diff options
Diffstat (limited to 'arch')
40 files changed, 379 insertions, 189 deletions
diff --git a/arch/arm/boot/dts/broadcom/bcm-ns.dtsi b/arch/arm/boot/dts/broadcom/bcm-ns.dtsi index 392a25713669..bd52de0faa3e 100644 --- a/arch/arm/boot/dts/broadcom/bcm-ns.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm-ns.dtsi @@ -141,7 +141,7 @@ /* PCIe Controller 2 */ <0x00014000 0 &gic GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>, - <0x00014000 1 &gic GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>, + <0x00014000 1 &gic GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>, <0x00014000 2 &gic GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>, <0x00014000 3 &gic GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>, <0x00014000 4 &gic GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/broadcom/bcm4709-linksys-ea9200.dts b/arch/arm/boot/dts/broadcom/bcm4709-linksys-ea9200.dts index 5bbc2ba0f959..87569408bb69 100644 --- a/arch/arm/boot/dts/broadcom/bcm4709-linksys-ea9200.dts +++ b/arch/arm/boot/dts/broadcom/bcm4709-linksys-ea9200.dts @@ -26,7 +26,7 @@ nvram@1c080000 { compatible = "brcm,nvram"; - reg = <0x1c080000 0x180000>; + reg = <0x1c080000 0x100000>; et2macaddr: et2macaddr { #nvmem-cell-cells = <1>; diff --git a/arch/arm/mach-npcm/platsmp.c b/arch/arm/mach-npcm/platsmp.c index 41891d3aa124..4c1fc9983746 100644 --- a/arch/arm/mach-npcm/platsmp.c +++ b/arch/arm/mach-npcm/platsmp.c @@ -32,6 +32,7 @@ static int npcm7xx_smp_boot_secondary(unsigned int cpu, goto out; } gcr_base = of_iomap(gcr_np, 0); + of_node_put(gcr_np); if (!gcr_base) { pr_err("could not iomap gcr"); ret = -ENOMEM; @@ -60,6 +61,7 @@ static void __init npcm7xx_smp_prepare_cpus(unsigned int max_cpus) return; } scu_base = of_iomap(scu_np, 0); + of_node_put(scu_np); if (!scu_base) { pr_err("could not iomap scu"); return; diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index 761c59d90ffc..09ff5e9959d3 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -678,8 +678,6 @@ <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | - IRQ_TYPE_LEVEL_LOW)>, - <GIC_PPI 12 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>; }; diff --git a/arch/arm64/boot/dts/qcom/eliza.dtsi b/arch/arm64/boot/dts/qcom/eliza.dtsi index 977de44b816e..72b786fec195 100644 --- a/arch/arm64/boot/dts/qcom/eliza.dtsi +++ b/arch/arm64/boot/dts/qcom/eliza.dtsi @@ -2559,7 +2559,7 @@ "dsi_pll"; clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>; + <&bi_tcxo_div2>; clock-names = "iface", "ref"; diff --git a/arch/arm64/boot/dts/qcom/glymur.dtsi b/arch/arm64/boot/dts/qcom/glymur.dtsi index 20b49af7298e..129be417ac42 100644 --- a/arch/arm64/boot/dts/qcom/glymur.dtsi +++ b/arch/arm64/boot/dts/qcom/glymur.dtsi @@ -1876,7 +1876,7 @@ spi0: spi@b80000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b80000 0x0 0x4000>; - interrupts = <GIC_SPI 1052 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 92 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S0_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1903,7 +1903,7 @@ i2c1: i2c@b84000 { compatible = "qcom,geni-i2c"; reg = <0x0 0x00b84000 0x0 0x4000>; - interrupts = <GIC_SPI 1053 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 93 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1930,7 +1930,7 @@ spi1: spi@b84000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b84000 0x0 0x4000>; - interrupts = <GIC_SPI 1053 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 93 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1957,7 +1957,7 @@ i2c2: i2c@b88000 { compatible = "qcom,geni-i2c"; reg = <0x0 0x00b88000 0x0 0x4000>; - interrupts = <GIC_SPI 1054 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 94 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1984,7 +1984,7 @@ spi2: spi@b88000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b88000 0x0 0x4000>; - interrupts = <GIC_SPI 1054 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 94 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2011,7 +2011,7 @@ uart2: serial@b88000 { compatible = "qcom,geni-uart"; reg = <0x0 0x00b88000 0x0 0x4000>; - interrupts = <GIC_SPI 1054 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 94 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2056,7 +2056,7 @@ spi3: spi@b8c000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b8c000 0x0 0x4000>; - interrupts = <GIC_SPI 1055 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 95 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S3_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2110,7 +2110,7 @@ spi4: spi@b90000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b90000 0x0 0x4000>; - interrupts = <GIC_SPI 1056 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S4_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2164,7 +2164,7 @@ spi5: spi@b94000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b94000 0x0 0x4000>; - interrupts = <GIC_SPI 1057 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 97 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S5_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2191,7 +2191,7 @@ i2c6: i2c@b98000 { compatible = "qcom,geni-i2c"; reg = <0x0 0x00b98000 0x0 0x4000>; - interrupts = <GIC_SPI 1058 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 98 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S6_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2218,7 +2218,7 @@ spi6: spi@b98000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b98000 0x0 0x4000>; - interrupts = <GIC_SPI 1058 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 98 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S6_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2245,7 +2245,7 @@ i2c7: i2c@b9c000 { compatible = "qcom,geni-i2c"; reg = <0x0 0x00b9c000 0x0 0x4000>; - interrupts = <GIC_SPI 1059 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 99 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S7_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2272,7 +2272,7 @@ spi7: spi@b9c000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b9c000 0x0 0x4000>; - interrupts = <GIC_SPI 1059 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 99 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S7_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -6874,9 +6874,9 @@ pcie_smmu: iommu@15480000 { compatible = "arm,smmu-v3"; reg = <0x0 0x15480000 0x0 0x20000>; - interrupts = <GIC_SPI 964 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 962 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 960 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 4 IRQ_TYPE_LEVEL_HIGH>, + <GIC_ESPI 2 IRQ_TYPE_LEVEL_HIGH>, + <GIC_ESPI 0 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "eventq", "cmdq-sync", "gerror"; dma-coherent; #iommu-cells = <1>; diff --git a/arch/arm64/boot/dts/qcom/monaco.dtsi b/arch/arm64/boot/dts/qcom/monaco.dtsi index e4c8466f941b..a350a8ba48fa 100644 --- a/arch/arm64/boot/dts/qcom/monaco.dtsi +++ b/arch/arm64/boot/dts/qcom/monaco.dtsi @@ -7384,6 +7384,7 @@ interrupt-controller; #redistributor-regions = <1>; redistributor-stride = <0x0 0x20000>; + #address-cells = <0>; }; watchdog@17c10000 { diff --git a/arch/arm64/boot/dts/qcom/purwa.dtsi b/arch/arm64/boot/dts/qcom/purwa.dtsi index 9ab4f26b35f2..5b17840fb62f 100644 --- a/arch/arm64/boot/dts/qcom/purwa.dtsi +++ b/arch/arm64/boot/dts/qcom/purwa.dtsi @@ -47,6 +47,8 @@ &gpu { compatible = "qcom,adreno-43030c00", "qcom,adreno"; + iommus = <&adreno_smmu 0 0x0>; + nvmem-cells = <&gpu_speed_bin>; nvmem-cell-names = "speed_bin"; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts b/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts index f3c00be67081..cd575e20d90a 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts @@ -637,7 +637,7 @@ compatible = "huawei,gaokun3-ec"; reg = <0x38>; - interrupts-extended = <&tlmm 107 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&tlmm 103 IRQ_TYPE_LEVEL_LOW>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index a2bd6b10e475..b0de9e262f29 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -5356,7 +5356,7 @@ <211 699 1>, <212 705 1>, <213 450 1>, - <214 643 1>, + <214 643 2>, <216 646 5>, <221 390 5>, <226 700 3>, @@ -5379,7 +5379,7 @@ <252 798 1>, <253 765 1>, <254 763 1>, - <255 454 1>, + <255 454 3>, <258 139 1>, <259 786 2>, <261 370 2>, diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index e41200839dbe..8cdaef5360d1 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -347,6 +347,10 @@ status = "okay"; }; +&cluster_sleep_0 { + arm,psci-suspend-param = <0x41008244>; +}; + &gcc { protected-clocks = <GCC_QSPI_CORE_CLK>, <GCC_QSPI_CORE_CLK_SRC>, diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index 160ead25ecf7..65c4a2b46d21 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -7091,8 +7091,8 @@ ranges = <0 0 0x14680000 0x2c000>; - ipa_modem_tables: modem-tables@8000 { - reg = <0x8000 0x2000>; + ipa_modem_tables: modem-tables@3000 { + reg = <0x3000 0x2000>; }; }; diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h index 5b374a6ab34a..50a195eda8ed 100644 --- a/arch/arm64/include/asm/ptdump.h +++ b/arch/arm64/include/asm/ptdump.h @@ -7,8 +7,6 @@ #include <linux/ptdump.h> -DECLARE_STATIC_KEY_FALSE(arm64_ptdump_lock_key); - #ifdef CONFIG_PTDUMP #include <linux/mm_types.h> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 18a8b0d3714e..d4de88770ecf 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -49,8 +49,6 @@ #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ -DEFINE_STATIC_KEY_FALSE(arm64_ptdump_lock_key); - u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -1864,8 +1862,7 @@ int pmd_clear_huge(pmd_t *pmdp) return 1; } -static int __pmd_free_pte_page(pmd_t *pmdp, unsigned long addr, - bool acquire_mmap_lock) +int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) { pte_t *table; pmd_t pmd; @@ -1877,25 +1874,13 @@ static int __pmd_free_pte_page(pmd_t *pmdp, unsigned long addr, return 1; } - /* See comment in pud_free_pmd_page for static key logic */ table = pte_offset_kernel(pmdp, addr); pmd_clear(pmdp); __flush_tlb_kernel_pgtable(addr); - if (static_branch_unlikely(&arm64_ptdump_lock_key) && acquire_mmap_lock) { - mmap_read_lock(&init_mm); - mmap_read_unlock(&init_mm); - } - pte_free_kernel(NULL, table); return 1; } -int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) -{ - /* If ptdump is walking the pagetables, acquire init_mm.mmap_lock */ - return __pmd_free_pte_page(pmdp, addr, /* acquire_mmap_lock = */ true); -} - int pud_free_pmd_page(pud_t *pudp, unsigned long addr) { pmd_t *table; @@ -1911,36 +1896,16 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) } table = pmd_offset(pudp, addr); - - /* - * Our objective is to prevent ptdump from reading a PMD table which has - * been freed. In this race, if pud_free_pmd_page observes the key on - * (which got flipped by ptdump) then the mmap lock sequence here will, - * as a result of the mmap write lock/unlock sequence in ptdump, give - * us the correct synchronization. If not, this means that ptdump has - * yet not started walking the pagetables - the sequence of barriers - * issued by __flush_tlb_kernel_pgtable() guarantees that ptdump will - * observe an empty PUD. - */ - pud_clear(pudp); - __flush_tlb_kernel_pgtable(addr); - if (static_branch_unlikely(&arm64_ptdump_lock_key)) { - mmap_read_lock(&init_mm); - mmap_read_unlock(&init_mm); - } - pmdp = table; next = addr; end = addr + PUD_SIZE; do { if (pmd_present(pmdp_get(pmdp))) - /* - * PMD has been isolated, so ptdump won't see it. No - * need to acquire init_mm.mmap_lock. - */ - __pmd_free_pte_page(pmdp, next, /* acquire_mmap_lock = */ false); + pmd_free_pte_page(pmdp, next); } while (pmdp++, next += PMD_SIZE, next != end); + pud_clear(pudp); + __flush_tlb_kernel_pgtable(addr); pmd_free(NULL, table); return 1; } diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index 1c20144700d7..5a76c59b5ada 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -283,13 +283,6 @@ void note_page_flush(struct ptdump_state *pt_st) note_page(pt_st, 0, -1, pte_val(pte_zero)); } -static