diff options
196 files changed, 2889 insertions, 1414 deletions
@@ -377,7 +377,7 @@ Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com> -Mathieu Othacehe <m.othacehe@gmail.com> +Mathieu Othacehe <m.othacehe@gmail.com> <othacehe@gnu.org> Mat Martineau <martineau@kernel.org> <mathew.j.martineau@linux.intel.com> Mat Martineau <martineau@kernel.org> <mathewm@codeaurora.org> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> @@ -436,6 +436,7 @@ Muna Sinada <quic_msinada@quicinc.com> <msinada@codeaurora.org> Murali Nalajala <quic_mnalajal@quicinc.com> <mnalajal@codeaurora.org> Mythri P K <mythripk@ti.com> Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com> +Naoya Horiguchi <naoya.horiguchi@nec.com> <n-horiguchi@ah.jp.nec.com> Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com> Neeraj Upadhyay <quic_neeraju@quicinc.com> <neeraju@codeaurora.org> Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com> @@ -637,4 +638,5 @@ Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de> Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yusuke Goda <goda.yusuke@renesas.com> +Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com> Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com> @@ -1855,6 +1855,10 @@ D: Fedora kernel maintenance (2003-2014). D: 'Trinity' and similar fuzz testing work. D: Misc/Other. +N: Tom Joseph +E: tjoseph@cadence.com +D: Cadence PCIe driver + N: Martin Josfsson E: gandalf@wlug.westbo.se P: 1024D/F6B6D3B1 7610 7CED 5C34 4AA6 DBA2 8BE1 5A6D AF95 F6B6 D3B1 @@ -2126,6 +2130,10 @@ S: 2213 La Terrace Circle S: San Jose, CA 95123 S: USA +N: Mike Kravetz +E: mike.kravetz@oracle.com +D: Maintenance and development of the hugetlb subsystem + N: Andreas S. Krebs E: akrebs@altavista.net D: CYPRESS CY82C693 chipset IDE, Digital's PC-Alpha 164SX boards diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 4dfe0d9a57bb..7afff42612e9 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2511,7 +2511,7 @@ temp_valid_lft - INTEGER temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. If temp_prefered_lft is less than the minimum required lifetime (typically - 5 seconds), the preferred lifetime is the minimum required. If + 5 seconds), temporary addresses will not be created. If temp_prefered_lft is greater than temp_valid_lft, the preferred lifetime is temp_valid_lft. diff --git a/MAINTAINERS b/MAINTAINERS index 7cef2d2ef8d7..a7c4cf8201e0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4127,7 +4127,6 @@ M: Franky Lin <franky.lin@broadcom.com> M: Hante Meuleman <hante.meuleman@broadcom.com> L: linux-wireless@vger.kernel.org L: brcm80211-dev-list.pdl@broadcom.com -L: SHA-cyfmac-dev-list@infineon.com S: Supported F: drivers/net/wireless/broadcom/brcm80211/ @@ -6902,8 +6901,8 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/vboxvideo/ DRM DRIVER FOR VMWARE VIRTUAL GPU -M: Zack Rusin <zackr@vmware.com> -R: VMware Graphics Reviewers <linux-graphics-maintainer@vmware.com> +M: Zack Rusin <zack.rusin@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: dri-devel@lists.freedesktop.org S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc @@ -9000,12 +8999,9 @@ K: (devm_)?gpio_regmap_(un)?register GPIO SUBSYSTEM M: Linus Walleij <linus.walleij@linaro.org> M: Bartosz Golaszewski <brgl@bgdev.pl> -R: Andy Shevchenko <andy@kernel.org> L: linux-gpio@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git -F: Documentation/ABI/obsolete/sysfs-gpio -F: Documentation/ABI/testing/gpio-cdev F: Documentation/admin-guide/gpio/ F: Documentation/devicetree/bindings/gpio/ F: Documentation/driver-api/gpio/ @@ -9014,6 +9010,16 @@ F: include/dt-bindings/gpio/ F: include/linux/gpio.h F: include/linux/gpio/ F: include/linux/of_gpio.h + +GPIO UAPI +M: Bartosz Golaszewski <brgl@bgdev.pl> +R: Kent Gibson <warthog618@gmail.com> +L: linux-gpio@vger.kernel.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git +F: Documentation/ABI/obsolete/sysfs-gpio +F: Documentation/ABI/testing/gpio-cdev +F: drivers/gpio/gpiolib-cdev.c F: include/uapi/linux/gpio.h F: tools/gpio/ @@ -9761,7 +9767,6 @@ F: Documentation/networking/device_drivers/ethernet/huawei/hinic.rst F: drivers/net/ethernet/huawei/hinic/ HUGETLB SUBSYSTEM -M: Mike Kravetz <mike.kravetz@oracle.com> M: Muchun Song <muchun.song@linux.dev> L: linux-mm@kvack.org S: Maintained @@ -9785,8 +9790,8 @@ T: git git://linuxtv.org/media_tree.git F: drivers/media/platform/st/sti/hva HWPOISON MEMORY FAILURE HANDLING -M: Naoya Horiguchi <naoya.horiguchi@nec.com> -R: Miaohe Lin <linmiaohe@huawei.com> +M: Miaohe Lin <linmiaohe@huawei.com> +R: Naoya Horiguchi <naoya.horiguchi@nec.com> L: linux-mm@kvack.org S: Maintained F: mm/hwpoison-inject.c @@ -10639,6 +10644,7 @@ F: drivers/gpio/gpio-pch.c F: drivers/gpio/gpio-sch.c F: drivers/gpio/gpio-sodaville.c F: drivers/gpio/gpio-tangier.c +F: drivers/gpio/gpio-tangier.h INTEL GVT-g DRIVERS (Intel GPU Virtualization) M: Zhenyu Wang <zhenyuw@linux.intel.com> @@ -11469,6 +11475,7 @@ F: scripts/*vmlinux* F: scripts/Kbuild* F: scripts/Makefile* F: scripts/basic/ +F: scripts/clang-tools/ F: scripts/dummy-tools/ F: scripts/mk* F: scripts/mod/ @@ -12815,7 +12822,7 @@ S: Maintained F: drivers/net/ethernet/marvell/mvneta.* MARVELL MVPP2 ETHERNET DRIVER -M: Marcin Wojtas <mw@semihalf.com> +M: Marcin Wojtas <marcin.s.wojtas@gmail.com> M: Russell King <linux@armlinux.org.uk> L: netdev@vger.kernel.org S: Maintained @@ -15078,6 +15085,7 @@ K: \bmdo_ NETWORKING [MPTCP] M: Matthieu Baerts <matttbe@kernel.org> M: Mat Martineau <martineau@kernel.org> +R: Geliang Tang <geliang.tang@linux.dev> L: netdev@vger.kernel.org L: mptcp@lists.linux.dev S: Maintained @@ -15425,7 +15433,7 @@ F: Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml F: drivers/bluetooth/btnxpuart.c NXP C45 TJA11XX PHY DRIVER -M: Radu Pirea <radu-nicolae.pirea@oss.nxp.com> +M: Andrei Botila <andrei.botila@oss.nxp.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/phy/nxp-c45-tja11xx.c @@ -16449,11 +16457,10 @@ F: Documentation/devicetree/bindings/pci/pci-armada8k.txt F: drivers/pci/controller/dwc/pcie-armada8k.c PCI DRIVER FOR CADENCE PCIE IP -M: Tom Joseph <tjoseph@cadence.com> L: linux-pci@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/pci/cdns,* -F: drivers/pci/controller/cadence/ +F: drivers/pci/controller/cadence/*cadence* PCI DRIVER FOR FREESCALE LAYERSCAPE M: Minghuan Lian <minghuan.Lian@nxp.com> @@ -23207,9 +23214,8 @@ F: drivers/misc/vmw_vmci/ F: include/linux/vmw_vmci* VMWARE VMMOUSE SUBDRIVER -M: Zack Rusin <zackr@vmware.com> -R: VMware Graphics Reviewers <linux-graphics-maintainer@vmware.com> -R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com> +M: Zack Rusin <zack.rusin@broadcom.com> +R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-input@vger.kernel.org S: Supported F: drivers/input/mouse/vmmouse.c @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c index cb63921232a6..277f6aa8e6c2 100644 --- a/arch/arm/mach-sunxi/mc_smp.c +++ b/arch/arm/mach-sunxi/mc_smp.c @@ -803,16 +803,16 @@ static int __init sunxi_mc_smp_init(void) for (i = 0; i < ARRAY_SIZE(sunxi_mc_smp_data); i++) { ret = of_property_match_string(node, "enable-method", sunxi_mc_smp_data[i].enable_method); - if (!ret) + if (ret >= 0) break; } - is_a83t = sunxi_mc_smp_data[i].is_a83t; - of_node_put(node); - if (ret) + if (ret < 0) return -ENODEV; + is_a83t = sunxi_mc_smp_data[i].is_a83t; + if (!sunxi_mc_smp_cpu_table_init()) return -EINVAL; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 460d799e1296..55f6455a8284 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -607,6 +607,8 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + mm_flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6f105ee4f3cf..1f11a62809f2 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -608,10 +608,10 @@ config ARCH_SUPPORTS_KEXEC def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP) config ARCH_SUPPORTS_KEXEC_FILE - def_bool PPC64 && CRYPTO=y && CRYPTO_SHA256=y + def_bool PPC64 config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SELECTS_KEXEC_FILE def_bool y diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 9e49ede2bc1c..53335ae21a40 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -497,6 +497,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 24c1799e2ec4..cd4c9a204d08 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -702,9 +702,7 @@ config ARCH_SELECTS_KEXEC_FILE select KEXEC_ELF config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE - depends on CRYPTO=y - depends on CRYPTO_SHA256=y + def_bool ARCH_SUPPORTS_KEXEC_FILE config ARCH_SUPPORTS_CRASH_DUMP def_bool y diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 90d4ba36d1d0..081339ddf47e 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -304,6 +304,8 @@ void handle_page_fault(struct pt_regs *regs) goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 3bec98d20283..d5d8f99d1f25 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -254,13 +254,13 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool CRYPTO && CRYPTO_SHA256 && CRYPTO_SHA256_S390 + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool MODULE_SIG_FORMAT config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_CRASH_DUMP def_bool y diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 249aefcf7c4e..ab4098886e56 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -337,6 +337,9 @@ static void do_exception(struct pt_regs *regs, int access) return; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; + /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3762f41bb092..1566748f16c4 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2072,7 +2072,7 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool X86_64 && CRYPTO && CRYPTO_SHA256 + def_bool X86_64 config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -2080,7 +2080,7 @@ config ARCH_SELECTS_KEXEC_FILE select HAVE_IMA_KEXEC if IMA config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool y diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index ce1c777227b4..0f2786d4e405 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4051,12 +4051,17 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable; int global_ctrl, pebs_enable; + /* + * In addition to obeying exclude_guest/exclude_host, remove bits being + * used for PEBS when running a guest, because PEBS writes to virtual + * addresses (not physical addresses). + */ *nr = 0; global_ctrl = (*nr)++; arr[global_ctrl] = (struct perf_guest_switch_msr){ .msr = MSR_CORE_PERF_GLOBAL_CTRL, .host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask, - .guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask), + .guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask, }; if (!x86_pmu.pebs) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index e8babebad7b8..a0ce46c0a2d8 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -576,7 +576,8 @@ static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs) { unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg]; - int3_emulate_call(regs, regs_get_register(regs, offs)); + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + p->ainsn.size); + int3_emulate_jmp(regs, regs_get_register(regs, offs)); } NOKPROBE_SYMBOL(kprobe_emulate_call_indirect); diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index cea25ca8b8cf..c9dae65ac01b 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -11,26 +11,23 @@ #include <asm/checksum.h> #include <asm/word-at-a-time.h> -static inline unsigned short from32to16(unsigned a) +static inline __wsum csum_finalize_sum(u64 temp64) { - unsigned short b = a >> 16; - asm("addw %w2,%w0\n\t" - "adcw $0,%w0\n" - : "=r" (b) - : "0" (b), "r" (a)); - return b; + return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32); } -static inline __wsum csum_tail(u64 temp64, int odd) +static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5]) { - unsigned int result; - - result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff); - if (unlikely(odd)) { - result = from32to16(result); - result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); - } - return (__force __wsum)result; + asm("addq %1,%0\n\t" + "adcq %2,%0\n\t" + "adcq %3,%0\n\t" + "adcq %4,%0\n\t" + "adcq %5,%0\n\t" + "adcq $0,%0" + :"+r" (sum) + :"m" (m[0]), "m" (m[1]), "m" (m[2]), + "m" (m[3]), "m" (m[4])); + return sum; } /* @@ -47,64 +44,32 @@ static inline __wsum csum_tail(u64 temp64, int odd) __wsum csum_partial(const void *buff, int len, __wsum sum) { u64 temp64 = (__force u64)sum; - unsigned odd; - odd = 1 & (unsigned long) buff; - if (unlikely(odd)) { - if (unlikely(len == 0)) - return sum; - temp64 = ror32((__force u32)sum, 8); - temp64 += (*(unsigned char *)buff << 8); - len--; - buff++; + /* Do two 40-byte chunks in parallel to get better ILP */ + if (likely(len >= 80)) { + u64 temp64_2 = 0; + do { + temp64 = update_csum_40b(temp64, buff); + temp64_2 = update_csum_40b(temp64_2, buff + 40); + buff += 80; + len -= 80; + } while (len >= 80); + + asm("addq %1,%0\n\t" + "adcq $0,%0" + :"+r" (temp64): "r" (temp64_2)); } /* - * len == 40 is the hot case due to IPv6 headers, but annotating it likely() - * has noticeable negative affect on codegen for all other cases with - * minimal performance benefit here. + * len == 40 is the hot case due to IPv6 headers, so return + * early for that exact case without checking the tail bytes. */ - if (len == 40) { - asm("addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcq 4*8(%[src]),%[res]\n\t" - "adcq $0,%[res]" - : [res] "+r"(temp64) - : [src] "r"(buff), "m"(*(const char(*)[40])buff)); - return csum_tail(temp64, odd); - } - if (unlikely(len >= 64)) { - /* - * Extra accumulators for better ILP in the loop. - */ - u64 tmp_accum, tmp_carries; - - asm("xorl %k[tmp_accum],%k[tmp_accum]\n\t" - "xorl %k[tmp_carries],%k[tmp_carries]\n\t" - "subl $64, %[len]\n\t" - "1:\n\t" - "addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcl $0,%k[tmp_carries]\n\t" - "addq 4*8(%[src]),%[tmp_accum]\n\t" - "adcq 5*8(%[src]),%[tmp_accum]\n\t" - "adcq 6*8(%[src]),%[tmp_accum]\n\t" - "adcq 7*8(%[src]),%[tmp_accum]\n\t" - "adcl $0,%k[tmp_carries]\n\t" - "addq $64, %[src]\n\t" - "subl $64, %[len]\n\t" - "jge 1b\n\t" - "addq %[tmp_accum],%[res]\n\t" - "adcq %[tmp_carries],%[res]\n\t" - "adcq $0,%[res]" - : [tmp_accum] "=&r"(tmp_accum), - [tmp_carries] "=&r"(tmp_carries), [res] "+r"(temp64), - [len] "+r"(len), [src] "+r"(buff) - : "m"(*(const char *)buff)); + if (len >= 40) { + temp64 = update_csum_40b(temp64, buff); + len -= 40; + if (!len) + return csum_finalize_sum(temp64); + buff += 40; } if (len & 32) { @@ -143,7 +108,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) : [res] "+r"(temp64) : [trail] "r"(trail)); } - return csum_tail(temp64, odd); + return csum_finalize_sum(temp64); } EXPORT_SYMBOL(csum_partial); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index ab778eac1952..679b09cfe241 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1370,6 +1370,8 @@ void do_user_addr_fault(struct pt_regs *regs, goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { diff --git a/block/badblocks.c b/block/badblocks.c index fc92d4e18aa3..db4ec8b9b2a8 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -1312,12 +1312,14 @@ re_check: prev = prev_badblocks(bb, &bad, hint); /* start after all badblocks */ - if ((prev + 1) >= bb->count && !overlap_front(bb, prev, &bad)) { + if ((prev >= 0) && + ((prev + 1) >= bb->count) && !overlap_front(bb, prev, &bad)) { len = sectors; goto update_sectors; } - if (overlap_front(bb, prev, &bad)) { + /* Overlapped with front badblocks record */ + if ((prev >= 0) && overlap_front(bb, prev, &bad)) { if (BB_ACK(p[prev])) acked_badblocks++; else diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c index 5036e58e7235..1405623b03e4 100644 --- a/drivers/accel/qaic/mhi_controller.c +++ b/drivers/accel/qaic/mhi_controller.c @@ -404,8 +404,21 @@ static struct mhi_controller_config aic100_config = { static int mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 *out) { - u32 tmp = readl_relaxed(addr); + u32 tmp; + /* + * SOC_HW_VERSION quirk + * The SOC_HW_VERSION register (offset 0x224) is not reliable and + * may contain uninitialized values, including 0xFFFFFFFF. This could + * cause a false positive link down error. Instead, intercept any + * reads and provide the correct value of the register. + */ + if (addr - mhi_cntrl->regs == 0x224) { + *out = 0x60110200; + return 0; + } + + tmp = readl_relaxed(addr); if (tmp == U32_MAX) return -EIO; diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index 4a8e43a7a6a4..d42f002bc0cf 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -777,7 +777,6 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_ struct dma_buf_attachment *attach; struct drm_gem_object *obj; struct qaic_bo *bo; - size_t size; int ret; bo = qaic_alloc_init_bo(); @@ -795,13 +794,12 @@ struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_ goto attach_fail; } - size = PAGE_ALIGN(attach->dmabuf->size); - if (size == 0) { + if (!attach->dmabuf->size) { ret = -EINVAL; goto size_align_fail; } - drm_gem_private_object_init(dev, obj, size); + drm_gem_private_object_init(dev, obj, attach->dmabuf->size); /* * skipping dma_buf_map_attachment() as we do not know the direction * just yet. Once the direction is known in the subsequent IOCTL to diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index d53d6aa8ee69..47556d8ccc32 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1019,12 +1019,12 @@ static void virtblk_config_changed(struct virtio_device *vdev) static int init_vq(struct virtio_blk *vblk) { int err; - int i; + unsigned short i; vq_callback_t **callbacks; const char **names; struct virtqueue **vqs; unsigned short num_vqs; - unsigned int num_poll_vqs; + unsigned short num_poll_vqs; struct virtio_device *vdev = vblk->vdev; struct irq_affinity desc = { 0, }; @@ -1068,13 +1068,13 @@ static int init_vq(struct virtio_blk *vblk) for (i = 0; i < num_vqs - num_poll_vqs; i++) { callbacks[i] = virtblk_done; - snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i); + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%u", i); names[i] = vblk->vqs[i].name; } for (; i < num_vqs; i++) { callbacks[i] = NULL; - snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%d", i); + snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req_poll.%u", i); names[i] = vblk->vqs[i].name; } diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 44b19e696176..3d5e6d705fc6 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -108,8 +108,9 @@ static inline void send_msg(struct cn_msg *msg) filter_data[1] = 0; } - cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, - cn_filter, (void *)filter_data); + if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, + cn_filter, (void *)filter_data) == -ESRCH) + atomic_set(&proc_event_num_listeners, 0); local_unlock(&local_event.lock); } diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 7e88fd489741..9db9290c3269 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -279,6 +279,51 @@ static char ohci_driver_name[] = KBUILD_MODNAME; #define QUIRK_TI_SLLZ059 0x20 #define QUIRK_IR_WAKE 0x40 +// On PCI Express Root Complex in any type of AMD Ryzen machine, VIA VT6306/6307/6308 with Asmedia +// ASM1083/1085 brings an inconvenience that the read accesses to 'Isochronous Cycle Timer' register +// (at offset 0xf0 in PCI I/O space) often causes unexpected system reboot. The mechanism is not +// clear, since the read access to the other registers is enough safe; e.g. 'Node ID' register, +// while it is probable due to detection of any type of PCIe error. +#define QUIRK_REBOOT_BY_CYCLE_TIMER_READ 0x80000000 + +#if IS_ENABLED(CONFIG_X86) + +static bool has_reboot_by_cycle_timer_read_quirk(const struct fw_ohci *ohci) +{ + return !!(ohci->quirks & QUIRK_REBOOT_BY_CYCLE_TIMER_READ); +} + +#define PCI_DEVICE_ID_ASMEDIA_ASM108X 0x1080 + +static bool detect_vt630x_with_asm1083_on_amd_ryzen_machine(const struct pci_dev *pdev) +{ + const struct pci_dev *pcie_to_pci_bridge; + + // Detect any type of AMD Ryzen machine. + if (!static_cpu_has(X86_FEATURE_ZEN)) + return false; + + // Detect VIA VT6306/6307/6308. + if (pdev->vendor != PCI_VENDOR_ID_VIA) + return false; + if (pdev->device != PCI_DEVICE_ID_VIA_VT630X) + return false; + + // Detect Asmedia ASM1083/1085. + pcie_to_pci_bridge = pdev->bus->self; + if (pcie_to_pci_bridge->vendor != PCI_VENDOR_ID_ASMEDIA) + return false; + if (pcie_to_pci_bridge->device != PCI_DEVICE_ID_ASMEDIA_ASM108X) + return false; + + return true; +} + +#else +#define has_reboot_by_cycle_timer_read_quirk(ohci) false +#define detect_vt630x_with_asm1083_on_amd_ryzen_machine(pdev) false +#endif + /* In case of multiple matches in ohci_quirks[], only the first one is used. */ static const struct { unsigned short vendor, device, revision, flags; @@ -1724,6 +1769,9 @@ static u32 get_cycle_time(struct fw_ohci *ohci) s32 diff01, diff12; int i; + if (has_reboot_by_cycle_timer_read_quirk(ohci)) + return 0; + c2 = reg_read(ohci, OHCI1394_IsochronousCycleTimer); if (ohci->quirks & QUIRK_CYCLE_TIMER) { @@ -3630,6 +3678,9 @@ static int pci_probe(struct pci_dev *dev, if (param_quirks) ohci->quirks = param_quirks; + if (detect_vt630x_with_asm1083_on_amd_ryzen_machine(dev)) + ohci->quirks |= QUIRK_REBOOT_BY_CYCLE_TIMER_READ; + /* * Because dma_alloc_coherent() allocates at least one page, * we save space by using a common buffer for the AR request/ diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index da9b7b8d0716..0d510c9a06a4 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -787,6 +787,8 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n"); seed[0] = 0; } + + boot_params_ptr->hdr.loadflags |= KASLR_FLAG; } status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8dee52ce26d0..93cf73d6fa11 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2188,15 +2188,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) adev->firmware.gpu_info_fw = NULL; - if (adev->mman.discovery_bin) { - /* - * FIXME: The bounding box is still needed by Navi12, so - * temporarily read it from gpu_info firmware. Should be dropped - * when DAL no longer needs it. - */ - if (adev->asic_type != CHIP_NAVI12) - return 0; - } + if (adev->mman.discovery_bin) + return 0; switch (adev->asic_type) { default: diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c8c00c2a5224..4e82ee4d74ac 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6170,8 +6170,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket); - - if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) { + else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT || + stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST || + stream->signal == SIGNAL_TYPE_EDP) { // // should decide stream support vsc sdp colorimetry capability // before building vsc info packet @@ -6187,8 +6188,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) tf = TRANSFER_FUNC_GAMMA_22; mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf); - aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; + if (stream->link->psr_settings.psr_feature_enabled) + aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; } finish: dc_sink_release(sink); @@ -6914,8 +6916,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, if (IS_ERR(mst_state)) return PTR_ERR(mst_state); - if (!mst_state->pbn_div) - mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link); + mst_state->pbn_div = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link); if (!state->duplicated) { int max_bpc = conn_state->max_requested_bpc; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index ec77b2b41ba3..d2271e308fa0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -440,7 +440,115 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { .use_urgent_burst_bw = 0 }; -struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 1069.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 1324.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 1670.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + }, + + .num_states = 5, + .sr_exit_time_us = 1.9, + .sr_enter_plus_exit_time_us = 4.4, + .urgent_latency_us = 3.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 16, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.5, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 4096, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 16, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 45.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 50, + .use_urgent_burst_bw = 0, +}; struct _vcs_dpi_ip_params_st dcn2_1_ip = { .odm_capable = 1, diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index 84f9b412a4f1..738ee763f24a 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -147,12 +147,15 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream, } /* VSC packet set to 4 for PSR-SU, or 2 for PSR1 */ - if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) - vsc_packet_revision = vsc_packet_rev4; - else if (stream->link->replay_settings.config.replay_supported) + if (stream->link->psr_settings.psr_feature_enabled) { + if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) + vsc_packet_revision = vsc_packet_rev4; + else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) + vsc_packet_revision = vsc_packet_rev2; + } + + if (stream->link->replay_settings.config.replay_supported) vsc_packet_revision = vsc_packet_rev4; - else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) - vsc_packet_revision = vsc_packet_rev2; /* Update to revision 5 for extended colorimetry support */ if (stream->use_vsc_sdp_for_colorimetry) diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 1c5049e894e3..c2ccf3724e37 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -318,6 +318,7 @@ enum pp_xgmi_plpd_mode { #define MAX_GFX_CLKS 8 #define MAX_CLKS 4 #define NUM_VCN 4 +#define NUM_JPEG_ENG 32 struct seq_file; enum amd_pp_clock_type; @@ -774,6 +775,85 @@ struct gpu_metrics_v1_4 { uint16_t padding; }; +struct gpu_metrics_v1_5 { + struct metrics_table_header common_header; + + /* Temperature (Celsius) */ + uint16_t temperature_hotspot; + uint16_t temperature_mem; + uint16_t temperature_vrsoc; + + /* Power (Watts) */ + uint16_t curr_socket_power; + + /* Utilization (%) */ + uint16_t average_gfx_activity; + uint16_t average_umc_activity; // memory controller + uint16_t vcn_activity[NUM_VCN]; + uint16_t jpeg_activity[NUM_JPEG_ENG]; + + /* Energy (15.259uJ (2^-16) units) */ + uint64_t energy_accumulator; + + /* Driver attached timestamp (in ns) */ + uint64_t system_clock_counter; + + /* Throttle status */ + uint32_t throttle_status; + + /* Clock Lock Status. Each bit corresponds to clock instance */ + uint32_t gfxclk_lock_status; + + /* Link width (number of lanes) and speed (in 0.1 GT/s) */ + uint16_t pcie_link_width; + uint16_t pcie_link_speed; + + /* XGMI bus width and bitrate (in Gbps) */ + uint16_t xgmi_link_width; + uint16_t xgmi_link_speed; + + /* Utilization Accumulated (%) */ + uint32_t gfx_activity_acc; + uint32_t mem_activity_acc; + + /*PCIE accumulated bandwidth (GB/sec) */ + uint64_t pcie_bandwidth_acc; + + /*PCIE instantaneous bandwidth (GB/sec) */ + uint64_t pcie_bandwidth_inst; + + /* PCIE L0 to recovery state transition accumulated count */ + uint64_t pcie_l0_to_recov_count_acc; + + /* PCIE replay accumulated count */ + uint64_t pcie_replay_count_acc; + + /* PCIE replay rollover accumulated count */ + uint64_t pcie_replay_rover_count_acc; + + /* PCIE NAK sent accumulated count */ + uint32_t pcie_nak_sent_count_acc; + + /* PCIE NAK received accumulated count */ + uint32_t pcie_nak_rcvd_count_acc; + + /* XGMI accumulated data transfer size(KiloBytes) */ + uint64_t xgmi_read_data_acc[NUM_XGMI_LINKS]; + uint64_t xgmi_write_data_acc[NUM_XGMI_LINKS]; + + /* PMFW attached timestamp (10ns resolution) */ + uint64_t firmware_timestamp; + + /* Current clocks (Mhz) */ + uint16_t current_gfxclk[MAX_GFX_CLKS]; + uint16_t current_socclk[MAX_CLKS]; + uint16_t current_vclk0[MAX_CLKS]; + uint16_t current_dclk0[MAX_CLKS]; + uint16_t current_uclk; + + uint16_t padding; +}; + /* * gpu_metrics_v2_0 is not recommended as it's not naturally aligned. * Use gpu_metrics_v2_1 or later instead. diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 49028dde0f87..20c53eefd680 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2128,7 +2128,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ if (amdgpu_dpm_is_overdrive_supported(adev)) *states = ATTR_STATE_SUPPORTED; } else if (DEVICE_ATTR_IS(mem_busy_percent)) { - if (adev->flags & AMD_IS_APU || gc_ver == IP_VERSION(9, 0, 1)) + if ((adev->flags & AMD_IS_APU && + gc_ver != IP_VERSION(9, 4, 3)) || + gc_ver == IP_VERSION(9, 0, 1)) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pcie_bw)) { /* PCIe Perf counters won't work on APU nodes */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h index fef2d290f3f2..7b812b9994d7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h @@ -123,7 +123,7 @@ typedef enum { VOLTAGE_GUARDBAND_COUNT } GFX_GUARDBAND_e; -#define SMU_METRICS_TABLE_VERSION 0x9 +#define SMU_METRICS_TABLE_VERSION 0xB typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; @@ -219,7 +219,103 @@ typedef struct __attribute__((packed, aligned(4))) { uint32_t PCIenReplayARolloverCountAcc; // The Pcie counter itself is accumulated uint32_t PCIeNAKSentCountAcc; // The Pcie counter itself is accumulated uint32_t PCIeNAKReceivedCountAcc; // The Pcie counter itself is accumulated -} MetricsTable_t; + + // VCN/JPEG ACTIVITY + uint32_t VcnBusy[4]; + uint32_t JpegBusy[32]; +} MetricsTableX_t; + +typedef struct __attribute__((packed, aligned(4))) { + uint32_t AccumulationCounter; + + //TEMPERATURE + uint32_t MaxSocketTemperature; + uint32_t MaxVrTemperature; + uint32_t MaxHbmTemperature; + uint64_t MaxSocketTemperatureAcc; + uint64_t MaxVrTemperatureAcc; + uint64_t MaxHbmTemperatureAcc; + + //POWER + uint32_t SocketPowerLimit; + uint32_t MaxSocketPowerLimit; + uint32_t SocketPower; + + //ENERGY + uint64_t Timestamp; + uint64_t SocketEnergyAcc; + uint64_t CcdEnergyAcc; + uint64_t XcdEnergyAcc; + uint64_t AidEnergyAcc; + uint64_t HbmEnergyAcc; + + //FREQUENCY + uint32_t CclkFrequencyLimit; + uint32_t GfxclkFrequencyLimit; + uint32_t FclkFrequency; + uint32_t UclkFrequency; + uint32_t SocclkFrequency[4]; + uint32_t VclkFrequency[4]; + uint32_t DclkFrequency[4]; + uint32_t LclkFrequency[4]; + uint64_t GfxclkFrequencyAcc[8]; + uint64_t CclkFrequencyAcc[96]; + + //FREQUENCY RANGE + uint32_t MaxCclkFrequency; + uint32_t MinCclkFrequency; + uint32_t MaxGfxclkFrequency; + uint32_t MinGfxclkFrequency; + uint32_t FclkFrequencyTable[4]; + uint32_t UclkFrequencyTable[4]; + uint32_t SocclkFrequencyTable[4]; + uint32_t VclkFrequencyTable[4]; + uint32_t DclkFrequencyTable[4]; + uint32_t LclkFrequencyTable[4]; + uint32_t MaxLclkDpmRange; + uint32_t MinLclkDpmRange; + + //XGMI + uint32_t XgmiWidth; + uint32_t XgmiBitrate; + uint64_t XgmiReadBandwidthAcc[8]; + uint64_t XgmiWriteBandwidthAcc[8]; + + //ACTIVITY + uint32_t SocketC0Residency; + uint32_t SocketGfxBusy; + uint32_t DramBandwidthUtilization; + uint64_t SocketC0ResidencyAcc; + uint64_t SocketGfxBusyAcc; + uint64_t DramBandwidthAcc; + uint32_t MaxDramBandwidth; + uint64_t DramBandwidthUtilizationAcc; + uint64_t PcieBandwidthAcc[4]; + + //THROTTLERS + uint32_t ProchotResidencyAcc; + uint32_t PptResidencyAcc; + uint32_t SocketThmResidencyAcc; + uint32_t VrThmResidencyAcc; + uint32_t HbmThmResidencyAcc; + uint32_t GfxLockXCDMak; + + // New Items at end to maintain driver compatibility + uint32_t GfxclkFrequency[8]; + + //PSNs + uint64_t PublicSerialNumber_AID[4]; + uint64_t PublicSerialNumber_XCD[8]; + uint64_t PublicSerialNumber_CCD[12]; + + //XGMI Data tranfser size + uint64_t XgmiReadDataSizeAcc[8];//in KByte + uint64_t XgmiWriteDataSizeAcc[8];//in KByte + + // VCN/JPEG ACTIVITY + uint32_t VcnBusy[4]; + uint32_t JpegBusy[32]; +} MetricsTableA_t; #define SMU_VF_METRICS_TABLE_VERSION 0x3 diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 900a2d9e6d85..b64e07b75937 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -245,6 +245,8 @@ struct PPTable_t { #define SMUQ10_TO_UINT(x) ((x) >> 10) #define SMUQ10_FRAC(x) ((x) & 0x3ff) #define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200)) +#define GET_METRIC_FIELD(field) ((adev->flags & AMD_IS_APU) ?