- Linux-stable-mirror - lists.linaro.org

[PATCH V3 2/2] LoongArch: KVM: fix "unreliable stack" issue

by Xianglai Li

Insert the appropriate UNWIND macro definition into the kvm_exc_entry in the assembly function to guide the generation of correct ORC table entries, thereby solving the timeout problem of loading the livepatch-sample module on a physical machine running multiple vcpus virtual machines. While solving the above problems, we have gained an additional benefit, that is, we can obtain more call stack information Stack information that can be obtained before the problem is fixed: [<0>] kvm_vcpu_block+0x88/0x120 [kvm] [<0>] kvm_vcpu_halt+0x68/0x580 [kvm] [<0>] kvm_emu_idle+0xd4/0xf0 [kvm] [<0>] kvm_handle_gspr+0x7c/0x700 [kvm] [<0>] kvm_handle_exit+0x160/0x270 [kvm] [<0>] kvm_exc_entry+0x100/0x1e0 Stack information that can be obtained after the problem is fixed: [<0>] kvm_vcpu_block+0x88/0x120 [kvm] [<0>] kvm_vcpu_halt+0x68/0x580 [kvm] [<0>] kvm_emu_idle+0xd4/0xf0 [kvm] [<0>] kvm_handle_gspr+0x7c/0x700 [kvm] [<0>] kvm_handle_exit+0x160/0x270 [kvm] [<0>] kvm_exc_entry+0x104/0x1e4 [<0>] kvm_enter_guest+0x38/0x11c [<0>] kvm_arch_vcpu_ioctl_run+0x26c/0x498 [kvm] [<0>] kvm_vcpu_ioctl+0x200/0xcf8 [kvm] [<0>] sys_ioctl+0x498/0xf00 [<0>] do_syscall+0x98/0x1d0 [<0>] handle_syscall+0xb8/0x158 Cc: stable(a)vger.kernel.org Signed-off-by: Xianglai Li <lixianglai(a)loongson.cn> --- Cc: Huacai Chen <chenhuacai(a)kernel.org> Cc: WANG Xuerui <kernel(a)xen0n.name> Cc: Tianrui Zhao <zhaotianrui(a)loongson.cn> Cc: Bibo Mao <maobibo(a)loongson.cn> Cc: Charlie Jenkins <charlie(a)rivosinc.com> Cc: Xianglai Li <lixianglai(a)loongson.cn> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Tiezhu Yang <yangtiezhu(a)loongson.cn> arch/loongarch/kvm/switch.S | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S index 93845ce53651..a3ea9567dbe5 100644 --- a/arch/loongarch/kvm/switch.S +++ b/arch/loongarch/kvm/switch.S @@ -10,6 +10,7 @@ #include <asm/loongarch.h> #include <asm/regdef.h> #include <asm/unwind_hints.h> +#include <linux/kvm_types.h> #define HGPR_OFFSET(x) (PT_R0 + 8*x) #define GGPR_OFFSET(x) (KVM_ARCH_GGPR + 8*x) @@ -110,9 +111,9 @@ * need to copy world switch code to DMW area. */ .text + .p2align PAGE_SHIFT .cfi_sections .debug_frame SYM_CODE_START(kvm_exc_entry) - .p2align PAGE_SHIFT UNWIND_HINT_UNDEFINED csrwr a2, KVM_TEMP_KS csrrd a2, KVM_VCPU_KS @@ -170,6 +171,7 @@ SYM_CODE_START(kvm_exc_entry) /* restore per cpu register */ ld.d u0, a2, KVM_ARCH_HPERCPU addi.d sp, sp, -PT_SIZE + UNWIND_HINT_REGS /* Prepare handle exception */ or a0, s0, zero @@ -200,7 +202,7 @@ ret_to_host: jr ra SYM_CODE_END(kvm_exc_entry) -EXPORT_SYMBOL(kvm_exc_entry) +EXPORT_SYMBOL_FOR_KVM(kvm_exc_entry) /* * int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu) @@ -215,6 +217,14 @@ SYM_FUNC_START(kvm_enter_guest) /* Save host GPRs */ kvm_save_host_gpr a2 + /* + * The csr_era member variable of the pt_regs structure is required + * for unwinding orc to perform stack traceback, so we need to put + * pc into csr_era member variable here. + */ + pcaddi t0, 0 + st.d t0, a2, PT_ERA + addi.d a2, a1, KVM_VCPU_ARCH st.d sp, a2, KVM_ARCH_HSP st.d tp, a2, KVM_ARCH_HTP @@ -225,7 +235,7 @@ SYM_FUNC_START(kvm_enter_guest) csrwr a1, KVM_VCPU_KS kvm_switch_to_guest SYM_FUNC_END(kvm_enter_guest) -EXPORT_SYMBOL(kvm_enter_guest) +EXPORT_SYMBOL_FOR_KVM(kvm_enter_guest) SYM_FUNC_START(kvm_save_fpu) fpu_save_csr a0 t1 @@ -233,7 +243,7 @@ SYM_FUNC_START(kvm_save_fpu) fpu_save_cc a0 t1 t2 jr ra SYM_FUNC_END(kvm_save_fpu) -EXPORT_SYMBOL(kvm_save_fpu) +EXPORT_SYMBOL_FOR_KVM(kvm_save_fpu) SYM_FUNC_START(kvm_restore_fpu) fpu_restore_double a0 t1 @@ -241,7 +251,7 @@ SYM_FUNC_START(kvm_restore_fpu) fpu_restore_cc a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_fpu) -EXPORT_SYMBOL(kvm_restore_fpu) +EXPORT_SYMBOL_FOR_KVM(kvm_restore_fpu) #ifdef CONFIG_CPU_HAS_LSX SYM_FUNC_START(kvm_save_lsx) @@ -250,7 +260,7 @@ SYM_FUNC_START(kvm_save_lsx) lsx_save_data a0 t1 jr ra SYM_FUNC_END(kvm_save_lsx) -EXPORT_SYMBOL(kvm_save_lsx) +EXPORT_SYMBOL_FOR_KVM(kvm_save_lsx) SYM_FUNC_START(kvm_restore_lsx) lsx_restore_data a0 t1 @@ -258,7 +268,7 @@ SYM_FUNC_START(kvm_restore_lsx) fpu_restore_csr a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_lsx) -EXPORT_SYMBOL(kvm_restore_lsx) +EXPORT_SYMBOL_FOR_KVM(kvm_restore_lsx) #endif #ifdef CONFIG_CPU_HAS_LASX @@ -268,7 +278,7 @@ SYM_FUNC_START(kvm_save_lasx) lasx_save_data a0 t1 jr ra SYM_FUNC_END(kvm_save_lasx) -EXPORT_SYMBOL(kvm_save_lasx) +EXPORT_SYMBOL_FOR_KVM(kvm_save_lasx) SYM_FUNC_START(kvm_restore_lasx) lasx_restore_data a0 t1 @@ -276,7 +286,7 @@ SYM_FUNC_START(kvm_restore_lasx) fpu_restore_csr a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_lasx) -EXPORT_SYMBOL(kvm_restore_lasx) +EXPORT_SYMBOL_FOR_KVM(kvm_restore_lasx) #endif #ifdef CONFIG_CPU_HAS_LBT -- 2.39.1

