diff options
132 files changed, 1019 insertions, 517 deletions
@@ -166,6 +166,7 @@ Daniel Borkmann <[email protected]> <[email protected]> Daniel Borkmann <[email protected]> <[email protected]> David Brownell <[email protected]> David Collins <[email protected]> <[email protected]> +David Heidelberg <[email protected]> <[email protected]> David Rheinsberg <[email protected]> <[email protected]> David Rheinsberg <[email protected]> <[email protected]> David Rheinsberg <[email protected]> <[email protected]> diff --git a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml index a1b71b35319e..42f9843d1868 100644 --- a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml +++ b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml @@ -38,6 +38,10 @@ properties: managed: true + phys: + description: A reference to the SerDes lane(s) + maxItems: 1 + required: - reg diff --git a/Documentation/wmi/devices/msi-wmi-platform.rst b/Documentation/wmi/devices/msi-wmi-platform.rst index 29b1b2e6d42c..31a136942892 100644 --- a/Documentation/wmi/devices/msi-wmi-platform.rst +++ b/Documentation/wmi/devices/msi-wmi-platform.rst @@ -130,12 +130,12 @@ data using the `bmfdec <https://github.com/pali/bmfdec>`_ utility: Due to a peculiarity in how Windows handles the ``CreateByteField()`` ACPI operator (errors only happen when a invalid byte field is ultimately accessed), all methods require a 32 byte input -buffer, even if the Binay MOF says otherwise. +buffer, even if the Binary MOF says otherwise. The input buffer contains a single byte to select the subfeature to be accessed and 31 bytes of input data, the meaning of which depends on the subfeature being accessed. -The output buffer contains a singe byte which signals success or failure (``0x00`` on failure) +The output buffer contains a single byte which signals success or failure (``0x00`` on failure) and 31 bytes of output data, the meaning if which depends on the subfeature being accessed. WMI method Get_EC() @@ -147,7 +147,7 @@ data contains a flag byte and a 28 byte controller firmware version string. The first 4 bits of the flag byte contain the minor version of the embedded controller interface, with the next 2 bits containing the major version of the embedded controller interface. -The 7th bit signals if the embedded controller page chaged (exact meaning is unknown), and the +The 7th bit signals if the embedded controller page changed (exact meaning is unknown), and the last bit signals if the platform is a Tigerlake platform. The MSI software seems to only use this interface when the last bit is set. diff --git a/MAINTAINERS b/MAINTAINERS index 8766f3e5e87e..82f19f0f0752 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13324,14 +13324,16 @@ F: Documentation/devicetree/bindings/i2c/i2c-mux-ltc4306.txt F: drivers/i2c/muxes/i2c-mux-ltc4306.c LTP (Linux Test Project) +M: Andrea Cervesato <[email protected]> M: Cyril Hrubis <[email protected]> M: Jan Stancek <[email protected]> M: Petr Vorel <[email protected]> M: Li Wang <[email protected]> M: Yang Xu <[email protected]> +M: Xiao Yang <[email protected]> L: [email protected] (subscribers-only) S: Maintained -W: http://linux-test-project.github.io/ +W: https://linux-test-project.readthedocs.io/ T: git https://github.com/linux-test-project/ltp.git LTR390 AMBIENT/UV LIGHT SENSOR DRIVER @@ -13539,7 +13541,7 @@ MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2) M: Mirko Lindner <[email protected]> M: Stephen Hemminger <[email protected]> -S: Maintained +S: Odd fixes F: drivers/net/ethernet/marvell/sk* MARVELL LIBERTAS WIRELESS DRIVER diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h index aa44b3fe43dd..5da32c00d483 100644 --- a/arch/loongarch/include/asm/hugetlb.h +++ b/arch/loongarch/include/asm/hugetlb.h @@ -34,7 +34,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t clear; - pte_t pte = *ptep; + pte_t pte = ptep_get(ptep); pte_val(clear) = (unsigned long)invalid_pte_table; set_pte_at(mm, addr, ptep, clear); @@ -65,7 +65,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t pte, int dirty) { - int changed = !pte_same(*ptep, pte); + int changed = !pte_same(ptep_get(ptep), pte); if (changed) { set_pte_at(vma->vm_mm, addr, ptep, pte); diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h index 92636e82957c..da9e93024626 100644 --- a/arch/loongarch/include/asm/kfence.h +++ b/arch/loongarch/include/asm/kfence.h @@ -53,13 +53,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) { pte_t *pte = virt_to_kpte(addr); - if (WARN_ON(!pte) || pte_none(*pte)) + if (WARN_ON(!pte) || pte_none(ptep_get(pte))) return false; if (protect) - set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT))); + set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~(_PAGE_VALID | _PAGE_PRESENT))); else - set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT))); + set_pte(pte, __pte(pte_val(ptep_get(pte)) | (_PAGE_VALID | _PAGE_PRESENT))); preempt_disable(); local_flush_tlb_one(addr); diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index 44b54965f5b4..5f0677e03817 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -26,8 +26,6 @@ #define KVM_MAX_VCPUS 256 #define KVM_MAX_CPUCFG_REGS 21 -/* memory slots that does not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 0 #define KVM_HALT_POLL_NS_DEFAULT 500000 #define KVM_REQ_TLB_FLUSH_GPA KVM_ARCH_REQ(0) diff --git a/arch/loongarch/include/asm/kvm_para.h b/arch/loongarch/include/asm/kvm_para.h index 335fb86778e2..43ec61589e6c 100644 --- a/arch/loongarch/include/asm/kvm_para.h +++ b/arch/loongarch/include/asm/kvm_para.h @@ -39,9 +39,9 @@ struct kvm_steal_time { * Hypercall interface for KVM hypervisor * * a0: function identifier - * a1-a6: args + * a1-a5: args * Return value will be placed in a0. - * Up to 6 arguments are passed in a1, a2, a3, a4, a5, a6. + * Up to 5 arguments are passed in a1, a2, a3, a4, a5. */ static __always_inline long kvm_hypercall0(u64 fid) { diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 3fbf1f37c58e..85431f20a14d 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -106,6 +106,9 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define KFENCE_AREA_START (VMEMMAP_END + 1) #define KFENCE_AREA_END (KFENCE_AREA_START + KFENCE_AREA_SIZE - 1) +#define ptep_get(ptep) READ_ONCE(*(ptep)) +#define pmdp_get(pmdp) READ_ONCE(*(pmdp)) + #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e)) #ifndef __PAGETABLE_PMD_FOLDED @@ -147,11 +150,6 @@ static inline int p4d_present(p4d_t p4d) return p4d_val(p4d) != (unsigned long)invalid_pud_table; } -static inline void p4d_clear(p4d_t *p4dp) -{ - p4d_val(*p4dp) = (unsigned long)invalid_pud_table; -} - static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)p4d_val(p4d); @@ -159,7 +157,12 @@ static inline pud_t *p4d_pgtable(p4d_t p4d) static inline void set_p4d(p4d_t *p4d, p4d_t p4dval) { - *p4d = p4dval; + WRITE_ONCE(*p4d, p4dval); +} + +static inline void p4d_clear(p4d_t *p4dp) +{ + set_p4d(p4dp, __p4d((unsigned long)invalid_pud_table)); } #define p4d_phys(p4d) PHYSADDR(p4d_val(p4d)) @@ -193,17 +196,20 @@ static inline int pud_present(pud_t pud) return pud_val(pud) != (unsigned long)invalid_pmd_table; } -static inline void pud_clear(pud_t *pudp) +static inline pmd_t *pud_pgtable(pud_t pud) { - pud_val(*pudp) = ((unsigned long)invalid_pmd_table); + return (pmd_t *)pud_val(pud); } -static inline pmd_t *pud_pgtable(pud_t pud) +static inline void set_pud(pud_t *pud, pud_t pudval) { - return (pmd_t *)pud_val(pud); + WRITE_ONCE(*pud, pudval); } -#define set_pud(pudptr, pudval) do { *(pudptr) = (pudval); } while (0) +static inline void pud_clear(pud_t *pudp) +{ + set_pud(pudp, __pud((unsigned long)invalid_pmd_table)); +} #define pud_phys(pud) PHYSADDR(pud_val(pud)) #define pud_page(pud) (pfn_to_page(pud_phys(pud) >> PAGE_SHIFT)) @@ -231,12 +237,15 @@ static inline int pmd_present(pmd_t pmd) return pmd_val(pmd) != (unsigned long)invalid_pte_table; } -static inline void pmd_clear(pmd_t *pmdp) +static inline void set_pmd(pmd_t *pmd, pmd_t pmdval) { - pmd_val(*pmdp) = ((unsigned long)invalid_pte_table); + WRITE_ONCE(*pmd, pmdval); } -#define set_pmd(pmdptr, pmdval) do { *(pmdptr) = (pmdval); } while (0) +static inline void pmd_clear(pmd_t *pmdp) +{ + set_pmd(pmdp, __pmd((unsigned long)invalid_pte_table)); +} #define pmd_phys(pmd) PHYSADDR(pmd_val(pmd)) @@ -314,7 +323,8 @@ extern void paging_init(void); static inline void set_pte(pte_t *ptep, pte_t pteval) { - *ptep = pteval; + WRITE_ONCE(*ptep, pteval); + if (pte_val(pteval) & _PAGE_GLOBAL) { pte_t *buddy = ptep_buddy(ptep); /* @@ -341,8 +351,8 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) : [global] "r" (page_global)); #else /* !CONFIG_SMP */ - if (pte_none(*buddy)) - pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL; + if (pte_none(ptep_get(buddy))) + WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL)); #endif /* CONFIG_SMP */ } } @@ -350,7 +360,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { /* Preserve global status for the pair */ - if (pte_val(*ptep_buddy(ptep)) & _PAGE_GLOBAL) + if (pte_val(ptep_get(ptep_buddy(ptep))) & _PAGE_GLOBAL) set_pte(ptep, __pte(_PAGE_GLOBAL)); else set_pte(ptep, __pte(0)); @@ -603,7 +613,7 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd) static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { - pmd_t old = *pmdp; + pmd_t old = pmdp_get(pmdp); pmd_clear(pmdp); diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index 000825406c1f..2bf86aeda874 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -66,6 +66,12 @@ void __init efi_runtime_init(void) set_bit(EFI_RUNTIME_SERVICES, &efi.flags); } +bool efi_poweroff_required(void) +{ + return efi_enabled(EFI_RUNTIME_SERVICES) && + (acpi_gbl_reduced_hardware || acpi_no_s5); +} + unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR; #if defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON) diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index 2634a9e8d82c..28681dfb4b85 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -714,19 +714,19 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, * value) and then p*d_offset() walks into the target huge page instead * of the old page table (sees the new value). */ - pgd = READ_ONCE(*pgd_offset(kvm->mm, hva)); + pgd = pgdp_get(pgd_offset(kvm->mm, hva)); if (pgd_none(pgd)) goto out; - p4d = READ_ONCE(*p4d_offset(&pgd, hva)); + p4d = p4dp_get(p4d_offset(&pgd, hva)); if (p4d_none(p4d) || !p4d_present(p4d)) goto out; - pud = READ_ONCE(*pud_offset(&p4d, hva)); + pud = pudp_get(pud_offset(&p4d, hva)); if (pud_none(pud) || !pud_present(pud)) goto out; - pmd = READ_ONCE(*pmd_offset(&pud, hva)); + pmd = pmdp_get(pmd_offset(&pud, hva)); if (pmd_none(pmd) || !pmd_present(pmd)) goto out; diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c index 12222c56cb59..e4068906143b 100644 --- a/arch/loongarch/mm/hugetlbpage.c +++ b/arch/loongarch/mm/hugetlbpage.c @@ -39,11 +39,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, pmd_t *pmd = NULL; pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { + if (pgd_present(pgdp_get(pgd))) { p4d = p4d_offset(pgd, addr); - if (p4d_present(*p4d)) { + if (p4d_present(p4dp_get(p4d))) { pud = pud_offset(p4d, addr); - if (pud_present(*pud)) + if (pud_present(pudp_get(pud))) pmd = pmd_offset(pud, addr); } } diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index bf789d114c2d..8a87a482c8f4 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -141,7 +141,7 @@ void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next) { - int huge = pmd_val(*pmd) & _PAGE_HUGE; + int huge = pmd_val(pmdp_get(pmd)) & _PAGE_HUGE; if (huge) vmemmap_verify((pte_t *)pmd, node, addr, next); @@ -173,7 +173,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr) pud_t *pud; pmd_t *pmd; - if (p4d_none(*p4d)) { + if (p4d_none(p4dp_get(p4d))) { pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!pud) panic("%s: Failed to allocate memory\n", __func__); @@ -184,7 +184,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr) } pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { + if (pud_none(pudp_get(pud))) { pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!pmd) panic("%s: Failed to allocate memory\n", __func__); @@ -195,7 +195,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr) } pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { + if (!pmd_present(pmdp_get(pmd))) { pte_t *pte; pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE); @@ -216,7 +216,7 @@ void __init __set_fixmap(enum fixed_addresses idx, BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); ptep = populate_kernel_pte(addr); - if (!pte_none(*ptep)) { + if (!pte_none(ptep_get(ptep))) { pte_ERROR(*ptep); return; } diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c index c608adc99845..427d6b1aec09 100644 --- a/arch/loongarch/mm/kasan_init.c +++ b/arch/loongarch/mm/kasan_init.c @@ -105,7 +105,7 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { - if (__pmd_none(early, READ_ONCE(*pmdp))) { + if (__pmd_none(early, pmdp_get(pmdp))) { phys_addr_t pte_phys = early ? __pa_symbol(kasan_early_shadow_pte) : kasan_alloc_zeroed_page(node); if (!early) @@ -118,7 +118,7 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { - if (__pud_none(early, READ_ONCE(*pudp))) { + if (__pud_none(early, pudp_get(pudp))) { phys_addr_t pmd_phys = early ? __pa_symbol(kasan_early_shadow_pmd) : kasan_alloc_zeroed_page(node); if (!early) @@ -131,7 +131,7 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, bool early) { - if (__p4d_none(early, READ_ONCE(*p4dp))) { + if (__p4d_none(early, p4dp_get(p4dp))) { phys_addr_t pud_phys = early ? __pa_symbol(kasan_early_shadow_pud) : kasan_alloc_zeroed_page(node); if (!early) @@ -154,7 +154,7 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, : kasan_alloc_zeroed_page(node); next = addr + PAGE_SIZE; set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); - } while (ptep++, addr = next, addr != end && __pte_none(early, READ_ONCE(*ptep))); + } while (ptep++, addr = next, addr != end && __pte_none(early, ptep_get(ptep))); } static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, @@ -166,7 +166,7 @@ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, do { next = pmd_addr_end(addr, end); kasan_pte_populate(pmdp, addr, next, node, early); - } while (pmdp++, addr = next, addr != end && __pmd_none(early, READ_ONCE(*pmdp))); + } while (pmdp++, addr = next, addr != end && __pmd_none(early, pmdp_get(pmdp))); } static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr, diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index bda018150000..eb6a29b491a7 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -128,7 +128,7 @@ pmd_t mk_pmd(struct page *page, pgprot_t prot) void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); flush_tlb_all(); } diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e7f713cd70d3..a876024d8a05 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index ca6466676902..45adc1560d94 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2160,7 +2160,7 @@ static void qca_power_shutdown(struct hci_uart *hu) qcadev = serdev_device_get_drvdata(hu->serdev); power = qcadev->bt_power; - if (power->pwrseq) { + if (power && power->pwrseq) { pwrseq_power_off(power->pwrseq); set_bit(QCA_BT_OFF, &qca->flags); return; @@ -2187,10 +2187,6 @@ static void qca_power_shutdown(struct hci_uart *hu) } break; - case QCA_QCA6390: - pwrseq_power_off(qcadev->bt_power->pwrseq); - break; - default: gpiod_set_value_cansleep(qcadev->bt_en, 0); } @@ -2416,11 +2412,14 @@ static int qca_serdev_probe(struct serdev_device *serdev) break; case QCA_QCA6390: - qcadev->bt_power->pwrseq = devm_pwrseq_get(&serdev->dev, - "bluetooth"); - if (IS_ERR(qcadev->bt_power->pwrseq)) - return PTR_ERR(qcadev->bt_power->pwrseq); - break; + if (dev_of_node(&serdev->dev)) { + qcadev->bt_power->pwrseq = devm_pwrseq_get(&serdev->dev, + "bluetooth"); + if (IS_ERR(qcadev->bt_power->pwrseq)) + return PTR_ERR(qcadev->bt_power->pwrseq); + break; + } + fallthrough; default: qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index ed1e6560df25..0e663ec0c12a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -675,8 +675,10 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) of_remove_property(child, prop); phydev = of_phy_find_device(child); - if (phydev) + if (phydev) { phy_device_remove(phydev); + phy_device_free(phydev); + } } err = mdiobus_register(priv->user_mii_bus); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index b074b4bb0629..1491099528be 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2578,7 +2578,11 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port) if (!port) return MICREL_KSZ8_P1_ERRATA; break; + case KSZ8567_CHIP_ID: case KSZ9477_CHIP_ID: + case KSZ9567_CHIP_ID: + case KSZ9896_CHIP_ID: + case KSZ9897_CHIP_ID: /* KSZ9477 Errata DS80000754C * * Module 4: Energy Efficient Ethernet (EEE) feature select must @@ -2588,6 +2592,13 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port) * controls. If not disabled, the PHY ports can auto-negotiate * to enable EEE, and this feature can cause link drops when * linked to another device supporting EEE. + * + * The same item appears in the errata for the KSZ9567, KSZ9896, + * and KSZ9897. + * + * A similar item appears in the errata for the KSZ8567, but + * provides an alternative workaround. For now, use the simple + * workaround of disabling the EEE feature for this device too. */ return MICREL_NO_EEE; } @@ -3764,6 +3775,11 @@ static int ksz_port_set_mac_address(struct dsa_switch *ds, int port, return -EBUSY; } + /* Need to initialize variable as the code to fill in settings may + * not be executed. + */ + wol.wolopts = 0; + ksz_get_wol(ds, dp->index, &wol); if (wol.wolopts & WAKE_MAGIC) { dev_err(ds->dev, diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index d9d3e30fd47a..e3f95d2cc2c1 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -40,6 +40,10 @@ #define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */ #define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */ +/* MII Block subblock */ +#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */ +#define VSC73XX_BLOCK_MII_EXTERNAL 0x1 /* External MDIO subblock */ + #define CPU_PORT 6 /* CPU port */ /* MAC Block registers */ @@ -225,6 +229,8 @@ #define VSC73XX_MII_CMD 0x1 #define VSC73XX_MII_DATA 0x2 +#define VSC73XX_MII_STAT_BUSY BIT(3) + /* Arbiter block 5 registers */ #define VSC73XX_ARBEMPTY 0x0c #define VSC73XX_ARBDISC 0x0e @@ -299,6 +305,7 @@ #define IS_739X(a) (IS_7395(a) || IS_7398(a)) #define VSC73XX_POLL_SLEEP_US 1000 +#define VSC73XX_MDIO_POLL_SLEEP_US 5 #define VSC73XX_POLL_TIMEOUT_US 10000 struct vsc73xx_counter { @@ -527,6 +534,22 @@ static int vsc73xx_detect(struct vsc73xx *vsc) return 0; } +static int vsc73xx_mdio_busy_check(struct vsc73xx *vsc) +{ + int ret, err; + u32 val; + + ret = read_poll_timeout(vsc73xx_read, err, + err < 0 || !(val & VSC73XX_MII_STAT_BUSY), + VSC73XX_MDIO_POLL_SLEEP_US, + VSC73XX_POLL_TIMEOUT_US, false, vsc, + VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_STAT, &val); + if (ret) + return ret; + return err; +} + static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) { struct vsc73xx *vsc = ds->priv; @@ -534,12 +557,20 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) u32 val; int ret; + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + /* Setting bit 26 means "read" */ cmd = BIT(26) | (phy << 21) | (regnum << 16); ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) return ret; - msleep(2); + + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val); if (ret) return ret; @@ -563,18 +594,11 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, u32 cmd; int ret; - /* It was found through tedious experiments that this router - * chip really hates to have it's PHYs reset. They - * never recover if that happens: autonegotiation stops - * working after a reset. Just filter out this command. - * (Resetting the whole chip is OK.) - */ - if (regnum == 0 && (val & BIT(15))) { - dev_info(vsc->dev, "reset PHY - disallowed\n"); - return 0; - } + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; - cmd = (phy << 21) | (regnum << 16); + cmd = (phy << 21) | (regnum << 16) | val; ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) return ret; @@ -957,6 +981,11 @@ static void vsc73xx_mac_link_up(struct phylink_config *config, if (duplex == DUPLEX_FULL) val |= VSC73XX_MAC_CFG_FDX; + else + /* In datasheet description ("Port Mode Procedure" in 5.6.2) + * this bit is configured only for half duplex. + */ + val |= VSC73XX_MAC_CFG_WEXC_DIS; /* This routine is described in the datasheet (below ARBDISC register * description) @@ -967,7 +996,6 @@ static void vsc73xx_mac_link_up(struct phylink_config *config, get_random_bytes(&seed, 1); val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET; val |= VSC73XX_MAC_CFG_SEED_LOAD; - val |= VSC73XX_MAC_CFG_WEXC_DIS; /* Those bits are responsible for MTU only. Kernel takes care about MTU, * let's enable +8 bytes frame length unconditionally. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 23f74c6c88b9..e27e1082ee33 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7591,19 +7591,20 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp) int rx = bp->rx_nr_rings, stat; int vnic, grp = rx; - if (hw_resc->resv_tx_rings != bp->tx_nr_rings && - bp->hwrm_spec_code >= 0x10601) - return true; - /* Old firmware does not need RX ring reservations but we still * need to setup a default RSS map when needed. With new firmware * we go through RX ring reservations first and then set up the * RSS map for the successfully reserved RX rings when needed. */ - if (!BNXT_NEW_RM(bp)) { + if (!BNXT_NEW_RM(bp)) bnxt_check_rss_tbl_no_rmgr(bp); + + if (hw_resc->resv_tx_rings != bp->tx_nr_rings && + bp->hwrm_spec_code >= 0x10601) + return true; + + if (!BNXT_NEW_RM(bp)) return false; - } vnic = bnxt_get_total_vnics(bp, rx); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index ab8e3f197e7b..9dadc89378f0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -5290,7 +5290,7 @@ void bnxt_ethtool_free(struct bnxt *bp) const struct ethtool_ops bnxt_ethtool_ops = { .cap_link_lanes_supported = 1, .cap_rss_ctx_supported = 1, - .rxfh_max_context_id = BNXT_MAX_ETH_RSS_CTX, + .rxfh_max_num_contexts = BNXT_MAX_ETH_RSS_CTX + 1, .rxfh_indir_space = BNXT_MAX_RSS_TABLE_ENTRIES_P5, .rxfh_priv_size = sizeof(struct bnxt_rss_ctx), .supported_coalesce_params = ETHTOOL_COALESCE_USECS | diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index 1248792d7fd4..0715ea5bf13e 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -42,19 +42,15 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct bcmgenet_priv *priv = netdev_priv(dev); struct device *kdev = &priv->pdev->dev; - if (dev->phydev) { + if (dev->phydev) phy_ethtool_get_wol(dev->phydev, wol); - if (wol->supported) - return; - } - if (!device_can_wakeup(kdev)) { - wol->supported = 0; - wol->wolopts = 0; + /* MAC is not wake-up capable, return what the PHY does */ + if (!device_can_wakeup(kdev)) return; - } - wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; + /* Overlay MAC capabilities with that of the PHY queried before */ + wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; wol->wolopts = priv->wolopts; memset(wol->sopass, 0, sizeof(wol->sopass)); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 11665be3a22c..dcd3f54ed0cf 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5250,8 +5250,8 @@ static int __maybe_unused macb_suspend(struct device *dev) if (bp->wol & MACB_WOL_ENABLED) { /* Check for IP address in WOL ARP mode */ idev = __in_dev_get_rcu(bp->dev); - if (idev && idev->ifa_list) - ifa = rcu_access_pointer(idev->ifa_list); + if (idev) + ifa = rcu_dereference(idev->ifa_list); if ((bp->wolopts & WAKE_ARP) && !ifa) { netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index e32f6724f568..2e4f3e1782a2 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -775,6 +775,9 @@ void fec_ptp_stop(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); + if (fep->pps_enable) + fec_ptp_enable_pps(fep, 0); + cancel_delayed_work_sync(&fep->time_keep); hrtimer_cancel(&fep->perout_timer); if (fep->ptp_clock) diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 3480ff5c7ed6..5a8b490ab3ad 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -495,7 +495,7 @@ static int gve_set_channels(struct net_device *netdev, return -EINVAL; } - if (!netif_carrier_ok(netdev)) { + if (!netif_running(netdev)) { priv->tx_cfg.num_queues = new_tx; priv->rx_cfg.num_queues = new_rx; return 0; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 9744b426940e..661566db68c8 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1566,7 +1566,7 @@ static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog, u32 status; old_prog = READ_ONCE(priv->xdp_prog); - if (!netif_carrier_ok(priv->dev)) { + if (!netif_running(priv->dev)) { WRITE_ONCE(priv->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); @@ -1847,7 +1847,7 @@ int gve_adjust_queues(struct gve_priv *priv, rx_alloc_cfg.qcfg = &new_rx_config; tx_alloc_cfg.num_rings = new_tx_config.num_queues; - if (netif_carrier_ok(priv->dev)) { + if (netif_running(priv->dev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); return err; } @@ -2064,7 +2064,7 @@ static int gve_set_features(struct net_device *netdev, if ((netdev->features & NETIF_F_LRO) != (features & NETIF_F_LRO)) { netdev->features ^= NETIF_F_LRO; - if (netif_carrier_ok(netdev)) { + if (netif_running(netdev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); if (err) goto revert_features; @@ -2359,7 +2359,7 @@ err: int gve_reset(struct gve_priv *priv, bool attempt_teardown) { - bool was_up = netif_carrier_ok(priv->dev); + bool was_up = netif_running(priv->dev); int err; dev_info(&priv->pdev->dev, "Performing reset\n"); @@ -2700,7 +2700,7 @@ static void gve_shutdown(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct gve_priv *priv = netdev_priv(netdev); - bool was_up = netif_carrier_ok(priv->dev); + bool was_up = netif_running(priv->dev); rtnl_lock(); if (was_up && gve_close(priv->dev)) { @@ -2718,7 +2718,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state) { struct net_device *netdev = pci_get_drvdata(pdev); struct gve_priv *priv = netdev_priv(netdev); - bool was_up = netif_carrier_ok(priv->dev); + bool was_up = netif_running(priv->dev); priv->suspend_cnt++; rtnl_lock(); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 8c990c976132..bc79ba974e49 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -4673,10 +4673,10 @@ static int ice_get_port_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port, if (err) return err; - fec_stats->uncorrectable_blocks.total = (fec_corr_high_val << 16) + - fec_corr_low_val; - fec_stats->corrected_blocks.total = (fec_uncorr_high_val << 16) + - fec_uncorr_low_val; + fec_stats->corrected_blocks.total = (fec_corr_high_val << 16) + + fec_corr_low_val; + fec_stats->uncorrectable_blocks.total = (fec_uncorr_high_val << 16) + + fec_uncorr_low_val; return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 3de020020bc4..6f97ed471fe9 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -559,6 +559,8 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) if (test_bit(ICE_PREPARED_FOR_RESET, pf->state)) return; + synchronize_irq(pf->oicr_irq.virq); + ice_unplug_aux_dev(pf); /* Notify VFs of impending reset */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index e2786cc13286..ef2e858f49bb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1477,6 +1477,10 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) /* Update cached link status for this port immediately */ ptp_port->link_up = linkup; + /* Skip HW writes if reset is in progress */ + if (pf->hw.reset_ongoing) + return; + switch (hw->ptp.phy_model) { case ICE_PHY_E810: /* Do not reconfigure E810 PHY */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 5dbf2b4ba1b0..0b6c8fd5bc90 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -900,8 +900,8 @@ static void idpf_vport_stop(struct idpf_vport *vport) vport->link_up = false; idpf_vport_intr_deinit(vport); - idpf_vport_intr_rel(vport); idpf_vport_queues_rel(vport); + idpf_vport_intr_rel(vport); np->state = __IDPF_VPORT_DOWN; } @@ -1335,9 +1335,8 @@ static void idpf_rx_init_buf_tail(struct idpf_vport *vport) /** * idpf_vport_open - Bring up a vport * @vport: vport to bring up - * @alloc_res: allocate queue resources */ -static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) +static int idpf_vport_open(struct idpf_vport *vport) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); struct idpf_adapter *adapter = vport->adapter; @@ -1350,45 +1349,43 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) /* we do not allow interface up just yet */ netif_carrier_off(vport->netdev); - if (alloc_res) { - err = idpf_vport_queues_alloc(vport); - if (err) - return err; - } - err = idpf_vport_intr_alloc(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to allocate interrupts for vport %u: %d\n", vport->vport_id, err); - goto queues_rel; + return err; } + err = idpf_vport_queues_alloc(vport); + if (err) + goto intr_rel; + err = idpf_vport_queue_ids_init(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize queue ids for vport %u: %d\n", vport->vport_id, err); - goto intr_rel; + goto queues_rel; } err = idpf_vport_intr_init(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize interrupts for vport %u: %d\n", vport->vport_id, err); - goto intr_rel; + goto queues_rel; } err = idpf_rx_bufs_init_all(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize RX buffers for vport %u: %d\n", vport->vport_id, err); - goto intr_rel; + goto queues_rel; } err = idpf_queue_reg_init(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize queue registers for vport %u: %d\n", vport->vport_id, err); - goto intr_rel; + goto queues_rel; } idpf_rx_init_buf_tail(vport); @@ -1455,10 +1452,10 @@ unmap_queue_vectors: idpf_send_map_unmap_queue_vector_msg(vport, false); intr_deinit: idpf_vport_intr_deinit(vport); -intr_rel: - idpf_vport_intr_rel(vport); queues_rel: idpf_vport_queues_rel(vport); +intr_rel: + idpf_vport_intr_rel(vport); return err; } @@ -1539,7 +1536,7 @@ void idpf_init_task(struct work_struct *work) np = netdev_priv(vport->netdev); np->state = __IDPF_VPORT_DOWN; if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, vport_config->flags)) - idpf_vport_open(vport, true); + idpf_vport_open(vport); /* Spawn and return 'idpf_init_task' work queue until all the * default vports are created @@ -1898,9 +1895,6 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, goto free_vport; } - err = idpf_vport_queues_alloc(new_vport); - if (err) - goto free_vport; if (current_state <= __IDPF_VPORT_DOWN) { idpf_send_delete_queues_msg(vport); } else { @@ -1932,17 +1926,23 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, err = idpf_set_real_num_queues(vport); if (err) - goto err_reset; + goto err_open; if (current_state == __IDPF_VPORT_UP) - err = idpf_vport_open(vport, false); + err = idpf_vport_open(vport); kfree(new_vport); return err; err_reset: - idpf_vport_queues_rel(new_vport); + idpf_send_add_queues_msg(vport, vport->num_txq, vport->num_complq, + vport->num_rxq, vport->num_bufq); + +err_open: + if (current_state == __IDPF_VPORT_UP) + idpf_vport_open(vport); + free_vport: kfree(new_vport); @@ -2171,7 +2171,7 @@ static int idpf_open(struct net_device *netdev) idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - err = idpf_vport_open(vport, true); + err = idpf_vport_open(vport); idpf_vport_ctrl_unlock(netdev); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index af2879f03b8d..585c3dadd9bf 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3576,9 +3576,7 @@ static void idpf_vport_intr_napi_dis_all(struct idpf_vport *vport) */ void idpf_vport_intr_rel(struct idpf_vport *vport) { - int i, j, v_idx; - - for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { + for (u32 v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx]; kfree(q_vector->complq); @@ -3593,26 +3591,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport) free_cpumask_var(q_vector->affinity_mask); } - /* Clean up the mapping of queues to vectors */ - for (i = 0; i < vport->num_rxq_grp; i++) { - struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; - - if (idpf_is_queue_model_split(vport->rxq_model)) - for (j = 0; j < rx_qgrp->splitq.num_rxq_sets; j++) - rx_qgrp->splitq.rxq_sets[j]->rxq.q_vector = NULL; - else - for (j = 0; j < rx_qgrp->singleq.num_rxq; j++) - rx_qgrp->singleq.rxqs[j]->q_vector = NULL; - } - - if (idpf_is_queue_model_split(vport->txq_model)) - for (i = 0; i < vport->num_txq_grp; i++) - vport->txq_grps[i].complq->q_vector = NULL; - else - for (i = 0; i < vport->num_txq_grp; i++) - for (j = 0; j < vport->txq_grps[i].num_txq; j++) - vport->txq_grps[i].txqs[j]->q_vector = NULL; - kfree(vport->q_vectors); vport->q_vectors = NULL; } @@ -3780,13 +3758,15 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) /** * idpf_vport_intr_req_irq - get MSI-X vectors from the OS for the vport * @vport: main vport structure - * @basename: name for the vector */ -static int idpf_vport_intr_req_irq(struct idpf_vport *vport, char *basename) +static int idpf_vport_intr_req_irq(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; + const char *drv_name, *if_name, *vec_name; int vector, err, irq_num, vidx; - const char *vec_name; + + drv_name = dev_driver_string(&adapter->pdev->dev); + if_name = netdev_name(vport->netdev); for (vector = 0; vector < vport->num_q_vectors; vector++) { struct idpf_q_vector *q_vector = &vport->q_vectors[vector]; @@ -3804,8 +3784,8 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport, char *basename) else continue; - name = kasprintf(GFP_KERNEL, "%s-%s-%d", basename, vec_name, - vidx); + name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name, + vec_name, vidx); err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0, name, q_vector); @@ -4326,7 +4306,6 @@ error: */ int idpf_vport_intr_init(struct idpf_vport *vport) { - char *int_name; int err; err = idpf_vport_intr_init_vec_idx(vport); @@ -4340,11 +4319,7 @@ int idpf_vport_intr_init(struct idpf_vport *vport) if (err) goto unroll_vectors_alloc; - int_name = kasprintf(GFP_KERNEL, "%s-%s", - dev_driver_string(&vport->adapter->pdev->dev), - vport->netdev->name); - - err = idpf_vport_intr_req_irq(vport, int_name); + err = idpf_vport_intr_req_irq(vport); if (err) goto unroll_vectors_alloc; diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 5f92b3c7c3d4..511384f3ec5c 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -404,6 +404,12 @@ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ +/* Retry Buffer Control */ +#define IGC_RETX_CTL 0x041C +#define IGC_RETX_CTL_WATERMARK_MASK 0xF +#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */ +#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */ + /* Transmit Scheduling Latency */ /* Latency between transmission scheduling (LaunchTime) and the time * the packet is transmitted to the network in nanosecond. diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 8daf938afc36..dfd6c00b4205 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6315,12 +6315,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL; + igc_ptp_read(adapter, &now); + + if (igc_tsn_is_taprio_activated_by_user(adapter) && + is_base_time_past(qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true; - igc_ptp_read(adapter, &now); - for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 22cefb1eeedf..d68fa7f3d5f0 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -49,12 +49,19 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) return new_flags; } +static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN); +} + void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; u16 txoffset; - if (!is_any_launchtime(adapter)) + if (!igc_tsn_is_tx_mode_in_tsn(adapter)) return; switch (adapter->link_speed) { @@ -78,6 +85,23 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) wr32(IGC_GTXOFFSET, txoffset); } +static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl; + + retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK; + wr32(IGC_RETX_CTL, retxctl); +} + +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && + adapter->taprio_offload_enable; +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -91,6 +115,9 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); + if (igc_is_device_id_i226(hw)) + igc_tsn_restore_retx_default(adapter); + tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); @@ -111,6 +138,25 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) return 0; } +/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes + * to 88 Bytes by setting RETX_CTL register using the recommendation from: + * a) Ethernet Controller I225/I226 Specification Update Rev 2.1 + * Item 9: TSN: Packet Transmission Might Cross the Qbv Window + * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control + */ +static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl, watermark; + + retxctl = rd32(IGC_RETX_CTL); + watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK; + /* Set QBVFULLTH value using watermark and set QBVFULLEN */ + retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) | + IGC_RETX_CTL_QBVFULLEN; + wr32(IGC_RETX_CTL, retxctl); +} + static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -123,6 +169,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN); + if (igc_is_device_id_i226(hw)) + igc_tsn_set_retx_qbvfullthreshold(adapter); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0; @@ -262,14 +311,6 @@ skip_cbs: s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); - - /* Increase the counter if scheduling into the past while - * Gate Control List (GCL) is running. - */ - if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && - (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) && - (adapter->qbv_count > 1)) - adapter->qbv_config_change_errors++; } else { if (igc_is_device_id_i226(hw)) { ktime_t adjust_time, expires_time; @@ -331,15 +372,22 @@ int igc_tsn_reset(struct igc_adapter *adapter) return err; } -int igc_tsn_offload_apply(struct igc_adapter *adapter) +static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; + bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) & + IGC_FLAG_TSN_ANY_ENABLED); - /* Per I225/6 HW Design Section 7.5.2.1, transmit mode - * cannot be changed dynamically. Require reset the adapter. + return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) || + (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter)); +} + +int igc_tsn_offload_apply(struct igc_adapter *adapter) +{ + /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change + * from legacy->tsn or tsn->legacy, then reset adapter is needed. */ if (netif_running(adapter->netdev) && - (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { + igc_tsn_will_tx_mode_change(adapter)) { schedule_work(&adapter->reset_task); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index b53e6af560b7..98ec845a86bf 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -7,5 +7,6 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter); #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index b06e24562973..d8be0e4dcb07 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -946,15 +946,13 @@ jme_udpsum(struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IP)) return csum; skb_set_network_header(skb, ETH_HLEN); - if ((ip_hdr(skb)->protocol != IPPROTO_UDP) || - (skb->len < (ETH_HLEN + - (ip_hdr(skb)->ihl << 2) + - sizeof(struct udphdr)))) { + + if (ip_hdr(skb)->protocol != IPPROTO_UDP || + skb->len < (ETH_HLEN + ip_hdrlen(skb) + sizeof(struct udphdr))) { skb_reset_network_header(skb); return csum; } - skb_set_transport_header(skb, - ETH_HLEN + (ip_hdr(skb)->ihl << 2)); + skb_set_transport_header(skb, ETH_HLEN + ip_hdrlen(skb)); csum = udp_hdr(skb)->check; skb_reset_transport_header(skb); skb_reset_network_header(skb); diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 61334a71058c..e212a4ba9275 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -2666,14 +2666,15 @@ mtk_wed_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_pri { struct mtk_wed_flow_block_priv *priv = cb_priv; struct flow_cls_offload *cls = type_data; - struct mtk_wed_hw *hw = priv->hw; + struct mtk_wed_hw *hw = NULL; - if (!tc_can_offload(priv->dev)) + if (!priv || !tc_can_offload(priv->dev)) return -EOPNOTSUPP; if (type != TC_SETUP_CLSFLOWER) return -EOPNOTSUPP; + hw = priv->hw; return mtk_flow_offload_cmd(hw->eth, cls, hw->index); } @@ -2729,6 +2730,7 @@ mtk_wed_setup_tc_block(struct mtk_wed_hw *hw, struct net_device *dev, flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); kfree(block_cb->cb_priv); + block_cb->cb_priv = NULL; } return 0; default: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 5fd82c67b6ab..bb5da42edc23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -130,7 +130,7 @@ struct page_pool; #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2 #define MLX5E_DEFAULT_LRO_TIMEOUT 32 -#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 +#define MLX5E_DEFAULT_SHAMPO_TIMEOUT 1024 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC 0x10 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 6c9ccccca81e..64b62ed17b07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -928,7 +928,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_headers_entry_size, mlx5e_shampo_get_log_hd_entry_size(mdev, params)); MLX5_SET(rqc, rqc, reservation_timeout, - params->packet_merge.timeout); + mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT)); MLX5_SET(rqc, rqc, shampo_match_criteria_type, params->packet_merge.shampo.match_criteria_type); MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity, @@ -1087,6 +1087,20 @@ static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev, return wqebbs; } +#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 + +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) +{ + int i; + + /* The supported periods are organized in ascending order */ + for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) + if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) + break; + + return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); +} + static u32 mlx5e_mpwrq_total_umr_wqebbs(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 749b2ec0436e..3f8986f9d862 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -108,6 +108,7 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev, u32 mlx5e_shampo_hd_per_wq(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param); +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout); u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 22918b2ef7f1..09433b91be17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -146,7 +146,9 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) return err; } + mutex_lock(&priv->state_lock); err = mlx5e_safe_reopen_channels(priv); + mutex_unlock(&priv->state_lock); if (!err) { to_ctx->status = 1; /* all channels recovered */ return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 3eccdadc0357..773624bb2c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -734,7 +734,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, if (num_tuples <= 0) { netdev_warn(priv->netdev, "%s: flow is not valid %d\n", __func__, num_tuples); - return num_tuples; + return num_tuples < 0 ? num_tuples : -EINVAL; } eth_ft = get_flow_table(priv, fs, num_tuples); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6f686fabed44..5df904639b0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5167,18 +5167,6 @@ const struct net_device_ops mlx5e_netdev_ops = { #endif }; -static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) -{ - int i; - - /* The supported periods are organized in ascending order */ - for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) - if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) - break; - - return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); -} - void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu) { struct mlx5e_params *params = &priv->channels.params; @@ -5308,7 +5296,7 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i, struct mlx5e_rq_stats *rq_stats; ASSERT_RTNL(); - if (mlx5e_is_uplink_rep(priv)) + if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch) return; channel_stats = priv->channel_stats[i]; @@ -5328,6 +5316,9 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i, struct mlx5e_sq_stats *sq_stats; ASSERT_RTNL(); + if (!priv->stats_nch) + return; + /* no special case needed for ptp htb etc since txq2sq_stats is kept up * to date for active sq_stats, otherwise get_base_stats takes care of * inactive sqs. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index f6deb5a3f820..eeb0b7ea05f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -126,7 +126,7 @@ static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) } static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, - u8 *host_buses, u8 *sd_group) + u8 *host_buses) { u32 out[MLX5_ST_SZ_DW(mpir_reg)]; int err; @@ -135,10 +135,6 @@ static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, if (err) return err; - err = mlx5_query_nic_vport_sd_group(dev, sd_group); - if (err) - return err; - *sdm = MLX5_GET(mpir_reg, out, sdm); *host_buses = MLX5_GET(mpir_reg, out, host_buses); @@ -166,19 +162,23 @@ static int sd_init(struct mlx5_core_dev *dev) if (mlx5_core_is_ecpf(dev)) return 0; + err = mlx5_query_nic_vport_sd_group(dev, &sd_group); + if (err) + return err; + + if (!sd_group) + return 0; + if (!MLX5_CAP_MCAM_REG(dev, mpir)) return 0; - err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group); + err = mlx5_query_sd(dev, &sdm, &host_buses); if (err) return err; if (!sdm) return 0; - if (!sd_group) - return 0; - group_id = mlx5_sd_group_id(dev, sd_group); if (!mlx5_sd_is_supported(dev, host_buses)) { diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h index bc94e75a7aeb..e7777700ee18 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h @@ -40,6 +40,7 @@ */ #define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0 #define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1 +#define MLXBF_GIGE_MAX_FILTER_IDX 3 /* Define for broadcast MAC literal */ #define BCAST_MAC_ADDR 0xFFFFFFFFFFFF @@ -175,6 +176,13 @@ enum mlxbf_gige_res { int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv); void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv); + +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 dmac); void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index b157f0f1c5a8..385a56ac7348 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -168,6 +168,10 @@ static int mlxbf_gige_open(struct net_device *netdev) if (err) goto napi_deinit; + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX); + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX); + mlxbf_gige_enable_multicast_rx(priv); + /* Set bits in INT_EN that we care about */ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | @@ -379,6 +383,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev) void __iomem *plu_base; void __iomem *base; int addr, phy_irq; + unsigned int i; int err; base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC); @@ -423,6 +428,11 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->rx_q_entries = MLXBF_GIGE_DEFAULT_RXQ_SZ; priv->tx_q_entries = MLXBF_GIGE_DEFAULT_TXQ_SZ; + for (i = 0; i <= MLXBF_GIGE_MAX_FILTER_IDX; i++) + mlxbf_gige_disable_mac_rx_filter(priv, i); + mlxbf_gige_disable_multicast_rx(priv); + mlxbf_gige_disable_promisc(priv); + /* Write initial MAC address to hardware */ mlxbf_gige_initial_mac(priv); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h index 98a8681c21b9..4d14cb13fd64 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -62,6 +62,8 @@ #define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520 #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528 +#define MLXBF_GIGE_RX_MAC_FILTER_GENERAL 0x0530 +#define MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540 #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548 diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index 699984358493..eb62620b63c7 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -11,15 +11,31 @@ #include "mlxbf_gige.h" #include "mlxbf_gige_regs.h" -void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, - unsigned int index, u64 