\ + (metrics_a->field) : (metrics_x->field)) struct smu_v13_0_6_dpm_map { enum smu_clk_type clk_type; @@ -327,7 +329,8 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu) SMU_TABLE_INIT(tables, SMU_TABLE_PMSTATUSLOG, SMU13_TOOL_SIZE, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(MetricsTable_t), + SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, + max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); @@ -335,12 +338,13 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu) PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); - smu_table->metrics_table = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL); + smu_table->metrics_table = kzalloc(max(sizeof(MetricsTableX_t), + sizeof(MetricsTableA_t)), GFP_KERNEL); if (!smu_table->metrics_table) return -ENOMEM; smu_table->metrics_time = 0; - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_4); + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_5); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) { @@ -431,9 +435,11 @@ static int smu_v13_0_6_get_metrics_table(struct smu_context *smu, static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; - MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table; + MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table; + MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table; struct PPTable_t *pptable = (struct PPTable_t *)smu_table->driver_pptable; + struct amdgpu_device *adev = smu->adev; int ret, i, retry = 100; /* Store one-time values in driver PPTable */ @@ -444,7 +450,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) return ret; /* Ensure that metrics have been updated */ - if (metrics->AccumulationCounter) + if (GET_METRIC_FIELD(AccumulationCounter)) break; usleep_range(1000, 1100); @@ -454,29 +460,29 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) return -ETIME; pptable->MaxSocketPowerLimit = - SMUQ10_ROUND(metrics->MaxSocketPowerLimit); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketPowerLimit)); pptable->MaxGfxclkFrequency = - SMUQ10_ROUND(metrics->MaxGfxclkFrequency); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxGfxclkFrequency)); pptable->MinGfxclkFrequency = - SMUQ10_ROUND(metrics->MinGfxclkFrequency); + SMUQ10_ROUND(GET_METRIC_FIELD(MinGfxclkFrequency)); for (i = 0; i < 4; ++i) { pptable->FclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->FclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(FclkFrequencyTable)[i]); pptable->UclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->UclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequencyTable)[i]); pptable->SocclkFrequencyTable[i] = SMUQ10_ROUND( - metrics->SocclkFrequencyTable[i]); + GET_METRIC_FIELD(SocclkFrequencyTable)[i]); pptable->VclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->VclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequencyTable)[i]); pptable->DclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->DclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequencyTable)[i]); pptable->LclkFrequencyTable[i] = - SMUQ10_ROUND(metrics->LclkFrequencyTable[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(LclkFrequencyTable)[i]); } /* use AID0 serial number by default */ - pptable->PublicSerialNumber_AID = metrics->PublicSerialNumber_AID[0]; + pptable->PublicSerialNumber_AID = GET_METRIC_FIELD(PublicSerialNumber_AID)[0]; pptable->Init = true; } @@ -778,7 +784,8 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, uint32_t *value) { struct smu_table_context *smu_table = &smu->smu_table; - MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table; + MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table; + MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table; struct amdgpu_device *adev = smu->adev; int ret = 0; int xcc_id; @@ -793,50 +800,50 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, case METRICS_AVERAGE_GFXCLK: if (smu->smc_fw_version >= 0x552F00) { xcc_id = GET_INST(GC, 0); - *value = SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency)[xcc_id]); } else { *value = 0; } break; case METRICS_CURR_SOCCLK: case METRICS_AVERAGE_SOCCLK: - *value = SMUQ10_ROUND(metrics->SocclkFrequency[0]); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(SocclkFrequency)[0]); break; case METRICS_CURR_UCLK: case METRICS_AVERAGE_UCLK: - *value = SMUQ10_ROUND(metrics->UclkFrequency); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequency)); break; case METRICS_CURR_VCLK: - *value = SMUQ10_ROUND(metrics->VclkFrequency[0]); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequency)[0]); break; case METRICS_CURR_DCLK: - *value = SMUQ10_ROUND(metrics->DclkFrequency[0]); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequency)[0]); break; case METRICS_CURR_FCLK: - *value = SMUQ10_ROUND(metrics->FclkFrequency); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(FclkFrequency)); break; case METRICS_AVERAGE_GFXACTIVITY: - *value = SMUQ10_ROUND(metrics->SocketGfxBusy); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusy)); break; case METRICS_AVERAGE_MEMACTIVITY: - *value = SMUQ10_ROUND(metrics->DramBandwidthUtilization); + *value = SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization)); break; case METRICS_CURR_SOCKETPOWER: - *value = SMUQ10_ROUND(metrics->SocketPower) << 8; + *value = SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower)) << 8; break; case METRICS_TEMPERATURE_HOTSPOT: - *value = SMUQ10_ROUND(metrics->MaxSocketTemperature) * + *value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature)) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_TEMPERATURE_MEM: - *value = SMUQ10_ROUND(metrics->MaxHbmTemperature) * + *value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxHbmTemperature)) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; /* This is the max of all VRs and not just SOC VR. * No need to define another data type for the same. */ case METRICS_TEMPERATURE_VRSOC: - *value = SMUQ10_ROUND(metrics->MaxVrTemperature) * + *value = SMUQ10_ROUND(GET_METRIC_FIELD(MaxVrTemperature)) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; default: @@ -2022,67 +2029,70 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu) static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; - struct gpu_metrics_v1_4 *gpu_metrics = - (struct gpu_metrics_v1_4 *)smu_table->gpu_metrics_table; + struct gpu_metrics_v1_5 *gpu_metrics = + (struct gpu_metrics_v1_5 *)smu_table->gpu_metrics_table; struct amdgpu_device *adev = smu->adev; - int ret = 0, xcc_id, inst, i; - MetricsTable_t *metrics; + int ret = 0, xcc_id, inst, i, j; + MetricsTableX_t *metrics_x; + MetricsTableA_t *metrics_a; u16 link_width_level; - metrics = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL); - ret = smu_v13_0_6_get_metrics_table(smu, metrics, true); + metrics_x = kzalloc(max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)), GFP_KERNEL); + ret = smu_v13_0_6_get_metrics_table(smu, metrics_x, true); if (ret) { - kfree(metrics); + kfree(metrics_x); return ret; } - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 4); + metrics_a = (MetricsTableA_t *)metrics_x; + + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 5); gpu_metrics->temperature_hotspot = - SMUQ10_ROUND(metrics->MaxSocketTemperature); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature)); /* Individual HBM stack temperature is not reported */ gpu_metrics->temperature_mem = - SMUQ10_ROUND(metrics->MaxHbmTemperature); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxHbmTemperature)); /* Reports max temperature of all voltage rails */ gpu_metrics->temperature_vrsoc = - SMUQ10_ROUND(metrics->MaxVrTemperature); + SMUQ10_ROUND(GET_METRIC_FIELD(MaxVrTemperature)); gpu_metrics->average_gfx_activity = - SMUQ10_ROUND(metrics->SocketGfxBusy); + SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusy)); gpu_metrics->average_umc_activity = - SMUQ10_ROUND(metrics->DramBandwidthUtilization); + SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilization)); gpu_metrics->curr_socket_power = - SMUQ10_ROUND(metrics->SocketPower); + SMUQ10_ROUND(GET_METRIC_FIELD(SocketPower)); /* Energy counter reported in 15.259uJ (2^-16) units */ - gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc; + gpu_metrics->energy_accumulator = GET_METRIC_FIELD(SocketEnergyAcc); for (i = 0; i < MAX_GFX_CLKS; i++) { xcc_id = GET_INST(GC, i); if (xcc_id >= 0) gpu_metrics->current_gfxclk[i] = - SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]); + SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency)[xcc_id]); if (i < MAX_CLKS) { gpu_metrics->current_socclk[i] = - SMUQ10_ROUND(metrics->SocclkFrequency[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(SocclkFrequency)[i]); inst = GET_INST(VCN, i); if (inst >= 0) { gpu_metrics->current_vclk0[i] = - SMUQ10_ROUND(metrics->VclkFrequency[inst]); + SMUQ10_ROUND(GET_METRIC_FIELD(VclkFrequency)[inst]); gpu_metrics->current_dclk0[i] = - SMUQ10_ROUND(metrics->DclkFrequency[inst]); + SMUQ10_ROUND(GET_METRIC_FIELD(DclkFrequency)[inst]); } } } - gpu_metrics->current_uclk = SMUQ10_ROUND(metrics->UclkFrequency); + gpu_metrics->current_uclk = SMUQ10_ROUND(GET_METRIC_FIELD(UclkFrequency)); /* Throttle status is not reported through metrics now */ gpu_metrics->throttle_status = 0; /* Clock Lock Status. Each bit corresponds to each GFXCLK instance */ - gpu_metrics->gfxclk_lock_status = metrics->GfxLockXCDMak >> GET_INST(GC, 0); + gpu_metrics->gfxclk_lock_status = GET_METRIC_FIELD(GfxLockXCDMak) >> GET_INST(GC, 0); if (!(adev->flags & AMD_IS_APU)) { link_width_level = smu_v13_0_6_get_current_pcie_link_width_level(smu); @@ -2094,38 +2104,57 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table gpu_metrics->pcie_link_speed = smu_v13_0_6_get_current_pcie_link_speed(smu); gpu_metrics->pcie_bandwidth_acc = - SMUQ10_ROUND(metrics->PcieBandwidthAcc[0]); + SMUQ10_ROUND(metrics_x->PcieBandwidthAcc[0]); gpu_metrics->pcie_bandwidth_inst = - SMUQ10_ROUND(metrics->PcieBandwidth[0]); + SMUQ10_ROUND(metrics_x->PcieBandwidth[0]); gpu_metrics->pcie_l0_to_recov_count_acc = - metrics->PCIeL0ToRecoveryCountAcc; + metrics_x->PCIeL0ToRecoveryCountAcc; gpu_metrics->pcie_replay_count_acc = - metrics->PCIenReplayAAcc; + metrics_x->PCIenReplayAAcc; gpu_metrics->pcie_replay_rover_count_acc = - metrics->PCIenReplayARolloverCountAcc; + metrics_x->PCIenReplayARolloverCountAcc; + gpu_metrics->pcie_nak_sent_count_acc = + metrics_x->PCIeNAKSentCountAcc; + gpu_metrics->pcie_nak_rcvd_count_acc = + metrics_x->PCIeNAKReceivedCountAcc; } gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); gpu_metrics->gfx_activity_acc = - SMUQ10_ROUND(metrics->SocketGfxBusyAcc); + SMUQ10_ROUND(GET_METRIC_FIELD(SocketGfxBusyAcc)); gpu_metrics->mem_activity_acc = - SMUQ10_ROUND(metrics->DramBandwidthUtilizationAcc); + SMUQ10_ROUND(GET_METRIC_FIELD(DramBandwidthUtilizationAcc)); for (i = 0; i < NUM_XGMI_LINKS; i++) { gpu_metrics->xgmi_read_data_acc[i] = - SMUQ10_ROUND(metrics->XgmiReadDataSizeAcc[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(XgmiReadDataSizeAcc)[i]); gpu_metrics->xgmi_write_data_acc[i] = - SMUQ10_ROUND(metrics->XgmiWriteDataSizeAcc[i]); + SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWriteDataSizeAcc)[i]); + } + + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { + inst = GET_INST(JPEG, i); + for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) { + gpu_metrics->jpeg_activity[(i * adev->jpeg.num_jpeg_rings) + j] = + SMUQ10_ROUND(GET_METRIC_FIELD(JpegBusy) + [(inst * adev->jpeg.num_jpeg_rings) + j]); + } + } + + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + inst = GET_INST(VCN, i); + gpu_metrics->vcn_activity[i] = + SMUQ10_ROUND(GET_METRIC_FIELD(VcnBusy)[inst]); } - gpu_metrics->xgmi_link_width = SMUQ10_ROUND(metrics->XgmiWidth); - gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(metrics->XgmiBitrate); + gpu_metrics->xgmi_link_width = SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWidth)); + gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(GET_METRIC_FIELD(XgmiBitrate)); - gpu_metrics->firmware_timestamp = metrics->Timestamp; + gpu_metrics->firmware_timestamp = GET_METRIC_FIELD(Timestamp); *table = (void *)gpu_metrics; - kfree(metrics); + kfree(metrics_x); return sizeof(*gpu_metrics); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 001a5cf09657..00cd615bbcdc 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -989,6 +989,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev) case METRICS_VERSION(1, 4): structure_size = sizeof(struct gpu_metrics_v1_4); break; + case METRICS_VERSION(1, 5): + structure_size = sizeof(struct gpu_metrics_v1_5); + break; case METRICS_VERSION(2, 0): structure_size = sizeof(struct gpu_metrics_v2_0); break; diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c index 8161b1a1a4b1..541e4f5afc4c 100644 --- a/drivers/gpu/drm/bridge/parade-ps8640.c +++ b/drivers/gpu/drm/bridge/parade-ps8640.c @@ -210,7 +210,7 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux, struct ps8640 *ps_bridge = aux_to_ps8640(aux); struct regmap *map = ps_bridge->regmap[PAGE0_DP_CNTL]; struct device *dev = &ps_bridge->page[PAGE0_DP_CNTL]->dev; - unsigned int len = msg->size; + size_t len = msg->size; unsigned int data; unsigned int base; int ret; @@ -330,11 +330,12 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux, return ret; } - buf[i] = data; + if (i < msg->size) + buf[i] = data; } } - return len; + return min(len, msg->size); } static ssize_t ps8640_aux_transfer(struct drm_dp_aux *aux, diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index c45c07840f64..b5464199b633 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -527,6 +527,7 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, u32 request_val = AUX_CMD_REQ(msg->request); u8 *buf = msg->buffer; unsigned int len = msg->size; + unsigned int short_len; unsigned int val; int ret; u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG]; @@ -600,7 +601,8 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, } if (val & AUX_IRQ_STATUS_AUX_SHORT) { - ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len); + ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &short_len); + len = min(len, short_len); if (ret) goto exit; } else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) { diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index b21bcd40f111..62ce92772367 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4496,7 +4496,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp, intel_dp->train_set, crtc_state->lane_count); drm_dp_set_phy_test_pattern(&intel_dp->aux, data, - link_status[DP_DPCD_REV]); + intel_dp->dpcd[DP_DPCD_REV]); } static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 7b1c8de2f9cb..2d695818f006 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -772,10 +772,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * The reason field includes flags identifying what * triggered this specific report (mostly timer * triggered or e.g. due to a context switch). - * - * In MMIO triggered reports, some platforms do not set the - * reason bit in this field and it is valid to have a reason - * field of zero. */ reason = oa_report_reason(stream, report); ctx_id = oa_context_id(stream, report32); @@ -787,8 +783,41 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * * Note: that we don't clear the valid_ctx_bit so userspace can * understand that the ID has been squashed by the kernel. + * + * Update: + * + * On XEHP platforms the behavior of context id valid bit has + * changed compared to prior platforms. To describe this, we + * define a few terms: + * + * context-switch-report: This is a report with the reason type + * being context-switch. It is generated when a context switches + * out. + * + * context-valid-bit: A bit that is set in the report ID field + * to indicate that a valid context has been loaded. + * + * gpu-idle: A condition characterized by a + * context-switch-report with context-valid-bit set to 0. + * + * On prior platforms, context-id-valid bit is set to 0 only + * when GPU goes idle. In all other reports, it is set to 1. + * + * On XEHP platforms, context-valid-bit is set to 1 in a context + * switch report if a new context switched in. For all other + * reports it is set to 0. + * + * This change in behavior causes an issue with MMIO triggered + * reports. MMIO triggered reports have the markers in the + * context ID field and the context-valid-bit is 0. The logic + * below to squash the context ID would render the report + * useless since the user will not be able to find it in the OA + * buffer. Since MMIO triggered reports exist only on XEHP, + * we should avoid squashing these for XEHP platforms. */ - if (oa_report_ctx_invalid(stream, report)) { + + if (oa_report_ctx_invalid(stream, report) && + GRAPHICS_VER_FULL(stream->engine->i915) < IP_VER(12, 50)) { ctx_id = INVALID_CTX_ID; oa_context_id_squash(stream, report32); } diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index 57c7edcab602..765e49fd8911 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -392,6 +392,11 @@ void mgag200_primary_plane_helper_atomic_disable(struct drm_plane *plane, .destroy = drm_plane_cleanup, \ DRM_GEM_SHADOW_PLANE_FUNCS +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, const struct drm_format_info *format); +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut); + enum drm_mode_status mgag200_crtc_helper_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode); int mgag200_crtc_helper_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *new_state); diff --git a/drivers/gpu/drm/mgag200/mgag200_g200er.c b/drivers/gpu/drm/mgag200/mgag200_g200er.c index bce267e0f7de..8d4538b71047 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200er.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200er.c @@ -202,6 +202,11 @@ static void mgag200_g200er_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200er_reset_tagfifo(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200ev.c b/drivers/gpu/drm/mgag200/mgag200_g200ev.c index ac957f42abe1..56e6f986bff3 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200ev.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200ev.c @@ -203,6 +203,11 @@ static void mgag200_g200ev_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200ev_set_hiprilvl(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200se.c b/drivers/gpu/drm/mgag200/mgag200_g200se.c index bd6e573c9a1a..ff2b3c6622e7 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200se.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200se.c @@ -334,6 +334,11 @@ static void mgag200_g200se_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200se_set_hiprilvl(mdev, adjusted_mode, format); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index af3ce5a6a636..0f0d59938c3a 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -28,8 +28,8 @@ * This file contains setup code for the CRTC. */ -static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, - const struct drm_format_info *format) +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, + const struct drm_format_info *format) { int i; @@ -65,9 +65,9 @@ static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, } } -static void mgag200_crtc_set_gamma(struct mga_device *mdev, - const struct drm_format_info *format, - struct drm_color_lut *lut) +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut) { int i; diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h index 2fa0445d8928..d1437c08645f 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h @@ -187,7 +187,7 @@ struct nvkm_gsp { void (*rpc_done)(struct nvkm_gsp *gsp, void *repv); void *(*rm_ctrl_get)(struct nvkm_gsp_object *, u32 cmd, u32 argc); - void *(*rm_ctrl_push)(struct nvkm_gsp_object *, void *argv, u32 repc); + int (*rm_ctrl_push)(struct nvkm_gsp_object *, void **argv, u32 repc); void (*rm_ctrl_done)(struct nvkm_gsp_object *, void *repv); void *(*rm_alloc_get)(struct nvkm_gsp_object *, u32 oclass, u32 argc); @@ -265,7 +265,7 @@ nvkm_gsp_rm_ctrl_get(struct nvkm_gsp_object *object, u32 cmd, u32 argc) return object->client->gsp->rm->rm_ctrl_get(object, cmd, argc); } -static inline void * +static inline int nvkm_gsp_rm_ctrl_push(struct nvkm_gsp_object *object, void *argv, u32 repc) { return object->client->gsp->rm->rm_ctrl_push(object, argv, repc); @@ -275,21 +275,24 @@ static inline void * nvkm_gsp_rm_ctrl_rd(struct nvkm_gsp_object *object, u32 cmd, u32 repc) { void *argv = nvkm_gsp_rm_ctrl_get(object, cmd, repc); + int ret; if (IS_ERR(argv)) return argv; - return nvkm_gsp_rm_ctrl_push(object, argv, repc); + ret = nvkm_gsp_rm_ctrl_push(object, &argv, repc); + if (ret) + return ERR_PTR(ret); + return argv; } static inline int nvkm_gsp_rm_ctrl_wr(struct nvkm_gsp_object *object, void *argv) { - void *repv = nvkm_gsp_rm_ctrl_push(object, argv, 0); - - if (IS_ERR(repv)) - return PTR_ERR(repv); + int ret = nvkm_gsp_rm_ctrl_push(object, &argv, 0); + if (ret) + return ret; return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index ca762ea55413..5057d976fa57 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -62,7 +62,7 @@ nouveau_fence_signal(struct nouveau_fence *fence) if (test_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags)) { struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - if (!--fctx->notify_ref) + if (atomic_dec_and_test(&fctx->notify_ref)) drop = 1; } @@ -103,6 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error) void nouveau_fence_context_del(struct nouveau_fence_chan *fctx) { + cancel_work_sync(&fctx->allow_block_work); nouveau_fence_context_kill(fctx, 0); nvif_event_dtor(&fctx->event); fctx->dead = 1; @@ -167,6 +168,18 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc return ret; } +static void +nouveau_fence_work_allow_block(struct work_struct *work) +{ + struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan, + allow_block_work); + + if (atomic_read(&fctx->notify_ref) == 0) + nvif_event_block(&fctx->event); + else + nvif_event_allow(&fctx->event); +} + void nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx) { @@ -178,6 +191,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha } args; int ret; + INIT_WORK(&fctx->allow_block_work, nouveau_fence_work_allow_block); INIT_LIST_HEAD(&fctx->flip); INIT_LIST_HEAD(&fctx->pending); spin_lock_init(&fctx->lock); @@ -521,15 +535,19 @@ static bool nouveau_fence_enable_signaling(struct dma_fence *f) struct nouveau_fence *fence = from_fence(f); struct nouveau_fence_chan *fctx = nouveau_fctx(fence); bool ret; + bool do_work; - if (!fctx->notify_ref++) - nvif_event_allow(&fctx->event); + if (atomic_inc_return(&fctx->notify_ref) == 0) + do_work = true; ret = nouveau_fence_no_signaling(f); if (ret) set_bit(DMA_FENCE_FLAG_USER_BITS, &fence->base.flags); - else if (!--fctx->notify_ref) - nvif_event_block(&fctx->event); + else if (atomic_dec_and_test(&fctx->notify_ref)) + do_work = true; + + if (do_work) + schedule_work(&fctx->allow_block_work); return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 64d33ae7f356..28f5cf013b89 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -3,6 +3,7 @@ #define __NOUVEAU_FENCE_H__ #include <linux/dma-fence.h> +#include <linux/workqueue.h> #include <nvif/event.h> struct nouveau_drm; @@ -45,7 +46,9 @@ struct nouveau_fence_chan { char name[32]; struct nvif_event event; - int notify_ref, dead, killed; + struct work_struct allow_block_work; + atomic_t notify_ref; + int dead, killed; }; struct nouveau_fence_priv { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c index 457ec5db794d..b24eb1e560bc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c @@ -209,7 +209,7 @@ nvkm_disp_dtor(struct nvkm_engine *engine) nvkm_head_del(&head); } - if (disp->func->dtor) + if (disp->func && disp->func->dtor) disp->func->dtor(disp); return data; @@ -243,8 +243,10 @@ nvkm_disp_new_(const struct nvkm_disp_func *func, struct nvkm_device *device, spin_lock_init(&disp->client.lock); ret = nvkm_engine_ctor(&nvkm_disp, device, type, inst, true, &disp->engine); - if (ret) + if (ret) { + disp->func = NULL; return ret; + } if (func->super) { disp->super.wq = create_singlethread_workqueue("nvkm-disp"); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c index 298035070b3a..6a0a4d3b8902 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c @@ -282,7 +282,7 @@ r535_sor_bl_get(struct nvkm_ior *sor) { struct nvkm_disp *disp = sor->disp; NV0073_CTRL_SPECIFIC_BACKLIGHT_BRIGHTNESS_PARAMS *ctrl; - int lvl; + int ret, lvl; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_SPECIFIC_GET_BACKLIGHT_BRIGHTNESS, @@ -292,9 +292,11 @@ r535_sor_bl_get(struct nvkm_ior *sor) ctrl->displayId = BIT(sor->asy.outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } lvl = ctrl->brightness; nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); @@ -649,9 +651,11 @@ r535_conn_new(struct nvkm_disp *disp, u32 id) ctrl->subDeviceInstance = 0; ctrl->displayId = BIT(id); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return (void *)ctrl; + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ERR_PTR(ret); + } list_for_each_entry(conn, &disp->conns, head) { if (conn->index == ctrl->data[0].index) { @@ -686,7 +690,7 @@ r535_outp_acquire(struct nvkm_outp *outp, bool hda) struct nvkm_disp *disp = outp->disp; struct nvkm_ior *ior; NV0073_CTRL_DFP_ASSIGN_SOR_PARAMS *ctrl; - int or; + int ret, or; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DFP_ASSIGN_SOR, sizeof(*ctrl)); @@ -699,9 +703,11 @@ r535_outp_acquire(struct nvkm_outp *outp, bool hda) if (hda) ctrl->flags |= NVDEF(NV0073_CTRL, DFP_ASSIGN_SOR_FLAGS, AUDIO, OPTIMAL); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } for (or = 0; or < ARRAY_SIZE(ctrl->sorAssignListWithTag); or++) { if (ctrl->sorAssignListWithTag[or].displayMask & BIT(outp->index)) { @@ -727,6 +733,7 @@ static int r535_disp_head_displayid(struct nvkm_disp *disp, int head, u32 *displayid) { NV0073_CTRL_SYSTEM_GET_ACTIVE_PARAMS *ctrl; + int ret; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_SYSTEM_GET_ACTIVE, sizeof(*ctrl)); @@ -736,9 +743,11 @@ r535_disp_head_displayid(struct nvkm_disp *disp, int head, u32 *displayid) ctrl->subDeviceInstance = 0; ctrl->head = head; - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } *displayid = ctrl->displayId; nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); @@ -772,9 +781,11 @@ r535_outp_inherit(struct nvkm_outp *outp) ctrl->subDeviceInstance = 0; ctrl->displayId = displayid; - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); return NULL; + } id = ctrl->index; proto = ctrl->protocol; @@ -825,6 +836,7 @@ r535_outp_dfp_get_info(struct nvkm_outp *outp) { NV0073_CTRL_DFP_GET_INFO_PARAMS *ctrl; struct nvkm_disp *disp = outp->disp; + int ret; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DFP_GET_INFO, sizeof(*ctrl)); if (IS_ERR(ctrl)) @@ -832,9 +844,11 @@ r535_outp_dfp_get_info(struct nvkm_outp *outp) ctrl->displayId = BIT(outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } nvkm_debug(&disp->engine.subdev, "DFP %08x: flags:%08x flags2:%08x\n", ctrl->displayId, ctrl->flags, ctrl->flags2); @@ -858,9 +872,11 @@ r535_outp_detect(struct nvkm_outp *outp) ctrl->subDeviceInstance = 0; ctrl->displayMask = BIT(outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } if (ctrl->displayMask & BIT(outp->index)) { ret = r535_outp_dfp_get_info(outp); @@ -895,6 +911,7 @@ r535_dp_mst_id_get(struct nvkm_outp *outp, u32 *pid) { NV0073_CTRL_CMD_DP_TOPOLOGY_ALLOCATE_DISPLAYID_PARAMS *ctrl; struct nvkm_disp *disp = outp->disp; + int ret; ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_TOPOLOGY_ALLOCATE_DISPLAYID, @@ -904,9 +921,11 @@ r535_dp_mst_id_get(struct nvkm_outp *outp, u32 *pid) ctrl->subDeviceInstance = 0; ctrl->displayId = BIT(outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } *pid = ctrl->displayIdAssigned; nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); @@ -938,38 +957,60 @@ r535_dp_train_target(struct nvkm_outp *outp, u8 target, bool mst, u8 link_nr, u8 { struct nvkm_disp *disp = outp->disp; NV0073_CTRL_DP_CTRL_PARAMS *ctrl; - int ret; - - ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CTRL, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + int ret, retries; + u32 cmd, data; - ctrl->subDeviceInstance = 0; - ctrl->displayId = BIT(outp->index); - ctrl->cmd = NVDEF(NV0073_CTRL, DP_CMD, SET_LANE_COUNT, TRUE) | - NVDEF(NV0073_CTRL, DP_CMD, SET_LINK_BW, TRUE) | - NVDEF(NV0073_CTRL, DP_CMD, TRAIN_PHY_REPEATER, YES); - ctrl->data = NVVAL(NV0073_CTRL, DP_DATA, SET_LANE_COUNT, link_nr) | - NVVAL(NV0073_CTRL, DP_DATA, SET_LINK_BW, link_bw) | - NVVAL(NV0073_CTRL, DP_DATA, TARGET, target); + cmd = NVDEF(NV0073_CTRL, DP_CMD, SET_LANE_COUNT, TRUE) | + NVDEF(NV0073_CTRL, DP_CMD, SET_LINK_BW, TRUE) | + NVDEF(NV0073_CTRL, DP_CMD, TRAIN_PHY_REPEATER, YES); + data = NVVAL(NV0073_CTRL, DP_DATA, SET_LANE_COUNT, link_nr) | + NVVAL(NV0073_CTRL, DP_DATA, SET_LINK_BW, link_bw) | + NVVAL(NV0073_CTRL, DP_DATA, TARGET, target); if (mst) - ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_FORMAT_MODE, MULTI_STREAM); + cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_FORMAT_MODE, MULTI_STREAM); if (outp->dp.dpcd[DPCD_RC02] & DPCD_RC02_ENHANCED_FRAME_CAP) - ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_ENHANCED_FRAMING, TRUE); + cmd |= NVDEF(NV0073_CTRL, DP_CMD, SET_ENHANCED_FRAMING, TRUE); if (target == 0 && (outp->dp.dpcd[DPCD_RC02] & 0x20) && !