(&event->comm, 0, sizeof(event->comm)); + + if (machine__is_host(machine)) { + if (perf_event__get_comm_ids(pid, event->comm.comm, + sizeof(event->comm.comm), + tgid, ppid) != 0) { + return -1; + } + } else { + *tgid = machine->pid; + } + + if (*tgid < 0) + return -1; + + event->comm.pid = *tgid; + event->comm.header.type = PERF_RECORD_COMM; + + size = strlen(event->comm.comm) + 1; + size = PERF_ALIGN(size, sizeof(u64)); + memset(event->comm.comm + size, 0, machine->id_hdr_size); + event->comm.header.size = (sizeof(event->comm) - + (sizeof(event->comm.comm) - size) + + machine->id_hdr_size); + event->comm.tid = pid; + + return 0; +} + +pid_t perf_event__synthesize_comm(struct perf_tool *tool, + union perf_event *event, pid_t pid, + perf_event__handler_t process, + struct machine *machine) +{ + pid_t tgid, ppid; + + if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0) + return -1; + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return tgid; +} + +static void perf_event__get_ns_link_info(pid_t pid, const char *ns, + struct perf_ns_link_info *ns_link_info) +{ + struct stat64 st; + char proc_ns[128]; + + sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns); + if (stat64(proc_ns, &st) == 0) { + ns_link_info->dev = st.st_dev; + ns_link_info->ino = st.st_ino; + } +} + +int perf_event__synthesize_namespaces(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine) +{ + u32 idx; + struct perf_ns_link_info *ns_link_info; + + if (!tool || !tool->namespace_events) + return 0; + + memset(&event->namespaces, 0, (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size)); + + event->namespaces.pid = tgid; + event->namespaces.tid = pid; + + event->namespaces.nr_namespaces = NR_NAMESPACES; + + ns_link_info = event->namespaces.link_info; + + for (idx = 0; idx < event->namespaces.nr_namespaces; idx++) + perf_event__get_ns_link_info(pid, perf_ns__name(idx), + &ns_link_info[idx]); + + event->namespaces.header.type = PERF_RECORD_NAMESPACES; + + event->namespaces.header.size = (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return 0; +} + +static int perf_event__synthesize_fork(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, pid_t ppid, + perf_event__handler_t process, + struct machine *machine) +{ + memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); + + /* + * for main thread set parent to ppid from status file. For other + * threads set parent pid to main thread. ie., assume main thread + * spawns all threads in a process + */ + if (tgid == pid) { + event->fork.ppid = ppid; + event->fork.ptid = ppid; + } else { + event->fork.ppid = tgid; + event->fork.ptid = tgid; + } + event->fork.pid = tgid; + event->fork.tid = pid; + event->fork.header.type = PERF_RECORD_FORK; + event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC; + + event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size); + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return 0; +} + +int perf_event__synthesize_mmap_events(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data) +{ + char filename[PATH_MAX]; + FILE *fp; + unsigned long long t; + bool truncation = false; + unsigned long long timeout = proc_map_timeout * 1000000ULL; + int rc = 0; + const char *hugetlbfs_mnt = hugetlbfs__mountpoint(); + int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0; + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps", + machine->root_dir, pid, pid); + + fp = fopen(filename, "r"); + if (fp == NULL) { + /* + * We raced with a task exiting - just return: + */ + pr_debug("couldn't open %s\n", filename); + return -1; + } + + event->header.type = PERF_RECORD_MMAP2; + t = rdclock(); + + while (1) { + char bf[BUFSIZ]; + char prot[5]; + char execname[PATH_MAX]; + char anonstr[] = "//anon"; + unsigned int ino; + size_t size; + ssize_t n; + + if (fgets(bf, sizeof(bf), fp) == NULL) + break; + + if ((rdclock() - t) > timeout) { + pr_warning("Reading %s time out. " + "You may want to increase " + "the time limit by --proc-map-timeout\n", + filename); + truncation = true; + goto out; + } + + /* ensure null termination since stack will be reused. */ + strcpy(execname, ""); + + /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ + n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n", + &event->mmap2.start, &event->mmap2.len, prot, + &event->mmap2.pgoff, &event->mmap2.maj, + &event->mmap2.min, + &ino, execname); + + /* + * Anon maps don't have the execname. + */ + if (n < 7) + continue; + + event->mmap2.ino = (u64)ino; + + /* + * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c + */ + if (machine__is_host(machine)) + event->header.misc = PERF_RECORD_MISC_USER; + else + event->header.misc = PERF_RECORD_MISC_GUEST_USER; + + /* map protection and flags bits */ + event->mmap2.prot = 0; + event->mmap2.flags = 0; + if (prot[0] == 'r') + event->mmap2.prot |= PROT_READ; + if (prot[1] == 'w') + event->mmap2.prot |= PROT_WRITE; + if (prot[2] == 'x') + event->mmap2.prot |= PROT_EXEC; + + if (prot[3] == 's') + event->mmap2.flags |= MAP_SHARED; + else + event->mmap2.flags |= MAP_PRIVATE; + + if (prot[2] != 'x') { + if (!mmap_data || prot[0] != 'r') + continue; + + event->header.misc |= PERF_RECORD_MISC_MMAP_DATA; + } + +out: + if (truncation) + event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT; + + if (!strcmp(execname, "")) + strcpy(execname, anonstr); + + if (hugetlbfs_mnt_len && + !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) { + strcpy(execname, anonstr); + event->mmap2.flags |= MAP_HUGETLB; + } + + size = strlen(execname) + 1; + memcpy(event->mmap2.filename, execname, size); + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap2.len -= event->mmap.start; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + event->mmap2.header.size += machine->id_hdr_size; + event->mmap2.pid = tgid; + event->mmap2.tid = pid; + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { + rc = -1; + break; + } + + if (truncation) + break; + } + + fclose(fp); + return rc; +} + +int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, + struct machine *machine) +{ + int rc = 0; + struct map *pos; + struct maps *maps = machine__kernel_maps(machine); + union perf_event *event = zalloc((sizeof(event->mmap) + + machine->id_hdr_size)); + if (event == NULL) { + pr_debug("Not enough memory synthesizing mmap event " + "for kernel modules\n"); + return -1; + } + + event->header.type = PERF_RECORD_MMAP; + + /* + * kernel uses 0 for user space maps, see kernel/perf_event.c + * __perf_event_mmap + */ + if (machine__is_host(machine)) + event->header.misc = PERF_RECORD_MISC_KERNEL; + else + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + + for (pos = maps__first(maps); pos; pos = map__next(pos)) { + size_t size; + + if (!