dmac) +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv) { void __iomem *base = priv->base; - u64 control; + u64 data; - /* Write destination MAC to specified MAC RX filter */ - writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + - (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data |= MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv) +{ + void __iomem *base = priv->base; + u64 data; + + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data &= ~MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control; /* Enable MAC receive filter mask for specified index */ control = readq(base + MLXBF_GIGE_CONTROL); @@ -27,6 +43,28 @@ void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, writeq(control, base + MLXBF_GIGE_CONTROL); } +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control; + + /* Disable MAC receive filter mask for specified index */ + control = readq(base + MLXBF_GIGE_CONTROL); + control &= ~(MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index); + writeq(control, base + MLXBF_GIGE_CONTROL); +} + +void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 dmac) +{ + void __iomem *base = priv->base; + + /* Write destination MAC to specified MAC RX filter */ + writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + + (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); +} + void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 *dmac) { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index d2f07e179e86..39f56973746d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -599,7 +599,11 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, else *headroom = XDP_PACKET_HEADROOM; - *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; + *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom); + + /* Using page pool in this case, so alloc_size is PAGE_SIZE */ + if (*alloc_size < PAGE_SIZE) + *alloc_size = PAGE_SIZE; *datasize = mtu + ETH_HLEN; } @@ -1788,7 +1792,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; - u8 arm_bit; int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1799,16 +1802,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_poll_tx_cq(cq); w = cq->work_done; - - if (w < cq->budget && - napi_complete_done(&cq->napi, w)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; + cq->work_done_since_doorbell += w; + + if (w < cq->budget) { + mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); + cq->work_done_since_doorbell = 0; + napi_complete_done(&cq->napi, w); + } else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + /* MANA hardware requires at least one doorbell ring every 8 + * wraparounds of CQ even if there is no need to arm the CQ. + * This driver rings the doorbell as soon as we have exceeded + * 4 wraparounds. + */ + mana_gd_ring_cq(gdma_queue, 0); + cq->work_done_since_doorbell = 0; } - mana_gd_ring_cq(gdma_queue, arm_bit); - return w; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index d3c5306f1c41..93a78fd0737b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -573,8 +573,6 @@ static inline u32 mtl_low_credx_base_addr(const struct dwmac4_addrs *addrs, #define GMAC_PHYIF_CTRLSTATUS_LNKSTS BIT(19) #define GMAC_PHYIF_CTRLSTATUS_JABTO BIT(20) #define GMAC_PHYIF_CTRLSTATUS_FALSECARDET BIT(21) -/* LNKMOD */ -#define GMAC_PHYIF_CTRLSTATUS_LNKMOD_MASK 0x1 /* LNKSPEED */ #define GMAC_PHYIF_CTRLSTATUS_SPEED_125 0x2 #define GMAC_PHYIF_CTRLSTATUS_SPEED_25 0x1 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f98741d2607e..31c387cc5f26 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -786,7 +786,7 @@ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x) else x->pcs_speed = SPEED_10; - x->pcs_duplex = (status & GMAC_PHYIF_CTRLSTATUS_LNKMOD_MASK); + x->pcs_duplex = (status & GMAC_PHYIF_CTRLSTATUS_LNKMOD); pr_info("Link is Up - %d/%s\n", (int)x->pcs_speed, x->pcs_duplex ? "Full" : "Half"); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index fa5500decc96..c7d9221fafdc 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -160,16 +160,16 @@ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */ #define XAE_FCC_OFFSET 0x0000040C /* Flow Control Configuration */ -#define XAE_EMMC_OFFSET 0x00000410 /* EMAC mode configuration */ -#define XAE_PHYC_OFFSET 0x00000414 /* RGMII/SGMII configuration */ +#define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */ +#define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */ -#define XAE_MDIO_MC_OFFSET 0x00000500 /* MII Management Config */ -#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MII Management Control */ -#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MII Management Write Data */ -#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MII Management Read Data */ +#define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */ +#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */ +#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */ +#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MDIO Read Data */ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */ -#define XAE_FMI_OFFSET 0x00000708 /* Filter Mask Index */ +#define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */ @@ -308,7 +308,7 @@ */ #define XAE_UAW1_UNICASTADDR_MASK 0x0000FFFF -/* Bit masks for Axi Ethernet FMI register */ +/* Bit masks for Axi Ethernet FMC register */ #define XAE_FMI_PM_MASK 0x80000000 /* Promis. mode enable */ #define XAE_FMI_IND_MASK 0x00000003 /* Index Mask */ diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 427b91aca50d..0696faf60013 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1269,6 +1269,9 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_cow_head(skb, dev->needed_headroom)) goto tx_err; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + skb_reset_inner_headers(skb); /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */ diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 897b979ec03c..3b5fcaf0dd36 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -237,16 +237,6 @@ static int vsc739x_config_init(struct phy_device *phydev) return 0; } -static int vsc73xx_config_aneg(struct phy_device *phydev) -{ - /* The VSC73xx switches does not like to be instructed to - * do autonegotiation in any way, it prefers that you just go - * with the power-on/reset defaults. Writing some registers will - * just make autonegotiation permanently fail. - */ - return 0; -} - /* This adds a skew for both TX and RX clocks, so the skew should only be * applied to "rgmii-id" interfaces. It may not work as expected * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. @@ -444,7 +434,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc738x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -453,7 +442,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc738x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -462,7 +450,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc739x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -471,7 +458,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc739x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 61f6ad9c1934..2ea75686a319 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -5,6 +5,7 @@ * Copyright (c) 2023 Bootlin, Kory Maincent <[email protected]> */ +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/firmware.h> #include <linux/i2c.h> @@ -29,6 +30,8 @@ #define TPS23881_REG_TPON BIT(0) #define TPS23881_REG_FWREV 0x41 #define TPS23881_REG_DEVID 0x43 +#define TPS23881_REG_DEVID_MASK 0xF0 +#define TPS23881_DEVICE_ID 0x02 #define TPS23881_REG_SRAM_CTRL 0x60 #define TPS23881_REG_SRAM_DATA 0x61 @@ -750,7 +753,7 @@ static int tps23881_i2c_probe(struct i2c_client *client) if (ret < 0) return ret; - if (ret != 0x22) { + if (FIELD_GET(TPS23881_REG_DEVID_MASK, ret) != TPS23881_DEVICE_ID) { dev_err(dev, "Wrong device ID\n"); return -ENXIO; } diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 687d70cfc556..46afb95ffabe 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -286,10 +286,11 @@ static void ipheth_rcvbulk_callback(struct urb *urb) return; } - if (urb->actual_length <= IPHETH_IP_ALIGN) { - dev->net->stats.rx_length_errors++; - return; - } + /* iPhone may periodically send URBs with no payload + * on the "bulk in" endpoint. It is safe to ignore them. + */ + if (urb->actual_length == 0) + goto rx_submit; /* RX URBs starting with 0x00 0x01 do not encapsulate Ethernet frames, * but rather are control frames. Their purpose is not documented, and @@ -298,7 +299,8 @@ static void ipheth_rcvbulk_callback(struct urb *urb) * URB received from the bulk IN endpoint. */ if (unlikely - (((char *)urb->transfer_buffer)[0] == 0 && + (urb->actual_length == 4 && + ((char *)urb->transfer_buffer)[0] == 0 && ((char *)urb->transfer_buffer)[1] == 1)) goto rx_submit; @@ -306,7 +308,6 @@ static void ipheth_rcvbulk_callback(struct urb *urb) if (retval != 0) { dev_err(&dev->intf->dev, "%s: callback retval: %d\n", __func__, retval); - return; } rx_submit: @@ -354,13 +355,14 @@ static int ipheth_carrier_set(struct ipheth_device *dev) 0x02, /* index */ dev->ctrl_buf, IPHETH_CTRL_BUF_SIZE, IPHETH_CTRL_TIMEOUT); - if (retval < 0) { + if (retval <= 0) { dev_err(&dev->intf->dev, "%s: usb_control_msg: %d\n", __func__, retval); return retval; } - if (dev->ctrl_buf[0] == IPHETH_CARRIER_ON) { + if ((retval == 1 && dev->ctrl_buf[0] == IPHETH_CARRIER_ON) || + (retval >= 2 && dev->ctrl_buf[1] == IPHETH_CARRIER_ON)) { netif_carrier_on(dev->net); if (dev->tx_urb->status != -EINPROGRESS) netif_wake_queue(dev->net); @@ -475,8 +477,8 @@ static int ipheth_close(struct net_device *net) { struct ipheth_device *dev = netdev_priv(net); - cancel_delayed_work_sync(&dev->carrier_work); netif_stop_queue(net); + cancel_delayed_work_sync(&dev->carrier_work); return 0; } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 386d62769ded..4823dbdf5465 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -201,6 +201,7 @@ static int qmimux_rx_fixup(struct usbnet *dev, struct sk_buff *skb) break; default: /* not ip - do not know what to do */ + kfree_skb(skbn); goto skip; } @@ -1431,6 +1432,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1546, 0x1312, 4)}, /* u-blox LARA-R6 01B */ {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ {QMI_QUIRK_SET_DTR(0x33f8, 0x0104, 4)}, /* Rolling RW101 RMNET */ + {QMI_FIXED_INTF(0x2dee, 0x4d22, 5)}, /* MeiG Smart SRM825L */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0383a3e136d6..3f10c72743e9 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3658,6 +3658,9 @@ static int virtnet_send_rx_ctrl_coal_vq_cmd(struct virtnet_info *vi, { int err; + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) + return -EOPNOTSUPP; + err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue), max_usecs, max_packets); if (err) @@ -3675,6 +3678,9 @@ static int virtnet_send_tx_ctrl_coal_vq_cmd(struct virtnet_info *vi, { int err; + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) + return -EOPNOTSUPP; + err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue), max_usecs, max_packets); if (err) @@ -3743,7 +3749,11 @@ static int virtnet_set_ringparam(struct net_device *dev, err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, i, vi->intr_coal_tx.max_usecs, vi->intr_coal_tx.max_packets); - if (err) + + /* Don't break the tx resize action if the vq coalescing is not + * supported. The same is true for rx resize below. + */ + if (err && err != -EOPNOTSUPP) return err; } @@ -3758,7 +3768,7 @@ static int virtnet_set_ringparam(struct net_device *dev, vi->intr_coal_rx.max_usecs, vi->intr_coal_rx.max_packets); mutex_unlock(&vi->rq[i].dim_lock); - if (err) + if (err && err != -EOPNOTSUPP) return err; } } diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index a3d881f6e5d9..c3e51f0a5c33 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -764,6 +764,7 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) case AMD_CPU_ID_CB: case AMD_CPU_ID_PS: case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT: + case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT: return MSG_OS_HINT_RN; } return -EINVAL; @@ -967,6 +968,7 @@ static const struct pci_device_id pmc_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RV) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_SP) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) }, { } }; diff --git a/drivers/platform/x86/amd/pmc/pmc.h b/drivers/platform/x86/amd/pmc/pmc.h index 9e32d3128c3a..f1166d15c856 100644 --- a/drivers/platform/x86/amd/pmc/pmc.h +++ b/drivers/platform/x86/amd/pmc/pmc.h @@ -67,6 +67,7 @@ void amd_mp2_stb_deinit(struct amd_pmc_dev *dev); #define AMD_CPU_ID_PS 0x14E8 #define AMD_CPU_ID_SP 0x14A4 #define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 +#define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122 #define PCI_DEVICE_ID_AMD_MP2_STB 0x172c #endif /* PMC_H */ diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index 2d6e2558863c..8f1f719befa3 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -41,6 +41,7 @@ #define AMD_CPU_ID_RMB 0x14b5 #define AMD_CPU_ID_PS 0x14e8 #define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 +#define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122 #define PMF_MSG_DELAY_MIN_US 50 #define RESPONSE_REGISTER_LOOP_MAX 20000 @@ -249,6 +250,7 @@ static const struct pci_device_id pmf_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RMB) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PS) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) }, { } }; @@ -382,6 +384,7 @@ static const struct acpi_device_id amd_pmf_acpi_ids[] = { {"AMDI0102", 0}, {"AMDI0103", 0}, {"AMDI0105", 0}, + {"AMDI0107", 0}, { } }; MODULE_DEVICE_TABLE(acpi, amd_pmf_acpi_ids); diff --git a/drivers/platform/x86/amd/pmf/pmf-quirks.c b/drivers/platform/x86/amd/pmf/pmf-quirks.c index 0b2eb0ae85fe..460444cda1b2 100644 --- a/drivers/platform/x86/amd/pmf/pmf-quirks.c +++ b/drivers/platform/x86/amd/pmf/pmf-quirks.c @@ -29,6 +29,14 @@ static const struct dmi_system_id fwbug_list[] = { }, .driver_data = &quirk_no_sps_bug, }, + { + .ident = "ROG Ally X", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "RC72LA"), + }, + .driver_data = &quirk_no_sps_bug, + }, {} }; @@ -48,4 +56,3 @@ void amd_pmf_quirks_init(struct amd_pmf_dev *dev) dmi_id->ident); } } - diff --git a/drivers/platform/x86/intel/ifs/runtest.c b/drivers/platform/x86/intel/ifs/runtest.c index 282e4bfe30da..be3d51ed0e47 100644 --- a/drivers/platform/x86/intel/ifs/runtest.c +++ b/drivers/platform/x86/intel/ifs/runtest.c @@ -221,8 +221,8 @@ static int doscan(void *data) */ static void ifs_test_core(int cpu, struct device *dev) { + union ifs_status status = {}; union ifs_scan activate; - union ifs_status status; unsigned long timeout; struct ifs_data *ifsd; int to_start, to_stop; diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 9b7ce03ba085..a353e830b65f 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -7,11 +7,13 @@ */ #include <linux/acpi.h> +#include <linux/cleanup.h> #include <linux/dmi.h> #include <linux/input.h> #include <linux/input/sparse-keymap.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/suspend.h> #include "../dual_accel_detect.h" @@ -66,6 +68,7 @@ static const struct key_entry intel_vbtn_switchmap[] = { }; struct intel_vbtn_priv { + struct mutex mutex; /* Avoid notify_handler() racing with itself */ struct input_dev *buttons_dev; struct input_dev *switches_dev; bool dual_accel; @@ -155,6 +158,8 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) bool autorelease; int ret; + guard(mutex)(&priv->mutex); + if ((ke = sparse_keymap_entry_from_scancode(priv->buttons_dev, event))) { if (!priv->has_buttons) { dev_warn(&device->dev, "Warning: received 0x%02x button event on a device without buttons, please report this.