(outp->dp.dpcd[DPCD_RC03] & DPCD_RC03_TPS4_SUPPORTED)) - ctrl->cmd |= NVDEF(NV0073_CTRL, DP_CMD, POST_LT_ADJ_REQ_GRANTED, YES); + cmd |= NVDEF(NV0073_CTRL, DP_CMD, POST_LT_ADJ_REQ_GRANTED, YES); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + /* We should retry up to 3 times, but only if GSP asks politely */ + for (retries = 0; retries < 3; ++retries) { + ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_CTRL, + sizeof(*ctrl)); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); + + ctrl->subDeviceInstance = 0; + ctrl->displayId = BIT(outp->index); + ctrl->retryTimeMs = 0; + ctrl->cmd = cmd; + ctrl->data = data; + + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret == -EAGAIN && ctrl->retryTimeMs) { + /* + * Device (likely an eDP panel) isn't ready yet, wait for the time specified + * by GSP before retrying again + */ + nvkm_debug(&disp->engine.subdev, + "Waiting %dms for GSP LT panel delay before retrying\n", + ctrl->retryTimeMs); + msleep(ctrl->retryTimeMs); + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + } else { + /* GSP didn't say to retry, or we were successful */ + if (ctrl->err) + ret = -EIO; + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + break; + } + } - ret = ctrl->err ? -EIO : 0; - nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); return ret; } @@ -1036,9 +1077,11 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize) ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0; memcpy(ctrl->data, data, size); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); return PTR_ERR(ctrl); + } memcpy(data, ctrl->data, size); *psize = ctrl->size; @@ -1111,10 +1154,13 @@ r535_tmds_edid_get(struct nvkm_outp *outp, u8 *data, u16 *psize) ctrl->subDeviceInstance = 0; ctrl->displayId = BIT(outp->index); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } + ret = -E2BIG; if (ctrl->bufferSize <= *psize) { memcpy(data, ctrl->edidBuffer, ctrl->bufferSize); *psize = ctrl->bufferSize; @@ -1153,9 +1199,11 @@ r535_outp_new(struct nvkm_disp *disp, u32 id) ctrl->subDeviceInstance = 0; ctrl->displayId = BIT(id); - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } switch (ctrl->type) { case NV0073_CTRL_SPECIFIC_OR_TYPE_NONE: @@ -1229,9 +1277,11 @@ r535_outp_new(struct nvkm_disp *disp, u32 id) ctrl->sorIndex = ~0; - ctrl = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, ctrl, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if (ret) { + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + return ret; + } switch (NVVAL_GET(ctrl->maxLinkRate, NV0073_CTRL_CMD, DP_GET_CAPS, MAX_LINK_RATE)) { case NV0073_CTRL_CMD_DP_GET_CAPS_MAX_LINK_RATE_1_62: @@ -1465,8 +1515,6 @@ r535_disp_oneinit(struct nvkm_disp *disp) bool nvhg = acpi_check_dsm(handle, &NVHG_DSM_GUID, NVHG_DSM_REV, 1ULL << 0x00000014); - printk(KERN_ERR "bl: nbci:%d nvhg:%d\n", nbci, nvhg); - if (nbci || nvhg) { union acpi_object argv4 = { .buffer.type = ACPI_TYPE_BUFFER, @@ -1479,9 +1527,6 @@ r535_disp_oneinit(struct nvkm_disp *disp) if (!obj) { acpi_handle_info(handle, "failed to evaluate _DSM\n"); } else { - printk(KERN_ERR "bl: obj type %d\n", obj->type); - printk(KERN_ERR "bl: obj len %d\n", obj->package.count); - for (int i = 0; i < obj->package.count; i++) { union acpi_object *elt = &obj->package.elements[i]; u32 size; @@ -1491,12 +1536,10 @@ r535_disp_oneinit(struct nvkm_disp *disp) else size = 4; - printk(KERN_ERR "elt %03d: type %d size %d\n", i, elt->type, size); memcpy(&ctrl->backLightData[ctrl->backLightDataSize], &elt->integer.value, size); ctrl->backLightDataSize += size; } - printk(KERN_ERR "bl: data size %d\n", ctrl->backLightDataSize); ctrl->status = 0; ACPI_FREE(obj); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c index d088e636edc3..b903785056b5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c @@ -242,6 +242,7 @@ r535_chan_id_put(struct nvkm_chan *chan) nvkm_memory_unref(&userd->mem); nvkm_chid_put(runl->chid, userd->chid, &chan->cgrp->lock); list_del(&userd->head); + kfree(userd); } break; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index 44fb86841c05..9ee58e2a0eb2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -70,6 +70,20 @@ struct r535_gsp_msg { #define GSP_MSG_HDR_SIZE offsetof(struct r535_gsp_msg, data) +static int +r535_rpc_status_to_errno(uint32_t rpc_status) +{ + switch (rpc_status) { + case 0x55: /* NV_ERR_NOT_READY */ + case 0x66: /* NV_ERR_TIMEOUT_RETRY */ + return -EAGAIN; + case 0x51: /* NV_ERR_NO_MEMORY */ + return -ENOMEM; + default: + return -EINVAL; + } +} + static void * r535_gsp_msgq_wait(struct nvkm_gsp *gsp, u32 repc, u32 *prepc, int *ptime) { @@ -298,7 +312,8 @@ retry: struct nvkm_gsp_msgq_ntfy *ntfy = &gsp->msgq.ntfy[i]; if (ntfy->fn == msg->function) { - ntfy->func(ntfy->priv, ntfy->fn, msg->data, msg->length - sizeof(*msg)); + if (ntfy->func) + ntfy->func(ntfy->priv, ntfy->fn, msg->data, msg->length - sizeof(*msg)); break; } } @@ -583,14 +598,14 @@ r535_gsp_rpc_rm_alloc_push(struct nvkm_gsp_object *object, void *argv, u32 repc) return rpc; if (rpc->status) { - nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status); - ret = ERR_PTR(-EINVAL); + ret = ERR_PTR(r535_rpc_status_to_errno(rpc->status)); + if (PTR_ERR(ret) != -EAGAIN) + nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status); } else { ret = repc ? rpc->params : NULL; } - if (IS_ERR_OR_NULL(ret)) - nvkm_gsp_rpc_done(gsp, rpc); + nvkm_gsp_rpc_done(gsp, rpc); return ret; } @@ -623,29 +638,34 @@ r535_gsp_rpc_rm_ctrl_done(struct nvkm_gsp_object *object, void *repv) { rpc_gsp_rm_control_v03_00 *rpc = container_of(repv, typeof(*rpc), params); + if (!repv) + return; nvkm_gsp_rpc_done(object->client->gsp, rpc); } -static void * -r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void *argv, u32 repc) +static int +r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void **argv, u32 repc) { - rpc_gsp_rm_control_v03_00 *rpc = container_of(argv, typeof(*rpc), params); + rpc_gsp_rm_control_v03_00 *rpc = container_of((*argv), typeof(*rpc), params); struct nvkm_gsp *gsp = object->client->gsp; - void *ret; + int ret = 0; rpc = nvkm_gsp_rpc_push(gsp, rpc, true, repc); - if (IS_ERR_OR_NULL(rpc)) - return rpc; + if (IS_ERR_OR_NULL(rpc)) { + *argv = NULL; + return PTR_ERR(rpc); + } if (rpc->status) { - nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n", - object->client->object.handle, object->handle, rpc->cmd, rpc->status); - ret = ERR_PTR(-EINVAL); - } else { - ret = repc ? rpc->params : NULL; + ret = r535_rpc_status_to_errno(rpc->status); + if (ret != -EAGAIN) + nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n", + object->client->object.handle, object->handle, rpc->cmd, rpc->status); } - if (IS_ERR_OR_NULL(ret)) + if (repc) + *argv = rpc->params; + else nvkm_gsp_rpc_done(gsp, rpc); return ret; @@ -843,9 +863,11 @@ r535_gsp_intr_get_table(struct nvkm_gsp *gsp) if (IS_ERR(ctrl)) return PTR_ERR(ctrl); - ctrl = nvkm_gsp_rm_ctrl_push(&gsp->internal.device.subdevice, ctrl, sizeof(*ctrl)); - if (WARN_ON(IS_ERR(ctrl))) - return PTR_ERR(ctrl); + ret = nvkm_gsp_rm_ctrl_push(&gsp->internal.device.subdevice, &ctrl, sizeof(*ctrl)); + if (WARN_ON(ret)) { + nvkm_gsp_rm_ctrl_done(&gsp->internal.device.subdevice, ctrl); + return ret; + } for (unsigned i = 0; i < ctrl->tableLen; i++) { enum nvkm_subdev_type type; @@ -1099,16 +1121,12 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps) if (!obj) return; - printk(KERN_ERR "nvop: obj type %d\n", obj->type); - printk(KERN_ERR "nvop: obj len %d\n", obj->buffer.length); - if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || WARN_ON(obj->buffer.length != 4)) return; caps->status = 0; caps->optimusCaps = *(u32 *)obj->buffer.pointer; - printk(KERN_ERR "nvop: caps %08x\n", caps->optimusCaps); ACPI_FREE(obj); @@ -1135,9 +1153,6 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt) if (!obj) return; - printk(KERN_ERR "jt: obj type %d\n", obj->type); - printk(KERN_ERR "jt: obj len %d\n", obj->buffer.length); - if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || WARN_ON(obj->buffer.length != 4)) return; @@ -1146,7 +1161,6 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt) jt->jtCaps = *(u32 *)obj->buffer.pointer; jt->jtRevId = (jt->jtCaps & 0xfff00000) >> 20; jt->bSBIOSCaps = 0; - printk(KERN_ERR "jt: caps %08x rev:%04x\n", jt->jtCaps, jt->jtRevId); ACPI_FREE(obj); @@ -1157,6 +1171,8 @@ static void r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode, MUX_METHOD_DATA_ELEMENT *part) { + union acpi_object mux_arg = { ACPI_TYPE_INTEGER }; + struct acpi_object_list input = { 1, &mux_arg }; acpi_handle iter = NULL, handle_mux = NULL; acpi_status status; unsigned long long value; @@ -1179,14 +1195,18 @@ r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode, if (!handle_mux) return; - status = acpi_evaluate_integer(handle_mux, "MXDM", NULL, &value); + /* I -think- 0 means "acquire" according to nvidia's driver source */ + input.pointer->integer.type = ACPI_TYPE_INTEGER; + input.pointer->integer.value = 0; + + status = acpi_evaluate_integer(handle_mux, "MXDM", &input, &value); if (ACPI_SUCCESS(status)) { mode->acpiId = id; mode->mode = value; mode->status = 0; } - status = acpi_evaluate_integer(handle_mux, "MXDS", NULL, &value); + status = acpi_evaluate_integer(handle_mux, "MXDS", &input, &value); if (ACPI_SUCCESS(status)) { part->acpiId = id; part->mode = value; @@ -1232,8 +1252,8 @@ r535_gsp_acpi_dod(acpi_handle handle, DOD_METHOD_DATA *dod) dod->acpiIdListLen += sizeof(dod->acpiIdList[0]); } - printk(KERN_ERR "_DOD: ok! len:%d\n", dod->acpiIdListLen); dod->status = 0; + kfree(output.pointer); } #endif @@ -2186,7 +2206,9 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp) r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_MMU_FAULT_QUEUED, r535_gsp_msg_mmu_fault_queued, gsp); r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_OS_ERROR_LOG, r535_gsp_msg_os_error_log, gsp); - + r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_PERF_BRIDGELESS_INFO_UPDATE, NULL, NULL); + r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_UCODE_LIBOS_PRINT, NULL, NULL); + r535_gsp_msg_ntfy_add(gsp, NV_VGPU_MSG_EVENT_GSP_SEND_USER_SHARED_DATA, NULL, NULL); ret = r535_gsp_rm_boot_ctor(gsp); if (ret) return ret; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index f9a5cffa64b1..134c36edb6cf 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -851,9 +851,10 @@ static const struct block_device_operations mmc_bdops = { static int mmc_blk_part_switch_pre(struct mmc_card *card, unsigned int part_type) { + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) { + if ((part_type & mask) == mask) { if (card->ext_csd.cmdq_en) { ret = mmc_cmdq_disable(card); if (ret) @@ -868,9 +869,10 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card, static int mmc_blk_part_switch_post(struct mmc_card *card, unsigned int part_type) { + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) { + if ((part_type & mask) == mask) { mmc_retune_unpause(card->host); if (card->reenable_cmdq && !card->ext_csd.cmdq_en) ret = mmc_cmdq_enable(card); @@ -3145,4 +3147,3 @@ module_exit(mmc_blk_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Multimedia Card (MMC) block device driver"); - diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 096093f7be00..2f51db4df1a8 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -692,6 +692,7 @@ EXPORT_SYMBOL(mmc_remove_host); */ void mmc_free_host(struct mmc_host *host) { + cancel_delayed_work_sync(&host->detect); mmc_pwrseq_free(host); put_device(&host->class_dev); } diff --git a/drivers/mmc/host/meson-mx-sdhc-mmc.c b/drivers/mmc/host/meson-mx-sdhc-mmc.c index 528ec8166e7c..1ed9731e77ef 100644 --- a/drivers/mmc/host/meson-mx-sdhc-mmc.c +++ b/drivers/mmc/host/meson-mx-sdhc-mmc.c @@ -269,7 +269,7 @@ static int meson_mx_sdhc_enable_clks(struct mmc_host *mmc) static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios) { struct meson_mx_sdhc_host *host = mmc_priv(mmc); - u32 rx_clk_phase; + u32 val, rx_clk_phase; int ret; meson_mx_sdhc_disable_clks(mmc); @@ -290,27 +290,11 @@ static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios) mmc->actual_clock = clk_get_rate(host->sd_clk); /* - * according to Amlogic the following latching points are - * selected with empirical values, there is no (known) formula - * to calculate these. + * Phase 90 should work in most cases. For data transmission, + * meson_mx_sdhc_execute_tuning() will find a accurate value */ - if (mmc->actual_clock > 100000000) { - rx_clk_phase = 1; - } else if (mmc->actual_clock > 45000000) { - if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) - rx_clk_phase = 15; - else - rx_clk_phase = 11; - } else if (mmc->actual_clock >= 25000000) { - rx_clk_phase = 15; - } else if (mmc->actual_clock > 5000000) { - rx_clk_phase = 23; - } else if (mmc->actual_clock > 1000000) { - rx_clk_phase = 55; - } else { - rx_clk_phase = 1061; - } - + regmap_read(host->regmap, MESON_SDHC_CLKC, &val); + rx_clk_phase = FIELD_GET(MESON_SDHC_CLKC_CLK_DIV, val) / 4; regmap_update_bits(host->regmap, MESON_SDHC_CLK2, MESON_SDHC_CLK2_RX_CLK_PHASE, FIELD_PREP(MESON_SDHC_CLK2_RX_CLK_PHASE, diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 6b8a57e2d20f..bed57a1c64b5 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -239,15 +239,19 @@ static inline void _sdhci_sprd_set_clock(struct sdhci_host *host, div = ((div & 0x300) >> 2) | ((div & 0xFF) << 8); sdhci_enable_clk(host, div); + val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); + mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; /* Enable CLK_AUTO when the clock is greater than 400K. */ if (clk > 400000) { - val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); - mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | - SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; if (mask != (val & mask)) { val |= mask; sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); } + } else { + if (val & mask) { + val &= ~mask; + sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); + } } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 579eebb6fc56..e1f1e646cf48 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12093,6 +12093,8 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_cfg_ntp_filters(bp); if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event)) bnxt_hwrm_exec_fwd_req(bp); + if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) + netdev_info(bp->dev, "Receive PF driver unload event!\n"); if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) { bnxt_hwrm_port_qstats(bp, 0); bnxt_hwrm_port_qstats_ext(bp, 0); @@ -13093,8 +13095,6 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) } } } - if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) - netdev_info(bp->dev, "Receive PF driver unload event!\n"); } #else diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 9282403d1bf6..2d7ae71287b1 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2132,8 +2132,10 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) /* Note: if we ever change from DMA_TX_APPEND_CRC below we * will need to restore software padding of "runt" packets */ + len_stat |= DMA_TX_APPEND_CRC; + if (!i) { - len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; + len_stat |= DMA_SOP; if (skb->ip_summed == CHECKSUM_PARTIAL) len_stat |= DMA_TX_DO_CSUM; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1ab8dbe2d880..d5519af34657 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -107,12 +107,18 @@ static struct workqueue_struct *i40e_wq; static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, struct net_device *netdev, int delta) { + struct netdev_hw_addr_list *ha_list; struct netdev_hw_addr *ha; if (!f || !netdev) return; - netdev_for_each_mc_addr(ha, netdev) { + if (is_unicast_ether_addr(f->macaddr) || is_link_local_ether_addr(f->macaddr)) + ha_list = &netdev->uc; + else + ha_list = &netdev->mc; + + netdev_hw_addr_list_for_each(ha, ha_list) { if (ether_addr_equal(ha->addr, f->macaddr)) { ha->refcount += delta; if (ha->refcount <= 0) @@ -16512,6 +16518,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev) return; i40e_reset_and_rebuild(pf, false, false); +#ifdef CONFIG_PCI_IOV + i40e_restore_all_vfs_msi_state(pdev); +#endif /* CONFIG_PCI_IOV */ } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 3f99eb198245..de5ec4e6bedf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -154,6 +154,32 @@ void i40e_vc_notify_reset(struct i40e_pf *pf) (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); } +#ifdef CONFIG_PCI_IOV +void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev) +{ + u16 vf_id; + u16 pos; + + /* Continue only if this is a PF */ + if (!pdev->is_physfn) + return; + + if (!pci_num_vf(pdev)) + return; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + if (pos) { + struct pci_dev *vf_dev = NULL; + + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_id); + while ((vf_dev = pci_get_device(pdev->vendor, vf_id, vf_dev))) { + if (vf_dev->is_virtfn && vf_dev->physfn == pdev) + pci_restore_msi_state(vf_dev); + } + } +} +#endif /* CONFIG_PCI_IOV */ + /** * i40e_vc_notify_vf_reset * @vf: pointer to the VF structure @@ -3521,16 +3547,16 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf, bool found = false; int bkt; - if (!tc_filter->action) { + if (tc_filter->action != VIRTCHNL_ACTION_TC_REDIRECT) { dev_info(&pf->pdev->dev, - "VF %d: Currently ADq doesn't support Drop Action\n", - vf->vf_id); + "VF %d: ADQ doesn't support this action (%d)\n", + vf->vf_id, tc_filter->action); goto err; } /* action_meta is TC number here to which the filter is applied */ if (!tc_filter->action_meta || - tc_filter->action_meta > I40E_MAX_VF_VSI) { + tc_filter->action_meta > vf->num_tc) { dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n", vf->vf_id, tc_filter->action_meta); goto err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 2ee0f8a23248..5fd607c0de0a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -137,6 +137,9 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable); void i40e_vc_notify_link_state(struct i40e_pf *pf); void i40e_vc_notify_reset(struct i40e_pf *pf); +#ifdef CONFIG_PCI_IOV +void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev); +#endif /* CONFIG_PCI_IOV */ int i40e_get_vf_stats(struct net_device *netdev, int vf_id, struct ifla_vf_stats *vf_stats); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index d7fdb7ba7268..fbd5d92182d3 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1359,8 +1359,9 @@ struct ice_aqc_get_link_status_data { u8 lp_flowcontrol; #define ICE_AQ_LINK_LP_PAUSE_ADV BIT(0) #define ICE_AQ_LINK_LP_ASM_DIR_ADV BIT(1) + u8 reserved5[5]; #define ICE_AQC_LS_DATA_SIZE_V2 \ - offsetofend(struct ice_aqc_get_link_status_data, lp_flowcontrol) + offsetofend(struct ice_aqc_get_link_status_data, reserved5) } __packed; /* Set event mask command (direct 0x0613) */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 9a6c25f98632..edac34c796ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -5332,7 +5332,6 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, u8 *eec_mode) { struct ice_aqc_get_cgu_dpll_status *cmd; - const s64 nsec_per_psec = 1000LL; struct ice_aq_desc desc; int status; @@ -5348,8 +5347,7 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state, *phase_offset = le32_to_cpu(cmd->phase_offset_h); *phase_offset <<= 32; *phase_offset += le32_to_cpu(cmd->phase_offset_l); - *phase_offset = div64_s64(sign_extend64(*phase_offset, 47), - nsec_per_psec); + *phase_offset = sign_extend64(*phase_offset, 47); *eec_mode = cmd->eec_mode; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index fb9c93f37e84..adfdea1e2805 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2146,7 +2146,7 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Ensure we have media as we cannot configure a medialess port */ if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) - return -EPERM; + return -ENOMEDIUM; ice_print_topo_conflict(vsi); @@ -9187,8 +9187,14 @@ int ice_stop(struct net_device *netdev) int link_err = ice_force_phys_link_state(vsi, false); if (link_err) { - netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", - vsi->vsi_num, link_err); + if (link_err == -ENOMEDIUM) + netdev_info(vsi->netdev, "Skipping link reconfig - no media attached, VSI %d\n", + vsi->vsi_num); + else + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", + vsi->vsi_num, link_err); + + ice_vsi_close(vsi); return -EIO; } } diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index 81288a17da2a..20c4b3a64710 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -1044,7 +1044,6 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget) } idpf_rx_sync_for_cpu(rx_buf, fields.size); - skb = rx_q->skb; if (skb) idpf_rx_add_frag(rx_buf, skb, fields.size); else diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 1f728a9004d9..9e942e5baf39 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -396,7 +396,7 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model) if (!rxq) return; - if (!bufq && idpf_is_queue_model_split(q_model) && rxq->skb) { + if (rxq->skb) { dev_kfree_skb_any(rxq->skb); rxq->skb = NULL; } diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h index 07e72c72d156..8dc837889723 100644 --- a/drivers/net/ethernet/intel/idpf/virtchnl2.h +++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h @@ -1104,9 +1104,9 @@ struct virtchnl2_rss_key { __le32 vport_id; __le16 key_len; u8 pad; - __DECLARE_FLEX_ARRAY(u8, key_flex); -}; -VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_rss_key); + u8 key_flex[]; +} __packed; +VIRTCHNL2_CHECK_STRUCT_LEN(7, virtchnl2_rss_key); /** * struct virtchnl2_queue_chunk - chunk of contiguous queues diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index f48f82d5e274..85cc16396506 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -568,6 +568,7 @@ struct igc_nfc_filter { u16 etype; __be16 vlan_etype; u16 vlan_tci; + u16 vlan_tci_mask; u8 src_addr[ETH_ALEN]; u8 dst_addr[ETH_ALEN]; u8 user_data[8]; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 785eaa8e0ba8..859b2636f3d9 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -958,6 +958,7 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev, } #define ETHER_TYPE_FULL_MASK ((__force __be16)~0) +#define VLAN_TCI_FULL_MASK ((__force __be16)~0) static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, struct ethtool_rxnfc *cmd) { @@ -980,10 +981,16 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK; } + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) { + fsp->flow_type |= FLOW_EXT; + fsp->h_ext.vlan_etype = rule->filter.vlan_etype; + fsp->m_ext.vlan_etype = ETHER_TYPE_FULL_MASK; + } + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) { fsp->flow_type |= FLOW_EXT; fsp->h_ext.vlan_tci = htons(rule->filter.vlan_tci); - fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK); + fsp->m_ext.vlan_tci = htons(rule->filter.vlan_tci_mask); } if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) { @@ -1218,6 +1225,7 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) { rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci); + rule->filter.vlan_tci_mask = ntohs(fsp->m_ext.vlan_tci); rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI; } @@ -1255,11 +1263,19 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, memcpy(rule->filter.user_mask, fsp->m_ext.data, sizeof(fsp->m_ext.data)); } - /* When multiple filter options or user data or vlan etype is set, use a - * flex filter. + /* The i225/i226 has various different filters. Flex filters provide a + * way to match up to the first 128 bytes of a packet. Use them for: + * a) For specific user data + * b) For VLAN EtherType + * c) For full TCI match + * d) Or in case multiple filter criteria are set + * + * Otherwise, use the simple MAC, VLAN PRIO or EtherType filters. */ if ((rule->filter.match_flags & IGC_FILTER_FLAG_USER_DATA) || (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) || + ((rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) && + rule->filter.vlan_tci_mask == ntohs(VLAN_TCI_FULL_MASK)) || (rule->filter.match_flags & (rule->filter.match_flags - 1))) rule->flex = true; else @@ -1329,6 +1345,26 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter, return -EINVAL; } + /* There are two ways to match the VLAN TCI: + * 1. Match on PCP field and use vlan prio filter for it + * 2. Match on complete TCI field and use flex filter for it + */ + if ((fsp->flow_type & FLOW_EXT) && + fsp->m_ext.vlan_tci && + fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK) && + fsp->m_ext.vlan_tci != VLAN_TCI_FULL_MASK) { + netdev_dbg(netdev, "VLAN mask not supported\n"); + return -EOPNOTSUPP; + } + + /* VLAN EtherType can only be matched by full mask. */ + if ((fsp->flow_type & FLOW_EXT) && + fsp->m_ext.vlan_etype && + fsp->m_ext.vlan_etype != ETHER_TYPE_FULL_MASK) { + netdev_dbg(netdev, "VLAN EtherType mask not supported\n"); + return -EOPNOTSUPP; + } + if (fsp->location >= IGC_MAX_RXNFC_RULES) { netdev_dbg(netdev, "Invalid location\n"); return -EINVAL; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index a9c08321aca9..22cefb1eeedf 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -227,7 +227,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_TQAVCC(i), tqavcc); wr32(IGC_TQAVHC(i), - 0x80000000 + ring->hicredit * 0x7735); + 0x80000000 + ring->hicredit * 0x7736); } else { /* Disable any CBS for the queue */ txqctl &= ~(IGC_TXQCTL_QAV_SEL_MASK); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index ab3e39eef2eb..8c0732c9a7ee 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -528,7 +528,7 @@ struct npc_lt_def { u8 ltype_mask; u8 ltype_match; u8 lid; -}; +} __packed; struct npc_lt_def_ipsec { u8 ltype_mask; @@ -536,7 +536,7 @@ struct npc_lt_def_ipsec { u8 lid; u8 spi_offset; u8 spi_nz; -}; +} __packed; struct npc_lt_def_apad { u8 ltype_mask; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index cce2806aaa50..8802961b8889 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -905,6 +905,7 @@ u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id); int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable); +int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable); int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause, u16 pfc_en); int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 15a319684ed3..38acdc7a73bb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -465,6 +465,23 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) return mac_ops->mac_rx_tx_enable(cgxd, lmac_id, start); } +int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable) +{ + int pf = rvu_get_pf(pcifunc); + struct mac_ops *mac_ops; + u8 cgx_id, lmac_id; + void *cgxd; + + if (!is_cgx_config_permitted(rvu, pcifunc)) + return LMAC_AF_ERR_PERM_DENIED; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + + return mac_ops->mac_tx_enable(cgxd, lmac_id, enable); +} + int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable) { struct mac_ops *mac_ops; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 4227ebb4a758..58744313f0eb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4143,90 +4143,18 @@ static void nix_find_link_frs(struct rvu *rvu, req->minlen = minlen; } -static int -nix_config_link_credits(struct rvu *rvu, int blkaddr, int link, - u16 pcifunc, u64 tx_credits) -{ - struct rvu_hwinfo *hw = rvu->hw; - int pf = rvu_get_pf(pcifunc); - u8 cgx_id = 0, lmac_id = 0; - unsigned long poll_tmo; - bool restore_tx_en = 0; - struct nix_hw *nix_hw; - u64 cfg, sw_xoff = 0; - u32 schq = 0; - u32 credits; - int rc; - - nix_hw = get_nix_hw(rvu->hw, blkaddr); - if (!nix_hw) - return NIX_AF_ERR_INVALID_NIXBLK; - - if (tx_credits == nix_hw->tx_credits[link]) - return 0; - - /* Enable cgx tx if disabled for credits to be back */ - if (is_pf_cgxmapped(rvu, pf)) { - rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); - restore_tx_en = !rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), - lmac_id, true); - } - - mutex_lock(&rvu->rsrc_lock); - /* Disable new traffic to link */ - if (hw->cap.nix_shaping) { - schq = nix_get_tx_link(rvu, pcifunc); - sw_xoff = rvu_read64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq)); - rvu_write64(rvu, blkaddr, - NIX_AF_TL1X_SW_XOFF(schq), BIT_ULL(0)); - } - - rc = NIX_AF_ERR_LINK_CREDITS; - poll_tmo = jiffies + usecs_to_jiffies(200000); - /* Wait for credits to return */ - do { - if (time_after(jiffies, poll_tmo)) - goto exit; - usleep_range(100, 200); - - cfg = rvu_read64(rvu, blkaddr, - NIX_AF_TX_LINKX_NORM_CREDIT(link)); - credits = (cfg >> 12) & 0xFFFFFULL; - } while (credits != nix_hw->tx_credits[link]); - - cfg &= ~(0xFFFFFULL << 12); - cfg |= (tx_credits << 12); - rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg); - rc = 0; - - nix_hw->tx_credits[link] = tx_credits; - -exit: - /* Enable traffic back */ - if (hw->cap.nix_shaping && !sw_xoff) - rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq), 0); - - /* Restore state of cgx tx */ - if (restore_tx_en) - rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false); - - mutex_unlock(&rvu->rsrc_lock); - return rc; -} - int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, struct msg_rsp *rsp) { struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; int pf = rvu_get_pf(pcifunc); - int blkaddr, schq, link = -1; - struct nix_txsch *txsch; - u64 cfg, lmac_fifo_len; + int blkaddr, link = -1; struct nix_hw *nix_hw; struct rvu_pfvf *pfvf; u8 cgx = 0, lmac = 0; u16 max_mtu; + u64 cfg; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); if (blkaddr < 0) @@ -4247,25 +4175,6 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, if (req->update_minlen && req->minlen < NIC_HW_MIN_FRS) return NIX_AF_ERR_FRS_INVALID; - /* Check if requester wants to update SMQ's */ - if (!req->update_smq) - goto rx_frscfg; - - /* Update min/maxlen in each of the SMQ attached to this PF/VF */ - txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ]; - mutex_lock(&rvu->rsrc_lock); - for (schq = 0; schq < txsch->schq.max; schq++) { - if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc) - continue; - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq)); - cfg = (cfg & ~(0xFFFFULL << 8)) | ((u64)req->maxlen << 8); - if (req->update_minlen) - cfg = (cfg & ~0x7FULL) | ((u64)req->minlen & 0x7F); - rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg); - } - mutex_unlock(&rvu->rsrc_lock); - -rx_frscfg: /* Check if config is for SDP link */ if (req->sdp_link) { if (!hw->sdp_links) @@ -4288,7 +4197,6 @@ rx_frscfg: if (link < 0) return NIX_AF_ERR_RX_LINK_INVALID; - linkcfg: nix_find_link_frs(rvu, req, pcifunc); @@ -4298,19 +4206,7 @@ linkcfg: cfg = (cfg & ~0xFFFFULL) | req->minlen; rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link), cfg); - if (req->sdp_link || pf == 0) - return 0; - - /* Update transmit credits for CGX links */ - lmac_fifo_len = rvu_cgx_get_lmac_fifolen(rvu, cgx, lmac); - if (!lmac_fifo_len) { - dev_err(rvu->dev, - "%s: Failed to get CGX/RPM%d:LMAC%d FIFO size\n", - __func__, cgx, lmac); - return 0; - } - return nix_config_link_credits(rvu, blkaddr, link, pcifunc, - (lmac_fifo_len - req->maxlen) / 16); + return 0; } int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req, @@ -4841,7 +4737,13 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, pfvf = rvu_get_pfvf(rvu, pcifunc); clear_bit(NIXLF_INITIALIZED, &pfvf->flags); - return rvu_cgx_start_stop_io(rvu, pcifunc, false); + err = rvu_cgx_start_stop_io(rvu, pcifunc, false); + if (err) + return err; + + rvu_cgx_tx_enable(rvu, pcifunc, true); + + return 0; } #define RX_SA_BASE GENMASK_ULL(52, 7) 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 0d5a41a2ae01..227d01cace3f 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -267,6 +267,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) priv->stats.rx_truncate_errors++; } + /* Read receive consumer index before replenish so that this routine + * returns accurate return value even if packet is received into + * just-replenished buffer prior to exiting this routine. + */ + rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); + rx_ci_rem = rx_ci % priv->rx_q_entries; + /* Let hardware know we've replenished one buffer */ rx_pi++; @@ -279,8 +286,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) rx_pi_rem = rx_pi % priv->rx_q_entries; if (rx_pi_rem == 0) priv->valid_polarity ^= 1; - rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); - rx_ci_rem = rx_ci % priv->rx_q_entries; if (skb) netif_receive_skb(skb); diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 0d57ffcedf0c..fc78bc959ded 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2591,6 +2591,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) if (qdev->lrg_buf_q_alloc_virt_addr == NULL) { netdev_err(qdev->ndev, "lBufQ failed\n"); + kfree(qdev->lrg_buf); return -ENOMEM; } qdev->lrg_buf_q_virt_addr = qdev->lrg_buf_q_alloc_virt_addr; @@ -2615,6 +2616,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) qdev->lrg_buf_q_alloc_size, qdev->lrg_buf_q_alloc_virt_addr, qdev->lrg_buf_q_alloc_phy_addr); + kfree(qdev->lrg_buf); return -ENOMEM; } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bb787a52bc75..81fd31f6fac4 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1211,7 +1211,7 @@ static void rtl8168ep_driver_start(struct rtl8169_private *tp) { r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 10); + rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); } static void rtl8168_driver_start(struct rtl8169_private *tp) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 664eda4b5a11..8649b3e90edb 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -66,16 +66,27 @@ int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value) return -ETIMEDOUT; } -static int ravb_config(struct net_device *ndev) +static int ravb_set_opmode(struct net_device *ndev, u32 opmode) { + u32 csr_ops = 1U << (opmode & CCC_OPC); + u32 ccc_mask = CCC_OPC; int error; - /* Set config mode */ - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); - /* Check if the operating mode is changed to the config mode */ - error = ravb_wait(ndev, CSR, CSR_OPS, CSR_OPS_CONFIG); - if (error) - netdev_err(ndev, "failed to switch device to config mode\n"); + /* If gPTP active in config mode is supported it needs to be configured + * along with CSEL and operating mode in the same access. This is a + * hardware limitation. + */ + if (opmode & CCC_GAC) + ccc_mask |= CCC_GAC | CCC_CSEL; + + /* Set operating mode */ + ravb_modify(ndev, CCC, ccc_mask, opmode); + /* Check if the operating mode is changed to the requested one */ + error = ravb_wait(ndev, CSR, CSR_OPS, csr_ops); + if (error) { + netdev_err(ndev, "failed to switch device to requested mode (%u)\n", + opmode & CCC_OPC); + } return error; } @@ -673,7 +684,7 @@ static int ravb_dmac_init(struct net_device *ndev) int error; /* Set CONFIG mode */ - error = ravb_config(ndev); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); if (error) return error; @@ -682,9 +693,7 @@ static int ravb_dmac_init(struct net_device *ndev) return error; /* Setting the control will start the AVB-DMAC process. */ - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_OPERATION); - - return 0; + return ravb_set_opmode(ndev, CCC_OPC_OPERATION); } static void ravb_get_tx_tstamp(struct net_device *ndev) @@ -1046,7 +1055,7 @@ static int ravb_stop_dma(struct net_device *ndev) return error; /* Stop AVB-DMAC process */ - return ravb_config(ndev); + return ravb_set_opmode(ndev, CCC_OPC_CONFIG); } /* E-MAC interrupt handler */ @@ -2560,21 +2569,25 @@ static int ravb_set_gti(struct net_device *ndev) return 0; } -static void ravb_set_config_mode(struct net_device *ndev) +static int ravb_set_config_mode(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; + int error; if (info->gptp) { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); + if (error) + return error; /* Set CSEL value */ ravb_modify(ndev, CCC, CCC_CSEL, CCC_CSEL_HPB); } else if (info->ccc_gac) { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG | - CCC_GAC | CCC_CSEL_HPB); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB); } else { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); } + + return error; } /* Set tx and rx clock internal delay modes */ @@ -2794,7 +2807,9 @@ static int ravb_probe(struct platform_device *pdev) ndev->ethtool_ops = &ravb_ethtool_ops; /* Set AVB config mode */ - ravb_set_config_mode(ndev); + error = ravb_set_config_mode(ndev); + if (error) + goto out_disable_gptp_clk; if (info->gptp || info->ccc_gac) { /* Set GTI value */ @@ -2917,8 +2932,7 @@ static void ravb_remove(struct platform_device *pdev) dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); - /* Set reset mode */ - ravb_write(ndev, CCC_OPC_RESET, CCC); + ravb_set_opmode(ndev, CCC_OPC_RESET); clk_disable_unprepare(priv->gptp_clk); clk_disable_unprepare(priv->refclk); @@ -3000,8 +3014,11 @@ static int __maybe_unused ravb_resume(struct device *dev) int ret = 0; /* If WoL is enabled set reset mode to rearm the WoL logic */ - if (priv->wol_enabled) - ravb_write(ndev, CCC_OPC_RESET, CCC); + if (priv->wol_enabled) { + ret = ravb_set_opmode(ndev, CCC_OPC_RESET); + if (ret) + return ret; + } /* All register have been reset to default values. * Restore all registers which where setup at probe time and @@ -3009,7 +3026,9 @@ static int __maybe_unused