void arm64_ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm) -{ - static_branch_inc(&arm64_ptdump_lock_key); - ptdump_walk_pgd(st, mm, NULL); - static_branch_dec(&arm64_ptdump_lock_key); -} - void ptdump_walk(struct seq_file *s, struct ptdump_info *info) { unsigned long end = ~0UL; @@ -318,7 +311,7 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info) } }; - arm64_ptdump_walk_pgd(&st.ptdump, info->mm); + ptdump_walk_pgd(&st.ptdump, info->mm, NULL); } static void __init ptdump_initialize(void) @@ -360,7 +353,7 @@ bool ptdump_check_wx(void) } }; - arm64_ptdump_walk_pgd(&st.ptdump, &init_mm); + ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); if (st.wx_pages || st.uxn_pages) { pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n", diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S index 808019c3b7ac..9bd3e513c89b 100644 --- a/arch/microblaze/kernel/head.S +++ b/arch/microblaze/kernel/head.S @@ -39,6 +39,8 @@ #include <asm/processor.h> .section .data +/* The MMU requires a page aligned page directory. */ +.align 12 .global swapper_pg_dir swapper_pg_dir: .space PAGE_SIZE diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 54b7ecf375b5..3280b7968cab 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -699,7 +699,7 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf, if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return -EINVAL; - if (count > sizeof(kbuf)) + if (count == 0 || count > sizeof(kbuf)) return -EINVAL; if (copy_from_user(kbuf, buf, count)) diff --git a/arch/powerpc/platforms/pseries/papr-phy-attest.c b/arch/powerpc/platforms/pseries/papr-phy-attest.c index 20a0e1581302..350ba26e5962 100644 --- a/arch/powerpc/platforms/pseries/papr-phy-attest.c +++ b/arch/powerpc/platforms/pseries/papr-phy-attest.c @@ -230,10 +230,17 @@ static long papr_phy_attest_create_handle(struct papr_phy_attest_io_block __user return -ENOMEM; if (copy_from_user(¶ms->cmd, ulc, - sizeof(struct papr_phy_attest_io_block))) + sizeof(struct papr_phy_attest_io_block))) { + kfree(params); return -EFAULT; + } params->cmd_len = be32_to_cpu(params->cmd.length); + if (params->cmd_len == 0 || params->cmd_len > sizeof(params->cmd)) { + kfree(params); + return -EINVAL; + } + seq = (struct papr_rtas_sequence) { .begin = phy_attest_sequence_begin, .end = phy_attest_sequence_end, @@ -246,6 +253,9 @@ static long papr_phy_attest_create_handle(struct papr_phy_attest_io_block __user &papr_phy_attest_handle_ops, "[papr-physical-attestation]"); + if (fd < 0) + kfree(params); + return fd; } diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 84e4ffe957a8..d11a64a086c1 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -132,7 +132,7 @@ static int pseries_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) /* First integer stores max config */ max_config_vfs = of_read_number(&max_vfs[0], 1); - if (max_config_vfs < num_vfs && num_vfs > MAX_VFS_FOR_MAP_PE) { + if (max_config_vfs < num_vfs || num_vfs > MAX_VFS_FOR_MAP_PE) { dev_err(&pdev->dev, "Num VFs %x > %x Configurable VFs\n", num_vfs, (num_vfs > MAX_VFS_FOR_MAP_PE) ? diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index c172f9b212d1..b4182ca4435f 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -440,6 +440,7 @@ struct kvm_vcpu_arch { bool skey_enabled; /* Indicator if the access registers have been loaded from guest */ bool acrs_loaded; + bool initialized; struct kvm_s390_pv_vcpu pv; union diag318_info diag318_info; struct kvm_s390_mmu_cache *mc; diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index ed4259d17629..3f2d6e8902d7 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -755,13 +755,15 @@ int dat_cond_set_storage_key(struct kvm_s390_mmu_cache *mmc, union asce asce, gf return rc; } -int dat_reset_reference_bit(union asce asce, gfn_t gfn) +int dat_reset_reference_bit(union asce asce, gfn_t gfn, union skey *skey) { union pgste pgste, old; union crste *crstep; union pte *ptep; int rc; + skey->skey = 0; + rc = dat_entry_walk(NULL, gfn, asce, DAT_WALK_ANY, TABLE_TYPE_PAGE_TABLE, &crstep, &ptep); if (rc) return rc; @@ -771,21 +773,23 @@ int dat_reset_reference_bit(union asce asce, gfn_t gfn) if (!crste.h.fc || !crste.s.fc1.pr) return 0; - return page_reset_referenced(large_crste_to_phys(*crstep, gfn)); + skey->skey = page_reset_referenced(large_crste_to_phys(*crstep, gfn)) << 1; + return 0; } old = pgste_get_lock(ptep); pgste = old; if (!ptep->h.i) { - rc = page_reset_referenced(pte_origin(*ptep)); - pgste.hr = rc >> 1; + skey->skey = page_reset_referenced(pte_origin(*ptep)) << 1; + pgste.hr = skey->r; } - rc |= (pgste.gr << 1) | pgste.gc; + skey->r |= pgste.gr; + skey->c |= pgste.gc; pgste.gr = 0; dat_update_ptep_sd(old, pgste, ptep); pgste_set_unlock(ptep, pgste); - return rc; + return 0; } static long dat_reset_skeys_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_walk *walk) @@ -846,6 +850,7 @@ static long _dat_slot_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_wal struct slot_priv *p = walk->priv; union crste dummy = { .val = p->token }; union pte new_pte, pte = READ_ONCE(*ptep); + union pgste pgste; new_pte = _PTE_TOK(dummy.tok.type, dummy.tok.par); @@ -853,7 +858,11 @@ static long _dat_slot_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_wal if (pte.val == new_pte.val) return 0; - dat_ptep_xchg(ptep, new_pte, gfn, walk->asce, false); + pgste = pgste_get_lock(ptep); + pgste = __dat_ptep_xchg(ptep, pgste, new_pte, gfn, walk->asce, false); + pgste.cmma_d = 0; + pgste_set_unlock(ptep, pgste); + return 0; } diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h index fad605305e05..141ee7b9f019 100644 --- a/arch/s390/kvm/dat.h +++ b/arch/s390/kvm/dat.h @@ -537,7 +537,7 @@ int dat_set_storage_key(struct kvm_s390_mmu_cache *mc, union asce asce, gfn_t gf union skey skey, bool nq); int dat_cond_set_storage_key(struct kvm_s390_mmu_cache *mmc, union asce asce, gfn_t gfn, union skey skey, union skey *oldkey, bool nq, bool mr, bool mc); -int dat_reset_reference_bit(union asce asce, gfn_t gfn); +int dat_reset_reference_bit(union asce asce, gfn_t