\n", @@ -290,6 +295,10 @@ static int intel_vbtn_probe(struct platform_device *device) return -ENOMEM; dev_set_drvdata(&device->dev, priv); + err = devm_mutex_init(&device->dev, &priv->mutex); + if (err) + return err; + priv->dual_accel = dual_accel; priv->has_buttons = has_buttons; priv->has_switches = has_switches; diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c index b5903193e2f9..ac05942e4e6a 100644 --- a/drivers/power/supply/axp288_charger.c +++ b/drivers/power/supply/axp288_charger.c @@ -178,18 +178,18 @@ static inline int axp288_charger_set_cv(struct axp288_chrg_info *info, int cv) u8 reg_val; int ret; - if (cv <= CV_4100MV) { - reg_val = CHRG_CCCV_CV_4100MV; - cv = CV_4100MV; - } else if (cv <= CV_4150MV) { - reg_val = CHRG_CCCV_CV_4150MV; - cv = CV_4150MV; - } else if (cv <= CV_4200MV) { + if (cv >= CV_4350MV) { + reg_val = CHRG_CCCV_CV_4350MV; + cv = CV_4350MV; + } else if (cv >= CV_4200MV) { reg_val = CHRG_CCCV_CV_4200MV; cv = CV_4200MV; + } else if (cv >= CV_4150MV) { + reg_val = CHRG_CCCV_CV_4150MV; + cv = CV_4150MV; } else { - reg_val = CHRG_CCCV_CV_4350MV; - cv = CV_4350MV; + reg_val = CHRG_CCCV_CV_4100MV; + cv = CV_4100MV; } reg_val = reg_val << CHRG_CCCV_CV_BIT_POS; @@ -337,8 +337,8 @@ static int axp288_charger_usb_set_property(struct power_supply *psy, } break; case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE: - scaled_val = min(val->intval, info->max_cv); - scaled_val = DIV_ROUND_CLOSEST(scaled_val, 1000); + scaled_val = DIV_ROUND_CLOSEST(val->intval, 1000); + scaled_val = min(scaled_val, info->max_cv); ret = axp288_charger_set_cv(info, scaled_val); if (ret < 0) { dev_warn(&info->pdev->dev, "set charge voltage failed\n"); diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index 46f36dcb185c..49bef4a5ac3f 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -486,7 +486,7 @@ static int qcom_battmgr_bat_get_property(struct power_supply *psy, int ret; if (!battmgr->service_up) - return -ENODEV; + return -EAGAIN; if (battmgr->variant == QCOM_BATTMGR_SC8280XP) ret = qcom_battmgr_bat_sc8280xp_update(battmgr, psp); @@ -683,7 +683,7 @@ static int qcom_battmgr_ac_get_property(struct power_supply *psy, int ret; if (!battmgr->service_up) - return -ENODEV; + return -EAGAIN; ret = qcom_battmgr_bat_sc8280xp_update(battmgr, psp); if (ret) @@ -748,7 +748,7 @@ static int qcom_battmgr_usb_get_property(struct power_supply *psy, int ret; if (!battmgr->service_up) - return -ENODEV; + return -EAGAIN; if (battmgr->variant == QCOM_BATTMGR_SC8280XP) ret = qcom_battmgr_bat_sc8280xp_update(battmgr, psp); @@ -867,7 +867,7 @@ static int qcom_battmgr_wls_get_property(struct power_supply *psy, int ret; if (!battmgr->service_up) - return -ENODEV; + return -EAGAIN; if (battmgr->variant == QCOM_BATTMGR_SC8280XP) ret = qcom_battmgr_bat_sc8280xp_update(battmgr, psp); @@ -1007,7 +1007,9 @@ static void qcom_battmgr_sc8280xp_callback(struct qcom_battmgr *battmgr, battmgr->error = 0; break; case BATTMGR_BAT_INFO: - if (payload_len != sizeof(resp->info)) { + /* some firmware versions report an extra __le32 at the end of the payload */ + if (payload_len != sizeof(resp->info) && + payload_len != (sizeof(resp->info) + sizeof(__le32))) { dev_warn(battmgr->dev, "invalid payload length for battery information request: %zd\n", payload_len); diff --git a/drivers/power/supply/rt5033_battery.c b/drivers/power/supply/rt5033_battery.c index 32eafe2c00af..7a27b262fb84 100644 --- a/drivers/power/supply/rt5033_battery.c +++ b/drivers/power/supply/rt5033_battery.c @@ -159,6 +159,7 @@ static int rt5033_battery_probe(struct i2c_client *client) return -EINVAL; } + i2c_set_clientdata(client, battery); psy_cfg.of_node = client->dev.of_node; psy_cfg.drv_data = battery; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index e31ec9ebc4ce..478cd46a49ed 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -1481,13 +1481,7 @@ static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf) notify = ops->get_vq_notification(vdpa, index); - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - if (remap_pfn_range(vma, vmf->address & PAGE_MASK, - PFN_DOWN(notify.addr), PAGE_SIZE, - vma->vm_page_prot)) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; + return vmf_insert_pfn(vma, vmf->address & PAGE_MASK, PFN_DOWN(notify.addr)); } static const struct vm_operations_struct vhost_vdpa_vm_ops = { diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h index 8d2b62c9588e..96a0444ea78f 100644 --- a/fs/bcachefs/alloc_background.h +++ b/fs/bcachefs/alloc_background.h @@ -82,6 +82,14 @@ static inline bool bucket_data_type_mismatch(enum bch_data_type bucket, bucket_data_type(bucket) != bucket_data_type(ptr); } +/* + * It is my general preference to use unsigned types for unsigned quantities - + * however, these helpers are used in disk accounting calculations run by + * triggers where the output will be negated and added to an s64. unsigned is + * right out even though all these quantities will fit in 32 bits, since it + * won't be sign extended correctly; u64 will negate "correctly", but s64 is the + * simpler option here. + */ static inline s64 bch2_bucket_sectors_total(struct bch_alloc_v4 a) { return a.stripe_sectors + a.dirty_sectors + a.cached_sectors; @@ -166,8 +174,8 @@ static inline u64 alloc_lru_idx_fragmentation(struct bch_alloc_v4 a, * avoid overflowing LRU_TIME_BITS on a corrupted fs, when * bucket_sectors_dirty is (much) bigger than bucket_size */ - u64 d = min(bch2_bucket_sectors_dirty(a), - ca->mi.bucket_size); + u64 d = min_t(s64, bch2_bucket_sectors_dirty(a), + ca->mi.bucket_size); return div_u64(d * (1ULL << 31), ca->mi.bucket_size); } diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index 618d2ff0292e..02de5ad2be2c 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -1603,7 +1603,8 @@ void bch2_open_bucket_to_text(struct printbuf *out, struct bch_fs *c, struct ope prt_newline(out); } -void bch2_open_buckets_to_text(struct printbuf *out, struct bch_fs *c) +void bch2_open_buckets_to_text(struct printbuf *out, struct bch_fs *c, + struct bch_dev *ca) { struct open_bucket *ob; @@ -1613,7 +1614,8 @@ void bch2_open_buckets_to_text(struct printbuf *out, struct bch_fs *c) ob < c->open_buckets + ARRAY_SIZE(c->open_buckets); ob++) { spin_lock(&ob->lock); - if (ob->valid && !ob->on_partial_list) + if (ob->valid && !ob->on_partial_list && + (!ca || ob->dev == ca->dev_idx)) bch2_open_bucket_to_text(out, c, ob); spin_unlock(&ob->lock); } @@ -1756,11 +1758,12 @@ void bch2_dev_alloc_debug_to_text(struct printbuf *out, struct bch_dev *ca) prt_printf(out, "buckets to invalidate\t%llu\r\n", should_invalidate_buckets(ca, stats)); } -void bch2_print_allocator_stuck(struct bch_fs *c) +static noinline void bch2_print_allocator_stuck(struct bch_fs *c) { struct printbuf buf = PRINTBUF; - prt_printf(&buf, "Allocator stuck? Waited for 10 seconds\n"); + prt_printf(&buf, "Allocator stuck? Waited for %u seconds\n", + c->opts.allocator_stuck_timeout); prt_printf(&buf, "Allocator debug:\n"); printbuf_indent_add(&buf, 2); @@ -1790,3 +1793,24 @@ void bch2_print_allocator_stuck(struct bch_fs *c) bch2_print_string_as_lines(KERN_ERR, buf.buf); printbuf_exit(&buf); } + +static inline unsigned allocator_wait_timeout(struct bch_fs *c) +{ + if (c->allocator_last_stuck && + time_after(c->allocator_last_stuck + HZ * 60 * 2, jiffies)) + return 0; + + return c->opts.allocator_stuck_timeout * HZ; +} + +void __bch2_wait_on_allocator(struct bch_fs *c, struct closure *cl) +{ + unsigned t = allocator_wait_timeout(c); + + if (t && closure_sync_timeout(cl, t)) { + c->allocator_last_stuck = jiffies; + bch2_print_allocator_stuck(c); + } + + closure_sync(cl); +} diff --git a/fs/bcachefs/alloc_foreground.h b/fs/bcachefs/alloc_foreground.h index 6da9e7e29026..386d231ceca3 100644 --- a/fs/bcachefs/alloc_foreground.h +++ b/fs/bcachefs/alloc_foreground.h @@ -223,7 +223,7 @@ static inline struct write_point_specifier writepoint_ptr(struct write_point *wp void bch2_fs_allocator_foreground_init(struct bch_fs *); void bch2_open_bucket_to_text(struct printbuf *, struct bch_fs *, struct open_bucket *); -void bch2_open_buckets_to_text(struct printbuf *, struct bch_fs *); +void bch2_open_buckets_to_text(struct printbuf *, struct bch_fs *, struct bch_dev *); void bch2_open_buckets_partial_to_text(struct printbuf *, struct bch_fs *); void bch2_write_points_to_text(struct printbuf *, struct bch_fs *); @@ -231,6 +231,11 @@ void bch2_write_points_to_text(struct printbuf *, struct bch_fs *); void bch2_fs_alloc_debug_to_text(struct printbuf *, struct bch_fs *); void bch2_dev_alloc_debug_to_text(struct printbuf *, struct bch_dev *); -void bch2_print_allocator_stuck(struct bch_fs *); +void __bch2_wait_on_allocator(struct bch_fs *, struct closure *); +static inline void bch2_wait_on_allocator(struct bch_fs *c, struct closure *cl) +{ + if (cl->closure_get_happened) + __bch2_wait_on_allocator(c, cl); +} #endif /* _BCACHEFS_ALLOC_FOREGROUND_H */ diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index 91361a167dcd..eedf2d6045e7 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -893,6 +893,8 @@ struct bch_fs { struct bch_fs_usage_base __percpu *usage; u64 __percpu *online_reserved; + unsigned long allocator_last_stuck; + struct io_clock io_clock[2]; /* JOURNAL SEQ BLACKLIST */ diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 74a60b1a4ddf..ad893684db52 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -836,6 +836,8 @@ LE64_BITMASK(BCH_SB_BACKGROUND_COMPRESSION_TYPE_HI, LE64_BITMASK(BCH_SB_VERSION_UPGRADE_COMPLETE, struct bch_sb, flags[5], 0, 16); +LE64_BITMASK(BCH_SB_ALLOCATOR_STUCK_TIMEOUT, + struct bch_sb, flags[5], 16, 32); static inline __u64 BCH_SB_COMPRESSION_TYPE(const struct bch_sb *sb) { diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index 36872207f09b..aa8a049071f4 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -1921,6 +1921,11 @@ struct btree *bch2_btree_iter_next_node(struct btree_iter *iter) bch2_trans_verify_not_in_restart(trans); bch2_btree_iter_verify(iter); + ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); + if (ret) + goto err; + + struct btree_path *path = btree_iter_path(trans, iter); /* already at end? */ diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index 31ee50184be2..e61f9695771e 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -1264,7 +1264,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, ret = bch2_btree_reserve_get(trans, as, nr_nodes, flags, &cl); bch2_trans_unlock(trans); - closure_sync(&cl); + bch2_wait_on_allocator(c, &cl); } while (bch2_err_matches(ret, BCH_ERR_operation_blocked)); } diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index 9b5b5c9a6c63..84f1cbf6497f 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -1809,6 +1809,9 @@ static int new_stripe_alloc_buckets(struct btree_trans *trans, struct ec_stripe_ BUG_ON(v->nr_blocks != h->s->nr_data + h->s->nr_parity); BUG_ON(v->nr_redundant != h->s->nr_parity); + /* * We bypass the sector allocator which normally does this: */ + bitmap_and(devs.d, devs.d, c->rw_devs[BCH_DATA_user].d, BCH_SB_MEMBERS_MAX); + for_each_set_bit(i, h->s->blocks_gotten, v->nr_blocks) { __clear_bit(v->ptrs[i].dev, devs.d); if (i < h->s->nr_data) @@ -2235,6 +2238,23 @@ void bch2_stripes_heap_to_text(struct printbuf *out, struct bch_fs *c) mutex_unlock(&c->ec_stripes_heap_lock); } +static void bch2_new_stripe_to_text(struct printbuf *out, struct bch_fs *c, + struct ec_stripe_new *s) +{ + prt_printf(out, "\tidx %llu blocks %u+%u allocated %u ref %u %u %s obs", + s->idx, s->nr_data, s->nr_parity, + bitmap_weight(s->blocks_allocated, s->nr_data), + atomic_read(&s->ref[STRIPE_REF_io]), + atomic_read(&s->ref[STRIPE_REF_stripe]), + bch2_watermarks[s->h->watermark]); + + struct bch_stripe *v = &bkey_i_to_stripe(&s->new_stripe.key)->v; + unsigned i; + for_each_set_bit(i, s->blocks_gotten, v->nr_blocks) + prt_printf(out, " %u", s->blocks[i]); + prt_newline(out); +} + void bch2_new_stripes_to_text(struct printbuf *out, struct bch_fs *c) { struct ec_stripe_head *h; @@ -2247,23 +2267,15 @@ void bch2_new_stripes_to_text(struct printbuf *out, struct bch_fs *c) bch2_watermarks[h->watermark]); if (h->s) - prt_printf(out, "\tidx %llu blocks %u+%u allocated %u\n", - h->s->idx, h->s->nr_data, h->s->nr_parity, - bitmap_weight(h->s->blocks_allocated, - h->s->nr_data)); + bch2_new_stripe_to_text(out, c, h->s); } mutex_unlock(&c->ec_stripe_head_lock); prt_printf(out, "in flight:\n"); mutex_lock(&c->ec_stripe_new_lock); - list_for_each_entry(s, &c->ec_stripe_new_list, list) { - prt_printf(out, "\tidx %llu blocks %u+%u ref %u %u %s\n", - s->idx, s->nr_data, s->nr_parity, - atomic_read(&s->ref[STRIPE_REF_io]), - atomic_read(&s->ref[STRIPE_REF_stripe]), - bch2_watermarks[s->h->watermark]); - } + list_for_each_entry(s, &c->ec_stripe_new_list, list) + bch2_new_stripe_to_text(out, c, s); mutex_unlock(&c->ec_stripe_new_lock); } diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c index 2cf6297756f8..177ed331c00b 100644 --- a/fs/bcachefs/io_misc.c +++ b/fs/bcachefs/io_misc.c @@ -126,11 +126,7 @@ err_noprint: if (closure_nr_remaining(&cl) != 1) { bch2_trans_unlock_long(trans); - - if (closure_sync_timeout(&cl, HZ * 10)) { - bch2_print_allocator_stuck(c); - closure_sync(&cl); - } + bch2_wait_on_allocator(c, &cl); } return ret; diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index 4531c9ab3e12..7ee3b75480df 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -406,6 +406,7 @@ static void bch2_read_retry_nodecode(struct bch_fs *c, struct bch_read_bio *rbio bch2_trans_iter_init(trans, &iter, rbio->data_btree, rbio->read_pos, BTREE_ITER_slots); retry: + bch2_trans_begin(trans); rbio->bio.bi_status = 0; k = bch2_btree_iter_peek_slot(&iter); diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index d31c8d006d97..1d4761d15002 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -1503,10 +1503,7 @@ err: if ((op->flags & BCH_WRITE_SYNC) || (!(op->flags & BCH_WRITE_SUBMITTED) && !(op->flags & BCH_WRITE_IN_WORKER))) { - if (closure_sync_timeout(&op->cl, HZ * 10)) { - bch2_print_allocator_stuck(c); - closure_sync(&op->cl); - } + bch2_wait_on_allocator(c, &op->cl); __bch2_write_index(op); diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 60b93018501f..cda1725702ea 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -391,6 +391,11 @@ enum fsck_err_opts { OPT_BOOL(), \ BCH_SB_JOURNAL_TRANSACTION_NAMES, true, \ NULL, "Log transaction function names in journal") \ + x(allocator_stuck_timeout, u16, \ + OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ + OPT_UINT(0, U16_MAX), \ + BCH_SB_ALLOCATOR_STUCK_TIMEOUT, 30, \ + NULL, "Default timeout in seconds for stuck allocator messages")\ x(noexcl, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index 8bc819832790..c8c2ccbdfbb5 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -414,6 +414,10 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, if (!BCH_SB_VERSION_UPGRADE_COMPLETE(sb)) SET_BCH_SB_VERSION_UPGRADE_COMPLETE(sb, le16_to_cpu(sb->version)); + + if (le16_to_cpu(sb->version) <= bcachefs_metadata_version_disk_accounting_v2 && + !BCH_SB_ALLOCATOR_STUCK_TIMEOUT(sb)) + SET_BCH_SB_ALLOCATOR_STUCK_TIMEOUT(sb, 30); } for (opt_id = 0; opt_id < bch2_opts_nr; opt_id++) { diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index 0455a1001fec..e7fa2de35014 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -1193,7 +1193,6 @@ static void bch2_dev_free(struct bch_dev *ca) if (ca->kobj.state_in_sysfs) kobject_del(&ca->kobj); - kfree(ca->buckets_nouse); bch2_free_super(&ca->disk_sb); bch2_dev_allocator_background_exit(ca); bch2_dev_journal_exit(ca); diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c index 1c0d1fb20276..f393023a3ae2 100644 --- a/fs/bcachefs/sysfs.c +++ b/fs/bcachefs/sysfs.c @@ -367,7 +367,7 @@ SHOW(bch2_fs) bch2_stripes_heap_to_text(out, c); if (attr == &sysfs_open_buckets) - bch2_open_buckets_to_text(out, c); + bch2_open_buckets_to_text(out, c, NULL); if (attr == &sysfs_open_buckets_partial) bch2_open_buckets_partial_to_text(out, c); @@ -811,6 +811,9 @@ SHOW(bch2_dev) if (attr == &sysfs_alloc_debug) bch2_dev_alloc_debug_to_text(out, ca); + if (attr == &sysfs_open_buckets) + bch2_open_buckets_to_text(out, c, ca); + return 0; } @@ -892,6 +895,7 @@ struct attribute *bch2_dev_files[] = { /* debug: */ &sysfs_alloc_debug, + &sysfs_open_buckets, NULL }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9f10a9f23fcc..9914419f3b7d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1868,7 +1868,10 @@ out: out_release_extents: btrfs_release_log_ctx_extents(&ctx); - btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); + if (skip_ilock) + up_write(&inode->i_mmap_lock); + else + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 19d05a4c5c33..333b0e8587a2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1585,6 +1585,7 @@ out_unlock: locked_page, &cached, clear_bits, page_ops); + btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL); start += cur_alloc_size; } @@ -1598,6 +1599,7 @@ out_unlock: clear_bits |= EXTENT_CLEAR_DATA_RESV; extent_clear_unlock_delalloc(inode, start, end, locked_page, &cached, clear_bits, page_ops); + btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL); } return ret; } @@ -2259,6 +2261,7 @@ error: EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); + btrfs_qgroup_free_data(inode, NULL, cur_offset, end - cur_offset + 1, NULL); } btrfs_free_path(path); return ret; @@ -7202,6 +7205,12 @@ static void wait_subpage_spinlock(struct page *page) spin_unlock_irq(&subpage->lock); } +static int btrfs_launder_folio(struct folio *folio) +{ + return btrfs_qgroup_free_data(folio_to_inode(folio), NULL, folio_pos(folio), + PAGE_SIZE, NULL); +} + static bool __btrfs_release_folio(struct folio *folio, gfp_t gfp_flags) { if (try_release_extent_mapping(&folio->page, gfp_flags)) { @@ -10137,6 +10146,7 @@ static const struct address_space_operations btrfs_aops = { .writepages = btrfs_writepages, .readahead = btrfs_readahead, .invalidate_folio = btrfs_invalidate_folio, + .launder_folio = btrfs_launder_folio, .release_folio = btrfs_release_folio, .migrate_folio = btrfs_migrate_folio, .dirty_folio = filemap_dirty_folio, diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 32dcea662da3..fc821aa446f0 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -14,7 +14,7 @@ struct root_name_map { u64 id; - char name[16]; + const char *name; }; static const struct root_name_map root_map[] = { diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 14a8d7100018..0de9162ff481 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1648,14 +1648,20 @@ static void scrub_reset_stripe(struct scrub_stripe *stripe) } } +static u32 stripe_length(const struct scrub_stripe *stripe) +{ + ASSERT(stripe->bg); + + return min(BTRFS_STRIPE_LEN, + stripe->bg->start + stripe->bg->length - stripe->logical); +} + static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx, struct scrub_stripe *stripe) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct btrfs_bio *bbio = NULL; - unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start + - stripe->bg->length - stripe->logical) >> - fs_info->sectorsize_bits; + unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits; u64 stripe_len = BTRFS_STRIPE_LEN; int mirror = stripe->mirror_num; int i; @@ -1729,9 +1735,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx, { struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_bio *bbio; - unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start + - stripe->bg->length - stripe->logical) >> - fs_info->sectorsize_bits; + unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits; int mirror = stripe->mirror_num; ASSERT(stripe->bg); @@ -1871,6 +1875,9 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx) stripe = &sctx->stripes[i]; wait_scrub_stripe_io(stripe); + spin_lock(&sctx->stat_lock); + sctx->stat.last_physical = stripe->physical + stripe_length(stripe); + spin_unlock(&sctx->stat_lock); scrub_reset_stripe(stripe); } out: @@ -2139,7 +2146,9 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx, cur_physical, &found_logical); if (ret > 0) { /* No more extent, just update the accounting */ + spin_lock(&sctx->stat_lock); sctx->stat.last_physical = physical + logical_length; + spin_unlock(&sctx->stat_lock); ret = 0; break; } @@ -2336,6 +2345,10 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, stripe_logical += chunk_logical; ret = scrub_raid56_parity_stripe(sctx, scrub_dev, bg, map, stripe_logical); + spin_lock(&sctx->stat_lock); + sctx->stat.last_physical = min(physical + BTRFS_STRIPE_LEN, + physical_end); + spin_unlock(&sctx->stat_lock); if (ret) goto out; goto next; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 08d33cb372fb..83478deada3b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -683,8 +683,11 @@ bool btrfs_check_options(const struct btrfs_fs_info *info, ret = false; if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) { - if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) + if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) { btrfs_info(info, "disk space caching is enabled"); + btrfs_warn(info, +"space cache v1 is being deprecated and will be removed in a future release, please use -o space_cache=v2"); + } if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE)) btrfs_info(info, "using free-space-tree"); } diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 5d88c184f0fc..01e99e98457d 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -112,7 +112,7 @@ static void release_ei(struct kref *ref) entry->release(entry->name, ei->data); } - call_rcu(&ei->rcu, free_ei_rcu); + call_srcu(&eventfs_srcu, &ei->rcu, free_ei_rcu); } static inline void put_ei(struct eventfs_inode *ei) @@ -736,7 +736,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode /* Was the parent freed? */ if (list_empty(&ei->list)) { cleanup_ei(ei); - ei = NULL; + ei = ERR_PTR(-EBUSY); } return ei; } diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 1028ab6d9a74..1748dff58c3b 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -42,7 +42,7 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb) struct tracefs_inode *ti; unsigned long flags; - ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL); + ti = alloc_inode_sb(sb, tracefs_inode_cachep, GFP_KERNEL); if (!ti) return NULL; @@ -53,15 +53,14 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb) return &ti->vfs_inode; } -static void tracefs_free_inode_rcu(struct rcu_head *rcu) +static void tracefs_free_inode(struct inode *inode) { - struct tracefs_inode *ti; + struct tracefs_inode *ti = get_tracefs(inode); - ti = container_of(rcu, struct tracefs_inode, rcu); kmem_cache_free(tracefs_inode_cachep, ti); } -static void tracefs_free_inode(struct inode *inode) +static void tracefs_destroy_inode(struct inode *inode) { struct tracefs_inode *ti = get_tracefs(inode); unsigned long flags; @@ -69,8 +68,6 @@ static void tracefs_free_inode(struct inode *inode) spin_lock_irqsave(&tracefs_inode_lock, flags); list_del_rcu(&ti->list); spin_unlock_irqrestore(&tracefs_inode_lock, flags); - - call_rcu(&ti->rcu, tracefs_free_inode_rcu); } static ssize_t default_read_file(struct file *file, char __user *buf, @@ -437,6 +434,7 @@ static int tracefs_drop_inode(struct inode *inode) static const struct super_operations tracefs_super_operations = { .alloc_inode = tracefs_alloc_inode, .free_inode = tracefs_free_inode, + .destroy_inode = tracefs_destroy_inode, .drop_inode = tracefs_drop_inode, .statfs = simple_statfs, .show_options = tracefs_show_options, diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index f704d8348357..d83c2a25f288 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -10,10 +10,7 @@ enum { }; struct tracefs_inode { - union { - struct inode vfs_inode; - struct rcu_head rcu; - }; + struct inode vfs_inode; /* The below gets initialized with memset_after(ti, 0, vfs_inode) */ struct list_head list; unsigned long flags; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 303fda54ef17..989c94eddb2b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -736,10 +736,10 @@ struct kernel_ethtool_ts_info { * @rxfh_key_space: same as @rxfh_indir_space, but for the key. * @rxfh_priv_size: size of the driver private data area the core should * allocate for an RSS context (in &struct ethtool_rxfh_context). - * @rxfh_max_context_id: maximum (exclusive) supported RSS context ID. If this - * is zero then the core may choose any (nonzero) ID, otherwise the core - * will only use IDs strictly less than this value, as the @rss_context - * argument to @create_rxfh_context and friends. + * @rxfh_max_num_contexts: maximum (exclusive) supported RSS context ID. + * If this is zero then the core may choose any (nonzero) ID, otherwise + * the core will only use IDs strictly less than this value, as the + * @rss_context argument to @create_rxfh_context and friends. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Modern drivers no @@ -954,7 +954,7 @@ struct ethtool_ops { u32 rxfh_indir_space; u16 rxfh_key_space; u16 rxfh_priv_size; - u32 rxfh_max_context_id; + u32 rxfh_max_num_contexts; u32 supported_coalesce_params; u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 96d2140b471e..fd35d4ec12e1 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -193,7 +193,6 @@ void ring_buffer_set_clock(struct trace_buffer *buffer, void ring_buffer_set_time_stamp_abs(struct trace_buffer *buffer, bool abs); bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); -size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); struct buffer_data_read_page; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 9df3e2973626..fed58e54f15e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -680,7 +680,7 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; - atomic_t ref; /* ref count for opened files */ + refcount_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6439fd8b437b..7caa334f4888 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -275,6 +275,7 @@ struct mana_cq { /* NAPI data */ struct napi_struct napi; int work_done; + int work_done_since_doorbell; int budget; }; diff --git a/kernel/kcov.c b/kernel/kcov.c index f0a69d402066..274b6b7c718d 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -161,6 +161,15 @@ static void kcov_remote_area_put(struct kcov_remote_area *area, kmsan_unpoison_memory(&area->list, sizeof(area->list)); } +/* + * Unlike in_serving_softirq(), this function returns false when called during + * a hardirq or an NMI that happened in the softirq context. + */ +static inline bool in_softirq_really(void) +{ + return in_serving_softirq() && !in_hardirq() && !in_nmi(); +} + static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { unsigned int mode; @@ -170,7 +179,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru * so we ignore code executed in interrupts, unless we are in a remote * coverage collection section in a softirq. */ - if (!in_task() && !(in_serving_softirq() && t->kcov_softirq)) + if (!in_task() && !(in_softirq_really() && t->kcov_softirq)) return false; mode = READ_ONCE(t->kcov_mode); /* @@ -849,7 +858,7 @@ void kcov_remote_start(u64 handle) if (WARN_ON(!kcov_check_handle(handle, true, true, true))) return; - if (!in_task() && !in_serving_softirq()) + if (!in_task() && !in_softirq_really()) return; local_lock_irqsave(&kcov_percpu_data.lock, flags); @@ -991,7 +1000,7 @@ void kcov_remote_stop(void) int sequence; unsigned long flags; - if (!in_task() && !in_serving_softirq()) + if (!in_task() && !in_softirq_really()) return; local_lock_irqsave(&kcov_percpu_data.lock, flags); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 58c88220a478..0349f957e672 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -5936,6 +5936,9 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip) if (DEBUG_LOCKS_WARN_ON(!depth)) return; + if (unlikely(lock->key == &__lockdep_no_track__)) + return; + hlock = find_held_lock(curr, lock, depth, &i); if (!hlock) { print_lock_contention_bug(curr, lock, ip); @@ -5978,6 +5981,9 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip) if (DEBUG_LOCKS_WARN_ON(!depth)) return; + if (unlikely(lock->key == &__lockdep_no_track__)) + return; + hlock = find_held_lock(curr, lock, depth, &i); if (!hlock) { print_lock_contention_bug(curr, lock, _RET_IP_); diff --git a/kernel/module/main.c b/kernel/module/main.c index d9592195c5bb..6f4ec857bdef 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3183,15 +3183,28 @@ static int idempotent_init_module(struct file *f, const char __user * uargs, int if (!f || !(f->f_mode & FMODE_READ)) return -EBADF; - /* See if somebody else is doing the operation? */ - if (idempotent(&idem, file_inode(f))) { - wait_for_completion(&idem.complete); - return idem.ret; + /* Are we the winners of the race and get to do this? */ + if (!idempotent(&idem, file_inode(f))) { + int ret = init_module_from_file(f, uargs, flags); + return idempotent_complete(&idem, ret); } - /* Otherwise, we'll do it and complete others */ - return idempotent_complete(&idem, - init_module_from_file(f, uargs, flags)); + /* + * Somebody else won the race and is loading the module. + * + * We have to wait for it forever, since our 'idem' is + * on the stack and the list entry stays there until + * completed (but we could fix it under the idem_lock) + * + * It's also unclear what a real timeout might be, + * but we could maybe at least make this killable + * and remove the idem entry in that case? + */ + for (;;) { + if (wait_for_completion_timeout(&idem.complete, 10*HZ)) + return idem.ret; + pr_warn_once("module '%pD' taking a long time to load", f); + } } SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) diff --git a/kernel/padata.c b/kernel/padata.c index 53f4bc912712..0fa6c2895460 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -517,6 +517,13 @@ void __init padata_do_multithreaded(struct padata_mt_job *job) ps.chunk_size = max(ps.chunk_size, job->min_chunk); ps.chunk_size = roundup(ps.chunk_size, job->align); + /* + * chunk_size can be 0 if the caller sets min_chunk to 0. So force it + * to at least 1 to prevent divide-by-0 panic in padata_mt_helper().` + */ + if (!ps.chunk_size) + ps.chunk_size = 1U; + list_for_each_entry(pw, &works, pw_list) if (job->numa_aware) { int old_node = atomic_read(&last_used_nid); diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index fc205ad167a9..d1d5ea2d0a1b 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -902,7 +902,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, i = *idx ? : task->curr_ret_stack; while (i > 0) { - ret_stack = get_ret_stack(current, i, &i); + ret_stack = get_ret_stack(task, i, &i); if (!ret_stack) break; /* diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 28853966aa9a..cebd879a30cb 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -693,18 +693,6 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, } /** - * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer - * @buffer: The ring_buffer to get the number of pages from - * @cpu: The cpu of the ring_buffer to get the number of pages from - * - * Returns the number of pages used by a per_cpu buffer of the ring buffer. - */ -size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu) -{ - return buffer->buffers[cpu]->nr_pages; -} - -/** * ring_buffer_nr_dirty_pages - get the number of used pages in the ring buffer * @buffer: The ring_buffer to get the number of pages from * @cpu: The cpu of the ring_buffer to get the number of pages from diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8783bebd0562..bd3e3069300e 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1634,6 +1634,29 @@ static inline void *event_file_data(struct file *filp) extern struct mutex event_mutex; extern struct list_head ftrace_events; +/* + * When the trace_event_file is the filp->i_private pointer, + * it must be taken under the event_mutex lock, and then checked + * if the EVENT_FILE_FL_FREED flag is set. If it is, then the + * data pointed to by the trace_event_file can not be trusted. + * + * Use the event_file_file() to access the trace_event_file from + * the filp the first time under the event_mutex and check for + * NULL. If it is needed to be retrieved again and the event_mutex + * is still held, then the event_file_data() can be used and it + * is guaranteed to be valid. + */ +static inline struct trace_event_file *event_file_file(struct file *filp) +{ + struct trace_event_file *file; + + lockdep_assert_held(&event_mutex); + file = READ_ONCE(file_inode(filp)->i_private); + if (!file || file->flags & EVENT_FILE_FL_FREED) + return NULL; + return file; +} + extern const struct file_operations event_trigger_fops; extern const struct file_operations event_hist_fops; extern const struct