ravb_resume(struct device *dev) */ /* Set AVB config mode */ - ravb_set_config_mode(ndev); + ret = ravb_set_config_mode(ndev); + if (ret) + return ret; if (info->gptp || info->ccc_gac) { /* Set GTI value */ diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index d2f35ee15eff..fac227d372db 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -823,8 +823,10 @@ int efx_probe_filters(struct efx_nic *efx) } if (!success) { - efx_for_each_channel(channel, efx) + efx_for_each_channel(channel, efx) { kfree(channel->rps_flow_id); + channel->rps_flow_id = NULL; + } efx->type->filter_table_remove(efx); rc = -ENOMEM; goto out_unlock; diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 3777c7e2e6fc..e47bb125048d 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -161,7 +161,9 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) u8 buf[ETH_ALEN]; struct ax88172a_private *priv; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + return ret; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d16f592c2061..51b1868d2f22 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -334,7 +334,6 @@ struct virtio_net_common_hdr { }; }; -static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf); static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf); static bool is_xdp_frame(void *ptr) @@ -408,6 +407,17 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask) return p; } +static void virtnet_rq_free_buf(struct virtnet_info *vi, + struct receive_queue *rq, void *buf) +{ + if (vi->mergeable_rx_bufs) + put_page(virt_to_head_page(buf)); + else if (vi->big_packets) + give_pages(rq, buf); + else + put_page(virt_to_head_page(buf)); +} + static void enable_delayed_refill(struct virtnet_info *vi) { spin_lock_bh(&vi->refill_lock); @@ -634,17 +644,6 @@ static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx) return buf; } -static void *virtnet_rq_detach_unused_buf(struct receive_queue *rq) -{ - void *buf; - - buf = virtqueue_detach_unused_buf(rq->vq); - if (buf && rq->do_dma) - virtnet_rq_unmap(rq, buf, 0); - - return buf; -} - static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len) { struct virtnet_rq_dma *dma; @@ -744,6 +743,20 @@ static void virtnet_rq_set_premapped(struct virtnet_info *vi) } } +static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) +{ + struct virtnet_info *vi = vq->vdev->priv; + struct receive_queue *rq; + int i = vq2rxq(vq); + + rq = &vi->rq[i]; + + if (rq->do_dma) + virtnet_rq_unmap(rq, buf, 0); + + virtnet_rq_free_buf(vi, rq, buf); +} + static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) { unsigned int len; @@ -1764,7 +1777,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); DEV_STATS_INC(dev, rx_length_errors); - virtnet_rq_free_unused_buf(rq->vq, buf); + virtnet_rq_free_buf(vi, rq, buf); return; } @@ -2392,7 +2405,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi, if (running) napi_disable(&rq->napi); - err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf); + err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf); if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); @@ -4031,19 +4044,6 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf) xdp_return_frame(ptr_to_xdp(buf)); } -static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf) -{ - struct virtnet_info *vi = vq->vdev->priv; - int i = vq2rxq(vq); - - if (vi->mergeable_rx_bufs) - put_page(virt_to_head_page(buf)); - else if (vi->big_packets) - give_pages(&vi->rq[i], buf); - else - put_page(virt_to_head_page(buf)); -} - static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -4057,10 +4057,10 @@ static void free_unused_bufs(struct virtnet_info *vi) } for (i = 0; i < vi->max_queue_pairs; i++) { - struct receive_queue *rq = &vi->rq[i]; + struct virtqueue *vq = vi->rq[i].vq; - while ((buf = virtnet_rq_detach_unused_buf(rq)) != NULL) - virtnet_rq_free_unused_buf(rq->vq, buf); + while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) + virtnet_rq_unmap_free_buf(vq, buf); cond_resched(); } } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index 56def20374f3..7805a42948af 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -770,7 +770,7 @@ static inline void iwl_enable_rfkill_int(struct iwl_trans *trans) } } -void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans); +void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq); static inline bool iwl_is_rfkill_set(struct iwl_trans *trans) { @@ -817,7 +817,7 @@ static inline bool iwl_pcie_dbg_on(struct iwl_trans *trans) return (trans->dbg.dest_tlv || iwl_trans_dbg_ini_valid(trans)); } -void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state); +void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq); void iwl_trans_pcie_dump_regs(struct iwl_trans *trans); #ifdef CONFIG_IWLWIFI_DEBUGFS diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index bc6a9f861711..07931c2db494 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1783,7 +1783,7 @@ static u32 iwl_pcie_int_cause_ict(struct iwl_trans *trans) return inta; } -void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans) +void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct isr_statistics *isr_stats = &trans_pcie->isr_stats; @@ -1807,7 +1807,7 @@ void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans) isr_stats->rfkill++; if (prev != report) - iwl_trans_pcie_rf_kill(trans, report); + iwl_trans_pcie_rf_kill(trans, report, from_irq); mutex_unlock(&trans_pcie->mutex); if (hw_rfkill) { @@ -1947,7 +1947,7 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id) /* HW RF KILL switch toggled */ if (inta & CSR_INT_BIT_RF_KILL) { - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, true); handled |= CSR_INT_BIT_RF_KILL; } @@ -2370,7 +2370,7 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id) /* HW RF KILL switch toggled */ if (inta_hw & MSIX_HW_INT_CAUSES_REG_RF_KILL) - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, true); if (inta_hw & MSIX_HW_INT_CAUSES_REG_HW_ERR) { IWL_ERR(trans, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 92253260f568..d10208075ae5 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1082,7 +1082,7 @@ bool iwl_pcie_check_hw_rf_kill(struct iwl_trans *trans) report = test_bit(STATUS_RFKILL_OPMODE, &trans->status); if (prev != report) - iwl_trans_pcie_rf_kill(trans, report); + iwl_trans_pcie_rf_kill(trans, report, false); return hw_rfkill; } @@ -1237,7 +1237,7 @@ static void iwl_pcie_init_msix(struct iwl_trans_pcie *trans_pcie) trans_pcie->hw_mask = trans_pcie->hw_init_mask; } -static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans) +static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool from_irq) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1264,7 +1264,8 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans) if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) { IWL_DEBUG_INFO(trans, "DEVICE_ENABLED bit was set and is now cleared\n"); - iwl_pcie_synchronize_irqs(trans); + if (!from_irq) + iwl_pcie_synchronize_irqs(trans); iwl_pcie_rx_napi_sync(trans); iwl_pcie_tx_stop(trans); iwl_pcie_rx_stop(trans); @@ -1454,7 +1455,7 @@ void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans, clear_bit(STATUS_RFKILL_OPMODE, &trans->status); } if (hw_rfkill != was_in_rfkill) - iwl_trans_pcie_rf_kill(trans, hw_rfkill); + iwl_trans_pcie_rf_kill(trans, hw_rfkill, false); } static void iwl_trans_pcie_stop_device(struct iwl_trans *trans) @@ -1469,12 +1470,12 @@ static void iwl_trans_pcie_stop_device(struct iwl_trans *trans) mutex_lock(&trans_pcie->mutex); trans_pcie->opmode_down = true; was_in_rfkill = test_bit(STATUS_RFKILL_OPMODE, &trans->status); - _iwl_trans_pcie_stop_device(trans); + _iwl_trans_pcie_stop_device(trans, false); iwl_trans_pcie_handle_stop_rfkill(trans, was_in_rfkill); mutex_unlock(&trans_pcie->mutex); } -void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state) +void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq) { struct iwl_trans_pcie __maybe_unused *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1487,7 +1488,7 @@ void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state) if (trans->trans_cfg->gen2) _iwl_trans_pcie_gen2_stop_device(trans); else - _iwl_trans_pcie_stop_device(trans); + _iwl_trans_pcie_stop_device(trans, from_irq); } } @@ -2887,7 +2888,7 @@ static ssize_t iwl_dbgfs_rfkill_write(struct file *file, IWL_WARN(trans, "changing debug rfkill %d->%d\n", trans_pcie->debug_rfkill, new_value); trans_pcie->debug_rfkill = new_value; - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, false); return count; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 55bc3576a985..bdbf8a94b4d0 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1335,6 +1335,9 @@ static int pci_set_full_power_state(struct pci_dev *dev) pci_restore_bars(dev); } + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + return 0; } @@ -1429,6 +1432,9 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) pci_power_name(dev->current_state), pci_power_name(state)); + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + return 0; } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 5ecbcf041179..f43873049d52 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -569,10 +569,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); +void pcie_aspm_pm_state_change(struct pci_dev *pdev); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } +static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } #endif diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 5dab531c8654..060f4b3c8698 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1008,6 +1008,25 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) up_read(&pci_bus_sem); } +/* @pdev: the root port or switch downstream port */ +void pcie_aspm_pm_state_change(struct pci_dev *pdev) +{ + struct pcie_link_state *link = pdev->link_state; + + if (aspm_disabled || !link) + return; + /* + * Devices changed PM state, we should recheck if latency + * meets all functions' requirement + */ + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + pcie_update_aspm_capable(link->root); + pcie_config_aspm_path(link); + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); +} + void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { struct pcie_link_state *link = pdev->link_state; diff --git a/drivers/platform/x86/intel/pmc/adl.c b/drivers/platform/x86/intel/pmc/adl.c index 5006008e01be..606f7678bcb0 100644 --- a/drivers/platform/x86/intel/pmc/adl.c +++ b/drivers/platform/x86/intel/pmc/adl.c @@ -314,16 +314,13 @@ int adl_core_init(struct pmc_dev *pmcdev) struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; int ret; + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + pmc->map = &adl_reg_map; ret = get_primary_reg_base(pmc); if (ret) return ret; - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/cnp.c b/drivers/platform/x86/intel/pmc/cnp.c index 420aaa1d7c76..98b36651201a 100644 --- a/drivers/platform/x86/intel/pmc/cnp.c +++ b/drivers/platform/x86/intel/pmc/cnp.c @@ -204,21 +204,35 @@ const struct pmc_reg_map cnp_reg_map = { .etr3_offset = ETR3_OFFSET, }; +void cnl_suspend(struct pmc_dev *pmcdev) +{ + /* + * Due to a hardware limitation, the GBE LTR blocks PC10 + * when a cable is attached. To unblock PC10 during suspend, + * tell the PMC to ignore it. + */ + pmc_core_send_ltr_ignore(pmcdev, 3, 1); +} + +int cnl_resume(struct pmc_dev *pmcdev) +{ + pmc_core_send_ltr_ignore(pmcdev, 3, 0); + + return pmc_core_resume_common(pmcdev); +} + int cnp_core_init(struct pmc_dev *pmcdev) { struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; int ret; + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + pmc->map = &cnp_reg_map; ret = get_primary_reg_base(pmc); if (ret) return ret; - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index e95d3011b999..022afb97d531 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -460,7 +460,7 @@ out_unlock: } DEFINE_SHOW_ATTRIBUTE(pmc_core_pll); -int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value) +int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value, int ignore) { struct pmc *pmc; const struct pmc_reg_map *map; @@ -498,7 +498,10 @@ int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value) mutex_lock(&pmcdev->lock); reg = pmc_core_reg_read(pmc, map->ltr_ignore_offset); - reg |= BIT(ltr_index); + if (ignore) + reg |= BIT(ltr_index); + else + reg &= ~BIT(ltr_index); pmc_core_reg_write(pmc, map->ltr_ignore_offset, reg); mutex_unlock(&pmcdev->lock); @@ -521,7 +524,7 @@ static ssize_t pmc_core_ltr_ignore_write(struct file *file, if (err) return err; - err = pmc_core_send_ltr_ignore(pmcdev, value); + err = pmc_core_send_ltr_ignore(pmcdev, value, 1); return err == 0 ? count : err; } @@ -1279,6 +1282,9 @@ static __maybe_unused int pmc_core_suspend(struct device *dev) struct pmc_dev *pmcdev = dev_get_drvdata(dev); struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; + if (pmcdev->suspend) + pmcdev->suspend(pmcdev); + /* Check if the syspend will actually use S0ix */ if (pm_suspend_via_firmware()) return 0; diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index 0729f593c6a7..b66dacbfb94b 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -363,6 +363,7 @@ struct pmc { * @s0ix_counter: S0ix residency (step adjusted) * @num_lpm_modes: Count of enabled modes * @lpm_en_modes: Array of enabled modes from lowest to highest priority + * @suspend: Function to perform platform specific suspend * @resume: Function to perform platform specific resume * * pmc_dev contains info about power management controller device. @@ -379,6 +380,7 @@ struct pmc_dev { u64 s0ix_counter; int num_lpm_modes; int lpm_en_modes[LPM_MAX_NUM_MODES]; + void (*suspend)(struct pmc_dev *pmcdev); int (*resume)(struct pmc_dev *pmcdev); bool has_die_c6; @@ -486,7 +488,7 @@ extern const struct pmc_bit_map *mtl_ioem_lpm_maps[]; extern const struct pmc_reg_map mtl_ioem_reg_map; extern void pmc_core_get_tgl_lpm_reqs(struct platform_device *pdev); -extern int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value); +int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value, int ignore); int pmc_core_resume_common(struct pmc_dev *pmcdev); int get_primary_reg_base(struct pmc *pmc); @@ -500,6 +502,9 @@ int tgl_core_init(struct pmc_dev *pmcdev); int adl_core_init(struct pmc_dev *pmcdev); int mtl_core_init(struct pmc_dev *pmcdev); +void cnl_suspend(struct pmc_dev *pmcdev); +int cnl_resume(struct pmc_dev *pmcdev); + #define pmc_for_each_mode(i, mode, pmcdev) \ for (i = 0, mode = pmcdev->lpm_en_modes[i]; \ i < pmcdev->num_lpm_modes; \ diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c index 2204bc666980..504e3e273c32 100644 --- a/drivers/platform/x86/intel/pmc/mtl.c +++ b/drivers/platform/x86/intel/pmc/mtl.c @@ -979,6 +979,8 @@ static void mtl_d3_fixup(void) static int mtl_resume(struct pmc_dev *pmcdev) { mtl_d3_fixup(); + pmc_core_send_ltr_ignore(pmcdev, 3, 0); + return pmc_core_resume_common(pmcdev); } @@ -989,6 +991,7 @@ int mtl_core_init(struct pmc_dev *pmcdev) mtl_d3_fixup(); + pmcdev->suspend = cnl_suspend; pmcdev->resume = mtl_resume; pmcdev->regmap_list = mtl_pmc_info_list; @@ -1002,11 +1005,5 @@ int mtl_core_init(struct pmc_dev *pmcdev) return ret; } - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/tgl.c b/drivers/platform/x86/intel/pmc/tgl.c index 2449940102db..e88d3d00c853 100644 --- a/drivers/platform/x86/intel/pmc/tgl.c +++ b/drivers/platform/x86/intel/pmc/tgl.c @@ -259,16 +259,15 @@ int tgl_core_init(struct pmc_dev *pmcdev) int ret; pmc->map = &tgl_reg_map; + + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + ret = get_primary_reg_base(pmc); if (ret) return ret; pmc_core_get_tgl_lpm_reqs(pmcdev->pdev); - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); return 0; } diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 4021d3d325f9..e7defce8cf48 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -4492,7 +4492,7 @@ ptp_ocp_remove(struct pci_dev *pdev) cancel_delayed_work_sync(&bp->sync_work); for (i = 0; i < OCP_SMA_NUM; i++) { if (bp->sma[i].dpll_pin) { - dpll_pin_unregister(bp->dpll, bp->sma[i].dpll_pin, &dpll_pins_ops, bp); + dpll_pin_unregister(bp->dpll, bp->sma[i].dpll_pin, &dpll_pins_ops, &bp->sma[i]); dpll_pin_put(bp->sma[i].dpll_pin); } } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 51d8f3299c10..49299b1f9ec7 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -3219,8 +3219,7 @@ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, if (!vq->use_dma_api) return; - dma_sync_single_range_for_cpu(dev, addr, offset, size, - DMA_BIDIRECTIONAL); + dma_sync_single_range_for_cpu(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_cpu); @@ -3246,8 +3245,7 @@ void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, if (!vq->use_dma_api) return; - dma_sync_single_range_for_device(dev, addr, offset, size, - DMA_BIDIRECTIONAL); + dma_sync_single_range_for_device(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_device); diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile index 45b64f89258c..b81268418174 100644 --- a/fs/bcachefs/Makefile +++ b/fs/bcachefs/Makefile @@ -28,6 +28,7 @@ bcachefs-y := \ clock.o \ compress.o \ counters.o \ + darray.o \ debug.o \ dirent.o \ disk_groups.o \ @@ -70,6 +71,7 @@ bcachefs-y := \ reflink.o \ replicas.o \ sb-clean.o \ + sb-downgrade.o \ sb-errors.o \ sb-members.o \ siphash.o \ diff --git a/fs/bcachefs/acl.c b/fs/bcachefs/acl.c index f3809897f00a..3640f417cce1 100644 --- a/fs/bcachefs/acl.c +++ b/fs/bcachefs/acl.c @@ -366,7 +366,8 @@ retry: bch2_trans_begin(trans); acl = _acl; - ret = bch2_inode_peek(trans, &inode_iter, &inode_u, inode_inum(inode), + ret = bch2_subvol_is_ro_trans(trans, inode->ei_subvol) ?: + bch2_inode_peek(trans, &inode_iter, &inode_u, inode_inum(inode), BTREE_ITER_INTENT); if (ret) goto btree_err; diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index dfa22f9d9a1d..b62737fdf5ab 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -737,6 +737,7 @@ struct bch_fs { unsigned nsec_per_time_unit; u64 features; u64 compat; + unsigned long errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)]; } sb; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 1ab1f08d763b..fe78e87603fc 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -1207,19 +1207,21 @@ struct bch_sb_field { }; #define BCH_SB_FIELDS() \ - x(journal, 0) \ - x(members_v1, 1) \ - x(crypt, 2) \ - x(replicas_v0, 3) \ - x(quota, 4) \ - x(disk_groups, 5) \ - x(clean, 6) \ - x(replicas, 7) \ - x(journal_seq_blacklist, 8) \ - x(journal_v2, 9) \ - x(counters, 10) \ - x(members_v2, 11) \ - x(errors, 12) + x(journal, 0) \ + x(members_v1, 1) \ + x(crypt, 2) \ + x(replicas_v0, 3) \ + x(quota, 4) \ + x(disk_groups, 5) \ + x(clean, 6) \ + x(replicas, 7) \ + x(journal_seq_blacklist, 8) \ + x(journal_v2, 9) \ + x(counters, 10) \ + x(members_v2, 11) \ + x(errors, 12) \ + x(ext, 13) \ + x(downgrade, 14) enum bch_sb_field_type { #define x(f, nr) BCH_SB_FIELD_##f = nr, @@ -1631,6 +1633,24 @@ struct bch_sb_field_errors { LE64_BITMASK(BCH_SB_ERROR_ENTRY_ID, struct bch_sb_field_error_entry, v, 0, 16); LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR, struct bch_sb_field_error_entry, v, 16, 64); +struct bch_sb_field_ext { + struct bch_sb_field field; + __le64 recovery_passes_required[2]; + __le64 errors_silent[8]; +}; + +struct bch_sb_field_downgrade_entry { + __le16 version; + __le64 recovery_passes[2]; + __le16 nr_errors; + __le16 errors[] __counted_by(nr_errors); +} __packed __aligned(2); + +struct bch_sb_field_downgrade { + struct bch_sb_field field; + struct bch_sb_field_downgrade_entry entries[]; +}; + /* Superblock: */ /* @@ -1644,6 +1664,11 @@ LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR, struct bch_sb_field_error_entry, v, 16, 64); #define RECOVERY_PASS_ALL_FSCK (1ULL << 63) +/* + * field 1: version name + * field 2: BCH_VERSION(major, minor) + * field 3: recovery passess required on upgrade + */ #define BCH_METADATA_VERSIONS() \ x(bkey_renumber, BCH_VERSION(0, 10), \ RECOVERY_PASS_ALL_FSCK) \ diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index 6be79129738d..da594e006769 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -2085,18 +2085,16 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e goto out_no_locked; /* - * iter->pos should be mononotically increasing, and always be - * equal to the key we just returned - except extents can - * straddle iter->pos: + * We need to check against @end before FILTER_SNAPSHOTS because + * if we get to a different inode that requested we might be + * seeing keys for a different snapshot tree that will all be + * filtered out. + * + * But we can't do the full check here, because bkey_start_pos() + * isn't monotonically increasing before FILTER_SNAPSHOTS, and + * that's what we check against in extents mode: */ - if (!(iter->flags & BTREE_ITER_IS_EXTENTS)) - iter_pos = k.k->p; - else - iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k)); - - if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS) - ? bkey_gt(iter_pos, end) - : bkey_ge(iter_pos, end))) + if (k.k->p.inode > end.inode) goto end; if (iter->update_path && @@ -2155,6 +2153,21 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e continue; } + /* + * iter->pos should be mononotically increasing, and always be + * equal to the key we just returned - except extents can + * straddle iter->pos: + */ + if (!(iter->flags & BTREE_ITER_IS_EXTENTS)) + iter_pos = k.k->p; + else + iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k)); + + if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS) + ? bkey_gt(iter_pos, end) + : bkey_ge(iter_pos, end))) + goto end; + break; } diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c index 25fdca00bf7b..2fd3c8cc6f51 100644 --- a/fs/bcachefs/btree_update.c +++ b/fs/bcachefs/btree_update.c @@ -186,8 +186,11 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans, enum btree_id btree_id = iter->btree_id; struct bkey_i *update; struct bpos new_start = bkey_start_pos(new.k); - bool front_split = bkey_lt(bkey_start_pos(old.k), new_start); - bool back_split = bkey_gt(old.k->p, new.k->p); + unsigned front_split = bkey_lt(bkey_start_pos(old.k), new_start); + unsigned back_split = bkey_gt(old.k->p, new.k->p); + unsigned middle_split = (front_split || back_split) && + old.k->p.snapshot != new.k->p.snapshot; + unsigned nr_splits = front_split + back_split + middle_split; int ret = 0, compressed_sectors; /* @@ -195,10 +198,9 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans, * so that __bch2_trans_commit() can increase our disk * reservation: */ - if (((front_split && back_split) || - ((front_split || back_split) && old.k->p.snapshot != new.k->p.snapshot)) && + if (nr_splits > 1 && (compressed_sectors = bch2_bkey_sectors_compressed(old))) - trans->extra_journal_res += compressed_sectors; + trans->extra_journal_res += compressed_sectors * (nr_splits - 1); if (front_split) { update = bch2_bkey_make_mut_noupdate(trans, old); @@ -216,8 +218,7 @@ int bch2_trans_update_extent_overwrite(struct btree_trans *trans, } /* If we're overwriting in a different snapshot - middle split: */ - if (old.k->p.snapshot != new.k->p.snapshot && - (front_split || back_split)) { + if (middle_split) { update = bch2_bkey_make_mut_noupdate(trans, old); if ((ret = PTR_ERR_OR_ZERO(update))) return ret; diff --git a/fs/bcachefs/darray.c b/fs/bcachefs/darray.c new file mode 100644 index 000000000000..ac35b8b705ae --- /dev/null +++ b/fs/bcachefs/darray.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/log2.h> +#include <linux/slab.h> +#include "darray.h" + +int __bch2_darray_resize(darray_char *d, size_t element_size, size_t new_size, gfp_t gfp) +{ + if (new_size > d->size) { + new_size = roundup_pow_of_two(new_size); + + void *data = kvmalloc_array(new_size, element_size, gfp); + if (!data) + return -ENOMEM; + + memcpy(data, d->data, d->size * element_size); + if (d->data != d->preallocated) + kvfree(d->data); + d->data = data; + d->size = new_size; + } + + return 0; +} diff --git a/fs/bcachefs/darray.h b/fs/bcachefs/darray.h index 87b4b2d1ec76..e367c625f057 100644 --- a/fs/bcachefs/darray.h +++ b/fs/bcachefs/darray.h @@ -8,39 +8,48 @@ * Inspired by CCAN's darray */ -#include "util.h" #include <linux/slab.h> -#define DARRAY(type) \ +#define DARRAY_PREALLOCATED(_type, _nr) \ struct { \ size_t nr, size; \ - type *data; \ + _type *data; \ + _type preallocated[_nr]; \ } -typedef DARRAY(void) darray_void; +#define DARRAY(_type) DARRAY_PREALLOCATED(_type, 0) -static inline int __darray_make_room(darray_void *d, size_t t_size, size_t more, gfp_t gfp) +typedef DARRAY(char) darray_char; + +int __bch2_darray_resize(darray_char *, size_t, size_t, gfp_t); + +static inline int __darray_resize(darray_char *d, size_t element_size, + size_t new_size, gfp_t gfp) { - if (d->nr + more > d->size) { - size_t new_size = roundup_pow_of_two(d->nr + more); - void *data = krealloc_array(d->data, new_size, t_size, gfp); + return unlikely(new_size > d->size) + ? __bch2_darray_resize(d, element_size, new_size, gfp) + : 0; +} - if (!data) - return -ENOMEM; +#define darray_resize_gfp(_d, _new_size, _gfp) \ + unlikely(__darray_resize((darray_char *) (_d), sizeof((_d)->data[0]), (_new_size), _gfp)) - d->data = data; - d->size = new_size; - } +#define darray_resize(_d, _new_size) \ + darray_resize_gfp(_d, _new_size, GFP_KERNEL) - return 0; +static inline int __darray_make_room(darray_char *d, size_t t_size, size_t more, gfp_t gfp) +{ + return __darray_resize(d, t_size, d->nr + more, gfp); } #define darray_make_room_gfp(_d, _more, _gfp) \ - __darray_make_room((darray_void *) (_d), sizeof((_d)->data[0]), (_more), _gfp) + __darray_make_room((darray_char *) (_d), sizeof((_d)->data[0]), (_more), _gfp) #define darray_make_room(_d, _more) \ darray_make_room_gfp(_d, _more, GFP_KERNEL) +#define darray_room(_d) ((_d).size - (_d).nr) + #define darray_top(_d) ((_d).data[(_d).nr]) #define darray_push_gfp(_d, _item, _gfp) \ @@ -80,13 +89,16 @@ static inline int __darray_make_room(darray_void *d, size_t t_size, size_t more, #define darray_init(_d) \ do { \ - (_d)->data = NULL; \ - (_d)->nr = (_d)->size = 0; \ + (_d)->nr = 0; \ + (_d)->size = ARRAY_SIZE((_d)->preallocated); \ + (_d)->data = (_d)->size ? (_d)->preallocated : NULL; \ } while (0) #define darray_exit(_d) \ do { \ - kfree((_d)->data); \ + if (!ARRAY_SIZE((_d)->preallocated) || \ + (_d)->data != (_d)->preallocated) \ + kvfree((_d)->data); \ darray_init(_d); \ } while (0) diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index b05457d284a6..37d6ecae8c30 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -587,7 +587,8 @@ int bch2_data_update_init(struct btree_trans *trans, * Increasing replication is an explicit operation triggered by * rereplicate, currently, so that users don't get an unexpected -ENOSPC */ - if (durability_have >= io_opts.data_replicas) { + if (!(m->data_opts.write_flags & BCH_WRITE_CACHED) && + durability_have >= io_opts.data_replicas) { m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs; m->data_opts.rewrite_ptrs = 0; /* if iter == NULL, it's just a promote */ diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index ae7910bf2228..9ce29681eec9 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -95,6 +95,7 @@ x(ENOSPC, ENOSPC_sb_members) \ x(ENOSPC, ENOSPC_sb_members_v2) \ x(ENOSPC, ENOSPC_sb_crypt) \ + x(ENOSPC, ENOSPC_sb_downgrade) \ x(ENOSPC, ENOSPC_btree_slot) \ x(ENOSPC, ENOSPC_snapshot_tree) \ x(ENOENT, ENOENT_bkey_type_mismatch) \ @@ -218,6 +219,8 @@ x(BCH_ERR_invalid_sb, invalid_sb_quota) \ x(BCH_ERR_invalid_sb, invalid_sb_errors) \ x(BCH_ERR_invalid_sb, invalid_sb_opt_compression) \ + x(BCH_ERR_invalid_sb, invalid_sb_ext) \ + x(BCH_ERR_invalid_sb, invalid_sb_downgrade) \ x(BCH_ERR_invalid, invalid_bkey) \ x(BCH_ERR_operation_blocked, nocow_lock_blocked) \ x(EIO, btree_node_read_err) \ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index 7b28d37922fd..25cf78a7b946 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -152,6 +152,9 @@ int bch2_fsck_err(struct bch_fs *c, struct printbuf buf = PRINTBUF, *out = &buf; int ret = -BCH_ERR_fsck_ignore; + if (test_bit(err, c->sb.errors_silent)) + return -BCH_ERR_fsck_fix; + bch2_sb_error_count(c, err); va_start(args, fmt); diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index d167d65986e0..fec17d1353d1 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -157,6 +157,7 @@ void bch2_flush_fsck_errs(struct bch_fs *); #define fsck_err_on(cond, c, _err_type, ...) \ __fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__) +__printf(4, 0) static inline void bch2_bkey_fsck_err(struct bch_fs *c, struct printbuf *err_msg, enum bch_sb_error_id err_type, @@ -167,7 +168,6 @@ static inline void bch2_bkey_fsck_err(struct bch_fs *c, va_start(args, fmt); prt_vprintf(err_msg, fmt, args); va_end(args); - } #define bkey_fsck_err(c, _err_msg, _err_type, ...) \ diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c index 9a479e4de6b3..84e20c3ada6c 100644 --- a/fs/bcachefs/fs-io-direct.c +++ b/fs/bcachefs/fs-io-direct.c @@ -216,11 +216,11 @@ struct dio_write { struct address_space *mapping; struct bch_inode_info *inode; struct mm_struct *mm; + const struct iovec *iov; unsigned loop:1, extending:1, sync:1, - flush:1, - free_iov:1; + flush:1; struct quota_res quota_res; u64 written; @@ -312,12 +312,10 @@ static noinline int bch2_dio_write_copy_iov(struct dio_write *dio) return -1; if (dio->iter.nr_segs > ARRAY_SIZE(dio->inline_vecs)) { - iov = kmalloc_array(dio->iter.nr_segs, sizeof(*iov), + dio->iov = iov = kmalloc_array(dio->iter.nr_segs, sizeof(*iov), GFP_KERNEL); if (unlikely(!iov)) return -ENOMEM; - - dio->free_iov = true; } memcpy(iov, dio->iter.__iov, dio->iter.nr_segs * sizeof(*iov)); @@ -381,8 +379,7 @@ static __always_inline long bch2_dio_write_done(struct dio_write *dio) bch2_pagecache_block_put(inode); - if (dio->free_iov) - kfree(dio->iter.__iov); + kfree(dio->iov); ret = dio->op.error ?: ((long) dio->written << 9); bio_put(&dio->op.wbio.bio); @@ -626,11 +623,11 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter) dio->mapping = mapping; dio->inode = inode; dio->mm = current->mm; + dio->iov = NULL; dio->loop = false; dio->extending = extending; dio->sync = is_sync_kiocb(req) || extending; dio->flush = iocb_is_dsync(req) && !c->opts.journal_flush_disabled; - dio->free_iov = false; dio->quota_res.sectors = 0; dio->written = 0; dio->iter = *iter; diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index a70b7a03057d..14d5cc6f90d7 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -100,7 +100,8 @@ static int bch2_ioc_setflags(struct bch_fs *c, } mutex_lock(&inode->ei_update_lock); - ret = bch2_write_inode(c, inode, bch2_inode_flags_set, &s, + ret = bch2_subvol_is_ro(c, inode->ei_subvol) ?: + bch2_write_inode(c, inode, bch2_inode_flags_set, &s, ATTR_CTIME); mutex_unlock(&inode->ei_update_lock); @@ -183,13 +184,10 @@ static int bch2_ioc_fssetxattr(struct bch_fs *c, } mutex_lock(&inode->ei_update_lock); - ret = bch2_set_projid(c, inode, fa.fsx_projid); - if (ret) - goto err_unlock; - - ret = bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s, + ret = bch2_subvol_is_ro(c, inode->ei_subvol) ?: + bch2_set_projid(c, inode, fa.fsx_projid) ?: + bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s, ATTR_CTIME); -err_unlock: mutex_unlock(&inode->ei_update_lock); err: inode_unlock(&inode->v); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index ba93e32d7708..49da8db1d9e9 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -258,7 +258,8 @@ __bch2_create(struct mnt_idmap *idmap, retry: bch2_trans_begin(trans); - ret = bch2_create_trans(trans, + ret = bch2_subvol_is_ro_trans(trans, dir->ei_subvol) ?: + bch2_create_trans(trans, inode_inum(dir), &dir_u, &inode_u, !