2 hours, 8 minutes

2
1
0 0

[PATCH] PCI: Avoid work_on_cpu() in async probe workers

by Jinhui Guo

Commit ef0ff68351be ("driver core: Probe devices asynchronously instead of the driver") speeds up the loading of large numbers of device drivers by submitting asynchronous probe workers to an unbounded workqueue and binding each worker to the CPU near the device’s NUMA node. These workers are not scheduled on isolated CPUs because their cpumask is restricted to housekeeping_cpumask(HK_TYPE_WQ) and housekeeping_cpumask(HK_TYPE_DOMAIN). However, when PCI devices reside on the same NUMA node, all their drivers’ probe workers are bound to the same CPU within that node, yet the probes still run in parallel because pci_call_probe() invokes work_on_cpu(). Introduced by commit 873392ca514f ("PCI: work_on_cpu: use in drivers/pci/pci-driver.c"), work_on_cpu() queues a worker on system_percpu_wq to bind the probe thread to the first CPU in the device’s NUMA node (chosen via cpumask_any_and() in pci_call_probe()). 1. The function __driver_attach() submits an asynchronous worker with callback __driver_attach_async_helper(). __driver_attach() async_schedule_dev(__driver_attach_async_helper, dev) async_schedule_node(func, dev, dev_to_node(dev)) async_schedule_node_domain(func, data, node, &async_dfl_domain) __async_schedule_node_domain(func, data, node, domain, entry) queue_work_node(node, async_wq, &entry->work) 2. The asynchronous probe worker ultimately calls work_on_cpu() in pci_call_probe(), binding the worker to the same CPU within the device’s NUMA node. __driver_attach_async_helper() driver_probe_device(drv, dev) __driver_probe_device(drv, dev) really_probe(dev, drv) call_driver_probe(dev, drv) dev->bus->probe(dev) pci_device_probe(dev) __pci_device_probe(drv, pci_dev) pci_call_probe(drv, pci_dev, id) cpu = cpumask_any_and(cpumask_of_node(node), wq_domain_mask) error = work_on_cpu(cpu, local_pci_probe, &ddi) schedule_work_on(cpu, &wfc.work); queue_work_on(cpu, system_percpu_wq, work) To fix the issue, pci_call_probe() must not call work_on_cpu() when it is already running inside an unbounded asynchronous worker. Because a driver can be probed asynchronously either by probe_type or by the kernel command line, we cannot rely on PROBE_PREFER_ASYNCHRONOUS alone. Instead, we test the PF_WQ_WORKER flag in current->flags; if it is set, pci_call_probe() is executing within an unbounded workqueue worker and should skip the extra work_on_cpu() call. Testing three NVMe devices on the same NUMA node of an AMD EPYC 9A64 2.4 GHz processor shows a 35 % probe-time improvement with the patch: Before (all on CPU 0): nvme 0000:01:00.0: CPU: 0, COMM: kworker/0:1, probe cost: 53372612 ns nvme 0000:02:00.0: CPU: 0, COMM: kworker/0:2, probe cost: 49532941 ns nvme 0000:03:00.0: CPU: 0, COMM: kworker/0:3, probe cost: 47315175 ns After (spread across CPUs 1, 2, 5): nvme 0000:01:00.0: CPU: 5, COMM: kworker/u1025:5, probe cost: 34765890 ns nvme 0000:02:00.0: CPU: 1, COMM: kworker/u1025:2, probe cost: 34696433 ns nvme 0000:03:00.0: CPU: 2, COMM: kworker/u1025:3, probe cost: 33233323 ns The improvement grows with more PCI devices because fewer probes contend for the same CPU. Fixes: ef0ff68351be ("driver core: Probe devices asynchronously instead of the driver") Cc: stable(a)vger.kernel.org Signed-off-by: Jinhui Guo <guojinhui.liam(a)bytedance.com> --- drivers/pci/pci-driver.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 7c2d9d596258..4bc47a84d330 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -366,9 +366,11 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, /* * Prevent nesting work_on_cpu() for the case where a Virtual Function * device is probed from work_on_cpu() of the Physical device. + * Check PF_WQ_WORKER to prevent invoking work_on_cpu() in an asynchronous + * probe worker when the driver allows asynchronous probing. */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node) || - pci_physfn_is_probed(dev)) { + pci_physfn_is_probed(dev) || (current->flags & PF_WQ_WORKER)) { cpu = nr_cpu_ids; } else { cpumask_var_t wq_domain_mask; -- 2.20.1