file_operations event_hist_debug_fops; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6ef29eba90ce..7266ec2a4eea 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -992,18 +992,18 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) void event_file_get(struct trace_event_file *file) { - atomic_inc(&file->ref); + refcount_inc(&file->ref); } void event_file_put(struct trace_event_file *file) { - if (WARN_ON_ONCE(!atomic_read(&file->ref))) { + if (WARN_ON_ONCE(!refcount_read(&file->ref))) { if (file->flags & EVENT_FILE_FL_FREED) kmem_cache_free(file_cachep, file); return; } - if (atomic_dec_and_test(&file->ref)) { + if (refcount_dec_and_test(&file->ref)) { /* Count should only go to zero when it is freed */ if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED))) return; @@ -1386,12 +1386,12 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, char buf[4] = "0"; mutex_lock(&event_mutex); - file = event_file_data(filp); + file = event_file_file(filp); if (likely(file)) flags = file->flags; mutex_unlock(&event_mutex); - if (!file || flags & EVENT_FILE_FL_FREED) + if (!file) return -ENODEV; if (flags & EVENT_FILE_FL_ENABLED && @@ -1424,8 +1424,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, case 1: ret = -ENODEV; mutex_lock(&event_mutex); - file = event_file_data(filp); - if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) { + file = event_file_file(filp); + if (likely(file)) { ret = tracing_update_buffers(file->tr); if (ret < 0) { mutex_unlock(&event_mutex); @@ -1540,7 +1540,8 @@ enum { static void *f_next(struct seq_file *m, void *v, loff_t *pos) { - struct trace_event_call *call = event_file_data(m->private); + struct trace_event_file *file = event_file_data(m->private); + struct trace_event_call *call = file->event_call; struct list_head *common_head = &ftrace_common_fields; struct list_head *head = trace_get_fields(call); struct list_head *node = v; @@ -1572,7 +1573,8 @@ static void *f_next(struct seq_file *m, void *v, loff_t *pos) static int f_show(struct seq_file *m, void *v) { - struct trace_event_call *call = event_file_data(m->private); + struct trace_event_file *file = event_file_data(m->private); + struct trace_event_call *call = file->event_call; struct ftrace_event_field *field; const char *array_descriptor; @@ -1627,12 +1629,14 @@ static int f_show(struct seq_file *m, void *v) static void *f_start(struct seq_file *m, loff_t *pos) { + struct trace_event_file *file; void *p = (void *)FORMAT_HEADER; loff_t l = 0; /* ->stop() is called even if ->start() fails */ mutex_lock(&event_mutex); - if (!event_file_data(m->private)) + file = event_file_file(m->private); + if (!file) return ERR_PTR(-ENODEV); while (l < *pos && p) @@ -1706,8 +1710,8 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, trace_seq_init(s); mutex_lock(&event_mutex); - file = event_file_data(filp); - if (file && !(file->flags & EVENT_FILE_FL_FREED)) + file = event_file_file(filp); + if (file) print_event_filter(file, s); mutex_unlock(&event_mutex); @@ -1736,9 +1740,13 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, return PTR_ERR(buf); mutex_lock(&event_mutex); - file = event_file_data(filp); - if (file) - err = apply_event_filter(file, buf); + file = event_file_file(filp); + if (file) { + if (file->flags & EVENT_FILE_FL_FREED) + err = -ENODEV; + else + err = apply_event_filter(file, buf); + } mutex_unlock(&event_mutex); kfree(buf); @@ -2485,7 +2493,6 @@ static int event_callback(const char *name, umode_t *mode, void **data, if (strcmp(name, "format") == 0) { *mode = TRACE_MODE_READ; *fops = &ftrace_event_format_fops; - *data = call; return 1; } @@ -2996,7 +3003,7 @@ trace_create_new_event(struct trace_event_call *call, atomic_set(&file->tm_ref, 0); INIT_LIST_HEAD(&file->triggers); list_add(&file->list, &tr->events); - event_file_get(file); + refcount_set(&file->ref, 1); return file; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 6ece1308d36a..5f9119eb7c67 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5601,7 +5601,7 @@ static int hist_show(struct seq_file *m, void *v) mutex_lock(&event_mutex); - event_file = event_file_data(m->private); + event_file = event_file_file(m->private); if (unlikely(!event_file)) { ret = -ENODEV; goto out_unlock; @@ -5880,7 +5880,7 @@ static int hist_debug_show(struct seq_file *m, void *v) mutex_lock(&event_mutex); - event_file = event_file_data(m->private); + event_file = event_file_file(m->private); if (unlikely(!event_file)) { ret = -ENODEV; goto out_unlock; diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index 8650562bdaa9..a8f076809db4 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -299,7 +299,7 @@ event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt, strim(buf); mutex_lock(&event_mutex); - file = event_file_data(filp); + file = event_file_file(filp); if (file) { call = file->event_call; size = parse_entry(buf, call, &entry); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 4bec043c8690..a5e3d6acf1e1 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -159,7 +159,7 @@ static void *trigger_start(struct seq_file *m, loff_t *pos) /* ->stop() is called even if ->start() fails */ mutex_lock(&event_mutex); - event_file = event_file_data(m->private); + event_file = event_file_file(m->private); if (unlikely(!event_file)) return ERR_PTR(-ENODEV); @@ -213,7 +213,7 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) mutex_lock(&event_mutex); - if (unlikely(!event_file_data(file))) { + if (unlikely(!event_file_file(file))) { mutex_unlock(&event_mutex); return -ENODEV; } @@ -293,7 +293,7 @@ static ssize_t event_trigger_regex_write(struct file *file, strim(buf); mutex_lock(&event_mutex); - event_file = event_file_data(file); + event_file = event_file_file(file); if (unlikely(!event_file)) { mutex_unlock(&event_mutex); kfree(buf); diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index a4dcf0f24352..3a56e7c8aa4f 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -454,7 +454,7 @@ static struct tracing_map_elt *get_free_elt(struct tracing_map *map) struct tracing_map_elt *elt = NULL; int idx; - idx = atomic_inc_return(&map->next_elt); + idx = atomic_fetch_add_unless(&map->next_elt, 1, map->max_elts); if (idx < map->max_elts) { elt = *(TRACING_MAP_ELT(map->elts, idx)); if (map->ops && map->ops->elt_init) @@ -699,7 +699,7 @@ void tracing_map_clear(struct tracing_map *map) { unsigned int i; - atomic_set(&map->next_elt, -1); + atomic_set(&map->next_elt, 0); atomic64_set(&map->hits, 0); atomic64_set(&map->drops, 0); @@ -783,7 +783,7 @@ struct tracing_map *tracing_map_create(unsigned int map_bits, map->map_bits = map_bits; map->max_elts = (1 << map_bits); - atomic_set(&map->next_elt, -1); + atomic_set(&map->next_elt, 0); map->map_size = (1 << (map_bits + 1)); map->ops = ops; diff --git a/mm/list_lru.c b/mm/list_lru.c index a29d96929d7c..9b7ff06e9d32 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -85,6 +85,7 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) } #endif /* CONFIG_MEMCG */ +/* The caller must ensure the memcg lifetime. */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { @@ -109,14 +110,22 @@ EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { + bool ret; int nid = page_to_nid(virt_to_page(item)); - struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ? - mem_cgroup_from_slab_obj(item) : NULL; - return list_lru_add(lru, item, nid, memcg); + if (list_lru_memcg_aware(lru)) { + rcu_read_lock(); + ret = list_lru_add(lru, item, nid, mem_cgroup_from_slab_obj(item)); + rcu_read_unlock(); + } else { + ret = list_lru_add(lru, item, nid, NULL); + } + + return ret; } EXPORT_SYMBOL_GPL(list_lru_add_obj); +/* The caller must ensure the memcg lifetime. */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { @@ -139,11 +148,18 @@ EXPORT_SYMBOL_GPL(list_lru_del); bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) { + bool ret; int nid = page_to_nid(virt_to_page(item)); - struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ? - mem_cgroup_from_slab_obj(item) : NULL; - return list_lru_del(lru, item, nid, memcg); + if (list_lru_memcg_aware(lru)) { + rcu_read_lock(); + ret = list_lru_del(lru, item, nid, mem_cgroup_from_slab_obj(item)); + rcu_read_unlock(); + } else { + ret = list_lru_del(lru, item, nid, NULL); + } + + return ret; } EXPORT_SYMBOL_GPL(list_lru_del_obj); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 960371788687..f29157288b7d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3386,11 +3386,28 @@ static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) #define MEM_CGROUP_ID_MAX ((1UL << MEM_CGROUP_ID_SHIFT) - 1) static DEFINE_IDR(mem_cgroup_idr); +static DEFINE_SPINLOCK(memcg_idr_lock); + +static int mem_cgroup_alloc_id(void) +{ + int ret; + + idr_preload(GFP_KERNEL); + spin_lock(&memcg_idr_lock); + ret = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX + 1, + GFP_NOWAIT); + spin_unlock(&memcg_idr_lock); + idr_preload_end(); + return ret; +} static void mem_cgroup_id_remove(struct mem_cgroup *memcg) { if (memcg->id.id > 0) { + spin_lock(&memcg_idr_lock); idr_remove(&mem_cgroup_idr, memcg->id.id); + spin_unlock(&memcg_idr_lock); + memcg->id.id = 0; } } @@ -3524,8 +3541,7 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent) if (!memcg) return ERR_PTR(error); - memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, - 1, MEM_CGROUP_ID_MAX + 1, GFP_KERNEL); + memcg->id.id = mem_cgroup_alloc_id(); if (memcg->id.id < 0) { error = memcg->id.id; goto fail; @@ -3667,7 +3683,9 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) * publish it here at the end of onlining. This matches the * regular ID destruction during offlining. */ + spin_lock(&memcg_idr_lock); idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); + spin_unlock(&memcg_idr_lock); return 0; offline_kmem: diff --git a/mm/shmem.c b/mm/shmem.c index 2faa9daaf54b..5a77acf6ac6a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1629,11 +1629,6 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, unsigned long mask = READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); unsigned long vm_flags = vma->vm_flags; - /* - * Check all the (large) orders below HPAGE_PMD_ORDER + 1 that - * are enabled for this vma. - */ - unsigned long orders = BIT(PMD_ORDER + 1) - 1; loff_t i_size; int order; @@ -1678,7 +1673,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, if (global_huge) mask |= READ_ONCE(huge_shmem_orders_inherit); - return orders & mask; + return THP_ORDERS_ALL_FILE_DEFAULT & mask; } static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault *vmf, @@ -1686,6 +1681,7 @@ static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault unsigned long orders) { struct vm_area_struct *vma = vmf->vma; + pgoff_t aligned_index; unsigned long pages; int order; @@ -1697,9 +1693,9 @@ static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault order = highest_order(orders); while (orders) { pages = 1UL << order; - index = round_down(index, pages); - if (!xa_find(&mapping->i_pages, &index, - index + pages - 1, XA_PRESENT)) + aligned_index = round_down(index, pages); + if (!xa_find(&mapping->i_pages, &aligned_index, + aligned_index + pages - 1, XA_PRESENT)) break; order = next_order(&orders, order); } diff --git a/mm/slub.c b/mm/slub.c index 3520acaf9afa..c9d8a2497fd6 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4690,6 +4690,9 @@ static void __kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) if (!df.slab) continue; + if (kfence_free(df.freelist)) + continue; + do_slab_free(df.s, df.slab, df.freelist, df.tail, df.cnt, _RET_IP_); } while (likely(size)); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index a31d39a821f4..e79cd40bd079 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3019,6 +3019,20 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) } else if (hci_is_adv_monitoring(hdev)) { window = hdev->le_scan_window_adv_monitor; interval = hdev->le_scan_int_adv_monitor; + + /* Disable duplicates filter when scanning for advertisement + * monitor for the following reasons. + * + * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm + * controllers ignore RSSI_Sampling_Period when the duplicates + * filter is enabled. + * + * For SW pattern filtering, when we're not doing interleaved + * scanning, it is necessary to disable duplicates filter, + * otherwise hosts can only receive one advertisement and it's + * impossible to know if a peer is still in range. + */ + filter_dups = LE_SCAN_FILTER_DUP_DISABLE; } else { window = hdev->le_scan_window; interval = hdev->le_scan_interval; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index c3c26bbb5dda..9988ba382b68 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6774,6 +6774,7 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, bt_cb(skb)->l2cap.psm = psm; if (!chan->ops->recv(chan, skb)) { + l2cap_chan_unlock(chan); l2cap_chan_put(chan); return; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 9a1cb5079a7a..b2ae0d2434d2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2045,16 +2045,14 @@ void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; - HLIST_HEAD(deleted_head); struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_find_del_pg(br, pg); - hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); - br_multicast_gc(&deleted_head); + flush_work(&br->mcast_gc_work); br_multicast_port_ctx_deinit(&port->multicast_ctx); free_percpu(port->mcast_stats); } diff --git a/net/core/dev.c b/net/core/dev.c index 751d9b70e6ad..f66e61407883 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9912,6 +9912,15 @@ static void netdev_sync_lower_features(struct net_device *upper, } } +static bool netdev_has_ip_or_hw_csum(netdev_features_t features) +{ + netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + bool ip_csum = (features & ip_csum_mask) == ip_csum_mask; + bool hw_csum = features & NETIF_F_HW_CSUM; + + return ip_csum || hw_csum; +} + static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { @@ -9993,15 +10002,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_LRO; } - if (features & NETIF_F_HW_TLS_TX) { - bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) == - (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - bool hw_csum = features & NETIF_F_HW_CSUM; - - if (!ip_csum && !hw_csum) { - netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); - features &= ~NETIF_F_HW_TLS_TX; - } + if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); + features &= ~NETIF_F_HW_TLS_TX; } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { @@ -10009,6 +10012,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_HW_TLS_RX; } + if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n"); + features &= ~NETIF_F_GSO_UDP_L4; + } + return features; } diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 8ec35194bfcb..ab150641142a 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -148,9 +148,9 @@ static void linkwatch_schedule_work(int urgent) * override the existing timer. */ if (test_bit(LW_URGENT, &linkwatch_flags)) - mod_delayed_work(system_wq, &linkwatch_work, 0); + mod_delayed_work(system_unbound_wq, &linkwatch_work, 0); else - schedule_delayed_work(&linkwatch_work, delay); + queue_delayed_work(system_unbound_wq, &linkwatch_work, delay); } diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 8ca13208d240..e18823bf2330 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1369,14 +1369,17 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, return -EOPNOTSUPP; create = rxfh.rss_context == ETH_RXFH_CONTEXT_ALLOC; - /* If either indir, hash key or function is valid, proceed further. - * Must request at least one change: indir size, hash key, function - * or input transformation. - */ if ((rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE && rxfh.indir_size != dev_indir_size) || - (rxfh.key_size && (rxfh.key_size != dev_key_size)) || + (rxfh.key_size && rxfh.key_size != dev_key_size)) + return -EINVAL; + + /* Must request at least one change: indir size, hash key, function + * or input transformation. + * There's no need for any of it in case of context creation. + */ + if (!create && (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE && rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE && rxfh.input_xfrm == RXH_XFRM_NO_CHANGE)) @@ -1449,12 +1452,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, } if (ops->create_rxfh_context) { - u32 limit = ops->rxfh_max_context_id ?: U32_MAX; + u32 limit = ops->rxfh_max_num_contexts ?: U32_MAX; u32 ctx_id; /* driver uses new API, core allocates ID */ ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx, - XA_LIMIT(1, limit), GFP_KERNEL_ACCOUNT); + XA_LIMIT(1, limit - 1), + GFP_KERNEL_ACCOUNT); if (ret < 0) { kfree(ctx); goto out; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 85531437890c..db6516092daf 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -267,32 +267,49 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head) kfree_sensitive(key); } -void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +static void tcp_ao_info_free_rcu(struct rcu_head *head) { - struct tcp_ao_info *ao; + struct tcp_ao_info *ao = container_of(head, struct tcp_ao_info, rcu); struct tcp_ao_key *key; struct hlist_node *n; + hlist_for_each_entry_safe(key, n, &ao->head, node) { + hlist_del(&key->node); + tcp_sigpool_release(key->tcp_sigpool_id); + kfree_sensitive(key); + } + kfree(ao); + static_branch_slow_dec_deferred(&tcp_ao_needed); +} + +static void tcp_ao_sk_omem_free(struct sock *sk, struct tcp_ao_info *ao) +{ + size_t total_ao_sk_mem = 0; + struct tcp_ao_key *key; + + hlist_for_each_entry(key, &ao->head, node) + total_ao_sk_mem += tcp_ao_sizeof_key(key); + atomic_sub(total_ao_sk_mem, &sk->sk_omem_alloc); +} + +void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +{ + struct tcp_ao_info *ao; + if (twsk) { ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1); - tcp_twsk(sk)->ao_info = NULL; + rcu_assign_pointer(tcp_twsk(sk)->ao_info, NULL); } else { ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1); - tcp_sk(sk)->ao_info = NULL; + rcu_assign_pointer(tcp_sk(sk)->ao_info, NULL); } if (!ao || !refcount_dec_and_test(&ao->refcnt)) return; - hlist_for_each_entry_safe(key, n, &ao->head, node) { - hlist_del_rcu(&key->node); - if (!twsk) - atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); - call_rcu(&key->rcu, tcp_ao_key_free_rcu); - } - - kfree_rcu(ao, rcu); - static_branch_slow_dec_deferred(&tcp_ao_needed); + if (!twsk) + tcp_ao_sk_omem_free(sk, ao); + call_rcu(&ao->rcu, tcp_ao_info_free_rcu); } void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e2b9583ed96a..e37488d3453f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ if (unlikely(len != icsk->icsk_ack.rcv_mss)) { u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE; + u8 old_ratio = tcp_sk(sk)->scaling_ratio; do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; + + if (old_ratio != tcp_sk(sk)->scaling_ratio) + WRITE_ONCE(tcp_sk(sk)->window_clamp, + tcp_win_from_space(sk, sk->sk_rcvbuf)); } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -754,7 +759,8 @@ void tcp_rcv_space_adjust(struct sock *sk) * <prev RTT . ><current RTT .. ><next RTT .... > */ - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && + !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { u64 rcvwin, grow; int rcvbuf; @@ -770,22 +776,12 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - if (rcvbuf > sk->sk_rcvbuf) { - WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - - /* Make the window clamp follow along. */ - WRITE_ONCE(tp->window_clamp, - tcp_win_from_space(sk, rcvbuf)); - } - } else { - /* Make the window clamp follow along while being bounded - * by SO_RCVBUF. - */ - int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf)); + if (rcvbuf > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - if (clamp > tp->window_clamp) - WRITE_ONCE(tp->window_clamp, clamp); + /* Make the window clamp follow along. */ + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); } } tp->rcvq_space.space = copied; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index bc8a9da750fe..b254a5dadfcf 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -282,6 +282,12 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, skb_transport_header(gso_skb))) return ERR_PTR(-EINVAL); + /* We don't know if egress device can segment and checksum the packet + * when IPv6 extension headers are present. Fall back to software GSO. + */ + if (gso_skb->ip_summed != CHECKSUM_PARTIAL) + features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index c80ab3f26084..2e86f520f799 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -86,6 +86,11 @@ /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 +#define L2TP_DEPTH_NESTING 2 +#if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING +#error "L2TP requires its own lockdep subclass" +#endif + /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { @@ -1124,7 +1129,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); - bh_lock_sock_nested(sk); + /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by + * nested socket calls on the same lockdep socket class. This can + * happen when data from a user socket is routed over l2tp, which uses + * another userspace socket. + */ + spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); + if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; @@ -1176,7 +1187,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: - bh_unlock_sock(sk); + spin_unlock(&sk->sk_lock.slock); return ret; } diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 3ae46b545d2c..2d3efb405437 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk) nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */ - nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ + nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8a68382a4fe9..ac2f1a54cc43 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (subflow->remote_key_valid && (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || - ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) { + ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && + (!mp_opt->echo || subflow->mp_join)))) { /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 37954a0b087d..4cae2aa7be5c 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -348,7 +348,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (add_entry) { - if (mptcp_pm_is_kernel(msk)) + if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; sk_reset_timer(sk, &add_entry->add_timer, @@ -512,8 +512,8 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { + struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL; struct sock *sk = (struct sock *)msk; - struct mptcp_pm_addr_entry *local; unsigned int add_addr_signal_max; unsigned int local_addr_max; struct pm_nl_pernet *pernet; @@ -555,8 +555,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check first for announce */ if (msk->pm.add_addr_signaled < add_addr_signal_max) { - local = select_signal_address(pernet, msk); - /* due to racing events on both ends we can reach here while * previous add address is still running: if we invoke now * mptcp_pm_announce_addr(), that will fail and the @@ -567,16 +565,26 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; - if (local) { - if (mptcp_pm_alloc_anno_list(msk, &local->addr)) { - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr, false); - mptcp_pm_nl_addr_send_ack(msk); - } - } + local = select_signal_address(pernet, msk); + if (!local) + goto subflow; + + /* If the alloc fails, we are on memory pressure, not worth + * continuing, and trying to create subflows. + */ + if (!mptcp_pm_alloc_anno_list(msk, &local->addr)) + return; + + __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled++; + mptcp_pm_announce_addr(msk, &local->addr, false); + mptcp_pm_nl_addr_send_ack(msk); + + if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + signal_and_subflow = local; } +subflow: /* check if should create a new subflow */ while (msk->pm.local_addr_used < local_addr_max && msk->pm.subflows < subflows_max) { @@ -584,9 +592,14 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) bool fullmesh; int i, nr; - local = select_local_address(pernet, msk); - if (!local) - break; + if (signal_and_subflow) { + local = signal_and_subflow; + signal_and_subflow = NULL; + } else { + local = select_local_address(pernet, msk); + if (!local) + break; + } fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); @@ -1328,8 +1341,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; - if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { - GENL_SET_ERR_MSG(info, "flags must have signal when using port"); + if (addr.addr.port && !address_use_port(&addr)) { + GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port"); return -EINVAL; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 17fcaa9b0df9..a8a254a5008e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -735,15 +735,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; + int err = 0; ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); struct sctp_endpoint *ep2; struct list_head *list; - int cnt = 0, err = 1; + int cnt = 0; + + err = 1; list_for_each(list, &ep->base.bind_addr.address_list) cnt++; @@ -761,24 +765,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) if (!err) { err = reuseport_add_sock(sk, sk2, any); if (err) - return err; + goto out; break; } else if (err < 0) { - return err; + goto out; } } if (err) { err = reuseport_alloc(sk, any); if (err) - return err; + goto out; } } - write_lock(&head->lock); hlist_add_head(&ep->node, &head->chain); +out: write_unlock(&head->lock); - return 0; + return err; } /* Add an endpoint to the hash. Local BH-safe. */ @@ -803,10 +807,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - - write_lock(&head->lock); hlist_del_init(&ep->node); write_unlock(&head->lock); } diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h index 9d32058db2b5..e19177ce4092 100644 --- a/net/smc/smc_stats.h +++ b/net/smc/smc_stats.h @@ -19,7 +19,7 @@ #include "smc_clc.h" -#define SMC_MAX_FBACK_RSN_CNT 30 +#define SMC_MAX_FBACK_RSN_CNT 36 enum { SMC_BUF_8K, diff --git a/tools/testing/selftests/kselftest/ksft.py b/tools/testing/selftests/kselftest/ksft.py index cd89fb2bc10e..bf215790a89d 100644 --- a/tools/testing/selftests/kselftest/ksft.py +++ b/tools/testing/selftests/kselftest/ksft.py @@ -70,7 +70,7 @@ def test_result(condition, description=""): def finished(): - if ksft_cnt["pass"] == ksft_num_tests: + if ksft_cnt["pass"] + ksft_cnt["skip"] == ksft_num_tests: exit_code = KSFT_PASS else: exit_code = KSFT_FAIL diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 901e0d07765b..7b8a5def54a1 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -110,7 +110,7 @@ endif endif -ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390)) TEST_GEN_FILES += va_high_addr_switch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index 16d0c172eaeb..535eb2c3d7d1 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata, static void __recvpair(struct __test_metadata *_metadata, FIXTURE_DATA(msg_oob) *self, - const void *expected_buf, int expected_len, + const char *expected_buf, int expected_len, int buf_len, int flags) { int i, ret[2], recv_errno[2], expected_errno = 0; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 4df48f1f14ab..9ea6d698e9d3 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1415,18 +1415,28 @@ chk_add_nr() local add_nr=$1 local echo_nr=$2 local port_nr=${3:-0} - local syn_nr=${4:-$port_nr} - local syn_ack_nr=${5:-$port_nr} - local ack_nr=${6:-$port_nr} - local mis_syn_nr=${7:-0} - local mis_ack_nr=${8:-0} + local ns_invert=${4:-""} + local syn_nr=$port_nr + local syn_ack_nr=$port_nr + local ack_nr=$port_nr + local mis_syn_nr=0 + local mis_ack_nr=0 + local ns_tx=$ns1 + local ns_rx=$ns2 + local extra_msg="" local count local timeout - timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) + if [[ $ns_invert = "invert" ]]; then + ns_tx=$ns2 + ns_rx=$ns1 + extra_msg="invert" + fi + + timeout=$(ip netns exec ${ns_tx} sysctl -n net.mptcp.add_addr_timeout) print_check "add" - count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtAddAddr") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtAddAddr") if [ -z "$count" ]; then print_skip # if the test configured a short timeout tolerate greater then expected @@ -1438,7 +1448,7 @@ chk_add_nr() fi print_check "echo" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtEchoAdd") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtEchoAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$echo_nr" ]; then @@ -1449,7 +1459,7 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then print_check "pt" - count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtPortAdd") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtPortAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$port_nr" ]; then @@ -1459,7 +1469,7 @@ chk_add_nr() fi print_check "syn" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_nr" ]; then @@ -1470,7 +1480,7 @@ chk_add_nr() fi print_check "synack" - count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPJoinPortSynAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_ack_nr" ]; then @@ -1481,7 +1491,7 @@ chk_add_nr() fi print_check "ack" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$ack_nr" ]; then @@ -1492,7 +1502,7 @@ chk_add_nr() fi print_check "syn" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_syn_nr" ]; then @@ -1503,7 +1513,7 @@ chk_add_nr() fi print_check "ack" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_ack_nr" ]; then @@ -1513,6 +1523,8 @@ chk_add_nr() print_ok fi fi + + print_info "$extra_msg" } chk_add_tx_nr() @@ -1977,6 +1989,21 @@ signal_address_tests() chk_add_nr 1 1 fi + # uncommon: subflow and signal flags on the same endpoint + # or because the user wrongly picked both, but still expects the client + # to create additional subflows + if reset "subflow and signal together"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags signal,subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 0 invert # only initiated by ns2 + chk_add_nr 0 0 0 # none initiated by ns1 + chk_rst_nr 0 0 invert # no RST sent by the client + chk_rst_nr 0 0 # no RST sent by the server + fi + # accept and use add_addr with additional subflows if reset "multiple subflows and signal"; then pm_nl_set_limits $ns1 0 3 diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 3e74cfa1a2bf..3f2fca02fec5 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -67,6 +67,7 @@ struct testcase { int gso_len; /* mss after applying gso */ int r_num_mss; /* recv(): number of calls of full mss */ int r_len_last; /* recv(): size of last non-mss dgram, if any */ + bool v6_ext_hdr; /* send() dgrams with IPv6 extension headers */ }; const struct in6_addr addr6 = { @@ -77,6 +78,8 @@ const struct in_addr addr4 = { __constant_htonl(0x0a000001), /* 10.0.0.1 */ }; +static const char ipv6_hopopts_pad1[8] = { 0 }; + struct testcase testcases_v4[] = { { /* no GSO: send a single byte */ @@ -256,6 +259,13 @@ struct testcase testcases_v6[] = { .r_num_mss = 2, }, { + /* send 2 1B segments with extension headers */ + .tlen = 2, + .gso_len = 1, + .r_num_mss = 2, + .v6_ext_hdr = true, + }, + { /* send 2B + 2B + 1B segments */ .tlen = 5, .gso_len = 2, @@ -396,11 +406,18 @@ static void run_one(struct testcase *test, int fdt, int fdr, int i, ret, val, mss; bool sent; - fprintf(stderr, "ipv%d tx:%d gso:%d %s\n", + fprintf(stderr, "ipv%d tx:%d gso:%d %s%s\n", addr->sa_family == AF_INET ? 4 : 6, test->tlen, test->gso_len, + test->v6_ext_hdr ? "ext-hdr " : "", test->tfail ? "(fail)" : ""); + if (test->v6_ext_hdr) { + if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, + ipv6_hopopts_pad1, sizeof(ipv6_hopopts_pad1))) + error(1, errno, "setsockopt ipv6 hopopts"); + } + val = test->gso_len; if (cfg_do_setsockopt) { if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val))) @@ -412,6 +429,12 @@ static void run_one(struct testcase *test, int fdt, int fdr, error(1, 0, "send succeeded while expecting failure"); if (!sent && !test->tfail) error(1, 0, "send failed while expecting success"); + + if (test->v6_ext_hdr) { + if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, NULL, 0)) + error(1, errno, "setsockopt ipv6 hopopts clear"); + } + if (!sent) return; |