gfn, union skey *skey); long dat_reset_skeys(union asce asce, gfn_t start); unsigned long dat_get_ptval(struct page_table *table, struct ptval_param param); diff --git a/arch/s390/kvm/faultin.c b/arch/s390/kvm/faultin.c index fee80047bd94..3cc45f7f5b2d 100644 --- a/arch/s390/kvm/faultin.c +++ b/arch/s390/kvm/faultin.c @@ -91,9 +91,9 @@ int kvm_s390_faultin_gfn(struct kvm_vcpu *vcpu, struct kvm *kvm, struct guest_fa /* Access outside memory, addressing exception. */ if (is_noslot_pfn(f->pfn)) return PGM_ADDRESSING; - /* Signal pending: try again. */ - if (f->pfn == KVM_PFN_ERR_SIGPENDING) - return -EAGAIN; + /* Fatal signal pending: bail out. */ + if (is_sigpending_pfn(f->pfn)) + return -EINTR; /* Check if it's read-only memory; don't try to actually handle that case. */ if (f->pfn == KVM_PFN_ERR_RO_FAULT) return -EOPNOTSUPP; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 7514d9e2403c..8f24bcd1a6d3 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -45,13 +45,16 @@ static struct kvm_s390_gib *gib; static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id) { struct esca_block *sca = vcpu->kvm->arch.sca; - union esca_sigp_ctrl sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl; + union esca_sigp_ctrl sigp_ctrl; if (!kvm_s390_test_cpuflags(vcpu, CPUSTAT_ECALL_PEND)) return 0; + if (kvm_is_ucontrol(vcpu->kvm)) + return 0; BUG_ON(!kvm_s390_use_sca_entries()); + sigp_ctrl = sca->cpu[vcpu->vcpu_id].sigp_ctrl; if (src_id) *src_id = sigp_ctrl.scn; @@ -60,13 +63,16 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id) static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) { - struct esca_block *sca = vcpu->kvm->arch.sca; - union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; union esca_sigp_ctrl old_val, new_val = {.scn = src_id, .c = 1}; + struct esca_block *sca = vcpu->kvm->arch.sca; + union esca_sigp_ctrl *sigp_ctrl; int expect, rc; BUG_ON(!kvm_s390_use_sca_entries()); + if (kvm_is_ucontrol(vcpu->kvm)) + return -EINVAL; + sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; old_val = READ_ONCE(*sigp_ctrl); old_val.c = 0; @@ -84,10 +90,13 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) static void sca_clear_ext_call(struct kvm_vcpu *vcpu) { struct esca_block *sca = vcpu->kvm->arch.sca; - union esca_sigp_ctrl *sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; + union esca_sigp_ctrl *sigp_ctrl; - if (!kvm_s390_use_sca_entries()) + if (!kvm_s390_use_sca_entries() || !vcpu->arch.initialized || kvm_is_ucontrol(vcpu->kvm)) return; + + /* Initialize after the above check, to prevent going out of bounds */ + sigp_ctrl = &sca->cpu[vcpu->vcpu_id].sigp_ctrl; kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND); WRITE_ONCE(sigp_ctrl->value, 0); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 150b5dd2170e..518a69c55e85 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -571,7 +571,7 @@ static int kvm_s390_keyop(struct kvm_s390_mmu_cache *mc, struct kvm *kvm, int op switch (op) { case KVM_S390_KEYOP_SSKE: r = dat_cond_set_storage_key(mc, asce, gfn, skey, &skey, 0, 0, 0); - if (r >= 0) + if (r == 0 || r == 1) return skey.skey; break; case KVM_S390_KEYOP_ISKE: @@ -580,14 +580,14 @@ static int kvm_s390_keyop(struct kvm_s390_mmu_cache *mc, struct kvm *kvm, int op return skey.skey; break; case KVM_S390_KEYOP_RRBE: - r = dat_reset_reference_bit(asce, gfn); - if (r > 0) - return r << 1; + r = dat_reset_reference_bit(asce, gfn, &skey); + if (!r) + return skey.skey; break; default: return -EINVAL; } - return r; + return r > 0 ? -EFAULT : r; } /* Section: device related */ @@ -1219,8 +1219,8 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) /* * Must be called with kvm->srcu held to avoid races on memslots, and with - * kvm->slots_lock to avoid races with ourselves, kvm_s390_vm_stop_migration(), - * and kvm_s390_get_cmma_bits(). + * kvm->slots_arch_lock to avoid races with ourselves, + * kvm_s390_vm_stop_migration(), and kvm_s390_get_cmma_bits(). */ static int kvm_s390_vm_start_migration(struct kvm *kvm) { @@ -1265,7 +1265,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) } /* - * Must be called with kvm->slots_lock to avoid races with ourselves, + * Must be called with kvm->slots_arch_lock to avoid races with ourselves, * kvm_s390_vm_start_migration() and kvm_s390_get_cmma_bits(). */ static int kvm_s390_vm_stop_migration(struct kvm *kvm) @@ -1300,7 +1300,9 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm, { int res = -ENXIO; - mutex_lock(&kvm->slots_lock); + guard(srcu)(&kvm->srcu); + guard(mutex)(&kvm->slots_arch_lock); + switch (attr->attr) { case KVM_S390_VM_MIGRATION_START: res = kvm_s390_vm_start_migration(kvm); @@ -1311,7 +1313,6 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm, default: break; } - mutex_unlock(&kvm->slots_lock); return res; } @@ -2214,7 +2215,7 @@ static int kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) } kvfree(keys); - return r; + return r <= 0 ? r : -EFAULT; } static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) @@ -2276,7 +2277,7 @@ static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) kvm_s390_free_mmu_cache(mc); out: kvfree(keys); - return r; + return r <= 0 ? r : -EFAULT; } /* @@ -2386,7 +2387,7 @@ static int kvm_s390_set_cmma_bits(struct kvm *kvm, set_bit(GMAP_FLAG_USES_CMM, &kvm->arch.gmap->flags); - return r; + return r <= 0 ? r : -EFAULT; } /** @@ -2934,6 +2935,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; + r = -EINVAL; + if (kvm_is_ucontrol(kvm)) + break; r = -EFAULT; if (copy_from_user(&s390int, argp, sizeof(s390int))) break; @@ -2998,9 +3002,8 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) r = -EFAULT; if (copy_from_user(&args, argp, sizeof(args))) break; - mutex_lock(&kvm->slots_lock); - r = kvm_s390_get_cmma_bits(kvm, &args); - mutex_unlock(&kvm->slots_lock); + scoped_guard(mutex, &kvm->slots_arch_lock) + r = kvm_s390_get_cmma_bits(kvm, &args); if (!r) { r = copy_to_user(argp, &args, sizeof(args)); if (r) @@ -3014,9 +3017,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) r = -EFAULT; if (copy_from_user(&args, argp, sizeof(args))) break; - mutex_lock(&kvm->slots_lock); + mutex_lock(&kvm->slots_arch_lock); r = kvm_s390_set_cmma_bits(kvm, &args); - mutex_unlock(&kvm->slots_lock); + mutex_unlock(&kvm->slots_arch_lock); break; } case KVM_S390_PV_COMMAND: { @@ -3247,7 +3250,8 @@ static void kvm_s390_crypto_init(struct kvm *kvm) static void sca_dispose(struct kvm *kvm) { - free_pages_exact(kvm->arch.sca, sizeof(*kvm->arch.sca)); + if (kvm->arch.sca) + free_pages_exact(kvm->arch.sca, sizeof(*kvm->arch.sca)); kvm->arch.sca = NULL; } @@ -3461,7 +3465,7 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu) { struct esca_block *sca = vcpu->kvm->arch.sca; - if (!kvm_s390_use_sca_entries()) + if (!kvm_s390_use_sca_entries() || !vcpu->arch.initialized) return; clear_bit_inv(vcpu->vcpu_id, (unsigned long *)sca->mcn); @@ -3481,8 +3485,8 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu) if (!kvm_s390_use_sca_entries()) return; + WRITE_ONCE(sca->cpu[vcpu->vcpu_id].sda, virt_to_phys(vcpu->arch.sie_block)); set_bit_inv(vcpu->vcpu_id, (unsigned long *)sca->mcn); - sca->cpu[vcpu->vcpu_id].sda = virt_to_phys(vcpu->arch.sie_block); } static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id) @@ -3613,6 +3617,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) if (test_kvm_facility(vcpu->kvm, 74) || vcpu->kvm->arch.user_instr0 || vcpu->kvm->arch.user_operexec) vcpu->arch.sie_block->ictl |= ICTL_OPEREXC; + + /* Pairs with smp_load_acquire() in kvm_arch_vcpu_ioctl_run() and kvm_arch_vcpu_ioctl() */ + smp_store_release(&vcpu->arch.initialized, true); } static bool kvm_has_pckmo_subfunc(struct kvm *kvm, unsigned long nr) @@ -3674,7 +3681,8 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu) { - free_page((unsigned long)phys_to_virt(vcpu->arch.sie_block->cbrlo)); + if (vcpu->arch.sie_block->cbrlo) + free_page((unsigned long)phys_to_virt(vcpu->arch.sie_block->cbrlo)); vcpu->arch.sie_block->cbrlo = 0; } @@ -3792,21 +3800,21 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) return 0; } +DEFINE_FREE(sie_page, struct sie_page *, if (_T) free_page((unsigned long)(_T))) + int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { - struct sie_page *sie_page; + struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL; + struct sie_page *sie_page __free(sie_page) = NULL; int rc; BUILD_BUG_ON(sizeof(struct sie_page) != 4096); - vcpu->arch.mc = kvm_s390_new_mmu_cache(); - if (!vcpu->arch.mc) + mc = kvm_s390_new_mmu_cache(); + if (!mc) return -ENOMEM; sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL_ACCOUNT); - if (!sie_page) { - kvm_s390_free_mmu_cache(vcpu->arch.mc); - vcpu->arch.mc = NULL; + if (!sie_page) return -ENOMEM; - } vcpu->arch.sie_block = &sie_page->sie_block; vcpu->arch.sie_block->itdba = virt_to_phys(&sie_page->itdb); @@ -3848,10 +3856,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; if (kvm_is_ucontrol(vcpu->kvm)) { - rc = -ENOMEM; vcpu->arch.gmap = gmap_new_child(vcpu->kvm->arch.gmap, -1UL); if (!vcpu->arch.gmap) - goto out_free_sie_block; + return -ENOMEM; } VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%p, sie block at 0x%p", @@ -3859,20 +3866,19 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); rc = kvm_s390_vcpu_setup(vcpu); - if (rc) - goto out_ucontrol_uninit; + if (rc) { + if (kvm_is_ucontrol(vcpu->kvm)) { + scoped_guard(spinlock, &vcpu->kvm->arch.gmap->children_lock) + gmap_remove_child(vcpu->arch.gmap); + vcpu->arch.gmap = gmap_put(vcpu->arch.gmap); + } + return rc; + } + vcpu->arch.mc = no_free_ptr(mc); + sie_page = NULL; kvm_s390_update_topology_change_report(vcpu->kvm, 1); return 0; - -out_ucontrol_uninit: - if (kvm_is_ucontrol(vcpu->kvm)) { - gmap_remove_child(vcpu->arch.gmap); - vcpu->arch.gmap = gmap_put(vcpu->arch.gmap); - } -out_free_sie_block: - free_page((unsigned long)(vcpu->arch.sie_block)); - return rc; } int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) @@ -5039,6 +5045,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->kvm_dirty_regs & ~KVM_SYNC_S390_VALID_FIELDS) return -EINVAL; + /* Pairs with smp_store_release() in kvm_arch_vcpu_postcreate() */ + if (!smp_load_acquire(&vcpu->arch.initialized)) + return -EINVAL; + vcpu_load(vcpu); if (guestdbg_exit_pending(vcpu)) { @@ -5447,6 +5457,8 @@ long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, struct kvm_s390_interrupt s390int; struct kvm_s390_irq s390irq = {}; + if (kvm_is_ucontrol(vcpu->kvm)) + return -EINVAL; if (copy_from_user(&s390int, argp, sizeof(s390int))) return -EFAULT; if (s390int_to_s390irq(&s390int, &s390irq)) @@ -5523,6 +5535,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, long r; u16 rc, rrc; + /* Pairs with smp_store_release() in kvm_arch_vcpu_postcreate() */ + if (!smp_load_acquire(&vcpu->arch.initialized)) + return -EINVAL; + vcpu_load(vcpu); switch (ioctl) { @@ -5794,14 +5810,30 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, return 0; } +static long cmma_d_count_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_walk *walk) +{ + union pgste pgste; + + pgste = pgste_get_lock(ptep); + if (pgste.cmma_d) { + pgste.cmma_d = 0; + atomic64_dec(walk->priv); + } + pgste_set_unlock(ptep, pgste); + return 0; +} + void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - struct kvm_s390_mmu_cache *mc = NULL; + const struct dat_walk_ops ops = { .pte_entry = cmma_d_count_pte, }; + struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL; int rc = 0; + guard(mutex)(&kvm->slots_arch_lock); + if (change == KVM_MR_FLAGS_ONLY) return; @@ -5812,6 +5844,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, } scoped_guard(write_lock, &kvm->mmu_lock) { + if (kvm->arch.migration_mode && kvm->arch.use_cmma && old) { + _dat_walk_gfn_range(old->base_gfn, old->base_gfn + old->npages, + kvm->arch.gmap->asce, &ops, DAT_WALK_IGN_HOLES, + &kvm->arch.cmma_dirty_pages); + } + switch (change) { case KVM_MR_DELETE: rc = dat_delete_slot(mc, kvm->arch.gmap->asce, old->base_gfn, old->npages); @@ -5833,7 +5871,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, out: if (rc) pr_warn("failed to commit