3 hours, 24 minutes

1
0
0 0

[PATCH] arm64: errata: Workaround for SI L1 downstream coherency issue

by Lucas Wei

When software issues a Cache Maintenance Operation (CMO) targeting a dirty cache line, the CPU and DSU cluster may optimize the operation by combining the CopyBack Write and CMO into a single combined CopyBack Write plus CMO transaction presented to the interconnect (MCN). For these combined transactions, the MCN splits the operation into two separate transactions, one Write and one CMO, and then propagates the write and optionally the CMO to the downstream memory system or external Point of Serialization (PoS). However, the MCN may return an early CompCMO response to the DSU cluster before the corresponding Write and CMO transactions have completed at the external PoS or downstream memory. As a result, stale data may be observed by external observers that are directly connected to the external PoS or downstream memory. This erratum affects any system topology in which the following conditions apply: - The Point of Serialization (PoS) is located downstream of the interconnect. - A downstream observer accesses memory directly, bypassing the interconnect. Conditions: This erratum occurs only when all of the following conditions are met: 1. Software executes a data cache maintenance operation, specifically, a clean or invalidate by virtual address (DC CVAC, DC CIVAC, or DC IVAC), that hits on unique dirty data in the CPU or DSU cache. This results in a combined CopyBack and CMO being issued to the interconnect. 2. The interconnect splits the combined transaction into separate Write and CMO transactions and returns an early completion response to the CPU or DSU before the write has completed at the downstream memory or PoS. 3. A downstream observer accesses the affected memory address after the early completion response is issued but before the actual memory write has completed. This allows the observer to read stale data that has not yet been updated at the PoS or downstream memory. The implementation of workaround put a second loop of CMOs at the same virtual address whose operation meet erratum conditions to wait until cache data be cleaned to PoC.. This way of implementation mitigates performance panalty compared to purly duplicate orignial CMO. Cc: stable(a)vger.kernel.org # 6.12.x Signed-off-by: Lucas Wei <lucaswei(a)google.com> --- Documentation/arch/arm64/silicon-errata.rst | 3 ++ arch/arm64/Kconfig | 19 +++++++++++++ arch/arm64/include/asm/assembler.h | 10 +++++++ arch/arm64/kernel/cpu_errata.c | 31 +++++++++++++++++++++ arch/arm64/mm/cache.S | 13 ++++++++- arch/arm64/tools/cpucaps | 1 + 6 files changed, 76 insertions(+), 1 deletion(-) diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index a7ec57060f64..98efdf528719 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -213,6 +213,9 @@ stable kernels. | ARM | GIC-700 | #2941627 | ARM64_ERRATUM_2941627 | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ +| ARM | SI L1 | #4311569 | ARM64_ERRATUM_4311569 | ++----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ | Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_845719 | +----------------+-----------------+-----------------+-----------------------------+ | Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_843419 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 93173f0a09c7..89326bb26f48 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1155,6 +1155,25 @@ config ARM64_ERRATUM_3194386 If unsure, say Y. +config ARM64_ERRATUM_4311569 + bool "SI L1: 4311569: workaround for premature CMO completion erratum" + default y + help + This option adds the workaround for ARM SI L1 erratum 4311569. + + The erratum of SI L1 can cause an early response to a combined write + and cache maintenance operation (WR+CMO) before the operation is fully + completed to the Point of Serialization (POS). + This can result in a non-I/O coherent agent observing stale data, + potentially leading to system instability or incorrect behavior. + + Enabling this option implements a software workaround by inserting a + second loop of Cache Maintenance Operation (CMO) immediately following the + end of function to do CMOs. This ensures that the data is correctly serialized + before the buffer is handed off to a non-coherent agent. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index f0ca7196f6fa..d3d46e5f7188 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -381,6 +381,9 @@ alternative_endif .macro dcache_by_myline_op op, domain, start, end, linesz, tmp, fixup sub \tmp, \linesz, #1 bic \start, \start, \tmp +alternative_if ARM64_WORKAROUND_4311569 + mov \tmp, \start +alternative_else_nop_endif .Ldcache_op\@: .ifc \op, cvau __dcache_op_workaround_clean_cache \op, \start @@ -402,6 +405,13 @@ alternative_endif add \start, \start, \linesz cmp \start, \end b.lo .Ldcache_op\@ +alternative_if ARM64_WORKAROUND_4311569 + .ifnc \op, cvau + mov \start, \tmp + mov \tmp, xzr + cbnz \start, .Ldcache_op\@ + .endif +alternative_else_nop_endif dsb \domain _cond_uaccess_extable .Ldcache_op\@, \fixup diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 8cb3b575a031..c69678c512f1 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -141,6 +141,30 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, return (ctr_real != sys) && (ctr_raw != sys); } +#ifdef CONFIG_ARM64_ERRATUM_4311569 +DEFINE_STATIC_KEY_FALSE(arm_si_l1_workaround_4311569); +static int __init early_arm_si_l1_workaround_4311569_cfg(char *arg) +{ + static_branch_enable(&arm_si_l1_workaround_4311569); + pr_info("Enabling cache maintenance workaround for ARM SI-L1 erratum 4311569\n"); + + return 0; +} +early_param("arm_si_l1_workaround_4311569", early_arm_si_l1_workaround_4311569_cfg); + +/* + * We have some earlier use cases to call cache maintenance operation functions, for example, + * dcache_inval_poc() and dcache_clean_poc() in head.S, before making decision to turn on this + * workaround. Since the scope of this workaround is limited to non-coherent DMA agents, its + * safe to have the workaround off by default. + */ +static bool +need_arm_si_l1_workaround_4311569(const struct arm64_cpu_capabilities *entry, int scope) +{ + return static_branch_unlikely(&arm_si_l1_workaround_4311569); +} +#endif + static void cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap) { @@ -870,6 +894,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_4311569 + { + .capability = ARM64_WORKAROUND_4311569, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = need_arm_si_l1_workaround_4311569, + }, +#endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD { .desc = "ARM errata 2966298, 3117295", diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 503567c864fd..ddf0097624ed 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -143,9 +143,14 @@ SYM_FUNC_END(dcache_clean_pou) * - end - kernel end address of region */ SYM_FUNC_START(__pi_dcache_inval_poc) +alternative_if ARM64_WORKAROUND_4311569 + mov x4, x0 + mov x5, x1 + mov x6, #1 +alternative_else_nop_endif dcache_line_size x2, x3 sub x3, x2, #1 - tst x1, x3 // end cache line aligned? +again: tst x1, x3 // end cache line aligned? bic x1, x1, x3 b.eq 1f dc civac, x1 // clean & invalidate D / U line @@ -158,6 +163,12 @@ SYM_FUNC_START(__pi_dcache_inval_poc) 3: add x0, x0, x2 cmp x0, x1 b.lo 2b +alternative_if ARM64_WORKAROUND_4311569 + mov x0, x4 + mov x1, x5 + sub x6, x6, #1 + cbz x6, again +alternative_else_nop_endif dsb sy ret SYM_FUNC_END(__pi_dcache_inval_poc) diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 0fac75f01534..856b6cf6e71e 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -103,6 +103,7 @@ WORKAROUND_2077057 WORKAROUND_2457168 WORKAROUND_2645198 WORKAROUND_2658417 +WORKAROUND_4311569 WORKAROUND_AMPERE_AC03_CPU_38 WORKAROUND_AMPERE_AC04_CPU_23 WORKAROUND_TRBE_OVERWRITE_FILL_MODE -- 2.52.0.358.g0dd7633a29-goog

5 hours, 4 minutes

2
1
0 0

[PATCH] powerpc/kexec: Enable SMT before waking offline CPUs

by Nysal Jan K.A.