(flags & BCH_CREATE_TMPFILE) ? &dentry->d_name : NULL, @@ -430,7 +431,9 @@ static int bch2_link(struct dentry *old_dentry, struct inode *vdir, lockdep_assert_held(&inode->v.i_rwsem); - ret = __bch2_link(c, inode, dir, dentry); + ret = bch2_subvol_is_ro(c, dir->ei_subvol) ?: + bch2_subvol_is_ro(c, inode->ei_subvol) ?: + __bch2_link(c, inode, dir, dentry); if (unlikely(ret)) return ret; @@ -481,7 +484,11 @@ err: static int bch2_unlink(struct inode *vdir, struct dentry *dentry) { - return __bch2_unlink(vdir, dentry, false); + struct bch_inode_info *dir= to_bch_ei(vdir); + struct bch_fs *c = dir->v.i_sb->s_fs_info; + + return bch2_subvol_is_ro(c, dir->ei_subvol) ?: + __bch2_unlink(vdir, dentry, false); } static int bch2_symlink(struct mnt_idmap *idmap, @@ -562,6 +569,11 @@ static int bch2_rename2(struct mnt_idmap *idmap, src_inode, dst_inode); + ret = bch2_subvol_is_ro_trans(trans, src_dir->ei_subvol) ?: + bch2_subvol_is_ro_trans(trans, dst_dir->ei_subvol); + if (ret) + goto err; + if (inode_attr_changing(dst_dir, src_inode, Inode_opt_project)) { ret = bch2_fs_quota_transfer(c, src_inode, dst_dir->ei_qid, @@ -783,11 +795,13 @@ static int bch2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct bch_inode_info *inode = to_bch_ei(dentry->d_inode); + struct bch_fs *c = inode->v.i_sb->s_fs_info; int ret; lockdep_assert_held(&inode->v.i_rwsem); - ret = setattr_prepare(idmap, dentry, iattr); + ret = bch2_subvol_is_ro(c, inode->ei_subvol) ?: + setattr_prepare(idmap, dentry, iattr); if (ret) return ret; @@ -1010,12 +1024,26 @@ static int bch2_vfs_readdir(struct file *file, struct dir_context *ctx) return bch2_err_class(ret); } +static int bch2_open(struct inode *vinode, struct file *file) +{ + if (file->f_flags & (O_WRONLY|O_RDWR)) { + struct bch_inode_info *inode = to_bch_ei(vinode); + struct bch_fs *c = inode->v.i_sb->s_fs_info; + + int ret = bch2_subvol_is_ro(c, inode->ei_subvol); + if (ret) + return ret; + } + + return generic_file_open(vinode, file); +} + static const struct file_operations bch_file_operations = { + .open = bch2_open, .llseek = bch2_llseek, .read_iter = bch2_read_iter, .write_iter = bch2_write_iter, .mmap = bch2_mmap, - .open = generic_file_open, .fsync = bch2_fsync, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index 8ede46b1e354..8c8cb1541ac9 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -1216,6 +1216,12 @@ static CLOSURE_CALLBACK(bch2_nocow_write_done) bch2_write_done(cl); } +struct bucket_to_lock { + struct bpos b; + unsigned gen; + struct nocow_lock_bucket *l; +}; + static void bch2_nocow_write(struct bch_write_op *op) { struct bch_fs *c = op->c; @@ -1224,18 +1230,16 @@ static void bch2_nocow_write(struct bch_write_op *op) struct bkey_s_c k; struct bkey_ptrs_c ptrs; const struct bch_extent_ptr *ptr; - struct { - struct bpos b; - unsigned gen; - struct nocow_lock_bucket *l; - } buckets[BCH_REPLICAS_MAX]; - unsigned nr_buckets = 0; + DARRAY_PREALLOCATED(struct bucket_to_lock, 3) buckets; + struct bucket_to_lock *i; u32 snapshot; - int ret, i; + struct bucket_to_lock *stale_at; + int ret; if (op->flags & BCH_WRITE_MOVE) return; + darray_init(&buckets); trans = bch2_trans_get(c); retry: bch2_trans_begin(trans); @@ -1250,7 +1254,7 @@ retry: while (1) { struct bio *bio = &op->wbio.bio; - nr_buckets = 0; + buckets.nr = 0; k = bch2_btree_iter_peek_slot(&iter); ret = bkey_err(k); @@ -1263,26 +1267,26 @@ retry: break; if (bch2_keylist_realloc(&op->insert_keys, - op->inline_keys, - ARRAY_SIZE(op->inline_keys), - k.k->u64s)) + op->inline_keys, + ARRAY_SIZE(op->inline_keys), + k.k->u64s)) break; /* Get iorefs before dropping btree locks: */ ptrs = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(ptrs, ptr) { - buckets[nr_buckets].b = PTR_BUCKET_POS(c, ptr); - buckets[nr_buckets].gen = ptr->gen; - buckets[nr_buckets].l = - bucket_nocow_lock(&c->nocow_locks, - bucket_to_u64(buckets[nr_buckets].b)); - - prefetch(buckets[nr_buckets].l); + struct bpos b = PTR_BUCKET_POS(c, ptr); + struct nocow_lock_bucket *l = + bucket_nocow_lock(&c->nocow_locks, bucket_to_u64(b)); + prefetch(l); if (unlikely(!bch2_dev_get_ioref(bch_dev_bkey_exists(c, ptr->dev), WRITE))) goto err_get_ioref; - nr_buckets++; + /* XXX allocating memory with btree locks held - rare */ + darray_push_gfp(&buckets, ((struct bucket_to_lock) { + .b = b, .gen = ptr->gen, .l = l, + }), GFP_KERNEL|__GFP_NOFAIL); if (ptr->unwritten) op->flags |= BCH_WRITE_CONVERT_UNWRITTEN; @@ -1296,21 +1300,21 @@ retry: if (op->flags & BCH_WRITE_CONVERT_UNWRITTEN) bch2_cut_back(POS(op->pos.inode, op->pos.offset + bio_sectors(bio)), op->insert_keys.top); - for (i = 0; i < nr_buckets; i++) { - struct bch_dev *ca = bch_dev_bkey_exists(c, buckets[i].b.inode); - struct nocow_lock_bucket *l = buckets[i].l; - bool stale; + darray_for_each(buckets, i) { + struct bch_dev *ca = bch_dev_bkey_exists(c, i->b.inode); - __bch2_bucket_nocow_lock(&c->nocow_locks, l, - bucket_to_u64(buckets[i].b), + __bch2_bucket_nocow_lock(&c->nocow_locks, i->l, + bucket_to_u64(i->b), BUCKET_NOCOW_LOCK_UPDATE); rcu_read_lock(); - stale = gen_after(*bucket_gen(ca, buckets[i].b.offset), buckets[i].gen); + bool stale = gen_after(*bucket_gen(ca, i->b.offset), i->gen); rcu_read_unlock(); - if (unlikely(stale)) + if (unlikely(stale)) { + stale_at = i; goto err_bucket_stale; + } } bio = &op->wbio.bio; @@ -1346,15 +1350,14 @@ err: if (ret) { bch_err_inum_offset_ratelimited(c, - op->pos.inode, - op->pos.offset << 9, - "%s: btree lookup error %s", - __func__, bch2_err_str(ret)); + op->pos.inode, op->pos.offset << 9, + "%s: btree lookup error %s", __func__, bch2_err_str(ret)); op->error = ret; op->flags |= BCH_WRITE_DONE; } bch2_trans_put(trans); + darray_exit(&buckets); /* fallback to cow write path? */ if (!(op->flags & BCH_WRITE_DONE)) { @@ -1374,24 +1377,21 @@ err: } return; err_get_ioref: - for (i = 0; i < nr_buckets; i++) - percpu_ref_put(&bch_dev_bkey_exists(c, buckets[i].b.inode)->io_ref); + darray_for_each(buckets, i) + percpu_ref_put(&bch_dev_bkey_exists(c, i->b.inode)->io_ref); /* Fall back to COW path: */ goto out; err_bucket_stale: - while (i >= 0) { - bch2_bucket_nocow_unlock(&c->nocow_locks, - buckets[i].b, - BUCKET_NOCOW_LOCK_UPDATE); - --i; + darray_for_each(buckets, i) { + bch2_bucket_nocow_unlock(&c->nocow_locks, i->b, BUCKET_NOCOW_LOCK_UPDATE); + if (i == stale_at) + break; } - for (i = 0; i < nr_buckets; i++) - percpu_ref_put(&bch_dev_bkey_exists(c, buckets[i].b.inode)->io_ref); /* We can retry this: */ ret = -BCH_ERR_transaction_restart; - goto out; + goto err_get_ioref; } static void __bch2_write(struct bch_write_op *op) diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 5de1b68fb8af..3eb6c3f62a81 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -408,8 +408,10 @@ static int journal_entry_btree_root_validate(struct bch_fs *c, return 0; } - return journal_validate_key(c, jset, entry, 1, entry->btree_id, k, - version, big_endian, flags); + ret = journal_validate_key(c, jset, entry, 1, entry->btree_id, k, + version, big_endian, flags); + if (ret == FSCK_DELETED_KEY) + ret = 0; fsck_err: return ret; } diff --git a/fs/bcachefs/printbuf.c b/fs/bcachefs/printbuf.c index 5e653eb81d54..accf246c3233 100644 --- a/fs/bcachefs/printbuf.c +++ b/fs/bcachefs/printbuf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: LGPL-2.1+ /* Copyright (C) 2022 Kent Overstreet */ +#include <linux/bitmap.h> #include <linux/err.h> #include <linux/export.h> #include <linux/kernel.h> @@ -423,3 +424,24 @@ void bch2_prt_bitflags(struct printbuf *out, flags ^= BIT_ULL(bit); } } + +void bch2_prt_bitflags_vector(struct printbuf *out, + const char * const list[], + unsigned long *v, unsigned nr) +{ + bool first = true; + unsigned i; + + for (i = 0; i < nr; i++) + if (!list[i]) { + nr = i - 1; + break; + } + + for_each_set_bit(i, v, nr) { + if (!first) + bch2_prt_printf(out, ","); + first = false; + bch2_prt_printf(out, "%s", list[i]); + } +} diff --git a/fs/bcachefs/printbuf.h b/fs/bcachefs/printbuf.h index 2191423d9f22..9a4a56c40937 100644 --- a/fs/bcachefs/printbuf.h +++ b/fs/bcachefs/printbuf.h @@ -124,6 +124,8 @@ void bch2_prt_units_u64(struct printbuf *, u64); void bch2_prt_units_s64(struct printbuf *, s64); void bch2_prt_string_option(struct printbuf *, const char * const[], size_t); void bch2_prt_bitflags(struct printbuf *, const char * const[], u64); +void bch2_prt_bitflags_vector(struct printbuf *, const char * const[], + unsigned long *, unsigned); /* Initializer for a heap allocated printbuf: */ #define PRINTBUF ((struct printbuf) { .heap_allocated = true }) diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index c7d9074c82d9..5cf7d0532002 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -27,6 +27,7 @@ #include "recovery.h" #include "replicas.h" #include "sb-clean.h" +#include "sb-downgrade.h" #include "snapshot.h" #include "subvolume.h" #include "super-io.h" @@ -481,7 +482,7 @@ static int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c) } const char * const bch2_recovery_passes[] = { -#define x(_fn, _when) #_fn, +#define x(_fn, ...) #_fn, BCH_RECOVERY_PASSES() #undef x NULL @@ -504,18 +505,47 @@ struct recovery_pass_fn { }; static struct recovery_pass_fn recovery_pass_fns[] = { -#define x(_fn, _when) { .fn = bch2_##_fn, .when = _when }, +#define x(_fn, _id, _when) { .fn = bch2_##_fn, .when = _when }, BCH_RECOVERY_PASSES() #undef x }; -static void check_version_upgrade(struct bch_fs *c) +u64 bch2_recovery_passes_to_stable(u64 v) +{ + static const u8 map[] = { +#define x(n, id, ...) [BCH_RECOVERY_PASS_##n] = BCH_RECOVERY_PASS_STABLE_##n, + BCH_RECOVERY_PASSES() +#undef x + }; + + u64 ret = 0; + for (unsigned i = 0; i < ARRAY_SIZE(map); i++) + if (v & BIT_ULL(i)) + ret |= BIT_ULL(map[i]); + return ret; +} + +u64 bch2_recovery_passes_from_stable(u64 v) +{ + static const u8 map[] = { +#define x(n, id, ...) [BCH_RECOVERY_PASS_STABLE_##n] = BCH_RECOVERY_PASS_##n, + BCH_RECOVERY_PASSES() +#undef x + }; + + u64 ret = 0; + for (unsigned i = 0; i < ARRAY_SIZE(map); i++) + if (v & BIT_ULL(i)) + ret |= BIT_ULL(map[i]); + return ret; +} + +static bool check_version_upgrade(struct bch_fs *c) { unsigned latest_compatible = bch2_latest_compatible_version(c->sb.version); unsigned latest_version = bcachefs_metadata_version_current; unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version; unsigned new_version = 0; - u64 recovery_passes; if (old_version < bcachefs_metadata_required_upgrade_below) { if (c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible || @@ -559,7 +589,7 @@ static void check_version_upgrade(struct bch_fs *c) bch2_version_to_text(&buf, new_version); prt_newline(&buf); - recovery_passes = bch2_upgrade_recovery_passes(c, old_version, new_version); + u64 recovery_passes = bch2_upgrade_recovery_passes(c, old_version, new_version); if (recovery_passes) { if ((recovery_passes & RECOVERY_PASS_ALL_FSCK) == RECOVERY_PASS_ALL_FSCK) prt_str(&buf, "fsck required"); @@ -574,12 +604,13 @@ static void check_version_upgrade(struct bch_fs *c) bch_info(c, "%s", buf.buf); - mutex_lock(&c->sb_lock); bch2_sb_upgrade(c, new_version); - mutex_unlock(&c->sb_lock); printbuf_exit(&buf); + return true; } + + return false; } u64 bch2_fsck_recovery_passes(void) @@ -654,7 +685,6 @@ int bch2_fs_recovery(struct bch_fs *c) struct bch_sb_field_clean *clean = NULL; struct jset *last_journal_entry = NULL; u64 last_seq = 0, blacklist_seq, journal_seq; - bool write_sb = false; int ret = 0; if (c->sb.clean) { @@ -682,15 +712,73 @@ int bch2_fs_recovery(struct bch_fs *c) goto err; } - if (c->opts.fsck || !(c->opts.nochanges && c->opts.norecovery)) - check_version_upgrade(c); - if (c->opts.fsck && c->opts.norecovery) { bch_err(c, "cannot select both norecovery and fsck"); ret = -EINVAL; goto err; } + if (!(c->opts.nochanges && c->opts.norecovery)) { + mutex_lock(&c->sb_lock); + bool write_sb = false; + + struct bch_sb_field_ext *ext = + bch2_sb_field_get_minsize(&c->disk_sb, ext, sizeof(*ext) / sizeof(u64)); + if (!ext) { + ret = -BCH_ERR_ENOSPC_sb; + mutex_unlock(&c->sb_lock); + goto err; + } + + if (BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb)) { + ext->recovery_passes_required[0] |= + cpu_to_le64(bch2_recovery_passes_to_stable(BIT_ULL(BCH_RECOVERY_PASS_check_topology))); + write_sb = true; + } + + u64 sb_passes = bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); + if (sb_passes) { + struct printbuf buf = PRINTBUF; + prt_str(&buf, "superblock requires following recovery passes to be run:\n "); + prt_bitflags(&buf, bch2_recovery_passes, sb_passes); + bch_info(c, "%s", buf.buf); + printbuf_exit(&buf); + } + + if (bch2_check_version_downgrade(c)) { + struct printbuf buf = PRINTBUF; + + prt_str(&buf, "Version downgrade required:\n"); + + __le64 passes = ext->recovery_passes_required[0]; + bch2_sb_set_downgrade(c, + BCH_VERSION_MINOR(bcachefs_metadata_version_current), + BCH_VERSION_MINOR(c->sb.version)); + passes = ext->recovery_passes_required[0] & ~passes; + if (passes) { + prt_str(&buf, " running recovery passes: "); + prt_bitflags(&buf, bch2_recovery_passes, + bch2_recovery_passes_from_stable(le64_to_cpu(passes))); + } + + bch_info(c, "%s", buf.buf); + printbuf_exit(&buf); + write_sb = true; + } + + if (check_version_upgrade(c)) + write_sb = true; + + if (write_sb) + bch2_write_super(c); + + c->recovery_passes_explicit |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); + mutex_unlock(&c->sb_lock); + } + + if (c->opts.fsck && IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) + c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); + ret = bch2_blacklist_table_initialize(c); if (ret) { bch_err(c, "error initializing blacklist table"); @@ -827,11 +915,6 @@ use_clean: if (ret) goto err; - if (c->opts.fsck && - (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) || - BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb))) - c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology); - ret = bch2_run_recovery_passes(c); if (ret) goto err; @@ -868,16 +951,30 @@ use_clean: } mutex_lock(&c->sb_lock); - if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != c->sb.version) { - SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, c->sb.version); + bool write_sb = false; + + if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != le16_to_cpu(c->disk_sb.sb->version)) { + SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, le16_to_cpu(c->disk_sb.sb->version)); write_sb = true; } - if (!test_bit(BCH_FS_ERROR, &c->flags)) { + if (!test_bit(BCH_FS_ERROR, &c->flags) && + !(c->disk_sb.sb->compat[0] & cpu_to_le64(1ULL << BCH_COMPAT_alloc_info))) { c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_alloc_info); write_sb = true; } + if (!test_bit(BCH_FS_ERROR, &c->flags)) { + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); + if (ext && + (!bch2_is_zero(ext->recovery_passes_required, sizeof(ext->recovery_passes_required)) || + !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent)))) { + memset(ext->recovery_passes_required, 0, sizeof(ext->recovery_passes_required)); + memset(ext->errors_silent, 0, sizeof(ext->errors_silent)); + write_sb = true; + } + } + if (c->opts.fsck && !test_bit(BCH_FS_ERROR, &c->flags) && !test_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags)) { @@ -947,7 +1044,7 @@ int bch2_fs_initialize(struct bch_fs *c) c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_extents_above_btree_updates_done); c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_bformat_overflow_done); - bch2_sb_maybe_downgrade(c); + bch2_check_version_downgrade(c); if (c->opts.version_upgrade != BCH_VERSION_UPGRADE_none) { bch2_sb_upgrade(c, bcachefs_metadata_version_current); diff --git a/fs/bcachefs/recovery.h b/fs/bcachefs/recovery.h index d266aae90200..3a554b0751d0 100644 --- a/fs/bcachefs/recovery.h +++ b/fs/bcachefs/recovery.h @@ -4,6 +4,9 @@ extern const char * const bch2_recovery_passes[]; +u64 bch2_recovery_passes_to_stable(u64 v); +u64 bch2_recovery_passes_from_stable(u64 v); + /* * For when we need to rewind recovery passes and run a pass we skipped: */ diff --git a/fs/bcachefs/recovery_types.h b/fs/bcachefs/recovery_types.h index 515e3d62c2ac..d37c6fd30e38 100644 --- a/fs/bcachefs/recovery_types.h +++ b/fs/bcachefs/recovery_types.h @@ -7,45 +7,57 @@ #define PASS_UNCLEAN BIT(2) #define PASS_ALWAYS BIT(3) -#define BCH_RECOVERY_PASSES() \ - x(alloc_read, PASS_ALWAYS) \ - x(stripes_read, PASS_ALWAYS) \ - x(initialize_subvolumes, 0) \ - x(snapshots_read, PASS_ALWAYS) \ - x(check_topology, 0) \ - x(check_allocations, PASS_FSCK) \ - x(trans_mark_dev_sbs, PASS_ALWAYS|PASS_SILENT) \ - x(fs_journal_alloc, PASS_ALWAYS|PASS_SILENT) \ - x(set_may_go_rw, PASS_ALWAYS|PASS_SILENT) \ - x(journal_replay, PASS_ALWAYS) \ - x(check_alloc_info, PASS_FSCK) \ - x(check_lrus, PASS_FSCK) \ - x(check_btree_backpointers, PASS_FSCK) \ - x(check_backpointers_to_extents,PASS_FSCK) \ - x(check_extents_to_backpointers,PASS_FSCK) \ - x(check_alloc_to_lru_refs, PASS_FSCK) \ - x(fs_freespace_init, PASS_ALWAYS|PASS_SILENT) \ - x(bucket_gens_init, 0) \ - x(check_snapshot_trees, PASS_FSCK) \ - x(check_snapshots, PASS_FSCK) \ - x(check_subvols, PASS_FSCK) \ - x(delete_dead_snapshots, PASS_FSCK) \ - x(fs_upgrade_for_subvolumes, 0) \ - x(resume_logged_ops, PASS_ALWAYS) \ - x(check_inodes, PASS_FSCK) \ - x(check_extents, PASS_FSCK) \ - x(check_indirect_extents, PASS_FSCK) \ - x(check_dirents, PASS_FSCK) \ - x(check_xattrs, PASS_FSCK) \ - x(check_root, PASS_FSCK) \ - x(check_directory_structure, PASS_FSCK) \ - x(check_nlinks, PASS_FSCK) \ - x(delete_dead_inodes, PASS_FSCK|PASS_UNCLEAN) \ - x(fix_reflink_p, 0) \ - x(set_fs_needs_rebalance, 0) \ +/* + * Passes may be reordered, but the second field is a persistent identifier and + * must never change: + */ +#define BCH_RECOVERY_PASSES() \ + x(alloc_read, 0, PASS_ALWAYS) \ + x(stripes_read, 1, PASS_ALWAYS) \ + x(initialize_subvolumes, 2, 0) \ + x(snapshots_read, 3, PASS_ALWAYS) \ + x(check_topology, 4, 0) \ + x(check_allocations, 5, PASS_FSCK) \ + x(trans_mark_dev_sbs, 6, PASS_ALWAYS|PASS_SILENT) \ + x(fs_journal_alloc, 7, PASS_ALWAYS|PASS_SILENT) \ + x(set_may_go_rw, 8, PASS_ALWAYS|PASS_SILENT) \ + x(journal_replay, 9, PASS_ALWAYS) \ + x(check_alloc_info, 10, PASS_FSCK) \ + x(check_lrus, 11, PASS_FSCK) \ + x(check_btree_backpointers, 12, PASS_FSCK) \ + x(check_backpointers_to_extents, 13, PASS_FSCK) \ + x(check_extents_to_backpointers, 14, PASS_FSCK) \ + x(check_alloc_to_lru_refs, 15, PASS_FSCK) \ + x(fs_freespace_init, 16, PASS_ALWAYS|PASS_SILENT) \ + x(bucket_gens_init, 17, 0) \ + x(check_snapshot_trees, 18, PASS_FSCK) \ + x(check_snapshots, 19, PASS_FSCK) \ + x(check_subvols, 20, PASS_FSCK) \ + x(delete_dead_snapshots, 21, PASS_FSCK) \ + x(fs_upgrade_for_subvolumes, 22, 0) \ + x(resume_logged_ops, 23, PASS_ALWAYS) \ + x(check_inodes, 24, PASS_FSCK) \ + x(check_extents, 25, PASS_FSCK) \ + x(check_indirect_extents, 26, PASS_FSCK) \ + x(check_dirents, 27, PASS_FSCK) \ + x(check_xattrs, 28, PASS_FSCK) \ + x(check_root, 29, PASS_FSCK) \ + x(check_directory_structure, 30, PASS_FSCK) \ + x(check_nlinks, 31, PASS_FSCK) \ + x(delete_dead_inodes, 32, PASS_FSCK|PASS_UNCLEAN) \ + x(fix_reflink_p, 33, 0) \ + x(set_fs_needs_rebalance, 34, 0) \ +/* We normally enumerate recovery passes in the order we run them: */ enum bch_recovery_pass { -#define x(n, when) BCH_RECOVERY_PASS_##n, +#define x(n, id, when) BCH_RECOVERY_PASS_##n, + BCH_RECOVERY_PASSES() +#undef x +}; + +/* But we also need stable identifiers that can be used in the superblock */ +enum bch_recovery_pass_stable { +#define x(n, id, when) BCH_RECOVERY_PASS_STABLE_##n = id, BCH_RECOVERY_PASSES() #undef x }; diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c index e151ada1c8bd..c76ad8ea5e4a 100644 --- a/fs/bcachefs/sb-clean.c +++ b/fs/bcachefs/sb-clean.c @@ -332,8 +332,6 @@ int bch2_fs_mark_dirty(struct bch_fs *c) mutex_lock(&c->sb_lock); SET_BCH_SB_CLEAN(c->disk_sb.sb, false); - - bch2_sb_maybe_downgrade(c); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALWAYS); ret = bch2_write_super(c); diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c new file mode 100644 index 000000000000..4919237bbe73 --- /dev/null +++ b/fs/bcachefs/sb-downgrade.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Superblock section that contains a list of recovery passes to run when + * downgrading past a given version + */ + +#include "bcachefs.h" +#include "darray.h" +#include "recovery.h" +#include "sb-downgrade.h" +#include "sb-errors.h" +#include "super-io.h" + +/* + * Downgrade table: + * When dowgrading past certain versions, we need to run certain recovery passes + * and fix certain errors: + * + * x(version, recovery_passes, errors...) + */ + +#define DOWNGRADE_TABLE() + +struct downgrade_entry { + u64 recovery_passes; + u16 version; + u16 nr_errors; + const u16 *errors; +}; + +#define x(ver, passes, ...) static const u16 ver_##errors[] = { __VA_ARGS__ }; +DOWNGRADE_TABLE() +#undef x + +static const struct downgrade_entry downgrade_table[] = { +#define x(ver, passes, ...) { \ + .recovery_passes = passes, \ + .version = bcachefs_metadata_version_##ver,\ + .nr_errors = ARRAY_SIZE(ver_##errors), \ + .errors = ver_##errors, \ +}, +DOWNGRADE_TABLE() +#undef x +}; + +static inline const struct bch_sb_field_downgrade_entry * +downgrade_entry_next_c(const struct bch_sb_field_downgrade_entry *e) +{ + return (void *) &e->errors[le16_to_cpu(e->nr_errors)]; +} + +#define for_each_downgrade_entry(_d, _i) \ + for (const struct bch_sb_field_downgrade_entry *_i = (_d)->entries; \ + (void *) _i < vstruct_end(&(_d)->field) && \ + (void *) &_i->errors[0] < vstruct_end(&(_d)->field); \ + _i = downgrade_entry_next_c(_i)) + +static int bch2_sb_downgrade_validate(struct bch_sb *sb, struct bch_sb_field *f, + struct printbuf *err) +{ + struct bch_sb_field_downgrade *e = field_to_type(f, downgrade); + + for_each_downgrade_entry(e, i) { + if (BCH_VERSION_MAJOR(le16_to_cpu(i->version)) != + BCH_VERSION_MAJOR(le16_to_cpu(sb->version))) { + prt_printf(err, "downgrade entry with mismatched major version (%u != %u)", + BCH_VERSION_MAJOR(le16_to_cpu(i->version)), + BCH_VERSION_MAJOR(le16_to_cpu(sb->version))); + return -BCH_ERR_invalid_sb_downgrade; + } + } + + return 0; +} + +static void bch2_sb_downgrade_to_text(struct printbuf *out, struct bch_sb *sb, + struct bch_sb_field *f) +{ + struct bch_sb_field_downgrade *e = field_to_type(f, downgrade); + + if (out->nr_tabstops <= 1) + printbuf_tabstop_push(out, 16); + + for_each_downgrade_entry(e, i) { + prt_str(out, "version:"); + prt_tab(out); + bch2_version_to_text(out, le16_to_cpu(i->version)); + prt_newline(out); + + prt_str(out, "recovery passes:"); + prt_tab(out); + prt_bitflags(out, bch2_recovery_passes, + bch2_recovery_passes_from_stable(le64_to_cpu(i->recovery_passes[0]))); + prt_newline(out); + + prt_str(out, "errors:"); + prt_tab(out); + bool first = true; + for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) { + if (!first) + prt_char(out, ','); + first = false; + unsigned e = le16_to_cpu(i->errors[j]); + prt_str(out, e < BCH_SB_ERR_MAX ? bch2_sb_error_strs[e] : "(unknown)"); + } + prt_newline(out); + } +} + +const struct bch_sb_field_ops bch_sb_field_ops_downgrade = { + .validate = bch2_sb_downgrade_validate, + .to_text = bch2_sb_downgrade_to_text, +}; + +int bch2_sb_downgrade_update(struct bch_fs *c) +{ + darray_char table = {}; + int ret = 0; + + for (const struct downgrade_entry *src = downgrade_table; + src < downgrade_table + ARRAY_SIZE(downgrade_table); + src++) { + if (BCH_VERSION_MAJOR(src->version) != BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version))) + continue; + + struct bch_sb_field_downgrade_entry *dst; + unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * src->nr_errors; + + ret = darray_make_room(&table, bytes); + if (ret) + goto out; + + dst = (void *) &darray_top(table); + dst->version = cpu_to_le16(src->version); + dst->recovery_passes[0] = cpu_to_le64(src->recovery_passes); + dst->recovery_passes[1] = 0; + dst->nr_errors = cpu_to_le16(src->nr_errors); + for (unsigned i = 0; i < src->nr_errors; i++) + dst->errors[i] = cpu_to_le16(src->errors[i]); + + table.nr += bytes; + } + + struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade); + + unsigned sb_u64s = DIV_ROUND_UP(sizeof(*d) + table.nr, sizeof(u64)); + + if (d && le32_to_cpu(d->field.u64s) > sb_u64s) + goto out; + + d = bch2_sb_field_resize(&c->disk_sb, downgrade, sb_u64s); + if (!d) { + ret = -BCH_ERR_ENOSPC_sb_downgrade; + goto out; + } + + memcpy(d->entries, table.data, table.nr); + memset_u64s_tail(d->entries, 0, table.nr); +out: + darray_exit(&table); + return ret; +} + +void bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_minor) +{ + struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade); + if (!d) + return; + + struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); + + for_each_downgrade_entry(d, i) { + unsigned minor = BCH_VERSION_MINOR(le16_to_cpu(i->version)); + if (new_minor < minor && minor <= old_minor) { + ext->recovery_passes_required[0] |= i->recovery_passes[0]; + ext->recovery_passes_required[1] |= i->recovery_passes[1]; + + for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) { + unsigned e = le16_to_cpu(i->errors[j]); + if (e < BCH_SB_ERR_MAX) + __set_bit(e, c->sb.errors_silent); + if (e < sizeof(ext->errors_silent) * 8) + ext->errors_silent[e / 64] |= cpu_to_le64(BIT_ULL(e % 64)); + } + } + } +} diff --git a/fs/bcachefs/sb-downgrade.h b/fs/bcachefs/sb-downgrade.h new file mode 100644 index 000000000000..bc48fd2ca70e --- /dev/null +++ b/fs/bcachefs/sb-downgrade.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_SB_DOWNGRADE_H +#define _BCACHEFS_SB_DOWNGRADE_H + +extern const struct bch_sb_field_ops bch_sb_field_ops_downgrade; + +int bch2_sb_downgrade_update(struct bch_fs *); +void bch2_sb_set_downgrade(struct bch_fs *, unsigned, unsigned); + +#endif /* _BCACHEFS_SB_DOWNGRADE_H */ diff --git a/fs/bcachefs/sb-errors.c b/fs/bcachefs/sb-errors.c index f0930ab7f036..5f5bcae391fb 100644 --- a/fs/bcachefs/sb-errors.c +++ b/fs/bcachefs/sb-errors.c @@ -4,7 +4,7 @@ #include "sb-errors.h" #include "super-io.h" -static const char * const bch2_sb_error_strs[] = { +const char * const bch2_sb_error_strs[] = { #define x(t, n, ...) [n] = #t, BCH_SB_ERRS() NULL @@ -20,9 +20,7 @@ static void bch2_sb_error_id_to_text(struct printbuf *out, enum bch_sb_error_id static inline unsigned bch2_sb_field_errors_nr_entries(struct bch_sb_field_errors *e) { - return e - ? (bch2_sb_field_bytes(&e->field) - sizeof(*e)) / sizeof(e->entries[0]) - : 0; + return bch2_sb_field_nr_entries(e); } static inline unsigned bch2_sb_field_errors_u64s(unsigned nr) diff --git a/fs/bcachefs/sb-errors.h b/fs/bcachefs/sb-errors.h index 5a09a53966be..8889001e7db4 100644 --- a/fs/bcachefs/sb-errors.h +++ b/fs/bcachefs/sb-errors.h @@ -4,258 +4,7 @@ #include "sb-errors_types.h" -#define BCH_SB_ERRS() \ - x(clean_but_journal_not_empty, 0) \ - x(dirty_but_no_journal_entries, 1) \ - x(dirty_but_no_journal_entries_post_drop_nonflushes, 2) \ - x(sb_clean_journal_seq_mismatch, 3) \ - x(sb_clean_btree_root_mismatch, 4) \ - x(sb_clean_missing, 5) \ - x(jset_unsupported_version, 6) \ - x(jset_unknown_csum, 7) \ - x(jset_last_seq_newer_than_seq, 8) \ - x(jset_past_bucket_end, 9) \ - x(jset_seq_blacklisted, 10) \ - x(journal_entries_missing, 11) \ - x(journal_entry_replicas_not_marked, 12) \ - x(journal_entry_past_jset_end, 13) \ - x(journal_entry_replicas_data_mismatch, 14) \ - x(journal_entry_bkey_u64s_0, 15) \ - x(journal_entry_bkey_past_end, 16) \ - x(journal_entry_bkey_bad_format, 17) \ - x(journal_entry_bkey_invalid, 18) \ - x(journal_entry_btree_root_bad_size, 19) \ - x(journal_entry_blacklist_bad_size, 20) \ - x(journal_entry_blacklist_v2_bad_size, 21) \ - x(journal_entry_blacklist_v2_start_past_end, 22) \ - x(journal_entry_usage_bad_size, 23) \ - x(journal_entry_data_usage_bad_size, 24) \ - x(journal_entry_clock_bad_size, 25) \ - x(journal_entry_clock_bad_rw, 26) \ - x(journal_entry_dev_usage_bad_size, 27) \ - x(journal_entry_dev_usage_bad_dev, 28) \ - x(journal_entry_dev_usage_bad_pad, 29) \ - x(btree_node_unreadable, 30) \ - x(btree_node_fault_injected, 31) \ - x(btree_node_bad_magic, 32) \ - x(btree_node_bad_seq, 33) \ - x(btree_node_unsupported_version, 34) \ - x(btree_node_bset_older_than_sb_min, 35) \ - x(btree_node_bset_newer_than_sb, 36) \ - x(btree_node_data_missing, 37) \ - x(btree_node_bset_after_end, 38) \ - x(btree_node_replicas_sectors_written_mismatch, 39) \ - x(btree_node_replicas_data_mismatch, 40) \ - x(bset_unknown_csum, 41) \ - x(bset_bad_csum, 42) \ - x(bset_past_end_of_btree_node, 43) \ - x(bset_wrong_sector_offset, 44) \ - x(bset_empty, 45) \ - x(bset_bad_seq, 46) \ - x(bset_blacklisted_journal_seq, 47) \ - x(first_bset_blacklisted_journal_seq, 48) \ - x(btree_node_bad_btree, 49) \ - x(btree_node_bad_level, 50) \ - x(btree_node_bad_min_key, 51) \ - x(btree_node_bad_max_key, 52) \ - x(btree_node_bad_format, 53) \ - x(btree_node_bkey_past_bset_end, 54) \ - x(btree_node_bkey_bad_format, 55) \ - x(btree_node_bad_bkey, 56) \ - x(btree_node_bkey_out_of_order, 57) \ - x(btree_root_bkey_invalid, 58) \ - x(btree_root_read_error, 59) \ - x(btree_root_bad_min_key, 50) \ - x(btree_root_bad_max_key, 61) \ - x(btree_node_read_error, 62) \ - x(btree_node_topology_bad_min_key, 63) \ - x(btree_node_topology_bad_max_key, 64) \ - x(btree_node_topology_overwritten_by_prev_node, 65) \ - x(btree_node_topology_overwritten_by_next_node, 66) \ - x(btree_node_topology_interior_node_empty, 67) \ - x(fs_usage_hidden_wrong, 68) \ - x(fs_usage_btree_wrong, 69) \ - x(fs_usage_data_wrong, 70) \ - x(fs_usage_cached_wrong, 71) \ - x(fs_usage_reserved_wrong, 72) \ - x(fs_usage_persistent_reserved_wrong, 73) \ - x(fs_usage_nr_inodes_wrong, 74) \ - x(fs_usage_replicas_wrong, 75) \ - x(dev_usage_buckets_wrong, 76) \ - x(dev_usage_sectors_wrong, 77) \ - x(dev_usage_fragmented_wrong, 78) \ - x(dev_usage_buckets_ec_wrong, 79) \ - x(bkey_version_in_future, 80) \ - x(bkey_u64s_too_small, 81) \ - x(bkey_invalid_type_for_btree, 82) \ - x(bkey_extent_size_zero, 83) \ - x(bkey_extent_size_greater_than_offset, 84) \ - x(bkey_size_nonzero, 85) \ - x(bkey_snapshot_nonzero, 86) \ - x(bkey_snapshot_zero, 87) \ - x(bkey_at_pos_max, 88) \ - x(bkey_before_start_of_btree_node, 89) \ - x(bkey_after_end_of_btree_node, 90) \ - x(bkey_val_size_nonzero, 91) \ - x(bkey_val_size_too_small, 92) \ - x(alloc_v1_val_size_bad, 93) \ - x(alloc_v2_unpack_error, 94) \ - x(alloc_v3_unpack_error, 95) \ - x(alloc_v4_val_size_bad, 96) \ - x(alloc_v4_backpointers_start_bad, 97) \ - x(alloc_key_data_type_bad, 98) \ - x(alloc_key_empty_but_have_data, 99) \ - x(alloc_key_dirty_sectors_0, 100) \ - x(alloc_key_data_type_inconsistency, 101) \ - x(alloc_key_to_missing_dev_bucket, 102) \ - x(alloc_key_cached_inconsistency, 103) \ - x(alloc_key_cached_but_read_time_zero, 104) \ - x(alloc_key_to_missing_lru_entry, 105) \ - x(alloc_key_data_type_wrong, 106) \ - x(alloc_key_gen_wrong, 107) \ - x(alloc_key_dirty_sectors_wrong, 108) \ - x(alloc_key_cached_sectors_wrong, 109) \ - x(alloc_key_stripe_wrong, 110) \ - x(alloc_key_stripe_redundancy_wrong, 111) \ - x(bucket_sector_count_overflow, 112) \ - x(bucket_metadata_type_mismatch, 113) \ - x(need_discard_key_wrong, 114) \ - x(freespace_key_wrong, 115) \ - x(freespace_hole_missing, 116) \ - x(bucket_gens_val_size_bad, 117) \ - x(bucket_gens_key_wrong, 118) \ - x(bucket_gens_hole_wrong, 119) \ - x(bucket_gens_to_invalid_dev, 120) \ - x(bucket_gens_to_invalid_buckets, 121) \ - x(bucket_gens_nonzero_for_invalid_buckets, 122) \ - x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ - x(need_discard_freespace_key_bad, 124) \ - x(backpointer_pos_wrong, 125) \ - x(backpointer_to_missing_device, 126) \ - x(backpointer_to_missing_alloc, 127) \ - x(backpointer_to_missing_ptr, 128) \ - x(lru_entry_at_time_0, 129) \ - x(lru_entry_to_invalid_bucket, 130) \ - x(lru_entry_bad, 131) \ - x(btree_ptr_val_too_big, 132) \ - x(btree_ptr_v2_val_too_big, 133) \ - x(btree_ptr_has_non_ptr, 134) \ - x(extent_ptrs_invalid_entry, 135) \ - x(extent_ptrs_no_ptrs, 136) \ - x(extent_ptrs_too_many_ptrs, 137) \ - x(extent_ptrs_redundant_crc, 138) \ - x(extent_ptrs_redundant_stripe, 139) \ - x(extent_ptrs_unwritten, 140) \ - x(extent_ptrs_written_and_unwritten, 141) \ - x(ptr_to_invalid_device, 142) \ - x(ptr_to_duplicate_device, 143) \ - x(ptr_after_last_bucket, 144) \ - x(ptr_before_first_bucket, 145) \ - x(ptr_spans_multiple_buckets, 146) \ - x(ptr_to_missing_backpointer, 147) \ - x(ptr_to_missing_alloc_key, 148) \ - x(ptr_to_missing_replicas_entry, 149) \ - x(ptr_to_missing_stripe, 150) \ - x(ptr_to_incorrect_stripe, 151) \ - x(ptr_gen_newer_than_bucket_gen, 152) \ - x(ptr_too_stale, 153) \ - x(stale_dirty_ptr, 154) \ - x(ptr_bucket_data_type_mismatch, 155) \ - x(ptr_cached_and_erasure_coded, 156) \ - x(ptr_crc_uncompressed_size_too_small, 157) \ - x(ptr_crc_csum_type_unknown, 158) \ - x(ptr_crc_compression_type_unknown, 159) \ - x(ptr_crc_redundant, 160) \ - x(ptr_crc_uncompressed_size_too_big, 161) \ - x(ptr_crc_nonce_mismatch, 162) \ - x(ptr_stripe_redundant, 163) \ - x(reservation_key_nr_replicas_invalid, 164) \ - x(reflink_v_refcount_wrong, 165) \ - x(reflink_p_to_missing_reflink_v, 166) \ - x(stripe_pos_bad, 167) \ - x(stripe_val_size_bad, 168) \ - x(stripe_sector_count_wrong, 169) \ - x(snapshot_tree_pos_bad, 170) \ - x(snapshot_tree_to_missing_snapshot, 171) \ - x(snapshot_tree_to_missing_subvol, 172) \ - x(snapshot_tree_to_wrong_subvol, 173) \ - x(snapshot_tree_to_snapshot_subvol, 174) \ - x(snapshot_pos_bad, 175) \ - x(snapshot_parent_bad, 176) \ - x(snapshot_children_not_normalized, 177) \ - x(snapshot_child_duplicate, 178) \ - x(snapshot_child_bad, 179) \ - x(snapshot_skiplist_not_normalized, 180) \ - x(snapshot_skiplist_bad, 181) \ - x(snapshot_should_not_have_subvol, 182) \ - x(snapshot_to_bad_snapshot_tree, 183) \ - x(snapshot_bad_depth, 184) \ - x(snapshot_bad_skiplist, 185) \ - x(subvol_pos_bad, 186) \ - x(subvol_not_master_and_not_snapshot, 187) \ - x(subvol_to_missing_root, 188) \ - x(subvol_root_wrong_bi_subvol, 189) \ - x(bkey_in_missing_snapshot, 190) \ - x(inode_pos_inode_nonzero, 191) \ - x(inode_pos_blockdev_range, 192) \ - x(inode_unpack_error, 193) \ - x(inode_str_hash_invalid, 194) \ - x(inode_v3_fields_start_bad, 195) \ - x(inode_snapshot_mismatch, 196) \ - x(inode_unlinked_but_clean, 197) \ - x(inode_unlinked_but_nlink_nonzero, 198) \ - x(inode_checksum_type_invalid, 199) \ - x(inode_compression_type_invalid, 200) \ - x(inode_subvol_root_but_not_dir, 201) \ - x(inode_i_size_dirty_but_clean, 202) \ - x(inode_i_sectors_dirty_but_clean, 203) \ - x(inode_i_sectors_wrong, 204) \ - x(inode_dir_wrong_nlink, 205) \ - x(inode_dir_multiple_links, 206) \ - x(inode_multiple_links_but_nlink_0, 207) \ - x(inode_wrong_backpointer, 208) \ - x(inode_wrong_nlink, 209) \ - x(inode_unreachable, 210) \ - x(deleted_inode_but_clean, 211) \ - x(deleted_inode_missing, 212) \ - x(deleted_inode_is_dir, 213) \ - x(deleted_inode_not_unlinked, 214) \ - x(extent_overlapping, 215) \ - x(extent_in_missing_inode, 216) \ - x(extent_in_non_reg_inode, 217) \ - x(extent_past_end_of_inode, 218) \ - x(dirent_empty_name, 219) \ - x(dirent_val_too_big, 220) \ - x(dirent_name_too_long, 221) \ - x(dirent_name_embedded_nul, 222) \ - x(dirent_name_dot_or_dotdot, 223) \ - x(dirent_name_has_slash, 224) \ - x(dirent_d_type_wrong, 225) \ - x(dirent_d_parent_subvol_wrong, 226) \ - x(dirent_in_missing_dir_inode, 227) \ - x(dirent_in_non_dir_inode, 228) \ - x(dirent_to_missing_inode, 229) \ - x(dirent_to_missing_subvol, 230) \ - x(dirent_to_itself, 231) \ - x(quota_type_invalid, 232) \ - x(xattr_val_size_too_small, 233) \ - x(xattr_val_size_too_big, 234) \ - x(xattr_invalid_type, 235) \ - x(xattr_name_invalid_chars, 236) \ - x(xattr_in_missing_inode, 237) \ - x(root_subvol_missing, 238) \ - x(root_dir_missing, 239) \ - x(root_inode_not_dir, 240) \ - x(dir_loop, 241) \ - x(hash_table_key_duplicate, 242) \ - x(hash_table_key_wrong_offset, 243) - -enum bch_sb_error_id { -#define x(t, n) BCH_FSCK_ERR_##t = n, - BCH_SB_ERRS() -#undef x - BCH_SB_ERR_MAX -}; +extern const char * const bch2_sb_error_strs[]; extern const struct bch_sb_field_ops bch_sb_field_ops_errors; diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h index b1c099843a39..3504c2d09c29 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -4,6 +4,259 @@ #include "darray.h" +#define BCH_SB_ERRS() \ + x(clean_but_journal_not_empty, 0) \ + x(dirty_but_no_journal_entries, 1) \ + x(dirty_but_no_journal_entries_post_drop_nonflushes, 2) \ + x(sb_clean_journal_seq_mismatch, 3) \ + x(sb_clean_btree_root_mismatch, 4) \ + x(sb_clean_missing, 5) \ + x(jset_unsupported_version, 6) \ + x(jset_unknown_csum, 7) \ + x(jset_last_seq_newer_than_seq, 8) \ + x(jset_past_bucket_end, 9) \ + x(jset_seq_blacklisted, 10) \ + x(journal_entries_missing, 11) \ + x(journal_entry_replicas_not_marked, 12) \ + x(journal_entry_past_jset_end, 13) \ + x(journal_entry_replicas_data_mismatch, 14) \ + x(journal_entry_bkey_u64s_0, 15) \ + x(journal_entry_bkey_past_end, 16) \ + x(journal_entry_bkey_bad_format, 17) \ + x(journal_entry_bkey_invalid, 18) \ + x(journal_entry_btree_root_bad_size, 19) \ + x(journal_entry_blacklist_bad_size, 20) \ + x(journal_entry_blacklist_v2_bad_size, 21) \ + x(journal_entry_blacklist_v2_start_past_end, 22) \ + x(journal_entry_usage_bad_size, 23) \ + x(journal_entry_data_usage_bad_size, 24) \ + x(journal_entry_clock_bad_size, 25) \ + x(journal_entry_clock_bad_rw, 26) \ + x(journal_entry_dev_usage_bad_size, 27) \ + x(journal_entry_dev_usage_bad_dev, 28) \ + x(journal_entry_dev_usage_bad_pad, 29) \ + x(btree_node_unreadable, 30) \ + x(btree_node_fault_injected, 31) \ + x(btree_node_bad_magic, 32) \ + x(btree_node_bad_seq, 33) \ + x(btree_node_unsupported_version, 34) \ + x(btree_node_bset_older_than_sb_min, 35) \ + x(btree_node_bset_newer_than_sb, 36) \ + x(btree_node_data_missing, 37) \ + x(btree_node_bset_after_end, 38) \ + x(btree_node_replicas_sectors_written_mismatch, 39) \ + x(btree_node_replicas_data_mismatch, 40) \ + x(bset_unknown_csum, 41) \ + x(bset_bad_csum, 42) \ + x(bset_past_end_of_btree_node, 43) \ + x(bset_wrong_sector_offset, 44) \ + x(bset_empty, 45) \ + x(bset_bad_seq, 46) \ + x(bset_blacklisted_journal_seq, 47) \ + x(first_bset_blacklisted_journal_seq, 48) \ + x(btree_node_bad_btree, 49) \ + x(btree_node_bad_level, 50) \ + x(btree_node_bad_min_key, 51) \ + x(btree_node_bad_max_key, 52) \ + x(btree_node_bad_format, 53) \ + x(btree_node_bkey_past_bset_end, 54) \ + x(btree_node_bkey_bad_format, 55) \ + x(btree_node_bad_bkey, 56) \ + x(btree_node_bkey_out_of_order, 57) \ + x(btree_root_bkey_invalid, 58) \ + x(btree_root_read_error, 59) \ + x(btree_root_bad_min_key, 60) \ + x(btree_root_bad_max_key, 61) \ + x(btree_node_read_error, 62) \ + x(btree_node_topology_bad_min_key, 63) \ + x(btree_node_topology_bad_max_key, 64) \ + x(btree_node_topology_overwritten_by_prev_node, 65) \ + x(btree_node_topology_overwritten_by_next_node, 66) \ + x(btree_node_topology_interior_node_empty, 67) \ + x(fs_usage_hidden_wrong, 68) \ + x(fs_usage_btree_wrong, 69) \ + x(fs_usage_data_wrong, 70) \ + x(fs_usage_cached_wrong, 71) \ + x(fs_usage_reserved_wrong, 72) \ + x(fs_usage_persistent_reserved_wrong, 73) \ + x(fs_usage_nr_inodes_wrong, 74) \ + x(fs_usage_replicas_wrong, 75) \ + x(dev_usage_buckets_wrong, 76) \ + x(dev_usage_sectors_wrong, 77) \ + x(dev_usage_fragmented_wrong, 78) \ + x(dev_usage_buckets_ec_wrong, 79) \ + x(bkey_version_in_future, 80) \ + x(bkey_u64s_too_small, 81) \ + x(bkey_invalid_type_for_btree, 82) \ + x(bkey_extent_size_zero, 83) \ + x(bkey_extent_size_greater_than_offset, 84) \ + x(bkey_size_nonzero, 85) \ + x(bkey_snapshot_nonzero, 86) \ + x(bkey_snapshot_zero, 87) \ + x(bkey_at_pos_max, 88) \ + x(bkey_before_start_of_btree_node, 89) \ + x(bkey_after_end_of_btree_node, 90) \ + x(bkey_val_size_nonzero, 91) \ + x(bkey_val_size_too_small, 92) \ + x(alloc_v1_val_size_bad, 93) \ + x(alloc_v2_unpack_error, 94) \ + x(alloc_v3_unpack_error, 95) \ + x(alloc_v4_val_size_bad, 96) \ + x(alloc_v4_backpointers_start_bad, 97) \ + x(alloc_key_data_type_bad, 98) \ + x(alloc_key_empty_but_have_data, 99) \ + x(alloc_key_dirty_sectors_0, 100) \ + x(alloc_key_data_type_inconsistency, 101) \ + x(alloc_key_to_missing_dev_bucket, 102) \ + x(alloc_key_cached_inconsistency, 103) \ + x(alloc_key_cached_but_read_time_zero, 104) \ + x(alloc_key_to_missing_lru_entry, 105) \ + x(alloc_key_data_type_wrong, 106) \ + x(alloc_key_gen_wrong, 107) \ + x(alloc_key_dirty_sectors_wrong, 108) \ + x(alloc_key_cached_sectors_wrong, 109) \ + x(alloc_key_stripe_wrong, 110) \ + x(alloc_key_stripe_redundancy_wrong, 111) \ + x(bucket_sector_count_overflow, 112) \ + x(bucket_metadata_type_mismatch, 113) \ + x(need_discard_key_wrong, 114) \ + x(freespace_key_wrong, 115) \ + x(freespace_hole_missing, 116) \ + x(bucket_gens_val_size_bad, 117) \ + x(bucket_gens_key_wrong, 118) \ + x(bucket_gens_hole_wrong, 119) \ + x(bucket_gens_to_invalid_dev, 120) \ + x(bucket_gens_to_invalid_buckets, 121) \ + x(bucket_gens_nonzero_for_invalid_buckets, 122) \ + x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ + x(need_discard_freespace_key_bad, 124) \ + x(backpointer_pos_wrong, 125) \ + x(backpointer_to_missing_device, 126) \ + x(backpointer_to_missing_alloc, 127) \ + x(backpointer_to_missing_ptr, 128) \ + x(lru_entry_at_time_0, 129) \ + x(lru_entry_to_invalid_bucket, 130) \ + x(lru_entry_bad, 131) \ + x(btree_ptr_val_too_big, 132) \ + x(btree_ptr_v2_val_too_big, 133) \ + x(btree_ptr_has_non_ptr, 134) \ + x(extent_ptrs_invalid_entry, 135) \ + x(extent_ptrs_no_ptrs, 136) \ + x(extent_ptrs_too_many_ptrs, 137) \ + x(extent_ptrs_redundant_crc, 138) \ + x(extent_ptrs_redundant_stripe, 139) \ + x(extent_ptrs_unwritten, 140) \ + x(extent_ptrs_written_and_unwritten, 141) \ + x(ptr_to_invalid_device, 142) \ + x(ptr_to_duplicate_device, 143) \ + x(ptr_after_last_bucket, 144) \ + x(ptr_before_first_bucket, 145) \ + x(ptr_spans_multiple_buckets, 146) \ + x(ptr_to_missing_backpointer, 147) \ + x(ptr_to_missing_alloc_key, 148) \ + x(ptr_to_missing_replicas_entry, 149) \ + x(ptr_to_missing_stripe, 150) \ + x(ptr_to_incorrect_stripe, 151) \ + x(ptr_gen_newer_than_bucket_gen, 152) \ + x(ptr_too_stale, 153) \ + x(stale_dirty_ptr, 154) \ + x(ptr_bucket_data_type_mismatch, 155) \ + x(ptr_cached_and_erasure_coded, 156) \ + x(ptr_crc_uncompressed_size_too_small, 157) \ + x(ptr_crc_csum_type_unknown, 158) \ + x(ptr_crc_compression_type_unknown, 159) \ + x(ptr_crc_redundant, 160) \ + x(ptr_crc_uncompressed_size_too_big, 161) \ + x(ptr_crc_nonce_mismatch, 162) \ + x(ptr_stripe_redundant, 163) \ + x(reservation_key_nr_replicas_invalid, 164) \ + x(reflink_v_refcount_wrong, 165) \ + x(reflink_p_to_missing_reflink_v, 166) \ + x(stripe_pos_bad, 167) \ + x(stripe_val_size_bad, 168) \ + x(stripe_sector_count_wrong, 169) \ + x(snapshot_tree_pos_bad, 170) \ + x(snapshot_tree_to_missing_snapshot, 171) \ + x(snapshot_tree_to_missing_subvol, 172) \ + x(snapshot_tree_to_wrong_subvol, 173) \ + x(snapshot_tree_to_snapshot_subvol, 174) \ + x(snapshot_pos_bad, 175) \ + x(snapshot_parent_bad, 176) \ + x(snapshot_children_not_normalized, 177) \ + x(snapshot_child_duplicate, 178) \ + x(snapshot_child_bad, 179) \ + x(snapshot_skiplist_not_normalized, 180) \ + x(snapshot_skiplist_bad, 181) \ + x(snapshot_should_not_have_subvol, 182) \ + x(snapshot_to_bad_snapshot_tree, 183) \ + x(snapshot_bad_depth, 184) \ + x(snapshot_bad_skiplist, 185) \ + x(subvol_pos_bad, 186) \ + x(subvol_not_master_and_not_snapshot, 187) \ + x(subvol_to_missing_root, 188) \ + x(subvol_root_wrong_bi_subvol, 189) \ + x(bkey_in_missing_snapshot, 190) \ + x(inode_pos_inode_nonzero, 191) \ + x(inode_pos_blockdev_range, 192) \ + x(inode_unpack_error, 193) \ + x(inode_str_hash_invalid, 194) \ + x(inode_v3_fields_start_bad, 195) \ + x(inode_snapshot_mismatch, 196) \ + x(inode_unlinked_but_clean, 197) \ + x(inode_unlinked_but_nlink_nonzero, 198) \ + x(inode_checksum_type_invalid, 199) \ + x(inode_compression_type_invalid, 200) \ + x(inode_subvol_root_but_not_dir, 201) \ + x(inode_i_size_dirty_but_clean, 202) \ + x(inode_i_sectors_dirty_but_clean, 203) \ + x(inode_i_sectors_wrong, 204) \ + x(inode_dir_wrong_nlink, 205) \ + x(inode_dir_multiple_links, 206) \ + x(inode_multiple_links_but_nlink_0, 207) \ + x(inode_wrong_backpointer, 208) \ + x(inode_wrong_nlink, 209) \ + x(inode_unreachable, 210) \ + x(deleted_inode_but_clean, 211) \ + x(deleted_inode_missing, 212) \ + x(deleted_inode_is_dir, 213) \ + x(deleted_inode_not_unlinked, 214) \ + x(extent_overlapping, 215) \ + x(extent_in_missing_inode, 216) \ + x(extent_in_non_reg_inode, 217) \ + x(extent_past_end_of_inode, 218) \ + x(dirent_empty_name, 219) \ + x(dirent_val_too_big, 220) \ + x(dirent_name_too_long, 221) \ + x(dirent_name_embedded_nul, 222) \ + x(dirent_name_dot_or_dotdot, 223) \ + x(dirent_name_has_slash, 224) \ + x(dirent_d_type_wrong, 225) \ + x(dirent_d_parent_subvol_wrong, 226) \ + x(dirent_in_missing_dir_inode, 227) \ + x(dirent_in_non_dir_inode, 228) \ + x(dirent_to_missing_inode, 229) \ + x(dirent_to_missing_subvol, 230) \ + x(dirent_to_itself, 231) \ + x(quota_type_invalid, 232) \ + x(xattr_val_size_too_small, 233) \ + x(xattr_val_size_too_big, 234) \ + x(xattr_invalid_type, 235) \ + x(xattr_name_invalid_chars, 236) \ + x(xattr_in_missing_inode, 237) \ + x(root_subvol_missing, 238) \ + x(root_dir_missing, 239) \ + x(root_inode_not_dir, 240) \ + x(dir_loop, 241) \ + x(hash_table_key_duplicate, 242) \ + x(hash_table_key_wrong_offset, 243) + +enum bch_sb_error_id { +#define x(t, n) BCH_FSCK_ERR_##t = n, + BCH_SB_ERRS() +#undef x + BCH_SB_ERR_MAX +}; + struct bch_sb_error_entry_cpu { u64 id:16, nr:48; diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index fccd25aa3242..22b34a8e4d6e 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -146,6 +146,24 @@ int bch2_subvolume_get(struct btree_trans *trans, unsigned subvol, return bch2_subvolume_get_inlined(trans, subvol, inconsistent_if_not_found, iter_flags, s); } +int bch2_subvol_is_ro_trans(struct btree_trans *trans, u32 subvol) +{ + struct bch_subvolume s; + int ret = bch2_subvolume_get_inlined(trans, subvol, true, 0, &s); + if (ret) + return ret; + + if (BCH_SUBVOLUME_RO(&s)) + return -EROFS; + return 0; +} + +int bch2_subvol_is_ro(struct bch_fs *c, u32 subvol) +{ + return bch2_trans_do(c, NULL, NULL, 0, + bch2_subvol_is_ro_trans(trans, subvol)); +} + int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot, struct bch_subvolume *subvol) { diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h index a1003d30ab0a..a6f56f66e27c 100644 --- a/fs/bcachefs/subvolume.h +++ b/fs/bcachefs/subvolume.h @@ -23,6 +23,9 @@ int bch2_subvolume_get(struct btree_trans *, unsigned, bool, int, struct bch_subvolume *); int bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *); +int bch2_subvol_is_ro_trans(struct btree_trans *, u32); +int bch2_subvol_is_ro(struct bch_fs *, u32); + int bch2_delete_dead_snapshots(struct bch_fs *); void bch2_delete_dead_snapshots_async(struct bch_fs *); diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index f3e12f7979d5..4c98d8cc2a79 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -13,6 +13,7 @@ #include "replicas.h" #include "quota.h" #include "sb-clean.h" +#include "sb-downgrade.h" #include "sb-errors.h" #include "sb-members.h" #include "super-io.h" @@ -264,6 +265,17 @@ struct bch_sb_field *bch2_sb_field_resize_id(struct bch_sb_handle *sb, return f; } +struct bch_sb_field *bch2_sb_field_get_minsize_id(struct bch_sb_handle *sb, + enum bch_sb_field_type type, + unsigned u64s) +{ + struct bch_sb_field *f = bch2_sb_field_get_id(sb->sb, type); + + if (!f || le32_to_cpu(f->u64s) < u64s) + f = bch2_sb_field_resize_id(sb, type, u64s); + return f; +} + /* Superblock validate: */ static int validate_sb_layout(struct bch_sb_layout *layout, struct printbuf *out) @@ -484,6 +496,21 @@ static int bch2_sb_validate(struct bch_sb_handle *disk_sb, struct printbuf *out, /* device open: */ +static unsigned long le_ulong_to_cpu(unsigned long v) +{ + return sizeof(unsigned long) == 8 + ? le64_to_cpu(v) + : le32_to_cpu(v); +} + +static void le_bitvector_to_cpu(unsigned long *dst, unsigned long *src, unsigned nr) +{ + BUG_ON(nr & (BITS_PER_TYPE(long) - 1)); + + for (unsigned i = 0; i < BITS_TO_LONGS(nr); i++) + dst[i] = le_ulong_to_cpu(src[i]); +} + static void bch2_sb_update(struct bch_fs *c) { struct bch_sb *src = c->disk_sb.sb; @@ -512,8 +539,15 @@ static void bch2_sb_update(struct bch_fs *c) c->sb.features = le64_to_cpu(src->features[0]); c->sb.compat = le64_to_cpu(src->compat[0]); + memset(c->sb.errors_silent, 0, sizeof(c->sb.errors_silent)); + + struct bch_sb_field_ext *ext = bch2_sb_field_get(src, ext); + if (ext) + le_bitvector_to_cpu(c->sb.errors_silent, (void *) ext->errors_silent, + sizeof(c->sb.errors_silent) * 8); + for_each_member_device(ca, c, i) { - struct bch_member m = bch2_sb_member_get(src, i); + struct bch_member m = bch2_sb_member_get(src, ca->dev_idx); ca->mi = bch2_mi_to_cpu(&m); } } @@ -906,6 +940,7 @@ int bch2_write_super(struct bch_fs *c) bch2_sb_members_from_cpu(c); bch2_sb_members_cpy_v2_v1(&c->disk_sb); bch2_sb_errors_from_cpu(c); + bch2_sb_downgrade_update(c); for_each_online_member(ca, c, i) bch2_sb_from_fs(c, ca); @@ -1029,8 +1064,10 @@ void __bch2_check_set_feature(struct bch_fs *c, unsigned feat) } /* Downgrade if superblock is at a higher version than currently supported: */ -void bch2_sb_maybe_downgrade(struct bch_fs *c) +bool bch2_check_version_downgrade(struct bch_fs *c) { + bool ret = bcachefs_metadata_version_current < c->sb.version; + lockdep_assert_held(&c->sb_lock); /* @@ -1044,16 +1081,61 @@ void bch2_sb_maybe_downgrade(struct bch_fs *c) if (c->sb.version_min > bcachefs_metadata_version_current) c->disk_sb.sb->version_min = cpu_to_le16(bcachefs_metadata_version_current); c->disk_sb.sb->compat[0] &= cpu_to_le64((1ULL << BCH_COMPAT_NR) - 1); + return ret; } void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version) { lockdep_assert_held(&c->sb_lock); + if (BCH_VERSION_MAJOR(new_version) > + BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version))) + bch2_sb_field_resize(&c->disk_sb, downgrade, 0); + c->disk_sb.sb->version = cpu_to_le16(new_version); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL); } +static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f, + struct printbuf *err) +{ + if (vstruct_bytes(f) < 88) { + prt_printf(err, "field too small (%zu < %u)", vstruct_bytes(f), 88); + return -BCH_ERR_invalid_sb_ext; + } + + return 0; +} + +static void bch2_sb_ext_to_text(struct printbuf *out, struct bch_sb *sb, + struct bch_sb_field *f) +{ + struct bch_sb_field_ext *e = field_to_type(f, ext); + + prt_printf(out, "Recovery passes required:"); + prt_tab(out); + prt_bitflags(out, bch2_recovery_passes, + bch2_recovery_passes_from_stable(le64_to_cpu(e->recovery_passes_required[0]))); + prt_newline(out); + + unsigned long *errors_silent = kmalloc(sizeof(e->errors_silent), GFP_KERNEL); + if (errors_silent) { + le_bitvector_to_cpu(errors_silent, (void *) e->errors_silent, sizeof(e->errors_silent) * 8); + + prt_printf(out, "Errors to silently fix:"); + prt_tab(out); + prt_bitflags_vector(out, bch2_sb_error_strs, errors_silent, sizeof(e->errors_silent) * 8); + prt_newline(out); + + kfree(errors_silent); + } +} + +static const struct bch_sb_field_ops bch_sb_field_ops_ext = { + .validate = bch2_sb_ext_validate, + .to_text = bch2_sb_ext_to_text, +}; + static const struct bch_sb_field_ops *bch2_sb_field_ops[] = { #define x(f, nr) \ [BCH_SB_FIELD_##f] = &bch_sb_field_ops_##f, diff --git a/fs/bcachefs/super-io.h b/fs/bcachefs/super-io.h index f5abd102bff7..e41e5de531a0 100644 --- a/fs/bcachefs/super-io.h +++ b/fs/bcachefs/super-io.h @@ -40,6 +40,16 @@ struct bch_sb_field *bch2_sb_field_resize_id(struct bch_sb_handle *, #define bch2_sb_field_resize(_sb, _name, _u64s) \ field_to_type(bch2_sb_field_resize_id(_sb, BCH_SB_FIELD_##_name, _u64s), _name) +struct bch_sb_field *bch2_sb_field_get_minsize_id(struct bch_sb_handle *, + enum bch_sb_field_type, unsigned); +#define bch2_sb_field_get_minsize(_sb, _name, _u64s) \ + field_to_type(bch2_sb_field_get_minsize_id(_sb, BCH_SB_FIELD_##_name, _u64s), _name) + +#define bch2_sb_field_nr_entries(_f) \ + (_f ? ((bch2_sb_field_bytes(&_f->field) - sizeof(*_f)) / \ + sizeof(_f->entries[0])) \ + : 0) + void bch2_sb_field_delete(struct bch_sb_handle *, enum bch_sb_field_type); extern const char * const bch2_sb_fields[]; @@ -83,7 +93,7 @@ static inline void bch2_check_set_feature(struct bch_fs *c, unsigned feat) __bch2_check_set_feature(c, feat); } -void bch2_sb_maybe_downgrade(struct bch_fs *); +bool bch2_check_version_downgrade(struct bch_fs *); void bch2_sb_upgrade(struct bch_fs *, unsigned); void bch2_sb_field_to_text(struct printbuf *, struct bch_sb *, diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h index 2984b57b2958..b701f7fe0784 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -243,6 +243,7 @@ do { \ #define prt_units_s64(...) bch2_prt_units_s64(__VA_ARGS__) #define prt_string_option(...) bch2_prt_string_option(__VA_ARGS__) #define prt_bitflags(...) bch2_prt_bitflags(__VA_ARGS__) +#define prt_bitflags_vector(...) bch2_prt_bitflags_vector(__VA_ARGS__) void bch2_pr_time_units(struct printbuf *, u64); void bch2_prt_datetime(struct printbuf *, time64_t); diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c index 79d982674c18..5a1858fb9879 100644 --- a/fs/bcachefs/xattr.c +++ b/fs/bcachefs/xattr.c @@ -176,7 +176,8 @@ int bch2_xattr_set(struct btree_trans *trans, subvol_inum inum, struct btree_iter inode_iter = { NULL }; int ret; - ret = bch2_inode_peek(trans, &inode_iter, inode_u, inum, BTREE_ITER_INTENT); + ret = bch2_subvol_is_ro_trans(trans, inum.subvol) ?: + bch2_inode_peek(trans, &inode_iter, inode_u, inum, BTREE_ITER_INTENT); if (ret) return ret; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7cd513e59305..87fed75808ff 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -693,6 +693,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred char *mesg = buf; int fd, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; err = get_int(&mesg, &fd); if (err != 0 || fd < 0) @@ -703,15 +704,15 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); + serv = nn->nfsd_serv; + err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - if (err < 0 && !nn->nfsd_serv->sv_nrthreads && !nn->keep_active) + if (err < 0 && !serv->sv_nrthreads && !nn->keep_active) nfsd_last_thread(net); - else if (err >= 0 && - !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) - svc_get(nn->nfsd_serv); + else if (err >= 0 && !serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(serv); - nfsd_put(net); + svc_put(serv); return err; } @@ -725,6 +726,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr struct svc_xprt *xprt; int port, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; if (sscanf(buf, "%15s %5u", transport, &port) != 2) return -EINVAL; @@ -737,32 +739,33 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr if (err != 0) return err; - err = svc_xprt_create(nn->nfsd_serv, transport, net, + serv = nn->nfsd_serv; + err = svc_xprt_create(serv, transport, net, PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; - err = svc_xprt_create(nn->nfsd_serv, transport, net, + err = svc_xprt_create(serv, transport, net, PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; - if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) - svc_get(nn->nfsd_serv); + if (!serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(serv); - nfsd_put(net); + svc_put(serv); return 0; out_close: - xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port); + xprt = svc_find_xprt(serv, transport, net, PF_INET, port); if (xprt != NULL) { svc_xprt_close(xprt); svc_xprt_put(xprt); } out_err: - if (!nn->nfsd_serv->sv_nrthreads && !nn->keep_active) + if (!serv->sv_nrthreads && !nn->keep_active) nfsd_last_thread(net); - nfsd_put(net); + svc_put(serv); return err; } diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 3286ffacbc56..9ed0e08d16c2 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -113,13 +113,6 @@ int nfsd_pool_stats_open(struct inode *, struct file *); int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_shutdown_threads(struct net *net); -static inline void nfsd_put(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - svc_put(nn->nfsd_serv); -} - bool i_am_nfsd(void); struct nfsdfs_client { diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 55b3ce944022..5e32c79f03a7 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -994,7 +994,6 @@ release_iface(struct kref *ref) struct cifs_server_iface *iface = container_of(ref, struct cifs_server_iface, refcount); - list_del_init(&iface->iface_head); kfree(iface); } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index dd2a1fb65e71..dc9b95ca71e6 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -216,22 +216,29 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, /* If server is a channel, select the primary channel */ pserver = SERVER_IS_CHAN(server) ? server->primary_server : server; + /* + * if the server has been marked for termination, there is a + * chance that the remaining channels all need reconnect. To be + * on the safer side, mark the session and trees for reconnect + * for this scenario. This might cause a few redundant session + * setup and tree connect requests, but it is better than not doing + * a tree connect when needed, and all following requests failing + */ + if (server->terminate) { + mark_smb_session = true; + server = pserver; + } spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { - /* - * if channel has been marked for termination, nothing to do - * for the channel. in fact, we cannot find the channel for the - * server. So safe to exit here - */ - if (server->terminate) - break; - /* check if iface is still active */ - if (!cifs_chan_is_iface_active(ses, server)) + spin_lock(&ses->chan_lock); + if (!cifs_chan_is_iface_active(ses, server)) { + spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, server); + spin_lock(&ses->chan_lock); + } - spin_lock(&ses->chan_lock); if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) { spin_unlock(&ses->chan_lock); continue; diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 66b310208545..14bc745de199 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -595,16 +595,12 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, } /* - * Go through iface_list and do kref_put to remove - * any unused ifaces. ifaces in use will be removed - * when the last user calls a kref_put on it + * Go through iface_list and mark them as inactive */ list_for_each_entry_safe(iface, niface, &ses->iface_list, - iface_head) { + iface_head) iface->is_active = 0; - kref_put(&iface->refcount, release_iface); - ses->iface_count--; - } + spin_unlock(&ses->iface_lock); /* @@ -678,10 +674,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, iface_head) { ret = iface_cmp(iface, &tmp_iface); if (!ret) { - /* just get a ref so that it doesn't get picked/freed */ iface->is_active = 1; - kref_get(&iface->refcount); - ses->iface_count++; spin_unlock(&ses->iface_lock); goto next_iface; } else if (ret < 0) { @@ -748,6 +741,20 @@ next_iface: } out: + /* + * Go through the list again and put the inactive entries + */ + spin_lock(&ses->iface_lock); + list_for_each_entry_safe(iface, niface, &ses->iface_list, + iface_head) { + if (!iface->is_active) { + list_del(&iface->iface_head); + kref_put(&iface->refcount, release_iface); + ses->iface_count--; + } + } + spin_unlock(&ses->iface_lock); + return rc; } @@ -784,9 +791,14 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_ goto out; /* check if iface is still active */ + spin_lock(&ses->chan_lock); pserver = ses->chans[0].server; - if (pserver && !cifs_chan_is_iface_active(ses, pserver)) + if (pserver && !cifs_chan_is_iface_active(ses, pserver)) { + spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, pserver); + spin_lock(&ses->chan_lock); + } + spin_unlock(&ses->chan_lock); out: kfree(out_buf); diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 23bd3d1209df..03dded29a980 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -106,16 +106,25 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; case SMB2_CREATE: { + unsigned short int name_off = + le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); + unsigned short int name_len = + le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); + if (((struct smb2_create_req *)hdr)->CreateContextsLength) { *off = le32_to_cpu(((struct smb2_create_req *) hdr)->CreateContextsOffset); *len = le32_to_cpu(((struct smb2_create_req *) hdr)->CreateContextsLength); - break; + if (!name_len) + break; + + if (name_off + name_len < (u64)*off + *len) + break; } - *off = le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); - *len = le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); + *off = name_off; + *len = name_len; break; } case SMB2_QUERY_INFO: diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 2ccc849a5bda..f0677ea0ec24 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -113,7 +113,14 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, * determined by the parent directory. */ if (dentry->d_inode->i_mode & S_IFDIR) { - update_attr(&ei->attr, iattr); + /* + * The events directory dentry is never freed, unless its + * part of an instance that is deleted. It's attr is the + * default for its child files and directories. + * Do not update it. It's not used for its own mode or ownership + */ + if (!ei->is_events) + update_attr(&ei->attr, iattr); } else { name = dentry->d_name.name; @@ -148,28 +155,93 @@ static const struct file_operations eventfs_file_operations = { .release = eventfs_release, }; +/* Return the evenfs_inode of the "events" directory */ +static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) +{ + struct eventfs_inode *ei; + + mutex_lock(&eventfs_mutex); + do { + /* The parent always has an ei, except for events itself */ + ei = dentry->d_parent->d_fsdata; + + /* + * If the ei is being freed, the ownership of the children + * doesn't matter. + */ + if (ei->is_freed) { + ei = NULL; + break; + } + + dentry = ei->dentry; + } while (!ei->is_events); + mutex_unlock(&eventfs_mutex); + + return ei; +} + static void update_inode_attr(struct dentry *dentry, struct inode *inode, struct eventfs_attr *attr, umode_t mode) { - if (!attr) { - inode->i_mode = mode; + struct eventfs_inode *events_ei = eventfs_find_events(dentry); + + if (!events_ei) + return; + + inode->i_mode = mode; + inode->i_uid = events_ei->attr.uid; + inode->i_gid = events_ei->attr.gid; + + if (!attr) return; - } if (attr->mode & EVENTFS_SAVE_MODE) inode->i_mode = attr->mode & EVENTFS_MODE_MASK; - else - inode->i_mode = mode; if (attr->mode & EVENTFS_SAVE_UID) inode->i_uid = attr->uid; - else - inode->i_uid = d_inode(dentry->d_parent)->i_uid; if (attr->mode & EVENTFS_SAVE_GID) inode->i_gid = attr->gid; - else - inode->i_gid = d_inode(dentry->d_parent)->i_gid; +} + +static void update_gid(struct eventfs_inode *ei, kgid_t gid, int level) +{ + struct eventfs_inode *ei_child; + + /* at most we have events/system/event */ + if (WARN_ON_ONCE(level > 3)) + return; + + ei->attr.gid = gid; + + if (ei->entry_attrs) { + for (int i = 0; i < ei->nr_entries; i++) { + ei->entry_attrs[i].gid = gid; + } + } + + /* + * Only eventfs_inode with dentries are updated, make sure + * all eventfs_inodes are updated. If one of the children + * do not have a dentry, this function must traverse it. + */ + list_for_each_entry_srcu(ei_child, &ei->children, list, + srcu_read_lock_held(&eventfs_srcu)) { + if (!ei_child->dentry) + update_gid(ei_child, gid, level + 1); + } +} + +void eventfs_update_gid(struct dentry *dentry, kgid_t gid) +{ + struct eventfs_inode *ei = dentry->d_fsdata; + int idx; + + idx = srcu_read_lock(&eventfs_srcu); + update_gid(ei, gid, 0); + srcu_read_unlock(&eventfs_srcu, idx); } /** @@ -860,6 +932,8 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry struct eventfs_inode *ei; struct tracefs_inode *ti; struct inode *inode; + kuid_t uid; + kgid_t gid; if (security_locked_down(LOCKDOWN_TRACEFS)) return NULL; @@ -884,11 +958,20 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry ei->dentry = dentry; ei->entries = entries; ei->nr_entries = size; + ei->is_events = 1; ei->data = data; ei->name = kstrdup_const(name, GFP_KERNEL); if (!ei->name) goto fail; + /* Save the ownership of this directory */ + uid = d_inode(dentry->d_parent)->i_uid; + gid = d_inode(dentry->d_parent)->i_gid; + + /* This is used as the default ownership of the files and directories */ + ei->attr.uid = uid; + ei->attr.gid = gid; + INIT_LIST_HEAD(&ei->children); INIT_LIST_HEAD(&ei->list); @@ -897,6 +980,8 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry ti->private = ei; inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + inode->i_uid = uid; + inode->i_gid = gid; inode->i_op = &eventfs_root_dir_inode_operations; inode->i_fop = &eventfs_file_operations; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index ae648deed019..bc86ffdb103b 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -210,14 +210,24 @@ repeat: next = this_parent->d_subdirs.next; resume: while (next != &this_parent->d_subdirs) { + struct tracefs_inode *ti; struct list_head *tmp = next; struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; + /* Note, getdents() can add a cursor dentry with no inode */ + if (!dentry->d_inode) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); change_gid(dentry, gid); + /* If this is the events directory, update that too */ + ti = get_tracefs(dentry->d_inode); + if (ti && (ti->flags & TRACEFS_EVENT_INODE)) + eventfs_update_gid(dentry, gid); + if (!list_empty(&dentry->d_subdirs)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index ccee18ca66c7..42bdeb471a07 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -62,7 +62,8 @@ struct eventfs_inode { struct rcu_head rcu; }; unsigned int is_freed:1; - unsigned int nr_entries:31; + unsigned int is_events:1; + unsigned int nr_entries:30; }; static inline struct tracefs_inode *get_tracefs(const struct inode *inode) @@ -77,6 +78,7 @@ struct inode *tracefs_get_inode(struct super_block *sb); struct dentry *eventfs_start_creating(const char *name, struct dentry *parent); struct dentry *eventfs_failed_creating(struct dentry *dentry); struct dentry *eventfs_end_creating(struct dentry *dentry); +void eventfs_update_gid(struct dentry *dentry, kgid_t gid); void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry); #endif /* _TRACEFS_INTERNAL_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 51fa7ffdee83..88e9dd4b71fb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -538,7 +538,7 @@ struct request_queue { #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ -#define QUEUE_FLAG_HW_WC 18 /* Write back caching supported */ +#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index 69501e0ec239..d445705ac13c 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -16,10 +16,13 @@ * and eliminates the need for absolute relocations that require runtime * processing on relocatable kernels. */ +#define __KSYM_ALIGN ".balign 4" #define __KSYM_REF(sym) ".long " #sym "- ." #elif defined(CONFIG_64BIT) +#define __KSYM_ALIGN ".balign 8" #define __KSYM_REF(sym) ".quad " #sym #else +#define __KSYM_ALIGN ".balign 4" #define __KSYM_REF(sym) ".long " #sym #endif @@ -42,7 +45,7 @@ " .asciz \"" ns "\"" "\n" \ " .previous" "\n" \ " .section \"___ksymtab" sec "+" #name "\", \"a\"" "\n" \ - " .balign 4" "\n" \ + __KSYM_ALIGN "\n" \ "__ksymtab_" #name ":" "\n" \ __KSYM_REF(sym) "\n" \ __KSYM_REF(__kstrtab_ ##name) "\n" \ @@ -61,6 +64,7 @@ #define SYMBOL_CRC(sym, crc, sec) \ asm(".section \"___kcrctab" sec "+" #sym "\",\"a\"" "\n" \ + ".balign 4" "\n" \ "__crc_" #sym ":" "\n" \ ".long " #crc "\n" \ ".previous" "\n") diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 5581dbd3bd34..ea8fb31379e3 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -6,11 +6,6 @@ * An MCS like lock especially tailored for optimistic spinning for sleeping * lock implementations (mutex, rwsem, etc). */ -struct optimistic_spin_node { - struct optimistic_spin_node *next, *prev; - int locked; /* 1 if lock acquired */ - int cpu; /* encoded CPU # + 1 value */ -}; struct optimistic_spin_queue { /* diff --git a/include/linux/phy.h b/include/linux/phy.h index 3cc52826f18e..bd285950972c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -568,7 +568,6 @@ struct macsec_ops; * - Bits [31:24] are reserved for defining generic * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) - * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached * @sfp_bus: SFP bus attached to this PHY's fiber port diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 947973623dc7..60a7d0ce3080 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -30,7 +30,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) return -1; len = iph_totlen(pkt->skb, iph); - thoff = iph->ihl * 4; + thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4); if (pkt->skb->len < len) return -1; else if (len < thoff) diff --git a/include/net/tcp.h b/include/net/tcp.h index 144ba48bb07b..87f0e6c2e1f2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1788,8 +1788,6 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG -#include <linux/jump_label.h> -extern struct static_key_false_deferred tcp_md5_needed; struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family, bool any_l3index); diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 647781080613..b04afced4cc9 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -127,12 +127,35 @@ struct tcp_ao_info { struct rcu_head rcu; }; +#ifdef CONFIG_TCP_MD5SIG +#include <linux/jump_label.h> +extern struct static_key_false_deferred tcp_md5_needed; +#define static_branch_tcp_md5() static_branch_unlikely(&tcp_md5_needed.key) +#else +#define static_branch_tcp_md5() false +#endif +#ifdef CONFIG_TCP_AO +/* TCP-AO structures and functions */ +#include <linux/jump_label.h> +extern struct static_key_false_deferred tcp_ao_needed; +#define static_branch_tcp_ao() static_branch_unlikely(&tcp_ao_needed.key) +#else +#define static_branch_tcp_ao() false +#endif + +static inline bool tcp_hash_should_produce_warnings(void) +{ + return static_branch_tcp_md5() || static_branch_tcp_ao(); +} + #define tcp_hash_fail(msg, family, skb, fmt, ...) \ do { \ const struct tcphdr *th = tcp_hdr(skb); \ char hdr_flags[6]; \ char *f = hdr_flags; \ \ + if (!tcp_hash_should_produce_warnings()) \ + break; \ if (th->fin) \ *f++ = 'F'; \ if (th->syn) \ @@ -159,9 +182,6 @@ do { \ #ifdef CONFIG_TCP_AO /* TCP-AO structures and functions */ -#include <linux/jump_label.h> -extern struct static_key_false_deferred tcp_ao_needed; - struct tcp4_ao_context { __be32 saddr; __be32 daddr; diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 2fd510256604..946dffa048b7 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -36,6 +36,8 @@ config KEXEC config KEXEC_FILE bool "Enable kexec file based system call" depends on ARCH_SUPPORTS_KEXEC_FILE + select CRYPTO + select CRYPTO_SHA256 select KEXEC_CORE help This is new version of kexec system call. This system call is diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index d5610ad52b92..75a6f6133866 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -11,6 +11,13 @@ * called from interrupt context and we have preemption disabled while * spinning. */ + +struct optimistic_spin_node { + struct optimistic_spin_node *next, *prev; + int locked; /* 1 if lock acquired */ + int cpu; /* encoded CPU # + 1 value */ +}; + static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node); /* @@ -37,32 +44,28 @@ static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val) /* * Get a stable @node->next pointer, either for unlock() or unqueue() purposes. * Can return NULL in case we were the last queued and we updated @lock instead. + * + * If osq_lock() is being cancelled there must be a previous node + * and 'old_cpu' is its CPU #. + * For osq_unlock() there is never a previous node and old_cpu is + * set to OSQ_UNLOCKED_VAL. */ static inline struct optimistic_spin_node * osq_wait_next(struct optimistic_spin_queue *lock, struct optimistic_spin_node *node, - struct optimistic_spin_node *prev) + int old_cpu) { - struct optimistic_spin_node *next = NULL; int curr = encode_cpu(smp_processor_id()); - int old; - - /* - * If there is a prev node in queue, then the 'old' value will be - * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if - * we're currently last in queue, then the queue will then become empty. - */ - old = prev ? prev->cpu : OSQ_UNLOCKED_VAL; for (;;) { if (atomic_read(&lock->tail) == curr && - atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) { + atomic_cmpxchg_acquire(&lock->tail, curr, old_cpu) == curr) { /* * We were the last queued, we moved @lock back. @prev * will now observe @lock and will complete its * unlock()/unqueue(). */ - break; + return NULL; } /* @@ -76,15 +79,15 @@ osq_wait_next(struct optimistic_spin_queue *lock, * wait for a new @node->next from its Step-C. */ if (node->next) { + struct optimistic_spin_node *next; + next = xchg(&node->next, NULL); if (next) - break; + return next; } cpu_relax(); } - - return next; } bool osq_lock(struct optimistic_spin_queue *lock) @@ -186,7 +189,7 @@ bool osq_lock(struct optimistic_spin_queue *lock) * back to @prev. */ - next = osq_wait_next(lock, node, prev); + next = osq_wait_next(lock, node, prev->cpu); if (!next) return false; @@ -226,7 +229,7 @@ void osq_unlock(struct optimistic_spin_queue *lock) return; } - next = osq_wait_next(lock, node, NULL); + next = osq_wait_next(lock, node, OSQ_UNLOCKED_VAL); if (next) WRITE_ONCE(next->locked, 1); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8de8bec5f366..b01ae7d36021 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1183,18 +1183,19 @@ static void __add_hash_entry(struct ftrace_hash *hash, hash->count++; } -static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +static struct ftrace_func_entry * +add_hash_entry(struct ftrace_hash *hash, unsigned long ip) { struct ftrace_func_entry *entry; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) - return -ENOMEM; + return NULL; entry->ip = ip; __add_hash_entry(hash, entry); - return 0; + return entry; } static void @@ -1349,7 +1350,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) struct ftrace_func_entry *entry; struct ftrace_hash *new_hash; int size; - int ret; int i; new_hash = alloc_ftrace_hash(size_bits); @@ -1366,8 +1366,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(entry, &hash->buckets[i], hlist) { - ret = add_hash_entry(new_hash, entry->ip); - if (ret < 0) + if (add_hash_entry(new_hash, entry->ip) == NULL) goto free_hash; } } @@ -2536,7 +2535,7 @@ ftrace_find_unique_ops(struct dyn_ftrace *rec) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* Protected by rcu_tasks for reading, and direct_mutex for writing */ -static struct ftrace_hash *direct_functions = EMPTY_HASH; +static struct ftrace_hash __rcu *direct_functions = EMPTY_HASH; static DEFINE_MUTEX(direct_mutex); int ftrace_direct_func_count; @@ -2555,39 +2554,6 @@ unsigned long ftrace_find_rec_direct(unsigned long ip) return entry->direct; } -static struct ftrace_func_entry* -ftrace_add_rec_direct(unsigned long ip, unsigned long addr, - struct ftrace_hash **free_hash) -{ - struct ftrace_func_entry *entry; - - if (ftrace_hash_empty(direct_functions) || - direct_functions->count > 2 * (1 << direct_functions->size_bits)) { - struct ftrace_hash *new_hash; - int size = ftrace_hash_empty(direct_functions) ? 0 : - direct_functions->count + 1; - - if (size < 32) - size = 32; - - new_hash = dup_hash(direct_functions, size); - if (!new_hash) - return NULL; - - *free_hash = direct_functions; - direct_functions = new_hash; - } - - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return NULL; - - entry->ip = ip; - entry->direct = addr; - __add_hash_entry(direct_functions, entry); - return entry; -} - static void call_direct_funcs(unsigned long ip, unsigned long pip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { @@ -4223,8 +4189,8 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int clear_filter) /* Do nothing if it exists */ if (entry) return 0; - - ret = add_hash_entry(hash, rec->ip); + if (add_hash_entry(hash, rec->ip) == NULL) + ret = -ENOMEM; } return ret; } @@ -5266,7 +5232,8 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return 0; } - return add_hash_entry(hash, ip); + entry = add_hash_entry(hash, ip); + return entry ? 0 : -ENOMEM; } static int @@ -5410,7 +5377,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long */ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) { - struct ftrace_hash *hash, *free_hash = NULL; + struct ftrace_hash *hash, *new_hash = NULL, *free_hash = NULL; struct ftrace_func_entry *entry, *new; int err = -EBUSY, size, i; @@ -5436,17 +5403,44 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) } } - /* ... and insert them to direct_functions hash. */ err = -ENOMEM; + + /* Make a copy hash to place the new and the old entries in */ + size = hash->count + direct_functions->count; + if (size > 32) + size = 32; + new_hash = alloc_ftrace_hash(fls(size)); + if (!new_hash) + goto out_unlock; + + /* Now copy over the existing direct entries */ + size = 1 << direct_functions->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &direct_functions->buckets[i], hlist) { + new = add_hash_entry(new_hash, entry->ip); + if (!new) + goto out_unlock; + new->direct = entry->direct; + } + } + + /* ... and add the new entries */ + size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(entry, &hash->buckets[i], hlist) { - new = ftrace_add_rec_direct(entry->ip, addr, &free_hash); + new = add_hash_entry(new_hash, entry->ip); if (!new) - goto out_remove; + goto out_unlock; + /* Update both the copy and the hash entry */ + new->direct = addr; entry->direct = addr; } } + free_hash = direct_functions; + rcu_assign_pointer(direct_functions, new_hash); + new_hash = NULL; + ops->func = call_direct_funcs; ops->flags = MULTI_FLAGS; ops->trampoline = FTRACE_REGS_ADDR; @@ -5454,17 +5448,17 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) err = register_ftrace_function_nolock(ops); - out_remove: - if (err) - remove_direct_functions_hash(hash, addr); - out_unlock: mutex_unlock(&direct_mutex); - if (free_hash) { + if (free_hash && free_hash != EMPTY_HASH) { synchronize_rcu_tasks(); free_ftrace_hash(free_hash); } + + if (new_hash) + free_ftrace_hash(new_hash); + return err; } EXPORT_SYMBOL_GPL(register_ftrace_direct); @@ -6309,7 +6303,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer) if (entry) continue; - if (add_hash_entry(hash, rec->ip) < 0) + if (add_hash_entry(hash, rec->ip) == NULL) goto out; } else { if (entry) { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 83eab547f1d1..9286f88fcd32 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -881,9 +881,14 @@ static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int f if (!nr_pages || !full) return true; - dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + /* + * Add one as dirty will never equal nr_pages, as the sub-buffer + * that the writer is on is not counted as dirty. + * This is needed if "buffer_percent" is set to 100. + */ + dirty = ring_buffer_nr_dirty_pages(buffer, cpu) + 1; - return (dirty * 100) > (full * nr_pages); + return (dirty * 100) >= (full * nr_pages); } /* @@ -944,7 +949,8 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) /* make sure the waiters see the new index */ smp_wmb(); - rb_wake_up_waiters(&rbwork->work); + /* This can be called in any context */ + irq_work_queue(&rbwork->work); } /** diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 199df497db07..a0defe156b57 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1894,6 +1894,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); + + /* Any waiters on the old snapshot buffer need to wake up */ + ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS); } /** @@ -1945,12 +1948,23 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) static int wait_on_pipe(struct trace_iterator *iter, int full) { + int ret; + /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, - full); + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + +#ifdef CONFIG_TRACER_MAX_TRACE + /* + * Make sure this is still the snapshot buffer, as if a snapshot were + * to happen, this would now be the main buffer. + */ + if (iter->snapshot) + iter->array_buffer = &iter->tr->max_buffer; +#endif + return ret; } #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -8517,7 +8531,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->tr->buffer_percent); + ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; diff --git a/lib/maple_tree.c b/lib/maple_tree.c index bb24d84a4922..684689457d77 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5501,6 +5501,17 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) mas_wr_end_piv(&wr_mas); node_size = mas_wr_new_end(&wr_mas); + + /* Slot store, does not require additional nodes */ + if (node_size == wr_mas.node_end) { + /* reuse node */ + if (!mt_in_rcu(mas->tree)) + return 0; + /* shifting boundary */ + if (wr_mas.offset_end - mas->offset == 1) + return 0; + } + if (node_size >= mt_slots[wr_mas.type]) { /* Split, worst case for now. */ request = 1 + mas_mt_height(mas) * 2; diff --git a/mm/filemap.c b/mm/filemap.c index f1c8c278310f..ad5b4aa049a3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2608,6 +2608,15 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* + * Pairs with a barrier in + * block_write_end()->mark_buffer_dirty() or other page + * dirtying routines like iomap_write_end() to ensure + * changes to page contents are visible before we see + * increased inode size. + */ + smp_rmb(); + + /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4f542444a91f..86ee29b5c39c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2823,7 +2823,7 @@ void folio_undo_large_rmappable(struct folio *folio) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - list_del(&folio->_deferred_list); + list_del_init(&folio->_deferred_list); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index 8281eb42464b..34515a106ca5 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -493,14 +493,17 @@ static void kmalloc_oob_memset_2(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 2; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, 2)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 1, 0, memset_size)); kfree(ptr); } @@ -508,14 +511,17 @@ static void kmalloc_oob_memset_4(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 4; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, 4)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 3, 0, memset_size)); kfree(ptr); } @@ -523,14 +529,17 @@ static void kmalloc_oob_memset_8(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 8; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, 8)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 7, 0, memset_size)); kfree(ptr); } @@ -538,14 +547,17 @@ static void kmalloc_oob_memset_16(struct kunit *test) { char *ptr; size_t size = 128 - KASAN_GRANULE_SIZE; + size_t memset_size = 16; KASAN_TEST_NEEDS_CHECKED_MEMINTRINSICS(test); ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); - KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, 16)); + OPTIMIZER_HIDE_VAR(memset_size); + KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr + size - 15, 0, memset_size)); kfree(ptr); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b226090fd906..651b86ff03dd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7543,6 +7543,17 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new) /* Transfer the charge and the css ref */ commit_charge(new, memcg); + /* + * If the old folio is a large folio and is in the split queue, it needs + * to be removed from the split queue now, in case getting an incorrect + * split queue in destroy_large_folio() after the memcg of the old folio + * is cleared. + * + * In addition, the old folio is about to be freed after migration, so + * removing from the split queue a bit earlier seems reasonable. + */ + if (folio_test_large(old) && folio_test_large_rmappable(old)) + folio_undo_large_rmappable(old); old->memcg_data = 0; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 660c21859118..455093f73a70 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -595,10 +595,9 @@ struct task_struct *task_early_kill(struct task_struct *tsk, int force_early) /* * Collect processes when the error hit an anonymous page. */ -static void collect_procs_anon(struct page *page, struct list_head *to_kill, - int force_early) +static void collect_procs_anon(struct folio *folio, struct page *page, + struct list_head *to_kill, int force_early) { - struct folio *folio = page_folio(page); struct vm_area_struct *vma; struct task_struct *tsk; struct anon_vma *av; @@ -633,12 +632,12 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, /* * Collect processes when the error hit a file mapped page. */ -static void collect_procs_file(struct page *page, struct list_head *to_kill, - int force_early) +static void collect_procs_file(struct folio *folio, struct page *page, + struct list_head *to_kill, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; pgoff_t pgoff; i_mmap_lock_read(mapping); @@ -704,17 +703,17 @@ static void collect_procs_fsdax(struct page *page, /* * Collect the processes who have the corrupted page mapped to kill. */ -static void collect_procs(struct page *page, struct list_head *tokill, - int force_early) +static void collect_procs(struct folio *folio, struct page *page, + struct list_head *tokill, int force_early) { - if (!page->mapping) + if (!folio->mapping) return; if (unlikely(PageKsm(page))) collect_procs_ksm(page, tokill, force_early); else if (PageAnon(page)) - collect_procs_anon(page, tokill, force_early); + collect_procs_anon(folio, page, tokill, force_early); else - collect_procs_file(page, tokill, force_early); + collect_procs_file(folio, page, tokill, force_early); } struct hwpoison_walk { @@ -1571,7 +1570,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ - if (!page_mapped(hpage)) + if (!page_mapped(p)) return true; if (PageSwapCache(p)) { @@ -1602,7 +1601,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * mapped in dirty form. This has to be done before try_to_unmap, * because ttu takes the rmap data structures down. */ - collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); + collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); if (PageHuge(hpage) && !PageAnon(hpage)) { /* @@ -1622,10 +1621,10 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, try_to_unmap(folio, ttu); } - unmap_success = !page_mapped(hpage); + unmap_success = !page_mapped(p); if (!unmap_success) pr_err("%#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(p)); /* * try_to_unmap() might put mlocked page in lru cache, so call @@ -1705,7 +1704,7 @@ static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn, * mapping being torn down is communicated in siginfo, see * kill_proc() */ - loff_t start = (index << PAGE_SHIFT) & ~(size - 1); + loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1); unmap_mapping_range(mapping, start, size, 0); } @@ -1772,7 +1771,7 @@ static int mf_generic_kill_procs(unsigned long long pfn, int flags, * SIGBUS (i.e. MF_MUST_KILL) */ flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; - collect_procs(&folio->page, &to_kill, true); + collect_procs(folio, &folio->page, &to_kill, true); unmap_and_kill(&to_kill, pfn, folio->mapping, folio->index, flags); unlock: diff --git a/mm/memory.c b/mm/memory.c index 5c757fba8858..6e0712d06cd4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3624,8 +3624,8 @@ EXPORT_SYMBOL_GPL(unmap_mapping_pages); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { - pgoff_t hba = holebegin >> PAGE_SHIFT; - pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; + pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { diff --git a/mm/migrate.c b/mm/migrate.c index 35a88334bb3c..397f2a6e34cb 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -405,6 +405,7 @@ int folio_migrate_mapping(struct address_space *mapping, int dirty; int expected_count = folio_expected_refs(mapping, folio) + extra_count; long nr = folio_nr_pages(folio); + long entries, i; if (!mapping) { /* Anonymous page without mapping */ @@ -442,8 +443,10 @@ int folio_migrate_mapping(struct address_space *mapping, folio_set_swapcache(newfolio); newfolio->private = folio_get_private(folio); } + entries = nr; } else { VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); + entries = 1; } /* Move dirty while page refs frozen and newpage not yet exposed */ @@ -453,7 +456,11 @@ int folio_migrate_mapping(struct address_space *mapping, folio_set_dirty(newfolio); } - xas_store(&xas, newfolio); + /* Swap cache still stores N entries instead of a high-order entry */ + for (i = 0; i < entries; i++) { + xas_store(&xas, newfolio); + xas_next(&xas); + } /* * Drop cache reference from old page by unfreezing diff --git a/mm/mmap.c b/mm/mmap.c index 1971bfffcc03..aa82eec17489 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1829,6 +1829,9 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, */ pgoff = 0; get_area = shmem_get_unmapped_area; + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + /* Ensures that larger anonymous mappings are THP aligned. */ + get_area = thp_get_unmapped_area; } addr = get_area(file, addr, len, pgoff, flags); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ee2fd6a6af40..05e5c425b3ff 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -692,7 +692,6 @@ static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ra if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; - min_ratio *= BDI_RATIO_SCALE; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { @@ -729,7 +728,8 @@ static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ra ret = -EINVAL; } else { bdi->max_ratio = max_ratio; - bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100; + bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / + (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); diff --git a/mm/shrinker.c b/mm/shrinker.c index dd91eab43ed3..dc5d2a6fcfc4 100644 --- a/mm/shrinker.c +++ b/mm/shrinker.c @@ -126,7 +126,7 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size, if (new_nr_max <= old->map_nr_max) continue; - new = kvmalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid); + new = kvzalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid); if (!new) return -ENOMEM; diff --git a/mm/vmscan.c b/mm/vmscan.c index 9dd8977de5a2..bba207f41b14 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3955,6 +3955,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) int young = 0; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; + struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); bool can_swap = !folio_is_file_lru(folio); struct mem_cgroup *memcg = folio_memcg(folio); @@ -3969,11 +3970,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) if (spin_is_contended(pvmw->ptl)) return; + /* exclude special VMAs containing anon pages from COW */ + if (vma->vm_flags & VM_SPECIAL) + return; + /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; - start = max(addr & PMD_MASK, pvmw->vma->vm_start); - end = min(addr | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1; + start = max(addr & PMD_MASK, vma->vm_start); + end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) @@ -3998,7 +4003,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) unsigned long pfn; pte_t ptent = ptep_get(pte + i); - pfn = get_pte_pfn(ptent, pvmw->vma, addr); + pfn = get_pte_pfn(ptent, vma, addr); if (pfn == -1) continue; @@ -4009,7 +4014,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) if (!folio) continue; - if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i)) + if (!ptep_test_and_clear_young(vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; diff --git a/net/core/sock.c b/net/core/sock.c index fef349dd72fa..d02534c77413 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1711,9 +1711,16 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: lv = sizeof(v.timestamping); - v.timestamping.flags = READ_ONCE(sk->sk_tsflags); - v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); + /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only + * returning the flags when they were set through the same option. + * Don't change the beviour for the old case SO_TIMESTAMPING_OLD. + */ + if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) { + v.timestamping.flags = READ_ONCE(sk->sk_tsflags); + v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); + } break; case SO_RCVTIMEO_OLD: @@ -2806,6 +2813,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 2a6d363763a2..f18ca02aa95a 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -91,8 +91,6 @@ const struct cred *dns_resolver_cache; static int dns_resolver_preparse(struct key_preparsed_payload *prep) { - const struct dns_server_list_v1_header *v1; - const struct dns_payload_header *bin; struct user_key_payload *upayload; unsigned long derrno; int ret; @@ -103,27 +101,28 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) return -EINVAL; if (data[0] == 0) { + const struct dns_server_list_v1_header *v1; + /* It may be a server list. */ - if (datalen <= sizeof(*bin)) + if (datalen <= sizeof(*v1)) return -EINVAL; - bin = (const struct dns_payload_header *)data; - kenter("[%u,%u],%u", bin->content, bin->version, datalen); - if (bin->content != DNS_PAYLOAD_IS_SERVER_LIST) { + v1 = (const struct dns_server_list_v1_header *)data; + kenter("[%u,%u],%u", v1->hdr.content, v1->hdr.version, datalen); + if (v1->hdr.content != DNS_PAYLOAD_IS_SERVER_LIST) { pr_warn_ratelimited( "dns_resolver: Unsupported content type (%u)\n", - bin->content); + v1->hdr.content); return -EINVAL; } - if (bin->version != 1) { + if (v1->hdr.version != 1) { pr_warn_ratelimited( "dns_resolver: Unsupported server list version (%u)\n", - bin->version); + v1->hdr.version); return -EINVAL; } - v1 = (const struct dns_server_list_v1_header *)bin; if ((v1->status != DNS_LOOKUP_GOOD && v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) { if (prep->expiry == TIME64_MAX) diff --git a/net/ipv4/tcp_sigpool.c b/net/ipv4/tcp_sigpool.c index 55b310a722c7..8512cb09ebc0 100644 --- a/net/ipv4/tcp_sigpool.c +++ b/net/ipv4/tcp_sigpool.c @@ -162,9 +162,8 @@ int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size) if (strcmp(cpool[i].alg, alg)) continue; - if (kref_read(&cpool[i].kref) > 0) - kref_get(&cpool[i].kref); - else + /* pairs with tcp_sigpool_release() */ + if (!kref_get_unless_zero(&cpool[i].kref)) kref_init(&cpool[i].kref); ret = i; goto out; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2692a7b24c40..733ace18806c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1407,23 +1407,15 @@ retry: write_unlock_bh(&idev->lock); - /* From RFC 4941: - * - * A temporary address is created only if this calculated Preferred - * Lifetime is greater than REGEN_ADVANCE time units. In - * particular, an implementation must not create a temporary address - * with a zero Preferred Lifetime. - * - * Clamp the preferred lifetime to a minimum of regen_advance, unless - * that would exceed valid_lft. - * + /* A temporary address is created only if this calculated Preferred + * Lifetime is greater than REGEN_ADVANCE time units. In particular, + * an implementation must not create a temporary address with a zero + * Preferred Lifetime. * Use age calculation as in addrconf_verify to avoid unnecessary * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (cfg.preferred_lft <= regen_advance + age) - cfg.preferred_lft = regen_advance + age + 1; - if (cfg.preferred_lft > cfg.valid_lft) { + if (cfg.preferred_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 80aeb25f1b68..dce5606ed66d 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -1043,9 +1043,12 @@ void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata, { ieee80211_debugfs_remove_netdev(sdata); ieee80211_debugfs_add_netdev(sdata, mld_vif); - drv_vif_add_debugfs(sdata->local, sdata); - if (!mld_vif) - ieee80211_link_debugfs_drv_add(&sdata->deflink); + + if (sdata->flags & IEEE80211_SDATA_IN_DRIVER) { + drv_vif_add_debugfs(sdata->local, sdata); + if (!mld_vif) + ieee80211_link_debugfs_drv_add(&sdata->deflink); + } } void ieee80211_link_debugfs_add(struct ieee80211_link_data *link) diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index d3820333cd59..3b7f70073fc3 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -75,9 +75,9 @@ int drv_add_interface(struct ieee80211_local *local, if (ret) return ret; - sdata->flags |= IEEE80211_SDATA_IN_DRIVER; + if (!