__map__is_kmodule(pos)) + continue; + + size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size)); + memset(event->mmap.filename + size, 0, machine->id_hdr_size); + event->mmap.header.size += machine->id_hdr_size; + event->mmap.start = pos->start; + event->mmap.len = pos->end - pos->start; + event->mmap.pid = machine->pid; + + memcpy(event->mmap.filename, pos->dso->long_name, + pos->dso->long_name_len + 1); + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { + rc = -1; + break; + } + } + + free(event); + return rc; +} + +static int __event__synthesize_thread(union perf_event *comm_event, + union perf_event *mmap_event, + union perf_event *fork_event, + union perf_event *namespaces_event, + pid_t pid, int full, perf_event__handler_t process, + struct perf_tool *tool, struct machine *machine, bool mmap_data) +{ + char filename[PATH_MAX]; + DIR *tasks; + struct dirent *dirent; + pid_t tgid, ppid; + int rc = 0; + + /* special case: only send one comm event using passed in pid */ + if (!full) { + tgid = perf_event__synthesize_comm(tool, comm_event, pid, + process, machine); + + if (tgid == -1) + return -1; + + if (perf_event__synthesize_namespaces(tool, namespaces_event, pid, + tgid, process, machine) < 0) + return -1; + + /* + * send mmap only for thread group leader + * see thread__init_map_groups + */ + if (pid == tgid && + perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data)) + return -1; + + return 0; + } + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(filename, sizeof(filename), "%s/proc/%d/task", + machine->root_dir, pid); + + tasks = opendir(filename); + if (tasks == NULL) { + pr_debug("couldn't open %s\n", filename); + return 0; + } + + while ((dirent = readdir(tasks)) != NULL) { + char *end; + pid_t _pid; + + _pid = strtol(dirent->d_name, &end, 10); + if (*end) + continue; + + rc = -1; + if (perf_event__prepare_comm(comm_event, _pid, machine, + &tgid, &ppid) != 0) + break; + + if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, + ppid, process, machine) < 0) + break; + + if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid, + tgid, process, machine) < 0) + break; + + /* + * Send the prepared comm event + */ + if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0) + break; + + rc = 0; + if (_pid == pid) { + /* process the parent's maps too */ + rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data); + if (rc) + break; + } + } + + closedir(tasks); + return rc; +} + +int perf_event__synthesize_thread_map(struct perf_tool *tool, + struct perf_thread_map *threads, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data) +{ + union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; + int err = -1, thread, j; + + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); + if (comm_event == NULL) + goto out; + + mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); + if (mmap_event == NULL) + goto out_free_comm; + + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; + + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + + err = 0; + for (thread = 0; thread < threads->nr; ++thread) { + if (__event__synthesize_thread(comm_event, mmap_event, + fork_event, namespaces_event, + perf_thread_map__pid(threads, thread), 0, + process, tool, machine, + mmap_data)) { + err = -1; + break; + } + + /* + * comm.pid is set to thread group id by + * perf_event__synthesize_comm + */ + if ((int) comm_event->comm.pid != perf_thread_map__pid(threads, thread)) { + bool need_leader = true; + + /* is thread group leader in thread_map? */ + for (j = 0; j < threads->nr; ++j) { + if ((int) comm_event->comm.pid == perf_thread_map__pid(threads, j)) { + need_leader = false; + break; + } + } + + /* if not, generate events for it */ + if (need_leader && + __event__synthesize_thread(comm_event, mmap_event, + fork_event, namespaces_event, + comm_event->comm.pid, 0, + process, tool, machine, + mmap_data)) { + err = -1; + break; + } + } + } + free(namespaces_event); +out_free_fork: + free(fork_event); +out_free_mmap: + free(mmap_event); +out_free_comm: + free(comm_event); +out: + return err; +} + +static int __perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data, + struct dirent **dirent, + int start, + int num) +{ + union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; + int err = -1; + char *end; + pid_t pid; + int i; + + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); + if (comm_event == NULL) + goto out; + + mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size); + if (mmap_event == NULL) + goto out_free_comm; + + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; + + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + + for (i = start; i < start + num; i++) { + if (!isdigit(dirent[i]->d_name[0])) + continue; + + pid = (pid_t)strtol(dirent[i]->d_name, &end, 10); + /* only interested in proper numerical dirents */ + if (*end) + continue; + /* + * We may race with exiting thread, so don't stop just because + * one thread couldn't be synthesized. + */ + __event__synthesize_thread(comm_event, mmap_event, fork_event, + namespaces_event, pid, 1, process, + tool, machine, mmap_data); + } + err = 0; + + free(namespaces_event); +out_free_fork: + free(fork_event); +out_free_mmap: + free(mmap_event); +out_free_comm: + free(comm_event); +out: + return err; +} + +struct synthesize_threads_arg { + struct perf_tool *tool; + perf_event__handler_t process; + struct machine *machine; + bool mmap_data; + struct dirent **dirent; + int num; + int start; +}; + +static void *synthesize_threads_worker(void *arg) +{ + struct synthesize_threads_arg *args = arg; + + __perf_event__synthesize_threads(args->tool, args->process, + args->machine, args->mmap_data, + args->dirent, + args->start, args->num); + return NULL; +} + +int perf_event__synthesize_threads(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine, + bool mmap_data, + unsigned int nr_threads_synthesize) +{ + struct synthesize_threads_arg *args = NULL; + pthread_t *synthesize_threads = NULL; + char proc_path[PATH_MAX]; + struct dirent **dirent; + int num_per_thread; + int m, n, i, j; + int thread_nr; + int base = 0; + int err = -1; + + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); + n = scandir(proc_path, &dirent, 0, alphasort); + if (n < 0) + return err; + + if (nr_threads_synthesize == UINT_MAX) + thread_nr = sysconf(_SC_NPROCESSORS_ONLN); + else + thread_nr = nr_threads_synthesize; + + if (thread_nr <= 1) { + err = __perf_event__synthesize_threads(tool, process, + machine, mmap_data, + dirent, base, n); + goto free_dirent; + } + if (thread_nr > n) + thread_nr = n; + + synthesize_threads = calloc(sizeof(pthread_t), thread_nr); + if (synthesize_threads == NULL) + goto free_dirent; + + args = calloc(sizeof(*args), thread_nr); + if (args == NULL) + goto free_threads; + + num_per_thread = n / thread_nr; + m = n % thread_nr; + for (i = 0; i < thread_nr; i++) { + args[i].tool = tool; + args[i].process = process; + args[i].machine = machine; + args[i].mmap_data = mmap_data; + args[i].dirent = dirent; + } + for (i = 0; i < m; i++) { + args[i].num = num_per_thread + 1; + args[i].start = i * args[i].num; + } + if (i != 0) + base = args[i-1].start + args[i-1].num; + for (j = i; j < thread_nr; j++) { + args[j].num = num_per_thread; + args[j].start = base + (j - i) * args[i].num; + } + + for (i = 0; i < thread_nr; i++) { + if (pthread_create(&synthesize_threads[i], NULL, + synthesize_threads_worker, &args[i])) + goto out_join; + } + err = 0; +out_join: + for (i = 0; i < thread_nr; i++) + pthread_join(synthesize_threads[i], NULL); + free(args); +free_threads: + free(synthesize_threads); +free_dirent: + for (i = 0; i < n; i++) + zfree(&dirent[i]); + free(dirent); + + return err; +} + +int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + size_t size; + struct map *map = machine__kernel_map(machine); + struct kmap *kmap; + int err; + union perf_event *event; + + if (map == NULL) + return -1; + + kmap = map__kmap(map); + if (!kmap->ref_reloc_sym) + return -1; + + /* + * We should get this from /sys/kernel/sections/.text, but till that is + * available use this, and after it is use this as a fallback for older + * kernels. + */ + event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); + if (event == NULL) { + pr_debug("Not enough memory synthesizing mmap event " + "for kernel modules\n"); + return -1; + } + + if (machine__is_host(machine)) { + /* + * kernel uses PERF_RECORD_MISC_USER for user space maps, + * see kernel/perf_event.c __perf_event_mmap + */ + event->header.misc = PERF_RECORD_MISC_KERNEL; + } else { + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + } + + size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), + "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); + event->mmap.pgoff = kmap->ref_reloc_sym->addr; + event->mmap.start = map->start; + event->mmap.len = map->end - event->mmap.start; + event->mmap.pid = machine->pid; + + err = perf_tool__process_synth_event(tool, event, machine, process); + free(event); + + return err; +} + +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + int err; + + err = __perf_event__synthesize_kernel_mmap(tool, process, machine); + if (err < 0) + return err; + + return perf_event__synthesize_extra_kmaps(tool, process, machine); +} + +int perf_event__synthesize_thread_map2(struct perf_tool *tool, + struct perf_thread_map *threads, + perf_event__handler_t process, + struct machine *machine) +{ + union perf_event *event; + int i, err, size; + + size = sizeof(event->thread_map); + size += threads->nr * sizeof(event->thread_map.entries[0]); + + event = zalloc(size); + if (!event) + return -ENOMEM; + + event->header.type = PERF_RECORD_THREAD_MAP; + event->header.size = size; + event->thread_map.nr = threads->nr; + + for (i = 0; i < threads->nr; i++) { + struct perf_record_thread_map_entry *entry = &event->thread_map.entries[i]; + char *comm = perf_thread_map__comm(threads, i); + + if (!comm) + comm = (char *) ""; + + entry->pid = perf_thread_map__pid(threads, i); + strncpy((char *) &entry->comm, comm, sizeof(entry->comm)); + } + + err = process(tool, event, NULL, machine); + + free(event); + return err; +} + +static void synthesize_cpus(struct cpu_map_entries *cpus, + struct perf_cpu_map *map) +{ + int i; + + cpus->nr = map->nr; + + for (i = 0; i < map->nr; i++) + cpus->cpu[i] = map->map[i]; +} + +static void synthesize_mask(struct perf_record_record_cpu_map *mask, + struct perf_cpu_map *map, int max) +{ + int i; + + mask->nr = BITS_TO_LONGS(max); + mask->long_size = sizeof(long); + + for (i = 0; i < map->nr; i++) + set_bit(map->map[i], mask->mask); +} + +static size_t cpus_size(struct perf_cpu_map *map) +{ + return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16); +} + +static size_t mask_size(struct perf_cpu_map *map, int *max) +{ + int i; + + *max = 0; + + for (i = 0; i < map->nr; i++) { + /* bit possition of the cpu is + 1 */ + int bit = map->map[i] + 1; + + if (bit > *max) + *max = bit; + } + + return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long); +} + +void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max) +{ + size_t size_cpus, size_mask; + bool is_dummy = perf_cpu_map__empty(map); + + /* + * Both array and mask data have variable size based + * on the number of cpus and their actual values. + * The size of the 'struct perf_record_cpu_map_data' is: + * + * array = size of 'struct cpu_map_entries' + + * number of cpus * sizeof(u64) + * + * mask = size of 'struct perf_record_record_cpu_map' + + * maximum cpu bit converted to size of longs + * + * and finaly + the size of 'struct perf_record_cpu_map_data'. + */ + size_cpus = cpus_size(map); + size_mask = mask_size(map, max); + + if (is_dummy || (size_cpus < size_mask)) { + *size += size_cpus; + *type = PERF_CPU_MAP__CPUS; + } else { + *size += size_mask; + *type = PERF_CPU_MAP__MASK; + } + + *size += sizeof(struct perf_record_cpu_map_data); + *size = PERF_ALIGN(*size, sizeof(u64)); + return zalloc(*size); +} + +void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map, + u16 type, int max) +{ + data->type = type; + + switch (type) { + case PERF_CPU_MAP__CPUS: + synthesize_cpus((struct cpu_map_entries *) data->data, map); + break; + case PERF_CPU_MAP__MASK: + synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max); + default: + break; + }; +} + +static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map) +{ + size_t size = sizeof(struct perf_record_cpu_map); + struct perf_record_cpu_map *event; + int max; + u16 type; + + event = cpu_map_data__alloc(map, &size, &type, &max); + if (!event) + return NULL; + + event->header.type = PERF_RECORD_CPU_MAP; + event->header.size = size; + event->data.type = type; + + cpu_map_data__synthesize(&event->data, map, type, max); + return event; +} + +int perf_event__synthesize_cpu_map(struct perf_tool *tool, + struct perf_cpu_map *map, + perf_event__handler_t process, + struct machine *machine) +{ + struct perf_record_cpu_map *event; + int err; + + event = cpu_map_event__new(map); + if (!event) + return -ENOMEM; + + err = process(tool, (union perf_event *) event, NULL, machine); + + free(event); + return err; +} + +int perf_event__synthesize_stat_config(struct perf_tool *tool, + struct perf_stat_config *config, + perf_event__handler_t process, + struct machine *machine) +{ + struct perf_record_stat_config *event; + int size, i = 0, err; + + size = sizeof(*event); + size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0])); + + event = zalloc(size); + if (!event) + return -ENOMEM; + + event->header.type = PERF_RECORD_STAT_CONFIG; + event->header.size = size; + event->nr = PERF_STAT_CONFIG_TERM__MAX; + +#define ADD(__term, __val) \ + event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term; \ + event->data[i].val = __val; \ + i++; + + ADD(AGGR_MODE, config->aggr_mode) + ADD(INTERVAL, config->interval) + ADD(SCALE, config->scale) + + WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX, + "stat config terms unbalanced\n"); +#undef ADD + + err = process(tool, (union perf_event *) event, NULL, machine); + + free(event); + return err; +} + +int perf_event__synthesize_stat(struct perf_tool *tool, + u32 cpu, u32 thread, u64 id, + struct perf_counts_values *count, + perf_event__handler_t process, + struct machine *machine) +{ + struct perf_record_stat event; + + event.header.type = PERF_RECORD_STAT; + event.header.size = sizeof(event); + event.header.misc = 0; + + event.id = id; + event.cpu = cpu; + event.thread = thread; + event.val = count->val; + event.ena = count->ena; + event.run = count->run; + + return process(tool, (union perf_event *) &event, NULL, machine); +} + +int perf_event__synthesize_stat_round(struct perf_tool *tool, + u64 evtime, u64 type, + perf_event__handler_t process, + struct machine *machine) +{ + struct perf_record_stat_round event; + + event.header.type = PERF_RECORD_STAT_ROUND; + event.header.size = sizeof(event); + event.header.misc = 0; + + event.time = evtime; + event.type = type; + + return process(tool, (union perf_event *) &event, NULL, machine); +} + +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format) +{ + size_t sz, result = sizeof(struct perf_record_sample); + + if (type & PERF_SAMPLE_IDENTIFIER) + result += sizeof(u64); + + if (type & PERF_SAMPLE_IP) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TIME) + result += sizeof(u64); + + if (type & PERF_SAMPLE_ADDR) + result += sizeof(u64); + + if (type & PERF_SAMPLE_ID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_STREAM_ID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_CPU) + result += sizeof(u64); + + if (type & PERF_SAMPLE_PERIOD) + result += sizeof(u64); + + if (type & PERF_SAMPLE_READ) { + result += sizeof(u64); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + result += sizeof(u64); + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + result += sizeof(u64); + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + sz = sample->read.group.nr * + sizeof(struct sample_read_value); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + sz = (sample->callchain->nr + 1) * sizeof(u64); + result += sz; + } + + if (type & PERF_SAMPLE_RAW) { + result += sizeof(u32); + result += sample->raw_size; + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + sz = sample->branch_stack->nr * sizeof(struct branch_entry); + sz += sizeof(u64); + result += sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + if (sample->user_regs.abi) { + result += sizeof(u64); + sz = hweight64(sample->user_regs.mask) * sizeof(u64); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + sz = sample->user_stack.size; + result += sizeof(u64); + if (sz) { + result += sz; + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_WEIGHT) + result += sizeof(u64); + + if (type & PERF_SAMPLE_DATA_SRC) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TRANSACTION) + result += sizeof(u64); + + if (type & PERF_SAMPLE_REGS_INTR) { + if (sample->intr_regs.abi) { + result += sizeof(u64); + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_PHYS_ADDR) + result += sizeof(u64); + + return result; +} + +int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, + const struct perf_sample *sample) +{ + __u64 *array; + size_t sz; + /* + * used for cross-endian analysis. See git commit 65014ab3 + * for why this goofiness is needed. + */ + union u64_swap u; + + array = event->sample.array; + + if (type & PERF_SAMPLE_IDENTIFIER) { + *array = sample->id; + array++; + } + + if (type & PERF_SAMPLE_IP) { + *array = sample->ip; + array++; + } + + if (type & PERF_SAMPLE_TID) { + u.val32[0] = sample->pid; + u.val32[1] = sample->tid; + *array = u.val64; + array++; + } + + if (type & PERF_SAMPLE_TIME) { + *array = sample->time; + array++; + } + + if (type & PERF_SAMPLE_ADDR) { + *array = sample->addr; + array++; + } + + if (type & PERF_SAMPLE_ID) { + *array = sample->id; + array++; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + *array = sample->stream_id; + array++; + } + + if (type & PERF_SAMPLE_CPU) { + u.val32[0] = sample->cpu; + u.val32[1] = 0; + *array = u.val64; + array++; + } + + if (type & PERF_SAMPLE_PERIOD) { + *array = sample->period; + array++; + } + + if (type & PERF_SAMPLE_READ) { + if (read_format & PERF_FORMAT_GROUP) + *array = sample->read.group.nr; + else + *array = sample->read.one.value; + array++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + *array = sample->read.time_enabled; + array++; + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + *array = sample->read.time_running; + array++; + } + + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + sz = sample->read.group.nr * + sizeof(struct sample_read_value); + memcpy(array, sample->read.group.values, sz); + array = (void *)array + sz; + } else { + *array = sample->read.one.id; + array++; + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + sz = (sample->callchain->nr + 1) * sizeof(u64); + memcpy(array, sample->callchain, sz); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_RAW) { + u.val32[0] = sample->raw_size; + *array = u.val64; + array = (void *)array + sizeof(u32); + + memcpy(array, sample->raw_data, sample->raw_size); + array = (void *)array + sample->raw_size; + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + sz = sample->branch_stack->nr * sizeof(struct branch_entry); + sz += sizeof(u64); + memcpy(array, sample->branch_stack, sz); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + if (sample->user_regs.abi) { + *array++ = sample->user_regs.abi; + sz = hweight64(sample->user_regs.mask) * sizeof(u64); + memcpy(array, sample->user_regs.regs, sz); + array = (void *)array + sz; + } else { + *array++ = 0; + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + sz = sample->user_stack.size; + *array++ = sz; + if (sz) { + memcpy(array, sample->user_stack.data, sz); + array = (void *)array + sz; + *array++ = sz; + } + } + + if (type & PERF_SAMPLE_WEIGHT) { + *array = sample->weight; + array++; + } + + if (type & PERF_SAMPLE_DATA_SRC) { + *array = sample->data_src; + array++; + } + + if (type & PERF_SAMPLE_TRANSACTION) { + *array = sample->transaction; + array++; + } + + if (type & PERF_SAMPLE_REGS_INTR) { + if (sample->intr_regs.abi) { + *array++ = sample->intr_regs.abi; + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); + memcpy(array, sample->intr_regs.regs, sz); + array = (void *)array + sz; + } else { + *array++ = 0; + } + } + + if (type & PERF_SAMPLE_PHYS_ADDR) { + *array = sample->phys_addr; + array++; + } + + return 0; +} + +int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, + struct evlist *evlist, struct machine *machine) +{ + union perf_event *ev; + struct evsel *evsel; + size_t nr = 0, i = 0, sz, max_nr, n; + int err; + + pr_debug2("Synthesizing id index\n"); + + max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) / + sizeof(struct id_index_entry); + + evlist__for_each_entry(evlist, evsel) + nr += evsel->core.ids; + + n = nr > max_nr ? max_nr : nr; + sz = sizeof(struct perf_record_id_index) + n * sizeof(struct id_index_entry); + ev = zalloc(sz); + if (!ev) + return -ENOMEM; + + ev->id_index.header.type = PERF_RECORD_ID_INDEX; + ev->id_index.header.size = sz; + ev->id_index.nr = n; + + evlist__for_each_entry(evlist, evsel) { + u32 j; + + for (j = 0; j < evsel->core.ids; j++) { + struct id_index_entry *e; + struct perf_sample_id *sid; + + if (i >= n) { + err = process(tool, ev, NULL, machine); + if (err) + goto out_err; + nr -= n; + i = 0; + } + + e = &ev->id_index.entries[i++]; + + e->id = evsel->core.id[j]; + + sid = perf_evlist__id2sid(evlist, e->id); + if (!sid) { + free(ev); + return -ENOENT; + } + + e->idx = sid->idx; + e->cpu = sid->cpu; + e->tid = sid->tid; + } + } + + sz = sizeof(struct perf_record_id_index) + nr * sizeof(struct id_index_entry); + ev->id_index.header.size = sz; + ev->id_index.nr = nr; + + err = process(tool, ev, NULL, machine); +out_err: + free(ev); + + return err; +} + +int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, + struct target *target, struct perf_thread_map *threads, + perf_event__handler_t process, bool data_mmap, + unsigned int nr_threads_synthesize) +{ + if (target__has_task(target)) + return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap); + else if (target__has_cpu(target)) + return perf_event__synthesize_threads(tool, process, + machine, data_mmap, + nr_threads_synthesize); + /* command specified */ + return 0; +} + +int machine__synthesize_threads(struct machine *machine, struct target *target, + struct perf_thread_map *threads, bool data_mmap, + unsigned int nr_threads_synthesize) +{ + return __machine__synthesize_threads(machine, NULL, target, threads, + perf_event__process, data_mmap, + nr_threads_synthesize); +} + +static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id) +{ + struct perf_record_event_update *ev; + + size += sizeof(*ev); + size = PERF_ALIGN(size, sizeof(u64)); + + ev = zalloc(size); + if (ev) { + ev->header.type = PERF_RECORD_EVENT_UPDATE; + ev->header.size = (u16)size; + ev->type = type; + ev->id = id; + } + return ev; +} + +int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct evsel *evsel, + perf_event__handler_t process) +{ + size_t size = strlen(evsel->unit); + struct perf_record_event_update *ev; + int err; + + ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->core.id[0]); + if (ev == NULL) + return -ENOMEM; + + strlcpy(ev->data, evsel->unit, size + 1); + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, + perf_event__handler_t process) +{ + struct perf_record_event_update *ev; + struct perf_record_event_update_scale *ev_data; + int err; + + ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->core.id[0]); + if (ev == NULL) + return -ENOMEM; + + ev_data = (struct perf_record_event_update_scale *)ev->data; + ev_data->scale = evsel->scale; + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, + perf_event__handler_t process) +{ + struct perf_record_event_update *ev; + size_t len = strlen(evsel->name); + int err; + + ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->core.id[0]); + if (ev == NULL) + return -ENOMEM; + + strlcpy(ev->data, evsel->name, len + 1); + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, + perf_event__handler_t process) +{ + size_t size = sizeof(struct perf_record_event_update); + struct perf_record_event_update *ev; + int max, err; + u16 type; + + if (!evsel->core.own_cpus) + return 0; + + ev = cpu_map_data__alloc(evsel->core.own_cpus, &size, &type, &max); + if (!ev) + return -ENOMEM; + + ev->header.type = PERF_RECORD_EVENT_UPDATE; + ev->header.size = (u16)size; + ev->type = PERF_EVENT_UPDATE__CPUS; + ev->id = evsel->core.id[0]; + + cpu_map_data__synthesize((struct perf_record_cpu_map_data *)ev->data, + evsel->core.own_cpus, type, max); + + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, + perf_event__handler_t process) +{ + struct evsel *evsel; + int err = 0; + + evlist__for_each_entry(evlist, evsel) { + err = perf_event__synthesize_attr(tool, &evsel->core.attr, evsel->core.ids, + evsel->core.id, process); + if (err) { + pr_debug("failed to create perf header attribute\n"); + return err; + } + } + + return err; +} + +static bool has_unit(struct evsel *evsel) +{ + return evsel->unit && *evsel->unit; +} + +static bool has_scale(struct evsel *evsel) +{ + return evsel->scale != 1; +} + +int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evsel_list, + perf_event__handler_t process, bool is_pipe) +{ + struct evsel *evsel; + int err; + + /* + * Synthesize other events stuff not carried within + * attr event - unit, scale, name + */ + evlist__for_each_entry(evsel_list, evsel) { + if (!evsel->supported) + continue; + + /* + * Synthesize unit and scale only if it's defined. + */ + if (has_unit(evsel)) { + err = perf_event__synthesize_event_update_unit(tool, evsel, process); + if (err < 0) { + pr_err("Couldn't synthesize evsel unit.\n"); + return err; + } + } + + if (has_scale(evsel)) { + err = perf_event__synthesize_event_update_scale(tool, evsel, process); + if (err < 0) { + pr_err("Couldn't synthesize evsel evsel.\n"); + return err; + } + } + + if (evsel->core.own_cpus) { + err = perf_event__synthesize_event_update_cpus(tool, evsel, process); + if (err < 0) { + pr_err("Couldn't synthesize evsel cpus.\n"); + return err; + } + } + + /* + * Name is needed only for pipe output, + * perf.data carries event names. + */ + if (is_pipe) { + err = perf_event__synthesize_event_update_name(tool, evsel, process); + if (err < 0) { + pr_err("Couldn't synthesize evsel name.\n"); + return err; + } + } + } + return 0; +} + +int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, + u32 ids, u64 *id, perf_event__handler_t process) +{ + union perf_event *ev; + size_t size; + int err; + + size = sizeof(struct perf_event_attr); + size = PERF_ALIGN(size, sizeof(u64)); + size += sizeof(struct perf_event_header); + size += ids * sizeof(u64); + + ev = zalloc(size); + + if (ev == NULL) + return -ENOMEM; + + ev->attr.attr = *attr; + memcpy(ev->attr.id, id, ids * sizeof(u64)); + + ev->attr.header.type = PERF_RECORD_HEADER_ATTR; + ev->attr.header.size = (u16)size; + + if (ev->attr.header.size == size) + err = process(tool, ev, NULL, NULL); + else + err = -E2BIG; + + free(ev); + + return err; +} + +int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, + perf_event__handler_t process) +{ + union perf_event ev; + struct tracing_data *tdata; + ssize_t size = 0, aligned_size = 0, padding; + struct feat_fd ff; + + /* + * We are going to store the size of the data followed + * by the data contents. Since the fd descriptor is a pipe, + * we cannot seek back to store the size of the data once + * we know it. Instead we: + * + * - write the tracing data to the temp file + * - get/write the data size to pipe + * - write the tracing data from the temp file + * to the pipe + */ + tdata = tracing_data_get(&evlist->core.entries, fd, true); + if (!tdata) + return -1; + + memset(&ev, 0, sizeof(ev)); + + ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; + size = tdata->size; + aligned_size = PERF_ALIGN(size, sizeof(u64)); + padding = aligned_size - size; + ev.tracing_data.header.size = sizeof(ev.tracing_data); + ev.tracing_data.size = aligned_size; + + process(tool, &ev, NULL, NULL); + + /* + * The put function will copy all the tracing data + * stored in temp file to the pipe. + */ + tracing_data_put(tdata); + + ff = (struct feat_fd){ .fd = fd }; + if (write_padded(&ff, NULL, 0, padding)) + return -1; + + return aligned_size; +} + +int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, + perf_event__handler_t process, struct machine *machine) +{ + union perf_event ev; + size_t len; + + if (!pos->hit) + return 0; + + memset(&ev, 0, sizeof(ev)); + + len = pos->long_name_len + 1; + len = PERF_ALIGN(len, NAME_ALIGN); + memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); + ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; + ev.build_id.header.misc = misc; + ev.build_id.pid = machine->pid; + ev.build_id.header.size = sizeof(ev.build_id) + len; + memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len); + + return process(tool, &ev, NULL, machine); +} + +int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, + struct evlist *evlist, perf_event__handler_t process, bool attrs) +{ + int err; + + if (attrs) { + err = perf_event__synthesize_attrs(tool, evlist, process); + if (err < 0) { + pr_err("Couldn't synthesize attrs.\n"); + return err; + } + } + + err = perf_event__synthesize_extra_attr(tool, evlist, process, attrs); + err = perf_event__synthesize_thread_map2(tool, evlist->core.threads, process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize thread map.\n"); + return err; + } + + err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize thread map.\n"); + return err; + } + + err = perf_event__synthesize_stat_config(tool, config, process, NULL); + if (err < 0) { + pr_err("Couldn't synthesize config.\n"); + return err; + } + + return 0; +} + +int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, + struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +extern const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE]; + +int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, + struct evlist *evlist, perf_event__handler_t process) +{ + struct perf_header *header = &session->header; + struct perf_record_header_feature *fe; + struct feat_fd ff; + size_t sz, sz_hdr; + int feat, ret; + + sz_hdr = sizeof(fe->header); + sz = sizeof(union perf_event); + /* get a nice alignment */ + sz = PERF_ALIGN(sz, page_size); + + memset(&ff, 0, sizeof(ff)); + + ff.buf = malloc(sz); + if (!ff.buf) + return -ENOMEM; + + ff.size = sz - sz_hdr; + ff.ph = &session->header; + + for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { + if (!feat_ops[feat].synthesize) { + pr_debug("No record header feature for header :%d\n", feat); + continue; + } + + ff.offset = sizeof(*fe); + + ret = feat_ops[feat].write(&ff, evlist); + if (ret || ff.offset <= (ssize_t)sizeof(*fe)) { + pr_debug("Error writing feature\n"); + continue; + } + /* ff.buf may have changed due to realloc in do_write() */ + fe = ff.buf; + memset(fe, 0, sizeof(*fe)); + + fe->feat_id = feat; + fe->header.type = PERF_RECORD_HEADER_FEATURE; + fe->header.size = ff.offset; + + ret = process(tool, ff.buf, NULL, NULL); + if (ret) { + free(ff.buf); + return ret; + } + } + + /* Send HEADER_LAST_FEATURE mark. */ + fe = ff.buf; + fe->feat_id = HEADER_LAST_FEATURE; + fe->header.type = PERF_RECORD_HEADER_FEATURE; + fe->header.size = sizeof(*fe); + + ret = process(tool, ff.buf, NULL, NULL); + + free(ff.buf); + return ret; +} diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h new file mode 100644 index 000000000000..baead0cdc381 --- /dev/null +++ b/tools/perf/util/synthetic-events.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_SYNTHETIC_EVENTS_H +#define __PERF_SYNTHETIC_EVENTS_H + +#include <stdbool.h> +#include <sys/types.h> // pid_t +#include <linux/compiler.h> +#include <linux/types.h> + +struct auxtrace_record; +struct dso; +struct evlist; +struct evsel; +struct machine; +struct perf_counts_values; +struct perf_cpu_map; +struct perf_event_attr; +struct perf_event_mmap_page; +struct perf_sample; +struct perf_session; +struct perf_stat_config; +struct perf_thread_map; +struct perf_tool; +struct record_opts; +struct target; + +union perf_event; + +typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, struct machine *machine); + +int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process); +int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); +int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); +int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); +int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); +int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); +int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evsel_list, perf_event__handler_t process, bool is_pipe); +int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, struct evlist *evlist, perf_event__handler_t process); +int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, struct evlist *evlist, struct machine *machine); +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data); +int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_namespaces(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample); +int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs); +int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data); +int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize); +int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process); +int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine); + +int perf_tool__process_synth_event(struct perf_tool *tool, union perf_event *event, struct machine *machine, perf_event__handler_t process); + +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format); + +int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, + struct target *target, struct perf_thread_map *threads, + perf_event__handler_t process, bool data_mmap, + unsigned int nr_threads_synthesize); +int machine__synthesize_threads(struct machine *machine, struct target *target, + struct perf_thread_map *threads, bool data_mmap, + unsigned int nr_threads_synthesize); + +#ifdef HAVE_AUXTRACE_SUPPORT +int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, struct perf_tool *tool, + struct perf_session *session, perf_event__handler_t process); + +#else // HAVE_AUXTRACE_SUPPORT + +#include <errno.h> + +static inline int +perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused, + struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, + perf_event__handler_t process __maybe_unused) +{ + return -EINVAL; +} +#endif // HAVE_AUXTRACE_SUPPORT + +#ifdef HAVE_LIBBPF_SUPPORT +int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process, + struct machine *machine, struct record_opts *opts); +#else // HAVE_LIBBPF_SUPPORT +static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused, + struct record_opts *opts __maybe_unused) +{ + return 0; +} +#endif // HAVE_LIBBPF_SUPPORT + +#endif // __PERF_SYNTHETIC_EVENTS_H diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index 565f7aef7e6c..a3db13dea937 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -6,8 +6,6 @@ */ #include "target.h" -#include "util.h" -#include "debug.h" #include <pwd.h> #include <stdio.h> diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 51fb574998bb..3dce2de9d005 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -5,7 +5,6 @@ * Refactored from builtin-top.c, see that files for further copyright notes. */ -#include "cpumap.h" #include "event.h" #include "evlist.h" #include "evsel.h" @@ -72,7 +71,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) } if (top->evlist->core.nr_entries == 1) { - struct evsel *first = perf_evlist__first(top->evlist); + struct evsel *first = evlist__first(top->evlist); ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", (uint64_t)first->core.attr.sample_period, opts->freq ? "Hz" : ""); diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index d63d542b2cde..086e98ff42a3 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -2,7 +2,6 @@ /* * Copyright (C) 2008,2009, Steven Rostedt <srostedt@redhat.com> */ -#include "util.h" #include <dirent.h> #include <mntent.h> #include <stdio.h> @@ -19,6 +18,7 @@ #include <linux/list.h> #include <linux/kernel.h> #include <linux/zalloc.h> +#include <internal/lib.h> // page_size #include "trace-event.h" #include <api/fs/tracing_path.h> diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index b6c0db068be0..8593d3c200c6 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -15,7 +15,6 @@ #include <unistd.h> #include <errno.h> -#include "util.h" #include "trace-event.h" #include "debug.h" diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index 01b9d89bf5bf..b3ee651e3d91 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -14,7 +14,6 @@ #include <api/fs/fs.h> #include "trace-event.h" #include "machine.h" -#include "util.h" /* * global trace_event object used by trace_event__tp_format diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h index e0c3af34ac8d..3c5a632ee57c 100644 --- a/tools/perf/util/tsc.h +++ b/tools/perf/util/tsc.h @@ -4,13 +4,12 @@ #include <linux/types.h> -#include "event.h" - struct perf_tsc_conversion { u16 time_shift; u32 time_mult; u64 time_zero; }; + struct perf_event_mmap_page; int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, @@ -20,13 +19,4 @@ u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); u64 rdtsc(void); -struct perf_event_mmap_page; -struct perf_tool; -struct machine; - -int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, - struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); - -#endif +#endif // __PERF_TSC_H diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 9ece188ae48a..15f6e46d7124 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -17,7 +17,6 @@ #include "event.h" #include "perf_regs.h" #include "callchain.h" -#include "util.h" static char *debuginfo_path; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index ebdbb056510c..1800887b2255 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -37,7 +37,6 @@ #include "unwind.h" #include "map.h" #include "symbol.h" -#include "util.h" #include "debug.h" #include "asm/bug.h" #include "dso.h" diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index 3949a60b00ae..196438ee4c9d 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -8,7 +8,6 @@ * Copyright (C) Linus Torvalds, 2005 */ #include "util.h" -#include "debug.h" #include <stdio.h> #include <stdlib.h> #include <linux/compiler.h> diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 32322a20a68b..5eda6e19c947 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -2,9 +2,7 @@ #include "util.h" #include "debug.h" #include "event.h" -#include "namespaces.h" #include <api/fs/fs.h> -#include <sys/mman.h> #include <sys/stat.h> #include <sys/utsname.h> #include <dirent.h> @@ -41,8 +39,6 @@ void perf_set_multithreaded(void) perf_singlethreaded = false; } -unsigned int page_size; - int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK; @@ -234,138 +230,6 @@ out: return list; } -static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi) -{ - int err = -1; - char *line = NULL; - size_t n; - FILE *from_fp, *to_fp; - struct nscookie nsc; - - nsinfo__mountns_enter(nsi, &nsc); - from_fp = fopen(from, "r"); - nsinfo__mountns_exit(&nsc); - if (from_fp == NULL) - goto out; - - to_fp = fopen(to, "w"); - if (to_fp == NULL) - goto out_fclose_from; - - while (getline(&line, &n, from_fp) > 0) - if (fputs(line, to_fp) == EOF) - goto out_fclose_to; - err = 0; -out_fclose_to: - fclose(to_fp); - free(line); -out_fclose_from: - fclose(from_fp); -out: - return err; -} - -int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) -{ - void *ptr; - loff_t pgoff; - - pgoff = off_in & ~(page_size - 1); - off_in -= pgoff; - - ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff); - if (ptr == MAP_FAILED) - return -1; - - while (size) { - ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out); - if (ret < 0 && errno == EINTR) - continue; - if (ret <= 0) - break; - - size -= ret; - off_in += ret; - off_out += ret; - } - munmap(ptr, off_in + size); - - return size ? -1 : 0; -} - -static int copyfile_mode_ns(const char *from, const char *to, mode_t mode, - struct nsinfo *nsi) -{ - int fromfd, tofd; - struct stat st; - int err; - char *tmp = NULL, *ptr = NULL; - struct nscookie nsc; - - nsinfo__mountns_enter(nsi, &nsc); - err = stat(from, &st); - nsinfo__mountns_exit(&nsc); - if (err) - goto out; - err = -1; - - /* extra 'x' at the end is to reserve space for '.' */ - if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) { - tmp = NULL; - goto out; - } - ptr = strrchr(tmp, '/'); - if (!ptr) - goto out; - ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1); - *ptr = '.'; - - tofd = mkstemp(tmp); - if (tofd < 0) - goto out; - - if (fchmod(tofd, mode)) - goto out_close_to; - - if (st.st_size == 0) { /* /proc? do it slowly... */ - err = slow_copyfile(from, tmp, nsi); - goto out_close_to; - } - - nsinfo__mountns_enter(nsi, &nsc); - fromfd = open(from, O_RDONLY); - nsinfo__mountns_exit(&nsc); - if (fromfd < 0) - goto out_close_to; - - err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size); - - close(fromfd); -out_close_to: - close(tofd); - if (!err) - err = link(tmp, to); - unlink(tmp); -out: - free(tmp); - return err; -} - -int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi) -{ - return copyfile_mode_ns(from, to, 0755, nsi); -} - -int copyfile_mode(const char *from, const char *to, mode_t mode) -{ - return copyfile_mode_ns(from, to, mode, NULL); -} - -int copyfile(const char *from, const char *to) -{ - return copyfile_mode(from, to, 0755); -} - size_t hex_width(u64 v) { size_t n = 1; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 45a5c6f20197..9969b8b46f7c 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -11,14 +11,12 @@ #include <stddef.h> #include <linux/compiler.h> #include <sys/types.h> -#include <internal/lib.h> /* General helper functions */ void usage(const char *err) __noreturn; void die(const char *err, ...) __noreturn __printf(1, 2); struct dirent; -struct nsinfo; struct strlist; int mkdir_p(char *path, mode_t mode); @@ -26,15 +24,9 @@ int rm_rf(const char *path); int rm_rf_perf_data(const char *path); struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *)); bool lsdir_no_dot_filter(const char *name, struct dirent *d); -int copyfile(const char *from, const char *to); -int copyfile_mode(const char *from, const char *to, mode_t mode); -int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); -int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size); size_t hex_width(u64 v); -extern unsigned int page_size; - int sysctl__max_stack(void); int fetch_kernel_version(unsigned int *puint, diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index e5e6599603f4..ba4b4395f35d 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -11,7 +11,7 @@ #include "vdso.h" #include "dso.h" -#include "util.h" +#include <internal/lib.h> #include "map.h" #include "symbol.h" #include "machine.h" diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index 59d456f716e9..78d2297c1b67 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -7,11 +7,9 @@ #include <sys/mman.h> #include <zlib.h> #include <linux/compiler.h> +#include <internal/lib.h> #include "util/compress.h" -#include "util/util.h" -#include "util/debug.h" - #define CHUNK_SIZE 16384 diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 25b43a8c2b15..c3feccb99ff5 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -126,9 +126,9 @@ endif # in the default INSTALL_HDR_PATH usr/include. khdr: ifeq (1,$(DEFAULT_INSTALL_HDR_PATH)) - make --no-builtin-rules ARCH=$(ARCH) -C $(top_srcdir) headers_install + $(MAKE) --no-builtin-rules ARCH=$(ARCH) -C $(top_srcdir) headers_install else - make --no-builtin-rules INSTALL_HDR_PATH=$$BUILD/usr \ + $(MAKE) --no-builtin-rules INSTALL_HDR_PATH=$$BUILD/usr \ ARCH=$(ARCH) -C $(top_srcdir) headers_install endif @@ -136,35 +136,35 @@ all: khdr @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; hotplug: @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_hotplug: hotplug @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\ done; clean_hotplug: @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; run_pstore_crash: - make -C pstore run_crash + $(MAKE) -C pstore run_crash # Use $BUILD as the default install root. $BUILD points to the # right output location for the following cases: @@ -184,7 +184,7 @@ ifdef INSTALL_PATH install -m 744 kselftest/prefix.pl $(INSTALL_PATH)/kselftest/ @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ done; @# Ask all targets to emit their test scripts @@ -203,7 +203,7 @@ ifdef INSTALL_PATH echo "[ -w /dev/kmsg ] && echo \"kselftest: Running tests in $$TARGET\" >> /dev/kmsg" >> $(ALL_SCRIPT); \ echo "cd $$TARGET" >> $(ALL_SCRIPT); \ echo -n "run_many" >> $(ALL_SCRIPT); \ - make -s --no-print-directory OUTPUT=$$BUILD_TARGET -C $$TARGET emit_tests >> $(ALL_SCRIPT); \ + $(MAKE) -s --no-print-directory OUTPUT=$$BUILD_TARGET -C $$TARGET emit_tests >> $(ALL_SCRIPT); \ echo "" >> $(ALL_SCRIPT); \ echo "cd \$$ROOT" >> $(ALL_SCRIPT); \ done; @@ -216,7 +216,7 @@ endif clean: @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; .PHONY: khdr all run_tests hotplug run_hotplug clean_hotplug run_pstore_crash install clean diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc index 7717c0a09686..ac738500d17f 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc @@ -28,7 +28,7 @@ if [ -z "$FEATURE" ]; then exit_unsupported fi -echo "Test snapshot tigger" +echo "Test snapshot trigger" echo 0 > snapshot echo 1 > events/sched/sched_process_fork/enable ( echo "forked") diff --git a/tools/testing/selftests/livepatch/config b/tools/testing/selftests/livepatch/config index 0dd7700464a8..ad23100cb27c 100644 --- a/tools/testing/selftests/livepatch/config +++ b/tools/testing/selftests/livepatch/config @@ -1 +1,3 @@ +CONFIG_LIVEPATCH=y +CONFIG_DYNAMIC_DEBUG=y CONFIG_TEST_LIVEPATCH=m diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 6ef7f16c4cf5..7f8b5c8982e3 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -199,6 +199,11 @@ struct seccomp_notif_sizes { }; #endif +#ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY +#define PTRACE_EVENTMSG_SYSCALL_ENTRY 1 +#define PTRACE_EVENTMSG_SYSCALL_EXIT 2 +#endif + #ifndef seccomp int seccomp(unsigned int op, unsigned int flags, void *args) { diff --git a/tools/testing/selftests/tpm2/Makefile b/tools/testing/selftests/tpm2/Makefile index bf401f725eef..1a5db1eb8ed5 100644 --- a/tools/testing/selftests/tpm2/Makefile +++ b/tools/testing/selftests/tpm2/Makefile @@ -2,4 +2,4 @@ include ../lib.mk TEST_PROGS := test_smoke.sh test_space.sh -TEST_FILES := tpm2.py tpm2_tests.py +TEST_PROGS_EXTENDED := tpm2.py tpm2_tests.py diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index c2333c78cf04..afff120c7be6 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -19,7 +19,7 @@ int fd; const char v = 'V'; -static const char sopts[] = "bdehp:t:Tn:NL"; +static const char sopts[] = "bdehp:t:Tn:NLf:"; static const struct option lopts[] = { {"bootstatus", no_argument, NULL, 'b'}, {"disable", no_argument, NULL, 'd'}, @@ -31,6 +31,7 @@ static const struct option lopts[] = { {"pretimeout", required_argument, NULL, 'n'}, {"getpretimeout", no_argument, NULL, 'N'}, {"gettimeleft", no_argument, NULL, 'L'}, + {"file", required_argument, NULL, 'f'}, {NULL, no_argument, NULL, 0x0} }; @@ -69,16 +70,19 @@ static void term(int sig) static void usage(char *progname) { printf("Usage: %s [options]\n", progname); - printf(" -b, --bootstatus Get last boot status (Watchdog/POR)\n"); - printf(" -d, --disable Turn off the watchdog timer\n"); - printf(" -e, --enable Turn on the watchdog timer\n"); - printf(" -h, --help Print the help message\n"); - printf(" -p, --pingrate=P Set ping rate to P seconds (default %d)\n", DEFAULT_PING_RATE); - printf(" -t, --timeout=T Set timeout to T seconds\n"); - printf(" -T, --gettimeout Get the timeout\n"); - printf(" -n, --pretimeout=T Set the pretimeout to T seconds\n"); - printf(" -N, --getpretimeout Get the pretimeout\n"); - printf(" -L, --gettimeleft Get the time left until timer expires\n"); + printf(" -f, --file\t\tOpen watchdog device file\n"); + printf("\t\t\tDefault is /dev/watchdog\n"); + printf(" -b, --bootstatus\tGet last boot status (Watchdog/POR)\n"); + printf(" -d, --disable\t\tTurn off the watchdog timer\n"); + printf(" -e, --enable\t\tTurn on the watchdog timer\n"); + printf(" -h, --help\t\tPrint the help message\n"); + printf(" -p, --pingrate=P\tSet ping rate to P seconds (default %d)\n", + DEFAULT_PING_RATE); + printf(" -t, --timeout=T\tSet timeout to T seconds\n"); + printf(" -T, --gettimeout\tGet the timeout\n"); + printf(" -n, --pretimeout=T\tSet the pretimeout to T seconds\n"); + printf(" -N, --getpretimeout\tGet the pretimeout\n"); + printf(" -L, --gettimeleft\tGet the time left until timer expires\n"); printf("\n"); printf("Parameters are parsed left-to-right in real-time.\n"); printf("Example: %s -d -t 10 -p 5 -e\n", progname); @@ -92,14 +96,20 @@ int main(int argc, char *argv[]) int ret; int c; int oneshot = 0; + char *file = "/dev/watchdog"; setbuf(stdout, NULL); - fd = open("/dev/watchdog", O_WRONLY); + while ((c = getopt_long(argc, argv, sopts, lopts, NULL)) != -1) { + if (c == 'f') + file = optarg; + } + + fd = open(file, O_WRONLY); if (fd == -1) { if (errno == ENOENT) - printf("Watchdog device not enabled.\n"); + printf("Watchdog device (%s) not found.\n", file); else if (errno == EACCES) printf("Run watchdog as root.\n"); else @@ -108,6 +118,8 @@ int main(int argc, char *argv[]) exit(-1); } + optind = 0; + while ((c = getopt_long(argc, argv, sopts, lopts, NULL)) != -1) { switch (c) { case 'b': @@ -190,6 +202,9 @@ int main(int argc, char *argv[]) else printf("WDIOC_GETTIMELEFT error '%s'\n", strerror(errno)); break; + case 'f': + /* Handled above */ + break; default: usage(argv[0]); |