If SMT is disabled or a partial SMT state is enabled, when a new kernel image is loaded for kexec, on reboot the following warning is observed: kexec: Waking offline cpu 228. WARNING: CPU: 0 PID: 9062 at arch/powerpc/kexec/core_64.c:223 kexec_prepare_cpus+0x1b0/0x1bc [snip] NIP kexec_prepare_cpus+0x1b0/0x1bc LR kexec_prepare_cpus+0x1a0/0x1bc Call Trace: kexec_prepare_cpus+0x1a0/0x1bc (unreliable) default_machine_kexec+0x160/0x19c machine_kexec+0x80/0x88 kernel_kexec+0xd0/0x118 __do_sys_reboot+0x210/0x2c4 system_call_exception+0x124/0x320 system_call_vectored_common+0x15c/0x2ec This occurs as add_cpu() fails due to cpu_bootable() returning false for CPUs that fail the cpu_smt_thread_allowed() check or non primary threads if SMT is disabled. Fix the issue by enabling SMT and resetting the number of SMT threads to the number of threads per core, before attempting to wake up all present CPUs. Fixes: 38253464bc82 ("cpu/SMT: Create topology_smt_thread_allowed()") Reported-by: Sachin P Bappalige <sachinpb(a)linux.ibm.com> Cc: stable(a)vger.kernel.org # v6.6+ Signed-off-by: Nysal Jan K.A. <nysal(a)linux.ibm.com> --- arch/powerpc/kexec/core_64.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 222aa326dace..ff6df43720c4 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -216,6 +216,11 @@ static void wake_offline_cpus(void) { int cpu = 0; + lock_device_hotplug(); + cpu_smt_num_threads = threads_per_core; + cpu_smt_control = CPU_SMT_ENABLED; + unlock_device_hotplug(); + for_each_present_cpu(cpu) { if (!cpu_online(cpu)) { printk(KERN_INFO "kexec: Waking offline cpu %d.\n", -- 2.51.0

10 hours, 33 minutes

6
8
0 0

[PATCH v2] powerpc: Add reloc_offset() to font bitmap pointer used for bootx_printf()

by Finn Thain

Since Linux v6.7, booting using BootX on an Old World PowerMac produces an early crash. Stan Johnson writes, "the symptoms are that the screen goes blank and the backlight stays on, and the system freezes (Linux doesn't boot)." Further testing revealed that the failure can be avoided by disabling CONFIG_BOOTX_TEXT. Bisection revealed that the regression was caused by a change to the font bitmap pointer that's used when btext_init() begins painting characters on the display, early in the boot process. Christophe Leroy explains, "before kernel text is relocated to its final location ... data is addressed with an offset which is added to the Global Offset Table (GOT) entries at the start of bootx_init() by function reloc_got2(). But the pointers that are located inside a structure are not referenced in the GOT and are therefore not updated by reloc_got2(). It is therefore needed to apply the offset manually by using PTRRELOC() macro." Cc: Cedar Maxwell <cedarmaxwell(a)mac.com> Cc: Stan Johnson <userm57(a)yahoo.com> Cc: "Dr. David Alan Gilbert" <linux(a)treblig.org> Cc: Benjamin Herrenschmidt <benh(a)kernel.crashing.org> Cc: stable(a)vger.kernel.org Link: https://lists.debian.org/debian-powerpc/2025/10/msg00111.html Link: https://lore.kernel.org/linuxppc-dev/d81ddca8-c5ee-d583-d579-02b19ed95301@y… Reported-by: Cedar Maxwell <cedarmaxwell(a)mac.com> Closes: https://lists.debian.org/debian-powerpc/2025/09/msg00031.html Bisected-by: Stan Johnson <userm57(a)yahoo.com> Tested-by: Stan Johnson <userm57(a)yahoo.com> Fixes: 0ebc7feae79a ("powerpc: Use shared font data") Suggested-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> Signed-off-by: Finn Thain <fthain(a)linux-m68k.org> --- Changed since v1: - Improved commit log entry to better explain the need for PTRRELOC(). --- arch/powerpc/kernel/btext.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 7f63f1cdc6c3..ca00c4824e31 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -20,6 +20,7 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/udbg.h> +#include <asm/setup.h> #define NO_SCROLL @@ -463,7 +464,7 @@ static noinline void draw_byte(unsigned char c, long locX, long locY) { unsigned char *base = calc_base(locX << 3, locY << 4); unsigned int font_index = c * 16; - const unsigned char *font = font_sun_8x16.data + font_index; + const unsigned char *font = PTRRELOC(font_sun_8x16.data) + font_index; int rb = dispDeviceRowBytes; rmci_maybe_on(); -- 2.49.1