(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) { + sdata->flags |= IEEE80211_SDATA_IN_DRIVER; - if (!local->in_reconfig) { drv_vif_add_debugfs(local, sdata); /* initially vif is not MLD */ ieee80211_link_debugfs_drv_add(&sdata->deflink); @@ -113,9 +113,13 @@ void drv_remove_interface(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return; + sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER; + + /* Remove driver debugfs entries */ + ieee80211_debugfs_recreate_netdev(sdata, sdata->vif.valid_links); + trace_drv_remove_interface(local, sdata); local->ops->remove_interface(&local->hw, &sdata->vif); - sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER; trace_drv_return_void(local); } @@ -534,7 +538,7 @@ int drv_change_vif_links(struct ieee80211_local *local, if (ret) return ret; - if (!local->in_reconfig) { + if (!local->in_reconfig && !local->resuming) { for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) { link = rcu_access_pointer(sdata->link[link_id]); @@ -590,7 +594,7 @@ int drv_change_sta_links(struct ieee80211_local *local, return ret; /* during reconfig don't add it to debugfs again */ - if (local->in_reconfig) + if (local->in_reconfig || local->resuming) return 0; for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 6d7684c35e93..852b3f4af000 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1982,6 +1982,17 @@ static void tcp_release_cb_override(struct sock *ssk) tcp_release_cb(ssk); } +static int tcp_abort_override(struct sock *ssk, int err) +{ + /* closing a listener subflow requires a great deal of care. + * keep it simple and just prevent such operation + */ + if (inet_sk_state_load(ssk) == TCP_LISTEN) + return -EINVAL; + + return tcp_abort(ssk, err); +} + static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { .name = "mptcp", .owner = THIS_MODULE, @@ -2026,6 +2037,7 @@ void __init mptcp_subflow_init(void) tcp_prot_override = tcp_prot; tcp_prot_override.release_cb = tcp_release_cb_override; + tcp_prot_override.diag_destroy = tcp_abort_override; #if IS_ENABLED(CONFIG_MPTCP_IPV6) /* In struct mptcp_subflow_request_sock, we assume the TCP request sock @@ -2061,6 +2073,7 @@ void __init mptcp_subflow_init(void) tcpv6_prot_override = tcpv6_prot; tcpv6_prot_override.release_cb = tcp_release_cb_override; + tcpv6_prot_override.diag_destroy = tcp_abort_override; #endif mptcp_diag_subflow_init(&subflow_ulp_ops); diff --git a/net/netfilter/nf_nat_ovs.c b/net/netfilter/nf_nat_ovs.c index 551abd2da614..0f9a559f6207 100644 --- a/net/netfilter/nf_nat_ovs.c +++ b/net/netfilter/nf_nat_ovs.c @@ -75,9 +75,10 @@ static int nf_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, } err = nf_nat_packet(ct, ctinfo, hooknum, skb); +out: if (err == NF_ACCEPT) *action |= BIT(maniptype); -out: + return err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c5c17c6e80ed..be04af433988 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9887,7 +9887,7 @@ static void nft_set_commit_update(struct list_head *set_update_list) list_for_each_entry_safe(set, next, set_update_list, pending_update) { list_del_init(&set->pending_update); - if (!set->ops->commit) + if (!set->ops->commit || set->dead) continue; set->ops->commit(set); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 8b536d7ef6c2..c3e635364701 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -158,7 +158,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, else { if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) return false; - ptr = skb_network_header(skb) + nft_thoff(pkt); + ptr = skb->data + nft_thoff(pkt); } ptr += priv->offset; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index fccb3cf7749c..6475c7abc1fe 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -78,7 +78,7 @@ static int nft_immediate_init(const struct nft_ctx *ctx, case NFT_GOTO: err = nf_tables_bind_chain(ctx, chain); if (err < 0) - return err; + goto err1; break; default: break; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 1dac28136e6a..18be13fb9b75 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -145,6 +145,13 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { + /* Since using nfc_llcp_local may result in usage of nfc_dev, whenever + * we hold a reference to local, we also need to hold a reference to + * the device to avoid UAF. + */ + if (!nfc_get_device(local->dev->idx)) + return NULL; + kref_get(&local->ref); return local; @@ -177,10 +184,18 @@ static void local_release(struct kref *ref) int nfc_llcp_local_put(struct nfc_llcp_local *local) { + struct nfc_dev *dev; + int ret; + if (local == NULL) return 0; - return kref_put(&local->ref, local_release); + dev = local->dev; + + ret = kref_put(&local->ref, local_release); + nfc_put_device(dev); + + return ret; } static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, @@ -959,8 +974,17 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, } new_sock = nfc_llcp_sock(new_sk); - new_sock->dev = local->dev; + new_sock->local = nfc_llcp_local_get(local); + if (!new_sock->local) { + reason = LLCP_DM_REJ; + sock_put(&new_sock->sk); + release_sock(&sock->sk); + sock_put(&sock->sk); + goto fail; + } + + new_sock->dev = local->dev; new_sock->rw = sock->rw; new_sock->miux = sock->miux; new_sock->nfc_protocol = sock->nfc_protocol; @@ -1597,7 +1621,16 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) if (local == NULL) return -ENOMEM; - local->dev = ndev; + /* As we are going to initialize local's refcount, we need to get the + * nfc_dev to avoid UAF, otherwise there is no point in continuing. + * See nfc_llcp_local_get(). + */ + local->dev = nfc_get_device(ndev->idx); + if (!local->dev) { + kfree(local); + return -ENODEV; + } + INIT_LIST_HEAD(&local->list); kref_init(&local->ref); mutex_init(&local->sdp_lock); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 645677f84dba..819157bbb5a2 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -796,6 +796,11 @@ static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg, } if (sk->sk_type == SOCK_DGRAM) { + if (sk->sk_state != LLCP_BOUND) { + release_sock(sk); + return -ENOTCONN; + } + DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, addr, msg->msg_name); diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index b1db0b519179..abb0c70ffc8b 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -512,7 +512,9 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, if (!node) return -ENOENT; - return server_del(node, port, true); + server_del(node, port, true); + + return 0; } static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 6f3c1fb2fb44..f176afb70559 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -97,8 +97,10 @@ retry: static void em_text_destroy(struct tcf_ematch *m) { - if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) + if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) { textsearch_destroy(EM_TEXT_PRIV(m)->config); + kfree(EM_TEXT_PRIV(m)); + } } static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index a584613aca12..5cc376834c57 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -153,8 +153,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, .lnk[0].link_id = link->link_id, }; - memcpy(linfo.lnk[0].ibname, - smc->conn.lgr->lnk[0].smcibdev->ibdev->name, + memcpy(linfo.lnk[0].ibname, link->smcibdev->ibdev->name, sizeof(link->smcibdev->ibdev->name)); smc_gid_be16_convert(linfo.lnk[0].gid, link->gid); smc_gid_be16_convert(linfo.lnk[0].peer_gid, link->peer_gid); diff --git a/net/socket.c b/net/socket.c index 3379c64217a4..89d79205bf50 100644 --- a/net/socket.c +++ b/net/socket.c @@ -757,6 +757,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; struct sockaddr_storage address; + int save_len = msg->msg_namelen; int ret; if (msg->msg_name) { @@ -766,6 +767,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) ret = __sock_sendmsg(sock, msg); msg->msg_name = save_addr; + msg->msg_namelen = save_len; return ret; } diff --git a/scripts/Makefile.vdsoinst b/scripts/Makefile.vdsoinst index 1022d9fdd976..c477d17b0aa5 100644 --- a/scripts/Makefile.vdsoinst +++ b/scripts/Makefile.vdsoinst @@ -22,7 +22,7 @@ $$(dest): $$(src) FORCE # Some architectures create .build-id symlinks ifneq ($(filter arm sparc x86, $(SRCARCH)),) -link := $(install-dir)/.build-id/$$(shell $(READELF) -n $$(src) | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p') +link := $(install-dir)/.build-id/$$(shell $(READELF) -n $$(src) | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p').debug __default: $$(link) $$(link): $$(dest) FORCE diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index 180952fb91c1..5dea4479240b 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -64,7 +64,7 @@ def parse_arguments(): args = parser.parse_args() return (args.log_level, - os.path.abspath(args.directory), + os.path.realpath(args.directory), args.output, args.ar, args.paths if len(args.paths) > 0 else [args.directory]) @@ -172,8 +172,8 @@ def process_line(root_directory, command_prefix, file_path): # by Make, so this code replaces the escaped version with '#'. prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#') - # Use os.path.abspath() to normalize the path resolving '.' and '..' . - abs_path = os.path.abspath(os.path.join(root_directory, file_path)) + # Return the canonical path, eliminating any symbolic links encountered in the path. + abs_path = os.path.realpath(os.path.join(root_directory, file_path)) if not os.path.exists(abs_path): raise ValueError('File %s not found' % abs_path) return { diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 16d8ac6005b6..ee1aed7e090c 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -20,6 +20,7 @@ use Getopt::Long qw(:config no_auto_abbrev); use Cwd; use File::Find; use File::Spec::Functions; +use open qw(:std :encoding(UTF-8)); my $cur_path = fastgetcwd() . '/'; my $lk_path = "./"; @@ -445,7 +446,7 @@ sub maintainers_in_file { my $text = do { local($/) ; <$f> }; close($f); - my @poss_addr = $text =~ m$[A-Za-zÀ-ÿ\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g; + my @poss_addr = $text =~ m$[\p{L}\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g; push(@file_emails, clean_file_emails(@poss_addr)); } } @@ -1152,6 +1153,17 @@ sub top_of_kernel_tree { return 0; } +sub escape_name { + my ($name) = @_; + + if ($name =~ /[^\w \-]/ai) { ##has "must quote" chars + $name =~ s/(?<!\\)"/\\"/g; ##escape quotes + $name = "\"$name\""; + } + + return $name; +} + sub parse_email { my ($formatted_email) = @_; @@ -1169,13 +1181,9 @@ sub parse_email { $name =~ s/^\s+|\s+$//g; $name =~ s/^\"|\"$//g; + $name = escape_name($name); $address =~ s/^\s+|\s+$//g; - if ($name =~ /[^\w \-]/i) { ##has "must quote" chars - $name =~ s/(?<!\\)"/\\"/g; ##escape quotes - $name = "\"$name\""; - } - return ($name, $address); } @@ -1186,13 +1194,9 @@ sub format_email { $name =~ s/^\s+|\s+$//g; $name =~ s/^\"|\"$//g; + $name = escape_name($name); $address =~ s/^\s+|\s+$//g; - if ($name =~ /[^\w \-]/i) { ##has "must quote" chars - $name =~ s/(?<!\\)"/\\"/g; ##escape quotes - $name = "\"$name\""; - } - if ($usename) { if ("$name" eq "") { $formatted_email = "$address"; @@ -2458,17 +2462,23 @@ sub clean_file_emails { foreach my $email (@file_emails) { $email =~ s/[\(\<\{]{0,1}([A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+)[\)\>\}]{0,1}/\<$1\>/g; my ($name, $address) = parse_email($email); - if ($name eq '"[,\.]"') { - $name = ""; - } - my @nw = split(/[^A-Za-zÀ-ÿ\'\,\.\+-]/, $name); + # Strip quotes for easier processing, format_email will add them back + $name =~ s/^"(.*)"$/$1/; + + # Split into name-like parts and remove stray punctuation particles + my @nw = split(/[^\p{L}\'\,\.\+-]/, $name); + @nw = grep(!/^[\'\,\.\+-]$/, @nw); + + # Make a best effort to extract the name, and only the name, by taking + # only the last two names, or in the case of obvious initials, the last + # three names. if (@nw > 2) { my $first = $nw[@nw - 3]; my $middle = $nw[@nw - 2]; my $last = $nw[@nw - 1]; - if (((length($first) == 1 && $first =~ m/[A-Za-z]/) || + if (((length($first) == 1 && $first =~ m/\p{L}/) || (length($first) == 2 && substr($first, -1) eq ".")) || (length($middle) == 1 || (length($middle) == 2 && substr($middle, -1) eq "."))) { @@ -2476,18 +2486,16 @@ sub clean_file_emails { } else { $name = "$middle $last"; } + } else { + $name = "@nw"; } if (substr($name, -1) =~ /[,\.]/) { $name = substr($name, 0, length($name) - 1); - } elsif (substr($name, -2) =~ /[,\.]"/) { - $name = substr($name, 0, length($name) - 2) . '"'; } if (substr($name, 0, 1) =~ /[,\.]/) { $name = substr($name, 1, length($name) - 1); - } elsif (substr($name, 0, 2) =~ /"[,\.]/) { - $name = '"' . substr($name, 2, length($name) - 2); } my $fmt_email = format_email($name, $address, $email_usename); diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 38650e52ef57..2d9f2a4b4519 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -2373,6 +2373,7 @@ static struct aa_sfs_entry aa_sfs_entry_policy[] = { static struct aa_sfs_entry aa_sfs_entry_mount[] = { AA_SFS_FILE_STRING("mask", "mount umount pivot_root"), + AA_SFS_FILE_STRING("move_mount", "detached"), { } }; diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c index fb30204c761a..49fe8da6fea4 100644 --- a/security/apparmor/mount.c +++ b/security/apparmor/mount.c @@ -499,6 +499,10 @@ int aa_move_mount(const struct cred *subj_cred, error = -ENOMEM; if (!to_buffer || !from_buffer) goto out; + + if (!our_mnt(from_path->mnt)) + /* moving a mount detached from the namespace */ + from_path = NULL; error = fn_for_each_confined(label, profile, match_mnt(subj_cred, profile, to_path, to_buffer, from_path, from_buffer, diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c index 194e1179a253..c1afb721b4c6 100644 --- a/sound/pci/hda/cs35l41_hda_property.c +++ b/sound/pci/hda/cs35l41_hda_property.c @@ -211,7 +211,6 @@ static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physde if (cfg->bus == SPI) { cs35l41->index = id; -#if IS_ENABLED(CONFIG_SPI) /* * Manually set the Chip Select for the second amp <cs_gpio_index> in the node. * This is only supported for systems with 2 amps, since we cannot expand the @@ -220,7 +219,7 @@ static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physde * uses a native chip select), to ensure the second amp does not clash with the * first. */ - if (cfg->cs_gpio_index >= 0) { + if (IS_ENABLED(CONFIG_SPI) && cfg->cs_gpio_index >= 0) { spi = to_spi_device(cs35l41->dev); if (cfg->num_amps != 2) { @@ -251,7 +250,6 @@ static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physde spi_setup(spi); } } -#endif } else { if (cfg->num_amps > 2) /* diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c3a756528886..70b17b08d4ff 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9799,6 +9799,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), + SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), @@ -9881,6 +9882,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x89d3, "HP EliteBook 645 G9 (MB 89D2)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), @@ -9925,6 +9927,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 2fb1a7037c82..dfe281b57aa6 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -65,6 +65,15 @@ enum calib_data { CALIB_MAX }; +struct tas2781_hda { + struct device *dev; + struct tasdevice_priv *priv; + struct snd_kcontrol *dsp_prog_ctl; + struct snd_kcontrol *dsp_conf_ctl; + struct snd_kcontrol *prof_ctl; + struct snd_kcontrol *snd_ctls[3]; +}; + static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data) { struct tasdevice_priv *tas_priv = data; @@ -125,26 +134,26 @@ err: static void tas2781_hda_playback_hook(struct device *dev, int action) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); - dev_dbg(tas_priv->dev, "%s: action = %d\n", __func__, action); + dev_dbg(tas_hda->dev, "%s: action = %d\n", __func__, action); switch (action) { case HDA_GEN_PCM_ACT_OPEN: pm_runtime_get_sync(dev); - mutex_lock(&tas_priv->codec_lock); - tasdevice_tuning_switch(tas_priv, 0); - mutex_unlock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); + tasdevice_tuning_switch(tas_hda->priv, 0); + mutex_unlock(&tas_hda->priv->codec_lock); break; case HDA_GEN_PCM_ACT_CLOSE: - mutex_lock(&tas_priv->codec_lock); - tasdevice_tuning_switch(tas_priv, 1); - mutex_unlock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); + tasdevice_tuning_switch(tas_hda->priv, 1); + mutex_unlock(&tas_hda->priv->codec_lock); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); break; default: - dev_dbg(tas_priv->dev, "Playback action not supported: %d\n", + dev_dbg(tas_hda->dev, "Playback action not supported: %d\n", action); break; } @@ -421,9 +430,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) } } -/* Update the calibrate data, including speaker impedance, f0, etc, into algo. +/* Update the calibration data, including speaker impedance, f0, etc, into algo. * Calibrate data is done by manufacturer in the factory. These data are used - * by Algo for calucating the speaker temperature, speaker membrance excursion + * by Algo for calculating the speaker temperature, speaker membrane excursion * and f0 in real time during playback. */ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv) @@ -477,9 +486,28 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv) return 0; } +static void tas2781_hda_remove_controls(struct tas2781_hda *tas_hda) +{ + struct hda_codec *codec = tas_hda->priv->codec; + + if (tas_hda->dsp_prog_ctl) + snd_ctl_remove(codec->card, tas_hda->dsp_prog_ctl); + + if (tas_hda->dsp_conf_ctl) + snd_ctl_remove(codec->card, tas_hda->dsp_conf_ctl); + + for (int i = ARRAY_SIZE(tas_hda->snd_ctls) - 1; i >= 0; i--) + if (tas_hda->snd_ctls[i]) + snd_ctl_remove(codec->card, tas_hda->snd_ctls[i]); + + if (tas_hda->prof_ctl) + snd_ctl_remove(codec->card, tas_hda->prof_ctl); +} + static void tasdev_fw_ready(const struct firmware *fmw, void *context) { struct tasdevice_priv *tas_priv = context; + struct tas2781_hda *tas_hda = dev_get_drvdata(tas_priv->dev); struct hda_codec *codec = tas_priv->codec; int i, ret; @@ -490,8 +518,8 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) if (ret) goto out; - ret = snd_ctl_add(codec->card, - snd_ctl_new1(&tas2781_prof_ctrl, tas_priv)); + tas_hda->prof_ctl = snd_ctl_new1(&tas2781_prof_ctrl, tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->prof_ctl); if (ret) { dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", @@ -500,8 +528,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) } for (i = 0; i < ARRAY_SIZE(tas2781_snd_controls); i++) { - ret = snd_ctl_add(codec->card, - snd_ctl_new1(&tas2781_snd_controls[i], tas_priv)); + tas_hda->snd_ctls[i] = snd_ctl_new1(&tas2781_snd_controls[i], + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->snd_ctls[i]); if (ret) { dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", @@ -523,8 +552,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) goto out; } - ret = snd_ctl_add(codec->card, - snd_ctl_new1(&tas2781_dsp_prog_ctrl, tas_priv)); + tas_hda->dsp_prog_ctl = snd_ctl_new1(&tas2781_dsp_prog_ctrl, + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->dsp_prog_ctl); if (ret) { dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", @@ -532,8 +562,9 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) goto out; } - ret = snd_ctl_add(codec->card, - snd_ctl_new1(&tas2781_dsp_conf_ctrl, tas_priv)); + tas_hda->dsp_conf_ctl = snd_ctl_new1(&tas2781_dsp_conf_ctrl, + tas_priv); + ret = snd_ctl_add(codec->card, tas_hda->dsp_conf_ctl); if (ret) { dev_err(tas_priv->dev, "Failed to add KControl %s = %d\n", @@ -554,27 +585,27 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) tas2781_save_calibration(tas_priv); out: - mutex_unlock(&tas_priv->codec_lock); + mutex_unlock(&tas_hda->priv->codec_lock); if (fmw) release_firmware(fmw); - pm_runtime_mark_last_busy(tas_priv->dev); - pm_runtime_put_autosuspend(tas_priv->dev); + pm_runtime_mark_last_busy(tas_hda->dev); + pm_runtime_put_autosuspend(tas_hda->dev); } static int tas2781_hda_bind(struct device *dev, struct device *master, void *master_data) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); struct hda_component *comps = master_data; struct hda_codec *codec; unsigned int subid; int ret; - if (!comps || tas_priv->index < 0 || - tas_priv->index >= HDA_MAX_COMPONENTS) + if (!comps || tas_hda->priv->index < 0 || + tas_hda->priv->index >= HDA_MAX_COMPONENTS) return -EINVAL; - comps = &comps[tas_priv->index]; + comps = &comps[tas_hda->priv->index]; if (comps->dev) return -EBUSY; @@ -583,10 +614,10 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, switch (subid) { case 0x17aa: - tas_priv->catlog_id = LENOVO; + tas_hda->priv->catlog_id = LENOVO; break; default: - tas_priv->catlog_id = OTHERS; + tas_hda->priv->catlog_id = OTHERS; break; } @@ -596,7 +627,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, strscpy(comps->name, dev_name(dev), sizeof(comps->name)); - ret = tascodec_init(tas_priv, codec, tasdev_fw_ready); + ret = tascodec_init(tas_hda->priv, codec, tasdev_fw_ready); if (!ret) comps->playback_hook = tas2781_hda_playback_hook; @@ -609,9 +640,9 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, static void tas2781_hda_unbind(struct device *dev, struct device *master, void *master_data) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); struct hda_component *comps = master_data; - comps = &comps[tas_priv->index]; + comps = &comps[tas_hda->priv->index]; if (comps->dev == dev) { comps->dev = NULL; @@ -619,10 +650,12 @@ static void tas2781_hda_unbind(struct device *dev, comps->playback_hook = NULL; } - tasdevice_config_info_remove(tas_priv); - tasdevice_dsp_remove(tas_priv); + tas2781_hda_remove_controls(tas_hda); - tas_priv->fw_state = TASDEVICE_DSP_FW_PENDING; + tasdevice_config_info_remove(tas_hda->priv); + tasdevice_dsp_remove(tas_hda->priv); + + tas_hda->priv->fw_state = TASDEVICE_DSP_FW_PENDING; } static const struct component_ops tas2781_hda_comp_ops = { @@ -632,21 +665,21 @@ static const struct component_ops tas2781_hda_comp_ops = { static void tas2781_hda_remove(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); - pm_runtime_get_sync(tas_priv->dev); - pm_runtime_disable(tas_priv->dev); + pm_runtime_get_sync(tas_hda->dev); + pm_runtime_disable(tas_hda->dev); - component_del(tas_priv->dev, &tas2781_hda_comp_ops); + component_del(tas_hda->dev, &tas2781_hda_comp_ops); - pm_runtime_put_noidle(tas_priv->dev); + pm_runtime_put_noidle(tas_hda->dev); - tasdevice_remove(tas_priv); + tasdevice_remove(tas_hda->priv); } static int tas2781_hda_i2c_probe(struct i2c_client *clt) { - struct tasdevice_priv *tas_priv; + struct tas2781_hda *tas_hda; const char *device_name; int ret; @@ -655,35 +688,42 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt) else return -ENODEV; - tas_priv = tasdevice_kzalloc(clt); - if (!tas_priv) + tas_hda = devm_kzalloc(&clt->dev, sizeof(*tas_hda), GFP_KERNEL); + if (!tas_hda) return -ENOMEM; - tas_priv->irq_info.irq = clt->irq; - ret = tas2781_read_acpi(tas_priv, device_name); + dev_set_drvdata(&clt->dev, tas_hda); + tas_hda->dev = &clt->dev; + + tas_hda->priv = tasdevice_kzalloc(clt); + if (!tas_hda->priv) + return -ENOMEM; + + tas_hda->priv->irq_info.irq = clt->irq; + ret = tas2781_read_acpi(tas_hda->priv, device_name); if (ret) - return dev_err_probe(tas_priv->dev, ret, + return dev_err_probe(tas_hda->dev, ret, "Platform not supported\n"); - ret = tasdevice_init(tas_priv); + ret = tasdevice_init(tas_hda->priv); if (ret) goto err; - pm_runtime_set_autosuspend_delay(tas_priv->dev, 3000); - pm_runtime_use_autosuspend(tas_priv->dev); - pm_runtime_mark_last_busy(tas_priv->dev); - pm_runtime_set_active(tas_priv->dev); - pm_runtime_get_noresume(tas_priv->dev); - pm_runtime_enable(tas_priv->dev); + pm_runtime_set_autosuspend_delay(tas_hda->dev, 3000); + pm_runtime_use_autosuspend(tas_hda->dev); + pm_runtime_mark_last_busy(tas_hda->dev); + pm_runtime_set_active(tas_hda->dev); + pm_runtime_get_noresume(tas_hda->dev); + pm_runtime_enable(tas_hda->dev); - pm_runtime_put_autosuspend(tas_priv->dev); + pm_runtime_put_autosuspend(tas_hda->dev); - tas2781_reset(tas_priv); + tas2781_reset(tas_hda->priv); - ret = component_add(tas_priv->dev, &tas2781_hda_comp_ops); + ret = component_add(tas_hda->dev, &tas2781_hda_comp_ops); if (ret) { - dev_err(tas_priv->dev, "Register component failed: %d\n", ret); - pm_runtime_disable(tas_priv->dev); + dev_err(tas_hda->dev, "Register component failed: %d\n", ret); + pm_runtime_disable(tas_hda->dev); } err: @@ -699,81 +739,65 @@ static void tas2781_hda_i2c_remove(struct i2c_client *clt) static int tas2781_runtime_suspend(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); int i; - dev_dbg(tas_priv->dev, "Runtime Suspend\n"); + dev_dbg(tas_hda->dev, "Runtime Suspend\n"); - mutex_lock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); - if (tas_priv->playback_started) { - tasdevice_tuning_switch(tas_priv, 1); - tas_priv->playback_started = false; + if (tas_hda->priv->playback_started) { + tasdevice_tuning_switch(tas_hda->priv, 1); + tas_hda->priv->playback_started = false; } - for (i = 0; i < tas_priv->ndev; i++) { - tas_priv->tasdevice[i].cur_book = -1; - tas_priv->tasdevice[i].cur_prog = -1; - tas_priv->tasdevice[i].cur_conf = -1; + for (i = 0; i < tas_hda->priv->ndev; i++) { + tas_hda->priv->tasdevice[i].cur_book = -1; + tas_hda->priv->tasdevice[i].cur_prog = -1; + tas_hda->priv->tasdevice[i].cur_conf = -1; } - regcache_cache_only(tas_priv->regmap, true); - regcache_mark_dirty(tas_priv->regmap); - - mutex_unlock(&tas_priv->codec_lock); + mutex_unlock(&tas_hda->priv->codec_lock); return 0; } static int tas2781_runtime_resume(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); unsigned long calib_data_sz = - tas_priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE; - int ret; - - dev_dbg(tas_priv->dev, "Runtime Resume\n"); + tas_hda->priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE; - mutex_lock(&tas_priv->codec_lock); + dev_dbg(tas_hda->dev, "Runtime Resume\n"); - regcache_cache_only(tas_priv->regmap, false); - ret = regcache_sync(tas_priv->regmap); - if (ret) { - dev_err(tas_priv->dev, - "Failed to restore register cache: %d\n", ret); - goto out; - } + mutex_lock(&tas_hda->priv->codec_lock); - tasdevice_prmg_load(tas_priv, tas_priv->cur_prog); + tasdevice_prmg_load(tas_hda->priv, tas_hda->priv->cur_prog); /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - if (tas_priv->cali_data.total_sz > calib_data_sz) - tas2781_apply_calib(tas_priv); + if (tas_hda->priv->cali_data.total_sz > calib_data_sz) + tas2781_apply_calib(tas_hda->priv); -out: - mutex_unlock(&tas_priv->codec_lock); + mutex_unlock(&tas_hda->priv->codec_lock); - return ret; + return 0; } static int tas2781_system_suspend(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); int ret; - dev_dbg(tas_priv->dev, "System Suspend\n"); + dev_dbg(tas_hda->priv->dev, "System Suspend\n"); ret = pm_runtime_force_suspend(dev); if (ret) return ret; /* Shutdown chip before system suspend */ - regcache_cache_only(tas_priv->regmap, false); - tasdevice_tuning_switch(tas_priv, 1); - regcache_cache_only(tas_priv->regmap, true); - regcache_mark_dirty(tas_priv->regmap); + tasdevice_tuning_switch(tas_hda->priv, 1); /* * Reset GPIO may be shared, so cannot reset here. @@ -784,33 +808,33 @@ static int tas2781_system_suspend(struct device *dev) static int tas2781_system_resume(struct device *dev) { - struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); + struct tas2781_hda *tas_hda = dev_get_drvdata(dev); unsigned long calib_data_sz = - tas_priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE; + tas_hda->priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE; int i, ret; - dev_dbg(tas_priv->dev, "System Resume\n"); + dev_info(tas_hda->priv->dev, "System Resume\n"); ret = pm_runtime_force_resume(dev); if (ret) return ret; - mutex_lock(&tas_priv->codec_lock); + mutex_lock(&tas_hda->priv->codec_lock); - for (i = 0; i < tas_priv->ndev; i++) { - tas_priv->tasdevice[i].cur_book = -1; - tas_priv->tasdevice[i].cur_prog = -1; - tas_priv->tasdevice[i].cur_conf = -1; + for (i = 0; i < tas_hda->priv->ndev; i++) { + tas_hda->priv->tasdevice[i].cur_book = -1; + tas_hda->priv->tasdevice[i].cur_prog = -1; + tas_hda->priv->tasdevice[i].cur_conf = -1; } - tas2781_reset(tas_priv); - tasdevice_prmg_load(tas_priv, tas_priv->cur_prog); + tas2781_reset(tas_hda->priv); + tasdevice_prmg_load(tas_hda->priv, tas_hda->priv->cur_prog); /* If calibrated data occurs error, dsp will still work with default * calibrated data inside algo. */ - if (tas_priv->cali_data.total_sz > calib_data_sz) - tas2781_apply_calib(tas_priv); - mutex_unlock(&tas_priv->codec_lock); + if (tas_hda->priv->cali_data.total_sz > calib_data_sz) + tas2781_apply_calib(tas_hda->priv); + mutex_unlock(&tas_hda->priv->codec_lock); return 0; } diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c index ffb26e4a7e2f..00e35169ae49 100644 --- a/sound/soc/codecs/tas2781-comlib.c +++ b/sound/soc/codecs/tas2781-comlib.c @@ -39,7 +39,7 @@ static const struct regmap_range_cfg tasdevice_ranges[] = { static const struct regmap_config tasdevice_regmap = { .reg_bits = 8, .val_bits = 8, - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_NONE, .ranges = tasdevice_ranges, .num_ranges = ARRAY_SIZE(tasdevice_ranges), .max_register = 256 * 128, @@ -316,8 +316,6 @@ int tasdevice_init(struct tasdevice_priv *tas_priv) tas_priv->tasdevice[i].cur_conf = -1; } - dev_set_drvdata(tas_priv->dev, tas_priv); - mutex_init(&tas_priv->codec_lock); out: diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 55cd5e3c23a5..917b1c15f71d 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -689,6 +689,8 @@ static int tasdevice_i2c_probe(struct i2c_client *i2c) if (!tas_priv) return -ENOMEM; + dev_set_drvdata(&i2c->dev, tas_priv); + if (ACPI_HANDLE(&i2c->dev)) { acpi_id = acpi_match_device(i2c->dev.driver->acpi_match_table, &i2c->dev); diff --git a/sound/soc/fsl/fsl_rpmsg.c b/sound/soc/fsl/fsl_rpmsg.c index 5c5c04ce9db7..00852f174a69 100644 --- a/sound/soc/fsl/fsl_rpmsg.c +++ b/sound/soc/fsl/fsl_rpmsg.c @@ -238,7 +238,7 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, &fsl_rpmsg_dai, 1); if (ret) - return ret; + goto err_pm_disable; rpmsg->card_pdev = platform_device_register_data(&pdev->dev, "imx-audio-rpmsg", @@ -248,16 +248,22 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) if (IS_ERR(rpmsg->card_pdev)) { dev_err(&pdev->dev, "failed to register rpmsg card\n"); ret = PTR_ERR(rpmsg->card_pdev); - return ret; + goto err_pm_disable; } return 0; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + return ret; } static void fsl_rpmsg_remove(struct platform_device *pdev) { struct fsl_rpmsg *rpmsg = platform_get_drvdata(pdev); + pm_runtime_disable(&pdev->dev); + if (rpmsg->card_pdev) platform_device_unregister(rpmsg->card_pdev); } diff --git a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c index 85ae3f76d951..ad6d4b5cf697 100644 --- a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c +++ b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c @@ -499,7 +499,7 @@ static const struct snd_soc_dapm_widget mtk_dai_adda_widgets[] = { SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD), SND_SOC_DAPM_SUPPLY_S("AUD_PAD_TOP", SUPPLY_SEQ_ADDA_AUD_PAD_TOP, - 0, 0, 0, + AFE_AUD_PAD_TOP, RG_RX_FIFO_ON_SFT, 0, mtk_adda_pad_top_event, SND_SOC_DAPM_PRE_PMU), SND_SOC_DAPM_SUPPLY_S("ADDA_MTKAIF_CFG", SUPPLY_SEQ_ADDA_MTKAIF_CFG, diff --git a/sound/soc/meson/g12a-toacodec.c b/sound/soc/meson/g12a-toacodec.c index 6c4503766fdc..531bb8707a3e 100644 --- a/sound/soc/meson/g12a-toacodec.c +++ b/sound/soc/meson/g12a-toacodec.c @@ -71,6 +71,9 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, reg; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); regmap_field_read(priv->field_dat_sel, ®); @@ -101,7 +104,7 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_toacodec_mux_enum, TOACODEC_CTRL0, diff --git a/sound/soc/meson/g12a-tohdmitx.c b/sound/soc/meson/g12a-tohdmitx.c index f7ef9aa1eed8..b92434125fac 100644 --- a/sound/soc/meson/g12a-tohdmitx.c +++ b/sound/soc/meson/g12a-tohdmitx.c @@ -45,6 +45,9 @@ static int g12a_tohdmitx_i2s_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, changed; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); changed = snd_soc_component_test_bits(component, e->reg, CTRL0_I2S_DAT_SEL, @@ -93,6 +96,9 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, changed; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); changed = snd_soc_component_test_bits(component, TOHDMITX_CTRL0, CTRL0_SPDIF_SEL, @@ -112,7 +118,7 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_tohdmitx_spdif_mux_enum, TOHDMITX_CTRL0, diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 28ecbebb4b84..9f84b0d287a5 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -54,8 +54,16 @@ static int request_codec_module(struct hda_codec *codec) static int hda_codec_load_module(struct hda_codec *codec) { - int ret = request_codec_module(codec); + int ret; + + ret = snd_hdac_device_register(&codec->core); + if (ret) { + dev_err(&codec->core.dev, "failed to register hdac device\n"); + put_device(&codec->core.dev); + return ret; + } + ret = request_codec_module(codec); if (ret <= 0) { codec->probe_id = HDA_CODEC_ID_GENERIC; ret = request_codec_module(codec); @@ -116,7 +124,6 @@ EXPORT_SYMBOL_NS_GPL(hda_codec_jack_check, SND_SOC_SOF_HDA_AUDIO_CODEC); static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, int type) { struct hda_codec *codec; - int ret; codec = snd_hda_codec_device_init(to_hda_bus(bus), addr, "ehdaudio%dD%d", bus->idx, addr); if (IS_ERR(codec)) { @@ -126,13 +133,6 @@ static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, i codec->core.type = type; - ret = snd_hdac_device_register(&codec->core); - if (ret) { - dev_err(bus->dev, "failed to register hdac device\n"); - put_device(&codec->core.dev); - return ERR_PTR(ret); - } - return codec; } diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index f7c57a2c3028..33a3d1161885 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -1966,7 +1966,7 @@ static int scarlett2_usb_get_meter_levels(struct usb_mixer_interface *mixer, __le16 num_meters; __le32 magic; } __packed req; - u32 resp[SCARLETT2_MAX_METERS]; + __le32 resp[SCARLETT2_MAX_METERS]; int i, err; req.pad = 0; @@ -1979,7 +1979,7 @@ static int scarlett2_usb_get_meter_levels(struct usb_mixer_interface *mixer, /* copy, convert to u16 */ for (i = 0; i < num_meters; i++) - levels[i] = resp[i]; + levels[i] = le32_to_cpu(resp[i]); return 0; } diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index e5da1cad70ba..76a8990bb14e 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -35538,7 +35538,7 @@ static noinline void __init check_prealloc(struct maple_tree *mt) MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated != 1); + MT_BUG_ON(mt, allocated != 0); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 4917dbb35a44..5667febee328 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -30,16 +30,16 @@ ip netns exec server ip addr add ${server_ip4}/24 dev eth0 ip netns exec client ip link add dev bond0 down type bond mode 1 \ miimon 100 all_slaves_active 1 -ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev eth0 master bond0 ip netns exec client ip link set dev bond0 up ip netns exec client ip addr add ${client_ip4}/24 dev bond0 ip netns exec client ping -c 5 $server_ip4 >/dev/null -ip netns exec client ip link set dev eth0 down nomaster +ip netns exec client ip link set dev eth0 nomaster ip netns exec client ip link set dev bond0 down ip netns exec client ip link set dev bond0 type bond mode 0 \ arp_interval 1000 arp_ip_target "+${server_ip4}" -ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev eth0 master bond0 ip netns exec client ip link set dev bond0 up ip netns exec client ping -c 5 $server_ip4 >/dev/null diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 957b9e18c729..9b298f6a04b3 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -62,6 +62,9 @@ static void test_mlock_limit(int fd) char *mem; len = mlock_limit_cur; + if (len % page_size != 0) + len = (len/page_size) * page_size; + mem = mmap(NULL, len, prot, mode, fd, 0); if (mem == MAP_FAILED) { fail("unable to mmap secret memory\n"); |