diff options
| author | Linaro CI <ci_notify@linaro.org> | 2022-01-28 15:19:10 +0000 |
|---|---|---|
| committer | Linaro CI <ci_notify@linaro.org> | 2022-01-28 15:19:10 +0000 |
| commit | 5d4f7ade4b00cc7d0f28c4722136eb78fdf4f69c (patch) | |
| tree | 19c470e104e47d6ce256e670077e2f2238cc6570 | |
| parent | 4283a27c40e6053cc8a93443863800468636f714 (diff) | |
| parent | 879438bccfc6e9cf4e6823749e5ad299646026e3 (diff) | |
Merge remote-tracking branch 'sa8155p-adp-dts-drivers/tracking-qcomlt-sa8155p-dts-drivers' into integration-linux-qcomlt
92 files changed, 1826 insertions, 625 deletions
diff --git a/Documentation/accounting/psi.rst b/Documentation/accounting/psi.rst index f2b3439edcc2..860fe651d645 100644 --- a/Documentation/accounting/psi.rst +++ b/Documentation/accounting/psi.rst @@ -92,7 +92,8 @@ Triggers can be set on more than one psi metric and more than one trigger for the same psi metric can be specified. However for each trigger a separate file descriptor is required to be able to poll it separately from others, therefore for each trigger a separate open() syscall should be made even -when opening the same psi interface file. +when opening the same psi interface file. Write operations to a file descriptor +with an already existing psi trigger will fail with EBUSY. Monitors activate only when system enters stall state for the monitored psi metric and deactivates upon exit from the stall state. While system is diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt index 98d89e53013d..bd3539644d3f 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt @@ -21,6 +21,7 @@ Properties: - "qcom,sc7180-pdc": For SC7180 - "qcom,sc7280-pdc": For SC7280 - "qcom,sdm845-pdc": For SDM845 + - "qcom,sdm8150-pdc": For SM8150 - "qcom,sdm8250-pdc": For SM8250 - "qcom,sdm8350-pdc": For SM8350 diff --git a/Documentation/devicetree/bindings/net/qcom,ethqos.txt b/Documentation/devicetree/bindings/net/qcom,ethqos.txt index fcf5035810b5..1f5746849a71 100644 --- a/Documentation/devicetree/bindings/net/qcom,ethqos.txt +++ b/Documentation/devicetree/bindings/net/qcom,ethqos.txt @@ -7,7 +7,9 @@ This device has following properties: Required properties: -- compatible: Should be qcom,qcs404-ethqos" +- compatible: Should be one of: + "qcom,qcs404-ethqos" + "qcom,sm8150-ethqos" - reg: Address and length of the register set for the device diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 7d23d4bb2168..6fe67963ba5a 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -288,6 +288,7 @@ */ #define ALT_UP(instr...) \ .pushsection ".alt.smp.init", "a" ;\ + .align 2 ;\ .long 9998b - . ;\ 9997: instr ;\ .if . - 9997b == 2 ;\ @@ -299,6 +300,7 @@ .popsection #define ALT_UP_B(label) \ .pushsection ".alt.smp.init", "a" ;\ + .align 2 ;\ .long 9998b - . ;\ W(b) . + (label - 9998b) ;\ .popsection diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 6af68edfa53a..bdc35c0e8dfb 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -96,6 +96,7 @@ unsigned long __get_wchan(struct task_struct *p); #define __ALT_SMP_ASM(smp, up) \ "9998: " smp "\n" \ " .pushsection \".alt.smp.init\", \"a\"\n" \ + " .align 2\n" \ " .long 9998b - .\n" \ " " up "\n" \ " .popsection\n" diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 36fbc3329252..32dbfd81f42a 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -11,6 +11,7 @@ #include <linux/string.h> #include <asm/memory.h> #include <asm/domain.h> +#include <asm/unaligned.h> #include <asm/unified.h> #include <asm/compiler.h> @@ -497,7 +498,10 @@ do { \ } \ default: __err = __get_user_bad(); break; \ } \ - *(type *)(dst) = __val; \ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) \ + put_unaligned(__val, (type *)(dst)); \ + else \ + *(type *)(dst) = __val; /* aligned by caller */ \ if (__err) \ goto err_label; \ } while (0) @@ -507,7 +511,9 @@ do { \ const type *__pk_ptr = (dst); \ unsigned long __dst = (unsigned long)__pk_ptr; \ int __err = 0; \ - type __val = *(type *)src; \ + type __val = IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) \ + ? get_unaligned((type *)(src)) \ + : *(type *)(src); /* aligned by caller */ \ switch (sizeof(type)) { \ case 1: __put_user_asm_byte(__val, __dst, __err, ""); break; \ case 2: __put_user_asm_half(__val, __dst, __err, ""); break; \ diff --git a/arch/arm/probes/kprobes/Makefile b/arch/arm/probes/kprobes/Makefile index 14db56f49f0a..6159010dac4a 100644 --- a/arch/arm/probes/kprobes/Makefile +++ b/arch/arm/probes/kprobes/Makefile @@ -1,4 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +KASAN_SANITIZE_actions-common.o := n +KASAN_SANITIZE_actions-arm.o := n +KASAN_SANITIZE_actions-thumb.o := n obj-$(CONFIG_KPROBES) += core.o actions-common.o checkers-common.o obj-$(CONFIG_ARM_KPROBES_TEST) += test-kprobes.o test-kprobes-objs := test-core.o diff --git a/arch/arm64/boot/dts/qcom/sa8155p-adp.dts b/arch/arm64/boot/dts/qcom/sa8155p-adp.dts index 8756c2b25c7e..474f688f14a2 100644 --- a/arch/arm64/boot/dts/qcom/sa8155p-adp.dts +++ b/arch/arm64/boot/dts/qcom/sa8155p-adp.dts @@ -47,6 +47,65 @@ vin-supply = <&vreg_3p3>; }; + + mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <4>; + snps,rx-sched-sp; + + queue0 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x0>; + snps,route-up; + snps,priority = <0x1>; + }; + + queue1 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x1>; + snps,route-ptp; + }; + + queue2 { + snps,avb-algorithm; + snps,map-to-dma-channel = <0x2>; + snps,route-avcp; + }; + + queue3 { + snps,avb-algorithm; + snps,map-to-dma-channel = <0x3>; + snps,priority = <0xC>; + }; + }; + + mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <4>; + snps,tx-sched-wrr; + + queue0 { + snps,weight = <0x10>; + snps,dcb-algorithm; + snps,priority = <0x0>; + }; + + queue1 { + snps,weight = <0x11>; + snps,dcb-algorithm; + snps,priority = <0x1>; + }; + + queue2 { + snps,weight = <0x12>; + snps,dcb-algorithm; + snps,priority = <0x2>; + }; + + queue3 { + snps,weight = <0x13>; + snps,dcb-algorithm; + snps,priority = <0x3>; + }; + }; }; &apps_rsc { @@ -317,6 +376,42 @@ firmware-name = "qcom/sa8155p/cdsp.mdt"; }; +ðernet { + status = "okay"; + + snps,reset-gpio = <&tlmm 79 GPIO_ACTIVE_LOW>; + snps,reset-active-low; + snps,reset-delays-us = <0 11000 70000>; + + snps,ptp-ref-clk-rate = <250000000>; + snps,ptp-req-clk-rate = <96000000>; + + snps,mtl-rx-config = <&mtl_rx_setup>; + snps,mtl-tx-config = <&mtl_tx_setup>; + + pinctrl-names = "default"; + pinctrl-0 = <ðernet_defaults>; + + phy-handle = <&rgmii_phy>; + phy-mode = "rgmii"; + mdio { + #address-cells = <0x1>; + #size-cells = <0x0>; + + compatible = "snps,dwmac-mdio"; + + /* Micrel KSZ9031RNZ PHY */ + rgmii_phy: phy@7 { + reg = <0x7>; + + interrupt-parent = <&tlmm>; + interrupts-extended = <&tlmm 124 IRQ_TYPE_EDGE_FALLING>; /* phy intr */ + device_type = "ethernet-phy"; + compatible = "ethernet-phy-ieee802.3-c22"; + }; + }; +}; + &uart2 { status = "okay"; }; @@ -407,4 +502,53 @@ drive-strength = <2>; }; }; + + ethernet_defaults: ethernet-defaults { + mdc { + pins = "gpio7"; + function = "rgmii"; + bias-pull-up; + }; + + mdio { + pins = "gpio59"; + function = "rgmii"; + bias-pull-up; + }; + + rgmii-rx { + pins = "gpio117", "gpio118", "gpio119", "gpio120", "gpio115", "gpio116"; + function = "rgmii"; + bias-disable; + drive-strength = <2>; + }; + + rgmii-tx { + pins = "gpio122", "gpio4", "gpio5", "gpio6", "gpio114", "gpio121"; + function = "rgmii"; + bias-pull-up; + drive-strength = <16>; + }; + + phy-intr { + pins = "gpio124"; + function = "emac_phy"; + bias-disable; + drive-strength = <8>; + }; + + pps { + pins = "gpio81"; + function = "emac_pps"; + bias-disable; + drive-strength = <8>; + }; + + phy-reset { + pins = "gpio79"; + function = "gpio"; + bias-pull-up; + drive-strength = <16>; + }; + }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index 6012322a5984..70cf4651598a 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -915,6 +915,33 @@ status = "disabled"; }; + ethernet: ethernet@20000 { + compatible = "qcom,sm8150-ethqos"; + reg = <0x0 0x00020000 0x0 0x10000>, + <0x0 0x00036000 0x0 0x100>; + reg-names = "stmmaceth", "rgmii"; + clock-names = "stmmaceth", "pclk", "ptp_ref", "rgmii"; + clocks = <&gcc GCC_EMAC_AXI_CLK>, + <&gcc GCC_EMAC_SLV_AHB_CLK>, + <&gcc GCC_EMAC_PTP_CLK>, + <&gcc GCC_EMAC_RGMII_CLK>; + interrupts = <GIC_SPI 689 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 699 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; + + power-domains = <&gcc EMAC_GDSC>; + resets = <&gcc GCC_EMAC_BCR>; + + iommus = <&apps_smmu 0x3C0 0x0>; + + snps,tso; + rx-fifo-depth = <4096>; + tx-fifo-depth = <4096>; + + status = "disabled"; + }; + + qupv3_id_0: geniqup@8c0000 { compatible = "qcom,geni-se-qup"; reg = <0x0 0x008c0000 0x0 0x6000>; @@ -1626,6 +1653,16 @@ interrupts = <GIC_SPI 582 IRQ_TYPE_LEVEL_HIGH>; }; + pdc: interrupt-controller@b220000 { + compatible = "qcom,sm8150-pdc", "qcom,pdc"; + reg = <0 0x0b220000 0 0x400>, <0 0x17c000f0 0 0x60>; + qcom,pdc-ranges = <0 480 94>, <94 609 31>, + <125 63 1>; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupt-controller; + }; + ufs_mem_hc: ufshc@1d84000 { compatible = "qcom,sm8150-ufshc", "qcom,ufshc", "jedec,ufs-2.0"; @@ -1637,6 +1674,8 @@ phy-names = "ufsphy"; lanes-per-direction = <2>; #reset-cells = <1>; + + power-domains = <&gcc UFS_PHY_GDSC>; resets = <&gcc GCC_UFS_PHY_BCR>; reset-names = "rst"; @@ -1687,6 +1726,9 @@ clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; + power-domains = <&gcc UFS_CARD_GDSC>, + <&gcc UFS_PHY_GDSC>; + power-domain-names = "ufs_card_gdsc", "ufs_phy_gdsc"; resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; status = "disabled"; @@ -1927,6 +1969,7 @@ #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; + wakeup-parent = <&pdc>; qup_i2c0_default: qup-i2c0-default { mux { diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h index 7be27862329f..78c6a5fde1d6 100644 --- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h @@ -223,6 +223,8 @@ static __always_inline void update_user_segments(u32 val) update_user_segment(15, val); } +int __init find_free_bat(void); +unsigned int bat_block_size(unsigned long base, unsigned long top); #endif /* !__ASSEMBLY__ */ /* We happily ignore the smaller BATs on 601, we don't actually use diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index a58fb4aa6c81..674e5aaafcbd 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -473,7 +473,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !(regs->msr & MSR_EE); } -static inline bool should_hard_irq_enable(void) +static __always_inline bool should_hard_irq_enable(void) { return false; } diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index efad07081cc0..9675303b724e 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -500,6 +500,7 @@ #define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LDBRX(r, base, b) (0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_STWCX(s, a, b) (0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_CMPWI(a, i) (0x2c000000 | ___PPC_RA(a) | IMM_L(i)) diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 52d05b465e3e..25fc8ad9a27a 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -90,7 +90,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long val, mask = -1UL; unsigned int n = 6; - if (is_32bit_task()) + if (is_tsk_32bit_task(task)) mask = 0xffffffff; while (n--) { @@ -105,7 +105,7 @@ static inline void syscall_get_arguments(struct task_struct *task, static inline int syscall_get_arch(struct task_struct *task) { - if (is_32bit_task()) + if (is_tsk_32bit_task(task)) return AUDIT_ARCH_PPC; else if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) return AUDIT_ARCH_PPC64LE; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 5725029aaa29..d6e649b3c70b 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -168,8 +168,10 @@ static inline bool test_thread_local_flags(unsigned int flags) #ifdef CONFIG_COMPAT #define is_32bit_task() (test_thread_flag(TIF_32BIT)) +#define is_tsk_32bit_task(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT)) #else #define is_32bit_task() (IS_ENABLED(CONFIG_PPC32)) +#define is_tsk_32bit_task(tsk) (IS_ENABLED(CONFIG_PPC32)) #endif #if defined(CONFIG_PPC64) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 92088f848266..7bab2d7de372 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -30,6 +30,7 @@ COMPAT_SYS_CALL_TABLE: .ifc \srr,srr mfspr r11,SPRN_SRR0 ld r12,_NIP(r1) + clrrdi r11,r11,2 clrrdi r12,r12,2 100: tdne r11,r12 EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) @@ -40,6 +41,7 @@ COMPAT_SYS_CALL_TABLE: .else mfspr r11,SPRN_HSRR0 ld r12,_NIP(r1) + clrrdi r11,r11,2 clrrdi r12,r12,2 100: tdne r11,r12 EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 94045b265b6b..203735caf691 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -76,7 +76,7 @@ unsigned long p_block_mapped(phys_addr_t pa) return 0; } -static int __init find_free_bat(void) +int __init find_free_bat(void) { int b; int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; @@ -100,7 +100,7 @@ static int __init find_free_bat(void) * - block size has to be a power of two. This is calculated by finding the * highest bit set to 1. */ -static unsigned int block_size(unsigned long base, unsigned long top) +unsigned int bat_block_size(unsigned long base, unsigned long top) { unsigned int max_size = SZ_256M; unsigned int base_shift = (ffs(base) - 1) & 31; @@ -145,7 +145,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to int idx; while ((idx = find_free_bat()) != -1 && base != top) { - unsigned int size = block_size(base, top); + unsigned int size = bat_block_size(base, top); if (size < 128 << 10) break; @@ -201,12 +201,12 @@ void mmu_mark_initmem_nx(void) unsigned long size; for (i = 0; i < nb - 1 && base < top;) { - size = block_size(base, top); + size = bat_block_size(base, top); setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT); base += size; } if (base < top) { - size = block_size(base, top); + size = bat_block_size(base, top); if ((top - base) > size) { size <<= 1; if (strict_kernel_rwx_enabled() && base + size > border) diff --git a/arch/powerpc/mm/kasan/book3s_32.c b/arch/powerpc/mm/kasan/book3s_32.c index 35b287b0a8da..450a67ef0bbe 100644 --- a/arch/powerpc/mm/kasan/book3s_32.c +++ b/arch/powerpc/mm/kasan/book3s_32.c @@ -10,48 +10,51 @@ int __init kasan_init_region(void *start, size_t size) { unsigned long k_start = (unsigned long)kasan_mem_to_shadow(start); unsigned long k_end = (unsigned long)kasan_mem_to_shadow(start + size); - unsigned long k_cur = k_start; - int k_size = k_end - k_start; - int k_size_base = 1 << (ffs(k_size) - 1); + unsigned long k_nobat = k_start; + unsigned long k_cur; + phys_addr_t phys; int ret; - void *block; - block = memblock_alloc(k_size, k_size_base); - - if (block && k_size_base >= SZ_128K && k_start == ALIGN(k_start, k_size_base)) { - int shift = ffs(k_size - k_size_base); - int k_size_more = shift ? 1 << (shift - 1) : 0; - - setbat(-1, k_start, __pa(block), k_size_base, PAGE_KERNEL); - if (k_size_more >= SZ_128K) - setbat(-1, k_start + k_size_base, __pa(block) + k_size_base, - k_size_more, PAGE_KERNEL); - if (v_block_mapped(k_start)) - k_cur = k_start + k_size_base; - if (v_block_mapped(k_start + k_size_base)) - k_cur = k_start + k_size_base + k_size_more; - - update_bats(); + while (k_nobat < k_end) { + unsigned int k_size = bat_block_size(k_nobat, k_end); + int idx = find_free_bat(); + + if (idx == -1) + break; + if (k_size < SZ_128K) + break; + phys = memblock_phys_alloc_range(k_size, k_size, 0, + MEMBLOCK_ALLOC_ANYWHERE); + if (!phys) + break; + + setbat(idx, k_nobat, phys, k_size, PAGE_KERNEL); + k_nobat += k_size; } + if (k_nobat != k_start) + update_bats(); - if (!block) - block = memblock_alloc(k_size, PAGE_SIZE); - if (!block) - return -ENOMEM; + if (k_nobat < k_end) { + phys = memblock_phys_alloc_range(k_end - k_nobat, PAGE_SIZE, 0, + MEMBLOCK_ALLOC_ANYWHERE); + if (!phys) + return -ENOMEM; + } ret = kasan_init_shadow_page_tables(k_start, k_end); if (ret) return ret; - kasan_update_early_region(k_start, k_cur, __pte(0)); + kasan_update_early_region(k_start, k_nobat, __pte(0)); - for (; k_cur < k_end; k_cur += PAGE_SIZE) { + for (k_cur = k_nobat; k_cur < k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_off_k(k_cur); - void *va = block + k_cur - k_start; - pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL); + pte_t pte = pfn_pte(PHYS_PFN(phys + k_cur - k_nobat), PAGE_KERNEL); __set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0); } flush_tlb_kernel_range(k_start, k_end); + memset(kasan_mem_to_shadow(start), 0, k_end - k_start); + return 0; } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index d6ffdd0f2309..56dd1f4e3e44 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -23,15 +23,15 @@ static void bpf_jit_fill_ill_insns(void *area, unsigned int size) memset32(area, BREAKPOINT_INSTRUCTION, size / 4); } -/* Fix the branch target addresses for subprog calls */ -static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image, - struct codegen_context *ctx, u32 *addrs) +/* Fix updated addresses (for subprog calls, ldimm64, et al) during extra pass */ +static int bpf_jit_fixup_addresses(struct bpf_prog *fp, u32 *image, + struct codegen_context *ctx, u32 *addrs) { const struct bpf_insn *insn = fp->insnsi; bool func_addr_fixed; u64 func_addr; u32 tmp_idx; - int i, ret; + int i, j, ret; for (i = 0; i < fp->len; i++) { /* @@ -66,6 +66,23 @@ static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image, * of the JITed sequence remains unchanged. */ ctx->idx = tmp_idx; + } else if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW)) { + tmp_idx = ctx->idx; + ctx->idx = addrs[i] / 4; +#ifdef CONFIG_PPC32 + PPC_LI32(ctx->b2p[insn[i].dst_reg] - 1, (u32)insn[i + 1].imm); + PPC_LI32(ctx->b2p[insn[i].dst_reg], (u32)insn[i].imm); + for (j = ctx->idx - addrs[i] / 4; j < 4; j++) + EMIT(PPC_RAW_NOP()); +#else + func_addr = ((u64)(u32)insn[i].imm) | (((u64)(u32)insn[i + 1].imm) << 32); + PPC_LI64(b2p[insn[i].dst_reg], func_addr); + /* overwrite rest with nops */ + for (j = ctx->idx - addrs[i] / 4; j < 5; j++) + EMIT(PPC_RAW_NOP()); +#endif + ctx->idx = tmp_idx; + i++; } } @@ -200,13 +217,13 @@ skip_init_ctx: /* * Do not touch the prologue and epilogue as they will remain * unchanged. Only fix the branch target address for subprog - * calls in the body. + * calls in the body, and ldimm64 instructions. * * This does not change the offsets and lengths of the subprog * call instruction sequences and hence, the size of the JITed * image as well. */ - bpf_jit_fixup_subprog_calls(fp, code_base, &cgctx, addrs); + bpf_jit_fixup_addresses(fp, code_base, &cgctx, addrs); /* There is no need to perform the usual passes. */ goto skip_codegen_passes; diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index faaebd446cad..cf8dd8aea386 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -191,6 +191,9 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun if (image && rel < 0x2000000 && rel >= -0x2000000) { PPC_BL_ABS(func); + EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_NOP()); } else { /* Load function address into r0 */ EMIT(PPC_RAW_LIS(_R0, IMM_H(func))); @@ -290,6 +293,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * bool func_addr_fixed; u64 func_addr; u32 true_cond; + u32 tmp_idx; + int j; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -905,8 +910,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * * 16 byte instruction that uses two 'struct bpf_insn' */ case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */ + tmp_idx = ctx->idx; PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm); PPC_LI32(dst_reg, (u32)insn[i].imm); + /* padding to allow full 4 instructions for later patching */ + for (j = ctx->idx - tmp_idx; j < 4; j++) + EMIT(PPC_RAW_NOP()); /* Adjust for two bpf instructions */ addrs[++i] = ctx->idx * 4; break; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 9eae8d8ed340..e1e8c934308a 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -319,6 +319,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * u64 imm64; u32 true_cond; u32 tmp_idx; + int j; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -633,17 +634,21 @@ bpf_alu32_trunc: EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); break; case 64: - /* - * Way easier and faster(?) to store the value - * into stack and then use ldbrx - * - * ctx->seen will be reliable in pass2, but - * the instructions generated will remain the - * same across all passes - */ + /* Store the value to stack and then use byte-reverse loads */ PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx))); - EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + } else { + EMIT(PPC_RAW_LWBRX(dst_reg, 0, b2p[TMP_REG_1])); + if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) + EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, 32)); + EMIT(PPC_RAW_LI(b2p[TMP_REG_2], 4)); + EMIT(PPC_RAW_LWBRX(b2p[TMP_REG_2], b2p[TMP_REG_2], b2p[TMP_REG_1])); + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + EMIT(PPC_RAW_SLDI(b2p[TMP_REG_2], b2p[TMP_REG_2], 32)); + EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_2])); + } break; } break; @@ -848,9 +853,13 @@ emit_clear: case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */ imm64 = ((u64)(u32) insn[i].imm) | (((u64)(u32) insn[i+1].imm) << 32); + tmp_idx = ctx->idx; + PPC_LI64(dst_reg, imm64); + /* padding to allow full 5 instructions for later patching */ + for (j = ctx->idx - tmp_idx; j < 5; j++) + EMIT(PPC_RAW_NOP()); /* Adjust for two bpf instructions */ addrs[++i] = ctx->idx * 4; - PPC_LI64(dst_reg, imm64); break; /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index a684901b6965..32b98b7a1f86 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -776,6 +776,34 @@ static void pmao_restore_workaround(bool ebb) mtspr(SPRN_PMC6, pmcs[5]); } +/* + * If the perf subsystem wants performance monitor interrupts as soon as + * possible (e.g., to sample the instruction address and stack chain), + * this should return true. The IRQ masking code can then enable MSR[EE] + * in some places (e.g., interrupt handlers) that allows PMI interrupts + * through to improve accuracy of profiles, at the cost of some performance. + * + * The PMU counters can be enabled by other means (e.g., sysfs raw SPR + * access), but in that case there is no need for prompt PMI handling. + * + * This currently returns true if any perf counter is being used. It + * could possibly return false if only events are being counted rather than + * samples being taken, but for now this is good enough. + */ +bool power_pmu_wants_prompt_pmi(void) +{ + struct cpu_hw_events *cpuhw; + + /* + * This could simply test local_paca->pmcregs_in_use if that were not + * under ifdef KVM. + */ + if (!ppmu) + return false; + + cpuhw = this_cpu_ptr(&cpu_hw_events); + return cpuhw->n_events; +} #endif /* CONFIG_PPC64 */ static void perf_event_interrupt(struct pt_regs *regs); @@ -2438,36 +2466,6 @@ static void perf_event_interrupt(struct pt_regs *regs) perf_sample_event_took(sched_clock() - start_clock); } -/* - * If the perf subsystem wants performance monitor interrupts as soon as - * possible (e.g., to sample the instruction address and stack chain), - * this should return true. The IRQ masking code can then enable MSR[EE] - * in some places (e.g., interrupt handlers) that allows PMI interrupts - * though to improve accuracy of profiles, at the cost of some performance. - * - * The PMU counters can be enabled by other means (e.g., sysfs raw SPR - * access), but in that case there is no need for prompt PMI handling. - * - * This currently returns true if any perf counter is being used. It - * could possibly return false if only events are being counted rather than - * samples being taken, but for now this is good enough. - */ -bool power_pmu_wants_prompt_pmi(void) -{ - struct cpu_hw_events *cpuhw; - - /* - * This could simply test local_paca->pmcregs_in_use if that were not - * under ifdef KVM. - */ - - if (!ppmu) - return false; - - cpuhw = this_cpu_ptr(&cpu_hw_events); - return cpuhw->n_events; -} - static int power_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fd9f908debe5..c91434056c29 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6236,6 +6236,19 @@ __init int intel_pmu_init(void) pmu->num_counters = x86_pmu.num_counters; pmu->num_counters_fixed = x86_pmu.num_counters_fixed; } + + /* + * Quirk: For some Alder Lake machine, when all E-cores are disabled in + * a BIOS, the leaf 0xA will enumerate all counters of P-cores. However, + * the X86_FEATURE_HYBRID_CPU is still set. The above codes will + * mistakenly add extra counters for P-cores. Correct the number of + * counters here. + */ + if ((pmu->num_counters > 8) || (pmu->num_counters_fixed > 4)) { + pmu->num_counters = x86_pmu.num_counters; + pmu->num_counters_fixed = x86_pmu.num_counters_fixed; + } + pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters); pmu->unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, @@ -6340,6 +6353,8 @@ __init int intel_pmu_init(void) } if (x86_pmu.lbr_nr) { + intel_pmu_lbr_init(); + pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); /* only support branch_stack snapshot for perfmon >= v2 */ diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 8043213b75a5..669c2be14784 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -8,14 +8,6 @@ #include "../perf_event.h" -static const enum { - LBR_EIP_FLAGS = 1, - LBR_TSX = 2, -} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { - [LBR_FORMAT_EIP_FLAGS] = LBR_EIP_FLAGS, - [LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX, -}; - /* * Intel LBR_SELECT bits * Intel Vol3a, April 2011, Section 16.7 Table 16-10 @@ -243,7 +235,7 @@ void intel_pmu_lbr_reset_64(void) for (i = 0; i < x86_pmu.lbr_nr; i++) { wrmsrl(x86_pmu.lbr_from + i, 0); wrmsrl(x86_pmu.lbr_to + i, 0); - if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + if (x86_pmu.lbr_has_info) wrmsrl(x86_pmu.lbr_info + i, 0); } } @@ -305,11 +297,10 @@ enum { */ static inline bool lbr_from_signext_quirk_needed(void) { - int lbr_format = x86_pmu.intel_cap.lbr_format; bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM); - return !tsx_support && (lbr_desc[lbr_format] & LBR_TSX); + return !tsx_support && x86_pmu.lbr_has_tsx; } static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key); @@ -427,12 +418,12 @@ rdlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info) void intel_pmu_lbr_restore(void *ctx) { - bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx = ctx; - int i; - unsigned lbr_idx, mask; + bool need_info = x86_pmu.lbr_has_info; u64 tos = task_ctx->tos; + unsigned lbr_idx, mask; + int i; mask = x86_pmu.lbr_nr - 1; for (i = 0; i < task_ctx->valid_lbrs; i++) { @@ -444,7 +435,7 @@ void intel_pmu_lbr_restore(void *ctx) lbr_idx = (tos - i) & mask; wrlbr_from(lbr_idx, 0); wrlbr_to(lbr_idx, 0); - if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + if (need_info) wrlbr_info(lbr_idx, 0); } @@ -519,9 +510,9 @@ static void __intel_pmu_lbr_restore(void *ctx) void intel_pmu_lbr_save(void *ctx) { - bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx = ctx; + bool need_info = x86_pmu.lbr_has_info; unsigned lbr_idx, mask; u64 tos; int i; @@ -816,7 +807,6 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { bool need_info = false, call_stack = false; unsigned long mask = x86_pmu.lbr_nr - 1; - int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); int i; int out = 0; @@ -831,9 +821,7 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0; - int skip = 0; u16 cycles = 0; - int lbr_flags = lbr_desc[lbr_format]; from = rdlbr_from(lbr_idx, NULL); to = rdlbr_to(lbr_idx, NULL); @@ -845,37 +833,39 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) if (call_stack && !from) break; - if (lbr_format == LBR_FORMAT_INFO && need_info) { - u64 info; - - info = rdlbr_info(lbr_idx, NULL); - mis = !!(info & LBR_INFO_MISPRED); - pred = !mis; - in_tx = !!(info & LBR_INFO_IN_TX); - abort = !!(info & LBR_INFO_ABORT); - cycles = (info & LBR_INFO_CYCLES); - } - - if (lbr_format == LBR_FORMAT_TIME) { - mis = !!(from & LBR_FROM_FLAG_MISPRED); - pred = !mis; - skip = 1; - cycles = ((to >> 48) & LBR_INFO_CYCLES); - - to = (u64)((((s64)to) << 16) >> 16); - } - - if (lbr_flags & LBR_EIP_FLAGS) { - mis = !!(from & LBR_FROM_FLAG_MISPRED); - pred = !mis; - skip = 1; - } - if (lbr_flags & LBR_TSX) { - in_tx = !!(from & LBR_FROM_FLAG_IN_TX); - abort = !!(from & LBR_FROM_FLAG_ABORT); - skip = 3; + if (x86_pmu.lbr_has_info) { + if (need_info) { + u64 info; + + info = rdlbr_info(lbr_idx, NULL); + mis = !!(info & LBR_INFO_MISPRED); + pred = !mis; + cycles = (info & LBR_INFO_CYCLES); + if (x86_pmu.lbr_has_tsx) { + in_tx = !!(info & LBR_INFO_IN_TX); + abort = !!(info & LBR_INFO_ABORT); + } + } + } else { + int skip = 0; + + if (x86_pmu.lbr_from_flags) { + mis = !!(from & LBR_FROM_FLAG_MISPRED); + pred = !mis; + skip = 1; + } + if (x86_pmu.lbr_has_tsx) { + in_tx = !!(from & LBR_FROM_FLAG_IN_TX); + abort = !!(from & LBR_FROM_FLAG_ABORT); + skip = 3; + } + from = (u64)((((s64)from) << skip) >> skip); + + if (x86_pmu.lbr_to_cycles) { + cycles = ((to >> 48) & LBR_INFO_CYCLES); + to = (u64)((((s64)to) << 16) >> 16); + } } - from = (u64)((((s64)from) << skip) >> skip); /* * Some CPUs report duplicated abort records, @@ -903,37 +893,40 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_stack.hw_idx = tos; } +static DEFINE_STATIC_KEY_FALSE(x86_lbr_mispred); +static DEFINE_STATIC_KEY_FALSE(x86_lbr_cycles); +static DEFINE_STATIC_KEY_FALSE(x86_lbr_type); + static __always_inline int get_lbr_br_type(u64 info) { - if (!static_cpu_has(X86_FEATURE_ARCH_LBR) || !x86_pmu.lbr_br_type) - return 0; + int type = 0; - return (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET; + if (static_branch_likely(&x86_lbr_type)) + type = (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET; + + return type; } static __always_inline bool get_lbr_mispred(u64 info) { - if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred) - return 0; + bool mispred = 0; - return !!(info & LBR_INFO_MISPRED); -} + if (static_branch_likely(&x86_lbr_mispred)) + mispred = !!(info & LBR_INFO_MISPRED); -static __always_inline bool get_lbr_predicted(u64 info) -{ - if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred) - return 0; - - return !(info & LBR_INFO_MISPRED); + return mispred; } static __always_inline u16 get_lbr_cycles(u64 info) { + u16 cycles = info & LBR_INFO_CYCLES; + if (static_cpu_has(X86_FEATURE_ARCH_LBR) && - !(x86_pmu.lbr_timed_lbr && info & LBR_INFO_CYC_CNT_VALID)) - return 0; + (!static_branch_likely(&x86_lbr_cycles) || + !(info & LBR_INFO_CYC_CNT_VALID))) + cycles = 0; - return info & LBR_INFO_CYCLES; + return cycles; } static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, @@ -961,7 +954,7 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, e->from = from; e->to = to; e->mispred = get_lbr_mispred(info); - e->predicted = get_lbr_predicted(info); + e->predicted = !e->mispred; e->in_tx = !!(info & LBR_INFO_IN_TX); e->abort = !!(info & LBR_INFO_ABORT); e->cycles = get_lbr_cycles(info); @@ -1120,7 +1113,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && - (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)) + x86_pmu.lbr_has_info) reg->config |= LBR_NO_INFO; return 0; @@ -1706,6 +1699,38 @@ void intel_pmu_lbr_init_knl(void) x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS; } +void intel_pmu_lbr_init(void) +{ + switch (x86_pmu.intel_cap.lbr_format) { + case LBR_FORMAT_EIP_FLAGS2: + x86_pmu.lbr_has_tsx = 1; + fallthrough; + case LBR_FORMAT_EIP_FLAGS: + x86_pmu.lbr_from_flags = 1; + break; + + case LBR_FORMAT_INFO: + x86_pmu.lbr_has_tsx = 1; + fallthrough; + case LBR_FORMAT_INFO2: + x86_pmu.lbr_has_info = 1; + break; + + case LBR_FORMAT_TIME: + x86_pmu.lbr_from_flags = 1; + x86_pmu.lbr_to_cycles = 1; + break; + } + + if (x86_pmu.lbr_has_info) { + /* + * Only used in combination with baseline pebs. + */ + static_branch_enable(&x86_lbr_mispred); + static_branch_enable(&x86_lbr_cycles); + } +} + /* * LBR state size is variable based on the max number of registers. * This calculates the expected state size, which should match @@ -1726,6 +1751,9 @@ static bool is_arch_lbr_xsave_available(void) * Check the LBR state with the corresponding software structure. * Disable LBR XSAVES support if the size doesn't match. */ + if (xfeature_size(XFEATURE_LBR) == 0) + return false; + if (WARN_ON(xfeature_size(XFEATURE_LBR) != get_lbr_state_size())) return false; @@ -1765,6 +1793,12 @@ void __init intel_pmu_arch_lbr_init(void) x86_pmu.lbr_br_type = ecx.split.lbr_br_type; x86_pmu.lbr_nr = lbr_nr; + if (x86_pmu.lbr_mispred) + static_branch_enable(&x86_lbr_mispred); + if (x86_pmu.lbr_timed_lbr) + static_branch_enable(&x86_lbr_cycles); + if (x86_pmu.lbr_br_type) + static_branch_enable(&x86_lbr_type); arch_lbr_xsave = is_arch_lbr_xsave_available(); if (arch_lbr_xsave) { diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index f1ba6ab2e97e..e497da9bf427 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1762,7 +1762,7 @@ static const struct intel_uncore_init_fun rkl_uncore_init __initconst = { static const struct intel_uncore_init_fun adl_uncore_init __initconst = { .cpu_init = adl_uncore_cpu_init, - .mmio_init = tgl_uncore_mmio_init, + .mmio_init = adl_uncore_mmio_init, }; static const struct intel_uncore_init_fun icx_uncore_init __initconst = { diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index b9687980aab6..2adeaf4de4df 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -584,10 +584,11 @@ void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); void icl_uncore_cpu_init(void); -void adl_uncore_cpu_init(void); void tgl_uncore_cpu_init(void); +void adl_uncore_cpu_init(void); void tgl_uncore_mmio_init(void); void tgl_l_uncore_mmio_init(void); +void adl_uncore_mmio_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c index 3049c646fa20..6ddadb482f68 100644 --- a/arch/x86/events/intel/uncore_discovery.c +++ b/arch/x86/events/intel/uncore_discovery.c @@ -494,8 +494,8 @@ void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box) writel(0, box->io_addr); } -static void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, - struct perf_event *event) +void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, + struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h index 6d735611c281..cfaf558bdb6b 100644 --- a/arch/x86/events/intel/uncore_discovery.h +++ b/arch/x86/events/intel/uncore_discovery.h @@ -139,6 +139,8 @@ void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box); void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box); void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box, struct perf_event *event); +void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, + struct perf_event *event); void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box); void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 0f63706cdadf..f698a55bde81 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Nehalem/SandBridge/Haswell/Broadwell/Skylake uncore support */ #include "uncore.h" +#include "uncore_discovery.h" /* Uncore IMC PCI IDs */ #define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100 @@ -64,6 +65,20 @@ #define PCI_DEVICE_ID_INTEL_RKL_2_IMC 0x4c53 #define PCI_DEVICE_ID_INTEL_ADL_1_IMC 0x4660 #define PCI_DEVICE_ID_INTEL_ADL_2_IMC 0x4641 +#define PCI_DEVICE_ID_INTEL_ADL_3_IMC 0x4601 +#define PCI_DEVICE_ID_INTEL_ADL_4_IMC 0x4602 +#define PCI_DEVICE_ID_INTEL_ADL_5_IMC 0x4609 +#define PCI_DEVICE_ID_INTEL_ADL_6_IMC 0x460a +#define PCI_DEVICE_ID_INTEL_ADL_7_IMC 0x4621 +#define PCI_DEVICE_ID_INTEL_ADL_8_IMC 0x4623 +#define PCI_DEVICE_ID_INTEL_ADL_9_IMC 0x4629 +#define PCI_DEVICE_ID_INTEL_ADL_10_IMC 0x4637 +#define PCI_DEVICE_ID_INTEL_ADL_11_IMC 0x463b +#define PCI_DEVICE_ID_INTEL_ADL_12_IMC 0x4648 +#define PCI_DEVICE_ID_INTEL_ADL_13_IMC 0x4649 +#define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 +#define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 +#define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -155,6 +170,7 @@ DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(chmask, chmask, "config:8-11"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); @@ -1334,6 +1350,62 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_2_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_5_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_6_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_7_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_8_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_9_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_10_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_11_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_12_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_13_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_14_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_15_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; @@ -1390,7 +1462,8 @@ static struct pci_dev *tgl_uncore_get_mc_dev(void) #define TGL_UNCORE_MMIO_IMC_MEM_OFFSET 0x10000 #define TGL_UNCORE_PCI_IMC_MAP_SIZE 0xe000 -static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +static void __uncore_imc_init_box(struct intel_uncore_box *box, + unsigned int base_offset) { struct pci_dev *pdev = tgl_uncore_get_mc_dev(); struct intel_uncore_pmu *pmu = box->pmu; @@ -1417,11 +1490,17 @@ static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) addr |= ((resource_size_t)mch_bar << 32); #endif + addr += base_offset; box->io_addr = ioremap(addr, type->mmio_map_size); if (!box->io_addr) pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name); } +static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, 0); +} + static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = { .init_box = tgl_uncore_imc_freerunning_init_box, .exit_box = uncore_mmio_exit_box, @@ -1469,3 +1548,136 @@ void tgl_uncore_mmio_init(void) } /* end of Tiger Lake MMIO uncore support */ + +/* Alder Lake MMIO uncore support */ +#define ADL_UNCORE_IMC_BASE 0xd900 +#define ADL_UNCORE_IMC_MAP_SIZE 0x200 +#define ADL_UNCORE_IMC_CTR 0xe8 +#define ADL_UNCORE_IMC_CTRL 0xd0 +#define ADL_UNCORE_IMC_GLOBAL_CTL 0xc0 +#define ADL_UNCORE_IMC_BOX_CTL 0xc4 +#define ADL_UNCORE_IMC_FREERUNNING_BASE 0xd800 +#define ADL_UNCORE_IMC_FREERUNNING_MAP_SIZE 0x100 + +#define ADL_UNCORE_IMC_CTL_FRZ (1 << 0) +#define ADL_UNCORE_IMC_CTL_RST_CTRL (1 << 1) +#define ADL_UNCORE_IMC_CTL_RST_CTRS (1 << 2) +#define ADL_UNCORE_IMC_CTL_INT (ADL_UNCORE_IMC_CTL_RST_CTRL | \ + ADL_UNCORE_IMC_CTL_RST_CTRS) + +static void adl_uncore_imc_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, ADL_UNCORE_IMC_BASE); + + /* The global control in MC1 can control both MCs. */ + if (box->io_addr && (box->pmu->pmu_idx == 1)) + writel(ADL_UNCORE_IMC_CTL_INT, box->io_addr + ADL_UNCORE_IMC_GLOBAL_CTL); +} + +static void adl_uncore_mmio_disable_box(struct intel_uncore_box *box) +{ + if (!box->io_addr) + return; + + writel(ADL_UNCORE_IMC_CTL_FRZ, box->io_addr + uncore_mmio_box_ctl(box)); +} + +static void adl_uncore_mmio_enable_box(struct intel_uncore_box *box) +{ + if (!box->io_addr) + return; + + writel(0, box->io_addr + uncore_mmio_box_ctl(box)); +} + +static struct intel_uncore_ops adl_uncore_mmio_ops = { + .init_box = adl_uncore_imc_init_box, + .exit_box = uncore_mmio_exit_box, + .disable_box = adl_uncore_mmio_disable_box, + .enable_box = adl_uncore_mmio_enable_box, + .disable_event = intel_generic_uncore_mmio_disable_event, + .enable_event = intel_generic_uncore_mmio_enable_event, + .read_counter = uncore_mmio_read_counter, +}; + +#define ADL_UNC_CTL_CHMASK_MASK 0x00000f00 +#define ADL_UNC_IMC_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + ADL_UNC_CTL_CHMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET) + +static struct attribute *adl_uncore_imc_formats_attr[] = { + &format_attr_event.attr, + &format_attr_chmask.attr, + &format_attr_edge.attr, + NULL, +}; + +static const struct attribute_group adl_uncore_imc_format_group = { + .name = "format", + .attrs = adl_uncore_imc_formats_attr, +}; + +static struct intel_uncore_type adl_uncore_imc = { + .name = "imc", + .num_counters = 5, + .num_boxes = 2, + .perf_ctr_bits = 64, + .perf_ctr = ADL_UNCORE_IMC_CTR, + .event_ctl = ADL_UNCORE_IMC_CTRL, + .event_mask = ADL_UNC_IMC_EVENT_MASK, + .box_ctl = ADL_UNCORE_IMC_BOX_CTL, + .mmio_offset = 0, + .mmio_map_size = ADL_UNCORE_IMC_MAP_SIZE, + .ops = &adl_uncore_mmio_ops, + .format_group = &adl_uncore_imc_format_group, +}; + +enum perf_adl_uncore_imc_freerunning_types { + ADL_MMIO_UNCORE_IMC_DATA_TOTAL, + ADL_MMIO_UNCORE_IMC_DATA_READ, + ADL_MMIO_UNCORE_IMC_DATA_WRITE, + ADL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX +}; + +static struct freerunning_counters adl_uncore_imc_freerunning[] = { + [ADL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0x40, 0x0, 0x0, 1, 64 }, + [ADL_MMIO_UNCORE_IMC_DATA_READ] = { 0x58, 0x0, 0x0, 1, 64 }, + [ADL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0xA0, 0x0, 0x0, 1, 64 }, +}; + +static void adl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, ADL_UNCORE_IMC_FREERUNNING_BASE); +} + +static struct intel_uncore_ops adl_uncore_imc_freerunning_ops = { + .init_box = adl_uncore_imc_freerunning_init_box, + .exit_box = uncore_mmio_exit_box, + .read_counter = uncore_mmio_read_counter, + .hw_config = uncore_freerunning_hw_config, +}; + +static struct intel_uncore_type adl_uncore_imc_free_running = { + .name = "imc_free_running", + .num_counters = 3, + .num_boxes = 2, + .num_freerunning_types = ADL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX, + .mmio_map_size = ADL_UNCORE_IMC_FREERUNNING_MAP_SIZE, + .freerunning = adl_uncore_imc_freerunning, + .ops = &adl_uncore_imc_freerunning_ops, + .event_descs = tgl_uncore_imc_events, + .format_group = &tgl_uncore_imc_format_group, +}; + +static struct intel_uncore_type *adl_mmio_uncores[] = { + &adl_uncore_imc, + &adl_uncore_imc_free_running, + NULL +}; + +void adl_uncore_mmio_init(void) +{ + uncore_mmio_uncores = adl_mmio_uncores; +} + +/* end of Alder Lake MMIO uncore support */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 3660f698fb2a..ed869443efb2 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -5482,7 +5482,7 @@ static struct intel_uncore_type icx_uncore_imc = { .fixed_ctr_bits = 48, .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, - .event_descs = hswep_uncore_imc_events, + .event_descs = snr_uncore_imc_events, .perf_ctr = SNR_IMC_MMIO_PMON_CTR0, .event_ctl = SNR_IMC_MMIO_PMON_CTL0, .event_mask = SNBEP_PMON_RAW_EVENT_MASK, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 9d376e528dfc..150261d929b9 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -215,7 +215,8 @@ enum { LBR_FORMAT_EIP_FLAGS2 = 0x04, LBR_FORMAT_INFO = 0x05, LBR_FORMAT_TIME = 0x06, - LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME, + LBR_FORMAT_INFO2 = 0x07, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO2, }; enum { @@ -840,6 +841,11 @@ struct x86_pmu { bool lbr_double_abort; /* duplicated lbr aborts */ bool lbr_pt_coexist; /* (LBR|BTS) may coexist with PT */ + unsigned int lbr_has_info:1; + unsigned int lbr_has_tsx:1; + unsigned int lbr_from_flags:1; + unsigned int lbr_to_cycles:1; + /* * Intel Architectural LBR CPUID Enumeration */ @@ -1392,6 +1398,8 @@ void intel_pmu_lbr_init_skl(void); void intel_pmu_lbr_init_knl(void); +void intel_pmu_lbr_init(void); + void intel_pmu_arch_lbr_init(void); void intel_pmu_pebs_data_source_nhm(void); diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 85feafacc445..77e3a47af5ad 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -536,11 +536,14 @@ static struct perf_msr intel_rapl_spr_msrs[] = { * - perf_msr_probe(PERF_RAPL_MAX) * - want to use same event codes across both architectures */ -static struct perf_msr amd_rapl_msrs[PERF_RAPL_MAX] = { - [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr }, +static struct perf_msr amd_rapl_msrs[] = { + [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, 0, false, 0 }, + [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, 0, false, 0 }, + [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, 0, false, 0 }, + [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, 0, false, 0 }, }; - static int rapl_cpu_offline(unsigned int cpu) { struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); diff --git a/drivers/clk/qcom/gcc-sm8150.c b/drivers/clk/qcom/gcc-sm8150.c index 245794485719..fd7e931d3c09 100644 --- a/drivers/clk/qcom/gcc-sm8150.c +++ b/drivers/clk/qcom/gcc-sm8150.c @@ -5,6 +5,7 @@ #include <linux/bitops.h> #include <linux/err.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_device.h> @@ -3448,22 +3449,71 @@ static struct clk_branch gcc_video_xo_clk = { }, }; +/* To Do: EMAC GDSC currently has issues when its turn'ed ON, once + * its already in OFF state. So use PWRSTS_ON state (only) as a + * workaround for now. + */ +static struct gdsc emac_gdsc = { + .gdscr = 0x6004, + .pd = { + .name = "emac_gdsc", + }, + .pwrsts = PWRSTS_ON, + .flags = POLL_CFG_GDSCR, +}; + +static struct gdsc pcie_0_gdsc = { + .gdscr = 0x6b004, + .pd = { + .name = "pcie_0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR, +}; + +static struct gdsc pcie_1_gdsc = { + .gdscr = 0x8d004, + .pd = { + .name = "pcie_1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR, +}; + +static struct gdsc ufs_card_gdsc = { + .gdscr = 0x75004, + .pd = { + .name = "ufs_card_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR, +}; + +static struct gdsc ufs_phy_gdsc = { + .gdscr = 0x77004, + .pd = { + .name = "ufs_phy_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR, +}; + static struct gdsc usb30_prim_gdsc = { - .gdscr = 0xf004, - .pd = { - .name = "usb30_prim_gdsc", - }, - .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .gdscr = 0xf004, + .pd = { + .name = "usb30_prim_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR, }; static struct gdsc usb30_sec_gdsc = { - .gdscr = 0x10004, - .pd = { - .name = "usb30_sec_gdsc", - }, - .pwrsts = PWRSTS_OFF_ON, - .flags = POLL_CFG_GDSCR, + .gdscr = 0x10004, + .pd = { + .name = "usb30_sec_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = POLL_CFG_GDSCR, }; static struct clk_regmap *gcc_sm8150_clocks[] = { @@ -3714,6 +3764,11 @@ static const struct qcom_reset_map gcc_sm8150_resets[] = { }; static struct gdsc *gcc_sm8150_gdscs[] = { + [EMAC_GDSC] = &emac_gdsc, + [PCIE_0_GDSC] = &pcie_0_gdsc, + [PCIE_1_GDSC] = &pcie_1_gdsc, + [UFS_CARD_GDSC] = &ufs_card_gdsc, + [UFS_PHY_GDSC] = &ufs_phy_gdsc, [USB30_PRIM_GDSC] = &usb30_prim_gdsc, [USB30_SEC_GDSC] = &usb30_sec_gdsc, }; @@ -3742,19 +3797,41 @@ static const struct of_device_id gcc_sm8150_match_table[] = { }; MODULE_DEVICE_TABLE(of, gcc_sm8150_match_table); +static void gcc_sm8150_pm_runtime_disable(void *data) +{ + pm_runtime_disable(data); +} + static int gcc_sm8150_probe(struct platform_device *pdev) { struct regmap *regmap; + int ret; + + pm_runtime_enable(&pdev->dev); + + ret = devm_add_action_or_reset(&pdev->dev, gcc_sm8150_pm_runtime_disable, &pdev->dev); + if (ret) + return ret; + + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) + return ret; regmap = qcom_cc_map(pdev, &gcc_sm8150_desc); - if (IS_ERR(regmap)) + if (IS_ERR(regmap)) { + pm_runtime_put(&pdev->dev); return PTR_ERR(regmap); + } /* Disable the GPLL0 active input to NPU and GPU via MISC registers */ regmap_update_bits(regmap, 0x4d110, 0x3, 0x3); regmap_update_bits(regmap, 0x71028, 0x3, 0x3); - return qcom_cc_really_probe(pdev, &gcc_sm8150_desc, regmap); + ret = qcom_cc_really_probe(pdev, &gcc_sm8150_desc, regmap); + + pm_runtime_put(&pdev->dev); + + return ret; } static struct platform_driver gcc_sm8150_driver = { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 4b4829eb16c2..0dd107dcecc2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -311,6 +311,7 @@ struct drm_i915_gem_object { #define I915_BO_READONLY BIT(6) #define I915_TILING_QUIRK_BIT 7 /* unknown swizzling; do not release! */ #define I915_BO_PROTECTED BIT(8) +#define I915_BO_WAS_BOUND_BIT 9 /** * @mem_flags - Mutable placement-related flags * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 9f429ed6e78a..a50f884973bc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -10,6 +10,8 @@ #include "i915_gem_lmem.h" #include "i915_gem_mman.h" +#include "gt/intel_gt.h" + void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, struct sg_table *pages, unsigned int sg_page_sizes) @@ -221,6 +223,14 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj) __i915_gem_object_reset_page_iter(obj); obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0; + if (test_and_clear_bit(I915_BO_WAS_BOUND_BIT, &obj->flags)) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); + intel_wakeref_t wakeref; + + with_intel_runtime_pm_if_active(&i915->runtime_pm, wakeref) + intel_gt_invalidate_tlbs(to_gt(i915)); + } + return pages; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index f98f0fb21efb..35d0fcd3a86c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -29,6 +29,8 @@ void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) { spin_lock_init(>->irq_lock); + mutex_init(>->tlb_invalidate_lock); + INIT_LIST_HEAD(>->closed_vma); spin_lock_init(>->closed_lock); @@ -912,3 +914,109 @@ void intel_gt_info_print(const struct intel_gt_info *info, intel_sseu_dump(&info->sseu, p); } + +struct reg_and_bit { + i915_reg_t reg; + u32 bit; +}; + +static struct reg_and_bit +get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8, + const i915_reg_t *regs, const unsigned int num) +{ + const unsigned int class = engine->class; + struct reg_and_bit rb = { }; + + if (drm_WARN_ON_ONCE(&engine->i915->drm, + class >= num || !regs[class].reg)) + return rb; + + rb.reg = regs[class]; + if (gen8 && class == VIDEO_DECODE_CLASS) + rb.reg.reg += 4 * engine->instance; /* GEN8_M2TCR */ + else + rb.bit = engine->instance; + + rb.bit = BIT(rb.bit); + + return rb; +} + +void intel_gt_invalidate_tlbs(struct intel_gt *gt) +{ + static const i915_reg_t gen8_regs[] = { + [RENDER_CLASS] = GEN8_RTCR, + [VIDEO_DECODE_CLASS] = GEN8_M1TCR, /* , GEN8_M2TCR */ + [VIDEO_ENHANCEMENT_CLASS] = GEN8_VTCR, + [COPY_ENGINE_CLASS] = GEN8_BTCR, + }; + static const i915_reg_t gen12_regs[] = { + [RENDER_CLASS] = GEN12_GFX_TLB_INV_CR, + [VIDEO_DECODE_CLASS] = GEN12_VD_TLB_INV_CR, + [VIDEO_ENHANCEMENT_CLASS] = GEN12_VE_TLB_INV_CR, + [COPY_ENGINE_CLASS] = GEN12_BLT_TLB_INV_CR, + }; + struct drm_i915_private *i915 = gt->i915; + struct intel_uncore *uncore = gt->uncore; + struct intel_engine_cs *engine; + enum intel_engine_id id; + const i915_reg_t *regs; + unsigned int num = 0; + + if (I915_SELFTEST_ONLY(gt->awake == -ENODEV)) + return; + + if (GRAPHICS_VER(i915) == 12) { + regs = gen12_regs; + num = ARRAY_SIZE(gen12_regs); + } else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) { + regs = gen8_regs; + num = ARRAY_SIZE(gen8_regs); + } else if (GRAPHICS_VER(i915) < 8) { + return; + } + + if (drm_WARN_ONCE(&i915->drm, !num, + "Platform does not implement TLB invalidation!")) + return; + + GEM_TRACE("\n"); + + assert_rpm_wakelock_held(&i915->runtime_pm); + + mutex_lock(>->tlb_invalidate_lock); + intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); + + for_each_engine(engine, gt, id) { + /* + * HW architecture suggest typical invalidation time at 40us, + * with pessimistic cases up to 100us and a recommendation to + * cap at 1ms. We go a bit higher just in case. + */ + const unsigned int timeout_us = 100; + const unsigned int timeout_ms = 4; + struct reg_and_bit rb; + + rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); + if (!i915_mmio_reg_offset(rb.reg)) + continue; + + intel_uncore_write_fw(uncore, rb.reg, rb.bit); + if (__intel_wait_for_register_fw(uncore, + rb.reg, rb.bit, 0, + timeout_us, timeout_ms, + NULL)) + drm_err_ratelimited(>->i915->drm, + "%s TLB invalidation did not complete in %ums!\n", + engine->name, timeout_ms); + } + + /* + * Use delayed put since a) we mostly expect a flurry of TLB + * invalidations so it is good to avoid paying the forcewake cost and + * b) it works around a bug in Icelake which cannot cope with too rapid + * transitions. + */ + intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL); + mutex_unlock(>->tlb_invalidate_lock); +} diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 3ace129eb2af..a913fb6ffec3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -91,4 +91,6 @@ void intel_gt_info_print(const struct intel_gt_info *info, void intel_gt_watchdog_work(struct work_struct *work); +void intel_gt_invalidate_tlbs(struct intel_gt *gt); + #endif /* __INTEL_GT_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index 14216cc471b1..f20687796490 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -73,6 +73,8 @@ struct intel_gt { struct intel_uc uc; + struct mutex tlb_invalidate_lock; + struct i915_wa_list wa_list; struct intel_gt_timelines { diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 971d601fe751..c32420cb8ed5 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2721,6 +2721,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING (1 << 28) #define GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT (1 << 24) +#define GEN8_RTCR _MMIO(0x4260) +#define GEN8_M1TCR _MMIO(0x4264) +#define GEN8_M2TCR _MMIO(0x4268) +#define GEN8_BTCR _MMIO(0x426c) +#define GEN8_VTCR _MMIO(0x4270) + #if 0 #define PRB0_TAIL _MMIO(0x2030) #define PRB0_HEAD _MMIO(0x2034) @@ -2819,6 +2825,11 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define FAULT_VA_HIGH_BITS (0xf << 0) #define FAULT_GTT_SEL (1 << 4) +#define GEN12_GFX_TLB_INV_CR _MMIO(0xced8) +#define GEN12_VD_TLB_INV_CR _MMIO(0xcedc) +#define GEN12_VE_TLB_INV_CR _MMIO(0xcee0) +#define GEN12_BLT_TLB_INV_CR _MMIO(0xcee4) + #define GEN12_AUX_ERR_DBG _MMIO(0x43f4) #define FPGA_DBG _MMIO(0x42300) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 29a858c53bdd..c0d6d5526abe 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -457,6 +457,9 @@ int i915_vma_bind(struct i915_vma *vma, vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags); } + if (vma->obj) + set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags); + atomic_or(bind_flags, &vma->flags); return 0; } diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index fc25ebf1a593..778da3179b3c 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -724,7 +724,8 @@ void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore, } static void __intel_uncore_forcewake_put(struct intel_uncore *uncore, - enum forcewake_domains fw_domains) + enum forcewake_domains fw_domains, + bool delayed) { struct intel_uncore_forcewake_domain *domain; unsigned int tmp; @@ -739,7 +740,11 @@ static void __intel_uncore_forcewake_put(struct intel_uncore *uncore, continue; } - fw_domains_put(uncore, domain->mask); + if (delayed && + !(domain->uncore->fw_domains_timer & domain->mask)) + fw_domain_arm_timer(domain); + else + fw_domains_put(uncore, domain->mask); } } @@ -760,7 +765,20 @@ void intel_uncore_forcewake_put(struct intel_uncore *uncore, return; spin_lock_irqsave(&uncore->lock, irqflags); - __intel_uncore_forcewake_put(uncore, fw_domains); + __intel_uncore_forcewake_put(uncore, fw_domains, false); + spin_unlock_irqrestore(&uncore->lock, irqflags); +} + +void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore, + enum forcewake_domains fw_domains) +{ + unsigned long irqflags; + + if (!uncore->fw_get_funcs) + return; + + spin_lock_irqsave(&uncore->lock, irqflags); + __intel_uncore_forcewake_put(uncore, fw_domains, true); spin_unlock_irqrestore(&uncore->lock, irqflags); } @@ -802,7 +820,7 @@ void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore, if (!uncore->fw_get_funcs) return; - __intel_uncore_forcewake_put(uncore, fw_domains); + __intel_uncore_forcewake_put(uncore, fw_domains, false); } void assert_forcewakes_inactive(struct intel_uncore *uncore) diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index 210fe2a71612..2a15b2b2e2fc 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -246,6 +246,8 @@ void intel_uncore_forcewake_get(struct intel_uncore *uncore, enum forcewake_domains domains); void intel_uncore_forcewake_put(struct intel_uncore *uncore, enum forcewake_domains domains); +void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore, + enum forcewake_domains domains); void intel_uncore_forcewake_flush(struct intel_uncore *uncore, enum forcewake_domains fw_domains); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 2ffa0a11eea5..0cc28c79cc61 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -78,6 +78,7 @@ struct ethqos_emac_por { struct ethqos_emac_driver_data { const struct ethqos_emac_por *por; unsigned int num_por; + bool rgmii_config_looback_en; }; struct qcom_ethqos { @@ -90,6 +91,7 @@ struct qcom_ethqos { const struct ethqos_emac_por *por; unsigned int num_por; + bool rgmii_config_looback_en; }; static int rgmii_readl(struct qcom_ethqos *ethqos, unsigned int offset) @@ -181,6 +183,22 @@ static const struct ethqos_emac_por emac_v2_3_0_por[] = { static const struct ethqos_emac_driver_data emac_v2_3_0_data = { .por = emac_v2_3_0_por, .num_por = ARRAY_SIZE(emac_v2_3_0_por), + .rgmii_config_looback_en = true, +}; + +static const struct ethqos_emac_por emac_v2_1_0_por[] = { + { .offset = RGMII_IO_MACRO_CONFIG, .value = 0x40C01343 }, + { .offset = SDCC_HC_REG_DLL_CONFIG, .value = 0x2004642C }, + { .offset = SDCC_HC_REG_DDR_CONFIG, .value = 0x00000000 }, + { .offset = SDCC_HC_REG_DLL_CONFIG2, .value = 0x00200000 }, + { .offset = SDCC_USR_CTL, .value = 0x00010800 }, + { .offset = RGMII_IO_MACRO_CONFIG2, .value = 0x00002060 }, +}; + +static const struct ethqos_emac_driver_data emac_v2_1_0_data = { + .por = emac_v2_1_0_por, + .num_por = ARRAY_SIZE(emac_v2_1_0_por), + .rgmii_config_looback_en = false, }; static int ethqos_dll_configure(struct qcom_ethqos *ethqos) @@ -297,8 +315,12 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos) rgmii_updatel(ethqos, SDCC_DDR_CONFIG_PRG_DLY_EN, SDCC_DDR_CONFIG_PRG_DLY_EN, SDCC_HC_REG_DDR_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, - RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG); + if (ethqos->rgmii_config_looback_en) + rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, + RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG); + else + rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, + 0, RGMII_IO_MACRO_CONFIG); break; case SPEED_100: @@ -331,8 +353,13 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos) rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN, SDCC_HC_REG_DDR_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, - RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG); + if (ethqos->rgmii_config_looback_en) + rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, + RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG); + else + rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, + 0, RGMII_IO_MACRO_CONFIG); + break; case SPEED_10: @@ -504,6 +531,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) data = of_device_get_match_data(&pdev->dev); ethqos->por = data->por; ethqos->num_por = data->num_por; + ethqos->rgmii_config_looback_en = data->rgmii_config_looback_en; ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii"); if (IS_ERR(ethqos->rgmii_clk)) { @@ -558,6 +586,7 @@ static int qcom_ethqos_remove(struct platform_device *pdev) static const struct of_device_id qcom_ethqos_match[] = { { .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_data}, + { .compatible = "qcom,sm8150-ethqos", .data = &emac_v2_1_0_data}, { } }; MODULE_DEVICE_TABLE(of, qcom_ethqos_match); diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 0d63541c4052..e9cf318e6670 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -28,6 +28,7 @@ void pci_msi_teardown_msi_irqs(struct pci_dev *dev) msi_domain_free_irqs_descs_locked(domain, &dev->dev); else pci_msi_legacy_teardown_msi_irqs(dev); + msi_free_msi_descs(&dev->dev); } /** @@ -171,8 +172,7 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) pci_msi_domain_update_chip_ops(info); - info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS | - MSI_FLAG_FREE_MSI_DESCS; + info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS; if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) info->flags |= MSI_FLAG_MUST_REACTIVATE; diff --git a/drivers/pci/msi/legacy.c b/drivers/pci/msi/legacy.c index cdbb4689db78..db761adef652 100644 --- a/drivers/pci/msi/legacy.c +++ b/drivers/pci/msi/legacy.c @@ -77,5 +77,4 @@ void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) { msi_device_destroy_sysfs(&dev->dev); arch_teardown_msi_irqs(dev); - msi_free_msi_descs(&dev->dev); } diff --git a/drivers/pinctrl/qcom/pinctrl-sm8150.c b/drivers/pinctrl/qcom/pinctrl-sm8150.c index 7359bae68c69..499dd05c3e3d 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8150.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8150.c @@ -1500,6 +1500,25 @@ static const struct msm_pingroup sm8150_groups[] = { [178] = SDC_QDSD_PINGROUP(sdc2_data, 0xB2000, 9, 0), }; +static const struct msm_gpio_wakeirq_map sm8150_pdc_map[] = { + { 3, 31 }, { 5, 32 }, { 8, 33 }, { 9, 34 }, { 10, 100 }, + { 12, 104 }, { 24, 37 }, { 26, 38 }, { 27, 41 }, { 28, 42 }, + { 30, 39 }, { 36, 43 }, { 37, 44 }, { 38, 30 }, { 39, 118 }, + { 39, 125 }, { 41, 47 }, { 42, 48 }, { 46, 50 }, { 47, 49 }, + { 48, 51 }, { 49, 53 }, { 50, 52 }, { 51, 116 }, { 51, 123 }, + { 53, 54 }, { 54, 55 }, { 55, 56 }, { 56, 57 }, { 58, 58 }, + { 60, 60 }, { 61, 61 }, { 68, 62 }, { 70, 63 }, { 76, 71 }, + { 77, 66 }, { 81, 64 }, { 83, 65 }, { 86, 67 }, { 87, 84 }, + { 88, 117 }, { 88, 124 }, { 90, 69 }, { 91, 70 }, { 93, 75 }, + { 95, 72 }, { 96, 73 }, { 97, 74 }, { 101, 40 }, { 103, 77 }, + { 104, 78 }, { 108, 79 }, { 112, 80 }, { 113, 81 }, { 114, 82 }, + { 117, 85 }, { 118, 101 }, { 119, 87 }, { 120, 88 }, { 121, 89 }, + { 122, 90 }, { 123, 91 }, { 124, 92 }, { 125, 93 }, { 129, 94 }, + { 132, 105 }, { 133, 83 }, { 134, 36 }, { 136, 97 }, { 142, 103 }, + { 144, 115 }, { 144, 122 }, { 147, 102 }, { 150, 107 }, + { 152, 108 }, { 153, 109 } +}; + static const struct msm_pinctrl_soc_data sm8150_pinctrl = { .pins = sm8150_pins, .npins = ARRAY_SIZE(sm8150_pins), @@ -1510,6 +1529,8 @@ static const struct msm_pinctrl_soc_data sm8150_pinctrl = { .ngpios = 176, .tiles = sm8150_tiles, .ntiles = ARRAY_SIZE(sm8150_tiles), + .wakeirq_map = sm8150_pdc_map, + .nwakeirq_map = ARRAY_SIZE(sm8150_pdc_map), }; static int sm8150_pinctrl_probe(struct platform_device *pdev) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a5bd6926f7ff..eef5b300b9a9 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1214,6 +1214,35 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto next; /* + * Our start offset might be in the middle of an existing extent + * map, so take that into account. + */ + range_len = em->len - (cur - em->start); + /* + * If this range of the extent map is already flagged for delalloc, + * skip it, because: + * + * 1) We could deadlock later, when trying to reserve space for + * delalloc, because in case we can't immediately reserve space + * the flusher can start delalloc and wait for the respective + * ordered extents to complete. The deadlock would happen + * because we do the space reservation while holding the range + * locked, and starting writeback, or finishing an ordered + * extent, requires locking the range; + * + * 2) If there's delalloc there, it means there's dirty pages for + * which writeback has not started yet (we clean the delalloc + * flag when starting writeback and after creating an ordered + * extent). If we mark pages in an adjacent range for defrag, + * then we will have a larger contiguous range for delalloc, + * very likely resulting in a larger extent after writeback is + * triggered (except in a case of free space fragmentation). + */ + if (test_range_bit(&inode->io_tree, cur, cur + range_len - 1, + EXTENT_DELALLOC, 0, NULL)) + goto next; + + /* * For do_compress case, we want to compress all valid file * extents, thus no @extent_thresh or mergeable check. */ @@ -1221,7 +1250,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto add; /* Skip too large extent */ - if (em->len >= extent_thresh) + if (range_len >= extent_thresh) goto next; next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, @@ -1442,9 +1471,11 @@ static int defrag_one_cluster(struct btrfs_inode *inode, list_for_each_entry(entry, &target_list, list) { u32 range_len = entry->len; - /* Reached the limit */ - if (max_sectors && max_sectors == *sectors_defragged) + /* Reached or beyond the limit */ + if (max_sectors && *sectors_defragged >= max_sectors) { + ret = 1; break; + } if (max_sectors) range_len = min_t(u32, range_len, @@ -1465,7 +1496,8 @@ static int defrag_one_cluster(struct btrfs_inode *inode, extent_thresh, newer_than, do_compress); if (ret < 0) break; - *sectors_defragged += range_len; + *sectors_defragged += range_len >> + inode->root->fs_info->sectorsize_bits; } out: list_for_each_entry_safe(entry, tmp, &target_list, list) { @@ -1484,6 +1516,12 @@ out: * @newer_than: minimum transid to defrag * @max_to_defrag: max number of sectors to be defragged, if 0, the whole inode * will be defragged. + * + * Return <0 for error. + * Return >=0 for the number of sectors defragged, and range->start will be updated + * to indicate the file offset where next defrag should be started at. + * (Mostly for autodefrag, which sets @max_to_defrag thus we may exit early without + * defragging all the range). */ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, struct btrfs_ioctl_defrag_range_args *range, @@ -1499,6 +1537,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, int compress_type = BTRFS_COMPRESS_ZLIB; int ret = 0; u32 extent_thresh = range->extent_thresh; + pgoff_t start_index; if (isize == 0) return 0; @@ -1518,12 +1557,16 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, if (range->start + range->len > range->start) { /* Got a specific range */ - last_byte = min(isize, range->start + range->len) - 1; + last_byte = min(isize, range->start + range->len); } else { /* Defrag until file end */ - last_byte = isize - 1; + last_byte = isize; } + /* Align the range */ + cur = round_down(range->start, fs_info->sectorsize); + last_byte = round_up(last_byte, fs_info->sectorsize) - 1; + /* * If we were not given a ra, allocate a readahead context. As * readahead is just an optimization, defrag will work without it so @@ -1536,16 +1579,26 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, file_ra_state_init(ra, inode->i_mapping); } - /* Align the range */ - cur = round_down(range->start, fs_info->sectorsize); - last_byte = round_up(last_byte, fs_info->sectorsize) - 1; + /* + * Make writeback start from the beginning of the range, so that the + * defrag range can be written sequentially. + */ + start_index = cur >> PAGE_SHIFT; + if (start_index < inode->i_mapping->writeback_index) + inode->i_mapping->writeback_index = start_index; while (cur < last_byte) { + const unsigned long prev_sectors_defragged = sectors_defragged; u64 cluster_end; /* The cluster size 256K should always be page aligned */ BUILD_BUG_ON(!IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE)); + if (btrfs_defrag_cancelled(fs_info)) { + ret = -EAGAIN; + break; + } + /* We want the cluster end at page boundary when possible */ cluster_end = (((cur >> PAGE_SHIFT) + (SZ_256K >> PAGE_SHIFT)) << PAGE_SHIFT) - 1; @@ -1567,14 +1620,27 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, cluster_end + 1 - cur, extent_thresh, newer_than, do_compress, §ors_defragged, max_to_defrag); + + if (sectors_defragged > prev_sectors_defragged) + balance_dirty_pages_ratelimited(inode->i_mapping); + btrfs_inode_unlock(inode, 0); if (ret < 0) break; cur = cluster_end + 1; + if (ret > 0) { + ret = 0; + break; + } } if (ra_allocated) kfree(ra); + /* + * Update range.start for autodefrag, this will indicate where to start + * in next run. + */ + range->start = cur; if (sectors_defragged) { /* * We have defragged some sectors, for compression case they diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index 6a2033131c06..ccd4f245cae2 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -170,7 +170,7 @@ struct cb_devicenotifyitem { }; struct cb_devicenotifyargs { - int ndevs; + uint32_t ndevs; struct cb_devicenotifyitem *devs; }; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 09c5b1cb3e07..c343666d9a42 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -358,7 +358,7 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp, struct cb_process_state *cps) { struct cb_devicenotifyargs *args = argp; - int i; + uint32_t i; __be32 res = 0; struct nfs_client *clp = cps->clp; struct nfs_server *server = NULL; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index a67c41ec545f..f90de8043b0f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -258,11 +258,9 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, void *argp) { struct cb_devicenotifyargs *args = argp; + uint32_t tmp, n, i; __be32 *p; __be32 status = 0; - u32 tmp; - int n, i; - args->ndevs = 0; /* Num of device notifications */ p = xdr_inline_decode(xdr, sizeof(uint32_t)); @@ -271,7 +269,7 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, goto out; } n = ntohl(*p++); - if (n <= 0) + if (n == 0) goto out; if (n > ULONG_MAX / sizeof(*args->devs)) { status = htonl(NFS4ERR_BADXDR); @@ -330,19 +328,21 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, dev->cbd_immediate = 0; } - args->ndevs++; - dprintk("%s: type %d layout 0x%x immediate %d\n", __func__, dev->cbd_notify_type, dev->cbd_layout_type, dev->cbd_immediate); } + args->ndevs = n; + dprintk("%s: ndevs %d\n", __func__, args->ndevs); + return 0; +err: + kfree(args->devs); out: + args->devs = NULL; + args->ndevs = 0; dprintk("%s: status %d ndevs %d\n", __func__, ntohl(status), args->ndevs); return status; -err: - kfree(args->devs); - goto out; } static __be32 decode_sessionid(struct xdr_stream *xdr, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8d8b85b5a641..f18e80fda9bf 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -856,6 +856,13 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str server->namelen = pathinfo.max_namelen; } + if (clp->rpc_ops->discover_trunking != NULL && + (server->caps & NFS_CAP_FS_LOCATIONS)) { + error = clp->rpc_ops->discover_trunking(server, mntfh); + if (error < 0) + return error; + } + return 0; } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 347793626f19..848f3b8fb821 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1325,6 +1325,14 @@ void nfs_clear_verifier_delegated(struct inode *inode) EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ +static int nfs_dentry_verify_change(struct inode *dir, struct dentry *dentry) +{ + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE) && + d_really_is_negative(dentry)) + return dentry->d_time == inode_peek_iversion_raw(dir); + return nfs_verify_change_attribute(dir, dentry->d_time); +} + /* * A check for whether or not the parent directory has changed. * In the case it has, we assume that the dentries are untrustworthy @@ -1338,7 +1346,7 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, return 1; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE) return 0; - if (!nfs_verify_change_attribute(dir, dentry->d_time)) + if (!nfs_dentry_verify_change(dir, dentry)) return 0; /* Revalidate nfsi->cache_change_attribute before we declare a match */ if (nfs_mapping_need_revalidate_inode(dir)) { @@ -1347,7 +1355,7 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, if (__nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0) return 0; } - if (!nfs_verify_change_attribute(dir, dentry->d_time)) + if (!nfs_dentry_verify_change(dir, dentry)) return 0; return 1; } @@ -1437,6 +1445,9 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, return 0; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) return 1; + /* Case insensitive server? Revalidate negative dentries */ + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + return 1; return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU); } @@ -1537,7 +1548,7 @@ out: * If the lookup failed despite the dentry change attribute being * a match, then we should revalidate the directory cache. */ - if (!ret && nfs_verify_change_attribute(dir, dentry->d_time)) + if (!ret && nfs_dentry_verify_change(dir, dentry)) nfs_mark_dir_for_revalidate(dir); return nfs_lookup_revalidate_done(dir, dentry, inode, ret); } @@ -1776,8 +1787,11 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); - if (error == -ENOENT) + if (error == -ENOENT) { + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + dir_verifier = inode_peek_iversion_raw(dir); goto no_entry; + } if (error < 0) { res = ERR_PTR(error); goto out; @@ -1806,6 +1820,14 @@ out: } EXPORT_SYMBOL_GPL(nfs_lookup); +void nfs_d_prune_case_insensitive_aliases(struct inode *inode) +{ + /* Case insensitive server? Revalidate dentries */ + if (inode && nfs_server_capable(inode, NFS_CAP_CASE_INSENSITIVE)) + d_prune_aliases(inode); +} +EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases); + #if IS_ENABLED(CONFIG_NFS_V4) static int nfs4_lookup_revalidate(struct dentry *, unsigned int); @@ -1867,6 +1889,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; unsigned int lookup_flags = 0; + unsigned long dir_verifier; bool switched = false; int created = 0; int err; @@ -1940,7 +1963,11 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, switch (err) { case -ENOENT: d_splice_alias(NULL, dentry); - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + dir_verifier = inode_peek_iversion_raw(dir); + else + dir_verifier = nfs_save_change_attribute(dir); + nfs_set_verifier(dentry, dir_verifier); break; case -EISDIR: case -ENOTDIR: @@ -1968,6 +1995,24 @@ out: no_open: res = nfs_lookup(dir, dentry, lookup_flags); + if (!res) { + inode = d_inode(dentry); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !S_ISDIR(inode->i_mode)) + res = ERR_PTR(-ENOTDIR); + else if (inode && S_ISREG(inode->i_mode)) + res = ERR_PTR(-EOPENSTALE); + } else if (!IS_ERR(res)) { + inode = d_inode(res); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !S_ISDIR(inode->i_mode)) { + dput(res); + res = ERR_PTR(-ENOTDIR); + } else if (inode && S_ISREG(inode->i_mode)) { + dput(res); + res = ERR_PTR(-EOPENSTALE); + } + } if (switched) { d_lookup_done(dentry); if (!res) @@ -2186,8 +2231,10 @@ static void nfs_dentry_remove_handle_error(struct inode *dir, switch (error) { case -ENOENT: d_delete(dentry); - fallthrough; + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + break; case 0: + nfs_d_prune_case_insensitive_aliases(d_inode(dentry)); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); } } @@ -2380,6 +2427,8 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) trace_nfs_link_enter(inode, dir, dentry); d_drop(dentry); + if (S_ISREG(inode->i_mode)) + nfs_sync_inode(inode); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); @@ -2469,6 +2518,8 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, } } + if (S_ISREG(old_inode->i_mode)) + nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); if (IS_ERR(task)) { error = PTR_ERR(task); @@ -2529,7 +2580,7 @@ MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache lengt static void nfs_access_free_entry(struct nfs_access_entry *entry) { - put_cred(entry->cred); + put_group_info(entry->group_info); kfree_rcu(entry, rcu_head); smp_mb__before_atomic(); atomic_long_dec(&nfs_access_nr_entries); @@ -2655,6 +2706,43 @@ void nfs_access_zap_cache(struct inode *inode) } EXPORT_SYMBOL_GPL(nfs_access_zap_cache); +static int access_cmp(const struct cred *a, const struct nfs_access_entry *b) +{ + struct group_info *ga, *gb; + int g; + + if (uid_lt(a->fsuid, b->fsuid)) + return -1; + if (uid_gt(a->fsuid, b->fsuid)) + return 1; + + if (gid_lt(a->fsgid, b->fsgid)) + return -1; + if (gid_gt(a->fsgid, b->fsgid)) + return 1; + + ga = a->group_info; + gb = b->group_info; + if (ga == gb) + return 0; + if (ga == NULL) + return -1; + if (gb == NULL) + return 1; + if (ga->ngroups < gb->ngroups) + return -1; + if (ga->ngroups > gb->ngroups) + return 1; + + for (g = 0; g < ga->ngroups; g++) { + if (gid_lt(ga->gid[g], gb->gid[g])) + return -1; + if (gid_gt(ga->gid[g], gb->gid[g])) + return 1; + } + return 0; +} + static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred) { struct rb_node *n = NFS_I(inode)->access_cache.rb_node; @@ -2662,7 +2750,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co while (n != NULL) { struct nfs_access_entry *entry = rb_entry(n, struct nfs_access_entry, rb_node); - int cmp = cred_fscmp(cred, entry->cred); + int cmp = access_cmp(cred, entry); if (cmp < 0) n = n->rb_left; @@ -2674,7 +2762,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co return NULL; } -static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block) +static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_access_entry *cache; @@ -2704,8 +2792,7 @@ static int nfs_access_get_cached_locked(struct inode *inode, const struct cred * spin_lock(&inode->i_lock); retry = false; } - res->cred = cache->cred; - res->mask = cache->mask; + *mask = cache->mask; list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru); err = 0; out: @@ -2717,7 +2804,7 @@ out_zap: return -ENOENT; } -static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res) +static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, u32 *mask) { /* Only check the most recently returned cache entry, * but do it without locking. @@ -2733,35 +2820,36 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru)); cache = list_entry(lh, struct nfs_access_entry, lru); if (lh == &nfsi->access_cache_entry_lru || - cred_fscmp(cred, cache->cred) != 0) + access_cmp(cred, cache) != 0) cache = NULL; if (cache == NULL) goto out; if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) goto out; - res->cred = cache->cred; - res->mask = cache->mask; + *mask = cache->mask; err = 0; out: rcu_read_unlock(); return err; } -int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct -nfs_access_entry *res, bool may_block) +int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block) { int status; - status = nfs_access_get_cached_rcu(inode, cred, res); + status = nfs_access_get_cached_rcu(inode, cred, mask); if (status != 0) - status = nfs_access_get_cached_locked(inode, cred, res, + status = nfs_access_get_cached_locked(inode, cred, mask, may_block); return status; } EXPORT_SYMBOL_GPL(nfs_access_get_cached); -static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set) +static void nfs_access_add_rbtree(struct inode *inode, + struct nfs_access_entry *set, + const struct cred *cred) { struct nfs_inode *nfsi = NFS_I(inode); struct rb_root *root_node = &nfsi->access_cache; @@ -2774,7 +2862,7 @@ static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry * while (*p != NULL) { parent = *p; entry = rb_entry(parent, struct nfs_access_entry, rb_node); - cmp = cred_fscmp(set->cred, entry->cred); + cmp = access_cmp(cred, entry); if (cmp < 0) p = &parent->rb_left; @@ -2796,13 +2884,16 @@ found: nfs_access_free_entry(entry); } -void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) +void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set, + const struct cred *cred) { struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL); if (cache == NULL) return; RB_CLEAR_NODE(&cache->rb_node); - cache->cred = get_cred(set->cred); + cache->fsuid = cred->fsuid; + cache->fsgid = cred->fsgid; + cache->group_info = get_group_info(cred->group_info); cache->mask = set->mask; /* The above field assignments must be visible @@ -2810,7 +2901,7 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) * use rcu_assign_pointer, so just force the memory barrier. */ smp_wmb(); - nfs_access_add_rbtree(inode, cache); + nfs_access_add_rbtree(inode, cache, cred); /* Update accounting */ smp_mb__before_atomic(); @@ -2875,7 +2966,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) trace_nfs_access_enter(inode); - status = nfs_access_get_cached(inode, cred, &cache, may_block); + status = nfs_access_get_cached(inode, cred, &cache.mask, may_block); if (status == 0) goto out_cached; @@ -2895,8 +2986,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP; else cache.mask |= NFS_ACCESS_EXECUTE; - cache.cred = cred; - status = NFS_PROTO(inode)->access(inode, &cache); + status = NFS_PROTO(inode)->access(inode, &cache, cred); if (status != 0) { if (status == -ESTALE) { if (!S_ISDIR(inode->i_mode)) @@ -2906,7 +2996,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) } goto out; } - nfs_access_add_cache(inode, &cache); + nfs_access_add_cache(inode, &cache, cred); out_cached: cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode); if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h index 79323b5dab0c..aed0748fd6ec 100644 --- a/fs/nfs/filelayout/filelayout.h +++ b/fs/nfs/filelayout/filelayout.h @@ -51,7 +51,7 @@ struct nfs4_file_layout_dsaddr { u32 stripe_count; u8 *stripe_indices; u32 ds_num; - struct nfs4_pnfs_ds *ds_list[1]; + struct nfs4_pnfs_ds *ds_list[]; }; struct nfs4_filelayout_segment { diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 86c3f7e69ec4..acf4b88889dc 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -136,9 +136,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, goto out_err_free_stripe_indices; } - dsaddr = kzalloc(sizeof(*dsaddr) + - (sizeof(struct nfs4_pnfs_ds *) * (num - 1)), - gfp_flags); + dsaddr = kzalloc(struct_size(dsaddr, ds_list, num), gfp_flags); if (!dsaddr) goto out_err_free_stripe_indices; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 12f6acb483bb..2de7c56a1fbe 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -373,6 +373,7 @@ extern unsigned long nfs_access_cache_count(struct shrinker *shrink, extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); +void nfs_d_prune_case_insensitive_aliases(struct inode *inode); int nfs_create(struct user_namespace *, struct inode *, struct dentry *, umode_t, bool); int nfs_mkdir(struct user_namespace *, struct inode *, struct dentry *, diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 7100514d306b..1597eef40d54 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -220,7 +220,8 @@ static int nfs3_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, task_flags); } -static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs3_accessargs arg = { .fh = NFS_FH(inode), @@ -231,7 +232,7 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) .rpc_proc = &nfs3_procedures[NFS3PROC_ACCESS], .rpc_argp = &arg, .rpc_resp = &res, - .rpc_cred = entry->cred, + .rpc_cred = cred, }; int status = -ENOMEM; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 8b21ff1be717..32129446beca 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -46,7 +46,7 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, { struct inode *inode = file_inode(filep); struct nfs_server *server = NFS_SERVER(inode); - u32 bitmask[3]; + u32 bitmask[NFS_BITMASK_SZ]; struct nfs42_falloc_args args = { .falloc_fh = NFS_FH(inode), .falloc_offset = offset, @@ -69,9 +69,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, return status; } - memcpy(bitmask, server->cache_consistency_bitmask, sizeof(bitmask)); - if (server->attr_bitmask[1] & FATTR4_WORD1_SPACE_USED) - bitmask[1] |= FATTR4_WORD1_SPACE_USED; + nfs4_bitmask_set(bitmask, server->cache_consistency_bitmask, inode, + NFS_INO_INVALID_BLOCKS); res.falloc_fattr = nfs_alloc_fattr(); if (!res.falloc_fattr) @@ -1044,13 +1043,14 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, struct inode *src_inode = file_inode(src_f); struct inode *dst_inode = file_inode(dst_f); struct nfs_server *server = NFS_SERVER(dst_inode); + __u32 dst_bitmask[NFS_BITMASK_SZ]; struct nfs42_clone_args args = { .src_fh = NFS_FH(src_inode), .dst_fh = NFS_FH(dst_inode), .src_offset = src_offset, .dst_offset = dst_offset, .count = count, - .dst_bitmask = server->cache_consistency_bitmask, + .dst_bitmask = dst_bitmask, }; struct nfs42_clone_res res = { .server = server, @@ -1079,6 +1079,9 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, if (!res.dst_fattr) return -ENOMEM; + nfs4_bitmask_set(dst_bitmask, server->cache_consistency_bitmask, + dst_inode, NFS_INO_INVALID_BLOCKS); + status = nfs4_call_sync(server->client, server, msg, &args.seq_args, &res.seq_res, 0); trace_nfs4_clone(src_inode, dst_inode, &args, status); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index ed5eaca6801e..84f39b6f1b1e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -260,8 +260,8 @@ struct nfs4_state_maintenance_ops { }; struct nfs4_mig_recovery_ops { - int (*get_locations)(struct inode *, struct nfs4_fs_locations *, - struct page *, const struct cred *); + int (*get_locations)(struct nfs_server *, struct nfs_fh *, + struct nfs4_fs_locations *, struct page *, const struct cred *); int (*fsid_present)(struct inode *, const struct cred *); }; @@ -280,7 +280,8 @@ struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *, int nfs4_submount(struct fs_context *, struct nfs_server *); int nfs4_replace_transport(struct nfs_server *server, const struct nfs4_fs_locations *locations); - +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa, + size_t salen, struct net *net, int port); /* nfs4proc.c */ extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *); extern int nfs4_async_handle_error(struct rpc_task *task, @@ -302,8 +303,9 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, struct nfs4_fs_locations *, struct page *); -extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, - struct page *page, const struct cred *); +extern int nfs4_proc_get_locations(struct nfs_server *, struct nfs_fh *, + struct nfs4_fs_locations *, + struct page *page, const struct cred *); extern int nfs4_proc_fsid_present(struct inode *, const struct cred *); extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct dentry *, @@ -315,6 +317,8 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx, fmode_t fmode); +extern void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[], + struct inode *inode, unsigned long cache_validity); extern int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct inode *inode); extern int update_open_stateid(struct nfs4_state *state, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index d8b5a250ca05..47a6cf892c95 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1343,8 +1343,11 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, } nfs_put_client(clp); - if (server->nfs_client->cl_hostname == NULL) + if (server->nfs_client->cl_hostname == NULL) { server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL); + if (server->nfs_client->cl_hostname == NULL) + return -ENOMEM; + } nfs_server_insert_lists(server); return nfs_probe_server(server, NFS_FH(d_inode(server->super->s_root))); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 873342308dc0..3680c8da510c 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -164,16 +164,21 @@ static int nfs4_validate_fspath(struct dentry *dentry, return 0; } -static size_t nfs_parse_server_name(char *string, size_t len, - struct sockaddr *sa, size_t salen, struct net *net) +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa, + size_t salen, struct net *net, int port) { ssize_t ret; ret = rpc_pton(net, string, len, sa, salen); if (ret == 0) { - ret = nfs_dns_resolve_name(net, string, len, sa, salen); - if (ret < 0) - ret = 0; + ret = rpc_uaddr2sockaddr(net, string, len, sa, salen); + if (ret == 0) { + ret = nfs_dns_resolve_name(net, string, len, sa, salen); + if (ret < 0) + ret = 0; + } + } else if (port) { + rpc_set_port(sa, port); } return ret; } @@ -328,7 +333,7 @@ static int try_location(struct fs_context *fc, nfs_parse_server_name(buf->data, buf->len, &ctx->nfs_server.address, sizeof(ctx->nfs_server._address), - fc->net_ns); + fc->net_ns, 0); if (ctx->nfs_server.addrlen == 0) continue; @@ -496,7 +501,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, continue; salen = nfs_parse_server_name(buf->data, buf->len, - sap, addr_bufsize, net); + sap, addr_bufsize, net, 0); if (salen == 0) continue; rpc_set_port(sap, NFS_PORT); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ee3bc79f6ca3..b18f31b2c9e7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -108,10 +108,6 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *, static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *, const struct cred *, bool); #endif -static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], - const __u32 *src, struct inode *inode, - struct nfs_server *server, - struct nfs4_label *label); #ifdef CONFIG_NFS_V4_SECURITY_LABEL static inline struct nfs4_label * @@ -2653,9 +2649,8 @@ static int nfs4_opendata_access(const struct cred *cred, } else if ((fmode & FMODE_READ) && !opendata->file_created) mask = NFS4_ACCESS_READ; - cache.cred = cred; nfs_access_set_mask(&cache, opendata->o_res.access_result); - nfs_access_add_cache(state->inode, &cache); + nfs_access_add_cache(state->inode, &cache, cred); flags = NFS4_ACCESS_READ | NFS4_ACCESS_EXECUTE | NFS4_ACCESS_LOOKUP; if ((mask & ~cache.mask & flags) == 0) @@ -3670,7 +3665,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) if (!nfs4_have_delegation(inode, FMODE_READ)) { nfs4_bitmask_set(calldata->arg.bitmask_store, server->cache_consistency_bitmask, - inode, server, NULL); + inode, 0); calldata->arg.bitmask = calldata->arg.bitmask_store; } else calldata->arg.bitmask = NULL; @@ -3841,7 +3836,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f FATTR4_WORD0_FH_EXPIRE_TYPE | FATTR4_WORD0_LINK_SUPPORT | FATTR4_WORD0_SYMLINK_SUPPORT | - FATTR4_WORD0_ACLSUPPORT; + FATTR4_WORD0_ACLSUPPORT | + FATTR4_WORD0_CASE_INSENSITIVE | + FATTR4_WORD0_CASE_PRESERVING; if (minorversion) bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT; @@ -3870,10 +3867,16 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f server->caps |= NFS_CAP_HARDLINKS; if (res.has_symlinks != 0) server->caps |= NFS_CAP_SYMLINKS; + if (res.case_insensitive) + server->caps |= NFS_CAP_CASE_INSENSITIVE; + if (res.case_preserving) + server->caps |= NFS_CAP_CASE_PRESERVING; #ifdef CONFIG_NFS_V4_SECURITY_LABEL if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL) server->caps |= NFS_CAP_SECURITY_LABEL; #endif + if (res.attr_bitmask[0] & FATTR4_WORD0_FS_LOCATIONS) + server->caps |= NFS_CAP_FS_LOCATIONS; if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID)) server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID; if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE)) @@ -3932,6 +3935,114 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) return err; } +static void test_fs_location_for_trunking(struct nfs4_fs_location *location, + struct nfs_client *clp, + struct nfs_server *server) +{ + int i; + + for (i = 0; i < location->nservers; i++) { + struct nfs4_string *srv_loc = &location->servers[i]; + struct sockaddr addr; + size_t addrlen; + struct xprt_create xprt_args = { + .ident = 0, + .net = clp->cl_net, + }; + struct nfs4_add_xprt_data xprtdata = { + .clp = clp, + }; + struct rpc_add_xprt_test rpcdata = { + .add_xprt_test = clp->cl_mvops->session_trunk, + .data = &xprtdata, + }; + char *servername = NULL; + + if (!srv_loc->len) + continue; + + addrlen = nfs_parse_server_name(srv_loc->data, srv_loc->len, + &addr, sizeof(addr), + clp->cl_net, server->port); + if (!addrlen) + return; + xprt_args.dstaddr = &addr; + xprt_args.addrlen = addrlen; + servername = kmalloc(srv_loc->len + 1, GFP_KERNEL); + if (!servername) + return; + memcpy(servername, srv_loc->data, srv_loc->len); + servername[srv_loc->len] = '\0'; + xprt_args.servername = servername; + + xprtdata.cred = nfs4_get_clid_cred(clp); + rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, + rpc_clnt_setup_test_and_add_xprt, + &rpcdata); + if (xprtdata.cred) + put_cred(xprtdata.cred); + kfree(servername); + } +} + +static int _nfs4_discover_trunking(struct nfs_server *server, + struct nfs_fh *fhandle) +{ + struct nfs4_fs_locations *locations = NULL; + struct page *page; + const struct cred *cred; + struct nfs_client *clp = server->nfs_client; + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + int status = -ENOMEM, i; + + cred = ops->get_state_renewal_cred(clp); + if (cred == NULL) { + cred = nfs4_get_clid_cred(clp); + if (cred == NULL) + return -ENOKEY; + } + + page = alloc_page(GFP_KERNEL); + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (page == NULL || locations == NULL) + goto out; + + status = nfs4_proc_get_locations(server, fhandle, locations, page, + cred); + if (status) + goto out; + + for (i = 0; i < locations->nlocations; i++) + test_fs_location_for_trunking(&locations->locations[i], clp, + server); +out: + if (page) + __free_page(page); + kfree(locations); + return status; +} + +static int nfs4_discover_trunking(struct nfs_server *server, + struct nfs_fh *fhandle) +{ + struct nfs4_exception exception = { + .interruptible = true, + }; + struct nfs_client *clp = server->nfs_client; + int err = 0; + + if (!nfs4_has_session(clp)) + goto out; + do { + err = nfs4_handle_exception(server, + _nfs4_discover_trunking(server, fhandle), + &exception); + } while (exception.retry); +out: + return err; +} + static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info) { @@ -4441,7 +4552,8 @@ static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, return err; } -static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct nfs4_accessargs args = { @@ -4455,7 +4567,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ACCESS], .rpc_argp = &args, .rpc_resp = &res, - .rpc_cred = entry->cred, + .rpc_cred = cred, }; int status = 0; @@ -4475,14 +4587,15 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry return status; } -static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs4_exception exception = { .interruptible = true, }; int err; do { - err = _nfs4_proc_access(inode, entry); + err = _nfs4_proc_access(inode, entry, cred); trace_nfs4_access(inode, err); err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); @@ -4663,8 +4776,10 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, nfs_fattr_init(res->dir_attr); - if (inode) + if (inode) { nfs4_inode_return_delegation(inode); + nfs_d_prune_case_insensitive_aliases(inode); + } } static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data) @@ -4730,6 +4845,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, return 0; if (task->tk_status == 0) { + nfs_d_prune_case_insensitive_aliases(d_inode(data->old_dentry)); if (new_dir != old_dir) { /* Note: If we moved a directory, nlink will change */ nfs4_update_changeattr(old_dir, &res->old_cinfo, @@ -5422,14 +5538,14 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr) return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0; } -static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src, - struct inode *inode, struct nfs_server *server, - struct nfs4_label *label) +void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[], + struct inode *inode, unsigned long cache_validity) { - unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); + struct nfs_server *server = NFS_SERVER(inode); unsigned int i; memcpy(bitmask, src, sizeof(*bitmask) * NFS4_BITMASK_SZ); + cache_validity |= READ_ONCE(NFS_I(inode)->cache_validity); if (cache_validity & NFS_INO_INVALID_CHANGE) bitmask[0] |= FATTR4_WORD0_CHANGE; @@ -5441,8 +5557,6 @@ static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src, bitmask[1] |= FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP; if (cache_validity & NFS_INO_INVALID_NLINK) bitmask[1] |= FATTR4_WORD1_NUMLINKS; - if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL) - bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL; if (cache_validity & NFS_INO_INVALID_CTIME) bitmask[1] |= FATTR4_WORD1_TIME_METADATA; if (cache_validity & NFS_INO_INVALID_MTIME) @@ -5469,7 +5583,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr, } else { nfs4_bitmask_set(hdr->args.bitmask_store, server->cache_consistency_bitmask, - hdr->inode, server, NULL); + hdr->inode, NFS_INO_INVALID_BLOCKS); hdr->args.bitmask = hdr->args.bitmask_store; } @@ -6507,8 +6621,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->args.fhandle = &data->fh; data->args.stateid = &data->stateid; nfs4_bitmask_set(data->args.bitmask_store, - server->cache_consistency_bitmask, inode, server, - NULL); + server->cache_consistency_bitmask, inode, 0); data->args.bitmask = data->args.bitmask_store; nfs_copy_fh(&data->fh, NFS_FH(inode)); nfs4_stateid_copy(&data->stateid, stateid); @@ -7611,7 +7724,7 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, const char *key, const void *buf, size_t buflen, int flags) { - struct nfs_access_entry cache; + u32 mask; int ret; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) @@ -7626,8 +7739,8 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, * do a cached access check for the XA* flags to possibly avoid * doing an RPC and getting EACCES back. */ - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XAWRITE)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XAWRITE)) return -EACCES; } @@ -7648,14 +7761,14 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *key, void *buf, size_t buflen) { - struct nfs_access_entry cache; + u32 mask; ssize_t ret; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) return -EOPNOTSUPP; - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XAREAD)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XAREAD)) return -EACCES; } @@ -7680,13 +7793,13 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len) ssize_t ret, size; char *buf; size_t buflen; - struct nfs_access_entry cache; + u32 mask; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) return 0; - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XALIST)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XALIST)) return 0; } @@ -7818,18 +7931,18 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, * appended to this compound to identify the client ID which is * performing recovery. */ -static int _nfs40_proc_get_locations(struct inode *inode, +static int _nfs40_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, }; struct nfs4_fs_locations_arg args = { .clientid = server->nfs_client->cl_clientid, - .fh = NFS_FH(inode), + .fh = fhandle, .page = page, .bitmask = bitmask, .migration = 1, /* skip LOOKUP */ @@ -7875,17 +7988,17 @@ static int _nfs40_proc_get_locations(struct inode *inode, * When the client supports GETATTR(fs_locations_info), it can * be plumbed in here. */ -static int _nfs41_proc_get_locations(struct inode *inode, +static int _nfs41_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, }; struct nfs4_fs_locations_arg args = { - .fh = NFS_FH(inode), + .fh = fhandle, .page = page, .bitmask = bitmask, .migration = 1, /* skip LOOKUP */ @@ -7934,11 +8047,11 @@ static int _nfs41_proc_get_locations(struct inode *inode, * -NFS4ERR_LEASE_MOVED is returned if the server still has leases * from this client that require migration recovery. */ -int nfs4_proc_get_locations(struct inode *inode, +int nfs4_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct nfs_client *clp = server->nfs_client; const struct nfs4_mig_recovery_ops *ops = clp->cl_mvops->mig_recovery_ops; @@ -7951,10 +8064,11 @@ int nfs4_proc_get_locations(struct inode *inode, (unsigned long long)server->fsid.major, (unsigned long long)server->fsid.minor, clp->cl_hostname); - nfs_display_fhandle(NFS_FH(inode), __func__); + nfs_display_fhandle(fhandle, __func__); do { - status = ops->get_locations(inode, locations, page, cred); + status = ops->get_locations(server, fhandle, locations, page, + cred); if (status != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, status, &exception); @@ -10423,6 +10537,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .free_client = nfs4_free_client, .create_server = nfs4_create_server, .clone_server = nfs_clone_server, + .discover_trunking = nfs4_discover_trunking, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index d88b779f9dd0..f5a62c0d999b 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2098,7 +2098,8 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred } inode = d_inode(server->super->s_root); - result = nfs4_proc_get_locations(inode, locations, page, cred); + result = nfs4_proc_get_locations(server, NFS_FH(inode), locations, + page, cred); if (result) { dprintk("<-- %s: failed to retrieve fs_locations: %d\n", __func__, result); @@ -2106,6 +2107,9 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred } result = -NFS4ERR_NXIO; + if (!locations->nlocations) + goto out; + if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) { dprintk("<-- %s: No fs_locations data, migration skipped\n", __func__); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 69862bf6db00..8e70b92df4cc 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3533,6 +3533,42 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint return 0; } +static int decode_attr_case_insensitive(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_INSENSITIVE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CASE_INSENSITIVE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_CASE_INSENSITIVE; + } + dprintk("%s: case_insensitive=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +} + +static int decode_attr_case_preserving(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_PRESERVING - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CASE_PRESERVING)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_CASE_PRESERVING; + } + dprintk("%s: case_preserving=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +} + static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) { __be32 *p; @@ -3696,8 +3732,6 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st if (unlikely(!p)) goto out_eio; n = be32_to_cpup(p); - if (n <= 0) - goto out_eio; for (res->nlocations = 0; res->nlocations < n; res->nlocations++) { u32 m; struct nfs4_fs_location *loc; @@ -4200,10 +4234,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, } else printk(KERN_WARNING "%s: label too long (%u)!\n", __func__, len); + if (label && label->label) + dprintk("%s: label=%.*s, len=%d, PI=%d, LFS=%d\n", + __func__, label->len, (char *)label->label, + label->len, label->pi, label->lfs); } - if (label && label->label) - dprintk("%s: label=%s, len=%d, PI=%d, LFS=%d\n", __func__, - (char *)label->label, label->len, label->pi, label->lfs); return status; } @@ -4412,6 +4447,10 @@ static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_re goto xdr_error; if ((status = decode_attr_aclsupport(xdr, bitmap, &res->acl_bitmask)) != 0) goto xdr_error; + if ((status = decode_attr_case_insensitive(xdr, bitmap, &res->case_insensitive)) != 0) + goto xdr_error; + if ((status = decode_attr_case_preserving(xdr, bitmap, &res->case_preserving)) != 0) + goto xdr_error; if ((status = decode_attr_exclcreat_supported(xdr, bitmap, res->exclcreat_bitmask)) != 0) goto xdr_error; diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index 8cb70755e3c9..a6f740366963 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -142,10 +142,11 @@ static struct attribute *nfs_netns_client_attrs[] = { &nfs_netns_client_id.attr, NULL, }; +ATTRIBUTE_GROUPS(nfs_netns_client); static struct kobj_type nfs_netns_client_type = { .release = nfs_netns_client_release, - .default_attrs = nfs_netns_client_attrs, + .default_groups = nfs_netns_client_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_client_namespace, }; diff --git a/include/dt-bindings/clock/qcom,gcc-sm8150.h b/include/dt-bindings/clock/qcom,gcc-sm8150.h index 3e1a91876610..35d80ae411a0 100644 --- a/include/dt-bindings/clock/qcom,gcc-sm8150.h +++ b/include/dt-bindings/clock/qcom,gcc-sm8150.h @@ -241,7 +241,12 @@ #define GCC_USB_PHY_CFG_AHB2PHY_BCR 28 /* GCC GDSCRs */ -#define USB30_PRIM_GDSC 4 -#define USB30_SEC_GDSC 5 +#define EMAC_GDSC 0 +#define PCIE_0_GDSC 1 +#define PCIE_1_GDSC 2 +#define UFS_CARD_GDSC 3 +#define UFS_PHY_GDSC 4 +#define USB30_PRIM_GDSC 5 +#define USB30_SEC_GDSC 6 #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 00835bacd236..02aa49323d1d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -61,7 +61,9 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - const struct cred * cred; + kuid_t fsuid; + kgid_t fsgid; + struct group_info *group_info; __u32 mask; struct rcu_head rcu_head; }; @@ -395,7 +397,7 @@ extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fa extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); -extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); +extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct user_namespace *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); @@ -532,8 +534,8 @@ extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); -extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, - bool may_block); +extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block); /* * linux/fs/nfs/symlink.c diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 77b2dba27bbb..ca0959e51e81 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -266,6 +266,8 @@ struct nfs_server { #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) #define NFS_CAP_LGOPEN (1U << 5) +#define NFS_CAP_CASE_INSENSITIVE (1U << 6) +#define NFS_CAP_CASE_PRESERVING (1U << 7) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) @@ -282,5 +284,5 @@ struct nfs_server { #define NFS_CAP_COPY_NOTIFY (1U << 27) #define NFS_CAP_XATTR (1U << 28) #define NFS_CAP_READ_PLUS (1U << 29) - +#define NFS_CAP_FS_LOCATIONS (1U << 30) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 967a0098f0a9..728cb0c1f0b6 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1194,6 +1194,8 @@ struct nfs4_server_caps_res { u32 has_links; u32 has_symlinks; u32 fh_expire_type; + u32 case_insensitive; + u32 case_preserving; }; #define NFS4_PATHNAME_MAXCOMPONENTS 512 @@ -1737,7 +1739,7 @@ struct nfs_rpc_ops { struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *); - int (*access) (struct inode *, struct nfs_access_entry *); + int (*access) (struct inode *, struct nfs_access_entry *, const struct cred *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); int (*create) (struct inode *, struct dentry *, @@ -1795,6 +1797,7 @@ struct nfs_rpc_ops { struct nfs_server *(*create_server)(struct fs_context *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); + int (*discover_trunking)(struct nfs_server *, struct nfs_fh *); }; /* diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 117f230bcdfd..733649184b27 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -693,18 +693,6 @@ struct perf_event { u64 total_time_running; u64 tstamp; - /* - * timestamp shadows the actual context timing but it can - * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in, - * or when ctx_sched_in failed to schedule the event because we - * run out of PMC. - * - * ctx_time already accounts for ctx->timestamp. Therefore to - * compute ctx_time for a sample, simply add perf_clock(). - */ - u64 shadow_ctx_time; - struct perf_event_attr attr; u16 header_size; u16 id_header_size; @@ -852,6 +840,7 @@ struct perf_event_context { */ u64 time; u64 timestamp; + u64 timeoffset; /* * These fields let us detect when two contexts have both @@ -934,6 +923,8 @@ struct bpf_perf_event_data_kern { struct perf_cgroup_info { u64 time; u64 timestamp; + u64 timeoffset; + int active; }; struct perf_cgroup { diff --git a/include/linux/psi.h b/include/linux/psi.h index a70ca833c6d7..f8ce53bfdb2a 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -33,7 +33,7 @@ void cgroup_move_task(struct task_struct *p, struct css_set *to); struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res); -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); +void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 516c0fe836fd..1a3cef26d129 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -141,9 +141,6 @@ struct psi_trigger { * events to one per window */ u64 last_event_time; - - /* Refcounting to prevent premature destruction */ - struct kref refcount; }; struct psi_group { diff --git a/include/linux/sched.h b/include/linux/sched.h index 508b91d57470..f5b2be39a78c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -619,10 +619,6 @@ struct sched_dl_entity { * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * - * @dl_boosted tells if we are boosted due to DI. If so we are - * outside bandwidth enforcement mechanism (but only until we - * exit the critical section); - * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 1e566ac4b812..29982d60b68a 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -794,6 +794,9 @@ RPC_SHOW_SOCKET RPC_SHOW_SOCK + +#include <trace/events/net_probe_common.h> + /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. @@ -816,27 +819,32 @@ DECLARE_EVENT_CLASS(xs_socket_event, __field(unsigned int, socket_state) __field(unsigned int, sock_state) __field(unsigned long long, ino) - __string(dstaddr, - xprt->address_strings[RPC_DISPLAY_ADDR]) - __string(dstport, - xprt->address_strings[RPC_DISPLAY_PORT]) + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( struct inode *inode = SOCK_INODE(socket); + const struct sock *sk = socket->sk; + const struct inet_sock *inet = inet_sk(sk); + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + TP_STORE_ADDR_PORTS(__entry, inet, sk); + __entry->socket_state = socket->state; __entry->sock_state = socket->sk->sk_state; __entry->ino = (unsigned long long)inode->i_ino; - __assign_str(dstaddr, - xprt->address_strings[RPC_DISPLAY_ADDR]); - __assign_str(dstport, - xprt->address_strings[RPC_DISPLAY_PORT]); + ), TP_printk( - "socket:[%llu] dstaddr=%s/%s " + "socket:[%llu] srcaddr=%pISpc dstaddr=%pISpc " "state=%u (%s) sk_state=%u (%s)", - __entry->ino, __get_str(dstaddr), __get_str(dstport), + __entry->ino, + __entry->saddr, + __entry->daddr, __entry->socket_state, rpc_show_socket_state(__entry->socket_state), __entry->sock_state, @@ -866,29 +874,33 @@ DECLARE_EVENT_CLASS(xs_socket_event_done, __field(unsigned int, socket_state) __field(unsigned int, sock_state) __field(unsigned long long, ino) - __string(dstaddr, - xprt->address_strings[RPC_DISPLAY_ADDR]) - __string(dstport, - xprt->address_strings[RPC_DISPLAY_PORT]) + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( struct inode *inode = SOCK_INODE(socket); + const struct sock *sk = socket->sk; + const struct inet_sock *inet = inet_sk(sk); + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + TP_STORE_ADDR_PORTS(__entry, inet, sk); + __entry->socket_state = socket->state; __entry->sock_state = socket->sk->sk_state; __entry->ino = (unsigned long long)inode->i_ino; __entry->error = error; - __assign_str(dstaddr, - xprt->address_strings[RPC_DISPLAY_ADDR]); - __assign_str(dstport, - xprt->address_strings[RPC_DISPLAY_PORT]); ), TP_printk( - "error=%d socket:[%llu] dstaddr=%s/%s " + "error=%d socket:[%llu] srcaddr=%pISpc dstaddr=%pISpc " "state=%u (%s) sk_state=%u (%s)", __entry->error, - __entry->ino, __get_str(dstaddr), __get_str(dstport), + __entry->ino, + __entry->saddr, + __entry->daddr, __entry->socket_state, rpc_show_socket_state(__entry->socket_state), __entry->sock_state, @@ -953,7 +965,8 @@ TRACE_EVENT(rpc_socket_nospace, { BIT(XPRT_REMOVE), "REMOVE" }, \ { BIT(XPRT_CONGESTED), "CONGESTED" }, \ { BIT(XPRT_CWND_WAIT), "CWND_WAIT" }, \ - { BIT(XPRT_WRITE_SPACE), "WRITE_SPACE" }) + { BIT(XPRT_WRITE_SPACE), "WRITE_SPACE" }, \ + { BIT(XPRT_SND_IS_COOKIE), "SND_IS_COOKIE" }) DECLARE_EVENT_CLASS(rpc_xprt_lifetime_class, TP_PROTO( @@ -1150,8 +1163,11 @@ DECLARE_EVENT_CLASS(xprt_writelock_event, __entry->task_id = -1; __entry->client_id = -1; } - __entry->snd_task_id = xprt->snd_task ? - xprt->snd_task->tk_pid : -1; + if (xprt->snd_task && + !test_bit(XPRT_SND_IS_COOKIE, &xprt->state)) + __entry->snd_task_id = xprt->snd_task->tk_pid; + else + __entry->snd_task_id = -1; ), TP_printk(SUNRPC_TRACE_TASK_SPECIFIER @@ -1196,8 +1212,12 @@ DECLARE_EVENT_CLASS(xprt_cong_event, __entry->task_id = -1; __entry->client_id = -1; } - __entry->snd_task_id = xprt->snd_task ? - xprt->snd_task->tk_pid : -1; + if (xprt->snd_task && + !test_bit(XPRT_SND_IS_COOKIE, &xprt->state)) + __entry->snd_task_id = xprt->snd_task->tk_pid; + else + __entry->snd_task_id = -1; + __entry->cong = xprt->cong; __entry->cwnd = xprt->cwnd; __entry->wait = test_bit(XPRT_CWND_WAIT, &xprt->state); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 49e567209c6b..22c8ae94e4c1 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -472,13 +472,14 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, u32, size, u64, flags) { struct pt_regs *regs; - long res; + long res = -EINVAL; if (!try_get_task_stack(task)) return -EFAULT; regs = task_pt_regs(task); - res = __bpf_get_stack(regs, task, NULL, buf, size, flags); + if (regs) + res = __bpf_get_stack(regs, task, NULL, buf, size, flags); put_task_stack(task); return res; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b31e1465868a..9d05c3ca2d5e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3643,6 +3643,12 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, cgroup_get(cgrp); cgroup_kn_unlock(of->kn); + /* Allow only one trigger per file descriptor */ + if (ctx->psi.trigger) { + cgroup_put(cgrp); + return -EBUSY; + } + psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; new = psi_trigger_create(psi, buf, nbytes, res); if (IS_ERR(new)) { @@ -3650,8 +3656,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return PTR_ERR(new); } - psi_trigger_replace(&ctx->psi.trigger, new); - + smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; @@ -3690,7 +3695,7 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; - psi_trigger_replace(&ctx->psi.trigger, NULL); + psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) diff --git a/kernel/events/core.c b/kernel/events/core.c index fc18664f49b0..479c9e672ec4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -674,6 +674,23 @@ perf_event_set_state(struct perf_event *event, enum perf_event_state state) WRITE_ONCE(event->state, state); } +/* + * UP store-release, load-acquire + */ + +#define __store_release(ptr, val) \ +do { \ + barrier(); \ + WRITE_ONCE(*(ptr), (val)); \ +} while (0) + +#define __load_acquire(ptr) \ +({ \ + __unqual_scalar_typeof(*(ptr)) ___p = READ_ONCE(*(ptr)); \ + barrier(); \ + ___p; \ +}) + #ifdef CONFIG_CGROUP_PERF static inline bool @@ -719,34 +736,51 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event) return t->time; } -static inline void __update_cgrp_time(struct perf_cgroup *cgrp) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { - struct perf_cgroup_info *info; - u64 now; - - now = perf_clock(); + struct perf_cgroup_info *t; - info = this_cpu_ptr(cgrp->info); + t = per_cpu_ptr(event->cgrp->info, event->cpu); + if (!__load_acquire(&t->active)) + return t->time; + now += READ_ONCE(t->timeoffset); + return now; +} - info->time += now - info->timestamp; +static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv) +{ + if (adv) + info->time += now - info->timestamp; info->timestamp = now; + /* + * see update_context_time() + */ + WRITE_ONCE(info->timeoffset, info->time - info->timestamp); } -static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final) { struct perf_cgroup *cgrp = cpuctx->cgrp; struct cgroup_subsys_state *css; + struct perf_cgroup_info *info; if (cgrp) { + u64 now = perf_clock(); + for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); - __update_cgrp_time(cgrp); + info = this_cpu_ptr(cgrp->info); + + __update_cgrp_time(info, now, true); + if (final) + __store_release(&info->active, 0); } } } static inline void update_cgrp_time_from_event(struct perf_event *event) { + struct perf_cgroup_info *info; struct perf_cgroup *cgrp; /* @@ -760,8 +794,10 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - __update_cgrp_time(event->cgrp); + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { + info = this_cpu_ptr(event->cgrp->info); + __update_cgrp_time(info, perf_clock(), true); + } } static inline void @@ -785,7 +821,8 @@ perf_cgroup_set_timestamp(struct task_struct *task, for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); info = this_cpu_ptr(cgrp->info); - info->timestamp = ctx->timestamp; + __update_cgrp_time(info, ctx->timestamp, false); + __store_release(&info->active, 1); } } @@ -982,14 +1019,6 @@ out: } static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) -{ - struct perf_cgroup_info *t; - t = per_cpu_ptr(event->cgrp->info, event->cpu); - event->shadow_ctx_time = now - t->timestamp; -} - -static inline void perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_cpu_context *cpuctx; @@ -1066,7 +1095,8 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) { } -static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, + bool final) { } @@ -1098,12 +1128,12 @@ perf_cgroup_switch(struct task_struct *task, struct task_struct *next) { } -static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +static inline u64 perf_cgroup_event_time(struct perf_event *event) { + return 0; } -static inline u64 perf_cgroup_event_time(struct perf_event *event) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { return 0; } @@ -1525,22 +1555,59 @@ static void perf_unpin_context(struct perf_event_context *ctx) /* * Update the record of the current time in a context. */ -static void update_context_time(struct perf_event_context *ctx) +static void __update_context_time(struct perf_event_context *ctx, bool adv) { u64 now = perf_clock(); - ctx->time += now - ctx->timestamp; + if (adv) + ctx->time += now - ctx->timestamp; ctx->timestamp = now; + + /* + * The above: time' = time + (now - timestamp), can be re-arranged + * into: time` = now + (time - timestamp), which gives a single value + * offset to compute future time without locks on. + * + * See perf_event_time_now(), which can be used from NMI context where + * it's (obviously) not possible to acquire ctx->lock in order to read + * both the above values in a consistent manner. + */ + WRITE_ONCE(ctx->timeoffset, ctx->time - ctx->timestamp); +} + +static void update_context_time(struct perf_event_context *ctx) +{ + __update_context_time(ctx, true); } static u64 perf_event_time(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; + if (unlikely(!ctx)) + return 0; + if (is_cgroup_event(event)) return perf_cgroup_event_time(event); - return ctx ? ctx->time : 0; + return ctx->time; +} + +static u64 perf_event_time_now(struct perf_event *event, u64 now) +{ + struct perf_event_context *ctx = event->ctx; + + if (unlikely(!ctx)) + return 0; + + if (is_cgroup_event(event)) + return perf_cgroup_event_time_now(event, now); + + if (!(__load_acquire(&ctx->is_active) & EVENT_TIME)) + return ctx->time; + + now += READ_ONCE(ctx->timeoffset); + return now; } static enum event_type_t get_event_type(struct perf_event *event) @@ -2350,7 +2417,7 @@ __perf_remove_from_context(struct perf_event *event, if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, false); } event_sched_out(event, cpuctx, ctx); @@ -2361,6 +2428,9 @@ __perf_remove_from_context(struct perf_event *event, list_del_event(event, ctx); if (!ctx->nr_events && ctx->is_active) { + if (ctx == &cpuctx->ctx) + update_cgrp_time_from_cpuctx(cpuctx, true); + ctx->is_active = 0; ctx->rotate_necessary = 0; if (ctx->task) { @@ -2482,40 +2552,6 @@ void perf_event_disable_inatomic(struct perf_event *event) irq_work_queue(&event->pending); } -static void perf_set_shadow_time(struct perf_event *event, - struct perf_event_context *ctx) -{ - /* - * use the correct time source for the time snapshot - * - * We could get by without this by leveraging the - * fact that to get to this function, the caller - * has most likely already called update_context_time() - * and update_cgrp_time_xx() and thus both timestamp - * are identical (or very close). Given that tstamp is, - * already adjusted for cgroup, we could say that: - * tstamp - ctx->timestamp - * is equivalent to - * tstamp - cgrp->timestamp. - * - * Then, in perf_output_read(), the calculation would - * work with no changes because: - * - event is guaranteed scheduled in - * - no scheduled out in between - * - thus the timestamp would be the same - * - * But this is a bit hairy. - * - * So instead, we have an explicit cgroup call to remain - * within the time source all along. We believe it - * is cleaner and simpler to understand. - */ - if (is_cgroup_event(event)) - perf_cgroup_set_shadow_time(event, event->tstamp); - else - event->shadow_ctx_time = event->tstamp - ctx->timestamp; -} - #define MAX_INTERRUPTS (~0ULL) static void perf_log_throttle(struct perf_event *event, int enable); @@ -2556,8 +2592,6 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); - perf_set_shadow_time(event, ctx); - perf_log_itrace_start(event); if (event->pmu->add(event, PERF_EF_START)) { @@ -3251,16 +3285,6 @@ static void ctx_sched_out(struct perf_event_context *ctx, return; } - ctx->is_active &= ~event_type; - if (!(ctx->is_active & EVENT_ALL)) - ctx->is_active = 0; - - if (ctx->task) { - WARN_ON_ONCE(cpuctx->task_ctx != ctx); - if (!ctx->is_active) - cpuctx->task_ctx = NULL; - } - /* * Always update time if it was set; not only when it changes. * Otherwise we can 'forget' to update time for any but the last @@ -3274,7 +3298,22 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (is_active & EVENT_TIME) { /* update (and stop) ctx time */ update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, ctx == &cpuctx->ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + + ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + if (!ctx->is_active) + cpuctx->task_ctx = NULL; } is_active ^= ctx->is_active; /* changed bits */ @@ -3711,13 +3750,19 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +/* + * Because the userpage is strictly per-event (there is no concept of context, + * so there cannot be a context indirection), every userpage must be updated + * when context time starts :-( + * + * IOW, we must not miss EVENT_TIME edges. + */ static inline bool event_update_userpage(struct perf_event *event) { if (likely(!atomic_read(&event->mmap_count))) return false; perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_update_userpage(event); return true; @@ -3801,13 +3846,23 @@ ctx_sched_in(struct perf_event_context *ctx, struct task_struct *task) { int is_active = ctx->is_active; - u64 now; lockdep_assert_held(&ctx->lock); if (likely(!ctx->nr_events)) return; + if (is_active ^ EVENT_TIME) { + /* start ctx time */ + __update_context_time(ctx, false); + perf_cgroup_set_timestamp(task, ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) @@ -3818,13 +3873,6 @@ ctx_sched_in(struct perf_event_context *ctx, is_active ^= ctx->is_active; /* changed bits */ - if (is_active & EVENT_TIME) { - /* start ctx time */ - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); - } - /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. @@ -4418,6 +4466,18 @@ static inline u64 perf_event_count(struct perf_event *event) return local64_read(&event->count) + atomic64_read(&event->child_count); } +static void calc_timer_values(struct perf_event *event, + u64 *now, + u64 *enabled, + u64 *running) +{ + u64 ctx_time; + + *now = perf_clock(); + ctx_time = perf_event_time_now(event, *now); + __perf_update_times(event, ctx_time, enabled, running); +} + /* * NMI-safe method to read a local event, that is an event that * is: @@ -4477,10 +4537,9 @@ int perf_event_read_local(struct perf_event *event, u64 *value, *value = local64_read(&event->count); if (enabled || running) { - u64 now = event->shadow_ctx_time + perf_clock(); - u64 __enabled, __running; + u64 __enabled, __running, __now;; - __perf_update_times(event, now, &__enabled, &__running); + calc_timer_values(event, &__now, &__enabled, &__running); if (enabled) *enabled = __enabled; if (running) @@ -5802,18 +5861,6 @@ static int perf_event_index(struct perf_event *event) return event->pmu->event_idx(event); } -static void calc_timer_values(struct perf_event *event, - u64 *now, - u64 *enabled, - u64 *running) -{ - u64 ctx_time; - - *now = perf_clock(); - ctx_time = event->shadow_ctx_time + *now; - __perf_update_times(event, ctx_time, enabled, running); -} - static void perf_event_init_userpage(struct perf_event *event) { struct perf_event_mmap_page *userpg; @@ -6353,7 +6400,6 @@ accounting: ring_buffer_attach(event, rb); perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2e4ae00e52d1..848eaa0efe0e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5822,8 +5822,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } if (schedstat_enabled() && rq->core->core_forceidle_count) { - if (cookie) - rq->core->core_forceidle_start = rq_clock(rq->core); + rq->core->core_forceidle_start = rq_clock(rq->core); rq->core->core_forceidle_occupation = occ; } @@ -8219,9 +8218,7 @@ int __cond_resched_lock(spinlock_t *lock) if (spin_needbreak(lock) || resched) { spin_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; spin_lock(lock); @@ -8239,9 +8236,7 @@ int __cond_resched_rwlock_read(rwlock_t *lock) if (rwlock_needbreak(lock) || resched) { read_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; read_lock(lock); @@ -8259,9 +8254,7 @@ int __cond_resched_rwlock_write(rwlock_t *lock) if (rwlock_needbreak(lock) || resched) { write_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; write_lock(lock); diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 1fb45672ec85..c8746a9a7ada 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -277,7 +277,7 @@ void __sched_core_account_forceidle(struct rq *rq) rq_i = cpu_rq(i); p = rq_i->core_pick ?: rq_i->curr; - if (!p->core_cookie) + if (p == rq_i->idle) continue; __schedstat_add(p->stats.core_forceidle_sum, delta); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 095b0aa378df..5146163bfabb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3028,9 +3028,11 @@ enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u32 divider = get_pelt_divider(&se->avg); sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); - cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; + sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } #else static inline void @@ -3381,7 +3383,6 @@ void set_task_rq_fair(struct sched_entity *se, se->avg.last_update_time = n_last_update_time; } - /* * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to * propagate its contribution. The key to this propagation is the invariant @@ -3449,15 +3450,14 @@ void set_task_rq_fair(struct sched_entity *se, * XXX: only do this for the part of runnable > running ? * */ - static inline void update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.util_avg - se->avg.util_avg; - u32 divider; + long delta_sum, delta_avg = gcfs_rq->avg.util_avg - se->avg.util_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* @@ -3466,23 +3466,30 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq */ divider = get_pelt_divider(&cfs_rq->avg); + /* Set new sched_entity's utilization */ se->avg.util_avg = gcfs_rq->avg.util_avg; - se->avg.util_sum = se->avg.util_avg * divider; + new_sum = se->avg.util_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.util_sum; + se->avg.util_sum = new_sum; /* Update parent cfs_rq utilization */ - add_positive(&cfs_rq->avg.util_avg, delta); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; + add_positive(&cfs_rq->avg.util_avg, delta_avg); + add_positive(&cfs_rq->avg.util_sum, delta_sum); + + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; - u32 divider; + long delta_sum, delta_avg = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* @@ -3493,19 +3500,25 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf /* Set new sched_entity's runnable */ se->avg.runnable_avg = gcfs_rq->avg.runnable_avg; - se->avg.runnable_sum = se->avg.runnable_avg * divider; + new_sum = se->avg.runnable_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.runnable_sum; + se->avg.runnable_sum = new_sum; /* Update parent cfs_rq runnable */ - add_positive(&cfs_rq->avg.runnable_avg, delta); - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; + add_positive(&cfs_rq->avg.runnable_avg, delta_avg); + add_positive(&cfs_rq->avg.runnable_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; + long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; unsigned long load_avg; u64 load_sum = 0; + s64 delta_sum; u32 divider; if (!runnable_sum) @@ -3532,7 +3545,7 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq * assuming all tasks are equally runnable. */ if (scale_load_down(gcfs_rq->load.weight)) { - load_sum = div_s64(gcfs_rq->avg.load_sum, + load_sum = div_u64(gcfs_rq->avg.load_sum, scale_load_down(gcfs_rq->load.weight)); } @@ -3549,19 +3562,22 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT; runnable_sum = max(runnable_sum, running_sum); - load_sum = (s64)se_weight(se) * runnable_sum; - load_avg = div_s64(load_sum, divider); - - se->avg.load_sum = runnable_sum; + load_sum = se_weight(se) * runnable_sum; + load_avg = div_u64(load_sum, divider); - delta = load_avg - se->avg.load_avg; - if (!delta) + delta_avg = load_avg - se->avg.load_avg; + if (!delta_avg) return; - se->avg.load_avg = load_avg; + delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; - add_positive(&cfs_rq->avg.load_avg, delta); - cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; + se->avg.load_sum = runnable_sum; + se->avg.load_avg = load_avg; + add_positive(&cfs_rq->avg.load_avg, delta_avg); + add_positive(&cfs_rq->avg.load_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) @@ -3652,7 +3668,7 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum * * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example. * - * Returns true if the load decayed or we removed load. + * Return: true if the load decayed or we removed load. * * Since both these conditions indicate a changed cfs_rq->avg.load we should * call update_tg_load_avg() when this function returns true. @@ -3677,15 +3693,32 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) r = removed_load; sub_positive(&sa->load_avg, r); - sa->load_sum = sa->load_avg * divider; + sub_positive(&sa->load_sum, r * divider); + /* See sa->util_sum below */ + sa->load_sum = max_t(u32, sa->load_sum, sa->load_avg * PELT_MIN_DIVIDER); r = removed_util; sub_positive(&sa->util_avg, r); - sa->util_sum = sa->util_avg * divider; + sub_positive(&sa->util_sum, r * divider); + /* + * Because of rounding, se->util_sum might ends up being +1 more than + * cfs->util_sum. Although this is not a problem by itself, detaching + * a lot of tasks with the rounding problem between 2 updates of + * util_avg (~1ms) can make cfs->util_sum becoming null whereas + * cfs_util_avg is not. + * Check that util_sum is still above its lower bound for the new + * util_avg. Given that period_contrib might have moved since the last + * sync, we are only sure that util_sum must be above or equal to + * util_avg * minimum possible divider + */ + sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER); r = removed_runnable; sub_positive(&sa->runnable_avg, r); - sa->runnable_sum = sa->runnable_avg * divider; + sub_positive(&sa->runnable_sum, r * divider); + /* See sa->util_sum above */ + sa->runnable_sum = max_t(u32, sa->runnable_sum, + sa->runnable_avg * PELT_MIN_DIVIDER); /* * removed_runnable is the unweighted version of removed_load so we @@ -3772,17 +3805,18 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - /* - * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. - * See ___update_load_avg() for details. - */ - u32 divider = get_pelt_divider(&cfs_rq->avg); - dequeue_load_avg(cfs_rq, se); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; + sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); + sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; + sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); @@ -8539,6 +8573,8 @@ group_type group_classify(unsigned int imbalance_pct, * * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings * of @dst_cpu are idle and @sg has lower priority. + * + * Return: true if @dst_cpu can pull tasks, false otherwise. */ static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds, struct sg_lb_stats *sgs, @@ -8614,6 +8650,7 @@ sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. + * @sds: Load-balancing data with statistics of the local group. * @group: sched_group whose statistics are to be updated. * @sgs: variable to hold the statistics for this group. * @sg_status: Holds flag indicating the status of the sched_group @@ -9421,12 +9458,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /** * find_busiest_group - Returns the busiest group within the sched_domain * if there is an imbalance. + * @env: The load balancing environment. * * Also calculates the amount of runnable load which should be moved * to restore balance. * - * @env: The load balancing environment. - * * Return: - The busiest group if imbalance exists. */ static struct sched_group *find_busiest_group(struct lb_env *env) diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index e06071bf3472..c336f5f481bc 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -37,9 +37,11 @@ update_irq_load_avg(struct rq *rq, u64 running) } #endif +#define PELT_MIN_DIVIDER (LOAD_AVG_MAX - 1024) + static inline u32 get_pelt_divider(struct sched_avg *avg) { - return LOAD_AVG_MAX - 1024 + avg->period_contrib; + return PELT_MIN_DIVIDER + avg->period_contrib; } static inline void cfs_se_util_change(struct sched_avg *avg) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a679613a7cb7..c137c4d6983e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1162,7 +1162,6 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->event = 0; t->last_event_time = 0; init_waitqueue_head(&t->event_wait); - kref_init(&t->refcount); mutex_lock(&group->trigger_lock); @@ -1191,15 +1190,19 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, return t; } -static void psi_trigger_destroy(struct kref *ref) +void psi_trigger_destroy(struct psi_trigger *t) { - struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount); - struct psi_group *group = t->group; + struct psi_group *group; struct task_struct *task_to_destroy = NULL; - if (static_branch_likely(&psi_disabled)) + /* + * We do not check psi_disabled since it might have been disabled after + * the trigger got created. + */ + if (!t) return; + group = t->group; /* * Wakeup waiters to stop polling. Can happen if cgroup is deleted * from under a polling process. @@ -1235,9 +1238,9 @@ static void psi_trigger_destroy(struct kref *ref) mutex_unlock(&group->trigger_lock); /* - * Wait for both *trigger_ptr from psi_trigger_replace and - * poll_task RCUs to complete their read-side critical sections - * before destroying the trigger and optionally the poll_task + * Wait for psi_schedule_poll_work RCU to complete its read-side + * critical section before destroying the trigger and optionally the + * poll_task. */ synchronize_rcu(); /* @@ -1254,18 +1257,6 @@ static void psi_trigger_destroy(struct kref *ref) kfree(t); } -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new) -{ - struct psi_trigger *old = *trigger_ptr; - - if (static_branch_likely(&psi_disabled)) - return; - - rcu_assign_pointer(*trigger_ptr, new); - if (old) - kref_put(&old->refcount, psi_trigger_destroy); -} - __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait) { @@ -1275,24 +1266,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (static_branch_likely(&psi_disabled)) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - rcu_read_lock(); - - t = rcu_dereference(*(void __rcu __force **)trigger_ptr); - if (!t) { - rcu_read_unlock(); + t = smp_load_acquire(trigger_ptr); + if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - } - kref_get(&t->refcount); - - rcu_read_unlock(); poll_wait(file, &t->event_wait, wait); if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; - kref_put(&t->refcount, psi_trigger_destroy); - return ret; } @@ -1316,14 +1298,24 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, buf[buf_size - 1] = '\0'; - new = psi_trigger_create(&psi_system, buf, nbytes, res); - if (IS_ERR(new)) - return PTR_ERR(new); - seq = file->private_data; + /* Take seq->lock to protect seq->private from concurrent writes */ mutex_lock(&seq->lock); - psi_trigger_replace(&seq->private, new); + + /* Allow only one trigger per file descriptor */ + if (seq->private) { + mutex_unlock(&seq->lock); + return -EBUSY; + } + + new = psi_trigger_create(&psi_system, buf, nbytes, res); + if (IS_ERR(new)) { + mutex_unlock(&seq->lock); + return PTR_ERR(new); + } + + smp_store_release(&seq->private, new); mutex_unlock(&seq->lock); return nbytes; @@ -1358,7 +1350,7 @@ static int psi_fop_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; - psi_trigger_replace(&seq->private, NULL); + psi_trigger_destroy(seq->private); return single_release(inode, file); } diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c index fe97f3106536..4a4082bb22ad 100644 --- a/net/sunrpc/auth_gss/gss_generic_token.c +++ b/net/sunrpc/auth_gss/gss_generic_token.c @@ -222,10 +222,8 @@ g_verify_token_header(struct xdr_netobj *mech, int *body_size, if (ret) return ret; - if (!ret) { - *buf_in = buf; - *body_size = toksize; - } + *buf_in = buf; + *body_size = toksize; return ret; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index a312ea2bc440..c83fe618767c 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2900,7 +2900,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, unsigned long connect_timeout; unsigned long reconnect_timeout; unsigned char resvport, reuseport; - int ret = 0; + int ret = 0, ident; rcu_read_lock(); xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); @@ -2914,8 +2914,11 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, reuseport = xprt->reuseport; connect_timeout = xprt->connect_timeout; reconnect_timeout = xprt->max_reconnect_timeout; + ident = xprt->xprt_class->ident; rcu_read_unlock(); + if (!xprtargs->ident) + xprtargs->ident = ident; xprt = xprt_create_transport(xprtargs); if (IS_ERR(xprt)) { ret = PTR_ERR(xprt); diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index 2766dd21935b..b64a0286b182 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -295,8 +295,10 @@ static ssize_t rpc_sysfs_xprt_state_change(struct kobject *kobj, online = 1; else if (!strncmp(buf, "remove", 6)) remove = 1; - else - return -EINVAL; + else { + count = -EINVAL; + goto out_put; + } if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) { count = -EINTR; @@ -307,25 +309,28 @@ static ssize_t rpc_sysfs_xprt_state_change(struct kobject *kobj, goto release_tasks; } if (offline) { - set_bit(XPRT_OFFLINE, &xprt->state); - spin_lock(&xps->xps_lock); - xps->xps_nactive--; - spin_unlock(&xps->xps_lock); + if (!test_and_set_bit(XPRT_OFFLINE, &xprt->state)) { + spin_lock(&xps->xps_lock); + xps->xps_nactive--; + spin_unlock(&xps->xps_lock); + } } else if (online) { - clear_bit(XPRT_OFFLINE, &xprt->state); - spin_lock(&xps->xps_lock); - xps->xps_nactive++; - spin_unlock(&xps->xps_lock); + if (test_and_clear_bit(XPRT_OFFLINE, &xprt->state)) { + spin_lock(&xps->xps_lock); + xps->xps_nactive++; + spin_unlock(&xps->xps_lock); + } } else if (remove) { if (test_bit(XPRT_OFFLINE, &xprt->state)) { - set_bit(XPRT_REMOVE, &xprt->state); - xprt_force_disconnect(xprt); - if (test_bit(XPRT_CONNECTED, &xprt->state)) { - if (!xprt->sending.qlen && - !xprt->pending.qlen && - !xprt->backlog.qlen && - !atomic_long_read(&xprt->queuelen)) - rpc_xprt_switch_remove_xprt(xps, xprt); + if (!test_and_set_bit(XPRT_REMOVE, &xprt->state)) { + xprt_force_disconnect(xprt); + if (test_bit(XPRT_CONNECTED, &xprt->state)) { + if (!xprt->sending.qlen && + !xprt->pending.qlen && + !xprt->backlog.qlen && + !atomic_long_read(&xprt->queuelen)) + rpc_xprt_switch_remove_xprt(xps, xprt); + } } } else { count = -EINVAL; @@ -422,6 +427,7 @@ static struct attribute *rpc_sysfs_xprt_attrs[] = { &rpc_sysfs_xprt_change_state.attr, NULL, }; +ATTRIBUTE_GROUPS(rpc_sysfs_xprt); static struct kobj_attribute rpc_sysfs_xprt_switch_info = __ATTR(xprt_switch_info, 0444, rpc_sysfs_xprt_switch_info_show, NULL); @@ -430,6 +436,7 @@ static struct attribute *rpc_sysfs_xprt_switch_attrs[] = { &rpc_sysfs_xprt_switch_info.attr, NULL, }; +ATTRIBUTE_GROUPS(rpc_sysfs_xprt_switch); static struct kobj_type rpc_sysfs_client_type = { .release = rpc_sysfs_client_release, @@ -439,14 +446,14 @@ static struct kobj_type rpc_sysfs_client_type = { static struct kobj_type rpc_sysfs_xprt_switch_type = { .release = rpc_sysfs_xprt_switch_release, - .default_attrs = rpc_sysfs_xprt_switch_attrs, + .default_groups = rpc_sysfs_xprt_switch_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = rpc_sysfs_xprt_switch_namespace, }; static struct kobj_type rpc_sysfs_xprt_type = { .release = rpc_sysfs_xprt_release, - .default_attrs = rpc_sysfs_xprt_attrs, + .default_groups = rpc_sysfs_xprt_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = rpc_sysfs_xprt_namespace, }; diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 17f174d6ea3b..faba7136dd9a 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -13,10 +13,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - #undef RPCRDMA_BACKCHANNEL_DEBUG /** diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index ff699307e820..515dd7a66a04 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -45,10 +45,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - static void frwr_cid_init(struct rpcrdma_ep *ep, struct rpcrdma_mr *mr) { diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 8035a983c8ce..281ddb87ac8d 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -54,10 +54,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - /* Returns size of largest RPC-over-RDMA header in a Call message * * The largest Call header contains a full-size Read list and a diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 16e5696314a4..42e375dbdadb 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -60,10 +60,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - /* * tunables */ diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3d3673ba9e1e..f172d1298013 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -63,17 +63,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -/* - * Globals/Macros - */ - -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - -/* - * internal functions - */ static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_sendctxs_destroy(struct rpcrdma_xprt *r_xprt); static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt, @@ -274,8 +263,6 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) ep->re_connect_status = -ENETUNREACH; goto wake_connect_worker; case RDMA_CM_EVENT_REJECTED: - dprintk("rpcrdma: connection to %pISpc rejected: %s\n", - sap, rdma_reject_msg(id, event->status)); ep->re_connect_status = -ECONNREFUSED; if (event->status == IB_CM_REJ_STALE_CONN) ep->re_connect_status = -ENOTCONN; @@ -291,8 +278,6 @@ disconnected: break; } - dprintk("RPC: %s: %pISpc on %s/frwr: %s\n", __func__, sap, - ep->re_id->device->name, rdma_event_msg(event->event)); return 0; } @@ -419,14 +404,6 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) ep->re_attr.qp_type = IB_QPT_RC; ep->re_attr.port_num = ~0; - dprintk("RPC: %s: requested max: dtos: send %d recv %d; " - "iovs: send %d recv %d\n", - __func__, - ep->re_attr.cap.max_send_wr, - ep->re_attr.cap.max_recv_wr, - ep->re_attr.cap.max_send_sge, - ep->re_attr.cap.max_recv_sge); - ep->re_send_batch = ep->re_max_requests >> 3; ep->re_send_count = ep->re_send_batch; init_waitqueue_head(&ep->re_connect_wait); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index d8ee06a9650a..69b6ee5a5fd1 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1910,7 +1910,7 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); int ret; - if (RPC_IS_ASYNC(task)) { + if (RPC_IS_ASYNC(task)) { /* * We want the AF_LOCAL connect to be resolved in the * filesystem namespace of the process making the rpc diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c index ab9353f2fd46..9a5c1f008fe6 100644 --- a/tools/bpf/runqslower/runqslower.bpf.c +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -68,7 +68,7 @@ int handle__sched_switch(u64 *ctx) */ struct task_struct *prev = (struct task_struct *)ctx[1]; struct task_struct *next = (struct task_struct *)ctx[2]; - struct event event = {}; + struct runq_event event = {}; u64 *tsp, delta_us; long state; u32 pid; diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c index 2414cc764461..d78f4148597f 100644 --- a/tools/bpf/runqslower/runqslower.c +++ b/tools/bpf/runqslower/runqslower.c @@ -100,7 +100,7 @@ static int bump_memlock_rlimit(void) void handle_event(void *ctx, int cpu, void *data, __u32 data_sz) { - const struct event *e = data; + const struct runq_event *e = data; struct tm *tm; char ts[32]; time_t t; diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h index 9db225425e5f..4f70f07200c2 100644 --- a/tools/bpf/runqslower/runqslower.h +++ b/tools/bpf/runqslower/runqslower.h @@ -4,7 +4,7 @@ #define TASK_COMM_LEN 16 -struct event { +struct runq_event { char task[TASK_COMM_LEN]; __u64 delta_us; pid_t pid; |