10 hours, 34 minutes

3
4
0 0

Re: [PATCH v2] fbdev: bitblit: bound-check glyph index in bit_putcs*

by Vitaly Chikunov

Dear linux-fbdev, stable, On Mon, Oct 20, 2025 at 09:47:01PM +0800, Junjie Cao wrote: > bit_putcs_aligned()/unaligned() derived the glyph pointer from the > character value masked by 0xff/0x1ff, which may exceed the actual font's > glyph count and read past the end of the built-in font array. > Clamp the index to the actual glyph count before computing the address. > > This fixes a global out-of-bounds read reported by syzbot. > > Reported-by: syzbot+793cf822d213be1a74f2(a)syzkaller.appspotmail.com > Closes: https://syzkaller.appspot.com/bug?extid=793cf822d213be1a74f2 > Tested-by: syzbot+793cf822d213be1a74f2(a)syzkaller.appspotmail.com > Signed-off-by: Junjie Cao <junjie.cao(a)intel.com> This commit is applied to v5.10.247 and causes a regression: when switching VT with ctrl-alt-f2 the screen is blank or completely filled with angle characters, then new text is not appearing (or not visible). This commit is found with git bisect from v5.10.246 to v5.10.247: 0998a6cb232674408a03e8561dc15aa266b2f53b is the first bad commit commit 0998a6cb232674408a03e8561dc15aa266b2f53b Author: Junjie Cao <junjie.cao(a)intel.com> AuthorDate: 2025-10-20 21:47:01 +0800 Commit: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> CommitDate: 2025-12-07 06:08:07 +0900 fbdev: bitblit: bound-check glyph index in bit_putcs* commit 18c4ef4e765a798b47980555ed665d78b71aeadf upstream. bit_putcs_aligned()/unaligned() derived the glyph pointer from the character value masked by 0xff/0x1ff, which may exceed the actual font's glyph count and read past the end of the built-in font array. Clamp the index to the actual glyph count before computing the address. This fixes a global out-of-bounds read reported by syzbot. Reported-by: syzbot+793cf822d213be1a74f2(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=793cf822d213be1a74f2 Tested-by: syzbot+793cf822d213be1a74f2(a)syzkaller.appspotmail.com Signed-off-by: Junjie Cao <junjie.cao(a)intel.com> Reviewed-by: Thomas Zimmermann <tzimmermann(a)suse.de> Signed-off-by: Helge Deller <deller(a)gmx.de> Cc: stable(a)vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> drivers/video/fbdev/core/bitblit.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) The minimal reproducer in cli, after kernel is booted: date >/dev/tty2; chvt 2 and the date does not appear. Thanks, #regzbot introduced: 0998a6cb232674408a03e8561dc15aa266b2f53b > --- > v1: https://lore.kernel.org/linux-fbdev/5d237d1a-a528-4205-a4d8-71709134f1e1@su… > v1 -> v2: > - Fix indentation and add blank line after declarations with the .pl helper > - No functional changes > > drivers/video/fbdev/core/bitblit.c | 16 ++++++++++++---- > 1 file changed, 12 insertions(+), 4 deletions(-) > > diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c > index 9d2e59796c3e..085ffb44c51a 100644 > --- a/drivers/video/fbdev/core/bitblit.c > +++ b/drivers/video/fbdev/core/bitblit.c > @@ -79,12 +79,16 @@ static inline void bit_putcs_aligned(struct vc_data *vc, struct fb_info *info, > struct fb_image *image, u8 *buf, u8 *dst) > { > u16 charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; > + unsigned int charcnt = vc->vc_font.charcount; > u32 idx = vc->vc_font.width >> 3; > u8 *src; > > while (cnt--) { > - src = vc->vc_font.data + (scr_readw(s++)& > - charmask)*cellsize; > + u16 ch = scr_readw(s++) & charmask; > + > + if (ch >= charcnt) > + ch = 0; > + src = vc->vc_font.data + (unsigned int)ch * cellsize; > > if (attr) { > update_attr(buf, src, attr, vc); > @@ -112,14 +116,18 @@ static inline void bit_putcs_unaligned(struct vc_data *vc, > u8 *dst) > { > u16 charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff; > + unsigned int charcnt = vc->vc_font.charcount; > u32 shift_low = 0, mod = vc->vc_font.width % 8; > u32 shift_high = 8; > u32 idx = vc->vc_font.width >> 3; > u8 *src; > > while (cnt--) { > - src = vc->vc_font.data + (scr_readw(s++)& > - charmask)*cellsize; > + u16 ch = scr_readw(s++) & charmask; > + > + if (ch >= charcnt) > + ch = 0; > + src = vc->vc_font.data + (unsigned int)ch * cellsize; > > if (attr) { > update_attr(buf, src, attr, vc); > -- > 2.48.1 >

12 hours, 53 minutes

2
2
0 0

[PATCH V3 1/2] LoongArch: KVM: Compile the switch.S file directly into the kernel