memory region\n"); - kvm_s390_free_mmu_cache(mc); return; } diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index ad0ddc433a73..b1ba24c346ef 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -289,6 +289,7 @@ static int handle_iske(struct kvm_vcpu *vcpu) static int handle_rrbe(struct kvm_vcpu *vcpu) { unsigned long gaddr; + union skey skey; int reg1, reg2; int rc; @@ -307,12 +308,12 @@ static int handle_rrbe(struct kvm_vcpu *vcpu) gaddr = kvm_s390_logical_to_effective(vcpu, gaddr); gaddr = kvm_s390_real_to_abs(vcpu, gaddr); scoped_guard(read_lock, &vcpu->kvm->mmu_lock) - rc = dat_reset_reference_bit(vcpu->arch.gmap->asce, gpa_to_gfn(gaddr)); + rc = dat_reset_reference_bit(vcpu->arch.gmap->asce, gpa_to_gfn(gaddr), &skey); if (rc > 0) return kvm_s390_inject_program_int(vcpu, rc); if (rc < 0) return rc; - kvm_s390_set_psw_cc(vcpu, rc); + kvm_s390_set_psw_cc(vcpu, (skey.skey >> 1) & 3); return 0; } @@ -1260,8 +1261,9 @@ static int handle_essa(struct kvm_vcpu *vcpu) /* Retry the ESSA instruction */ kvm_s390_retry_instr(vcpu); } else { - scoped_guard(read_lock, &vcpu->kvm->mmu_lock) - i = __do_essa(vcpu, orc); + scoped_guard(mutex, &vcpu->kvm->slots_arch_lock) + scoped_guard(read_lock, &vcpu->kvm->mmu_lock) + i = __do_essa(vcpu, orc); if (i < 0) return i; /* Account for the possible extra cbrl entry */ diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 1beacc841ca8..b02e0159d3cd 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -244,6 +244,24 @@ static void kvm_s390_clear_pv_state(struct kvm *kvm) kvm->arch.pv.stor_var = NULL; } +static void kvm_s390_pv_dispose_cpu(struct kvm_vcpu *vcpu, bool free_stor_base) +{ + if (free_stor_base) + free_pages(vcpu->arch.pv.stor_base, get_order(uv_info.guest_cpu_stor_len)); + free_page((unsigned long)sida_addr(vcpu->arch.sie_block)); + vcpu->arch.sie_block->pv_handle_cpu = 0; + vcpu->arch.sie_block->pv_handle_config = 0; + memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv)); + vcpu->arch.sie_block->sdf = 0; + /* + * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0). + * Use the reset value of gbea to avoid leaking the kernel pointer of + * the just freed sida. + */ + vcpu->arch.sie_block->gbea = 1; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); +} + int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) { int cc; @@ -258,24 +276,9 @@ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", *rc, *rrc); /* Intended memory leak for something that should never happen. */ - if (!cc) - free_pages(vcpu->arch.pv.stor_base, - get_order(uv_info.guest_cpu_stor_len)); - - free_page((unsigned long)sida_addr(vcpu->arch.sie_block)); - vcpu->arch.sie_block->pv_handle_cpu = 0; - vcpu->arch.sie_block->pv_handle_config = 0; - memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv)); - vcpu->arch.sie_block->sdf = 0; - /* - * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0). - * Use the reset value of gbea to avoid leaking the kernel pointer of - * the just freed sida. - */ - vcpu->arch.sie_block->gbea = 1; - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + kvm_s390_pv_dispose_cpu(vcpu, !cc); - return cc ? EIO : 0; + return cc ? -EIO : 0; } int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) @@ -319,9 +322,7 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) uvcb.header.rrc); if (cc) { - u16 dummy; - - kvm_s390_pv_destroy_cpu(vcpu, &dummy, &dummy); + kvm_s390_pv_dispose_cpu(vcpu, true); return -EIO; } @@ -809,7 +810,7 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak, return -EAGAIN; } - if (ret && ret != -EAGAIN) + if (ret && ret != -EAGAIN && ret != -EINTR) KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x", uvcb.gaddr, *rc, *rrc); return ret; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index c6d996593f32..253f0a585927 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -937,6 +937,8 @@ SYM_CODE_START(paranoid_entry) IBRS_ENTER save_reg=%r15 UNTRAIN_RET_FROM_CALL + HANDLE_INTR_SAFERET 8(%rsp) + RET SYM_CODE_END(paranoid_entry) @@ -1039,6 +1041,11 @@ SYM_CODE_START(error_entry) movl %ecx, %eax /* zero extend */ cmpq %rax, RIP+8(%rsp) je .Lbstep_iret + + VALIDATE_UNRET_END + + HANDLE_INTR_SAFERET 8(%rsp) + cmpq $.Lgs_change, RIP+8(%rsp) jne .Lerror_entry_done_lfence @@ -1057,7 +1064,6 @@ SYM_CODE_START(error_entry) FENCE_SWAPGS_KERNEL_ENTRY CALL_DEPTH_ACCOUNT leaq 8(%rsp), %rax /* return pt_regs pointer */ - VALIDATE_UNRET_END RET .Lbstep_iret: diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5f6c1ce9673b..6db5b5f79df9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1858,7 +1858,7 @@ struct kvm_x86_ops { * Can potentially get non-canonical addresses through INVLPGs, which * the implementation may choose to ignore if appropriate. */ - void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr); + void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr, bool *full); /* * Flush any TLB entries created by the guest. Like tlb_flush_gva(), diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index b68892e6d58c..2ea6591bc7b9 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -12,6 +12,7 @@ #include <asm/msr-index.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> +#include <asm/ptrace-abi.h> /* * Call depth tracking for Intel SKL CPUs to address the RSB underflow @@ -176,6 +177,50 @@ add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; +/* + * Helper for detecting if an interrupt occurred at an unsafe location within + * Safe-RET. If Safe-RET is interrupted after the CALL or LEA the RSB may get + * poisoned by the interrupt handler. + * + * The Safe-RET sequence is: + * + * CALL + * LEA 8(%RSP), %RSP + * RET + * + * The two CMPs below check whether RIP points to after the CALL or after the + * LEA. + * + * The LFENCE below is to address this particular speculation case: + * + * 1. Userspace runs and poisons the BTB around the safe-RET routine + * + * 2. Userspace triggers some kind of exception + * + * 3. Kernel executes error_entry() and mis-speculates the branch into thinking + * it actually came from kernel space + * + * 4. The kernel then further mis-speculates that the exception occurred due + * to an interrupted safe-RET + * + * 5. The handle_interrupted_saferet() routine speculatively executes and + * speculatively does a safe-RET. But this is unsafe since it was never + * untrained. + * + * The LFENCE fixes this by ensuring step 5 is never reached speculatively. + * Note that this LFENCE only occurs if safe-RET was actually interrupted (so + * it's outside of the normal path). + */ +#define __HANDLE_INTR_SAFERET(name, pt_regs) \ + cmpq $(name), RIP+pt_regs; \ + jb 1f; \ + cmpq $(name)+5, RIP+pt_regs; \ + ja 1f; \ + lfence; \ + leaq pt_regs, %rdi; \ + call handle_interrupted_saferet; \ + 1: + #ifdef __ASSEMBLER__ /* @@ -293,6 +338,14 @@ #define UNTRAIN_RET_FROM_CALL \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL) +.macro HANDLE_INTR_SAFERET pt_regs +#ifdef CONFIG_MITIGATION_SRSO + ALTERNATIVE_2 "", \ + __stringify(__HANDLE_INTR_SAFERET(srso_safe_ret, \pt_regs)), X86_FEATURE_SRSO, \ + __stringify(__HANDLE_INTR_SAFERET(srso_alias_safe_ret, \pt_regs)), X86_FEATURE_SRSO_ALIAS + +#endif +.endm .macro CALL_DEPTH_ACCOUNT #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING @@ -625,6 +678,10 @@ static __always_inline void x86_idle_clear_cpu_buffers(void) x86_clear_cpu_buffers(); } +void srso_safe_ret(void); +void srso_alias_safe_ret(void); +void handle_interrupted_saferet(struct pt_regs *regs); + #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d9af230c0512..82436b3534fa 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -3775,3 +3775,42 @@ void __warn_thunk(void) { WARN_ONCE(1, "Unpatched return thunk in use. This should not happen!\n"); } + +#ifdef CONFIG_MITIGATION_SRSO +/* + * Called during exception/interrupt entry if interrupted during the + * safe-RET sequence. The safe-RET sequence consists of 3 instructions: + * + * CALL + * LEA 8(%RSP), %RSP + * RET + * + * An interrupt after the CALL or after the LEA could potentially lead + * to branch predictor poisoning and results in the sequence not being + * able to be safely resumed. + * + * Therefore, modify the regs state as if the remaining part of the + * safe-RET sequence executed so the interrupt returns back to the + * desired return target, instead of the to the safe-RET sequence. + */ +void noinstr handle_interrupted_saferet(struct pt_regs *regs) +{ + unsigned long rip = regs->ip; + + if (rip == (unsigned long) srso_safe_ret || + rip == (unsigned long) srso_alias_safe_ret) { + /* Modify stack pointer as if LEA executed: */ + regs->sp += 8; + } + + /* + * Adjust registers as if RET executed: + * + * 1. Read the return address off the stack and into rIP: + */ + regs->ip = *(unsigned long *)(regs->sp); + + /* 2. Pop rIP off the stack: */ + regs->sp += 8; +} +#endif /* CONFIG_MITIGATION_SRSO */ diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index fd4eb1e561f7..d8736b5dfcd3 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1974,6 +1974,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) u64 entries[KVM_HV_TLB_FLUSH_FIFO_SIZE]; int i, j, count; gva_t gva; + bool full = false; if (!tdp_enabled || !hv_vcpu) return -EINVAL; @@ -1982,7 +1983,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) count = kfifo_out(&tlb_flush_fifo->entries, entries, KVM_HV_TLB_FLUSH_FIFO_SIZE); - for (i = 0; i < count; i++) { + for (i = 0; i < count && !full; i++) { if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) goto out_flush_all; @@ -1991,11 +1992,11 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) * pages to flush. */ gva = entries[i] & PAGE_MASK; - for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) { + for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1 && !full; j++) { if (is_noncanonical_invlpg_address(gva + j * PAGE_SIZE, vcpu)) continue; - kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE); + kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE, &full); } ++vcpu->stat.tlb_flush; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 66e69d2a41b3..a61750f8e1e3 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2442,6 +2442,9 @@ static union kvm_mmu_page_role kvm_mmu_child_role(u64 *sptep, bool direct, role.direct = direct; role.passthrough = 0; + WARN_ON_ONCE(role.invalid); + role.invalid = 0; + /* * If the guest has 4-byte PTEs then that means it's using 32-bit, * 2-level, non-PAE paging. KVM shadows such guests with PAE paging @@ -6652,7 +6655,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, if (is_noncanonical_invlpg_address(addr, vcpu)) return; - kvm_x86_call(flush_tlb_gva)(vcpu, addr); + kvm_x86_call(flush_tlb_gva)(vcpu, addr, NULL); } if (!mmu->sync_spte) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 944aaea6501f..0f0ea7896af5 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -97,6 +97,8 @@ static u64 sev_supported_vmsa_features __ro_after_init; static u8 sev_enc_bit; static DECLARE_RWSEM(sev_deactivate_lock); static DEFINE_MUTEX(sev_bitmap_lock); +/* Protects kvm_sev_info's enc_context_owner, mirror_vms and mirror_entry. */ +static DEFINE_MUTEX(sev_mirror_lock); unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned int max_sev_es_asid; @@ -2018,7 +2020,6 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) dst->asid = src->asid; dst->handle = src->handle; dst->pages_locked = src->pages_locked; - dst->enc_context_owner = src->enc_context_owner; dst->es_active = src->es_active; dst->vmsa_features = src->vmsa_features; @@ -2026,11 +2027,12 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) src->active = false; src->handle = 0; src->pages_locked = 0; - src->enc_context_owner = NULL; src->es_active = false; list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); + mutex_lock(&sev_mirror_lock); + /* * If this VM has mirrors, "transfer" each mirror's refcount of the * source to the destination (this KVM). The caller holds a reference @@ -2047,12 +2049,15 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) * If this VM is a mirror, remove the old mirror from the owners list * and add the new mirror to the list. */ - if (is_mirroring_enc_context(dst_kvm)) { - struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(dst->enc_context_owner); + if (is_mirroring_enc_context(src_kvm)) { + struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(src->enc_context_owner); + dst->enc_context_owner = src->enc_context_owner; + src->enc_context_owner = NULL; list_del(&src->mirror_entry); list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms); } + mutex_unlock(&sev_mirror_lock); kvm_for_each_vcpu(i, dst_vcpu, dst_kvm) { dst_svm = to_svm(dst_vcpu); @@ -2871,11 +2876,14 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) * disappear until we're done with it */ source_sev = to_kvm_sev_info(source_kvm); - kvm_get_kvm(source_kvm); - list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms); /* Set enc_context_owner and copy its encryption context over */ + mutex_lock(&sev_mirror_lock); + kvm_get_kvm(source_kvm); + list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms); mirror_sev->enc_context_owner = source_kvm; + mutex_unlock(&sev_mirror_lock); + mirror_sev->active = true; mirror_sev->asid = source_sev->asid; mirror_sev->fd = source_sev->fd; @@ -2963,11 +2971,19 @@ void sev_vm_destroy(struct kvm *kvm) * Note, mirror VMs don't support registering encrypted regions. */ if (is_mirroring_enc_context(kvm)) { - struct kvm *owner_kvm = sev->enc_context_owner; + struct kvm *owner_kvm; - mutex_lock(&owner_kvm->lock); + mutex_lock(&sev_mirror_lock); + owner_kvm = sev->enc_context_owner; list_del(&sev->mirror_entry); - mutex_unlock(&owner_kvm->lock); + sev->enc_context_owner = NULL; + + /* + * The reference to owner_kvm cannot move after sev_mirror_lock is + * released. Release it before kvm_put_kvm() so that owner_kvm is + * never destroyed inside sev_mirror_lock. + */ + mutex_unlock(&sev_mirror_lock); kvm_put_kvm(owner_kvm); return; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d0971685034b..60495447f0ca 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4227,18 +4227,31 @@ static void svm_flush_tlb_all(struct kvm_vcpu *vcpu) svm_flush_tlb_asid(vcpu); } -static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva) +static void svm_flush_tlb_guest(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); + kvm_register_mark_dirty(vcpu, VCPU_REG_ERAPS); - invlpga(gva, svm->vmcb->control.asid); + svm_flush_tlb_asid(vcpu); } -static void svm_flush_tlb_guest(struct kvm_vcpu *vcpu) +static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva, bool *full) { - kvm_register_mark_dirty(vcpu, VCPU_REG_ERAPS); + struct vcpu_svm *svm = to_svm(vcpu); - svm_flush_tlb_asid(vcpu); + /* + * INVLPGA has had errata on Genoa and Turin, and even on older + * generations there were reports of Windows BSODs if INVLPGA + * was used for Hyper-V tlbflush. Use it only for shadow paging + * where it seems to be okay. + */ + if (!npt_enabled) { + invlpga(gva, svm->vmcb->control.asid); + return; + } + + svm_flush_tlb_guest(vcpu); + if (full) + *full = true; } static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 716be21fba33..d63e5878988a 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -109,6 +109,7 @@ struct kvm_sev_info { u64 ap_jump_table; /* SEV-ES AP Jump Table address */ u64 vmsa_features; u16 ghcb_version; /* Highest guest GHCB protocol version allowed */ + /* The three fields below are protected by sev_mirror_lock */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ struct list_head mirror_vms; /* List of VMs mirroring */ struct list_head mirror_entry; /* Use as a list entry of mirrors */ diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 83d9921277ea..f204a0fc0a57 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -535,12 +535,12 @@ static void vt_flush_tlb_current(struct kvm_vcpu *vcpu) vmx_flush_tlb_current(vcpu); } -static void vt_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +static void vt_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr, bool *full) { if (is_td_vcpu(vcpu)) return; - vmx_flush_tlb_gva(vcpu, addr); + vmx_flush_tlb_gva(vcpu, addr, full); } static void vt_flush_tlb_guest(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index cc75feec05da..b8d745f6fd22 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -3361,7 +3361,7 @@ void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) vpid_sync_context(vmx_get_current_vpid(vcpu)); } -void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr, bool *full) { /* * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 409858074246..17595d52985c 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -82,7 +82,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); bool vmx_get_if_flag(struct kvm_vcpu *vcpu); void vmx_flush_tlb_all(struct kvm_vcpu *vcpu); void vmx_flush_tlb_current(struct kvm_vcpu *vcpu); -void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr); +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr, bool *full); void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu); void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask); u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 8f1fed0c3b83..f9ca1d8eabca 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -207,10 +207,24 @@ __EXPORT_THUNK(srso_alias_untrain_ret) .pushsection .text..__x86.rethunk_safe SYM_CODE_START_NOALIGN(srso_alias_safe_ret) + + /* + * Tell objtool that those are not function pointers referenced by + * __HANDLE_INTR_SAFERET(). Below too. + */ + ANNOTATE_NOENDBR + + /* + * Safe-RET sequence. If you need to change it, adjust + * handle_interrupted_saferet() too. + */ lea 8(%_ASM_SP), %_ASM_SP UNWIND_HINT_FUNC + + ANNOTATE_NOENDBR ANNOTATE_UNRET_SAFE ret + /* End of Safe-RET sequence */ int3 SYM_FUNC_END(srso_alias_safe_ret) @@ -245,8 +259,14 @@ SYM_CODE_START_LOCAL_NOALIGN(srso_untrain_ret) * the stack. */ SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + /* + * Safe-RET sequence. If you need to change it, adjust + * handle_interrupted_saferet() too. + */ lea 8(%_ASM_SP), %_ASM_SP ret + /* End of Safe-RET sequence */ + int3 int3 /* end of movabs */ |