by Xianglai Li

If we directly compile the switch.S file into the kernel, the address of the kvm_exc_entry function will definitely be within the DMW memory area. Therefore, we will no longer need to perform a copy relocation of kvm_exc_entry. Based on the above description, compile switch.S directly into the kernel, and then remove the copy relocation execution logic for the kvm_exc_entry function. Cc: stable(a)vger.kernel.org Signed-off-by: Xianglai Li <lixianglai(a)loongson.cn> --- Cc: Huacai Chen <chenhuacai(a)kernel.org> Cc: WANG Xuerui <kernel(a)xen0n.name> Cc: Tianrui Zhao <zhaotianrui(a)loongson.cn> Cc: Bibo Mao <maobibo(a)loongson.cn> Cc: Charlie Jenkins <charlie(a)rivosinc.com> Cc: Xianglai Li <lixianglai(a)loongson.cn> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Tiezhu Yang <yangtiezhu(a)loongson.cn> arch/loongarch/Kbuild | 2 +- arch/loongarch/include/asm/asm-prototypes.h | 21 +++++++++++++ arch/loongarch/include/asm/kvm_host.h | 3 -- arch/loongarch/kvm/Makefile | 2 +- arch/loongarch/kvm/main.c | 35 ++------------------- arch/loongarch/kvm/switch.S | 22 ++++++++++--- 6 files changed, 43 insertions(+), 42 deletions(-) diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild index beb8499dd8ed..1c7a0dbe5e72 100644 --- a/arch/loongarch/Kbuild +++ b/arch/loongarch/Kbuild @@ -3,7 +3,7 @@ obj-y += mm/ obj-y += net/ obj-y += vdso/ -obj-$(CONFIG_KVM) += kvm/ +obj-$(subst m,y,$(CONFIG_KVM)) += kvm/ # for cleaning subdir- += boot diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h index 704066b4f736..e8ce153691e5 100644 --- a/arch/loongarch/include/asm/asm-prototypes.h +++ b/arch/loongarch/include/asm/asm-prototypes.h @@ -20,3 +20,24 @@ asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_ struct pt_regs *regs, int (*fn)(void *), void *fn_arg); + +struct kvm_run; +struct kvm_vcpu; + +void kvm_exc_entry(void); +int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); + +struct loongarch_fpu; + +#ifdef CONFIG_CPU_HAS_LSX +void kvm_save_lsx(struct loongarch_fpu *fpu); +void kvm_restore_lsx(struct loongarch_fpu *fpu); +#endif + +#ifdef CONFIG_CPU_HAS_LASX +void kvm_save_lasx(struct loongarch_fpu *fpu); +void kvm_restore_lasx(struct loongarch_fpu *fpu); +#endif + +void kvm_save_fpu(struct loongarch_fpu *fpu); +void kvm_restore_fpu(struct loongarch_fpu *fpu); diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h index e4fe5b8e8149..1a1be10e3803 100644 --- a/arch/loongarch/include/asm/kvm_host.h +++ b/arch/loongarch/include/asm/kvm_host.h @@ -85,7 +85,6 @@ struct kvm_context { struct kvm_world_switch { int (*exc_entry)(void); int (*enter_guest)(struct kvm_run *run, struct kvm_vcpu *vcpu); - unsigned long page_order; }; #define MAX_PGTABLE_LEVELS 4 @@ -347,8 +346,6 @@ void kvm_exc_entry(void); int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu); extern unsigned long vpid_mask; -extern const unsigned long kvm_exception_size; -extern const unsigned long kvm_enter_guest_size; extern struct kvm_world_switch *kvm_loongarch_ops; #define SW_GCSR (1 << 0) diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile index cb41d9265662..fe665054f824 100644 --- a/arch/loongarch/kvm/Makefile +++ b/arch/loongarch/kvm/Makefile @@ -11,7 +11,7 @@ kvm-y += exit.o kvm-y += interrupt.o kvm-y += main.o kvm-y += mmu.o -kvm-y += switch.o +obj-y += switch.o kvm-y += timer.o kvm-y += tlb.o kvm-y += vcpu.o diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 80ea63d465b8..67d234540ed4 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -340,8 +340,7 @@ void kvm_arch_disable_virtualization_cpu(void) static int kvm_loongarch_env_init(void) { - int cpu, order, ret; - void *addr; + int cpu, ret; struct kvm_context *context; vmcs = alloc_percpu(struct kvm_context); @@ -357,30 +356,8 @@ static int kvm_loongarch_env_init(void) return -ENOMEM; } - /* - * PGD register is shared between root kernel and kvm hypervisor. - * So world switch entry should be in DMW area rather than TLB area - * to avoid page fault reenter. - * - * In future if hardware pagetable walking is supported, we won't - * need to copy world switch code to DMW area. - */ - order = get_order(kvm_exception_size + kvm_enter_guest_size); - addr = (void *)__get_free_pages(GFP_KERNEL, order); - if (!addr) { - free_percpu(vmcs); - vmcs = NULL; - kfree(kvm_loongarch_ops); - kvm_loongarch_ops = NULL; - return -ENOMEM; - } - - memcpy(addr, kvm_exc_entry, kvm_exception_size); - memcpy(addr + kvm_exception_size, kvm_enter_guest, kvm_enter_guest_size); - flush_icache_range((unsigned long)addr, (unsigned long)addr + kvm_exception_size + kvm_enter_guest_size); - kvm_loongarch_ops->exc_entry = addr; - kvm_loongarch_ops->enter_guest = addr + kvm_exception_size; - kvm_loongarch_ops->page_order = order; + kvm_loongarch_ops->exc_entry = (void *)kvm_exc_entry; + kvm_loongarch_ops->enter_guest = (void *)kvm_enter_guest; vpid_mask = read_csr_gstat(); vpid_mask = (vpid_mask & CSR_GSTAT_GIDBIT) >> CSR_GSTAT_GIDBIT_SHIFT; @@ -414,16 +391,10 @@ static int kvm_loongarch_env_init(void) static void kvm_loongarch_env_exit(void) { - unsigned long addr; - if (vmcs) free_percpu(vmcs); if (kvm_loongarch_ops) { - if (kvm_loongarch_ops->exc_entry) { - addr = (unsigned long)kvm_loongarch_ops->exc_entry; - free_pages(addr, kvm_loongarch_ops->page_order); - } kfree(kvm_loongarch_ops); } diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S index f1768b7a6194..93845ce53651 100644 --- a/arch/loongarch/kvm/switch.S +++ b/arch/loongarch/kvm/switch.S @@ -5,6 +5,7 @@ #include <linux/linkage.h> #include <asm/asm.h> +#include <asm/page.h> #include <asm/asmmacro.h> #include <asm/loongarch.h> #include <asm/regdef.h> @@ -100,10 +101,18 @@ * - is still in guest mode, such as pgd table/vmid registers etc, * - will fix with hw page walk enabled in future * load kvm_vcpu from reserved CSR KVM_VCPU_KS, and save a2 to KVM_TEMP_KS + * + * PGD register is shared between root kernel and kvm hypervisor. + * So world switch entry should be in DMW area rather than TLB area + * to avoid page fault reenter. + * + * In future if hardware pagetable walking is supported, we won't + * need to copy world switch code to DMW area. */ .text .cfi_sections .debug_frame SYM_CODE_START(kvm_exc_entry) + .p2align PAGE_SHIFT UNWIND_HINT_UNDEFINED csrwr a2, KVM_TEMP_KS csrrd a2, KVM_VCPU_KS @@ -190,8 +199,8 @@ ret_to_host: kvm_restore_host_gpr a2 jr ra -SYM_INNER_LABEL(kvm_exc_entry_end, SYM_L_LOCAL) SYM_CODE_END(kvm_exc_entry) +EXPORT_SYMBOL(kvm_exc_entry) /* * int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu) @@ -215,8 +224,8 @@ SYM_FUNC_START(kvm_enter_guest) /* Save kvm_vcpu to kscratch */ csrwr a1, KVM_VCPU_KS kvm_switch_to_guest -SYM_INNER_LABEL(kvm_enter_guest_end, SYM_L_LOCAL) SYM_FUNC_END(kvm_enter_guest) +EXPORT_SYMBOL(kvm_enter_guest) SYM_FUNC_START(kvm_save_fpu) fpu_save_csr a0 t1 @@ -224,6 +233,7 @@ SYM_FUNC_START(kvm_save_fpu) fpu_save_cc a0 t1 t2 jr ra SYM_FUNC_END(kvm_save_fpu) +EXPORT_SYMBOL(kvm_save_fpu) SYM_FUNC_START(kvm_restore_fpu) fpu_restore_double a0 t1 @@ -231,6 +241,7 @@ SYM_FUNC_START(kvm_restore_fpu) fpu_restore_cc a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_fpu) +EXPORT_SYMBOL(kvm_restore_fpu) #ifdef CONFIG_CPU_HAS_LSX SYM_FUNC_START(kvm_save_lsx) @@ -239,6 +250,7 @@ SYM_FUNC_START(kvm_save_lsx) lsx_save_data a0 t1 jr ra SYM_FUNC_END(kvm_save_lsx) +EXPORT_SYMBOL(kvm_save_lsx) SYM_FUNC_START(kvm_restore_lsx) lsx_restore_data a0 t1 @@ -246,6 +258,7 @@ SYM_FUNC_START(kvm_restore_lsx) fpu_restore_csr a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_lsx) +EXPORT_SYMBOL(kvm_restore_lsx) #endif #ifdef CONFIG_CPU_HAS_LASX @@ -255,6 +268,7 @@ SYM_FUNC_START(kvm_save_lasx) lasx_save_data a0 t1 jr ra SYM_FUNC_END(kvm_save_lasx) +EXPORT_SYMBOL(kvm_save_lasx) SYM_FUNC_START(kvm_restore_lasx) lasx_restore_data a0 t1 @@ -262,10 +276,8 @@ SYM_FUNC_START(kvm_restore_lasx) fpu_restore_csr a0 t1 t2 jr ra SYM_FUNC_END(kvm_restore_lasx) +EXPORT_SYMBOL(kvm_restore_lasx) #endif - .section ".rodata" -SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry) -SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest) #ifdef CONFIG_CPU_HAS_LBT STACK_FRAME_NON_STANDARD kvm_restore_fpu -- 2.39.1

13 hours, 30 minutes

1
0
0 0

[PATCH V3 0/2] LoongArch: KVM: fix "unreliable stack" issue

by Xianglai Li

When starting multi-core loongarch virtualization on loongarch physical machine, loading livepatch on the physical machine will cause an error similar to the following: [ 411.686289] livepatch: klp_try_switch_task: CPU 31/KVM:3116 has an unreliable stack The specific test steps are as follows: 1.Start a multi-core virtual machine on a physical machine 2.Enter the following command on the physical machine to turn on the debug switch: echo "file kernel/livepatch/transition.c +p" > /sys/kernel/debug/\ dynamic_debug/control 3.Load livepatch: modprobe livepatch-sample Through the above steps, similar prints can be viewed in dmesg. The reason for this issue is that the code of the kvm_exc_entry function was copied in the function kvm_loongarch_env_init. When the cpu needs to execute kvm_exc_entry, it will switch to the copied address for execution. The new address of the kvm_exc_entry function cannot be recognized in ORC, which eventually leads to the arch_stack_walk_reliable function returning an error and printing an exception message. To solve the above problems, we directly compile the switch.S file into the kernel instead of the module. In this way, the function kvm_exc_entry will no longer need to be copied. changlog: V3<-V2: 1.Replace the EXPORT_SYMBOL macro declaration symbol with the EXPORT_SYMBOL_FOR_KVM macro 2.Add some comments in kvm_enter_guest 3.Place the correct pc address in era 4.Move .p2align after .text V2<-V1: 1.Rollback the modification of function parameter types such as kvm_save_fpu. In the asm-prototypes.h header file, only the parameter types it depends on are included Cc: Huacai Chen <chenhuacai(a)kernel.org> Cc: WANG Xuerui <kernel(a)xen0n.name> Cc: Tianrui Zhao <zhaotianrui(a)loongson.cn> Cc: Bibo Mao <maobibo(a)loongson.cn> Cc: Charlie Jenkins <charlie(a)rivosinc.com> Cc: Xianglai Li <lixianglai(a)loongson.cn> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Cc: Tiezhu Yang <yangtiezhu(a)loongson.cn> Xianglai Li (2): LoongArch: KVM: Compile the switch.S file directly into the kernel LoongArch: KVM: fix "unreliable stack" issue arch/loongarch/Kbuild | 2 +- arch/loongarch/include/asm/asm-prototypes.h | 21 +++++++++++++ arch/loongarch/include/asm/kvm_host.h | 3 -- arch/loongarch/kvm/Makefile | 2 +- arch/loongarch/kvm/main.c | 35 ++------------------- arch/loongarch/kvm/switch.S | 32 ++++++++++++++++--- 6 files changed, 53 insertions(+), 42 deletions(-) base-commit: 8f0b4cce4481fb22653697cced8d0d04027cb1e8 -- 2.39.1

13 hours, 30 minutes

1
0
0 0

[PATCH v2 1/6] Revert "PCI: dw-rockchip: Don't wait for link since we can detect Link Up"

by Niklas Cassel

This reverts commit ec9fd499b9c60a187ac8d6414c3c343c77d32e42. While this fake hotplugging was a nice idea, it has shown that this feature does not handle PCIe switches correctly: pci_bus 0004:43: busn_res: can not insert [bus 43-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:43: busn_res: [bus 43-41] end is updated to 43 pci_bus 0004:43: busn_res: can not insert [bus 43] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:00.0: devices behind bridge are unusable because [bus 43] cannot be assigned for them pci_bus 0004:44: busn_res: can not insert [bus 44-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:44: busn_res: [bus 44-41] end is updated to 44 pci_bus 0004:44: busn_res: can not insert [bus 44] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:02.0: devices behind bridge are unusable because [bus 44] cannot be assigned for them pci_bus 0004:45: busn_res: can not insert [bus 45-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:45: busn_res: [bus 45-41] end is updated to 45 pci_bus 0004:45: busn_res: can not insert [bus 45] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:06.0: devices behind bridge are unusable because [bus 45] cannot be assigned for them pci_bus 0004:46: busn_res: can not insert [bus 46-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:46: busn_res: [bus 46-41] end is updated to 46 pci_bus 0004:46: busn_res: can not insert [bus 46] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:0e.0: devices behind bridge are unusable because [bus 46] cannot be assigned for them pci_bus 0004:42: busn_res: [bus 42-41] end is updated to 46 pci_bus 0004:42: busn_res: can not insert [bus 42-46] under [bus 41] (conflicts with (null) [bus 41]) pci 0004:41:00.0: devices behind bridge are unusable because [bus 42-46] cannot be assigned for them pcieport 0004:40:00.0: bridge has subordinate 41 but max busn 46 During the initial scan, PCI core doesn't see the switch and since the Root Port is not hot plug capable, the secondary bus number gets assigned as the subordinate bus number. This means, the PCI core assumes that only one bus will appear behind the Root Port since the Root Port is not hot plug capable. This works perfectly fine for PCIe endpoints connected to the Root Port, since they don't extend the bus. However, if a PCIe switch is connected, then there is a problem when the downstream busses starts showing up and the PCI core doesn't extend the subordinate bus number after initial scan during boot. The long term plan is to migrate this driver to the pwrctrl framework, once it adds proper support for powering up and enumerating PCIe switches. Cc: stable(a)vger.kernel.org Suggested-by: Manivannan Sadhasivam <mani(a)kernel.org> Acked-by: Shawn Lin <shawn.lin(a)rock-chips.com> Tested-by: Shawn Lin <shawn.lin(a)rock-chips.com> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/dwc/pcie-dw-rockchip.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c index 8c1c92208802..ca808d8f7975 100644 --- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c +++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c @@ -601,7 +601,6 @@ static int rockchip_pcie_configure_rc(struct platform_device *pdev, pp = &rockchip->pci.pp; pp->ops = &rockchip_pcie_host_ops; - pp->use_linkup_irq = true; ret = dw_pcie_host_init(pp); if (ret) { -- 2.52.0

16 hours, 25 minutes

2
1
0 0

[PATCH] PCI: j721e: Add config guards for Cadence Host and Endpoint library APIs

by Siddharth Vadapalli

Commit under Fixes enabled loadable module support for the driver under the assumption that it shall be the sole user of the Cadence Host and Endpoint library APIs. This assumption guarantees that we won't end up in a case where the driver is built-in and the library support is built as a loadable module. With the introduction of [1], this assumption is no longer valid. The SG2042 driver could be built as a loadable module, implying that the Cadence Host library is also selected as a loadable module. However, the pci-j721e.c driver could be built-in as indicated by CONFIG_PCI_J721E=y due to which the Cadence Endpoint library is built-in. Despite the library drivers being built as specified by their respective consumers, since the 'pci-j721e.c' driver has references to the Cadence Host library APIs as well, we run into a build error as reported at [0]. Fix this by adding config guards as a temporary workaround. The proper fix is to split the 'pci-j721e.c' driver into independent Host and Endpoint drivers as aligned at [2]. Fixes: a2790bf81f0f ("PCI: j721e: Add support to build as a loadable module") Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202511111705.MZ7ls8Hm-lkp@intel.com/ Cc: <stable(a)vger.kernel.org> [0]: https://lore.kernel.org/r/202511111705.MZ7ls8Hm-lkp@intel.com/ [1]: commit 1c72774df028 ("PCI: sg2042: Add Sophgo SG2042 PCIe driver") [2]: https://lore.kernel.org/r/37f6f8ce-12b2-44ee-a94c-f21b29c98821@app.fastmail… Suggested-by: Arnd Bergmann <arnd(a)arndb.de> Signed-off-by: Siddharth Vadapalli <s-vadapalli(a)ti.com> --- drivers/pci/controller/cadence/pci-j721e.c | 43 +++++++++++++--------- 1 file changed, 26 insertions(+), 17 deletions(-) diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c index 5bc5ab20aa6d..67c5e02afccf 100644 --- a/drivers/pci/controller/cadence/pci-j721e.c +++ b/drivers/pci/controller/cadence/pci-j721e.c @@ -628,10 +628,12 @@ static int j721e_pcie_probe(struct platform_device *pdev) gpiod_set_value_cansleep(gpiod, 1); } - ret = cdns_pcie_host_setup(rc); - if (ret < 0) { - clk_disable_unprepare(pcie->refclk); - goto err_pcie_setup; + if (IS_ENABLED(CONFIG_PCI_J721E_HOST)) { + ret = cdns_pcie_host_setup(rc); + if (ret < 0) { + clk_disable_unprepare(pcie->refclk); + goto err_pcie_setup; + } } break; @@ -642,9 +644,11 @@ static int j721e_pcie_probe(struct platform_device *pdev) goto err_get_sync; } - ret = cdns_pcie_ep_setup(ep); - if (ret < 0) - goto err_pcie_setup; + if (IS_ENABLED(CONFIG_PCI_J721E_EP)) { + ret = cdns_pcie_ep_setup(ep); + if (ret < 0) + goto err_pcie_setup; + } break; } @@ -669,10 +673,11 @@ static void j721e_pcie_remove(struct platform_device *pdev) struct cdns_pcie_ep *ep; struct cdns_pcie_rc *rc; - if (pcie->mode == PCI_MODE_RC) { + if (IS_ENABLED(CONFIG_PCI_J721E_HOST) && + pcie->mode == PCI_MODE_RC) { rc = container_of(cdns_pcie, struct cdns_pcie_rc, pcie); cdns_pcie_host_disable(rc); - } else { + } else if (IS_ENABLED(CONFIG_PCI_J721E_EP)) { ep = container_of(cdns_pcie, struct cdns_pcie_ep, pcie); cdns_pcie_ep_disable(ep); } @@ -739,10 +744,12 @@ static int j721e_pcie_resume_noirq(struct device *dev) gpiod_set_value_cansleep(pcie->reset_gpio, 1); } - ret = cdns_pcie_host_link_setup(rc); - if (ret < 0) { - clk_disable_unprepare(pcie->refclk); - return ret; + if (IS_ENABLED(CONFIG_PCI_J721E_HOST)) { + ret = cdns_pcie_host_link_setup(rc); + if (ret < 0) { + clk_disable_unprepare(pcie->refclk); + return ret; + } } /* @@ -752,10 +759,12 @@ static int j721e_pcie_resume_noirq(struct device *dev) for (enum cdns_pcie_rp_bar bar = RP_BAR0; bar <= RP_NO_BAR; bar++) rc->avail_ib_bar[bar] = true; - ret = cdns_pcie_host_init(rc); - if (ret) { - clk_disable_unprepare(pcie->refclk); - return ret; + if (IS_ENABLED(CONFIG_PCI_J721E_HOST)) { + ret = cdns_pcie_host_init(rc); + if (ret) { + clk_disable_unprepare(pcie->refclk); + return ret; + } } } -- 2.51.1

21 hours, 38 minutes

4
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror